Department of Electrical and Computer Engineering (ECE)

Permanent URI for this community

https://repository.northsouth.edu/handle/123456789/10

In 1993, during the founding of North South University, the first private university of Bangladesh, the department was established in the name of Department of Computer Science. Since its inception it has gone through many transformations and transitions. The department continued with the same name till 2006 when it was renamed as Department of Computer Science & Engineering (CSE) as it had been offering Computer Engineering program from Spring 2003. As the number of students was growing and the demand for Electrical and Electronic Engineering was creating, the department started offering BS in Electrical and Electronic Engineering (EEE) degree from Spring 2009 and the department was renamed again as Department of Electrical Engineering and Computer Science (EECS) in that same year. Later on it was renamed again as the Department of Electrical and Computer Engineering (ECE) in 2014.

Browse

Now showing 1 - 20 of 70

Open Access
3-SURVIVORS: Rough Terrain Negotiable Teleported Mobile Rescue Robot with Object Detection
(North South University, 2019) Rafia Alif Bindu; Sazid Alam; Nusrat Jahan Moni; Dr. Shahnewaz Siddique; 1510080643; 1511394042; 1510531042
Today, technology is developing in the same direction in line with rapidly increasing human needs. The work done to meet these needs makes life easier every day, and these studies are concentrated in robotic arm studies. Robot arms work with an outside user or by performing predetermined commands. Nowadays, the most developed field of robot arms in every field is the industry and medicine sector. When we talk about robots, people tend to think that robots are only suitable to use in the industry or just for the scientist to test new technologies. However, the main function of robots is to help humans in doing work either in the industries or just helping out doing normal household chores. To bridge the gap of the normal perception of “robots are for the industries only” is omitted for our project. This project presents the development of a radio-controlled robotic arm. The movement of the robot arm can be controlled by a FlySky FS-CT6B 2.4GHz 6CH Transmitter and a radio controller. This robot can be used to demonstrate that a robot can be used inside a home or outside for daily human chores. The robot is controlled by Arduino that interfaced with the controller by a 500 GHz receiver. Designed and realized in the project, the robot arm has the ability to move in 6 axis directions with 6 servo motors. Two types of analysis was done for this project that is servo motor analysis and accuracy test. The accuracy test shows that the results of the actual output of the servo motor as compared to the input send to Arduino Uno via controller is between 90% to 95%. This prototype of the robot showed that the operation was successful. This user-friendly robot is expected to bridge the gap between robot and household chores
Open Access
A Comparative Study of Machine Learning Techniques for Autism Spectrum Disorder (ASD) Detection
(North South University, 2022) Zahid Hasan; Towsif Muhtadi Khan; Dr. Atiqur Rahman; 1911509042; 1911576042
Autism Spectrum Disorder (ASD) is a developmental impairment caused by brain differences. ASD patients may have a recognized difference, such as a genetic disease [1]. Autism can be diagnosed at any age and is referred to as a "behavioral disorder" since symptoms often develop within the first two years of life [1]. In this study, we have implemented different classifier algorithms such as Decision Tree Classifier, Logistic Regression, and Multi-layer Perceptron classifier (MLP Classifier) for detecting ASD in three types of people - adults, adolescents, and children. The proposed techniques are evaluated on publicly available three different non-clinically ASD datasets [2]. After applying various machine learning techniques and handling missing values, results strongly suggest that ANN-based prediction models work better on all these datasets with higher accuracy of 98.58%, 98.30%, and 95.24% for Autistic Spectrum Disorder Screening Data for Adults, Children, and Adolescents, respectively.
