Browsing by Author "Islam, Mohammad Monirul"

Now showing 1 - 12 of 12

A Deep Learning Approach to Recognize Bangladeshi Shrimp Species
(Independent University, Bangladesh, 2023-07) Hasan, Md. Mehedi; Nishi, Jubiria Subrin; Habib, Md. Tarek; Islam, Mohammad Monirul; Ahmed, Farruk
Shrimp, the most popular shellfish in Bangladesh, is a good source of protein, minerals, vitamin D, and iodine that promote a healthy body and balanced nutrition. In Bangladesh shrimp is referred to as white gold. It consumes about 70% of exported agricultural food. In our country, about 56 species of shrimp are found. Most people do not know all of the species very well. Ordinary people even the fisherman are sometimes confused about different species because of looking like the same. To solve the problem in this work we introduced an intelligence mahine that can help people to concede Shrimp species accurately. We expect this work also help the export sector to differentiate the shrimp species monitoring. To achieve the goal, we build a custom CNN algorithm for image processing and feature extraction. We build three different CNN architectures and differentiate them by hyperparameter and number of convolutional layers. Model 1 and Model 3 both obtain an accuracy of 99.01%, however Model 3 was chosen as the final model for Computer Vision integration. Though both models generated the best accuracy why do we use model 3 as the final model? In this work, we will also describe with appropriate reason.
A Novel Compound Feature Based Driver Identification
(Daffodil International University, 2022-01-20) Khan, Md. Abbas Ali; Ali, Mohammad Hanif; Haque, AKM Fazlul; Islam, Md. Iktidar; Islam, Mohammad Monirul
Abstract: In today's world, it is time to identify the driver through technology. At present, it is possible to find out the driving style of the drivers from every car through controller area network (CAN-BUS) sensor data which was not possible through the conventional car. Many researchers did their work and their main purpose was to find out the driver driving style from end-to-end analysis of CAN-BUS sensor data. So, it is potential to identify each driver individually based on the driver's driving style. We propose a novel compound feature-based driver identification to reduce the number of input attributes based on some mathematical operation. Now, the role of machine learning in the field of any type of data analysis is incomparable and significant. The state-of-the-art algorithms have been applied in different fields. Occasionally these are tested in a similar domain. As a result, we have used some prominent algorithms of machine learning, which show different results in the field of aspiration of the model. The other goal of this study is to compare the conspicuous classification algorithms in the index of performance metrics in driver behavior identification. Hence, we compare the performance of SVM, Naïve Bayes, Logistic Regression, k-NN, Random Forest, Decision tree, Gradient boosting.
A study on social media addiction analysis on the people of Bangladesh using machine learning algorithms
(Scopus, 2024-10) Mim, Minjun Nahar; Firoz, Mehedi; Islam, Mohammad Monirul; Hasan, Mahady; Habib, Md. Tarek
: Social media has become a fundamental element of contemporary life, providing countless benefits but also posing substantial concerns. While technology improves connectedness and information exchange, excessive use raises issues about social and personal well-being. The emergence of social media addiction emphasizes its influence on everyday routines and mental health, with many people favoring online activities above vital tasks, resulting in real repercussions. Twitter, Facebook, and Snapchat have a significant impact on emotional well-being, adding to global rates of despair and anxiety. To measure the frequency of social media reliance, we studied data from 1,417 individuals using machine learning methods such as decision tree (DT) classifier, random forest (RF) classifier, support vector classifier (SVC), k-nearest neighbors (K-NN), and multinomial naive Bayes (NB). Understanding the behavioral patterns that drive addiction allows us to create tailored therapies to encourage healthy digital behaviors. This study highlights the critical necessity to address social media addiction as a complicated societal issue. Our major goal is to determine the amount of people who are addicted to social media.
