Browsing by Author "Islam, Md Rakibul"

Now showing 1 - 7 of 7

A methodological analysis of consumption patterns and anomaly detection in prepaid and postpaid metering systems: an N-BEATS-driven predictive modeling approach
(BRAC University, 2024-10) Islam, Nusaba; Debnath, Partha; Islam, Md Rakibul; Kamrul, Awon Bin; Sheakh, Md Rishat; Anwar, Md. Tawhid; Ahmed, Md. Sabbir
The introduction of the prepaid metering system has caused severe dissatisfaction among the masses, claiming that there was a noticeable spike in the bills of their monthly electricity bill. This issue was addressed in this thesis paper through a rigorous investigation, comparing the existing prepaid metering system with the previously used post-paid metering system to identify the underlying causes of this discrepancy. Related datasets were collected through the Dhaka Power Distribution Company (DPDC), mainly focusing on the Paribagh, the first area introduced with this intelligent prepaid meter system. The dataset includes 22,000 individual customers’ billing information, and then a robust survey was conducted to accumulate 1797 households’ information on appliance usage, family size, and other relevant factors. To predict the prepaid and postpaid consumption trends, we incorporated the deep learning model N-BEATS, which efficiently forecasts time series data. We also conducted several operations on our prepaid and postpaid data to better address the issue. Moreover, we deployed the isolation forest model to address the anomalies that would align with the underlying cause of the dissatisfaction of the masses. To assist in validating our survey data, we deployed several data validation methods, such as the Kolmogorov-Smirnov test, and Pearson’s correlation. Furthermore, Pearson’s correlation technique has been used to demonstrate the correlation between prepaid and postpaid appliance usage. With N-BEATS providing a crystal difference between prepaid and postpaid data, Isolation Forest also directed us to the irregularities that may lean towards the reason for the increased billing. To address customers’ growing concerns, the authority might find our findings fruitful in solving the irregularities to ensure a seamless transition to the prepaid system. This research also illustrates actionable recommendations to ensure a satisfactory customer experience with transparent energy billing.
Analysis and Finding Problem Solar Rooftop System (SRS) Under Dhaka Power Distribution Company (DPDC) of Bangladesh
(Daffodil International University, 2018-12) Ali, Md Nawshad; Islam, Md Rakibul
Daily headlines make everyone aware of the dangerous long-term effects of power generation from the fossil fuels. It is widely believed that continuing to depend on fossil fuels to generate electricity can cause serious environmental problems. Moreover, fossil fuels are finite in amount and cost a lot of money as well. Hence, renewable energy is a potential solution to meet up electricity demand for the developing countries like Bangladesh. Among all the renewable technologies, solar photo voltaic (PV) is the most potential, favorable and promising one which converts solar energy into electrical energy, including or excluding battery backup. Although solar technology has nearly been successful in rural areas where most of the technologies are adopted based on Solar Home System (SHS), it has not yet been effective in urban areas after the imposed rule of meeting 3% of light fan load of a building. We have investigated the installed solar rooftop of 86 houses in Narayanganj, where the solar system of most of the houses were found in active. Among them only 50 systems are active. In this thesis the overall analysis of urban solar prospect has been done in three layers based on this investigation. A comparable discussion on cost efficiency of different solar panels has been given depending on amounts of loads being run. Efficient batteries are modeled by HOMER in context of Bangladesh to improvise PV systems. A cost analysis has been performed by software HOMER for different types of watt peak ranges. Apart from these, a renovated design of solar system has been proposed to make urban rooftop solar installation effective and successful.
Analysis of Railway Passengers’ Satisfaction with Service Quality:
(Daffodil International University, 2025-12-22) Islam, Md Rakibul; Anam, Md Sadman Sakib
Train platforms play a vital role in the rail transport system. A range of platform-related services available at railway stations contribute significantly to passenger satisfaction. This research utilized survey questionnaires at Kamalapur and Ishwardi railway stations to assess how content passengers were with these amenities. The study employed factor analysis as its analytical method to identify the primary factors that influence passengers’ satisfaction with service quality. Data collection was conducted through an econometric analysis involving passenger surveys. Findings were based on passenger responses regarding service quality across seventeen major categories. The study revealed that key factors—such as the availability of refreshments and food, ticketing services, reservation chart visibility, lighting, restroom hygiene, staff behavior, schedule accuracy, and overall cleanliness—collectively accounted for 51.102% of the explained variance in satisfaction levels. A satisfaction model was developed, leading to conclusions and discussions on both theoretical and practical implications. This model is expected to be a valuable resource for policymakers in formulating strategies to improve facilities on railway platforms.