Open Access
A Deep Learning approach using Action Recognition for Pedestrians & Vehicle Overtaking of Bangladesh Highway Road Dataset & it’s Implementation
(North South University, 2022) Kazi Tamzid Akhter, Md Hasib Iftekhar Islam Khan Pranta, Shams Saniat, A. S. M. Samiul Islam ; Dr. Nabeel Mohammed; 1620570042; 1721194042; 1821848042; 1921826042
Intelligent transportation systems have been met with resounding approval from individuals, governments and automobile manufacturers located all over the globe. The primary problems in the field of intelligent and self-driving & non self driving vehicles are identifying impediments, particularly people, and preventing accidents with them. In order to advance intelligent transportation systems for both self-driving cars and all other manual cars, we focused on using deep learning methods to identify pedestrians. After that, some of the most popular deep learning techniques were covered. The accurate identification of pedestrians in self-built automobiles still has a lot of flaws. This study highlights the challenges the transportation industry faces. The solutions are intended to help reduce traffic, accidents. Large automakers (including Google and Tesla) , working to develop self-driving and non-selfdriving vehicles that can transport passengers safely even while the driver is sleepy. Sensors that can sense their surroundings, identify what is close by, and communicate that information to the driver must be installed in these cars. neural networks, which often include several hidden layers and nonlinear processing units, are the basis for most deep learning approaches.
Open Access
A Machine Learning and Embedded Approach to Detect Fire, Identify the Cause of it and Extinguish Using the Best Possible Extinguisher
(North South University, 2023-02-01) Md. Rashiqur Rahman; Sabbir Ahmed; Md Shafin Islam Rudro; Sadia Aktar; Md. Shahriar Hussain; 1812366042; 1813515042; 1821054642; 1821516042
Chemical fires are a major cause of devastating situations and fatalities in Bangladesh, where inadequate knowledge of extinguishing such fires has led to numerous deaths, including those of firefighters. To address this issue, we propose a machine learning and embedded systems approach to design a dynamic and portable prototype that can remotely monitor the fire incident and determine its cause. The prototype uses a dashboard camera to stream video and gas sensors to detect the chemical gas information in the environment to identify and extinguish the fire. The embedded approach clarifies the cause of the fire and suggests the most suitable extinguisher to the user. The device is economical, portable, user-friendly, and marketable in Bangladesh. The system produces satisfactory results with high accuracy in fire detection and maintains its objective of being low-cost and user-friendly. The device can be remotely controlled using a mobile phone and web-based application. The system's machine learning approach uses appropriate datasets and algorithms (YOLOV5), while the embedded approach employs suitable sensors and a microcontroller (ESP32). The system's accuracy has been shown to be perfect.
Open Access
A Smart Online Medicine Selling System Along With DIMS And BDMS
(North South University, 2020-06) Muttakin Ahamed; Md. Golam Haider; Monjur A-Elahi Tanmoy; Dr. Tanzilur Rahman; 1610830042; 1620218042; 1620587042
An Online Medicine Selling System is a platform where the user will be able to buy medicines online. There are some websites available in our country running online medicine selling systems. But the change we have made in ours is to sell not only New Medicines but also Unused Medicines by the user. Pharmaceuticals, generics, and indications will categorize each of the medicines. Pharmaceuticals will help users to know from which company this medicine has been produced, generics will allow users to know which type of drug it is, and indication will help to know for what disease or problem you need to take that medicine. Secondly, we made a Blood Donor Management System from where the user will find out blood donors available in our country for their needs. And finally, we made a Drug Information Management System, which will help users know about medicines in detail like pharmacology, indications, contraindications, side-effects, precautions, dosage & administrations, and so on. We planned to make a platform that will be a complete hospitality system related to the medical sector that will be a great help for the people of our country. From this thought, we collaborated on three important sectors of medical sectors under one single platform.
Open Access
All object on-chip tractor beam using SPP
(North South University, 2022) Masudur Rahim; Md. Mohaimanul Masud Sunny; Fahim Al Ifran Rahim; Dr. Mahdy Rahman Chowdhury; 1320251043; 1220446043; 1320650043
In this paper we designed an on-chip configuration where implementation of an all object optical tractor beam was made possible. By all object, we are referring to spherical nanoparticles of dielectric, plasmonic and chiral material. This tractor beam was composed of the superposition of two evanescently confined surface waves called SPP (Surface Plasmon Polariton), which was excited over the on-chip base by the incidence of a plane polarized laser light propagating vertically upwards. Arrays of nanoantenna like structures called metasurfaces has been used in this setup to manipulate the evanescent surface wave. Exerting pulling force is only possible when the beam incident over the particle has a non-paraxial nature. In reality, non-paraxiality of a beam is a somewhat hypothetical requirement. However, this issue is resolved by creating an interference field formed by the superposition of the SPP beam along with the induced effect within the particle and the substrate which led to the emergence of this backward pulling force. Pulling force was realized within certain diameter range (Mie Range). To the best of our knowledge, this article stands as the first proposal of realizing all object tractor beam in an on-chip configuration where the configuration itself is mitigating the paraxiality issue for all objects and using the same setup, pulling of such particles can be realized. Our work can be extended to sorting of particles in an inhomogeneous mixture, such as analysis of biomolecules.
