http://lib.buet.ac.bd;localhosthttp://:8080/xmlui/handle/123456789/4 2026-09-20T23:24:22Z 2026-09-20T23:24:22Z Rifat Rahman http://lib.buet.ac.bd;localhosthttp://:8080/xmlui/handle/123456789/7387 2026-09-07T05:03:21Z 2024-12-17T00:00:00Z

Advanced topic modeling approach to identify mental health insights of Bangladeshi university students from social media data Eunus Ali, Dr. Mohammed; Rifat Rahman; 0419052028; 005.8/RIF/2024 Mental wellness encompasses emotional, psychological, and social well-being that influences our ways of thinking, emotions, and actions. Any mental health conditions may impair people’s everyday life. University-going students experience additional obstacles in disclosing mental health issues in open talks owing to stigma and privacy threats. However, they show mental health-relevant signals on social networking networks. In most situations, researchers or psychiatrists try to figure out the mental health issues of students utilizing longitudinal studies from their self- reported data that may be error-prone, prejudiced, and expensive & time-consuming. In this study, we examine both self-reported survey data and social media data to identify the underlying elements and reasons behind mental health issues (i.e., anxiety, stress, depression, and suicide ideation or suicidality) of students. It will also show how social media data analysis may be more robust in uncovering fresh and valuable insights connected to mental health illnesses. We intend to find related factors with mental health disorders of Bangladeshi university students from their self-reported data and create classification & regression models for predicting mental health disorder levels and scores, respectively, employing the associated factors. Then, we offer a unique topic modeling technique in Bangla for analyzing social media data and, lastly, explore social media data to acquire valuable knowledge related to mental health diseases. In most situations, the insights from the social media data complement the conclusions from the self-reported survey data. However, social media data analysis exposes fresh insights that are more valuable than survey data analysis. Moreover, the social media data analysis validates the upward and downward trends in the mental health disorder scores owing to diverse events (i.e., political turmoil, demonstrations or movements, disasters, pandemics, etc.) across time.

2024-12-17T00:00:00Z Kaysaru Zaman Kawshiq, A S M. http://lib.buet.ac.bd;localhosthttp://:8080/xmlui/handle/123456789/7324 2026-05-19T04:04:18Z 2025-03-15T00:00:00Z

Development of standard design methodology for slopes reinforced with plastic pins and Vetiver Grass Shariful Islam, Dr. Mohammad; Kaysaru Zaman Kawshiq, A S M.; 0421042201; 624.162095492/KAY/2025 Slope stability is a critical concern in geotechnical engineering, particularly in regions prone to erosion, shallow failures, and infrastructure instability. This research presents the development of a design methodology for slope stabilization using Vetiver grass and Recycled Plastic Pins (RPP) as a sustainable, cost-effective, and environmentally friendly alternative to conventional stabilization techniques. The study integrates laboratory testing, field monitoring, numerical modeling, and predictive modeling to evaluate the effectiveness of Vetiver and RPP in improving slope stability. The research begins with soil characterization through laboratory testing, assessing index properties, engineering properties, and chemical characteristics of different soil samples. Three soil types were analyzed: Tahirpur soil, classified as clayey silt with high plasticity, consisting of 84% silt and 16% clay, requiring pH adjustment for optimal vegetation growth. Dacope soil, categorized as lean clay with moderate plasticity, contained 73% silt and 27% clay but exhibited high salinity (ECe = 9 dS/m), making it challenging for plant survival. Chilmari soil, identified as silty sand with 60% sand, 35% silt, and 5% clay. Field monitoring of Vetiver growth at two sites, Dacope (Khulna) and Chilmari (Kurigram), demonstrated Vetiver’s ability to thrive in saline and nutrient-deficient soils. Survival rates exceeded 75% in high-salinity conditions and reached 95% in sandy soil. Growth data indicated shoot lengths of up to 213 cm and root penetration extending to 70 cm, confirming Vetiver’s strong anchorage and effectiveness in erosion control. To enhance real-time assessment of soil movement, moisture content, and reinforcement performance, an IoT-based monitoring framework was conceptually introduced. Numerical analysis using PLAXIS 2D was performed to assess the effectiveness of Vetiver and RPP reinforcement. The results were validated against conventional method of slices. A parametric study was conducted to evaluate the influence of slope geometry, soil strength, reinforcement depth, plant age, and spacing on stability. The findings revealed that increasing the slope angle from 20° to 60° led to a 61% decrease in FS, indicating the vulnerability of steeper slopes to failure. Soil cohesion played a crucial role in stability, as an increase from 0 to 20 kPa resulted in a 126% improvement in FS, confirming that cohesive soils provide better stability. The effectiveness of Vetiver reinforcement was strongly correlated with plant age, with a 62% increase in stability observed after two years due to deeper root penetration. Denser Vetiver and RPP spacing configurations contributed to higher FS values, while wider spacing reduced reinforcement effectiveness. The optimal RPP length was determined to be up to 2.0 meters for RPP alone, beyond which additional length yielded diminishing returns, but with vetiver deeper RPP lengths provided additional 16% improvement of FS when length was increased from 2 to 3 meters. To develop a practical design tool, Multi-Linear Regression (MLR) and Artificial Neural Network (ANN) models were formulated for FS prediction. A cost analysis demonstrated that Vetiver and RPP reinforcement was significantly more economical than conventional concrete-based stabilization methods, reducing costs by up to 56%. The Vetiver and RPP hybrid system had more cost-to-performance ratio, making it a viable solution for large-scale slope protection projects.

