M. RAIHANACADEMIC PORTFOLIO
.01

ABOUT

PERSONAL DETAILS
13, Yousuf Row Mirzapur Road, (Boro Mirzapur 4th floor) Khulna-9100, Bangladesh
mapiconimg
mail@mraihan.me
+8801714070902
Teacher, Researcher, Data Analyst

BIOGRAPHY

ABOUT ME

M. Raihan has completed his graduation from Khulna University and post-graduation from Khulna University of Engineering & Technology (KUET). He has more than 60 publications till now and out of that 50 publications are already published and available in different online portals. He has worked as a guest reviewer in several international conferences and journals like Heliyon (Q1), IEEE Acess (Q1), Information Science (Q1), Gene Reports, Informatics in Medicine Unlocked etc. His total teaching experience till now is more than 6 Years. He has now serving as Assistant Professor at North Western University, Khulna, Bangladesh. His total citations till now are 527, h-index 11 and i10-index 19.

Current Research Areas:

  • Health Informatics
  • Data Science
  • Machine Learning
  • Biomedical Engineering
  • Cognitive Science
  • Predictive Modeling
  • Mobile Computing

HOBBIES

INTERESTS

  • Painting and Sketching
  • Writings
  • Reading Books
  • Watching Movie

Activities

Participation in Several Competition

  • 2006: Participation in First Bangladesh Astro-Olympiad.
  • 2006: Participation in Divisional Mathematical Olympiad.
  • 2008: Participation in Third Bangladesh Astro-Olympiad.
  • 2011: Participation in GPIT Festival in KUET.
  • 2013: Participation in EATLAPPS Contest.
  • 2014: Participation in 3rd EESTEC Competition for Android and placed 20th in final round.
  • 2014: Participation in imagine cup 2014 primarily round.
  • 2014: Participation in IUT 6th National ICT Fest.
  • 2015: Participation in 4th EESTEC Competition for Android.

Workshop and Seminars

Participation in Several Seminars

  • Social Business : Building Prosperity By SAYS.
  • Introduction To Online Work For Freelancers by Elance.
  • Participation in BDS 12th National Debate Workshop.
  • Professional Resume & CV writting by Rightsight Consultancy & Training Center.
  • Participation in Digital Innovation Fair in 2015.
  • EESTEC Online Seminar, Part 1 to 3: Android Basics.
.02

RESUME

EDUCATION
  • 2019
    Khulna, Bangladesh

    Master of Science (M.Sc. Eng.) in Biomedical Engineering

    Khulna University of Engineering and Technology (KUET)

    Thesis Title: Prediction on Ischemic Heart Disease using Machine Learning Approaches
    Abstract:

    Ischemic heart disease (IHD) is a terrible experience that occurs when the flow of blood severely reduced or cut off due to plaque deposited on the inner wall of arteries that brings oxygen to the heart muscle, leads to the ischemic heart attack (IHA). Atherosclerosis i.e. plaque deposition on the inner wall of arteries is a silent process, has no critical symptoms to get a warning before IHD. For this reason, early detection is very important for the proper management of patients prone to IHD. In this thesis work, it was tried to predict IHD on the basis of patient history, symptoms and pathological findings of patients with heart disease using computational intelligence. Total 506 patient’s data with a maximum of 151 features including historic, symptomatic and pathologic findings were collected from AFC Fortis Escort Heart Institute, Khulna, Bangladesh. First, it was tried to identify the significant risk factors of IHD i.e. the features which are significantly correlated with IHD by applying different feature selection techniques. Then IHD was predicted using significant risk factors by applying different classifier algorithms. The significant risk factors of IHD were determined by using Chi-Square correlation, Ranking the features based on information gain and Best First Search techniques. Among 151 collected features only 28 features showed high correlations with IHD based on 0.05 significance level and information gain 1% or above. 10-fold cross-validation technique was applied with different classification algorithms e.g. Artificial Neural Network (ANN), Bagging, Logistic Regression, and Random Forest to predict IHD using the most significant 28 risk factors. IHD prediction accuracy was observed ranges from 95.85% to 97.63% with different classifier algorithm. Random Forest showed the best prediction performance with an accuracy of 97.63%. The same processing technique and classification algorithms were applied to the Cleveland hospital dataset to validate our prediction approach. The observed IHD prediction accuracy was 80.46-83.77% without applying the proposed processing techniques, but the accuracy degraded to 79.80-81.46% applying the proposed processing techniques. The Cleveland hospital data contains 303 patients’ data with only 13 features whereas the collected dataset contains 506 patient’s data with 28 nicely correlated IHD risk factors. This is why the proposed method is not suitably applicable to Cleveland dataset.

    Download Link : https://dspace.kuet.ac.bd/handle/20.500.12228/827
  • 2016
    Khulna, Bangladesh

    Bachelor of Science (B.Sc. Eng.) in Computer Science and Engineering

    Khulna University

    Thesis Title: Heart Diseases Prediction Using Clinical Data And Data Mining Approaches
    Abstract:

    Heart disease is now very frequent in Bangladesh. The healthcare industry collects huge amounts of data, however that is not mined. Medical diagnosis is very important but very expensive. In our country most of our people cannot afford this expensive diagnosis cost. Thus we want to develop a smart phone based system that can initially predict heart disease risk. The clinical data from 787 patients was correlated and analyzed with the risk factors like Hypertension, Diabetes, Dyslipidemia, Smoking, Family History, Exercise, Stress and existing clinical symptom which may suggest underlying non detected IHD. The data was mined with data mining technology in computer science and a score was generated. The risk was classified into Low, Medium and High for IHD. On comparing and categorizing the patients whose data was obtained for generating the score; we found there was significant correlation of having a cardiac event when Low and High category was compared and p value = 0.0004. Our thesis is motivated to make simple approach to detect the heart disease risk and aware the population to get themselves evaluated by a cardiologist to avoid sudden deaths and morbidities. Currently available tools has mandatory input of lipid values which makes them underutilized by population though those risk calculators bear excellent academic importance. Our thesis product may reduce this limitation and promote a risk evaluation on time.

  • 2009
    Khulna, Bangladesh

    Higher Secondary Certifcate (HSC)

    Govt. M. M. City College

    • Board: Jessore
    • Group: Science
    • Position: 282 in Jessore Board
    • GPA: 5.00
    • Passing Year: 2009
  • 2007
    Khulna, Bangladesh

    Secondary School Certifcate (SSC)

    Khulna Zilla School

    • Board: Jessore
    • Group: Science
    • GPA: 5.00
    • Passing Year: 2007
ACADEMIC AND PROFESSIONAL POSITIONS
  • 2018
    2021
    Netherlands

    Reviewer

    Information Sciences - An International Journal, Publisher: Elsevier

    Works as Reviewer in Information Sciences - An International Journal, Publisher: Elsevier, (Duration: December (2018)-Present.)
  • 2019
    Sikkim, India

    Reviewer

    IEEE Conference

    Worked as Reviewer in “International Conference on Advanced Computational and Communication Paradigms -2019” (ICACCP-2019) on 25 to 28 February, 2019 in Sikkim, India. (IEEE Conference Record No : 45516).
  • 2019
    Bangalore, India

    Reviewer

    IEEE Conference

    Worked as Reviewer in “2019 International Conference on Advanced Technologies in Intelligent Control, Environment, Computing & Communication Engineering”(ICATIECE) on 19th and 20th March, 2019 in Bangalore, India. (IEEE Conference Record No : 45860).
  • 2019
    Coimbatore, India

    Reviewer

    IEEE Conference

    Worked as Reviewer in “2019 IEEE International Conference on Electrical, Computer and Communication Technologies”(IEEE ICECCT 2019) on 20 - 22, February, 2019 in Coimbatore, India. (IEEE Conference Record No : 45014).
  • 2017
    2021
    United States

    Reviewer

    Advances in Science, Technology & Engineering Systems

    Works as Reviewer in Advances in Science, Technology & Engineering Systems Journal (ASTESJ) (ISSN: 2415-6698), Reviewer Code: RVCAI0429 (Duration: November (2017)-Present.)
  • 2017
    Khulna, Bangladesh

    Organizer

    IEEE Bangladesh Section

    Worked in organizing committee to organize Workshop on University-Industry Collaboration: Challenges and Opportunities arranged by Industry Activity Coordinator, IEEE Bangladesh Section.
  • 2018

    Editorial Member

    Journal of Computer

    Works as Editorial Member in SCIREA Journal of Computer.(Duration: August (2018)-Present.)
  • 2015
    Bangladesh

    Management

    ICT Ministry (MoICT)

    Worked in management committee to organize National 500 Apps Trainer and Innovative Apps Development Program inauguration ceremony in Khulna University arranged by ICT Ministry (MoICT), Bangladesh.
AWARDS AND SCHOLARSHIPS
  • 2015
    Khulna, Bangladesh

    2nd Prize in Project Showcasing

    CLUSTER

    Got 2nd Prize for project show in CSE Festival arranged by CLUSTER , Khulna University
  • 2014
    Khulna, Bangladesh

    District 1st in National Mobile Application Awareness & Capacity Building Program

