Browsing by Author "Islam, Md. Tarequl"

Now showing 1 - 10 of 10

Automatic Brain Tumor Detection Using Feature Selection and Machine Learning from MRI Images.
(Proceedings of the 6th International Conference on Electrical, Control and Computer Engineering. Lecture Notes in Electrical Engineering, vol 842. Springer, Singapore, 2023-03-09) Shafi, A. S. M.; Hasan, Md. Mahmudul; Mollah, M. M. Imran; Alam, Mohammad Khurshed; Islam, Md. Tarequl
A brain tumor is a group of defective cells in the brain. It happens when a cell in the brain develops a dysfunctional structure. Nowadays it becom-ing a crucial factor of death for a large number of people. Among all the varie-ties of tumors, the seriousness of a brain tumor is high. Therefore, instant detec-tion and proper care to be done to save a life from brain tumors. Microscopic examination can separate the tumor cells from healthy cells. They are typically less well separated than normal cells. In modern imaging technology, the de-tection and classification of brain tumors is a primary concern. For a clinical supervisor or radiologist, it is time-consuming and frustrating work. The accu-racy of recognition and classification of tumors executed by radiologists or clin-ical experts is depended on their experience only. Therefore, accurate identifi-cation and classification of brain tumors can be determined by image processing techniques. This research suggests a machine learning module to detect brain tumors using magnetic resonance imaging (MRI) of brain tumors. The method consists of pre-processing of nearly raw raster data (NRRD) of the MRI images, feature extraction, feature selection, and the classification learner to evaluate and construct the final model. The classification learner is designed with a sup-port vector machine (SVM) classifier. The classification method performs well with weighted sensitivity, specificity, precision, and accuracy of 98.81%, 98.88%, 98.82%, and 98.81% respectively. The findings may infer a remarka-ble step for detecting the presence of tumors in neuro-medicine diagnosis.
Design and Development of a Web Based Application for Online Job Search and CV Create
(Daffodil International University, 2018-11-24) Islam, Md. Muhafi; Islam, Md. Tarequl; Hasan, Md. Sazzad
“Your Job” is an online web based application where anyone can search for Jobs. In this system job search will be much more easier than ever. In this system, there will be a CV creation option where the CV will be created by giving proper information of the applier. The CV format can be chosen from five or six given formats which will be in the web application. In this system, firstly the applier or job searcher have to fill up the information form where the applier have to fill up all of his or her personal, educational and academical information. After giving the information the system will create the CV and the applier can save his or her created CV from the system in PDF format to his or her digital system. The main attraction of the system is to search jobs according to the appliers qualification. The applier don’t have to search for his or her jobs. The web application will do the work for the applier. After making the CV the applier have to choose a option “Search for Jobs”. After clicking the “Search for Jobs” option the system will begin to search for Jobs through the information that are given in the CV. If there is any Job, The system will automatically show the jobs to the applier. And then the applier would be able to submit his or her CV in that Job option. If there is no Job according to the given information then the applier don’t have to worry about. The applier have to login or sign-up with his or her e-mail address and of course with a password for security reasons. After signing up the system will give update about new jobs according to his or her qualification. This web based application will also have the common features like other web application in Bangladesh such as Job portals, Contact, Information, Job Blogs etc.
Design and Performance Improvement of Microstrip Patch Antenna Using Graphene Material for Communication Applications
(2021 IEEE 11th IEEE Symposium on Computer Applications & Industrial Electronics (ISCAIE), IEEE, 2021-05-26) Mollah, Mohammad Sarwar Hossain; Faruk, Omar; Hossain, Md. Selim; Islam, Md. Tarequl; Shafi, A.S.M.; Molla, M. M. Imran
In this paper, we discuss the process to fabricate a microstrip patch antenna by using graphene as a substrate material. Ours is the age of modern technology. Wireless communication is one of them. In wireless communication, graphene is widely used in the twenty-first century. Microstrip patch antenna provides better performance and better anticipation compared to other antennas. Microstrip patch antennas are more preferable compared to others because of their low cost, small size, and high performance. The graphene has a reconfigurable surface conductivity that can be tuned to operate at the desired frequencies. The main concept we focus on here to locate the best feed point of a microstrip patch antenna. This paper represents a graphene-based microstrip patch antenna. It has a 2.45 GHz resonant frequency for wireless communication. Here we use CST STUDIO SUITE 2017 software for designing and simulation our antenna. It shows the voltage standing wave ratio (VSWR), return loss, H-plane radiation pattern, and input impedance. The simulation output result shows a gain 6.801 dB and directivity of 7.302 dBi. It has return loss -23.673dB. Finally, we build up a design process of a graphene-based microstrip patch antenna.
