http://dspace.daffodilvarsity.edu.bd:8080/handle/123456789/40 2026-07-06T06:19:58Z 2026-07-06T06:19:58Z Rafsun, Sk. Salman http://dspace.daffodilvarsity.edu.bd:8080/handle/123456789/17467 2026-06-25T21:01:33Z 2025-01-25T00:00:00Z

Prediction Of Diabetes Using Machine Learning Algorithms Rafsun, Sk. Salman Diabetes is a frequent condition in humans that is brought on by a collection of metabolic diseases in which the body's sugar levels remain abnormally high for an extended length of time. Because it damages many of the body's systems by affecting various organs, we are all trying to prevent diabetes at an early stage by anticipating its symptoms using a variety of techniques. Human life can be saved by controlling such diseases early on. In order to accomplish the goal, this research project primarily uses machine learning approaches to investigate differentrisk variables associated with this disease. Effective knowledge extraction is accomplished by machine learning methods that build prediction models using diagnostic medical datasets from diabetic patients. It may be possible to forecast diabetic people by gleaning information from such data. K-Means Cluster, Naive Bayes (NB), Support Vector Machine (SVM), K- Nearest Neighbor (KNN), Linear Regression, Decision Tree (DT), Logistic Regression, Random Forest (RF) and Hierarchical Cluster are nine well-known machine learning algorithms that I use in this work to predict diabetic disease using data from the adult population. In comparison to other machine learning methods, the findings from my experiments indicate that when compared to alternative approaches, the C4.5 decision tree attained a greater level of accuracy. M.SC. in ETE

2025-01-25T00:00:00Z Roy, Pijush Chandro http://dspace.daffodilvarsity.edu.bd:8080/handle/123456789/17448 2026-06-25T21:01:30Z 2025-10-15T00:00:00Z

A Hybrid AI-Based Model for Depression Detection in Bangla Social Media Posts Using the BSMDD Dataset Roy, Pijush Chandro Depression is a significant healthcare problem worldwide, impacting countless people of all ages annually. This paper presents a novel approach for depression identification by using complex datasets and employing various machine learning models such as LightGBM, XGBoost, Naïve Bayes, and Random Forest. The study emphasizes how itis possible to change the face of mental health diagnosis with those models relying on the data. In the future, the analysis should aim at improving model interpretability, reducing bias in the algorithms, using multi-source data as well ethical issues such as rights of privacy and consent. These innovations are designed to help improve the diagnostic capabilities, promote inclusiveness in the outcomes, and support the means of real-time monitoring their health of the individual. Among the models tested, LightGBM proved to be the best as it achieved an accuracy of 83.67% and an F1 score of 84.06%. XGBoost had a higher accuracy rate while Naive Bayes had a higher recall rate. Random Forest also proved effective, performing well in all areas metrics which show their different benefits for dealing with issues in mental health care. M.SC. in ETE

2025-10-15T00:00:00Z Biswas, Sajib http://dspace.daffodilvarsity.edu.bd:8080/handle/123456789/17440 2026-06-25T21:01:18Z 2025-01-30T00:00:00Z

Empirical Study on Network System Administration with Mikrotik Platform Biswas, Sajib An extensive summary of my network system administration internship experience is given in this report, with particular attention to the usage of MikroTik as a platform for network infrastructure design, configuration, and management. By providing practical experience in setting routers, switches, and firewalls to enable safe and effective data transfer inside an organizational setup, the internship sought to close the knowledge gap between theory and practice. The study describes the design of MikroTik devices, their use in contemporary networking systems, and the basic ideas of network system administration. I was introduced to a variety of network design topics throughout my internship, such as traffic management, VLAN setup, IP addressing, subnetting, and troubleshooting network problems. I was able to comprehend sophisticated networking features like Quality of Service (QoS), Virtual Private Networks (VPNs), and network security measures by using MikroTik's RouterOS. The report also outlines certain projects and activities completed during the internship, including network topology configuration, firewall deployment to reduce security risks, and bandwidth optimization to improve network performance. These assignments highlighted how crucial it is to keep up a strong and expandable network infrastructure in order to satisfy organizational demands. Internship Report

2025-01-30T00:00:00Z Islam, Rafiqul http://dspace.daffodilvarsity.edu.bd:8080/handle/123456789/17439 2026-06-25T21:01:20Z 2024-01-30T00:00:00Z

Empirical Study On Isp Operation And Maintenance With Mikrotik Islam, Rafiqul This study's primary goal is to clarify how to set up and maintain a network and bandwidth using the network management software Mikrotik. The goal is to become the most appealing and trustworthy online retailer for customers. The Mikrotik router's design is created by Winbox. This system acts as a successful example and is subjected to incremental testing afterall the services have been deployed. The Winbox platform's use of a Mikrotik router includes a number of tasks, such as network design, analysis, and troubleshooting. It can also be used for network security, PPPoE deployment, VPN and tunneling, network monitoring, and consultancy. Furthermore, it provides capabilities like firewalls, bridges, DNS, NAT, ARP, and a number of other features. By using cnPilot access points for Wi-Fi with cnMaestro management, network management and maintenance costs can be decreased while user comfort is increased. Internship Report

2024-01-30T00:00:00Z