NSU IR :: Browsing by Author "Dr. Shahnewaz Siddique"

Browsing by Author "Dr. Shahnewaz Siddique"

Now showing 1 - 20 of 25

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 Real Time Pothole and Speed Breaker Detection Using Deep Learning
(North-south University, 2019-04-30) Zahid Hasan; Tasmia Rahman Shahidi; Samsoon Nahar Shampa; Dr. Shahnewaz Siddique; 1510846042; 1521367642; 1511148042
The road accident rate in Bangladesh is increasing day by day due to various reasons. One of these reasons are poor road conditions. Unwanted potholes, missing pitches, improper speed breakers, unfinished manhole covers and slabs transform many roads into obstacles courses thus greatly increasing the probability of serious accidents. However, the arrival of new assistive driving technologies hold much promise in making the roads the safer and avoid serious accidents and damages. The main goal of our project is to create real-time assistive technologies to detect potholes and speed breakers for on-road drivers in general but especially for bikers and cyclists. Our system will provide drivers with advance notification about upcoming potholes and speed breakers and thus assist in avoiding unwanted accidents. Our system will provide drivers sufficient time to react to and avoid these impending road hazards
Open Access
BanglaSense: Bangla Text Summarization Using Generative AI with Large Language Model
(North South University, 2023) Md. Jahidul Islam; Dr. Shahnewaz Siddique; 1831533042
Text summarization is used in various domains, such as generating concise summaries of news articles, documents including research papers, social media’s long-form posts, and conversations to quickly and easily understand a long text. On abstractive text summarization, due to the scarcity of datasets and computing resources for mid-level languages, recent efforts have concentrated mostly on high-resource languages like English. In this research, we propose a Bangla Text Summarization system Using Generative AI with a Large Language Model. We use in-context learning techniques and instruction fine-tuning to train the mT5 pre-trained multilingual Transformer model on the XL-Sum (Bangla) dataset from the Hugging Face library. Our fine-tuned model performed the best in terms of relevancy and correctness with a remarkable 45.41 rouge1, and 33.85 regulome Scores.
Open Access
BOMB DEFUSAL ROBOT
(North-south University, 2021-08-30) AL AMIN HOSSAIN; G.M. MUSTAFIZUR RAHMAN; LAMISA TASNIM; Dr. Shahnewaz Siddique; 1620017042; 1713056642; 1811472642
Robotics is the pinnacle of success in the field of engineering. People uses robots to do from simplest household works to complex tasks in space. Bomb disposal robot is a tool to help the bomb defusing squad. It's a four wheeler steel bodied robot with a 4 DOF arm. A camera and metal detector is used to give feedback to the user. All functions can be remotely operated by a controller. DC servo motor is used as actuator of the arm and it's controlled by a micro controller. A total of 4 motors (2+2) are parallelly connected to aid movement in all directions. The goal of this project is to find, inspect and dispose bomb while keeping humans at a safe distance. This paper contains methodology of development of a bomb disposal robot with 4 DOF arm
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.
Open Access
Designing an Electrical Energy Storage System for Commercial and Residential Use by Using Solar Energy
(North South University, 2020) KASHFIA MAHMOOD; JAHIDUL ISLAM; MD. AL – AMIN BHUIYAN; MD. IFTAKHAR HOSSAIN; Dr. Shahnewaz Siddique; 1610376043; 1610441043; 1610458043; 1611865043
Electrification is one important goal for any developing country like Bangladesh for bringing about social and economic developments. But unfortunately, there is no supply or insufficient supply of electricity in many remote areas of Bangladesh which protract the developments of whose areas. As a result, both government and nongovernmental organizations are trying to introduce solar power system in those areas. However, for being expensive, donor driven and fragile the expected results haven’t seen. On the other hand, many people are using diesel or petrol generators which produce sound and emit Carbon dioxide in the air, consequently pollute the environment. Therefore, this research focuses the way to solve these problems and produce a new environmentally friendly power system to provide electricity in those areas. In this system using concave mirrors to concentrate the rays of sunlight to evaporate water then using the steam, turbine will be rotated to generate electricity and stored in battery as power to supply to the load when needed.
