Browsing by Author "Islam, Md. Monirul"

Now showing 1 - 20 of 29

A Comprehensive Review of Predictive Analytics Models for Mental Illness Using Machine Learning Algorithms
(Elsevier, 2024-06-17) Islam, Md. Monirul; Hassan, Shahriar; Hassan, Shahriar; Akter, Sharmin; Jibon, Ferdaus Anam; Sahidullah, Md.
Our emotional, psychological, and social well-being are all parts of our mental health, influencing our thoughts, emotions, and behaviors. Mental health also influences how we respond to stress, interact with others, and make good or bad decisions. There has been growing interest in the use of machine learning for the early detection of mental illness. This study reviews the machine learning models, algorithms, and applications for the early detection of mental disease, particularly emphasizing the data modalities. We further propose a comprehensive methodology for assessing mental health that synergistically combines social media monitoring, data analytics from wearable devices, verbal polls, and individualized support. We provide an overview of the field’s current state, highlight the potential benefits and challenges of using machine learning in mental health care, and a new taxonomy of mental disorders issues based on five domains of data types. We review existing research on using machine learning to detect and treat mental illness and discuss the implications for future research. Finally, the value of this work lies in its potential to provide a fast and accurate method for predicting the mental health status of a person, which may assist in the diagnosis and treatment of mental illness.
A real-time dataset of air quality index monitoring using IoT and machine learning in the perspective of Bangladesh
(Scopus, 2024-08-30) Islam, Md. Monirul; Jibon, Ferdaus Anam; Tarek, M. Masud; Kanchan, Muntasir Hasan; Shakil, Shalah Uddin Perbhez
This paper produces a real-time air quality index dataset of three places named Kuril Bishow Road, Uttara, and Tongi in Dhaka and Gazipur City, Bangladesh. The IoT framework consists of MQ9, MQ135, MQ131, and dust or PM sensors with an Arduino microcontroller to collect real data on sulfur dioxide, carbon monoxide, nitrogen dioxide, ozone, particle matters 2.5 and 10 µm. The data is stored in an Excel file as a comma-separated file and after that, authors applied regression type and classification type machine learning algorithms to analyze the data. The dataset consists of 11 columns and 155,406 rows, where sulfur dioxide, carbon monoxide, nitrogen dioxide, ozone, and particle matter 2.5 and 10 are recorded where AQI is marked as the target variable and the others are indicated as independent variables. In the dataset, AQI is categorized into five classes named Good, satisfactory, Moderate, Poor and Very Poor. After experimental results, it is seen that two places including Uttara and Kuril are comparatively suitable for Air Quality among the three places as well as the Random Forest algorithm outperforms the models. The study describes details of the embedded system's hardware as well. This dataset will be beneficial for environmental researchers to use to analyze the air quality.
A Representation of the Congestion Situation Including Saturation Flow Analysis Adjacent to Daffodil International University
(Daffodil International University, 2020-01-08) Sarkar, Md. Nafiul Islam; Hemal, Afrose-Al-Raza; Islam, Md. Monirul
Traffic is now a growing concern in most cities around the world. Inadequate traffic control wastes time and energy and causes harmful carbon emissions, road accidents and many economic problems. This thesis focuses on a cooperative traffic control framework to optimize travel time for better uniform traffic flow across multiple sections of Mirpur Road. To reach the target, we first select three segments from Mirpur Road. The number of vehicles up and down in each section will be calculated for the three scheduled times of the day. We need to count traffic to get a better picture of the traffic scene. We will then convert the calculated data into a PCU (passenger car unit) based on a standard reference. We will determine the capacity of the road for the selected sections and we will also determine the saturation flow for the selected intersections. Lastly, a comparison will be made between our roadway capacity and saturation flow. Then compare the output which will help to represent the current traffic conditions of the Mirpur road. However, while data computation may not be decent enough to illustrate the actual situation, it may be helpful to have a true scale of information to help traffic computation lead to digitalization. Thus, in future studies this approach can be used to determine the method of automation of the traffic signals.