    Khulna University

    Got android mobile Phone as prize.
  • 2007
    Khulna, Bangladesh

    Bangladesh Children Festival award

  • 2006
    Khulna, Bangladesh

    Bissho-shahitto Kendro award

  • 2008
    Khulna, Bangladesh

    Islami Bank Educational Scholarship in S.S.C level

    Islami Bank

  • 2009
    Khulna, Bangladesh

    Board Scholarship in H.S.C level

    Jessore Board

.03

PUBLICATIONS

PUBLICATIONS LIST
27 Oct 2019

Prediction on Ischemic Heart Disease using Machine Learning Approaches

Khulna, Bangladesh

Khulna University of Engineering & Technology (KUET), Khulna, Bangladesh

Thesis Selected M. Raihan

Prediction on Ischemic Heart Disease using Machine Learning Approaches

M. Raihan
Thesis Selected
About The Publication
Ischemic heart disease (IHD) is a terrible experience that occurs when the flow of blood severely reduced or cut off due to plaque deposited on the inner wall of arteries that brings oxygen to the heart muscle, leads to the ischemic heart attack (IHA). Atherosclerosis i.e. plaque deposition on the inner wall of arteries is a silent process, has no critical symptoms to get a warning before IHD. For this reason, early detection is very important for the proper management of patients prone to IHD. In this thesis work, it was tried to predict IHD on the basis of patient history, symptoms and pathological findings of patients with heart disease using computational intelligence. Total 506 patient’s data with a maximum of 151 features including historic, symptomatic and pathologic findings were collected from AFC Fortis Escort Heart Institute, Khulna, Bangladesh. First, it was tried to identify the significant risk factors of IHD i.e. the features which are significantly correlated with IHD by applying different feature selection techniques. Then IHD was predicted using significant risk factors by applying different classifier algorithms. The significant risk factors of IHD were determined by using Chi-Square correlation, Ranking the features based on information gain and Best First Search techniques. Among 151 collected features only 28 features showed high correlations with IHD based on 0.05 significance level and information gain 1% or above. 10-fold cross-validation technique was applied with different classification algorithms e.g. Artificial Neural Network (ANN), Bagging, Logistic Regression, and Random Forest to predict IHD using the most significant 28 risk factors. IHD prediction accuracy was observed ranges from 95.85% to 97.63% with different classifier algorithm. Random Forest showed the best prediction performance with an accuracy of 97.63%. The same processing technique and classification algorithms were applied to the Cleveland hospital dataset to validate our prediction approach. The observed IHD prediction accuracy was 80.46-83.77% without applying the proposed processing techniques, but the accuracy degraded to 79.80-81.46% applying the proposed processing techniques. The Cleveland hospital data contains 303 patients’ data with only 13 features whereas the collected dataset contains 506 patient’s data with 28 nicely correlated IHD risk factors. This is why the proposed method is not suitably applicable to Cleveland dataset.
10 Sep 2016

Smartphone Based “Heart Attack’’ Risk Prediction; Initiation of A Clinically Simple Approach

Wolters Kluwer Health

Journal of Hypertension

Journal Paper Selected Arun More, M Raihan, Md Omar Faruqe Sagor, Gopal Sikder, Saikat Mondal, Md Abdullah Al Manjur

Smartphone Based “Heart Attack’’ Risk Prediction; Initiation of A Clinically Simple Approach

Arun More, M Raihan, Md Omar Faruqe Sagor, Gopal Sikder, Saikat Mondal, Md Abdullah Al Manjur
Journal Paper Selected
About The Publication
Paper Title: Smartphone Based “Heart Attack’’ Risk Prediction; Initiation of A Clinically Simple Approach Abstract: Objective: To develop a simple approach to predict risk of developing Ischemic Heart Disease (IHD) (“Heart Attack”) by using most widely used technology of smartphone. Collection of demographic data of risk factors for IHD. To initiate a activity for social awareness for “Check yourself before event”. Design and Method: A prototype software (Android based) was developed by integrating clinical data obtained from patients admitted with IHD. Obtained data was processed by “data mining” technology of computer sciences. Results: The clinical data from 787 patients was correlated and analyzed with the risk factors like, Hypertension, Diabetes, Dyslipidemia, Smoking, Family History, Obesity, Stress and existing clinical symptom which may suggest underlying non detected IHD. The data was mined with Data Mining technology in computer sciences and a score was generated. The risk was classified into Low, Medium and High for IHD. On comparing and categorizing the patients whose data was obtained for generating the score; we found there was significant correlation of having a cardiac event when Low and High category was compared; p = 0.004. Among patients categorized into High; 85% had IHD while among low category, only 25 % had IHD. However there was no significant difference between medium and high risk categories. Conclusions: Our research is motivated to make simple approach to detect the IHD risk and aware the population to get themselves evaluated by a cardiologist to avoid sudden deaths and morbidities. Currently available tools has mandatory input of lipid values which makes them underutilized by population though those risk calculators bear excellent academic importance. Our research product may reduce this limitation and promote a risk evaluation on time. Our research is in experimental phase to check sensitivity and specificity and how the population takes it to walk upto a cardiologist to check their risks to have IHD.
18 Dec 2016

Smartphone based ischemic heart disease (heart attack) risk prediction using clinical data and data mining approaches, a prototype design

Dhaka, Bangladesh

2016 19th International Conference on Computer and Information Technology (ICCIT)

Conferences Selected M Raihan, Saikat Mondal, Arun More, Md Omar Faruqe Sagor, Gopal Sikder, Mahbub Arab Majumder, Mohammad Abdullah Al Manjur, Kushal Ghosh

Smartphone based ischemic heart disease (heart attack) risk prediction using clinical data and data mining approaches, a prototype design

M Raihan, Saikat Mondal, Arun More, Md Omar Faruqe Sagor, Gopal Sikder, Mahbub Arab Majumder, Mohammad Abdullah Al Manjur, Kushal Ghosh
Conferences Selected
About The Publication
Paper Title: Smartphone based ischemic heart disease (heart attack) risk prediction using clinical data and data mining approaches, a prototype design Abstract: We developed a simple approach to predict risk of developing Ischemic Heart Disease (IHD) (Heart Attack) using smartphone. An Android based prototype software has been developed by integrating clinical data obtained from patients admitted with IHD. The clinical data from 787 patients has been analyzed and correlated with the risk factors like Hypertension, Diabetes, Dyslipidemia (Abnormal cholesterol), Smoking, Family History, Obesity, Stress and existing clinical symptom which may suggest underlying non detected IHD. The data was mined with data mining technology and a score is generated. Risks are classified into low, medium and high for IHD. On comparing and categorizing the patients whose data is obtained for generating the score; we found there is a significant correlation of having a cardiac event when low & high and medium & high category are compared; p=0.0001 and 0.0001 respectively. Our research is to make simple approach to detect the IHD risk and aware the population to get themselves evaluated by a cardiologist to avoid sudden deaths. Currently available tools has some limitations which makes them underutilized by population. Our research product may reduce this limitation and promote risk evaluation on time.
03 Nov 2017

Smartphone Based Heart Attack Risk Prediction System with Statistical Analysis and Data Mining Approaches

United States

Advances in Science, Technology and Engineering Systems Journal

Journal Paper Selected M. Raihan, Saikat Mondal, Arun More, Pritam Khan Boni, Md Omar Faruqe Sagor

Smartphone Based Heart Attack Risk Prediction System with Statistical Analysis and Data Mining Approaches

M. Raihan, Saikat Mondal, Arun More, Pritam Khan Boni, Md Omar Faruqe Sagor
Journal Paper Selected
About The Publication
Paper Title: Smartphone Based Heart Attack Risk Prediction System with Statistical Analysis and Data Mining Approaches Abstract: Nowadays, Ischemic Heart Disease (IHD)(Heart Attack) is ubiquitous and one of the major reasons of death worldwide. Early screening of people at risk of having IHD may lead to minimize morbidity and mortality. A simple approach is proposed in this paper to predict risk of developing heart attack using smartphone and data mining. Clinical data from 835 patients was collected, analyzed and also correlated with their risk existing clinical symptoms which may suggest underlying non detected IHD. A user friendly Android application was developed by incorporating clinical data obtained from patients who admitted with chest pain in a cardiac hospital. Upon user input of risk factors, the application categorizes the level of IHD risks of the user as high, low or medium. It was found by analyzing and correlating the data that there was a significant correlation of having an IHD and the application results in high & low, medium & low and medium & high categories; where the p values were 0.0001, 0.0001 and 0.0001 respectively. The experimental results showed that the sensitivity and accuracy of the proposed technique were 89.25% and 76.05% respectively, whereas, using C4. 5 decision tree, accuracy was found 86% and sensitivity was obtained 91.6%. Existing tools need mandatory input of lipid values which makes them underutilized by general people; though these risk calculators bear significant academic importance. Our research is motivated to reduce that limitation and promote a risk evaluation on time.
22 Dec 2017

A simple acute myocardial infarction (Heart Attack) prediction system using clinical data and data mining techniques

Dhaka, Bangladesh

20th International Conference of Computer and Information Technology (ICCIT)

Conferences Procheta Nag, Saikat Mondal, Foysal Ahmed, Arun More, M. Raihan

A simple acute myocardial infarction (Heart Attack) prediction system using clinical data and data mining techniques

Procheta Nag, Saikat Mondal, Foysal Ahmed, Arun More, M. Raihan
Conferences
About The Publication
Paper Title: A simple acute myocardial infarction (Heart Attack) prediction system using clinical data and data mining techniques Abstract: Acute Myocardial Infarction (Heart Attack), a Cardiovascular Disease (CVD) leads to Ischemic Heart Disease(IHD) is one of the major killers worldwide. A proficient approach is proposed in this paper that can predict the chances of heart attack when a person is bearing chest pain or equivalent symptoms. We have developed a prototype by integrating clinical data collected from patients admitted in different hospitals attacked by Acute Myocardial Infarction (AMI). 25 attributes related to symptoms of heart attack are collected and analyzed where chest pain, palpitation, breathlessness, syncope with nausea, sweating, vomiting are the prominent symptoms of a person getting heart attack. The data mining techniques namely decision tree and random forest are used to analyze heart attack dataset where classification of more common symptoms related to heart attack is done using c4.5 decision tree algorithm, alongside, random forest is applied to improve the accuracy of the classification result of heart attack prediction. A guiding system to suspect the chest pain as having heart attack or not may help many people who tend to neglect the chest pain and later land up in catastrophe of heart attacks.
09 Feb 2018