2025-03-15T00:00:00Z Sheezanul Hassan http://lib.buet.ac.bd;localhosthttp://:8080/xmlui/handle/123456789/7323 2026-05-19T03:53:10Z 2024-10-19T00:00:00Z

An automated walking guide to assist way-finding and situation awareness for the visually impaired Liakot Ali, Dr. Md.; Sheezanul Hassan; 1018312010; 006.424/SHE/2024 Safe and independent mobility is one of the major daily challenges faced by the visually impaired. To navigate a new area safely, they need to know the location of obstacles and other things in their path. They struggle with object detection and obstacle avoidance, making it challenging to navigate new or unfamiliar situations and be aware of obstacles and their relative positions. However, establishing secure and safe mobility and pathfinding for the visually impaired is a critical issue in their life that must be solved accurately and efficiently. Recognizing currency is another severe problem for them because different notes in our country have similar colors, surfaces and sizes causing major problems for the visually impaired. Object recognition alone may not be sufficient to assist visually impaired individuals effectively. Incorporating lateral position identification can provide users with a sense of spatial orientation within their environment, enabling them to navigate paths toward recognized objects more accurately. In this thesis, a system is proposed to assist visually impaired individuals by identifying both navigation objects and their corresponding lateral positions, and recognizing Bangladeshi currency. This system aims to serve as a comprehensive walking guide, offering benefits for both indoor and outdoor navigation. By enhancing spatial awareness and providing critical information about their surroundings, this system will enable visually impaired users to make informed decisions regarding their movements and actions; thereby, improving their independence and quality of life. The system utilizes EfficientNet, a Convolutional Neural Network architecture for Machine Learning to design a model for currency and navigation objects that can recognize fifteen classes of objects for assisting the visually impaired. The architecture also applies computational logic to the model to identify lateral positions of the navigation objects; and thus conceptualizing a system that can act as a walking guide for visually impaired people aiding navigation and awareness. The model proposed in the system has been evaluated with real-world objects to assess the performance of the proposed method. The experimental analysis demonstrates that the system achieves notable Accuracy, Precision, Recall, and F1 scores, highlighting its prospective relevance and effectiveness in the field.

2024-10-19T00:00:00Z Sumon Chowdhury, Md. http://lib.buet.ac.bd;localhosthttp://:8080/xmlui/handle/123456789/7322 2026-05-19T03:45:05Z 2024-05-28T00:00:00Z

Experimental study on rheological properties of water based drilling fluid and its impact on drilling operations Mahbubur Rahman, Dr. Mohammed; Sumon Chowdhury, Md.; 1018132012; 622.3381/SUM/2024 Most encountered problems like fluid loss, wellbore stability, well control, poor capacity of cuttings transport, poor torque performance, increased drag, and stuck pipe can occur during drilling due to the improper design of the drilling mud, which can increase the cost of drilling. This study looks into the rheological properties of ten water-based drilling mud and their impact on drilling operations. A viscometer is used to conduct the analysis in the laboratory. The density of the prepared mud ranges from 8.7 ppg to 10.01 ppg. This experimental study focuses on determining the viscosity, gel strength, and yield point of ten water-based drilling mud which are formulated under different barite concentrations. The plastic viscosity of the ten mud samples ranges from 10 cp to 18 cp, yield point ranges from 5 lb/100ft2 to 12.75 lb/100ft2 and gel strength ranges from 2 lb/100ft2 to 9 lb/100ft2. The effect of density on viscosity, gel strength, and yield point is also observed in this study. Key findings indicate that the viscosity, gel strength, and yield point of the drilling fluid are significantly influenced by the density of mud at constant pressure and temperature. Five drilling mud rheological models such as Newtonian, Bingham plastic, Power law, API, and Herschel-Bulkley are analyzed to select the most suitable fluid model and measure the total frictional pressure drop in the wellbore, considering the suitable model. The error analysis of experimental/measured shear stress and theoretical/modeled shear stress is done to choose the most perfect fluid model. The minimum error indicates the best fitted rheological fluid model. This study found the error between experimental/measured shear stress and theoretical/modeled shear stress maximum for Newtonian model (7% to 18%) and minimum for API model (up to 0.16%). The mud samples are preferable for the API model to calculate the standpipe or pump pressure. Data matching is done to compare the experimental and real pressure loss data, SBHP and FBHP. There is good scope in the future to study the effect of some chemical additives on the rheological properties of water based drilling mud in different pressure and temperature.

2024-05-28T00:00:00Z