A Study on Social Media Addiction Analysis on the People of Bangladesh Using Machine Learning Algorithms
(Institute of Advanced Engineering and Science (IAES), 2024-10-15) Mim, Minjun Nahar; Firoz, Mehedi; Islam, Mohammad Monirul; Hasan, Mahady; Habib, Md. Tarek
Social media has become a fundamental element of contemporary life, providing countless benefits but also posing substantial concerns. While technology improves connectedness and information exchange, excessive use raises issues about social and personal well-being. The emergence of social media addiction emphasizes its influence on everyday routines and mental health, with many people favoring online activities above vital tasks, resulting in real repercussions. Twitter, Facebook, and Snapchat have a significant impact on emotional well-being, adding to global rates of despair and anxiety. To measure the frequency of social media reliance, we studied data from 1,417 individuals using machine learning methods such as decision tree (DT) classifier, random forest (RF) classifier, support vector classifier (SVC), k-nearest neighbors (K-NN), and multinomial naive Bayes (NB). Understanding the behavioral patterns that drive addiction allows us to create tailored therapies to encourage healthy digital behaviors. This study highlights the critical necessity to address social media addiction as a complicated societal issue. Our major goal is to determine the amount of people who are addicted to social media.
An Economic Analysis of Crop Diversification in Northern Bangladesh
(University of Rajshahi, 2015) Islam, Mohammad Monirul; Hossain, Md. Elias
The strategy of practicing crop diversification (CD) has significant socio-economic and environmental implications for farm households in Bangladesh. Crop diversification contributes to food and nutrition intake for the households, employment generation for the rural people and sustainable management of available resources. Thus, the main objective of this study is to explore the state of CD and to investigate the determinants of CD in the study area. Moreover the study aims to analyze economic viability and profitability of CD in the context of northern Bangladesh. The study has measured the level of CD applying Entropy and Herfindahl indices. Tobit regression model has been used to identify the determinants of CD. Net return and benefit cost ratio (BCR) approaches have been employed to analyze the economic viability of CD. In addition, two-way ANOVA and independent sample t test have been carried out to compare the mean differences of some characteristics of the farms and farmers in the study area. Chi-square (χ2) test has also been used to test the association between CD and variations of districts and farm size. By random sampling technique, a total of 343 farms were selected from eight villages of four districts of which two from Rajshahi division and two from Rangpur division of northern Bangladesh. The study found that level of crop diversification in Bangladesh is very low, though it is increasing gradually with some fluctuations. Similarly, northern Bangladesh has made a remarkable progress in practicing crop diversification over the years. Most of the areas in northern Bangladesh produce varieties of crops like vegetables, pulses, spices, etc. including cereals. In the study area, on average, a farm produces 4.46 crops in a cropping year with maximum 17 crops. It is revealed that in the study area only one fourth of total farms are specialized which produce only rice and three fourths of total farms are diversified which produce multiple crops. Level of crop diversification in northern Bangladesh is higher compared to many other areas of Bangladesh. It is also found that likelihood of crop diversification increases with the increase in the household size, defragmentation of land, annual income of the farms and developed infrastructure. On the other hand, probability of diversification decreases with the increase of farm size, non-farm income of the family, irrigation intensity and training exposure. The study also found that growing non-rice crops like vegetables, pulses and spices, etc. offer higher profit than that of rice. Employment generation of non-rice crops like vegetables, spices etc. is also comparatively high. Considering all these aspects of crop production, it is found that economic viability of crop diversification is much higher than that of rice monoculture. As policy suggestions this study observes that government initiative towards increased practice of crop diversification is required. In this connection, government can extent supports for the farmers to increase aman production during the rainy season and cultivate non-rice crops during the Rabi season. In addition, to increase practice of crop diversification in Bangladesh, modernization of irrigation system, development of infrastructure, raising frequency of extension activities and specific training for the farmer, appropriate natural storage and processing techniques of perishable crops,are important.
Design and Development of SEMS - An IoT-based Smart Environment Monitoring System
(IEEE, 2023-10-26) Sharif, Mohammed Fahim Hasan; Rahman, Md. Ataur; Khan, Abbas Ali; Islam, Mohammad Monirul; Habib, Md. Tarek
The twenty-first century is known as the "Age of Science and Technology". By believing in the potential of technology to improve lives, people gain new experiences and come up with innovative innovations in response to how the global environment is changing as technology advances. With each passing day, the environment in our living space undergoes continuous changes. To address the crisis, a budget-friendly and beneficial environment monitoring system for the classroom was devised. This is an Internet of Things (IoT)-based initiative. To create a classroom monitoring system dubbed "IoT-Based Smart Environment Monitoring System," where Multi-purpose sensors, NodeMCU, a display, an alarm, Firebase, and IoT technology were employed. An Android-based user interface was developed for monitoring real-time temperature, humidity, gas, smoke, and other parameters. Thus, LPG gas, smoke, NH4, temperature, and humidity are detected and/or measured simultaneously with a user-friendly interface and a cheap cost.
