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!


Photo by @Ashik
 

Recent Submissions

Item
Embargo
Stock Market Price Forecasting Service using LSTM
(North-south University, 2019-04-30) Md. Mahabubul Hasan; Pritom Roy; Sabbir Sarker; Dr. Mohammad Monirujjaman Khan; 1421274042; 1430378042; 1420134042
In recent years we’ve seen in Bangladesh that the Stock market is not stable at all. In 2011 Stocks continued to tumble amid jitters over banks' liquidity crisis. After starting the day at 5,710, DSEX, the benchmark index of the Dhaka Stock Exchange, plunged to below 5,700 points in less than half an hour. Eventually, it lost 81.92 points to close the day at 5,623.64. People invest a lot in stock market. Many people just lost their hard-earned money in a blink of an eye because of investing at the wrong place. But we’ve seen the vice versa situation from the stock market as well. Stockify comes in play here. Stockify is dedicated to show accurate predicated prices of market shares. 70% accuracy have been achieved via training the algorithm Using LSTM which is an artificial neural network. Deep learning algorithm library TensorFlow have been implemented to show us predicted price using the closing prices of a day. Currently we are providing free service via our website and application. It would be on subscription based when the site will be more enriched in a business level. Thus, we hope to help people to make a profit in stock market and upraise the stock market of Bangladesh.
Item
Embargo
E-learning App with Augmented Reality
(North South University, 2019-04-30) Md Nazmus Shakib; Safin Mahmud; Polash Chakrabarty; Abdullah All Noman Abir; Dr. Shazzad Hosain; 1511336042; 1510903042; 1520579042; ID # 1521047042
Smartphone has become a great tool for teaching kids. As kids nowadays spend a lot of time on a smartphone. Preschool education is considered pivotal for a child’s development. Mobile learning is a new way to access learning content. Mobile learning is very popular among preschool kids. Because it really motivates kids to learn if they can use mobile phones or tablets. That's why we have developed a marker-based AR application, which will help children to learn or study the basics of Alphabets with fun. While using our app, kids will learn interactively with the help of Augmented Reality. Our app will help the parents teach their kids without much effort.
Item
Embargo
Chiral and Plasmonic dimers: Broadband reversal of optical binding force
(North South University, 2022-12-31) Missing information; Missing Information
The behavior between the chiral –plasmonic nanoparticles and their optical binding force in near and far field has not been investigated in the literature yet. There is no generic way to reverse the far field optical binding force for chiral and plasmonic (sphere) heterodimers. Also the behavior of Fano resonance and the reversal of far field optical binding force of chiral plasmonic heterodimers with and without plasmonic substrates have not been studied so far. In this article, for chiral and plasmonic heterodimers, we have demonstrated a general way to control the reversal of far field binding force. However, if the chiral-plasmonic nanoparticles are located at different distance, positive and reversal of optical binding force occurs in far field. We have varied the wavelength of the dimers. We have also observed Fano resonance at both near and far field without substrate .Also while applying the same set-up over a plasmonic substrate, stable Fano resonance occurs along with the reversal of far field optical binding force. It is observed that during such Fano resonance, stronger coupling occurs between the dimers and plasmonic substrate. The reversal of optical binding force occurs near the Fano dip position. Notably, for particle clustering and aggregation, controlling the far fled binding force can be a key factor. Our proposed idea can be confirmed by simple experiment.