Open Access
An economic and automatic water quality monitoring system in the light of industry 4.0
(North South University, 2022-04-22) Abrar Zuhaer Tariq; Dr. Mohammad Monirujjaman Khan; 1431152043
Water quality monitoring is significant for sustainable aquaculture. It helps to reduce the risk of unwanted fish loss due to poor water quality, as a result, farmers can maximize profit. DO, Ammonia, pH, Temperature, Turbidity and TDS are the key parameters and their correct level in water ensures favourable conditions for aquaculture. However, in the aquaculture industry, DO and ammonia measurement with digital systems are costly. Eventually, it is inevitable for the aquaculture farmers to measure the other parameters (pH, Temperature, Turbidity and TDS) by the side of DO, Ammonia. Therefore, we have developed a system in the light of industry 4.0 with the aid of IoT that can monitor automatically the above-mentioned water quality parameters without human involvement and keep the users updated remotely with the help of an android app. The system is expected to achieve more than 98% accuracy in DO tests and nearly 99+% accuracy in ammonia measurement in water. Other parameter readings like temperature, turbidity, and PH have produced a high precision result as modern sensors are used. Our study shows that the developed system can cut down the overall cost (accusation and test) by approximately 85% and it will open a new door of opportunity for aquaculture automation. DO, Ammonia, PH, Temperature, Turbidity and TDS
Embargo
An Intelligent Traffic Control System for Trouble-free Movement of Ambulances and Fire Trucks on Heavy Traffic Roads in Bangladesh Using YOLOv5 Algorithm and GSM Module
(North South University, 2022) TASFIA SAMIN; FARZANA HAQUE; NESHAT ANJUMAN MOURI; Md. Shahriar Hussain; 1821823042; 1821386042; 1812749042
One of the biggest problems developing countries like Bangladesh are facing is traffic problems. Especially metropolitan cities in a country need a proper traffic control system for stress-free movement, so the situation gets less stressful. This work has been designed to create a smooth- movement process for emergency vehicles like ambulances and fire trucks, which needs to be accessible as soon as possible during traffic congestion. The system would notify the traffic controller after detecting the emergency vehicle among all the stuck vehicles. This work uses a dataset constructed and labelled manually. To train the model, we have used the YOLOv5 algorithm. The accuracy of our model is 94%. The model detects emergency vehicles like ambulances and fire trucks as well as other vehicles captured by the CCTV camera of the road. However, only the detection of emergency vehicles would be notified to the traffic controller through Arduino Uno and GSM Module. That way, the traffic controller could clear that road for the easy movement of those emergency vehicles.
Open Access
Arduino Based Apartment Security System with Automation
(North South University, 2020) Faysal Ahmed; Md. Mozammel Hossain Fahim; Manjida Islam Mohona; Sadia Awal Alo; Kanij Fatema; Dr. Riasat Khan; 1620491042; 1611685042; 1611328042; 1612155042; 1610161042
One of the most prominent things in the home security solutions is IOT(Internet of things)that can handle layered security based on any advanced algorithm. But most of them lack proper management issues besides backups and volatile issues. Beside those it has cost efficiency issues. In fact most of them can have much needed features like home automation, portability and command operations. This papers aims to provide a high quality and reliable home security that supports home automation, portability, data records, backups, data encryption and IOT. It has introduces friendly home operating system is a single master device that handles other slave devices. Portability and flexibility is the beauty besides the security layers is strength of the device. The device's price range was kept to a minimum level to make it easier for home implementation alongside providing a quality security.