Open Access
ELECTRONIC VOTING SYSTEM সুনির্বাচন
(North South University, 2020) ALISA HOSSAIN; MD. TANVIR NEAZ; Md. HAIDARUZZAMAN; Dr. Shahnewaz Siddique; 1522014042; 1530716642; 1610977042
Using the decade old election system to collect votes from the citizens is no longer considered efficient due to the various recurring errors. So time has arrived that the paper based primordial voting system which has already proven itself an inefficient and slow procedure is changed immediately. The system that is being followed currently, from data collection procedure to counting of the votes is a manual process. Here we are proposing an automated electronic voting system. It starts with automated registration system that will provide the secured database of the voters’ information. Voter details will be stored against their finger prints in the main database. The election commission authority is authorized to access the details but they aren’t authorized for modifying or changing the details. Modification of the voters’ information requires the fingerprint of the particular voter. So the system will help to minimize the corruption done by others, and hopefully corruption may be diminished at some point of time. In this system Voter will select his/her preferable candidate by providing his or her opinion on a touch screen where all candidates’ voting sign is displayed. Among them one application server will work as dispatcher. The encrypted votes will be sent from the client to the dispatcher through an application server and this layer will send those votes to main database through another application server. They will be counted there automatically which will take lesser time than the manual system. So the result will be faster, more accurate and reliable.
Open Access
EVENT DETECTION
(North South University, 2022-12-30) Md. Alamin Hossain; Bibi Aysha; Md. Mehedi Hasan; Dr. Shahnewaz Siddique; 1821570042; 1822162642; 1811145042
Today people are not so careful about their life. so we know that awareness is the key error in anyone’s life. But in the modern world, we clearly see that people are not so aware. That's why many kinds of incidents happen in people's lives. The events mentioned on social networks are related to topics, locations, and time periods. The events are a range, like celebrities or dogmas, native social events, accidents, protests, or natural disasters. Messages square measure denoted by users once they need knowledge about or witnessed the events happening within the real world and that they need to share their experiences now. individuals conjointly categorical themselves ad libitum with reference to the social events in their social networks. Instead, policy-makers might want to grasp the emotions of users for a selected event to create knowing choices. With the increasing variety of real-world events that square measure originated and mentioned over social networks, event detection, and pursuit is changing into a compelling analysis issue.
Open Access
ExoArm: Patient Rehabilitation, Mobility and Heavy-lifting, using COTS products
(North South University, 2019-04-30) Tanzim Bin Khalid; Kazi Azmain Faieq; Md Muhtasim Alam Chowdhury; Dr. Shahnewaz Siddique; 1520894043; 1512200643; 1520334643
Exoskeleton, a revolutionizing new term which has taken the world of technology by storm in the last few decades. A technology, improving at a rate faster than anticipated. Some living organisms are found to be naturally supported by external skeletons, giving birth to the concept of exoskeleton where human beings who are physically disabled are to be supported by an external framework to support and aid them in their day to day activities. Therefore, using the concept of exoskeleton we plan to build an automated, at the same time independent, mechanical arm for rehabilitation and providing aid to the people who are suffering. In addition to the primary goal, our device will also be able to aid people without any disabilities, in performing daily chores or lifting heavy objects. We plan to execute this system using commercially off the Shelf Components (COTS) such as: Arduino, Myoware Muscle Sensor and Linear Actuator, having researched on efficiency and cost of other relevant components. The sensor will sense the EMG signals from the targeted muscle group, the Arduino will convert these signals to analogue values and eventually send in the commands to linear actuator for execution. If successful, affordability and reliability will be maximum, making sure such a high-end product is available for the masses.