A STEGANOGRAPHIC APPROACH IN VIDEO WITH ATTACK DETECTION
(Daffodil International University, 2010-07-01) Alam, Md. Golam Rabiul; Islam, Md. Monirul; Naznen, Tahmina; Niger, Tasnim; Sharmin, Shanjida
Steganography is the art and science of writing hidden messages in such a way that no one apart from the sender and intended recipient even realizes there is a hidden message. Studies have shown that Human Vision Systems (HVS) is unable to detect changes in uncorrelated areas of the digital media, due to the complexity of such areas, where it is easy to detect changes in correlated areas. Security and quality are two important issues of steganography. In this paper we have introduced a model of steganography with attack detection using Least Significant Bit (LSB) hiding. Here we have used a video file as a cover media to hide a message. In our algorithm error detection code is used, so that receiver will be able to detect if there is any alteration in the cover media and retrieve the message.
Analysis on Wavelet Based Image Compression and Denoising for Medical Application
(Daffodil International University, 2019-10-15) Sajib, D. K. Sheakh; Islam, Md. Monirul
The medical images carry very sensitive data in order to detect the abnormalities in the organ of a body. These images contain huge information and the images size is too large to store the images, that’s why it requires huge space causing an extra cost and the images are affected by different noises during transmission. The bandwidth management can grounds the extra cost, so compression can be the solution to overcome the drawbacks. The aims of the project is to compress the medical image in a popular existing method of Wavelet 2D analysis. The project is divided into 2 parts as the noisy image analysis and de-noised image analysis. The noises are added in the image and de-noised images are considered to analysis the actual susceptibility to the actual images. The noisy images and de-noised images are analyzed in the Wavelet 2D and different variations are observed by their statistical analysis. The compression ratio of different compression threshold methods are also compared in the result section and performance of different filter has also been observed
Assessing the economic viability and factors affecting farmer adoption of black soldier fly larvae as broiler feed in Bangladesh: a comparative analysis
(Discover Agriculture, 2024-10) Roy, Joy Kumar; Ahmed, Jasim Uddin; Mannaf, Maksuda; Jannat, Arifa; Islam, Md. Monirul
Despite its impressive economic growth, Bangladesh faces a persistent malnutrition challenge, costing over US$1 billion annually. The broiler industry plays a vital role in addressing nutritional needs by providing essential protein through meat and eggs. However, small and medium enterprises (SMEs) in this sector struggle with high feed prices, impacting their profitability and growth. Black Soldier Fly Larvae (BSFL) offers a sustainable and cost-effective alternative to conventional poultry feed, addressing both rising costs and environmental impacts. This study examined different aspects of BSFL, such as broiler feed, and farmers' perceptions of them in some selected areas of the Sylhet region of Bangladesh. A total of 60 respondents from three subdistricts in Sylhet district were selected using the purposive sampling technique. Data were analyzed through descriptive statistics, discriminative power value, binary logistic regression model, and profitability equation. Among the respondents, 70% (42) had a favorable attitude toward BSFL, and 30% (18) had a highly favorable attitude towards BSFL. Among eight socioeconomic attributes examined for the likeliness of adopting BSFL as broiler feed, the respondents' average income (p < 0.01), years of schooling (p < 0.05), and years of broiler farming experience (p < 0.01) were found to be significant. Further, farms using 50% BSFL and 50% traditional feed had a net return of BDT (Bangladeshi Taka) 35,045.67 (USD 419.71), higher than those using traditional feed, which had a net return of BDT 29670.67 (USD 355.38). Further, farms using 50% BSFL and 50% traditional feed had a benefit–cost ratio (BCR) of 1.16, compared to other farms with a BCR of 1.11. The study also found some problems causing slow growth in the adoption rate of BSFL in the study region, such as lack of training programs, extension campaigns, the uncertainty of input supply, and financial assistance. The study suggests making adequate measures to raise awareness about the profitability of BSFL as broiler feed, conducting training at the root level, and making inputs easily available to farmers.
