A5045216943- EEG and Brain-Computer Interfaces
- Retinal Imaging and Analysis
- Medical Image Segmentation Techniques
- Remote-Sensing Image Classification
- Image Retrieval and Classification Techniques
- ECG Monitoring and Analysis
- Face and Expression Recognition
- Digital Imaging for Blood Diseases
- AI in cancer detection
- Speech and Audio Processing
- Music and Audio Processing
- Brain Tumor Detection and Classification
- Blind Source Separation Techniques
- Machine Learning and ELM
- Phonocardiography and Auscultation Techniques
- Emotion and Mood Recognition
- COVID-19 diagnosis using AI
- Advanced Image and Video Retrieval Techniques
- Anomaly Detection Techniques and Applications
- Network Security and Intrusion Detection
- Advanced Neural Network Applications
- Glaucoma and retinal disorders
- Dental Radiography and Imaging
- Hand Gesture Recognition Systems
- Wireless Signal Modulation Classification
Fırat University
2016-2025
Bennett University
2020
Duhok Polytechnic University
2019
Islamic Azad University South Tehran Branch
2015
Shahid Beheshti University
2015
This paper introduces a methodology based on deep convolutional neural networks (DCNN) for motor imagery (MI) tasks recognition in the brain-computer interface (BCI) system. More specifically, DCNN is used classification of right hand and foot MI-tasks electroencephalogram (EEG) signals. The proposed method first transforms input EEG signals into images by applying time-frequency (T-F) approaches. T-F approaches are short-time-Fourier-transform (STFT) continuous-wavelet-transform (CWT)....
Treatment of lung diseases, which are the third most common cause death in world, is great importance medical field. Many studies using sounds recorded with stethoscope have been conducted literature order to diagnose diseases artificial intelligence-compatible devices and assist experts their diagnosis. In this paper, ICBHI 2017 database includes different sample frequencies, noise background was used for classification sounds. The sound signals were initially converted spectrogram images...
Abstract The reliable and rapid identification of the COVID-19 has become crucial to prevent spread disease, ease lockdown restrictions reduce pressure on public health infrastructures. Recently, several methods techniques have been proposed detect SARS-CoV-2 virus using different images data. However, this is first study that will explore possibility deep convolutional neural network (CNN) models from electrocardiogram (ECG) trace images. In work, other cardiovascular diseases (CVDs) were...
Background/Objectives: Epilepsy is a prevalent neurological disorder characterized by seizures that significantly impact individuals and their social environments. Given the unpredictable nature of epileptic seizures, developing automated epilepsy diagnosis systems increasingly important. traditionally relies on analyzing EEG signals, with recent deep learning methods gaining prominence due to ability bypass manual feature extraction. Methods: This study proposes continuous wavelet...
Early detection of driver drowsiness and the development a functioning alertness system may support prevention numerous vehicular accidents worldwide. Wearable sensors camera-based systems are generally employed in detection. Electroencephalogram (or EEG) is considered another effective option for Various EEG-based have been proposed to date. In this paper, EEG signals also used drowsiness, with method being composed three main building blocks. Both raw their corresponding spectrograms first...
Mild cognitive impairment (MCI) can be an indicator representing the early stage of Alzheimier's disease (AD). AD, which is most common form dementia, a major public health problem worldwide. Efficient detection MCI essential to identify risks AD and dementia. Currently Electroencephalography (EEG) popular tool investigate presenence biomarkers. This study aims develop new framework that use EEG data automatically distinguish patients from healthy control subjects. The proposed consists...
The recognition of various lung sounds recorded using electronic stethoscopes plays a significant role in the early diagnoses respiratory diseases. To increase accuracy specialist evaluations, machine learning techniques have been intensely employed during past 30 years. In current study, new pretrained Convolutional Neural Network (CNN) model is proposed for extraction deep features. CNN architecture, an average-pooling layer and max-pooling are connected parallel order to boost...