Open Access
Eyes For You A Deep Learning IoT device to assist visually impaired persons
(North South University, 2022-01-01) Abu Zafer Md. Fahim; Fahmida Alam; Minhajur Rahman Rifat; Dr. Shahnewaz Siddique; 1821677642; 1821204042; 1821569642
We live in an era where people occupy their own lives. All have to make their living depending on none. Nevertheless, some people need the help of others to do their daily chores. They can be disabled, blind, or physically challenged. Among them, visually impaired persons suffer the most even in this modernized world, as any alternative to eyesight has not been invented yet. Also, people’s eye health may get worse with time. Irrespective of the way of visual impairment, individuals suffering from it feel burden to others. So, we are trying to help them make their lives a little easier than usual through our machine. We have proposed a machine that will help people walk safely anytime. The device helps the user detect any obstacle, measure the distance between the user and the obstacle, measure the obstacle's speed or velocity, and the direction of the obstacle. Our device can detect up to 80 objects and inform our users that there is obstacle around him, that is how he can move freely around hous
Open Access
Game AI Agent using Deep Reinforcement Learning
(North South University, 2020-08-30) Md. Rafat Rahman Tushar; Fariha Islam Faiza; Md. Nuruzzaman; Anas Uddin; Dr. Shahnewaz Siddique; 1621450042; 1620518042; 1621557042; 1520143042
Nowadays, the field of deep learning is expanding very fast. We can use deep learning strategies in almost all of the decision making, intelligence problems as well as searching from insanely big amounts of data. In this project, we present an AI agent that learns how to play games from visionary input data. We, humans, also play games by seeing the screen where the game is being played. Our games have limited discrete action space. Our goal is to train an AI agent that has no previous idea of the games’ environments but can successfully learn the strategies of playing games and get scores same as humans. Even we have managed to gain scores more than humans. Our model successfully learns how to play games effectively and in a short amount of time. As we are working with image data, we have to consider the difficulties of processing and training that huge amount of data. Eventually, by implementing a model based on some deep learning strategies, we were able to reach our goal.
Open Access
Gender & Age Detection using CNN and Deep Learning
(North South University, 2022) Lamia Akter Shahinur; Mahmuda Akter Meem; Kaniz Fatema; Md. Mobasshir Miah; Dr. Shahnewaz Siddique; 1821023042; 1821029042; 1821382042; 1911248642
An application for video data analysis based on computer vision and machine learning method are presented. Novel gender and age classifiers based on adaptive features, local binary patterns and support vector machines are proposed. As features for the gender and age estimation, facial shape, skin texture, hue and Gabor feature are used. In order to show the effectiveness of proposed method, not only real-age database of facial image but also appearance-age database is employed. We also analyze the facial features characteristic to each age category and gender, and examine the difference feature of between the real-age and appearance-age in a facial area. Moreover, we examined the left-right symmetric property of the face concerning gender and age estimation by the proposed method. The promising practical application of such algorithms can be human-computer interaction, surveillance monitoring, video content analysis, targeted advertising, biometrics, and entertainment.
Open Access
Learn World Image Captioning Using Machine Learning Algorithm for Android Application
(North South University, 2019-08) Hamdan Kaiser; Sayeda Islam Nahid; Dr. Shahnewaz Siddique; 1512080042; 1510897042
Learn The World, an object learning based Android application, developed based on Machine Learning and Image Captioning. An android application that generates a description of an image that we know as image captioning. Image captioning works after recognizing the important objects, their attributes and their relationship in an image. From the following concept, we aim to designing a learning application, developed based on Image Caption using Machine Learning that detects objects from real time images (means an image taken instant) or previous taken image and describe image behavior with the help of speech descriptor with modifications. Also, our application marks each individual objects according to object annotations and lists the name of particular object on images into machine encoded text with its accuracy. Means it can be used for many purposes like recognizing objects from images, helping children to learn the surrounding behaviors, detect particular objects and so on. That means if anyone, specially a child takes a picture of an event surrounded by them the application will first introduces them with the object included in that picture. And it helps them showing accuracy of the objects present in the picture. They can see the caption and by speech descriptor they can acquired knowledge about the correct pronunciation. This application is very much informative related to children for every day’s knowledge gathering.