Item
Open Access
Sleep Apnea Detection From Raw Ecg Signal Using Deep Learning And Machine Learning
(North South University, 2023) Salem Shamsul Alam; Sumit Saha; Md. Shahriar Hussain; 1931849642; 1931415042
Sleep apnea, a prevalent yet underdiagnosed sleep disorder, necessitates robust and accurate diagnostic tools. In this project, we undertook an in-depth exploration of machine learning (ML) and deep learning (DL) models for sleep apnea detection, specifically utilizing raw electrocardiogram (ECG) signals. Our comparative analysis encompassed a range of ML models, including Random Forest, Logistic Regression, Decision Tree, AdaBoost, and XGBoost, and a specialized 1D-CNN model within the DL domain. Results underscore the exceptional performance of the 1D-CNN model, achieving a remarkable accuracy of 99.56%, sensitivity of 96.05%, and specificity of 99.66%. This outperforms traditional ML models, signifying the prowess of DL in extracting intricate patterns from raw ECG signals for accurate sleep apnea detection. The 1D-CNN model's ability to discern subtle features proves crucial for accurately identifying apnea events. Our study not only emphasizes the effectiveness of the 1D-CNN model for sleep apnea detection and highlights the transformative potential of deep learning in healthcare diagnostics. This research contributes valuable insights into the optimal choice of models for sleep apnea detection, paving the way for enhanced diagnostic accuracy and improved patient care.
Item
Open Access
Developing a Mobile Application using Deep Learning for Cataract Classification
(North South University, 2023) Tasnia Ishrat Khan; Fatima Ibrahim; Mohammad Monirujjaman Khan; 1911539642; 2121340642
One of the leading global causes of vision loss and blindness is the cataract. The percentage of blind people is around 50%. As a result, early cataract detection and prevention may limit vision loss and blindness. Contrary to cataract, artificial intelligence (AI) has made significant progress in the treatment of glaucoma, macular degeneration, diabetic retinopathy, corneal abnormalities, and age-related eye diseases. However, the vast majority of cataract detection algorithms in use are built using common machine learning techniques. On the other hand, manual extraction of retinal features is a laborious method that needs a skilled ophthalmologist. In order to detect cataracts, we have built the framework of an Android application. We then used algorithms to extract accuracy, graphs, trainable and untrainable parameters, and differentiation of cataract and non-cataract eye images from a gathered dataset. In order to identify the cataract using color fundus images, we presented the VGG19 (Visual Geometry Group), and digital image we presented Inception V3, which is a CNN (convolutional neural network) model. This will be incorporated into an Android application. The results of fundus image, the training procedure demonstrate that the model attained a flawless accuracy of 1.0000 on the training data for epochs 10 to 15. It scored an accuracy of 0.963 on the validation set, which is still quite high. With values ranging from 0.25 to 0.27, the validation loss was similarly largely consistent. The model is doing well and has mastered correctly classifying the photos. On the test data, the model produced a loss of 0.25735 and an accuracy of 0.9241. The result of the digital image, accuracy is 0.973 on the validation set, which is quite high and on the test data, the model produced a loss of 0.26753 and accuracy of 0.93491. The significance of these results is that the model performs effectively, can reliably categorize test photos with high accuracy, and will be trustworthy for patients to utilize.
Item
Open Access
Augmented Reality Home Decorator
(North South University, 2019) AL-AMIN; SHARIEAZ KAVIER; Atiqur Rahman; 1520664042; 1513192642
This project presents an application of Augmented Reality (AR) for interior design. Due to huge advancements in computer vision algorithms and cheap hardware, Augmented Reality is becoming mainstream. All over the world, most of the sales come from physical stores. Buying furniture from brick-and-mortar shops is cumbersome and time-consuming. AR is changing the furniture industry. In an AR environment, virtual furniture could be placed and manipulated in the physical world in real time, which allows the user to have an interactive experience. Users would be able to visualize exactly how a table would look in their kitchen, dining room, bedroom, or anywhere they want. When people can place an actual couch in the living room or visualize how a bookshelf would look in a Different color. The risk of product return and logistics is drastically reduced. As online stores replace brick-and-mortar shops. AR will play a vital role in the furniture sales. This project provides new ways an individual/enterprise could utilize AR to design interiors.