Benign and Malignant Oral Lesion Image Classification Using Fine-Tuned Transfer Learning Techniques
(MDPI Publications, 2023-11-01) Islam, Md. Monirul; Alam, K. M. Rafiqul; Uddin, Jia; Ashraf, Imran; Samad, Md Abdus
Oral lesions are a prevalent manifestation of oral disease, and the timely identification of oral lesions is imperative for effective intervention. Fortunately, deep learning algorithms have shown great potential for automated lesion detection. The primary aim of this study was to employ deep learning-based image classification algorithms to identify oral lesions. We used three deep learning models, namely VGG19, DeIT, and MobileNet, to assess the efficacy of various categorization methods. To evaluate the accuracy and reliability of the models, we employed a dataset consisting of oral pictures encompassing two distinct categories: benign and malignant lesions. The experimental findings indicate that VGG19 and MobileNet attained an almost perfect accuracy rate of 100%, while DeIT achieved a slightly lower accuracy rate of 98.73%. The results of this study indicate that deep learning algorithms for picture classification demonstrate a high level of effectiveness in detecting oral lesions by achieving 100% for VGG19 and MobileNet and 98.73% for DeIT. Specifically, the VGG19 and MobileNet models exhibit notable suitability for this particular task.
Design and Implementation of an IoT-based Home Automation System
(IEEE, 2021) Sadi, Md. Samin Al; Islam, Md. Monirul; Rumman, Tanvir Ahmed; Parvez, Md. Shahariar; Ahmed, Abir; Hazari, Md. Rifat
Home automation system has grown in popularity in recent years as technology has made day-to-day life easier. Almost everything has been auto-mated and digitalized. This paper has developed an automated system that inter-connects different sensors such as passive infrared (PIR), smoke, gas, and flame, and different onboard sources such as camera, many different home appliances, or user commands. The main focus of this work is to control appliances remotely through the internet of things (IoT). Different sensors and sources provide signals to the ATmega2560 microcontroller. After processing, signals are sent to control various connected devices and appliances through relays. Finally, the devices are being controlled through the Blynk app, which is an IoT-based mobile app. The proposed home automation system incorporates face detection system, keypad security system, and doctor calling feature.
Design and Implementation of an IoT-based Home Automation System
(2nd International Conference on Computing Advancements, 2023-03) Sadi, Md. Samin Al; Islam, Md. Monirul; Rumman, Tanvir Ahmed; Parvez, Md. Shahariar; Ahmed, Abir; Hazari, Md. Rifat
Home automation system has grown in popularity in recent years as technology has made day-to-day life easier. Almost everything has been auto-mated and digitalized. This paper has developed an automated system that inter-connects different sensors such as passive infrared (PIR), smoke, gas, and flame, and different onboard sources such as camera, many different home appliances, or user commands. The main focus of this work is to control appliances remotely through the internet of things (IoT). Different sensors and sources provide signals to the ATmega2560 microcontroller. After processing, signals are sent to control various connected devices and appliances through relays. Finally, the devices are being controlled through the Blynk app, which is an IoT-based mobile app. The proposed home automation system incorporates face detection system, keypad security system, and doctor calling feature.
Design and Implementation of an IoT-based Home Automation System: IoT-based Home Automation System
(ACM, 2022-08-11) Said, Md. Samin Al; Islam, Md. Monirul; Rumman, Tanvir Ahmed; Parvez, Md. Shahariar; Ahmed, Abir; Hazari, Md. Rifat
Home automation system has grown in popularity in recent years as technology has made day-to-day life easier. Almost everything has been auto-mated and digitalized. This paper has developed an automated system that inter-connects different sensors such as passive infrared (PIR), smoke, gas, and flame, and different onboard sources such as camera, many different home appliances, or user commands. The main focus of this work is to control appliances remotely through the internet of things (IoT). Different sensors and sources provide signals to the ATmega2560 microcontroller. After processing, signals are sent to control various connected devices and appliances through relays. Finally, the devices are being controlled through the Blynk app, which is an IoT-based mobile app. The proposed home automation system incorporates face detection system, keypad security system, and doctor calling feature.
Economic Growth and Environmental Pollution Nexus in Bangladesh
(Taylor & Francis Group, 2022-01-10) Islam, Md. Monirul; Alam, Md. Mahmudul; Ahmed, Faroque; Al-Amin, Abul Quasem
The paper reports a re-examination of the environmental Kuznets curve (EKC) hypothesis for Bangladesh; considering economic growth and greenhouse gas (GHG) emissions (such as CO2, CH4, and N2O). The autoregressive distributive lag (ARDL) model and VAR-based innovative accounting approach (IAA) with the combination of Variance Decomposition and Impulse Response Function are used to check cointegration among the variables using data from 1976 to 2014. This approach is specifically employed for variance analysis in order to measure causal association and regressors’ shock to dependent variables. The EKC hypothesis is not supported because there is a positive association between economic growth and pollutants (CO2 and CH4 emissions) over time. However, the EKC is valid for N2O emissions. IAA causal analysis reveals a bilateral causative relationship between GDP and CO2 emissions, as well as a unilateral causal relationship between CH4 emissions and GDP. Trade liberalisation, urbanisation, and financial liberalisation do not necessarily improve or save the natural environment. Bangladesh needs to use renewable energies and cut GHG emissions by abandoning fossil fuels.
