A5001354552- EEG and Brain-Computer Interfaces
- Non-Invasive Vital Sign Monitoring
- Gaze Tracking and Assistive Technology
- Blind Source Separation Techniques
- Heart Rate Variability and Autonomic Control
- Advanced Vision and Imaging
- Neuroscience and Neural Engineering
- AI in cancer detection
- ECG Monitoring and Analysis
- Emotion and Mood Recognition
- Optical Imaging and Spectroscopy Techniques
- Video Coding and Compression Technologies
- Hand Gesture Recognition Systems
- Video Surveillance and Tracking Methods
- Neural dynamics and brain function
- Quality and Safety in Healthcare
- Muscle activation and electromyography studies
- Brain Tumor Detection and Classification
- COVID-19 diagnosis using AI
- Digital Imaging for Blood Diseases
- Neural Networks and Applications
- Advanced Neural Network Applications
- Human Pose and Action Recognition
- Advanced Sensor and Energy Harvesting Materials
- Biomedical and Engineering Education
Khulna University of Engineering and Technology
2016-2025
United Arab Emirates University
2024
The University of Texas at El Paso
2022-2024
Universiti Malaysia Perlis
2024
Jashore University of Science and Technology
2019
Dhaka Medical College and Hospital
2015
California Institute of Technology
2012
Korea University
2006-2008
South Valley University
2008
Aligarh Muslim University
2007
Recently, electroencephalogram-based emotion recognition has become crucial in enabling the Human-Computer Interaction (HCI) system to more intelligent. Due outstanding applications of recognition, e.g., person-based decision making, mind-machine interfacing, cognitive interaction, affect detection, feeling etc., successful attracting recent hype AI-empowered research. Therefore, numerous studies have been conducted driven by a range approaches, which demand systematic review methodologies...
Diabetes is one of the most rapidly spreading diseases in world, resulting an array significant complications, including cardiovascular disease, kidney failure, diabetic retinopathy, and neuropathy, among others, which contribute to increase morbidity mortality rate. If diabetes diagnosed at early stage, its severity underlying risk factors can be significantly reduced. However, there a shortage labeled data occurrence outliers or missingness clinical datasets that are reliable effective for...
A brain tumor is an uncontrolled malignant cell growth in the brain, which denoted as one of deadliest types cancer people all ages. Early detection tumors needed to get proper and accurate treatment. Recently, deep learning technology has attained much attraction physicians for diagnosis treatment tumors. This research presents a novel effective classification approach from MRIs utilizing AlexNet CNN separating dataset into training test data along with extracting features. The extracted...
Liver disease includes a range of health conditions resulting from various factors that impact the normal functioning liver over an extended period. Effective treatment Hepatitis C, type disease, can be significantly enhanced by accurately and timely predicting risk severity, covering different stages like fibrosis cirrhosis. This research utilizes C dataset UCI repository to present comprehensive framework for prediction across stages. All analyses were performed on this dataset. We have...
In this paper, we present a novel method for human action recognition from any arbitrary view image sequence that uses the Cartesian component of optical flow velocity and body silhouette feature vector information. We use principal analysis (PCA) to reduce higher dimensional space into lower space. The region in an frame represents Q-dimensional R-dimensional vector. represent each using set hidden Markov models model viewing direction by combined (Q + R)-dimensional features at instant...
Abstract This paper proposes a novel feature selection method utilizing Rényi min-entropy-based algorithm for achieving highly efficient brain–computer interface (BCI). Usually, wavelet packet transformation (WPT) is extensively used extraction from electro-encephalogram (EEG) signals. For the case of multiple-class problem, classification accuracy solely depends on effective WPT features. In conventional approaches, Shannon entropy and mutual information methods are often to select this...
Emotions are the most fundamental feature for non-verbal communication between human and machine. To extract original expectation of mind, emotion recognition classification is essential. But due to some complexities, proper from Electroencephalogram (EEG) has become too much challenging. In this paper, we propose a system EEG signal based on Discrete Wavelet Transform. The significant features (i) Energy (ii) Entropy calculated detecting four different emotions namely happy, angry, sad...