Feature Selection and Prediction of Heart Disease Using Machine Learning Approaches
(Proceedings of the 6th International Conference on Electrical, Control and Computer Engineering. Lecture Notes in Electrical Engineering, vol 842. Springer, Singapore. https://doi.org/10.1007/978-981-16-8690-0_83, 2023-03-09) Mollah, M. M. Imran; Islam, Md. Sakirul; Shafi, A. S. M.; Alam, Mohammad Khurshed; Islam, Md. Tarequl; Jui, Julakha Jahan
Heart Disease (HD) is the world's most serious illness that seriously impacts human life. The heart does not push blood to other areas of the body in cardiac disease. For the prevention and treatment of cardiac failure, accurate and timely diagnosis of heart disease is critical. The diagnosis of cardiac disease has been considered via conventional medical history. Non-invasive approaches like machine learning are effective and powerful to categorize healthy people and people with heart disease. In the proposed research, by using the cardiovascular disease dataset, we created a machine-learning model to predict cardiac disease. In this paper, it is capable of recognizing and classifying the heart disease patient from healthy people by using three standard machine learning algorithms: Ran-dom Forest (RF), Support Vector Machine (SVM) and K-Nearest Neighbor (KNN). In addition, the ROC/AUC curve is calculated for each classification al-gorithms. In the proposed scheme, we also used the feature selection algorithm to reduce dimensions over a qualified heart disease dataset. After that, the whole structure for the classification of heart disease has been created. On complete features and reduced features, the performance of the proposed approach has been verified. The decrease in features affects the accuracy and time of execution of the classifiers. With the selected features, the highest classification accuracy is obtained for the KNN algorithm is about 93%, with a sensitivity is 0.9750 and specificity is 0.8529. Therefore, with the complete features, the classification ac-curacy is about 91%.
Feature Selection and Prediction of Heart Disease Using Machine Learning Approaches
(Proceedings of the 6th International Conference on Electrical, Control and Computer Engineering. Lecture Notes in Electrical Engineering, vol 842. Springer, Singapore., 2022-01-09) Molla, M. M. Imran; Islam, Md. Sakirul; Shafi, A. S. M.; Alam, Mohammad Khurshed; Islam, Md. Tarequl; Jui, Julakha Jahan
Heart Disease (HD) is the world's most serious illness that seriously impacts human life. The heart does not push blood to other areas of the body in cardiac disease. For the prevention and treatment of cardiac failure, accurate and timely diagnosis of heart disease is critical. The diagnosis of cardiac disease has been considered via conventional medical history. Non-invasive approaches like machine learning are effective and powerful to categorize healthy people and people with heart disease. In the proposed research, by using the cardiovascular disease dataset, we created a machine-learning model to predict cardiac disease. In this paper, it is capable of recognizing and classifying the heart disease patient from healthy people by using three standard machine learning algorithms: Ran-dom Forest (RF), Support Vector Machine (SVM) and K-Nearest Neighbor (KNN). In addition, the ROC/AUC curve is calculated for each classification al-gorithms. In the proposed scheme, we also used the feature selection algorithm to reduce dimensions over a qualified heart disease dataset. After that, the whole structure for the classification of heart disease has been created. On complete features and reduced features, the performance of the proposed approach has been verified. The decrease in features affects the accuracy and time of execution of the classifiers. With the selected features, the highest classification accuracy is obtained for the KNN algorithm is about 93%, with a sensitivity is 0.9750 and specificity is 0.8529. Therefore, with the complete features, the classification ac-curacy is about 91%.
Manifesting a Mobile Application on Safety Which Ascertains Women Salus in Bangladesh
(International Journal of Electrical and Computer Engineering, Institute of Advanced Engineering and Science, 2019-04-30) Hossain, Md. Elias; Rahman, Md. Wahidur; Islam, Md. Tarequl; Hossain, Md. Selim; Hossain, Md. Selim
This paper reflects on the indemnity of women in our society. The proposed model ensures the embodiment of a mobile application. The algorithm, we developed for this model focuses the safety issues which is applicable to both inside as well as outside of the house for the women in Bangladesh. The solution of this problems can be done through some interrelated features such as i) SOS button pressing which ensures automatic calling, instant location tracking system through GPS of the phone and sending tracked location to all trusted numbers, automatically secrete video recording system ii) voice command detection which assures exact same features as SOS button pressing iii) phone shaking features serve user instant immunity by calling a trusted number. This research also assures experimented data analysis at Dhaka city based on respond time, the time it takes to arrive the SMS and Phone call and current location of the victim. Also do a short comparison among the most popular safety related mobile applications.
POSTNATAL DEVELOPMENT OF LIVER OF COBB 500 BROILER STRAIN UNDER SMALL SCALE FARMING CONDITION
(Chattogram Veterinary & Animal Sciences University, Khulshi,Chattogram, 2015-01) Islam, Md. Tarequl
The objective of this study was to investigate the postnatal development of liver in “Cob-500” broilers from day 1 to day 32. Four groups of Cob-500 broilers were taken at day 1, day 14, day 28 and day 32. Five apparently healthy broilers were taken in each group. They were killed in halal method, dissected in systemic way and liver were collected. Then their shape, size, weight of liver and diameter of hepatic lobule, number of hepatic lobule were recorded. Samples from different segments were prepared and stained with haematoxylin and eosin staining technique to study the histology under light microscope. The average length (mm), weight (gm) of liver and diameter (µm) of hepatic lobule, number of hepatic lobule were significantly higher in Cobb 500 at day 35than that at day28, day 14, and day 1.