Open Access
Automated Customer Complaint Processing for Business Development Based on Natural Language Processing and Federated Learning - Case Study of Laptops
(North South University, 2023-01-01) Md Ulfat Tahsin; Md Saeem Hossain Shanto; M. Rashedur Rahman; 1913057642; 1912218042
Empathy is considered one of the key elements while developing a better version of any product or service. Recent developments in online shopping, business analytics, and business intelligence are taking organizations to sky-high profit margins. Many big and small organizations invest huge capital in collecting and analyzing customer feedback and market information. It is often a tedious process as it takes a long time to reach the manufacturers as they think of developing a better version of their products. Whereas companies performing no market research often fail to promote and increase the sales of their products due to a lack of empathy and failure to understand customer satisfaction and demands. Keeping that in mind, we put forward a complete system to generate product summaries, customer dissatisfaction reports, and graphical illustrations of the product based on customer reviews, complaints, and feedback, depending on their usage history. We employ Natural Language Processing to classify and analyze customer reviews and feedback and extract issues that customers face while using that product. Federated learning is utilized to ensure the data privacy of the participating clients, deal with non-uniform data distribution, and reduce the stress on the central server. With federated training rounds, the NLP models are updated after each round of federated computation using the FedAvg algorithm. We also analyzed the impact of federated training on the three BERT variants (BERT, DistillBERT, and RoBERTa) for performing the classification task, which is later managed by our web application system to generate an overall product complaint report and graphical illustration. The best result was obtained by the RoBERTa variant during our experiments. On our web application, the bestperforming model variant is deployed and tested. The simulation and web application show that our suggested system can be implemented successfully.
Open Access
Automated Face Recognition Attendance System
(North South University, 2020) Md. Zahidul Hasan; Aishwaria Roy; Mohammad Abdullah Siddiky; Monisha Saha; Tahamina Akhter Akhi; Mohammad Rezaul Islam; 1510942042; 1610624042; 1620641042; 1631667042; 1611937043
To any company or any organization taking attendance is a must. In this era, there are many types of attendance system. These are RFID based attendance system, fingerprint-based attendance system or traditional hand note attendance. Those processes that we have described so far are time consuming to record as well as it cannot guaranty the presence of employees in the office between full office time. Those two barriers, which forced us to find a way, which will ensure the presence and increase the productivity time of employees. In our senior design project, we have tried to find a solution of those two problems. Here we have proposed a system that will automatically take the attendance of each employee in every 1 minute to update presence status of each employee and register it in the database. This method will ensure the presence of employees in the office as well as it will save time of taking attendance.
Open Access
Automated Fisheries Water Quality Monitoring System
(North South University, 2020-04-30) Tanbin Akter Mitaly; Paplu Dash; Md. Shahriar Hussain; 1712438642; 1611420043
Fisheries is one of the main prospects to grow economically also we benefit from it by the production of food and the nutrition that is required us to live by. For fisheries, it's important to maintain good water quality as it is an important factor that affects fish health and performance in the aquaculture production system. It matters what type of fish we are culturing in our system due to different fish species need a different range of water quality aspects in which they can survive. Different fish species have a different optimized point to growing well. Don't maintain the water quality can result in parasite infestations, poor growth, erratic behaviour and various disease system. The water quality is dependent on climate, seasonal changes also how a culture system is used. To maintain good water quality conditions we need to look at physical and chemical components of water that have an impact on water quality.
Open Access
Automated Parking Entrance System Using Different Approaches
(North South University, 2020) Md.Naimul Islam Suvon; Mehebuba Ferdous; Riasat Khan
Automatic license plate identification in today's world plays a vital role in vehicle tracking and organization. Our proposed model of automation in the detection and recognizing vehicles through the use of number plate computerization is expected to create a new scope of evolution for large cities. The machine can be used for the parking system of motor vehicles, as well as to collect tolls. The detection of the Bangla license plates from different cities and multi-class vehicles is the first step of the proposed system. The license plate detection has been performed with mathematical morphological approach and the Faster R-CNN architecture. Next, the Tesseract Optical Character Recognition system, in conjunction with the Bangla character recognition model, has been used for vehicle indexing. We are also planning to make an application for the parking lot system. That will manage all the information about the parking lot system. Numerical results demonstrate that the accuracies of license plate detection for the computer vision and Faster R-CNN are 95% with limitation and 98% without any limitation, respectively. Finally, our model achieved an accuracy of 96% for character recognition with some limitation.
