Browsing by Author "Chakraborty, Partha"

Now showing 1 - 12 of 12

A Comparative Study of Machine Learning Algorithms to Detect Cardiovascular Disease with Feature Selection Method
(2022-08-22) Ali, Md. Jubier; Das, Badhan Chandra; Saha, Suman; Biswas, Al Amin; Chakraborty, Partha
Heart disease is considered one of the calamitous diseases which eventually leads to the death of a human, if not diagnosed earlier. Manually, detecting heart disease needs doing several tests. By analyzing the result of tests, it can be assured whether the patient got heart disease or not. It is time consuming and costly to predict heart disease in this conventional way. This paper describes different machine learning (ML) algorithms to predict heart disease incorporating a Cardiovascular Disease dataset. Although many studies have been conducted in this field, the performance of prediction still needs to be improved. In this paper, we have focused to find the best features of the dataset by feature selection method and applied six machine learning algorithms to the dataset in three steps. Among these ML algorithms, the random forest algorithm gives the highest accuracy which is 72.59%, with our best possible feature setup. The proposed system will help the medical sector to predict heart disease more accurately and quickly.
Design and implementation of a simple electromechanical system to reduce domestic gas wastage and accidents in South-Asia
(© 2012 IEEE, 2012) M. Huq, Rachaen; Hoque, Md. Anamul; Chakraborty, Partha; B. Jafar, Imran; Rahman, Khan H.
This paper elaborates design and implementation aspects of a system design project which aims at modernizing the current design of domestic gas-stoves with a simple electromechanical sensor-integrated system in order to reduce wastage of gas and accident possibilities in South-Asian households. Statistics show that a significant amount of natural gas is wasted every day in the domestic cooking purpose because of the ignorance of the users by keeping the gas line on even after cooking is done, or during breaks. One of the two major portions of the proposed system will sense the situation of 'activity' of the stove (idle or cooking); the other will sense the state of the gas knob (on or off) and send signals to the controller-unit accordingly. Both of these electromechanical sensors were designed and implemented in this project. If the stove remains 'idle' and gas-line is 'on' for a specific amount of time, say five minutes, the controller will automatically close the gas line. The gas line will again automatically 'open' when any of the above states changes (if the stove becomes 'active' or the line is manually closed). The system components were designed and implemented as a whole successfully. The proposed system can either be implemented as an external modification to the existing gas-stoves or can be industrially integrated to make the next-generation energy saving stoves.
Design and implementation of a simple electromechanical system to reduce domestic gas wastage and accidents in South-Asia
(© 2012 IEEE, 2012) M. Huq, Rachaen; Hoque, Md. Anamul; Chakraborty, Partha; B. Jafar, Imran; Rahman, Khan H.
This paper elaborates design and implementation aspects of a system design project which aims at modernizing the current design of domestic gas-stoves with a simple electromechanical sensor-integrated system in order to reduce wastage of gas and accident possibilities in South-Asian households. Statistics show that a significant amount of natural gas is wasted every day in the domestic cooking purpose because of the ignorance of the users by keeping the gas line on even after cooking is done, or during breaks. One of the two major portions of the proposed system will sense the situation of 'activity' of the stove (idle or cooking); the other will sense the state of the gas knob (on or off) and send signals to the controller-unit accordingly. Both of these electromechanical sensors were designed and implemented in this project. If the stove remains 'idle' and gas-line is 'on' for a specific amount of time, say five minutes, the controller will automatically close the gas line. The gas line will again automatically 'open' when any of the above states changes (if the stove becomes 'active' or the line is manually closed). The system components were designed and implemented as a whole successfully. The proposed system can either be implemented as an external modification to the existing gas-stoves or can be industrially integrated to make the next-generation energy saving stoves.
Design and implementation of a simple electromechanical system to reduce domestic gas wastage and accidents in South-Asia
(© 2012 IEEE, 2012) M. Huq, Rachaen; Hoque, Md. Anamul; Chakraborty, Partha; B. Jafar, Imran; Rahman, Khan H.
This paper elaborates design and implementation aspects of a system design project which aims at modernizing the current design of domestic gas-stoves with a simple electromechanical sensor-integrated system in order to reduce wastage of gas and accident possibilities in South-Asian households. Statistics show that a significant amount of natural gas is wasted every day in the domestic cooking purpose because of the ignorance of the users by keeping the gas line on even after cooking is done, or during breaks. One of the two major portions of the proposed system will sense the situation of 'activity' of the stove (idle or cooking); the other will sense the state of the gas knob (on or off) and send signals to the controller-unit accordingly. Both of these electromechanical sensors were designed and implemented in this project. If the stove remains 'idle' and gas-line is 'on' for a specific amount of time, say five minutes, the controller will automatically close the gas line. The gas line will again automatically 'open' when any of the above states changes (if the stove becomes 'active' or the line is manually closed). The system components were designed and implemented as a whole successfully. The proposed system can either be implemented as an external modification to the existing gas-stoves or can be industrially integrated to make the next-generation energy saving stoves.