IOT Based Temperature Control System of Home by Using an Android Device
(2021 1st International Conference on Emerging Smart Technologies and Applications (eSmarTA), IEEE, 2021-08-23) Foysal, Musfiqur Rahman; Hossain, Refath Ara; Islam, Mohammad Monirul; Sharmin, Shayla; Moon, Nazmun Nessa
This IOT-based architecture research project is created for people who are familiar with emerging smart technologies. This project is primarily based on controlling the voltage of AC-supported equipment and developing an automatic temperature ventilation system that can make a space fully temperate. Additionally, this will protect our appliances from overheating. Using the widely used Node MCU microcontroller and IP networking for remote access and control, this project aims to automate machines and appliances. You can also use an Android-based smartphone app to access these computers while you are not at work. Many electrical and appliances, such as lamps, fans, and refrigerators, can be controlled by an Android smartphone, which can also help against overheating. This technology is more valuable in today's world in business environments where temperature control is a big concern. The proposed voltage control scheme has been combined with products such as an AC lamp, an AC fan, and a DC cooling fan to demonstrate its feasibility and effectiveness.
Predicting Satisfaction of Online Banking System in Bangladesh by Machine Learning
(2021 International Conference on Artificial Intelligence and Computer Science Technology (ICAICST), IEEE, 2021-07-30) Shetu, Syeda Farjana; Jahan, Israt; Islam, Mohammad Monirul; Hossain, Refath Ara; Moon, Nazmun Nessa; Nur, Fernaz Narin
Online banking refers to using your smartphone, tablet, or another internet-connected computer to browse and access your bank account. It is quick and free, and it usually allows you to perform a variety of activities, such as paying bills and exchanging currency, without having to visit or call your branch. As a developing nation, Bangladesh is seeing an increase in online banking. People are still reliant on online banking because it makes a man's life much easier. During the Corona incident, the use of online banking increased at an unprecedented pace. Online banking services such as Rocket, bKash, and Nagad are now available in the region. While online banking makes life easier, third-party money laundering incidents do occur from time to time. As a result, some people are unhappy with online banking. However, some people say that they are happy with their online banking experience. This work tries to address this critique and give the right advice to the customer. Customer satisfaction and frustration with online banking have been predicted using Machine Learning techniques in this study. Seven traditional machine learning classification algorithms Logistic Regression, Random Forest, Naïve Bayes, support vector machine, Neural network, Decision tree, K nearest neighbor algorithms to complete this research work and find the concluded delimiter.
Relationship and Causality between Technology-intensive Trade and Poverty –A Panel ARDL and Granger Causality based Analysis
(Faculty of Business Studies, BUFT, 2021-08-01) Islam, Mohammad Monirul
Purpose: The purpose of this study is to identify whether trade in different sectors classified based on technology intensity has differential effects on poverty in emerging economies. The study classified trade into high technology (HT), medium technology (MT), low technology (LT), and periphery products using classified trade data collected from the UNcomtrade database. The study then examined whether the relationship and causality between trade in different sectors and poverty vary. Methodology: The study applies a panel ARDL model to identify the long-term and short-term between trade in different sectors and poverty as well as the VECM based Granger causality approach to find out the direction of causality between the variables. Findings: The results of the study support the view that the relationships and causality between technology-intensive trade compositions and poverty differ across measures of poverty and country groups. Trade-in any sector substantially raises the average income of the poorest quintile both in low growth and high growth developing countries but they have a differential effect on extreme poverty measured by poverty HCR in different countries. Limitations: The major limitation of the study is the unavailability of trade data. The trade data for emerging countries is not available for a long time and there are problems with missing data. Moreover, poverty and income data are not also available. Due to the unavailability of data, the study excludes some emerging countries from the analysis. Practical Implication: The results of the study would help to identify the effects of trade on alleviating poverty and formulate trade policies that would be pro-poor. The study also opens a new window for trade-poverty linkage research. Originality: This study is one of the unique approaches to look into the trade-poverty nexus from a different point of view. The results of the study evidence that trade in different sectors affects countries' poverty differently and thus urge research in this field in a broader scope.
