A5001389659- Vehicle License Plate Recognition
- Hand Gesture Recognition Systems
- Handwritten Text Recognition Techniques
- Hearing Impairment and Communication
- Advanced Neural Network Applications
- Human Pose and Action Recognition
- Radiomics and Machine Learning in Medical Imaging
- Gait Recognition and Analysis
- Fire Detection and Safety Systems
- Blockchain Technology Applications and Security
- COVID-19 diagnosis using AI
- Sentiment Analysis and Opinion Mining
- EEG and Brain-Computer Interfaces
- Fire dynamics and safety research
- Advanced Authentication Protocols Security
- Image Processing Techniques and Applications
- Gaze Tracking and Assistive Technology
- Advanced Steganography and Watermarking Techniques
- Autism Spectrum Disorder Research
- Cardiac electrophysiology and arrhythmias
- Advanced Image and Video Retrieval Techniques
- Autonomous Vehicle Technology and Safety
- Artificial Intelligence in Healthcare and Education
- Advanced Text Analysis Techniques
- Energy, Environment, and Transportation Policies
University of Asia Pacific
2020-2024
Rajshahi University of Engineering and Technology
2022
A License Plate Recognition (LPR) is a technique to automatically identify and recognize the license plate of vehicle. In today's world where we want do everything in no time, automated LPR has opened new door Intelligent Traffic System. With help ALPR, can implement many smart systems starting from parking facility crime investigation. For effective Recognition, accurate Detection Segmentation are crucial. Many existing algorithms using different image processing machine learning techniques...
Early fire detection is the key to saving lives and limiting property damage. Advanced technology can detect fires in high-risk zones with minimal human presence before they escalate beyond control. This study focuses on providing a more advanced model structure based YOLOv8 architecture enhance early recognition of fire. Although excellent at real-time object detection, it still be better adjusted nuances detection. We achieved this advancement by incorporating an additional context-to-flow...
The electrocardiogram (ECG) is one of the simplest and oldest tools to assess heart condition cardiac patients. Heart diseases have emerged as leading causes death all over world. According world health organization (WHO), millions people are dying every year from heart-related diseases. A classification model that can early detect arrhythmia will be able reduce this number by manyfold. Many researchers working in area proposed many deep learning machine Learning based models for...
Sign language is the most commonly used form of communication for persons with disabilities who have hearing or speech difficulties. However, without impairment cannot understand these signs in many cases. As a consequence, experience difficulties while expressing their emotions needs. Thus, sign character detection and text generation system necessary to mitigate this issue. In paper, we propose an end-to-end that can detect Bengali characters from input images video frames generate...
Autism spectrum disorder (ASD) is a neurodevelopmental state that becomes evident during early childhood. It often distinguished by its chronic and non-remissive nature. Early ASD diagnosis essential because it allows for the prompt start of specialized education to successfully lessen negative impacts. However, since comorbidities are present in 10 25 percent patients, correct can be difficult may call further diagnostic techniques like neuroimaging. Deep learning (DL) has grown favor tool...
Sign language is developed to bridge the com-munication gap between individuals with and without hearing impairment or speech difficulties. Individuals typically rely on hand signs as a means of expressing themselves. However, people, in general, may not have sufficient knowledge sign language, thus recognition system an embedded device most needed. Literature related such systems devices scarce these tasks are very complex computationally expensive. The limited resources cannot execute...
A License Plate Recognition (LPR) is a technique to automatically identify and recognize the license plate of vehicle. In today's world where we want do everything in no time, automated LPR opened new door Intelligent Traffic System. With help ALPR, can implement many smart systems starting from parking facility crime investigations. For effective Recognition, accurate Detection Segmentation crucial. Many existing algorithms are using different image processing machine learning techniques...
Automated License Plate Detection and Recognition (ALPDR) system is a technology that automatically detects recognizes the license plate from video or an image. An ALPDR usually 3 steps process; detection, segmentation of characters, finally recognition. For effective system, every step process should be highly accurate robust. This very active research field many researchers are working towards building proposed various recognition systems for Bangladeshi plates. In this paper, we propose...
To minimize the rate of death from COVID-19 and stop disease spreading early detection is vital. The normal RT-PCR tests for take a long time to complete. In contrast this test, Covid-19 can be quickly detected using various machine-learning technologies. Previous studies only had access smaller datasets, as data was not readily available back then. Since dangerous virus, model needs robust trustworthy, must trained on large diverse dataset. overcome that problem, study combines six publicly...
A microbial infection that results in chronic inflammation of the lung cells causes pneumonia. It is mainly caused by bacteria, viruses, fungi or other microorganisms. alveoli lungs. The patient with pneumonia faces difficulties breathing as their lungs become filled pus fluids. This can also cause chest pain, a fever, coughing. Severe considered primary death among infants under age 5. Traditionally, detection using X-ray images entrusted to ability radiologists, which quite time-consuming...
Security professionals and law enforcement, who presently have to manually go through hours of film find minor incidents, are becoming more interested in automated crime violence detection. Developments computer vision machine learning enabling systems quickly scan mark relevant reducing the workload human investigators. Most existing datasets tend focus on too specific situations (e.g., vehicle violence). Typically, these consist a limited number video clips gathered from various sources,...
Fire detection is crucial for ensuring human safety and minimizing property damage. By utilizing advanced technologies, we can identify fires early, before they escalate. Autonomous fire systems are particularly vital in high-risk areas with minimal presence. To address this need, propose an automated fire-detection model based on YOLOv8. We modified the architecture of YOLOv8 achieved impressive performances. Through comprehensive analysis different YOLO models their predecessors,...
Sentiment analysis is one of the core fields Natural Language Processing(NLP). Numerous machine learning and deep algorithms have been developed to achieve this task. Generally, models perform better in task as they are trained on massive amounts data. This, however, also poses a disadvantage collecting sufficient data challenge training with requires devices high computational power. Word embedding vital step applying for NLP tasks. Different word techniques affect performance algorithms....
Online education has become an essential part of the modern system, but keeping integrity online examination remains a challenge. A significant increase in cheating examinations (from 29.9% before COVID-19 to 54.7% during COVID-19, as per recent survey) points out necessity exam proctoring systems. Traditionally, educational institutes utilize different questions onsite exams: multiple-choice (MCQs), analytical questions, descriptive etc. For exams, form-based exams using MCQs are popular...
The majority of city establishments in developing cities are unlabeled due to the time-consuming process manual annotation. As a result, location and trajectory services such places remain underutilized. Accurate signboard localization natural scene photos is critical for retrieving information as cities, streets, etc. This can be used several purposes, including autonomous robot navigation, translators, assisting foreigners visually impaired people, company listings, In this research, we...