Open Access
Leveraging YOLOv5 Object Detection on Satellite Imagery: A Comprehensive Building Damage Detection and Severity Assessment System for PostDisaster Environments
(North South Univesity, 2023) Abdullah Hel Asif; Shafin Ahmed Zidan; Dr. Shahnewaz Siddique; 1911331642; 1912891042
Leveraging YOLOv5 Object Detection on Satellite Imagery: A Comprehensive Building Damage Detection and Severity Assessment System for Post- Disaster Environments Natural disasters are a plague that has haunted life on Earth from the beginning of time. Whenever a natural disaster occurs first responders and aid workers always have to put their lives on the line to save the ones in need. The basis of our work is the creation of a system that can detect and analyze the severity of damage on post-disaster environments caused by natural events. Our Deep Learning based system is able to recognize damaged buildings and surrounding areas caused due to earthquakes, floods, etc. from satellite images and simultaneously assign a damage severity rating to it. We have made the use of the YOLOv5 model based on PyTorch as the backbone of our system. Our project will allow the first respondents and aid workers in question to efficiently distribute their resources and provide help based on degree of severity of damages in the event of a natural disaster.
Open Access
NSUECE_HELPDESK: An Intelligent Assistant for ECE Department
(North South University, 2019-08-31) Mumin Az Zahira Maria; MD. Rifatul Islam Rifat; Marjana Rahman; Dr. Shahnewaz Siddique; 1430117642; 1511704042; 1510010042
We have designed a chatbot for the Electrical and Computer Engineering Department of North South University, with a great deal of information about the department. It is very much structured with the data about course curriculum, faculty details, department’s necessities, and other requirements for students. As a student of Electrical and Computer Engineering Department, sometimes we don't get that much time to go here and there for a single information. Our fundamental objective for making this to save the spare time of a student. In this chatbot we planned the inquiry of users dependent on phrases, keywords and examples. It is particularly simple to have almost desired answer by giving just single word by any user. We have planned this for the student of Electrical and Computer Engineering Department as well as the outsiders who needs to think about to know any information with no problem. Looking in sites for quite a while, it is smarter to simply open our chatbot application to locate the precise information. it is connected with Google Assistant, so user just need to consider that for reacting our chatbot which is additionally very much time consuming for occupied student
Open Access
Online Tutoring Platform for NSU Students - TutorYouNSU
(Northsouth University, 2019-05-03) Saad Islam; Samia Ahnob; Dr. Shahnewaz Siddique; 1331278042; 1321615042
TutorYouNSU.com is the first online peer-to-peer tutoring platform designed to help NSU students connect with NSU Tutors. It will help NSU students connect with NSU Tutors directly. Students will be able to get both online tutoring and in-person tutoring. It will help students get better grades and make their courses easier. As an NSU student, they will have access to our high quality NSU Tutors for their particular course. They will also have online access to all resources and course files that can be updated in real-time by faculties, so that students will always have the latest file. The aim of TutorYouNSU is to make it easier to help connect students who needed help in a certain course with students who had already completed that course. All tutors have completed the course (under a particular faculty) they will tutor. They know exactly what to expect and how to do well on that particular course. Each tutor has their preferred tutoring times on their own page. Tutoring everywhere has been increasing each day. Moreover, it has been shown to very useful for students. There will also be video tutorials on our website for each course. TutorYouNSU will also have other educational tools and features such as the ability to download a GPA calculator, get an unofficial grade sheet via online, and do their course analysis online by themselves from home. That willsave the students a considerable amount of time, so that they can concentrate on their education instead. It will also ease pressure off the university authority who will have a lower number of students go to them to solve their problems, since now many problems can and will be solved by the students themselves.
Open Access
Personal Protective Gear Detection Surveillance System
(North South University, 2020-12-30) Amzad Hossain Rafi; Md. Adban Akib Protik; Dipto Roy; Dr. Shahnewaz Siddique; 1530520642; 1610523042; 1530639643
The world in present days is going through a tough time and every country a suffering from the present pandemic caused by covid-19 and also at present there is no 100% curable vaccine of this disease. Covid-19 is spreading in rapid rate form one person to another. To minimize the spreading of this diseases WHO (world health org) provided various guideline like wearing mask, maintaining social distancing, avoiding any public gathering. But people are not maintaining those guide line mainly in the countries like Bangladesh, India, Pakistan and many other under developed countries where people live from day to day earning. Keeping that entire thing in our mind we tried to develop a surveillance system that monitor if they are taking enough precautions to save themselves from Covid-19. This surveillance system monitor people are having basic personal protective gear like mask, face shield, PPE, gloves not only that this surveillance system will able to detect if any person is violating the guide line and our system is able to take picture of the violator not only that this surveillance system will able the live detection that will help the people who are monitoring the people.