Simplistic Approach to Design a Prototype of an Automated Wheelchair Based on Electrooculography

Rajshahi, Bangladesh

2018 4th International Conference on Computer, Communication, Chemical, Material and Electronic Engineering (IC4ME2)

Conferences Mubtasim Rafid Chowdhury, S. Poonguzhali, Aravind Balan K R, Suresh R, Md. Nurunnabi Mollah, M. Raihan, Abu Shakil Ahmed

Simplistic Approach to Design a Prototype of an Automated Wheelchair Based on Electrooculography

Mubtasim Rafid Chowdhury, S. Poonguzhali, Aravind Balan K R, Suresh R, Md. Nurunnabi Mollah, M. Raihan, Abu Shakil Ahmed
Conferences
About The Publication
Paper Title: Simplistic Approach to Design a Prototype of an Automated Wheelchair Based on Electrooculography Abstract: Many people suffer from the disability to control different limbs of their bodies inherently or due to an accident. Immobility impedes their daily activities and detaches themselves from various social events to a certain extent. Although motorized mechanical systems such as wheelchair enhance the movability, it is not beneficial for the patients suffering from quadriplegia whose entire body is paralyzed. We have proposed a prototype of an automated wheelchair which can be controlled by directional movement of the eye using electrooculography (EOG) signal. The performance appraisal of the proposed prototype after proper assembly justifies its effectiveness.
10 Oct 2018

Smart phone based “heart attack” risk prediction; innovation of clinical and social approach for preventive cardiac health

Wolters Kluwer Health

Journal of Hypertension

Journal Paper Selected Kaanchan More, M. Raihan, Arun More, Sharad Padule, Saikat Mondal

Smart phone based “heart attack” risk prediction; innovation of clinical and social approach for preventive cardiac health

Kaanchan More, M. Raihan, Arun More, Sharad Padule, Saikat Mondal
Journal Paper Selected
About The Publication
Paper Title: Smart phone based “heart attack” risk prediction; innovation of clinical and social approach for preventive cardiac health Abstract: Objectives: To develop a risk factor based approach to predict risk of developing Heart Attack by using smart phone technology. To initiate a social activity “Check yourself before event”. Methods: A prototype software (Android) was developed by integrating clinical data obtained from 506 patients admitted in a cardiac hospital irrespective of final diagnosis. Data was correlated & analysed with presence of ischemic heart disease (IHD). Risk factors like,Hypertension,Diabetes,Dyslipidemia,Smoking,Family History,Obesity,Stress & existing clinical symptoms suggesting sub-clinical or non detected IHD were considered. The data was mined with Data Mining technology and a score was generated. The risk was classified into Low, Medium and High for IHD as per the score. App was tested prospectively with 89 participants with acute coronary syndrome (ACS) Results: On comparing patients whose data was obtained for generating the score;we found there is a significant correlation of having a cardiac event when low and high category was compared;p = 0.0001. Among patients categorized into high;83.9 % had IHD while in low category,only 12.5%. The difference between medium and high was also significant with p = 0.0001. In a prospective observation among those who presented to hospital with ACS, 86.69 % patients had high scores. Conclusion: Our research is motivated to make simple & social approach to predict the IHD risk and aware individuals to get evaluated. Currently available tools are underutilized by population;Our mobile application may reduce this limitation and promote a risk evaluation on time. Based on data collection,we aim to develop”Help Centers” for high risk individuals to aware them on cardiac health and guide them for evaluation.
19 Jul 2018

Role and Impact of Biomedical Engineering Discipline for Developing Country Perspective

International Journal of Innovative Research in Computer Science & Technology

Journal Paper Md Rashid Al Asif, Saumendu Roy, Asif Abdullah, M Raihan, Rozina Akter, Md Zakir Hossain

Role and Impact of Biomedical Engineering Discipline for Developing Country Perspective

Md Rashid Al Asif, Saumendu Roy, Asif Abdullah, M Raihan, Rozina Akter, Md Zakir Hossain
Journal Paper
About The Publication
Paper Title: Role and Impact of Biomedical Engineering Discipline for Developing Country Perspective Abstract: For a developing and largely populated country, it is quite difficult to solve all healthcare related issues using existing technology with affordable cost and desired precision. Moreover, to carry out biomedical research and design to improve biomedical equipment, devices and maintenance are usually very expensive. Thus, it is imperative and possible to extent indigenous technologies and raw materials for the research activities to design and develop sustained biomedical devices and equipment, artificial organ and tissue, prosthetics and implants, image modalities and healthcare related software at low-cost. Thus, the research and study related to biomedical engineering need to improve to understand the role and impact of this subject as a discipline.
10 Jul 2018

Effective Business Strategy Decision Making Method Using Fuzzy Logic

Bengaluru, India

2018 9th International Conference on Computing, Communication and Networking Technologies (ICCCNT)

Conferences Himadri Shekhar Mondal, M. Raihan, Sunanda Roy, Sabyasachi Mondal

Effective Business Strategy Decision Making Method Using Fuzzy Logic

Himadri Shekhar Mondal, M. Raihan, Sunanda Roy, Sabyasachi Mondal
Conferences
About The Publication
Paper Title: Effective Business Strategy Decision Making Method Using Fuzzy Logic Abstract: Present world is based on technical evaluation. Modern science and technology spread its wings in every sector of this world and trying to make our world more and more beautiful. On the other hand business is the much needed phenomena through which a nation can reach the top of the development. Technology is helping to spread modern business strategy in many ways, as a result many dynamic businesses are growing faster. In this research a fuzzy based model is proposed, which is helpful for decision making criteria. Through this model the surprise level of a customer is measured which will be helpful for business strategy maker.
21 Dec 2018

A Comprehensive Analysis on Risk Prediction of Acute Coronary Syndrome Using Machine Learning Approaches

Dhaka, Bangladesh

2018 21st International Conference of Computer and Information Technology (ICCIT)

Conferences Selected M. Raihan, Muinul Muhammad Islam, Promila Ghosh, Shakil Ahmed Shaj, Mubtasim Rafid Chowdhury, Saikat Mondal, Arun More

A Comprehensive Analysis on Risk Prediction of Acute Coronary Syndrome Using Machine Learning Approaches

M. Raihan, Muinul Muhammad Islam, Promila Ghosh, Shakil Ahmed Shaj, Mubtasim Rafid Chowdhury, Saikat Mondal, Arun More
Conferences Selected
About The Publication
Paper Title: A Comprehensive Analysis on Risk Prediction of Acute Coronary Syndrome Using Machine Learning Approaches Abstract: Acute Coronary Syndrome (ACS) is liable for the sudden death. The originator of tachycardia is drug addiction, hyperpiesia polygenic disorder, lipidemia. From the healthcare unit, ACS patients dataset has been collected. By preprocessing the information the chances of the exigency of tachycardia by possessing machine learning (ML) approaches are analyzed. The proficiency of ML techniques for prediction is authentic than any other traditional systems. The central scheme of this analysis is to anticipate the significant contingency of tachycardia. Neural Network, SVM, AdaBoost, Bagging, K-NN, Random Forest approaches are used as long as anticipating the betrayal of ACS. The high-grade exactness with AdaBoost and Bagging are 75.49% and 76.28%. The precision and recall for AdaBoost are 0.741; 0.75 and 0.755; 0.763 for Bagging techniques respectively.
21 Dec 2018

Designing a Cost Effective Prototype of an Automated Wheelchair Based on EOG (Electrooculography)

Dhaka, Bangladesh

2018 21st International Conference of Computer and Information Technology (ICCIT)

Conferences Selected Mubtasim Rafid Chowdhury, Md. Nurunnabi Mollah, M. Raihan, Abu Shakil Ahmed, Md. Abdul Halim, Md. Shahin Hossain

Designing a Cost Effective Prototype of an Automated Wheelchair Based on EOG (Electrooculography)

Mubtasim Rafid Chowdhury, Md. Nurunnabi Mollah, M. Raihan, Abu Shakil Ahmed, Md. Abdul Halim, Md. Shahin Hossain
Conferences Selected
About The Publication
Paper Title: Designing a Cost Effective Prototype of an Automated Wheelchair Based on EOG (Electrooculography) Abstract: The disability to control different limbs of human body is a major obstacle in which many people suffer from. This might be inherent or occur due to an accident. Their day-to-day activities are impeded by immobility and they are segregated from various social events to an extent. For the patients suffering from quadriplegia whose entire body is paralyzed, motorized mechanical systems such as wheelchair are not sufficient enough. A simplistic approach of an automated wheelchair has been proposed here which can be operated by directional eye movement using electrooculography (EOG) signal. After proper assembly the performance appraisal justifies the proposed prototypes effectiveness.
07 Feb 2019

Risk Prediction of Ischemic Heart Disease Using Artificial Neural Network

Cox'sBazar, Bangladesh

2019 International Conference on Electrical, Computer and Communication Engineering (ECCE)

Conferences Selected M Raihan, Parichay Kumar Mandal, Muhammad Muinul Islam, Tanvir Hossain, Promila Ghosh, Shakil Ahmed Shaj, Abdullah Anik, Mubtasim Rafid Chowdhury, Saikat Mondal, Arun More

