NSU INSTITUTIONAL REPOSITORY
North South University Institutional Repository showcases the university's intellectual contributions, including journal articles, conference proceedings, theses, and more. Explore the latest research and advance your knowledge today!
Communities in NSU Repository
Select a community to browse its collections.
Conference Travel and Research Grants (CTRG) Confucius Institute at North South University North South University Journals North South University Library North South University Publications School of Business & Economics (SBE) School of Engineering & Physical Sciences (SEPS) School of Health & Life Sciences (SHLS) School of Humanities & Social Sciences (SHSS) The Office of External Affairs (OEA)
Recent Submissions
Item
Open Access
নরওয়ের সাবেক পরিবেশ মন্ত্রীকে সম্মানসূচক অধ্যাপক পদ দিল এনএসইউ
(বণিক বার্তা, 2026-02-09) বণিক বার্তা
নর্থ সাউথ ইউনিভার্সিটির (এনএসইউ) সেন্টার ফর ক্লাইমেট চেঞ্জ অ্যান্ড ডিজাস্টার রেজিলিয়েন্স (সিডিআর) ‘হাউ এশিয়া ইজ লিডিং দ্য গ্রীন ট্রান্সফরমেশন অ্যান্ড হাউ বাংলাদেশ ক্যান বেনিফিট’ শীর্ষক একটি সেমিনারের আয়োজন করে। রবিবার (০৮ ফেব্রুয়ারি) বিশ্ববিদ্যালয়ের সিন্ডিকেট হলে অনুষ্ঠিত এ সেমিনারে শিক্ষক, গবেষক ও শিক্ষার্থীরা অংশ নেন। সেমিনারে প্রধান অতিথি হিসেবে উপস্থিত ছিলেন বেল্ট অ্যান্ড রোড গ্রিন ডেভেলপমেন্ট ইনিশিয়েটিভের প্রেসিডেন্ট এবং নরওয়ের সাবেক পরিবেশ ও আন্তর্জাতিক উন্নয়নমন্ত্রী এরিক সোলহেইম। অনুষ্ঠানে সভাপতিত্ব করেন এনএসইউর উপাচার্য অধ্যাপক আবদুল হান্নান চৌধুরী। এছাড়া উপ-উপাচার্য অধ্যাপক নেছার উদ্দিন আহমেদ এবং চায়না–বাংলাদেশ পার্টনারশিপ ফোরামের সেক্রেটারি জেনারেল অ্যালেক্স ওয়াং উপস্থিত ছিলেন। অনুষ্ঠানে পরিবেশ ও টেকসই উন্নয়নে অসামান্য অবদানের স্বীকৃতিস্বরূপ নর্থ সাউথ ইউনিভার্সিটি জনাব. এরিক সোলহেইমকে সম্মানসূচক অধ্যাপক পদে ভূষিত করে।
Item
Open Access
Lumbar Spine MRI Segmentation using Deep Learning
(North South University, 2024-04-30) Istiak Ahmed; Tanvir Ibne Hossain; Md. Labib Hasan; Md. Zahirul Islam Nahid; Dr. Mohammad Monirujjaman Khan; 1722070042; 1912205042; 2011068042; 2013421642
In this study, an advanced approach to lumbar spine segmentation using deep learning techniques is presented, focusing on addressing key challenges such as class imbalance and data preprocessing. MRI scans of patients with low back pain are meticulously preprocessed to ensure accurate representation of three critical classes: vertebrae, spinal canal, and intervertebral discs (IVDs). By rectifying class inconsistencies, the fidelity of the training data is ensured. The modified U-Net model incorporates innovative architectural enhancements, including an upsample block with leaky ReLU and Glorot uniform initializer, to mitigate common issues such as the dying ReLU problem and improve stability during training. Introducing a custom combined loss function effectively tackles class imbalance, resulting in significant improvements in segmentation accuracy. Evaluation using a comprehensive suite of metrics showcases the superior performance of this approach, outperforming existing methods and advancing the current techniques in lumbar spine segmentation. These findings hold significant advancements for enhanced diagnostic accuracy of lumbar spine MRI and segmentation
Item
Open Access
NSU Tender No. NSU-26-27-T-02 (Hiring Transport Services)
(প্রথম আলো, 2026-08-20) প্রথম আলো; The Daily Star
North South University (NSU) invites sealed offers from bona fide/reputed transport operators, business partners, and logistics agents for the provisioning of comprehensive transport services. The selected vendor will manage daily commuting services for NSU members and administrative officials across the designated routes in Dhaka City. Last date of submission: September 09, 2026.