Open Access
Automatic Sleep Stages Detection Using Supervised Machine Learning
(North South University, 2020) Saidul Islam Tanveer; Tangim Hossain Akash; Rakibul Hoque Foysal; Dr. Tanzilur Rahman; 1611556043; 1530092042; 1431238043
Sleep is a natural behavior and part and parcel of Human‟s life. Nowadays, sleeping disorder is common question for both man and women. So, sleep related research is accelerated by researcher and heath care community. Sleep research can achieve the better way for diagnosis and treatment of sleeping related complaint. Over the past few decades, sleep classification is introduced. Automatic sleep stages classification is preferable approach for sleep researchers. Manual sleep scoring also visible Sometimes, nowadays. There is lot of difficulty in manual scoring which is very time consuming and prone to Human error. Automatic sleep stages classification using Machine learning model can create a great solution for diagnosis purpose. Different kinds of machine learning algorithms are used by many researchers. Here, in this research we use multiple supervised machine learning model to classify the sleep stages. In this research using EEG patterns of healthy and mild difficulty subjects over 95% of accuracy is obtained by the classifier. Total 31 features (spectral and statistical features) is applied to dataset before that 10 features were taken. For finding the significance nature of features Kruskalwallis anova test is applied. After that using Knn, Decision tree and Bagged tree algorithms evaluated the model accuracy. Bagged tree algorithm take vital role in accuracy which is higher than two other algothoms.So, the model used in this thesis is effective for both healthy and mild difficulty subject.
Open Access
Automatic Vehicle Detection and Counting System for Traffic Analysis
(North South University, 2020-12) Foizur Rahaman; Shadat Irtisamul Haque; Muntasir Karim Chowdhury; Imran Mahmud Sadman; Zunayeed Bin Zahir; 1620551042; 1610835042; 1620633042; 1610940042
Traffic Analysis has been a serious problem that urban planners and engineers are doing research to deal with. They are developing smarter ways to reduce or solve this serious issue. Traffic problems aren't a new issue but it is increasing day by day in many parts of the world due to the increase in vehicles. It is especially very evident in developing countries. Analysis of traffic is very significant and may be used to count the number of vehicles in an area or a lane. Over the time these systems have matured big time and some of them are highly effective, but all of them are not very budget friendly. The Government has to pay a hefty amount of money to maintain these services time and again. Sometimes in a manually traffic controlled area where three or more roads are connected, we see traffic police releasing one of the roads or direction frequently. But, the other direction or lanes are full of vehicles that he does not know. If some device or system could tell him the number of vehicles on the road, that would reduce traffic in that area. This device or system will also help them to take precaution in that particular time to increase traffic police or to take other necessary steps as they will be able to know the rush hours on a daily basis. Therefore, this study has proposed a vision based vehicle counting. We propose a solution which will aim to detect and count vehicles from Surveillance Footage (TSF) or video.
Open Access
Bangla Handwriting Recognition
(North South University, 2019-02-28) Sakib Mahmud; Arindam Kabir Ahmed; Sidratul Muntaha; Syed Athar Bin Amir; 1620802042; 1612010042; 1611756642
This report presents the design and implementation of a Bangla Handwritten OCR. This project is going to be useful for both the government and the general people. The software can be used to easily convert a handwritten Bangla document to editable text, i.e, we are going to digitize the handwritten text. We are going to take an input image of the handwritten text. The image is then preprocessed in various steps and then sent to the model. After that, the output is shown. The principal idea is to convert images of text documents such as those obtained from scanning a document into editable text.