Risk Prediction of Ischemic Heart Disease Using Artificial Neural Network

M Raihan, Parichay Kumar Mandal, Muhammad Muinul Islam, Tanvir Hossain, Promila Ghosh, Shakil Ahmed Shaj, Abdullah Anik, Mubtasim Rafid Chowdhury, Saikat Mondal, Arun More
Conferences Selected
About The Publication
Paper Title: Risk Prediction of Ischemic Heart Disease Using Artificial Neural Network Abstract: The fatty plaque deposits narrow artery walls leading to the heart Ischemic Heart Disease (IHD). For that, the flowing of blood is reduced. Hyperpiesia polygenic disorder, drug addiction, and lipidemia are the initiators of tachycardia. From the healthcare unit, 835 IHD patients data with 14 features like Age, Sex, Diabetes Mellitus (DM), Electrocardiograph (ECG), Exercise Tolerance Test (ETT) etc. have been collected. By implementing artificial neural network (ANN) techniques in our collected dataset the risk prediction is determined around 84.47%. The precision, sensitivity, specificity, and fl-score, for the ANN, are 79.97, 82.69, 72.63, and 85.17 respectively. The significant contingency of tachycardia is anticipated.
06 Jul 2019

Performance Analysis of Isolated Speech Recognition Technique Using MFCC and Cross-Correlation

Kanpur, India

2019 10th International Conference on Computing, Communication and Networking Technologies (ICCCNT)

Conferences Md Ekhlasur Rahaman, SM Shamsul Alam, Himadri Shekhar Mondal, Ahmed Saif Muntaseer, Rajib Mandal, M Raihan

Performance Analysis of Isolated Speech Recognition Technique Using MFCC and Cross-Correlation

Md Ekhlasur Rahaman, SM Shamsul Alam, Himadri Shekhar Mondal, Ahmed Saif Muntaseer, Rajib Mandal, M Raihan
Conferences
About The Publication
Paper Title: Performance Analysis of Isolated Speech Recognition Technique Using MFCC and Cross-Correlation Abstract: Speech signal processing has become an important mode of interaction with computer. In this paper, Mel Frequency Cepstral Coefficient (MFCC) technique has been used to process speech samples to attain the recognition. MFCC is a term which narrate the short-term power spectrum of a speech signal, depend on a linear cosine transform (FFT and DCT we have used in our work) of a log power spectrum on a nonlinear Mel scale of frequency. We have used Dynamic Time Warping algorithm and Cross Correlation algorithm to match feature vectors. We have taken five recorded reference word through “One” to “Five”. Then the feature vectors generated from this reference signals are stored in database. A test sample of any numeric in “One” to “Five” is again recorded and then the algorithm is applied to recognize the same with recorded reference voices. In our paper, the recognition techniques show different percentages of accuracy. The highest recognition accuracy we got 92% for Dynamic Time Warping algorithm with FFT transformation. The accuracy for Dynamic Time Warping algorithm using DCT is 86% which is less than DP algorithm using FFT. The average accuracy for Cross Correlation using FFT is 78% and average accuracy for DCT is only 60%.
06 Jul 2019

An Empirical Study on Diabetes Mellitus Prediction for Typical and Non-Typical Cases using Machine Learning Approaches

Kanpur, India

2019 10th International Conference on Computing, Communication and Networking Technologies (ICCCNT)

Conferences Md Tanvir Islam, M Raihan, Fahmida Farzana, Md Golam Morshed Raju, Md Bellal Hossain

An Empirical Study on Diabetes Mellitus Prediction for Typical and Non-Typical Cases using Machine Learning Approaches

Md Tanvir Islam, M Raihan, Fahmida Farzana, Md Golam Morshed Raju, Md Bellal Hossain
Conferences
About The Publication
Paper Title: An Empirical Study on Diabetes Mellitus Prediction for Typical and Non-Typical Cases using Machine Learning Approaches Abstract: Diabetes is a non-communicable disease and increasing at an alarming rate all over the world. Having a high sugar level in blood or lack of insulin are the primary reasons. So, it is important to find an effective way to predict diabetes before it turns into a major problem for human health. It is possible to take control of diabetes on an early stage if we take precautions. For this study, we have collected 340 instances with 26 features of patients who have already diabetes with various symptoms categorized by two types Typical and Non-Typical. For training the dataset, cross-validation technique has been used and for classification, three Machine Learning (ML) algorithms such as Bagging, Logistic Regression and Random Forest have been used. The accuracy for Bagging 89.12%, for Logistic Regression 83.24% and for Random Forest 90.29% which are very appreciative.
06 Jul 2019

An Empirical Study to Predict Diabetes Mellitus using K-Means and Hierarchical Clustering Techniques

Kanpur, India

2019 10th International Conference on Computing, Communication and Networking Technologies (ICCCNT)

Conferences Selected M Raihan, Md Tanvir Islam, Fahmida Farzana, Md Golam Morshed Raju, Himadri Shekhar Mondal

An Empirical Study to Predict Diabetes Mellitus using K-Means and Hierarchical Clustering Techniques

M Raihan, Md Tanvir Islam, Fahmida Farzana, Md Golam Morshed Raju, Himadri Shekhar Mondal
Conferences Selected
About The Publication
Paper Title: An Empirical Study to Predict Diabetes Mellitus using K-Means and Hierarchical Clustering Techniques Abstract: Diabetes is a serious disease which is increasing at an alarming rate all over the world and it may cause some longterm issues such as affecting the eyes, heart, kidneys, brain, feet and nerves. The best way to prevent diabetes is to control blood glucose and take care of yourself. So, to delay these problems we have to identify the disease and possibly in the early stage of the disease in our body to control over it. From this thinking, in this paper we have analyzed on a diabetes dataset to predict diabetes using two popular Machine Learning algorithms K-means and Hierarchical Clustering as we know that Machine Learning is a crucial division of algorithm which is playing a very important role to predict human diseases in this decade.
06 Jul 2019

Parametric Performance Estimation of Wireless Sensor Network Using Fuzzy Logic

Kanpur, India

2019 10th International Conference on Computing, Communication and Networking Technologies (ICCCNT)

Conferences Himadri Shekhar Mondal, Prianka Bhattacharjee, Md Mahmud Hassan, Md Bellal Hossain, Ahmed Saif Muntaseer, M Raihan

Parametric Performance Estimation of Wireless Sensor Network Using Fuzzy Logic

Himadri Shekhar Mondal, Prianka Bhattacharjee, Md Mahmud Hassan, Md Bellal Hossain, Ahmed Saif Muntaseer, M Raihan
Conferences
About The Publication
Paper Title: Parametric Performance Estimation of Wireless Sensor Network Using Fuzzy Logic Abstract: Fastest and improved data communication is a demand for present world. A wireless sensor network (WSN) can be helpful for establishing fastest data communication by supporting wireless connectivity with the help of its distributed nodes. In this research we presented a method to show the best possible way of selecting the nearest neighbor node for a network. We considered angle, energy and distance for observing the possible selecting way of selecting neighbor wireless network. Fuzzy logic is used in this research considering its performance and improved applicable areas. According to our research energy is the most effective parameter and responsible for selecting a neighbor node.
06 Jul 2019

Safeguard: A Prototype of An Application Programming Interface to Save the Disaster Affected People

Kanpur, India

2019 10th International Conference on Computing, Communication and Networking Technologies (ICCCNT)

Conferences Promila Ghosh, M Raihan, Md Tanvir Islam, Md Ekhlasur Rahaman

Safeguard: A Prototype of An Application Programming Interface to Save the Disaster Affected People

Promila Ghosh, M Raihan, Md Tanvir Islam, Md Ekhlasur Rahaman
Conferences
About The Publication
Paper Title: Safeguard: A Prototype of An Application Programming Interface to Save the Disaster Affected People Abstract: The automated chatbot system has introduced a new era of modern technology. Recently the chatbot system plays an important role as a virtual agent in different respects. A chatbot system cannot replace a human agent but it can provide initial support at any time instantly. This type of instant support can help a victim at the time of the natural disaster period efficiently. It can also play a role to reduce the amount of damage. In this research paper, we have proposed a chatbot application programming interface (API) system named Safeguard that can be integrated into different social media as well as in any application. This system will be able to support a victim and give guidelines on disaster period. For this purpose, natural language understanding was used by Dialogflow tool. Dialogflow has helped to create the application programming interface system by using intents, entities and text responses by the implementation of the natural language processing system, cloud storage and JSON.
06 Jul 2019

Identification of Cyanide within Hollow Core Photonics Crystal Fiber

Kanpur, India

2019 10th International Conference on Computing, Communication and Networking Technologies (ICCCNT)

Conferences Md Bellal Hossain, Etu Podder, Abdullah Al-Mamun Bulbul, Himadri Shekhar Mondal, M Raihan, Md Tanvir Islam

Identification of Cyanide within Hollow Core Photonics Crystal Fiber

Md Bellal Hossain, Etu Podder, Abdullah Al-Mamun Bulbul, Himadri Shekhar Mondal, M Raihan, Md Tanvir Islam
Conferences
About The Publication
Paper Title: Identification of Cyanide within Hollow Core Photonics Crystal Fiber Abstract: Nerve Cyanide is very dangerous especially for human body and for this reason, perfect extent identification of cyanide is very worthy. In this research, PCF based cyanide sensor is illustrated where, sodium cyanide (NaCN) and potassium cyanide (KCN) are taken as analyte. COMSOL Multiphysics is conducted for the simulation of recommended model. The recommended model exhibits 88.5% sensitivity while NaCN is chosen as analyte at frequency 1.3 THz. This model has very insignificant effective material loss (EML) and only 0.0050 cm -1 EML is noticed while KCN is chosen as analyte. Moreover, this recommended model has very negligible confinement loss (1.2×10 -13 dB/cm).
13 Dec 2019