Item
Open Access
Tweet Popularity Predicion Using Deep Learning
(North South University, 2022-12-30) Leyon Ibn Kamal; Nujhat Tabassum; Raihan Hasan Joy; Mahafuza Anzum Lia; Dr. Shahnewaz Siddique; 1811050042; 1731175042; 1712340642; 1711261642
Twitter is one of the most popular social media platforms. It is used for a wide range of uses, from just sharing information to promoting brands, and even by many governments and politicians to promote their policies and opinions. Regardless of the use, the most common expectation of the users is for their tweets to get higher likes and retweets, which eventually leads to a greater reach in the audience. From general observation, we can notice that on Twitter some tweets seem to get better reach than others. So our goal is to create a deep learning model that would allow us to predict if a certain text a user wants to tweet out will get popular so that they can optimize their tweets for maximum benefit. We will use text classification to create a rating system to allow us to get a general idea of how popular a tweet could get.
Item
Open Access
Disaster Rescue AI:
Advanced AI for Finding Alive People in Disasters and
Alert System
(North South University, 2025-04-30) Md. Adham Wahid; Fatema Afsan Ema; Istiak Ahasan; Dr. Sifat Momen; 2111177042; 2022281642; 2012082642
A developmental illness that may manifest in early childhood is Attention Deficit Hyperactivity Disorder (ADHD). It may lead to poor self-esteem and social function in children if it’s not considered at an early age. Early detection and diagnosis of ADHD results in early interventions that improve social development, academic performance, and treatment outcomes among children. This is the first integrated framework that not only predicts ADHD in early childhood using Machine learning and Natural language processing techniques but also offers a Dialogflow-based therapeutic chatbot as a primary intervention an approach not addressed in existing literature. A total of fourteen Machine Learning and five BERT-based transformer algorithms with optimized hyperparameters have been applied to classify ADHD-positive and ADHD-free children identifying the key factors. The Stacking ensemble model came out with the best-performing metrics with 94.27% accuracy, 87.00% precision, 82.07% recall and 84.30% f1 score, and AUC of 0.97 that achieves state-of-the-art performance on CAHMI survey and dataset. While DistilBERT outshined among other BERT-based transformer models with 93.45% accuracy, 19.25s runtime, and AUC of 0.968 highlighting the natural language processing. LIME and SHAP have added enhanced transparency and dynamic decision-making interpretability. Unlike prior studies that focus solely on prediction, our model emphasizes both early diagnosis and immediate therapeutic support, bridging a critical gap between detection and intervention. Moreover, domain experts raw feedback and generalization through unseen datasetscontribute significantly to the novelty and practical relevance of the proposed system. This study presents a comprehensive statistical analysis through a well-structured machine learning and transformer pipeline, incorporating detailed visualizations alongside textual explanations.
Item
Open Access
Swarnoshuta- A clothing brand E-commerce Website
(North South University, 2024-11-12) Rafiqun Nabi Torofder Navid; Ankita Kundu; Md. Shihab Tawsib Shown; 1911067042; 2012314642; 2211939042
The preservation of traditional handloom craftsmanship is crucial to safeguarding cultural heritage and fostering sustainable livelihoods. Swarnoshuta is an innovative e-commerce platform designed to promote and market traditional Bangladeshi handloom sarees, including Tant, Banarasi, Silk, Jamdani, and Muslin. This project aims to counter the growing dominance of machine-made products imported from neighboring countries like India and Pakistan, which threaten the survival of local artisans and their time-honored weaving traditions. The primary goal of this initiative is to establish a robust online presence through a dedicated website and Facebook page, serving as a bridge between customers and craftsmen. By creating a direct connection, Swarnoshuta seeks to revitalize the handloom industry, generate employment opportunities, and uplift marginalized weavers. The platform provides an avenue for artisans to showcase their craftsmanship to a global audience while enabling customers to access authentic, high-quality handloom sarees conveniently. The website was developed using modern web technologies to ensure a seamless user experience. React.js was employed for the frontend, providing an interactive and responsive interface, while Express.js and Node.js were utilized for backend development to handle server-side operations efficiently. MongoDB, a NoSQL database, was chosen for its scalability and flexibility in managing product and customer data. This research paper outlines the design, development, and implementation of the Swarnoshuta platform. It also explores the socio-economic impact of creating an online marketplace for traditional crafts and highlights the importance of preserving cultural identity through technological innovation. The findings suggest that such initiatives can play a pivotal role in sustaining traditional industries, fostering economic empowerment, and promoting cultural pride in a rapidly globalizing world.