IMPACT OF KNOWLEDGE AND LEADERSHIP QUALITY ON USER SATISFACTION: INVESTIGATING THE SITUATION OF SELECTED ACADEMIC LIBRARIES OF BANGLADESH
(© University of Dhaka, 2025-11-05) Islam, Md. Monirul
The assessment of knowledge and leadership quality is crucial in ensuring the effectiveness of university library services, as these factors directly influence user satisfaction and the library performance. There are no specific efforts to evaluate how leadership quality and knowledge affect user pleasure. This study examined how library professionals' knowledge and leadership quality influence user satisfaction and identified variations and gaps in leadership quality across user and university categories. A Structural Equation Modeling (SEM) was developed where knowledge competency, technical competency, negotiation skill, visionary, and responsiveness were used as independent variables and user satisfaction as the dependent variable. User and university types computed individual differences in leadership quality and adequacy, superiority, and realistic gaps in leadership quality by ANOVA. Several statistical methods supported sampling adequacy, reliability, validity, and fitness of the SEM model that attained specific objectives and hypotheses. The SEM approach was established as significant and indicated that leadership quality dimensions positively impact user satisfaction. The study found that technical competency (beta coefficient = 0.331, t-value= 2.21 and p-value < 0.027) and responsiveness (beta coefficient = 0.445, t-value = 3.954, p-value = < 0.000) dimensions have significant positive impacts on user satisfaction. ANOVA indicated that the users of private university libraries get significantly qualified leadership performance. The study recommended maintaining technical competency, emphasizing responsiveness approach, improving knowledge competency, increasing negotiation skill, enhancing visionary approach, reducing realistic gap in leadership quality. The authorities would be benefitted from this study in planning and executing library leadership performance to satisfy their users. More studies would be expected to make it a well accepted model that will prompt further research in academic libraries locally and globally.
Internet of Things in Pregnancy Care Coordination and Management: A Systematic Review
(MDPI Publications, 2023-11-23) Hossain, Mohammad Mobarak; Kashem, Mohammod Abul; Islam, Md. Monirul; Sahidullah, Md.; Mumu, Sumona Hoque; Uddin, Jia; Aray, Daniel Gavilanes; Diez, Isabel de la Torre; Ashraf, Imran; Samad, Md Abdus
The Internet of Things (IoT) has positioned itself globally as a dominant force in the technology sector. IoT, a technology based on interconnected devices, has found applications in various research areas, including healthcare. Embedded devices and wearable technologies powered by IoT have been shown to be effective in patient monitoring and management systems, with a particular focus on pregnant women. This study provides a comprehensive systematic review of the literature on IoT architectures, systems, models and devices used to monitor and manage complications during pregnancy, postpartum and neonatal care. The study identifies emerging research trends and highlights existing research challenges and gaps, offering insights to improve the well-being of pregnant women at a critical moment in their lives. The literature review and discussions presented here serve as valuable resources for stakeholders in this field and pave the way for new and effective paradigms. Additionally, we outline a future research scope discussion for the benefit of researchers and healthcare professionals.
KitBag: Courier Service Management Application
(Daffodil International University, 2022-01-30) Islam, Md. Monirul; Sarowal, Md.
In this project we are trying to build up a digital courier service platform. Where our customer can hand over their product in any bkash, Rocket and Nagad Agent point which product they want to deliver through our system. And here our customer can choose two ways to deliver their product these are our personal delivery man or local delivery man. If the customer chooses to deliver their product by our personal delivery man, then they have to pay a bit more than local delivery man. And if any customer chooses a local delivery man to deliver their product, then the delivery cost will be as minimum as possible. And we are determining to ensure the security of product delivery. Our project idea is so much unique because this type of project isn’t found in our country. As here our delivery point is almost everywhere and our delivery man could be any local person so the delivery time and delivery cost will be as minimum as possible. So, our customer will be happy as they can deliver their product with very minimum time and minimum cost. Besides our customer can track their product through our system. In any time, they can check out the present status of their product. So, this service will be so much satisfactory. Also, the customer can pick up their product from their nearest bKash, Rocket and Nagad agent point in near market. Also, any type of traveler will be so much benefited as they earn money by carrying product into their extra bag and luggage at the time of travel. As a result, their journey cost and tour cost will be reduced. Beside our county bus and truck driver, helper and supervisor can earn extra money by delivery product at their journey time. And their earing will be increased as they used to travel every day.
