Browsing by Author "Sarker, M. Mesbahuddin"

Now showing 1 - 6 of 6

COVID-19 Effects on Private Tuition in Bangladesh and Internet of Things Based Support System
(Bentham Science Publishers Ltd., 2023-05-30) Akhund, Tajim Md. Niamat Ullah; Newaz, Nishat Tasnim; Sarker, M. Mesbahuddin
Private tutoring is an important matter in Bangladesh. Many students take private tutor for various study. Many teachers and senior students become private tutor to get some extra income or primary income. During the covid-19 pandemic time this profession and teaching status are changed in a great extent. This work makes a survey about private tuition among thousands of students and teachers from Dhaka city in Bangladesh. This work analyzed the collected data in multiple aspects and suggested some support system with the Internet of Things and Information Technology. The proposed IoT based system can help the students and teachers with remote monitoring. With the IoT based system the tutor and student both can check each other's physical condition from a remote place without affecting them with virus. The collected data shows a clear concept about the condition of private tuition and the IoT based solution worked successfully. The outcome of the system showed good results.
Internet of Sensing Things-Based Machine Learning Approach to Predict Parkinson
(2023-09-15) Afroz, Sohana; Ullah Akhund, Tajim Md. Niamat; Khan, Tarikuzzaman; Hasan, Md. Umaid; Jesmin, Rashida; Sarker, M. Mesbahuddin
With the help of the Internet of things, therapeutic science has progressed surprisingly. Lots of elderly individuals are affected by Parkinson’s disease. This work proposed an Internet of sensing things-based system to collect data from Parkinson’s affected people analyze the collected data in a cloud server with machine learning algorithms and predict the condition of the patient. Multiple types of sensors are used and tested. Micro-controllers are used to collect data from sensors and send them to a cloud server. Then, multiple machine learning algorithms are used to predict the patient’s condition. Results between several methods are also compared.
Internet of Things based Low-cost Health Screening and Mask Recognition system
(2024-01-15) Newaz, Nishat; Akhund, Tajim; Sarker, M. Mesbahuddin
The world is facing a pandemic now. Face mask can reduce the spread of corona virus and help people to save many lives. Many people are not serious about wearing face mask. This work results a system that can detect face mask of a person with CNN. The system can identify anyone without face mask. An IoT based module is integrated with the system to monitor people’s temperature, blood pulse and oxygen level. Which can collect all the sensor data and send the data to a cloud database. From the cloud server the mask condition and health condition can be monitored. The collected data can also be used for future analysis. The proposed low-cost system worked properly with a good success rate
IOT Based Low-cost Robotic Agent Design for Disabled and Covid-19 Virus Affected People
(Proceedings of the World Conference on Smart Trends in Systems, Security and Sustainability, WS4 2020, IEEE, 2020-10-01) Akhund, Tajim Md. Niamat Ullah; Jyoty, Watry Biswas; Siddik, Md. Abu Bakkar; Newaz, Nishat Tasnim; Wahid, S.K. Ayub Al; Sarker, M. Mesbahuddin
Disabled people and Virus affected patients can be helped through Internet of Things and Robotic systems in this modern era. Recently the whole world is suffering from the Covid-19 pandemic. The virus affected and disabled people are helpless because caregivers, doctors and other people are afraid of the contagious virus. This work will result in an IOT based Robotic agent which will be able to help disabled and virus affected people with low cost systems. The robotic agent will be able to recognize the patient's Gesture and follow instructions through it with 360-degree movement. Without image processing the system is made with MPU 6050 Accelerometer Gyroscope sensor for Gesture Recognition. Radio Frequency communication was used to make the system wireless.
Simplified Mapreduce Mechanism for Large Scale Data Processing
(SPC, 2018) Munna, Md Tahsir Ahmed; Allayear, Shaikh Muhammad; Alam, Mirza Mohtashim; Rahman, Sheikh Shah Mohammad Motiur; Rahman, Md Samadur; Sarker, M. Mesbahuddin
MapReduce has become a popular programming model for processing and running large-scale data sets with a parallel, distributed paradigm on a cluster. Hadoop MapReduce is needed especially for large scale data like big data processing. In this paper, we work to modify the Hadoop MapReduce Algorithm and implement it to reduce processing time.
Supervised Ensemble Machine Learning Aided Performance Evaluation of Sentiment Classification
(IOP Science, 2018-07) Rahman, Sheikh Shah Mohammad Motiur; Rahman, Md. Habibur; Sarker, Kaushik; Rahman, Md. Samadur; Ahsan, Nazmul; Sarker, M. Mesbahuddin
Text vectorization, features extraction and machine learning algorithms play a vital role to the field of sentiment classification. Accuracy of sentiment classification varies depending on various machine learning approaches, vectorization models and features extraction methods. This paper represents multiple ways of evaluations with the necessary steps needed to achieve highest accuracy for classifying the sentiment of reviews. We apply two n-gram vectorization models - Unigram and Bigram individually. Later on, we also apply features extraction method TF-IDF with Unigram and Bigram respectively. Five ensemble machine learning algorithms namely Random Forest (RF), Extra Tree (ET), Bagging Classifier (BC), Ada Boost (ADA) and Gradient Boost (GB) are used here. The key findings in this study is to determine which combination of vectorization models (Bigram, Unigram) along with feature extraction method (TF-IDF) and ensemble classifier gives the better performance of sentiment classification. Full Text Link: https://doi.org/10.1088/1742-6596/1060/1/012036