Item
Open Access
Development of a Low-Cost Autonomous Vehicle System Using COTS for Obstacle Detection and Collision Avoidance
(North South University, 2024-04) Abrar Mahir Uddin Sahil; Nuzhat Jabeen Haque; Dr. Shahnewaz Siddique; 2013786043; 2031730643
In response to the prevalent issue of traffic accidents in Bangladesh, a low-cost autonomous vehicle prototype is developed utilizing readily available resources. In this study, we explore the feasibility of low-cost autonomous vehicles in reducing traffic accidents prevalent in Bangladesh, where an average of 11 accidents occur daily. The prototype utilizes an Arduino UNO microcontroller, an ESP32 WiFi camera module, and a combination of sensors, like, an ultrasonic sensor and servo motor, for obstacle detection and collision avoidance. Sensor fusion techniques allow the system to identify everyday objects, such as water bottles, furniture, and electronics, using datasets trained via Edge Impulse software. Additionally, YOLOv3 and OpenCV software contribute to object identification. This resource-efficient approach presents a potentially viable solution for enhancing road safety in developing nations.
Item
Open Access
ENHANCING IMAGES FOR COLOR VISION DEFICIENCY (CVD) USING DEEP LEARNING
(North South University, 2024-04-30) TANEEM AHMED; SIDDHARTHA SANKAR SAHA; MAHBUB MORSHED RIFAT; Dr. Mohammad Ashrafuzzaman Khan (AZK); 2013102042; 2011567042; 2011415042
In a stunning world full of colors, color vision deficiency is the most common difficulty every human being faces. This problem still has no treatment. The subject of this research is to expose artificial intelligence methods as profound studies that aim at material, tangible visualization through images of color blindness in humanity, hence becoming a hope that technology will eventually fill the gap in color perception. The two AI models are the basis for creating and utilizing the project. The first model is Daltonization, which simulates the perception of color by different kinds of CVD and hence can create image transformations that specifically cater to one's eye problems. Secondly, A CNN-based Autoencoder model trains on various images taken under normal vision color conditions and color vision deficiency (CVD) conditions. Therefore, the aim is to create an autoencoder that will convert any image into a better-colored one that is clearly visible to individuals suffering from CVDs. The triumph of this task is determined by how well it performs in terms of two criteria. Quantitative measurements allow for an analysis of the degree to which the latest picture reproduces original images through methods like SSIM (Structural similarity index). User testing and feedback obtained by people suffering from CVD constitute quality appraisals for verifying the acceptability of changes made to their visual perception. We ensure that data collection and utilization are done per strict ethical principles to avoid violating privacy rights or obtaining participants' permission. The primary objective of using converted images is to adhere to and also maintain established accessibility standards for people with Color Vision Deficiency (CVD), therefore rendering them more manageable. The project focuses on user feedback and iterative design methods aimed at guaranteeing that the produced tools are intuitive and user-friendly for persons with low vision (CVD). These AI models work well on web browsers, mobile devices, or picture-editing tools. This project looks not only at improving the accessibility of images but also examines possible uses for the models in this field within augmented reality and virtual reality, amongst other emerging technologies. By improving how they see things while learning or working with it every day during their hours of relaxation at home, we hope that through our efforts, those suffering from CVD would experience an enhanced quality of life. "The exploration of AI will demonstrate how deep learning could come in handy in solving accessibility issues, hence pushing the field further. A user-friendly tool will be developed through this project, which should integrate its software or applications with existing platforms and workflow easily. The project asserts higher levels of inclusivity in visual design by increasing awareness and promotion. This project combines leading-edge AI tech and user-centered design principles, potentially changing how people with color vision deficiencies see objects.
Item
Open Access
এনএসইউ নিয়োগ বিজ্ঞপ্তি- ৫ আগস্ট, ২০২৬
(দৈনিক ইত্তেফাক, 2026-08-05) দৈনিক ইত্তেফাক; যুগান্তর
নর্থ সাউথ ইউনিভার্সিটিতে বিভিন্ন পদে বেশ কিছু দক্ষ জনবল নিয়োগ করা হবে। আগ্রহী প্রার্থীদের সাদা কাগজে স্বহস্তে লিখিত আবেদনপত্র জমা দিতে হবে। আবেদনের শেষ সময়: ২০ আগস্ট, ২০২৬।
Item
Open Access
In Reverent memory Late Azim Uddin Ahmed by Southeast Bank
(বণিক বার্তা, 2026-07-31) বণিক বার্তা
The solemn tribute in reverent memory of the late Azim Uddin Ahmed, sponsored or presented by Southeast Bank. It honors his life, legacy, and significant contributions, acknowledging his enduring impact on the community, business sector, and institutional leadership. The publication pays homage to his visionary work and leadership legacy, reflecting the deep respect and remembrance held for him by Southeast Bank and the broader community.