Diabetes Mellitus Prediction Using Ensemble Machine Learning Techniques

Springer, Singapore

International Conference on Computational Intelligence, Security and Internet of Things

Book ChaptersBook Series Selected Md Tanvir Islam, M Raihan, Sheikh Raihan Islam Akash, Fahmida Farzana, Nasrin Aktar

Diabetes Mellitus Prediction Using Ensemble Machine Learning Techniques

Md Tanvir Islam, M Raihan, Sheikh Raihan Islam Akash, Fahmida Farzana, Nasrin Aktar
Book ChaptersBook Series Selected
About The Publication
Paper Title: Diabetes Mellitus Prediction Using Ensemble Machine Learning Techniques Abstract: Diabetes is a non-communicable disease and currently it is increasing at an alarming rate. It may cause different serious damage in particular; blur vision, myopia, burning extremities, kidney and heart failure. At this moment it is becoming one of the major diseases. Diabetes occurs when the level of sugar crosses a certain level or the human body can not produce sufficient insulin to balance the level. Therefore, diabetes affected patients need to be informed about it so that they can get proper treatments to control diabetes. For this reason, it is important to predict and classify diabetes at an early stage. So, in this analysis, two Machine Learning algorithms have been used to classify diabetes and compared the performances of the algorithms. The collected dataset has 340 instances and each instance has 26 features. In this study, two Ensemble Machine Learning algorithms have been used, namely Bagging and Decorate. Bagging classified the types of diabetes 95.59% accurately, whereas Decorate classified 98.53% accurately.
18 Dec 2019

A Wireless Electronic Stethoscope to Classify Children Heart Sound Abnormalities

Dhaka, Bangladesh

2019 22nd International Conference on Computer and Information Technology (ICCIT)

Conferences Md Riadul Islam, Md Mahadi Hassan, M. Raihan, Sabuz Kumar Datto, Abdullah Shahriar, Arun More

A Wireless Electronic Stethoscope to Classify Children Heart Sound Abnormalities

Md Riadul Islam, Md Mahadi Hassan, M. Raihan, Sabuz Kumar Datto, Abdullah Shahriar, Arun More
Conferences
About The Publication
Paper Title: A Wireless Electronic Stethoscope to Classify Children Heart Sound Abnormalities Abstract: In this research paper, a wireless stethoscope has introduced that can communicate with a smartphone to receive children’s heart sound. Along with an automated method that recognizes children heart sound abnormalities. That isolation of heart sound is based on time-frequency characteristics. Where it is preceded using Mel-frequency Cepstral Coefficients (MFCCs) signal processing method. The processed sounds are extracted using five feature extraction algorithms. Then it is classified using four support vector machines (SVM) kernel. Total 60 heart sounds were collected, where 30 sounds having abnormalities and rest 30 sounds containing normal heart sound. Though massive measures of action have already been done in this area, still necessity of more bearable cost device and accurate method is present. Here, the submitted apparatus cost is approximately 18 USD, which is the cheapest than most other device used in previous work. Simultaneously it is lightweight and bearable to use in rural and underprivileged area. With RBF kernel of SVM, the proposed method shows 94.12% accuracy which is the highest.
23 May 2020

Diabetes Mellitus Risk Prediction Using Artificial Neural Network

Springer, Singapore

Proceedings of International Joint Conference on Computational Intelligence

BookBook ChaptersBook Series Selected M. Raihan, Nasif Alvi, Md Tanvir Islam, Fahmida Farzana, Md Mahadi Hassan

Diabetes Mellitus Risk Prediction Using Artificial Neural Network

M. Raihan, Nasif Alvi, Md Tanvir Islam, Fahmida Farzana, Md Mahadi Hassan
BookBook ChaptersBook Series Selected
About The Publication
Paper Title: Diabetes Mellitus Risk Prediction Using Artificial Neural Network Abstract: Diabetes is a non-communicable disease and various types of dangerous diseases like heart attack, kidney failure, myopia, and so on are caused by it. The number of people suffering from diabetes is increasing rapidly. Though there has no perpetual cure for diabetes, it can be controlled by proper counseling and medication. For this perception, an early determination is needed. In our analysis, 464 patients data with 23 features were collected from various health-care units and preprocessed. A predictive model was developed with artificial neural network technique. Different learning rate, hidden layers were applied in our analysis. Average-weighted accuracy of all observations was approximately 99.69%.
10 Jan 2020

A Machine Learning Approach to Identify the Correlation and Association among the Students’ Educational Behavior

Association for Computing Machinery New York NY United States

Proceedings of the International Conference on Computing Advancements

Conferences Selected M. Raihan, Md Tanvir Islam, Promila Ghosh, Jarif Huda Angon, Md Mehedi Hassan, Fahmida Farzana

A Machine Learning Approach to Identify the Correlation and Association among the Students’ Educational Behavior

M. Raihan, Md Tanvir Islam, Promila Ghosh, Jarif Huda Angon, Md Mehedi Hassan, Fahmida Farzana
Conferences Selected
About The Publication
Paper Title: A Machine Learning Approach to Identify the Correlation and Association among the Students’ Educational Behavior Abstract: Education is known as the backbone of a nation. So, a nation must be concern about its people and their education system. In the modern era, most of the early age students are not abling to concentrate on their study due to various factors surrounding them. In this study, we have tried to find out the most significant factors harmful for a student. We have also tried to observe the correlation among the factors. These findings may help students and their parents to know about their daily activities which are restricting them to do better in their study. For performing this study, we have collected information and built a dataset which contains 1000 instances where each instance has 32 unique attributes. We have used Machine Learning techniques for processing the dataset as well as selecting the significant attributes. Moreover, we have used Association Rule Mining technique for finding out the most correlated features of the dataset. We have used Apriori algorithm for implementing Association Rule Mining and we found 4 rules.
01 Jul 2020

Detection of lung agents through rectangular hollow-core photonic crystal fiber

Kharagpur, India

2020 11th International Conference on Computing, Communication and Networking Technologies (ICCCNT)

Conferences Etu Podder, Abdullah Al-Mamun Bulbul, Md Bellal Hossain, Md Ekhlasur Rahaman, Himadri Shekhar Mondal, M Raihan, Sajib Kabiraj, Md Mahmudul Hasan, Ahmed Saif Muntaseer

Detection of lung agents through rectangular hollow-core photonic crystal fiber

Etu Podder, Abdullah Al-Mamun Bulbul, Md Bellal Hossain, Md Ekhlasur Rahaman, Himadri Shekhar Mondal, M Raihan, Sajib Kabiraj, Md Mahmudul Hasan, Ahmed Saif Muntaseer
Conferences
About The Publication
Paper Title: Detection of lung agents through rectangular hollow-core photonic crystal fiber Abstract: Hydrochloric Acid (HCL) and Methyl Bromide (MBX) are two lung agents which have a very harmful effect on the human nose, eyes, lung, etc. In this research, we present a rectangular core photonic crystal fiber (RCPCF) sensor to detect these lung agents in the terahertz (THz) regime and Zeonex is selected as a fiber material for its fascinating properties. Enlarged sensitivity is achieved by this presented model and we found the relative sensitivity of approximately 88.6% for HCL, 92.8% for MBX at frequency 1.7 THz. Also, we found the birefringence of 0.00265, the effective area of 294500 μm2, effective material loss (EML) of 0.0072 cm -1 and confinement loss of 4.39×10 -13 cm -1 for this RCPCF sensor at frequency 1.7 THz. In addition, 3D printing and extrusion techniques are more preferable in order to fabricate this RCPCF sensor.
01 Jul 2020

Diabetes Mellitus Prediction using Different Ensemble Machine Learning Approaches

Kharagpur, India

2020 11th International Conference on Computing, Communication and Networking Technologies (ICCCNT)

Conferences Md Tanvir Islam, M Raihan, Nasrin Aktar, Md Shahabub Alam, Romana Rahman Ema, Tajul Islam

Diabetes Mellitus Prediction using Different Ensemble Machine Learning Approaches

Md Tanvir Islam, M Raihan, Nasrin Aktar, Md Shahabub Alam, Romana Rahman Ema, Tajul Islam
Conferences
About The Publication
Paper Title: Diabetes Mellitus Prediction using Different Ensemble Machine Learning Approaches Abstract: Nowadays Diabetes Mellitus is one of the most rapidly growing diseases which makes the biggest contribution to morbidity and mortality worldwide. Diabetes Mellitus is a group of metabolic disorders defined by high blood glucose level over a prolonged period. Although this disease is familiar as hereditary disease, many people are suffering from this disease without having family background. If diabetes is not in control, the level of glucose goes up and it may cause damage to small vessels in human body which appears most often in the nerves, feet, eyes even in heart and kidneys. To get rid of these issues, it is very crucial to predict diabetes on the early stage. Hence, we have decided to do research on diabetes prediction using Machine Learning algorithms. In this study, we have used three popular Machine Learning algorithms called AdaBoost, Bagging and Random Forest. To train and test the algorithms we have collected real time information of both diabetic and non-diabetic people. The dataset contains 464 instances with 22 unique risk factors. In between the three algorithms, AdaBoost gave 97.84% accuracy, Bagging gave 98.28% accuracy and Random Forest gave 99.35 % accuracy with respect to predict diabetes disease precisely.
01 Jul 2020