MANAGING THE SEDIMENT LOAD IN TIDAL RIVER MANAGEMENT (TRM)
(R&D Wing, MIST, 2016-12) Navera, Umme Kulsum; Islam, Md. Monirul
Bangladesh has a large number of tidal rivers in the South-West region which are characterized by erosion and sedimentation and all of them discharges into the Bay of Bengal. Tidal River Management (TRM) which is a concept based on indigenous knowledge and sediment management practice is one of the key factors for river basin management in this region. Raising of low lying land inside the beel (depressed area) and maintaining proper drainage capacity of the rivers are the two main objectives of Tidal River Management (TRM) process. It was observed in the previous TRM practices in Beel Kedaria and East Beel Khuksia of South-West regionthat the sedimentation inside the beels were not uniform due to technical and operational problems inthe TRM process. The present practice of TRM operation, a link canal is constructed to connect the beel with the river. This results in sediment deposition at the mouth of the link canal, preventing uniform sedimentation inside the wider area of beel. Technical feasibility of this option has been assessed in this paperby a cohesive sediment transport model namely MIKE21 FM.The option which has been selected for sediment management inside the beel during TRM operation is such that one link has been constructed to connect the beel with the river. Deposition volume in Beel Baruna in Jessore district has been assessed. From the simulation results, it has been found that sedimentation inside the beel is not uniform with the present TRM practice. The deposition volume shows linear variation from 0.68Mm3 to 2.28Mm3 through the four consecutive years but the deposition pattern within the beel is non-uniform. The sediment deposition continues to increase even after four years in all areas. So it is necessary to implementa better functional technique for uniform and effective sedimentation inside the beel areas to overcome the long term drainage congestion and water logging problem from the study.
Mobile Commerce and Mobile Payment: A Study on Islamic Perspective
(CRP, International Islamic University Chittagong, Bangladesh, 2010-12) Islam, Md. Monirul; Masum, Abdul Kadar Muhammad
Electronic commerce, very important part of Information and Communication Technologies (ICT), is one of the most common business terms in use in 21st century. Developed countries are more popular because of their rapid growth of ICT, e-commerce and online transaction. But in developing or under develop countries the scenario is different. Technical laggings, dearth of infrastructure, infeasibility of the existing frameworks and people apathy are the main reasons behind this. There are several alternative ways of e-commerce and online transaction. Mobile payment, a way of online transaction, may be beneficial way of payment for developing countries because of its mobile network infrastructure. In this paper, a model of electronic payment system for M-Commerce has been proposed and analyzed the security for the system. This proposal may be suitable for developing countries where mobile phones are available but other e-payment tools like debit and credit cards are not much available. It also identifies what Islam has to say about our current use of M-Commerce and the way Islam can offer guidance for its use in the future. The paper also touches on the conditions and criteria that must be met in order to make an M-Commerce transaction acceptable under Islamic perspective.