Open Access
Renewable Energy Based Water Purification System
(North South University, 2020-12-30) Md. Rejuan Ahmed Khan; Md. Rashidul Hasan Rifat; Dr. Shahnewaz Siddique; 1231121043; 1521093042
A transition to clean energy is about making an investment into the future. Science has found that nothing can disappear without a trace. Nature does not know extinction. All it knows is transformation. And that transformation is what leads the life on earth keep moving. According to biologists, all life form came from the different form of water. We are living on this planet due to the blessing of water. From the dawn of civilization to till now, humans, both, cave dwellers and city dwellers have been using water for various seminal purposes: drinking, bathing, watering animals, irrigating lands and producing foods. In the developing countries, having fresh water is still considered to be a challenging task. Likewise, the rare availability of the resources and the cost of the management made this more difficult to have access to clean water even in our country as well. However the circumstances is, yet it is that urge which lets the humanity to still move on and find out the estimated solution in the best possible way.
Open Access
Semi-autonomous Wheelchair with Real-Time Object Detection Using YOLOv7
(North South University, 2022) Faysal Miah; Dr. Shahnewaz Siddique; 1721758042
Disability is part of being human. According to the World Health Organization(WHO) an estimated 1.3 billion people – about 16% of the global population – currently experience significant disability. In our senior design project we introduce a Semi-Autonomous wheelchair for the disabled people. Autonomous wheelchair is a technology that is appropriate for people who have lost mobility due to brain injury or the loss of limbs but or loss of eyesight. The technology can also enhance safety for users who use ordinary joystick- controlled powered wheelchairs, by preventing collisions with walls, fixed objects, furniture and other people. This project is intended towards contributing to the helping hand of the paralyzed patients. This is a multifunctional wheelchair that helps the is a multifunctional wheelchair that helps the unable person to control it in ways like automatic obstacle detection control and remote control. The main features of the wheel chairs are: Automotive format - (detects obstacles by YOLOv7 and finds new path to move). Remote controlled feature - (It's controlled by any android device through bluetooth connectivity). Security assurance - ( It can assure security of the disabled person by keeping record of the data of the moving paths through camera.)
Open Access
Senior Design Project 3D PRINTER
(North South University, 2024) Tauhid Rahman; Ibtehaz Ahmad; Saiful Islam Maruf; Syed Tofazzal Hossain; Dr. Shahnewaz Siddique; 1510449042; 1510438643; 1521827042; 1521381642
If we all try to imagine a world where the production of a given solid object would be in your home rather than some factory in china or USA which contribute heavily in global warming. Imagine a world where we can have tangible goods as well as intangible services delivered to our PC over the Internet. A future in which the everyday "atomization" of virtual objects into hard reality has turned the mass pre-production and stock -holding of a wide range of goods and spare parts into no more than an historical legacy. This sounds like a far-fetched theory to some, almost sounds like too good to be true but 3D printers can turn it into a reality. 3D printers are capable of outputting physical solid objects. This has been in practice for a two decades. For the rapid development of technology, the usage & utilization of 3D Printer in industries have increased greatly. 3D Printer has brought a revolutionary change in the field of production engineering. 3D printing is a processes in which materials are joined or solidified layer by layer under computer control to create a three-dimensional Object. 3D Printer is a highly accurate machine. 3D printer is used in both rapid prototyping and additive manufacturing. In this project, we will be building a low cost 3D printer using FDM model from the ground up to show everyone what it is capable of in producing quality objects. For better quality and accuracy, we will be implementing few algorithms and tricks on the 3D printer. So the idea is to show people, the true potential of a 3D printer using low cost products then everyone can understand and appreciate the advancement 3D printer can make in all fields in modern world. The use of 3D printer will only increase as we move to the future and it will gain more popularity and will become a household item in the coming days.