Typical and Non-Typical Diabetes Disease Prediction using Random Forest Algorithm

Kharagpur, India

2020 11th International Conference on Computing, Communication and Networking Technologies (ICCCNT)

Conferences Md Tanvir Islam, M Raihan, Fahmida Farzana, Nasrin Aktar, Promila Ghosh, Sajib Kabiraj

Typical and Non-Typical Diabetes Disease Prediction using Random Forest Algorithm

Md Tanvir Islam, M Raihan, Fahmida Farzana, Nasrin Aktar, Promila Ghosh, Sajib Kabiraj
Conferences
About The Publication
Paper Title: Typical and Non-Typical Diabetes Disease Prediction using Random Forest Algorithm Abstract: A non-communicable disease Diabetes is increasing day by day at an alarming rate all over the world and it may cause some long-term issues such as affecting the eyes, heart, kidneys, brain, feet and nerves. It is really important to find an effective way of predicting diabetes before it turns into one of the major problems for the human being. If we take proper precautions on the early stage, it is possible to take control of diabetes disease. In this analysis, 340 instances have been collected with 26 features of patients who have already been affected by diabetes with various symptoms categorized by two types namely Typical symptoms and Non-typical symptoms. The purpose of this study is to identify the Diabetes Mellitus type accurately using Random Forest algorithm which is an Ensemble Machine Learning technique and we obtained 98.24% accuracy for seed 2 and 97.94 % for seed 1 and 3.
01 Jul 2020

Breast Cancer Risk Prediction using XGBoost and Random Forest Algorithm

Kharagpur, India

2020 11th International Conference on Computing, Communication and Networking Technologies (ICCCNT)

Conferences Sajib Kabiraj, M Raihan, Nasif Alvi, Marina Afrin, Laboni Akter, Shawmi Akhter Sohagi, Etu Podder

Breast Cancer Risk Prediction using XGBoost and Random Forest Algorithm

Sajib Kabiraj, M Raihan, Nasif Alvi, Marina Afrin, Laboni Akter, Shawmi Akhter Sohagi, Etu Podder
Conferences
About The Publication
Paper Title: Breast Cancer Risk Prediction using XGBoost and Random Forest Algorithm Abstract: Breast cancer is as one of the common and serious cause of death among women globally. This is a disease where the cells grow out of control inside the breast. Family History of cancer disease, physical inactivity, psychological stress, increase in breast size are the risk factors of breast cancer. In this research paper, breast cancer dataset was analyzed to predict breast cancer using popular two ensemble machine learning algorithms. Random Forest and Extreme Gradient Boosting (XGBoost) were used to predict breast cancer. A total of 275 instances with 12 features were used for this analysis. With Random forest algorithm 74.73% accuracy and 73.63% using XGBoost had obtained in this analysis.
01 Jul 2020

Emotion Detection of Twitter Post using Multinomial Naive Bayes

Kharagpur, India

2020 11th International Conference on Computing, Communication and Networking Technologies (ICCCNT)

Conferences Nazia Anjum Sharupa, Minhaz Rahman, Nasif Alvi, M Raihan, Afsana Islam, Tanzil Raihan

Emotion Detection of Twitter Post using Multinomial Naive Bayes

Nazia Anjum Sharupa, Minhaz Rahman, Nasif Alvi, M Raihan, Afsana Islam, Tanzil Raihan
Conferences
About The Publication
Paper Title: Emotion Detection of Twitter Post using Multinomial Naive Bayes Abstract: In research fields, emotion analysis and opinion mining using data from different platforms are up burning field. In this paper, we tried to represent sentiment of twitter data on core text. But tweets can only be in 140 characters, with lots of noise. Tweets contain few words which is in short forms, ambiguous and noisy, so it is hard to figure out the user’s sentiments. So, it becomes very difficult to have the right opinion with these noise and short forms of words. The main job is to preprocess the data and then extract the features from there. But preprocessing demands, different theories, methods, steps which always varies. Our goal is to improve the outcomes using Naive Bayes classifier and an almost a good trained data set. Finally, we have our average accuracy for happy class 60%, surprise class 61%, relief class it is 71% and worry class has the highest 81%, by using unigram model for preprocessing. On the other hand, using unigram with POS tag model we have average accuracy of 63% same for happy and surprise class, 72% for relief and 83% for worry class.
01 Jul 2020

Prediction of Recurrence and Non-recurrence Events of Breast Cancer using Bagging Algorithm

Kharagpur, India

2020 11th International Conference on Computing, Communication and Networking Technologies (ICCCNT)

Conferences Sajib Kabiraj, Laboni Akter, M Raihan, Nusrat Jahan Diba, Etu Podder, Md Mehedi Hassan

Prediction of Recurrence and Non-recurrence Events of Breast Cancer using Bagging Algorithm

Sajib Kabiraj, Laboni Akter, M Raihan, Nusrat Jahan Diba, Etu Podder, Md Mehedi Hassan
Conferences
About The Publication
Paper Title: Prediction of Recurrence and Non-recurrence Events of Breast Cancer using Bagging Algorithm Abstract: Breast cancer is a type of cancer which prescribed life-threading cancer of women. Cancer growth begins when cells start to out of control. Breast cancer is basically found in family sources, routinely on account of DNA changes. Normal or inside parts, for instance: age, sex, procured inherited deformations and skin type. For this study, 275 instances with 12 features and outcome of having recurrence and non-recurrence event were collected. 10-fold cross-validation had applied for training the data and the accuracy for Bagging algorithm is 73.8182 %. Naive Bayes classifier had been used as base learner of Bagging algorithm.
01 Jul 2020

Obstructive Sleep Apnea Detection Based on Sound Interval Frequency using Wearable Device

Kharagpur, India

2020 11th International Conference on Computing, Communication and Networking Technologies (ICCCNT)

Conferences Sk Al Mamun, Md Mahadi Hassan, Md Riadul Islam, M Raihan

Obstructive Sleep Apnea Detection Based on Sound Interval Frequency using Wearable Device

Sk Al Mamun, Md Mahadi Hassan, Md Riadul Islam, M Raihan
Conferences
About The Publication
Paper Title: Obstructive Sleep Apnea Detection Based on Sound Interval Frequency using Wearable Device Abstract: This paper introduces an automated approach to identify the existence of Resistant Obstructive Sleep Apnea depending on breathing signal. The behavior of the breathing sounds is carried by decision making sound interval that detect respiratory signal when breathe and hold breathing. We have used the capability of recording breathing sound by a microphone and analyzed by sound frequency presence. Whether the recording data is abnormal has been analyzed with Audacity software. Respiratory signals are successfully analyzed by the decision making sound interval frequency made with 89.4% accuracy.
01 Jul 2020

Human Behavior Analysis using Association Rule Mining Techniques

Kharagpur, India

2020 11th International Conference on Computing, Communication and Networking Technologies (ICCCNT)

Conferences Selected M Raihan, Md Tanvir Islam, Promila Ghosh, Md Mehedi Hassan, Jarif Huda Angon, Sajib Kabiraj

Human Behavior Analysis using Association Rule Mining Techniques

M Raihan, Md Tanvir Islam, Promila Ghosh, Md Mehedi Hassan, Jarif Huda Angon, Sajib Kabiraj
Conferences Selected
About The Publication
Paper Title: Human Behavior Analysis using Association Rule Mining Techniques Abstract: At present, the use of social networks is growing rapidly. The matter is more alarming for all the users, who are sharing their personal information with various social media. In social media, their behavior can be reflected. In this research study, we have analyzed different human behavior acts on social media. The data we used in this analysis have been collected from different people in Bangladesh. Most of them are involved with different professions such as student, and various businesses. Approximately 1004 individuals’ information with 19 unique features were collected. Among those, only 10 features have a strong correlation with social media. Apriori algorithm has been applied to determine 8 association rules where the outcome of support and confidence were 0.45, and 0.95, respectively.
21 Jul 2020

An Empirical Study on Diabetes Mellitus Prediction Using Apriori Algorithm

Singapore

International Conference on Innovative Computing and Communications

BookBook ChaptersBook Series Selected Md Tanvir Islam, M Raihan, Fahmida Farzana, Promila Ghosh, Shakil Ahmed Shaj

An Empirical Study on Diabetes Mellitus Prediction Using Apriori Algorithm

Md Tanvir Islam, M Raihan, Fahmida Farzana, Promila Ghosh, Shakil Ahmed Shaj
BookBook ChaptersBook Series Selected
About The Publication
Paper Title: An Empirical Study on Diabetes Mellitus Prediction Using Apriori Algorithm Abstract: Diabetes Mellitus introduce various diseases that affect the way of using sugar in human body. Sugar plays a vital role as it is the main source of energy for cells that build up muscles and tissues. So, any issue that causes the problem to maintain normal blood sugar in our blood can create serious problems. Diabetes is one of the diseases which results in abnormal sugar level in the blood and can occur due to several problems like bad diet, obesity, hypertension, increasing age, depression, etc. Diabetes can lead to cardiovascular disease, kidney, brain, foot, skin, nerve, hearing impairment and eye damage. From this thinking, in this study, we have tried to build up some rules using Association Rule Mining technique with various diabetes symptoms and factors to predict diabetes efficiently. We have got 8 rules using Apriori Algorithm.
18 May 2021

Smartphone-Based Heart Attack Prediction Using Artificial Neural Network

Singapore

Proceedings of International Joint Conference on Advances in Computational Intelligence

Book Chapters Selected M Raihan, Md Nazmos Sakib, Sk Nizam Uddin, Md Arin Islam Omio, Saikat Mondal, Arun More