Detection of Copy–Move Image Forgery Applying Robust Matching with K-D Tree Sorting
(Daffodil International University, 2022-09-20) Chakraborty, Partha; Sayed, Md. Abu; Khatun, Mahmuda; Zulfiker, Md. Sabab; Paul, Priyanka; Hossain, Md. Farhad; Choudhury, Tanupriya
Digital images contribute significantly to the field of visualization. Using stronger technology, digital image forgery is easier. The most common method of image forgery is to re-create a portion of a person’s location or to conceal a portion of an image. In our paper, we worked on detecting region duplication forgery using COMOFORD databases by utilizing the discrete cosine transform (DCT), k-dimensional tree (k-d tree) for sorting efficiently, and a robust matching method. Here, the size of the block will be 16 × 16, and it will be divided into four blocks. This study can detect forged portions for PNG images with better performance by highlighting the images with a quality factor of 0.5 and a threshold value of 10, as well as gives good results for JPEG images.
Development of Torque Sensor Based Electrically Assisted Hybrid Rickshaw
(BRAC University, 9/4/2012) Huq, Rachaen Mahfuz; Shuvo, Numayer Tahmid; Chakraborty, Partha; Hoque, Md. Anamul; Azad, A. K. M. Abdul Malek
Cycle rickshaws are the most popular form of transportation inside the cities of Bangladesh, especially for its route and time-flexibility and door-to-door services. Considering the fact that a significant portion of underprivileged population of Bangladesh is directly or indirectly dependent upon the rickshaw-pulling profession, the necessity of scientifically thinking about its improvement and modernization was apparent. This paper describes a research and development project of Control and Applications Research Group, BRAC University, aiming to modernize these green fuelfree transports of Bangladesh using power-assistive technology. This involves design and implementation of an intelligent control system that would make the rickshaw pulling task easier-to-feel by assisting the human power with a motor, turning it into a hybrid vehicle. The motivation of the project was to relieve the rickshaw pullers from the excessive physical exhaustion associated with the task, which mainly occurs while initiating the momentum from rest or low speed to a moderate speed. A motor helping the pullers only during this particular time eradicates this exhaustion to a significant extent, at the same time saves energy by limiting over-use of the motor. A torque-sensor was involved to determine the need-of-assistance a puller feels at a particular time, and an external controller in addition to the motor controller was designed and tested. The model was developed so as to save energy, limit overuse, and keeping the identity and driving mechanism of old rickshaws. An idea of battery charging infrastructure using Solar- Battery-Charging-Station is also mentioned as a core factor of the project.
Employee satisfaction of Universal Medical College & Hospital Pvt. Ltd.
(BRAC University, 12/7/2017) Chakraborty, Partha; Ahmed, Riyashad
Health is one of five basic needs of human life. Now-a-days care for health has increased due to increasing education & health consciousness amongst people as well as increasing per capital income of the peoples. In consideration of the total population & rapid growth of population, we need & have wide demand for quality caring referral hospitals through the country, especially in urban areas is very much optimum. This sector is highly potential. To be a successful hospital first we have divided our hospital in several department as like marketing department, HR department, finance department, commercial department etc. these department will help to achieve the goal. We have also market strategies like target market , other variable, value innovation., value pricing, value delivery, value proposition to placed our product in the market. Top Management of Universal Medical College & Hospital Pvt. Ltd.. has already achieved goodwill to its corporate clients and patient, well-wishers, investors and in abroad as well. Therefore effective decision making is the strategy for the actual performance of the top management of Universal Medical College & Hospital Pvt. Ltd.. Calling for never-ending effort for improvement at all service levels, is the most important management concept of Universal Medical College & Hospital Pvt. Ltd.. we have advertised our services for knowing our services in hole country. We hope our services will be best in the hole country as well as world. From our study we saw that, for earning strong patients’ loyalty Universal Medical College & Hospital Pvt. Ltd.. has now established itself as renowned private hospital in Bangladesh with great services, high-tech technologies, strong control and monitoring, good visionary and integrity
Predicting Insomnia Using Multilayer Stacked Ensemble Model
(Scopus, 2021) Zulfiker, Md. Sabab; Kabir, Nasrin; Biswas, Al Amin; Chakraborty, Partha
Different forms of sleep disorders have become major health problems among people around the world, and insomnia is one of them. It is a physical condition in which a person faces difficulties to fall asleep at night. It leads to various mental disorders, like anxiety and depression. One of the vital causes of substance abuse is insomnia. This study has proposed a machine learning approach to predict insomnia using different socio-demographic factors of the participants. A multilayer stacking model has been employed in this study to predict the appearance of insomnia in a person. For feature reduction, Principal Component Analysis (PCA) has been used. Our proposed ensemble model has attained an accuracy of 88.60%. The effectiveness of our proposed model has been compared to that of other state-of-the-art ensemble classifiers, like AdaBoost, Gradient Boost, Bagging, and Weighted Voting classifier. The proposed model stated in this study has surpassed the performance of the other ensemble classifiers in terms of different efficacy metrics, like sensitivity, precision, specificity, area under the curve (AUC), accuracy, and F1-score.