Deep learning for truthfulness assessment: detecting fake news in social media through deep learning
(BRAC University, 2025) Alam, Mahabubul; Dipta, Nabil Faieaz; Islam, Md Rakibul; Wahid, Aunanna Binte; Rokti, Tanmin Alam; Hossain, Muhammad Iqbal; Ahmed, Md Faisal
Misleading information is mostly intended to trick and harm people is known as fake news. It is mostly designed to harm a person or organization’s reputation. In this era of information technology, the rapid dissemination of news through social media platforms such as Facebook, Instagram, Twitter and so on has become an integral part of our daily lives. It has also been seen how devastating consequences can be due to the spread of fake news. Rumors can create unimaginable havoc in real life. There are already some existing works that need more efficiency. To detect fake news from social media accu- rately with most accuracy, we intend to propose a deep learning-based approach. We have utilized two deep learning models LSTM and DNN, a hybrid model of DNN and LSTM, three advanced deep learning architectures such as DistilBERT+LSTM+DNN, DistilBERT+GRU+DNN, BERT+GRU+DNN and our TruthForge model to evaluate our work. Through our work, we aim to provide a robust tool for identifying and differentiat- ing between true and false news, thus advancing the accuracy of news verification.
Design and Development of a Web-based Application Named "Pet Care Management System"
(Daffodil International University, 2024-07-24) Islam, Md Rakibul
The Pet Care Management System is a web-based application that simplifies the pet care management system on online. The web application is a great resource for the pet owner who struggles with their pet's nutrition food and health care. By using the pet care management system website pet owners find nutritious food, pet furniture, pet medicine, and medical services. The primary objective of this website is to ensure the proper health of pets. The website is a multi-vendor type website. where different sellers can sell their products on this website. The website is built using MERN stack technology. Where the front end is built using React.js, and TailwindCSS, and the back end is built using Node.Js and Express.Js. Here MongoDB is used as a database. The implementation of the MERN stack ensures scalability, flexibility, and responsiveness of the application, making it accessible from various devices and platforms. The use of MongoDB provides a flexible and scalable database solution, while Express.js and Node.js facilitate efficient server-side development and API integration. React.js enables the creation of dynamic and interactive user interfaces, enhancing the overall user experience. Through this project, we aim to address the challenges faced by pet owners in managing their pets' care routines and foster better communication and collaboration between pet owners and service providers. The Pet Care Management System offers a modern, efficient, and user-centric solution to streamline pet care management and promote the health and well-being of pets worldwide.
Identification of the Core Ontologies and Signature Genes of Polycystic Ovary Syndrome (PCOS)
(Informatics in Medicine Unlocked, Elsevier, 2020) Islam, Md Rakibul; Ahmed, Md Liton; Paul, Bikash Kumar; Bhuiyan, Touhid; Ahmed, Kawsar; Moni, Mohammad Ali
Worldwide polycystic ovary syndrome (PCOS) is one of the most common hormonal disorders in women of reproductive age. However, there is a lack of genetic study of the internal mechanisms of PCOS. Herein, we identify core genes involved in the pathogenesis of PCOS by using bioinformatics analysis. For the study, the dataset GSE124226 was collected from the Gene Expression Omnibus (GEO) database. The differentially expressed genes (DEGs) were obtained by using the R package limma. We found a total of 180 DEGs in which 73 were overexpressed and 107 were down-expressed. The functional analysis was analysed using the DAVID database and software tools for the identified up-regulated and down-regulated DEGs. We generated protein-protein interaction (PPI) networks by using Cytoscape and identified four hub genes (RARA, KPNB1, REL, and MAP1B) from the PPI network according to the degree score using cytoHubba; module analysis was also performed by using the MCODE plugin. Finally, we used the identified hub genes to reveal significant drug signatures, which may be useful as therapeutic targets for PCOS.
Potential Therapeutic Drugs for Ischemic Stroke and Stress Disorder
(Informatics in Medicine Unlocked, Elsevier, 2019-10-24) Islam, Md Rakibul; Ahmed, Md Liton; Paul, Bikash Kumar; Bhuiyan, Touhid; Ahmed, Kawsar
Ischemic stroke (IS) is a complex disease affected by several environmental factors, genetic factors, and their interactions. Stress disorder (SD) can also independently increase the risk of stroke. Many genetic factors are similarly found in IS and SD. Genetic factors play an important part in the pathogenesis of IS and SD. The identification of genetic factors has become a hot topic for current research. In the investigation described herein, we aimed to identify possible common gene targets and relevant drug molecules in the pathogenesis of IS and SD. The microarray dataset of GSE16561 for IS and GSE125216 for SD were downloaded from the Gene Expression Omnibus database. The differentially expressed genes (DEGs) of IS and SD were attained using the limma package in R. Only 31 common DEGs overlapped in both datasets. The common DEGs were analyzed by Search Tool for the Retrieval of Interacting Genes online database and Cytoscape software. To predict their interaction relationship with the protein-protein interaction (PPI) network, hub proteins were counted by their node degree value from the PPI network. Functional analysis was also applied, and significant gene ontology (GO) terms were retrieved. Finally, identified common DEGs were submitted to the DSigDB database, and related drug molecules were retrieved. Ten molecules were identified from the common DEGs.