Open Access
Bangla Word Detection by Extracting Texts From Images
(North South University, 2020) S. M. Ashiqur Rahman; Md. Golam Mortuza Bhuiyan; Waseq Ayon; Abdullah Al Nauman Shuvo; Syed Athar Bin Amir; 1510039642; 1511710042; 1521061642; 1510041042
We will create a model that will be taking images as input and extract the Bangla words from there and translate it into English. The main idea is to recognize Bangla texts from images, extract it from there and translate it to English. We will use the knowledge on OCR, NLP, Google Cloud API, etc to make it happen. This application will be helpful to foreigners who will come to visit Bangladesh but don’t know Bangla. They can read any instruction and signs written in Bangla only by taking a photo of the sign and uploading it to our application to get the output. 8
Open Access
Blind Person Assistant - Object detection With Voice Feedback
(North South University, 2022) Mosarrat Shazia Kabir, Syeda Karishma Naaz, Simon Uddin, Sanjida Akter,; Md. Shahriar Hussain
This project was specially implemented to help visually impaired people. The project can detect different objects in real time, counts them, and delivers voice feedback. Since our project is an object detection system, the first thing we needed was a proper dataset. For this project, we used two datasets. One is from the Microsoft COCO object detection dataset, and another is from the Kaggle object detection dataset. However, the Kaggle dataset was not preprocessed. Therefore, we had to resize the image, and along with that, we had to make all the images in the same color format. To process the images, we used "OpenCV" as an image processing tool. Next, we moved to set the algorithm to train and test our system. We chose to use two commonly used algorithms. One is the SSD Mobilenet algorithm, and the other is the YOLO Algorithm. In our project, we used SSD Mobilenet v2, YOLO v4, and YOLO v7, which are one of the fastest and most accurate object detectors. The accuracy we got for SSD Mobilenet v2, YOLO v4, and YOLO v7 was 94%, 94%, and 98%. Among the three models, YOLO v7 had the highest accuracy. Therefore we chose YOLO v7 for further work. Then we implemented GTTS (Google Text To Speech) and a counting function that counts the object classes. Eventually, the system counts the objects in real-time detection, and with the help of GTTS, it returns voice feedback.
Open Access
Blockchain, IPFS, and Encryption based framework for disease diagnosis on smartphones
(North South University, 2020) Hasib Mahmud; Dr. Tanzilur Rahman; 1621065042
People are using many wearable sensors and medical IOT(Internet of Things) devices nowadays to measure and to diagnose their personal health status. Measuring heartbeat is one of them. Irregular heartbeat rate can indicate many potential or existing illnesses. But these sensors and IOT devices can be expensive and may not be easily available in the market. At present, we mostly use smartphones which need not to be very expensive and are easily available. We can offer rich reports using machine learning based on patient’s data. So, we have built a cloud based smartphone application framework that collects data (primarily heartbeat rate) from users using available sensors (e.g.: microphone), and processes the data with the help of machine learning scripts and maintains data integrity. Personal Health Record (PHR) service is becoming a valuable source of data for hospitals and doctors. It has become necessary that the patient keeps the ownership of the data, securely organises, shares these medical data and can remain anonymous in this system. In order to achieve these goals, we are going to implement Blockchain, IPFS, and Encryption technologies in a virtual private network, applications of which are getting very popular in health care services. This implementation complies with General Data Protection Regulation (GDPR). There are already some papers written on how we can implement Blockchain in the health care system but very few have been implemented till now. Besides, the use of cryptocurrencies for each transaction in Blockchain increases the overall cost and Blo
Embargo
Change Detection Analysis and Characterization of Land Components in Sylhet Division Using Remote Sensing
(North South University, 2020) Novera Tasnova Chowdhury; Sifat Jahan; Md. Shohug Hossain; Shourav Purkayastha; Dr. Shahnewaz Siddique; 1520378042; 1611702642; 1610193042; 1512325042
This paper illustrates the result of changing in different types of land cover of Sylhet Division of Bangladesh using Remote Sensing techniques and multispectral satellite image data from 1990 to 2020. Unsupervised classification is used to analyze the trend of changes of the components of land cover over the past decadal years and changing variation in different months (January, February & March). The spectral and spatial analysis are being done to characterize the land cover components in different months. The maps are created by using high resolution images such as LANDSAT 5 and LANDSAT 8. The overall analysis is indicating that different components of land covers in Sylhet division is decreasing over the past decadal years due to loss of natural soil nutrients, loss of natural water reservoirs and of their resultant benefits, increase in the occurrence of flooding and degeneration of wetland-based ecosystems, occupations, socio-economic institutions and cultures. Increased population in Sylhet division is another reason for the awful situation of land cover areas within the four decadal years.

Browse

Browsing Department of Electrical and Computer Engineering (ECE) by Subject "TECHNOLOGY::Electrical engineering, electronics and photonics::Electrical engineering"

Results Per Page

Sort Options