Smartphone-Based Heart Attack Prediction Using Artificial Neural Network

M Raihan, Md Nazmos Sakib, Sk Nizam Uddin, Md Arin Islam Omio, Saikat Mondal, Arun More
Book Chapters Selected
About The Publication
Paper Title: Smartphone-Based Heart Attack Prediction Using Artificial Neural Network Abstract: Heart attack is among a few of the deadly diseases that cause the death of thousands of people each year globally. It is possible to minimize morbidity and mortality by early screening for those who are at high risk of getting acute myocardial infarction (AMI), known as a heart attack. Android software was implemented to anticipate the risk of getting a heart attack to walk of sudden death. We conducted a survey and collected clinical data from 835 patients that have been analyzed and correlated with 14 risk factors. To predict the heart attack, we used the neural network technology to learn from the clinical data and make predictions. We chose Nesterov-accelerated adaptive moment estimation (Nadam) as an optimizer and categorical cross-entropy as loss function as it fit the best for our neural network model for the best prediction performance. We were able to train our model to predict AMI with 91% accurately. Then, we evaluated our model performance by computing sensitivity (i.e., 81%), specificity (i.e., 98%), precision (i.e., 96%), and F1-score is (i.e., 88%). This trained model was used to implement android software. A user has to answer 14 questions, and based on these answers, the software will predict if the user has a chance to get AMI. This software is free to use, and anyone can use it. The main goal of our research is to implement a simple system to track AMI on a daily basis to lead a healthy life and to avoid sudden deaths.
20 May 2021

A bioinformatics approach for identification of the core ontologies and signature genes of pulmonary disease and associated disease

Netherlands

Gene Reports

Journal Paper Selected Hasin Rehana, Md Raihan Ahmed, Rana Chakma, Sayed Asaduzzaman, M Raihan

A bioinformatics approach for identification of the core ontologies and signature genes of pulmonary disease and associated disease

Hasin Rehana, Md Raihan Ahmed, Rana Chakma, Sayed Asaduzzaman, M Raihan
Journal Paper Selected
About The Publication
Paper Title: A bioinformatics approach for identification of the core ontologies and signature genes of pulmonary disease and associated disease Abstract: Background and objective: Chronic Obstructive Pulmonary Disease (COPD), Diabetes mellitus (DM), Cirrhosis (CR), Ischemic Heart Disease (IHD), Ischemic Stroke (IS), Tuberculosis (TB), Obesity (OB) diseases are related to each other. Any patient affected by any of these diseases increases the possibility of being affected by other diseases. Background studies imply that there are large numbers of similar genetic and biological features among COPD, DM, CR, IHD, IS, TB, OB. For this reason, the common gene network models among these three diseases have been explored. Methods: Preprocessing and filtering has been applied to find the common genes among disease. Then the common genes or significant genes have been explored. Thirteen common genes among COPD, DM, CR, IHD, IS, TB, OB have been recognized. PPI, PDI, PCI, String Analysis and Enrichment, GRN have been carried out to imply the significant proteins, seeds, chemicals etc. Results: A drug signature suggestion for the hub proteins in the PDI and PCI network. From PPIN (Generic and Tissue-Specific), GRN, GO Enrichment, String analysis with algorithm 13 most responsible hub genes are found. K-means clustering was applied to find common clusters of those 13 genes. Conclusion: This analysis discovers the most substantial hub proteins based on biochemical, biological, and genetic relationships between common genes.
12 Apr 2021

A Data Mining Approach to Identify the Stress Level Based on Different Activities of Human

Dhaka, Bangladesh

2021 International Conference on Information and Communication Technology for Sustainable Development (ICICT4SD)

Conferences Selected Md. Al-Mamun Billah, M. Raihan, Nasif Alvi, Tamanna Akter, Nusrat Jahan Bristy

A Data Mining Approach to Identify the Stress Level Based on Different Activities of Human

Md. Al-Mamun Billah, M. Raihan, Nasif Alvi, Tamanna Akter, Nusrat Jahan Bristy
Conferences Selected
About The Publication
Paper Title: A Data Mining Approach to Identify the Stress Level Based on Different Activities of Human Abstract:
Stress is one of the biggest realities in our modern lives because of the rapid variations in human lives and it induces depression. Depression is an illness characterized by anxiety and gloominess felt over a phase of time. Some signs of depression matched with other physical illnesses implying huge trouble in diagnosing it. In this analysis, we have tried to identify the reason for depression among students, based on their nature. We have collected data and generated a dataset that contains 539 instances containing 23 unique attributes individually. By using this data, we created a system that helps to identify the reason for depression. In this paper, a dataset has been analyzed to identify the rate of depression among students using Multilayer Perceptron (MLP), Multi-objective Evolutionary Algorithm and Fuzzy Unordered Rule Induction Algorithm. With the assistance of 100-fold-cross validation, we measure the validity of data that is collected by us, and the performance matrix helps us to report the evaluation of data. This evaluation report has shown us the accuracy and effectiveness of constructing a model to predict the reason for depression. We have got 90.90% accuracy by using Multilayer Perceptron, 92.95% accuracy by using the Fuzzy Unordered Rule Induction Algorithm and 92.76% accuracy by using Multi-objective Evolutionary Algorithm. Our main goal is to identify the rate of depression among students based on human nature.
01 Feb 2021

A Comparative Study to Predict the Diabetes Risk Using Different Kernels of Support Vector Machine

DHAKA, Bangladesh

2021 2nd International Conference on Robotics, Electrical and Signal Processing Techniques (ICREST)

Conferences Selected Md Mohsin Sarker Raihan, M Raihan, Laboni Akter

A Comparative Study to Predict the Diabetes Risk Using Different Kernels of Support Vector Machine

Md Mohsin Sarker Raihan, M Raihan, Laboni Akter
Conferences Selected
About The Publication
Paper Title: A Comparative Study to Predict the Diabetes Risk Using Different Kernels of Support Vector Machine Abstract:
Diabetes is a metabolic issue wherein there is an increment in the level of glucose in the blood. The principle explanation behind diabetes is less emission of insulin from the pancreases. After some time, high blood glucose levels can harm the body’s organs. This research study aims to predict diabetes for a patient with a higher exactness by consolidating the aftereffects via Machine Learning methods including Support Vector Machine (SVM). In this system, four types of kernel Linear, RBF, Polynomial, Sigmoid are used. From Sigmoid, the best Kappa Statistics (98%) is gained whereas polynomial kernel has shown the lowest performance. From the perspective of Accuracy, Precision, Recall, F1-Score, Specificity and ROC area Sigmoid kernel is also given the best outcome rather than other kernels. So, in this research study, out of these four kernels, the Sigmoid is the most preferable for predicting diabetes disease.
07 Feb 2021

Regulatory Gene Network Pathway among Brain Cancer and Associated Disease: A Computational Analysis

VANCOUVER - CANADA

Biointerface Research in Applied Chemistry Volume 11, Issue 5, 2021, 12973 - 12984

Journal Paper Selected Sayed Asaduzzaman, Rana Chakma, Hasin Rehana, M Raihan

Regulatory Gene Network Pathway among Brain Cancer and Associated Disease: A Computational Analysis

Sayed Asaduzzaman, Rana Chakma, Hasin Rehana, M Raihan
Journal Paper Selected
About The Publication
Paper Title: Regulatory Gene Network Pathway among Brain Cancer and Associated Disease: A Computational Analysis Abstract:  Brain cancer (BC), melanoma (ML), bladder cancer (BDC), benign tumor (BT), gliomas (GM) are annihilating diseases among people because of their high death risk. These five diseases are associated among themselves. The analysis shows that there are eight common genes TERT, MYC, GSTP1, GSTM1, CXCR4, CXCL12, GSTT1, PROM1, among those associated with five diseases. Preprocessing has been done to find these eight common genes based on biological, biochemical, and genetic relationships between common genes. This analysis identifies the most significant hub proteins. Seed, nodes, and edges create networks that indicate the relationship between the genes and proteins. Protein-protein interaction (PPIs) network, TF–gene interactions, gene regulatory network (GRN), protein-drug, protein-chemical, gene-diseases analysis has been done the common genes and their interactions, correlation, association, and candidate drugs. Topological analysis finally provides eight common genes that can develop an efficient drug design for this research.
24 Dec 2020

Design and optimization of the perilous chemical sensor in the terahertz frequency range

Elsevier

Materials Today: Proceedings

Journal Paper Etu Podder, Md.Bellal Hossain, Md.Ekhlasur Rahaman, Himadri Shekhar Mondal, Sajib Kabiraj, M. Raihan

Design and optimization of the perilous chemical sensor in the terahertz frequency range

Etu Podder, Md.Bellal Hossain, Md.Ekhlasur Rahaman, Himadri Shekhar Mondal, Sajib Kabiraj, M. Raihan
Journal Paper
About The Publication
Paper Title: Design and optimization of the perilous chemical sensor in the terahertz frequency range Abstract:  Few man-made chemicals are excessively harmful to the human eye, skin, and breathing system. Therefore, the precious detection of these perilous chemicals is highly worthy. A sensor model is presented in this manuscript to sense three dangerous chemicals (Tabun, Soman, Sarin) where Topas is chosen as the fiber material. The optimized model shows enhanced relative sensitivity (94.34% for Sarin, 95.23% for Soman, and 96.12% for Tabun at frequency 2.6 THz). Besides, the effective material loss provided by the reported sensor is noticed to be very tiny (0.00970 cm−1 for Sarin, 0.00988 cm−1 for Soman and 0.01007 cm−1 for Tabun at frequency 2.6 THz) and also, the confinement loss is observed excessively low (only 3.600 × 10-13 cm−1 for Sarin, 3.593 × 10-13 cm−1 for Soman and 3.585 × 10-13 cm−1 for Tabun at frequency 2.6 THz). Moreover, we observe the large effective area (1.665 × 105 µm2 for Sarin, 1.654 × 105 µm2 for Soman and 1.640 × 105 µm2 for Tabun at frequency 2.6 THz) for this chemical sensor. 3D printing can be used to fabricate the presented sensor structure.
.04

RESEARCH

TEAM MEMBERS

Saikat Mondal

Assistant Professor

Dr. Arun More

Cardiologist

Sayed Asaduzzaman

Assistant Professor

RESEARCH PROJECTS

PredictRisk

Android based application to predict heart attack risk.