Acute Lymphoblastic Leukemia (ALL) is a blood cell cancer characterized by the presence of excess immature lymphocytes., Even though automation in ALL prognosis essential for diagnosis, it remains challenge due to morphological correlation between malignant and normal cells. The traditional classification strategy demands that experienced pathologists read images carefully, which arduous, time-consuming, often hampered interobserver variation. This article has automated recognition task...
Although automated Acute Lymphoblastic Leukemia (ALL) detection is essential, it challenging due to the morphological correlation between malignant and normal cells. The traditional ALL classification strategy arduous, time-consuming, often suffers inter-observer variations, necessitates experienced pathologists. This article has task, employing deep Convolutional Neural Networks (CNNs). We explore weighted ensemble of CNNs recommend a better cell classifier. weights are estimated from...
Diabetic retinopathy is one of the most significant retinal diseases that can lead to blindness. As a result, it critical receive prompt diagnosis disease. Manual screening result in misdiagnosis due human error and limited capability. In such cases, using deep learning-based automated disease could aid early detection treatment. analysis, original segmented blood vessels are typically used for diagnosis. However, still unclear which approach superior. this study, comparison two learning...
The appropriateness of selected features, contingent upon anthropometric factors, influences the efficacy algorithm classification in pregnancy monitoring and obstetric outcome forecasting. Obstetricians often lack technology to determine whether a cesarean delivery is necessary based on antepartum circumstances. objective this study develop an automated system for effective detection mode birth using EHG analyze data points shape structures across different BMI groups. Topological features...
Recognizing human action from image sequences is an active area of research in computer vision. In this paper, we present a novel method for recognition different viewing angles that uses the Cartesian component optical flow velocity and body shape feature vector information. We use principal analysis to reduce higher dimensional space into low space. represent each using set multidimensional discrete hidden Markov model any direction. performed experiments proposed by KU gesture database....
The prevalence of the coronavirus disease 2019 (COVID-19) pandemic has made a huge impact on global health and world economy. Easy detection COVID-19 through any technological tool like mobile phone can help lot. In this research, we focus detecting from X-ray images Android with Artificial Intelligence (AI). A convolutional neural network (CNN) model is developed in MATLAB then converted to CNN TensorFlow Lite (TFLite) deploy mobile. An application which uses TFLite detect using images. By...
Cognitive load level identification is an interesting challenge in the field of brain-computer-interface. The sole objective this work to classify different cognitive levels from multichannel electroencephalogram (EEG) which computationally though-provoking task. This proposed utilized discrete wavelet transform (DWT) decompose EEG signal for extracting non-stationary features task-wise signals. Furthermore, a support vector machine (SVM) implemented task DWT-based extracted features. ....
Underwater optical communication (UOC) and off-surface areas wireless communications are a rapidly growing field, especially with the emergence of new technologies such as autonomous underwater vehicles abovewater drones. The challenge lies in absence water surface platform to transfer signal from off surface. This research investigates design implementation hybrid system that successfully transmits signals environments above-water. study utilizes OFDM method generate data on integration...
Chest radiographs, or chest X-rays (CXRs), are widely used as first-line diagnostic tools for detecting various diseases. However, accurately interpreting CXRs remains challenging, human performance is influenced by individual expertise and other factors, often resulting in delays, high costs, potential misinterpretations. To address these limitations, automated computer-based detection systems offer the to enhance accuracy, reduce enable timely disease identification. This study presents...
The purpose of the research is to evaluate different human emotions through Electroencephalogram (EEG) signal and receive information about internal changes brain state. paper presents detection emotion based on some salient features EEG signal. For this purpose, seven emotional states have been specified such as relax, thought, memory related, motor action, pleasant, fear, enjoying music. Several signals collected for these analyzed using frequency transform statistical measures. Different...