Monitoring Water Quality Metrics of Ponds With IoT Sensors and Machine Learning To Predict Fish Species Survival
(Elsevier, 2023-10-15) Islam, Md. Monirul; Kashem, Mohammod Abul; Alyami, Salem A.; Moni, Mohammad Ali
Aquaculture involves cultivating various marine and freshwater aquatic creatures within regulated environments. Monitoring the aquatic environmental conditions in real-time is crucial for successful fish farming. The Internet of Things (IoT) offers significant potential for real-time monitoring, and this paper introduces an IoT framework designed for efficient monitoring and effective control of various water-related aquatic environmental parameters. The proposed system is implemented as an embedded system utilizing sensors and an Arduino microcontroller. In cultivating pond water, diverse sensors such as pH, temperature, and turbidity sensors are deployed, with each sensor connected to an Arduino Uno-based microcontroller board. These sensors collect data from the water, which is then stored as a CSV file in an IoT cloud platform called ThingSpeak through the Arduino microcontroller. To gather data for analysis, we conducted measurements across five ponds, varying in size and environmental conditions. After getting the real-time data, we compared our experimental results with the standard reference values. As a result, we could take the decision of whether a pond is suitable for cultivating fish or not. After that, we labeled the data with 11 fish categories: Katla, sing, prawn, shrimp, rui, tilapia, pangas, karpio, magur, silver carp, and koi. The data was analyzed using 10 machine learning (ML) algorithms, including J48, Random Forest, K Nearest Neighbors (K-NN), K*, Logistic Model Tree (LMT), Reduced Error Pruning Tree (REPTree), Jumping Rule Inference with Pruned Search (JRIP), Partial Decision Trees (PART), Decision Table, and Logit boost. After experimental analyses, it was discovered that only three of the five ponds were ideal for fish farming, and those three ponds only met the required standards for pH, Temperature, Turbidity, and Conductivity. Among the state-of-art machine learning algorithms, Random Forest achieved the highest score of performance metrics as accuracy 94.42%, kappa statistics 93.5%, and Avg. TP Rate 94.4%. In addition, we calculated the Biochemical Oxygen Demand (BOD), Chemical Oxygen Demand (COD), and Dissolved Oxygen (DO) for one scenario. This study includes prototype hardware details of the proposed IoT system.
PREVALENCE OF PPR AND ITS TREATMENT IN SHEEP AND GOAT OF SATKHIRA DISTRICT IN BANGLADESH
(Chattogram Veterinary & Animal Sciences Universiy, KHULSHI, CHITTAGONG-4225., 2011-02) Islam, Md. Monirul
The study was conducted at Thana Veterinary Hospital, Shyamnagar, Satkhira from 26th June to 25th August 2010, to find out the prevalence of PPR and its treatment in sheep and goat. During the study period a number of 223 diseased goats were examined of which 111 (49.78%) peste des petits ruminants (PPR) and 80 diseased sheep were examined of which 24 (30%) peste des petits ruminants (PPR); cases were diagnosed on the basis of clinical sings and gross pathological lesions. Dull and depression, rough hair coat, dyspnoea, diarrhoea, swollen and erosion of lip and occulonasal discharges were the common findings during clinical examination of PPR patients. The gross pathological lesions found during postmortem examinations were consolidated pneumonic lungs, hemorrhagic trachea, necrosis and hemorrhagic plugs in caecum and characteristics zebra striping in the mucosa of colon. Goats were more susceptible (49.78%) than sheep (30%). Male goats were more susceptible (58.52%) than female goats (41.48%). Mortality rate in goat is more (58.55%) than sheep (45.83). 7-12 months of age was found more prone (in sheep 66.67% and in goat 55.86%) to PPR than other age. Black Bengal goats were more susceptible (55.41%) than Jamunapari goats (36.36%). The combined therapy of atropine, antihistaminic aided antibiotic + fluid therapy is more (56.06%) effective than Atropine aided antibiotic + fluid therapy (33.33%) or Antihistaminic aided antibiotic + fluid therapy (29.17%).
Real-Time Dataset of Pond Water for Fish Farming Using IoT Devices
(Elsevier, 2023-11-04) Islam, Md. Monirul
This paper introduces a real-time water quality dataset of five ponds for fish farming obtained through an IoT frame- work for monitoring the aquatic environmental conditions. It utilizes sensors and an Arduino microcontroller to col- lect data on pH, temperature, and turbidity in pond water in Jamalpur District, Bangladesh. The data is stored in an IoT cloud platform named ThingSpeak and analyzed using 10 machine learning algorithms. The dataset consists of 4 columns and 40,280 rows, where pH, temperature, turbid- ity, and fish are recorded. Fish represents the target variable, while the others serve as independent variables. Within the dataset, there are 11 distinct fish categories including sing, silver carp, Katla, prawn, karpio, shrimp, rui, pangas, tilapia, magur, and koi. Results showed that only three ponds are suitable for fish farming among five ponds and the Random Forest algorithm performs the best. The study also includes details of the IoT system’s hardware. This dataset will be use- ful for researchers and fish farmers to predict fish survival.