Item
Open Access
Under Water Rescue Drone
(North South University, 2020) Al Shakline khan; Fahmida Alam Usha; Mohammad Momin; Mahmudur Rashid Remon; K. M. A. Salam; 1712095043; 1721645643; 1711370645; 1711224043
Remotely operated underwater vehicles (ROVs) are remote-controlled underwater robots driven by an individual on the surface. These robots are tethered by a series of wires that send signals between the operator and the ROV. All ROVs are equipped with a video camera, propulsion system, and lights. Other equipment is added depending on the specifications required. These include a manipulator arm, a water sampler, instruments that measure clarity, light penetration, temperature, and depth. Team Dubori was determined to recreate such an ROV in order to fulfill a specific mission. By using the system, an organization such as the military can explode mines underwater and also take real-time data of the river, which is also very helpful for rescue teams to identify the position of boats after any accident. The system has been designed in such a manner that it takes care of all the needs of a typical rescue team, and it is capable of providing easy and correct information about things underwater.
Item
Embargo
AUTONOMOUS HEAT SEEKING ROBOT FOR WASTE HEAT EXTRACTION
(North-south University, 2018-04-30) ATKIA SAMIHA; FARHAD HOSSAIN SARKER; ROZA NASER KHAN CHOWDHURY; DR. SHAHNEWAZ SIDDIQUE; 1431038043; 1430648043; 1430697043
The main aim of this project is to maximize the use of waste heat energy. The objective of this project is to detect higher heat emitting objects or surfaces and extract wasted heat energy from that very particular area and convert it into useful energy, such as electrical energy. Like a radar system, the autonomous vehicle keeps rotating until it locks under a threshold value of temperature. The servo motors help the robot to rotate 360 degrees. It uses non-contact thermometer sensor to detect the presence of heat emitting objects or surfaces. The robot will keep moving towards the object, until it reaches the pre-set highest temperature. Once it reaches its destination, with the help of thermoelectric generations, it absorbs heat from that very particular area or radius and converts the unwanted wasted heat energy into electrical energy.
Item
Open Access
Automatic Soil Irrigation System Using GSM Module
(North South University, 2020) Yaad Arefin; Saiful Islam; Mahdy Rahman Chowdhury; 1530702043; 1521065043
With the world trending towards new technologies and implementations, it is necessary to create in agriculture. Most projects signify wireless sensor networks that collect data from different sensors deployed at various nodes and send it through the wireless protocol. The collected data provides information about plenty of environmental factors. Observing the environmental factors can not be the complete solution to boost the yield of crops. Hence, automation must be implemented in agriculture to overcome these problems. So, purposely showing the solution to all such issues, it is necessary to develop an integrated system that will take care of all factors affecting productivity at every stage. But complete automation in agriculture is not achieved due to many issues. Though it is implemented at the research level, it is not given to the farmers to benefit from the resources. Hence, this paper deals with developing smart agriculture using IoT and is given to the farmers.
Item
Open Access
RER: Recycled Experience Replay with Dual Memory Architecture for Path Planning of a Moving Target using Deep Reinforcement Learning
(North South University, 2021) Samiya Kabir Youme; Hossain Ahamed; Towsif Alam Chowdhury; Sayeed Abid; Rusafa Binte Sohrawardi; Shahnewaz Siddique; 1711848042; 1711678042; 1712399042; 1711870042; 1711462042
All over the world, SAR operations are carried out to assist people in life-threatening situations. To search for a person in a life-threatening situation, the use of Unmanned Aerial Vehicles (UAVs) has increased drastically for different search and rescue missions to find the person at the earliest over the past few years. As UAVs are getting cheaper with advanced features like high-resolution cameras and long-lasting batteries, these devices are being used for autonomous search and rescue operations in different types of terrains and environments. These autonomous devices use artificial intelligence methods such as deep reinforcement learning algorithms for finding the optimal path and tracking the target. For marine-based environments, the target is continuously drifting with the ocean current, which makes it quite difficult for the UAV to search for the lost victim. In this project, we have made a simulation of a custom 2D marine environment and developed a dual memory architecture for finding the optimal path of a moving target to improve the learning of a UAV. We have incorporated our algorithm into popular deep reinforcement learning algorithms and improved the performance of classical algorithms by using our recycled experience replay. The results delineate that with a simple dual memory structure, immense progress in stable learning behavior can be obtained. The main goal of this project is to enhance the performance of prevalent deep reinforcement learning algorithms and test their performance in a simulated marine environment.