Nowadays, Ischemic Heart Disease (IHD) (Heart Attack) is ubiquitous and one of the major reasons of death worldwide. Early screening of people at risk of having IHD may lead to minimize morbidity and mortality. A simple approach is proposed in this paper to predict risk of developing heart attack using smartphone and data mining. Clinical data from 835 patients was collected, analyzed and also correlated with their risk existing clinical symptoms which may suggest underlying non detected IHD. A user friendly Android application was developed by incorporating clinical data obtained from patients who admitted with chest pain in a cardiac hospital. Upon user input of risk factors, the application categorizes the level of IHD risks of the user as high, low or medium. It was found by analyzing and correlating the data that there was a significant correlation of having an IHD and the application results in high & low, medium & low and medium & high categories; where the p values were 0.0001, 0.0001 and 0.0001 respectively. The experimental results showed that the sensitivity and accuracy of the proposed technique were 89.25 % and 76.05 % respectively, whereas, using C4.5 decision tree, accuracy was found 86% and sensitivity was obtained 91.6%. Existing tools need mandatory input of lipid values which makes them underutilized by general people; though these risk calculators bear significant academic importance. Our research is motivated to reduce that limitation and promote a risk evaluation on time.

Heart Sound Abnormalities

Wireless Electronic Stethoscope to Classify Children Heart Sound Abnormalities

In this research project, a wireless stethoscope has introduced that can communicate with a smartphone to receive children's heart sound. Along with an automated method that recognizes children heart sound abnormalities. That isolation of heart sound is based on time-frequency characteristics. Where it is preceded using Mel-frequency Cepstral Coefficients (MFCCs) signal processing method. The processed sounds are extracted using five feature extraction algorithms. Then it is classified using four support vector machines (SVM) kernel. Total 60 heart sounds were collected, where 30 sounds having abnormalities and rest 30 sounds containing normal heart sound. Though massive measures of action have already been done in this area, still necessity of more bearable cost device and accurate method is present. Here, the submitted apparatus cost is approximately 18 USD, which is the cheapest than most other device used in previous work. Simultaneously it is lightweight and bearable to use in rural and underprivileged area. With RBF kernel of SVM, the proposed method shows 94.12% accuracy which is the highest.

Safeguard

An Application Programming Interface to Save the Disaster Affected People

The automated chatbot system has introduced a new era of modern technology. Recently the chatbot system plays an important role as a virtual agent in different respects. A chatbot system cannot replace a human agent but it can provide initial support at any time instantly. This type of instant support can help a victim at the time of the natural disaster period efficiently. It can also play a role to reduce the amount of damage. In this research paper, we have proposed a chatbot application programming interface (API) system named Safeguard that can be integrated into different social media as well as in any application. This system will be able to support a victim and give guidelines on disaster period. For this purpose, natural language understanding was used by Dialogflow tool. Dialogflow has helped to create the application programming interface system by using intents, entities and text responses by the implementation of the natural language processing system, cloud storage and JSON.

Acute Myocardial Infarction (AMI) Prediction

Smartphone-Based Heart Attack Prediction Using Artificial Neural Network

Heart attack is among a few of the deadly diseases that cause the death of thousands of people each year globally. It is possible to minimize morbidity and mortality by early screening for those who are at high risk of getting acute myocardial infarction (AMI), known as a heart attack. Android software was implemented to anticipate the risk of getting a heart attack to walk of sudden death. We conducted a survey and collected clinical data from 835 patients that have been analyzed and correlated with 14 risk factors. To predict the heart attack, we used the neural network technology to learn from the clinical data and make predictions. We chose Nesterov-accelerated adaptive moment estimation (Nadam) as an optimizer and categorical cross-entropy as loss function as it fit the best for our neural network model for the best prediction performance. We were able to train our model to predict AMI with 91% accurately. Then, we evaluated our model performance by computing sensitivity (i.e., 81%), specificity (i.e., 98%), precision (i.e., 96%), and F1-score is (i.e., 88%). This trained model was used to implement android software. A user has to answer 14 questions, and based on these answers, the software will predict if the user has a chance to get AMI. This software is free to use, and anyone can use it. The main goal of our research is to implement a simple system to track AMI on a daily basis to lead a healthy life and to avoid sudden deaths.

.05

TEACHING

EXPERIENCES
  • Current
    2021
    Khulna, Bangladesh.

    Senior Lecturer

    North Western University

    Working as full time Senior Lecturer and Faculty Member of North Western University, Khulna, Bangladesh.
  • 2021
    2018
    Khulna, Bangladesh

    Lecturer

    North Western University

    Worked as full time Lecturer and Faculty Member of North Western University, Khulna, Bangladesh.
  • 2017
    Khulna, Bangladesh

    Part-time Lecturer

    Khulna University

    Worked as Part-time Lecturer under Computer Science & Engineering Discipline, Khulna University, Khulna, Bangladesh. (Duration: July (2017)- December (2017)).
  • 2017
    Khulna, Bangladesh

    Adjunct Faculty

    North Western University

    Worked as Part-time Lecturer under Computer Science & Engineering Department, North Western University, Khulna, Bangladesh. (Duration: September(2017)- December (2017)).
  • 2017
    Khulna, Bangladesh

    Part-time Lecturer

    South East Engineering College

    Worked as Part-time Lecturer under Computer Science & Engineering Department, South East Engineering College, Khulna an affiliated college under Rajshahi University, Bangladesh.(Duration: September(2017)- December (2017).)
  • 2017
    Khulna, Bangladesh

    Teaching Assistant

    Khulna University of Engineering and Technology

    Worked as Teaching Assistant under Biomedical Engineering Department, Khulna University of Engineering and Technology (KUET), Khulna, Bangladesh. (Duration: August (2017) - December (2017)).
  • 2018
    2015
    India

    Research Fellow

    Rural Health Progress Trust (RHPT)

    Worked remotely as medical researcher in an Indian NGO named Rural Health Progress Trust (RHPT) (Duration: September (2015)-2018.).
  • 2015
    Bangladesh

    Assistant Trainer

    ICT Ministry (MoICT)

    Worked as Trainer in National 500 Apps Trainer and Innovative Apps Development Program arranged by ICT Ministry (MoICT), Bangladesh.
.06

SKILLS

Language SKIILLS
Data Analysis and Pattern Recognition > Machine Learning, Statistical Analysis, Predictive Model Development, Artificial Intelligence and Expert System.
LEVEL : Advanced EXPERIENCE : More than 5 Years
WEKA IBM SPSS R Python Graphpad Prism Microsoft Power BI
MS OFFICE > MS WORD, EXCEL, POWER POINT, PUBLISHER
LEVEL : Advanced EXPERIENCE : More than 5 Years
WORD EXCEL POWER POINT PPT
C > Logic Development, Structural Programing.
LEVEL : Advanced EXPERIENCE : More than 5 Years
C C++ Array String Branching Looping
Java > Object Oriented Programming. SWING applications
LEVEL : Advanced EXPERIENCE : More than 5 Years
OOP JAVA JVM Swing
C#, .NET, SQL, XAML > Object Oriented Programming. Desktop Applications, Windows Phone Applications
LEVEL : Advanced EXPERIENCE : More than 5 Years
OOP C# Windows Phone Database Project Desktop Applications
Latex > Technical Writing
LEVEL : Advanced EXPERIENCE : More than 5 Years
Research Article Content Writing Presentation Research TeX Studio
Android > JAVA, OOP Programing, Mobile Application Development
LEVEL : Advanced EXPERIENCE : More than 5 Years
Android JAVA JVM XML
Web Programing > Website Development and Design
LEVEL : Intermediate EXPERIENCE : More than 5 Years
HTML CSS WordPress MySQL PHP
.07

PROJECTS

LIST OF PROJECTS
Android

TIRH NCD

TIRH NCD

About The Project
An online mobile based survey application for Rural Health Progress Trust NGO in India.
Desktop Application

KU Seminar Library

KU Seminar Library

About The Project
A desktop based database project.
AndroidData ScienceMachine Learning

PredictRisk

PredictRisk

About The Project
An android based application to predict heart attack risk.
Android

Ecare

Ecare

About The Project
An android based medical application.
Desktop Application

Printer

Printer

About The Project
Its a printing software for desktop use only.
Android

iTorch

iTorch

About The Project
It’s an android based torch application with sensor.
AndroidWindows Phone

iMediCare

iMediCare

About The Project
Both Windows Phone and Android based application.
Android

mKrishi

mKrishi

About The Project
Bengali language based android application for agriculture.
.08

Materials

COURSE MATERIALS

Google Drive Link

.09

CONTACT

Drop me a text

GET IN TOUCH WITH ME

If you want to contact with me mail on my personal mail: raihan1146@cseku.ac.bd or raihanbme@gmail.com