Sentiment Analysis on Bangla Conversation Using Machine Learning Approach
(Daffodil International University, 22-06-20) Hassan, Mahmudul; Shakil, Shahriar; Moon, Nazmun Nessa; Islam, Mohammad Monirul; Hossain, Refath Ara; Mariam, Asma; Nur, Fernaz Narin
Nowadays, online communication is more convenient and popular than face-to-face conversation. Therefore, people prefer online communication over face-to-face meetings. Enormous people use online chatting systems to speak with their loved ones at any given time throughout the world. People create massive quantities of conversation every second because of their online engagement. People's feelings during the conversation period can be gleaned as useful information from these conversations. Text analysis and conclusion of any material as summarization can be done using sentiment analysis by natural language processing. The use of communication for customer service portals in various e-commerce platforms and crime investigations based on digital evidence is increasing the need for sentiment analysis of a conversation. Other languages, such as English, have well-developed libraries and resources for natural language processing, yet there are few studies conducted on Bangla. It is more challenging to extract sentiments from Bangla conversational data due to the language's grammatical complexity. As a result, it opens vast study opportunities. So, support vector machine, multinomial naïve Bayes, k-nearest neighbors, logistic regression, decision tree, and random forest was used. From the dataset, extracted information was labeled as positive and negative.
University student's mental stress detection using machine learning
(Daffodil International University, 2023-09-23) Firoz, Mehedi; Islam, Mohammad Monirul; Shidujaman, Mohammad; Islam, Ashraful
University students are especially susceptible to the negative effects of mental stress in today's environment, which is a serious issue overall. A great deal of pressure is now being placed on a period of life that was traditionally considered to be the most carefree. People in today's culture are exposed to increasingly high levels of mental stress, which has been related to a broad variety of health problems, such as depression, suicide, heart attacks, and strokes. Because of this, in order to primarily extract, for the purposes of this research, the mental stress ratings of university students, we applied a total of six distinct machine learning methods. The Decision Tree Classifier, the Random Forest Classifier, the SVC, the KNN Classifier, the Multinomial NB, and the K-Nearest Neighbors Regressor are only some of the machine learning algorithms that are available. This investigation's principal objective is to determine the percentage of students who are struggling to deal with emotional pressure in their lives. The dataset was put together by hand with paper and manual information obtained from a survey. Out of the six distinct classification strategies, the Decision Tree Classifier and the Random Forest Classifier both achieved a test result of 0.99, which is the maximum score that can be achieved.
University Student's Mental Stress Detection Using Machine Learning
(Independent University, Bangladesh, 2023-06) Firoz, Mehedi; Islam, Mohammad Monirul; Shidujaman, Mohammad; Islam, Ashraful; Habib, Md. Tarek
University students are especially susceptible to the negative effects of mental stress in today's environment, which is a serious issue overall. A great deal of pressure is now being placed on a period of life that was traditionally considered to be the most carefree. People in today's culture are exposed to increasingly high levels of mental stress, which has been related to a broad variety of health problems, such as depression, suicide, heart attacks, and strokes. Because of this, in order to primarily extract, for the purposes of this research, the mental stress ratings of university students, we applied a total of six distinct machine learning methods. The Decision Tree Classifier, the Random Forest Classifier, the SVC, the KNN Classifier, the Multinomial NB, and the K-Nearest Neighbors Regressor are only some of the machine learning algorithms that are available. This investigation's principal objective is to determine the percentage of students who are struggling to deal with emotional pressure in their lives. The dataset was put together by hand with paper and manual information obtained from a survey. Out of the six distinct classification strategies, the Decision Tree Classifier and the Random Forest Classifier both achieved a test result of 0.99, which is the maximum score that can be achieved.