QUALITY STUDY OF RADISH (Raphanus sativus.L) SEED cv. TASAKI MULA IN DINAJPUR AND RANGPUR DISTRICT
(HAJEE MOHAMMAD DANESH SCIENCE AND TECHNOLOGY UNIVERSITY, DINAJPUR., 2008-12) Islam, Md. Tarequl; Prof. Dr. Md. Mamunur Rashid
In total 45 seed samples of radish cv. Tasaki mula were randomly collected from 40 farmers of four upazillas (Birgonj, Kaharol, Badargonj and Taragonj) comprising 10 farmers from each of the upazilla and five companies (Molla seed company, Supreme seed company, Lal teer seed company, Metal seed company and Alamgir seed company) were collected from Dinajpur local seed market during the period of April to September 2007 for testing their quality and health status. In field study, the field emergence of farmer’s seed samples ranged from 53.70-61.40% and company’s seed samples were found 50.50-73.00%. The plant stand of farmer’s seed samples was found 37.20-44.40% and in company’s seed samples were found 33.50-58.00%. In laboratory study, the germination percentages were recorded 64.92-77.95% in farmer’s seed samples and 42.50- 85.00% in company’s seed samples. In case of apparently diseased seed 22.20- 64.00% were recorded in farmer’s seed samples and 22.07-39.75% in company’s seed samples. The vigor indexes were recorded 917.32-1220.70 in farmer’s seed samples and 531.68-1395.70 in company’s seed samples. The highest percentage of Alternaria infected seed was observed 25.30% in Taragonj upazilla’s seed sample and the lowest 22.40% in Birgonj upazilla’s seed samples, where the highest 22.50% Alternaria infected seed was recorded in Molla seed company’s seed sample and the lowest 17.25% was recorded in supreme seed company’s seed sample. Finally it may be concluded that, company seed samples were superior in quality than farmer’s seed samples regarding all parameters.
QUALITY STUDY OF RADISH (Raphanus sativus.L) SEED cv. TASAKI MULA IN DINAJPUR AND RANGPUR DISTRICT
(HAJEE MOHAMMOD DANESH SCIENCE AND TECHNOLOGY UNIVERSITY, DINAJPUR, 2008-12) Islam, Md. Tarequl; Prof. Dr. Md. Mamunur Rashid
In total 45 seed samples of radish cv. Tasaki mula were randomly collected from 40 farmers of four upazillas (Birgonj, Kaharol, Badargonj and Taragonj) comprising 10 farmers from each of the upazilla and five companies (Molla seed company, Supreme seed company, Lal teer seed company, Metal seed company and Alamgir seed company) were collected from Dinajpur local seed market during the period of April to September 2007 for testing their quality and health status. In field study, the field emergence of farmer’s seed samples ranged from 53.70-61.40% and company’s seed samples were found 50.50-73.00%. The plant stand of farmer’s seed samples was found 37.20-44.40% and in company’s seed samples were found 33.50-58.00%. In laboratory study, the germination percentages were recorded 64.92-77.95% in farmer’s seed samples and 42.50- 85.00% in company’s seed samples. In case of apparently diseased seed 22.20- 64.00% were recorded in farmer’s seed samples and 22.07-39.75% in company’s seed samples. The vigor indexes were recorded 917.32-1220.70 in farmer’s seed samples and 531.68-1395.70 in company’s seed samples. The highest percentage of Alternaria infected seed was observed 25.30% in Taragonj upazilla’s seed sample and the lowest 22.40% in Birgonj upazilla’s seed samples, where the highest 22.50% Alternaria infected seed was recorded in Molla seed company’s seed sample and the lowest 17.25% was recorded in supreme seed company’s seed sample. Finally it may be concluded that, company seed samples were superior in quality than farmer’s seed samples regarding all parameters.
Transparent Blockchain-Based Electronic Voting System
(Daffodil International University, 2022-02-24) Islam, Md. Tarequl; Hasan, Md. Sabbir; Sikder, Abu Sayed; Hossain, Md. Selim; Azad, Mir Mohammad
The research work scrutinizes an e-voting concept that is on the platform ethereum blockchain. Ethereum is a distributed computing platform that is free, open source with the functionality of smart contracts. By utilizing this depiction, it is feasible to originate engrossing scientific prominence which enables the thoughtful in sober fact collaboration occurring in the blockchain. E-voting is the most accepted worldwide because it is a tool that every moment signifies the democracy of the election. Consequently, most of the countries persevere to experiment and development of the e-voting process. Blockchain technology is responsible for a decentralized design that designates advanced data simultaneously among the P2P network barring a central database. At last, the experiment addressed the debilitation of the existent e-voting method and successfully fruitful blockchain technology to unravel that feebleness.