http://103.99.128.19:8080/xmlui/handle/123456789/34 All Digital Collections of CSE Tue, 07 Apr 2026 09:28:17 GMT 2026-04-07T09:28:17Z http://103.99.128.19:8080/xmlui/handle/123456789/521 Identification of cyberbullying Bangla Linguistics Texts using deep learning and transformer based approaches. Saifullah, Md Khalid In today's digital era, social media platforms such as Facebook, Twitter, and YouTube play crucial roles in facilitating idea expression and interpersonal connections. However, alongside increased connectivity, these platforms have inadvertently facilitated negative behaviors, notably cyberbullying. While extensive research has delved into cyberbullying in high-resource languages like English, there remains a significant dearth of resources for low-resource languages such as Bengali, Arabic, Tamil, and others, particularly concerning language modeling. This study aims to bridge this gap by developing a cyberbullying text identification system, named BullyFilterNeT, tailored specifically for social media texts, with Bengali serving as a test case. The intelligent BullyFilterNeT system effectively tackles challenges associated with Out-of-Vocabulary (OOV) words inherent in non-contextual embeddings and addresses the limitations of context-aware feature representations. To provide a comprehensive analysis, three non-contextual embedding models—GloVe, FastText, and Word2Vec—are developed for feature extraction in Bengali. These embedding models are integrated into classification models employing both statistical methods (SVM, SGD, Libsvm) and deep learning architectures (CNN, VDCNN, LSTM, GRU). Furthermore, the study utilizes six transformer-based language models; mBERT, bELECTRA, IndicBERT, XML-RoBERTa, DistilBERT, and BanglaBERT to overcome shortcomings observed in earlier models. Notably, the BanglaBERT-based BullyFilterNeT achieves the highest accuracy of 88.04% in our test set, demonstrating its efficacy in identifying cyberbullying text in the Bengali language. Thesis in CSE Wed, 24 Jul 2024 00:00:00 GMT http://103.99.128.19:8080/xmlui/handle/123456789/521 2024-07-24T00:00:00Z http://103.99.128.19:8080/xmlui/handle/123456789/500 Ergonomic analysis of seats of human powered vehicles by digital human modeling for better ride comfort Hai, Tasmia Binte Rickshaws are essential for affordable and accessible transportation, particularly in densely populated urban areas. It is important to ensure the comfort of the rickshaw driver as it directly affects their health, well-being, and job satisfaction. It also influences customer satisfaction and safety. This study focuses on modifying the rickshaw driver's seat to enhance comfort while ensuring ergonomic principles are met. As proper cushioning, support, vibration absorption, and adjustability are key factors, this study involves measurements of rickshaw frames, CAD design of seat structures, ergonomic analysis using CATIA V5, and experimental vibration analysis. RULA and REBA analyses are performed on digital human models to evaluate posture and musculoskeletal risks associated with the conventional seat design. Modifications were suggested based on the analysis. Modified seat designs were introduced and analyzed identically to the conventional design using anthropometric data. Adjustments to handle height positively impacted driver comfort and ergonomics. These ergonomic analyses indicate that the modified design can provide more comfort to the driver. Afterward, vibration analysis is done as the springs in the driver's seat absorb shocks and vibrations, reducing fatigue and minimizing the risk of musculoskeletal issues. They contribute to overall comfort during long hours of driving. Vibration analysis is conducted to compare the conventional and modified seat designs. The modified design demonstrated better vibration absorption, indicating improved comfort for the driver. Overall, the study provides valuable insights into the importance of rickshaw driver comfort, the role of seat design and springs, and the methods to optimize comfort and performance through ergonomic analysis Thesis on ME Fri, 03 May 2024 00:00:00 GMT http://103.99.128.19:8080/xmlui/handle/123456789/500 2024-05-03T00:00:00Z http://103.99.128.19:8080/xmlui/handle/123456789/499 Assessing health related economic benefits from reduced particulate matter in air using BenMAP-CE Kabir, Maisha The residents of Chattogram City Corporation (CCC) are grappling with serious health risks due to air pollution, especially during the dry period. The Institute for Health Metrics and Evaluation (IHME) has documented a significant number of premature deaths attributed to polluted air. While the government has implemented policies to curb air pollution, their impact often falls short due to a lack of comprehensive benefit modeling for decision-making. There is a lack of localized studies on air pollution and its health impacts, particularly in Chattogram, with gaps in understanding the correlation between air pollution, heavy metals, mortality, and economic burden, highlighting the urgent need for investigations using tools like BenMAP-CE to assess the efficacy of pollution reduction measures. This study bridges the gap by utilizing the BenMAP-CE tool to assess health and economic benefits resulting from airborne particulate matter reduction. The study centers around the development of BenMAP-CE, utilizing data on particulate matter (PM) in the air, population statistics, air pollution hazards as well as health hazards due to road dust, and economic data. PM data has been gathered from Landsat 8 and selected monitoring sites in the CCC area. Trace metals in road dust were identified using acid digestion and atomic absorption spectrophotometry. The 24-hour average concentrations of PM10 and PM2.5 in air during November and December, obtained from Landsat 8 and cross-referenced with CAMS data, ranged from 84 to 532 μg/m3 and 70 to 339 μg/m3, respectively, with averages of 181 to 246 μg/m3 and 108 to 190 μg/m3 over the study period. These concentrations were found to exceed BNAAQS and WHO 24-hour threshold values, indicating a hazardous situation linked to associated health risks. The study reveals a temporal trend of rising PM concentrations from 2017 to 2019, followed by a decrease in 2020, a peak in 2021, and a slight decline in 2022. Elevated concentrations of metals like Mn, Zn, Fe, Cr, Cu, and Ni were also identified, potentially exacerbating air-associated health issues. The BenMAP-CE tool demonstrates substantial health and economic benefits achievable through air quality improvement policies in CCC. The study estimates the prevention of 7185 to 11643 premature deaths, translating to an economic benefit ranging from 1.131 billion US dollars to 2.297 billion US dollars, contributing 0.45% to 0.82% to the country’s GDP. Cardiovascular diseases accounted for more premature deaths than respiratory diseases, with the top 5 causes of death ranked as IHD>Stroke>COPD>LRI>LC. The age group 5 to 17 exhibited premature morbidity effects related to asthma and lower respiratory infections. Thesis on Civil Engineering Mon, 04 Mar 2024 00:00:00 GMT http://103.99.128.19:8080/xmlui/handle/123456789/499 2024-03-04T00:00:00Z http://103.99.128.19:8080/xmlui/handle/123456789/498 Modeling of the biological treatment process of domestic wastewater using Artificial Neural Network Saiful Islam, Mohammad Thesis on Civil Tue, 20 Feb 2024 00:00:00 GMT http://103.99.128.19:8080/xmlui/handle/123456789/498 2024-02-20T00:00:00Z