Predicting Students
(Scopus, 2020) Zulfiker, Md. Sabab; Kabir, Nasrin; Biswas, Al Amin; Chakraborty, Partha; Rahman, Md. Mahfujur
Every year thousands of students get admitted into different universities in Bangladesh. Among them, a large number of students complete their graduation with low scoring results which affect their careers. By predicting their grades before the final examination, they can take essential measures to ameliorate their grades. This article has proposed different machine learning approaches for predicting the grade of a student in a course, in the context of the private universities of Bangladesh. Using different features that affect the result of a student, seven different classifiers have been trained, namely: Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Logistic Regression, Decision Tree, AdaBoost, Multilayer Perceptron (MLP), and Extra Tree Classifier for classifying the students’ final grades into four quality classes: Excellent, Good, Poor, and Fail. Afterwards, the outputs of the base classifiers have been aggregated using the weighted voting approach to attain better results. And here this study has achieved an accuracy of 81.73%, where the weighted voting classifier outperforms the base classifiers.
Prospect and implementation of telemedicine centers in south Asian countries
(© 2015 Institute of Electrical and Electronics Engineers Inc., 2015) Jafar, Imran Bin; Shahin, Md Zahidul Islam; Chakraborty, Partha
In this paper a sensor based Remote Patient Diagnosing Center is implemented and the prospect of telemedicine in south Asian countries are analyzed accordingly. A computer with sensors and interfacing devices are dedicated to build the complete remote diagnosing center. Hence, to extract signals from the body of patient, combinational networks of sensors are attached to the patient. Electrocardiogram (ECG) signal, Blood-oxygen saturation (SpO2) level, Temperature and Blood Pressure are basically measured using the corresponding sensors and doctors would be able to interact with patients in real-time via internet. To process and accumulate the data of extracted Bio-Signals, a dedicated microcontroller is employed in this research. Moreover, several subroutines are called for each work by microcontroller. Additionally a Graphical User Interface (GUI) is developed to exhibit and record all the information including the details of patient. In the GUI, values of different sensors would be updated simultaneously for different patients and these are observed in real time via internet for the live analysis by doctor from a remote location. Therefore, unprivileged patients from rural community or secluded locations can get proper medical help from a specialized urban doctor which will actually contribute to promote the practice of telemedicine. Finally, experimental results of ECG signal processing, percentage of SpO2 levels, Temperature and Blood Pressure are presented in this paper.
Prospect and implementation of telemedicine centers in south Asian countries
(© 2015 Institute of Electrical and Electronics Engineers Inc., 2015) Jafar, Imran Bin; Shahin, Md Zahidul Islam; Chakraborty, Partha
In this paper a sensor based Remote Patient Diagnosing Center is implemented and the prospect of telemedicine in south Asian countries are analyzed accordingly. A computer with sensors and interfacing devices are dedicated to build the complete remote diagnosing center. Hence, to extract signals from the body of patient, combinational networks of sensors are attached to the patient. Electrocardiogram (ECG) signal, Blood-oxygen saturation (SpO2) level, Temperature and Blood Pressure are basically measured using the corresponding sensors and doctors would be able to interact with patients in real-time via internet. To process and accumulate the data of extracted Bio-Signals, a dedicated microcontroller is employed in this research. Moreover, several subroutines are called for each work by microcontroller. Additionally a Graphical User Interface (GUI) is developed to exhibit and record all the information including the details of patient. In the GUI, values of different sensors would be updated simultaneously for different patients and these are observed in real time via internet for the live analysis by doctor from a remote location. Therefore, unprivileged patients from rural community or secluded locations can get proper medical help from a specialized urban doctor which will actually contribute to promote the practice of telemedicine. Finally, experimental results of ECG signal processing, percentage of SpO2 levels, Temperature and Blood Pressure are presented in this paper.
Sentiment Analysis of Bengali Facebook Data Using Classical and Deep Learning Approaches
(Daffodil International University, 2022-02-17) Chakraborty, Partha; Nawar, Farah; Chowdhury, Humayra Afrin
Recently, sentiment analysis has been performed on various information on social media to derive market intelligence. As we know social media is filled with different content as a result audiences are interacting there making it a huge opportunity to perform sentiment analysis on this information. In terms of Bengali content, many audiences on social media interact with the Bengali language which makes social media a treasure trove to perform sentiment analysis in Bengali Natural Language Processing (NLP) field. Here in this study sentiment analysis has been performed on the audience’s Bengali comments expressing different views towards social media’s Bengali contents. The dataset contains 4000 Bengali comments collected from Facebook and YouTube Bengali Contents. Here positive, negative, and neutral classes are used to categorize the Bengali data, and a tokenizer from the Keras library is used to tokenize the Bengali text. Deep learning algorithm Long Short-Term Memory (LSTM) and BiDirectional Long Short-Term Memory (Bi-LSTM) are performed and Bi-LSTM has the highest accuracy of 97.25% than LSTM.