جامعة المعرفة
المصدر المعتمد للمعلومات البحثية والمخرجات هو قاعدة بيانات سكوبس (Elsevier Scopus) مع تدقيق بيانات الباحثين من عمادة البحث العلمي.
GK

Ghaith Koushaji

غيث بسام محمد قوشجي

— Industrial Engineering

كلية الهندسة وعلوم الحاسببانتظار توثيق الانتساب2023–2026
4وثائق Scopus
10استشهاداً
2مؤشر h
4منها بانتماء الجامعة
إجمالي Scopus (كل الجهات)ملف الباحث في Scopus ↗آخر تحديث: 2026-11-09

كل وثائق Scopus للباحث

4
مقالمفتوح (مستودع)2026

Optimized Deep Learning Techniques for Enhanced Epilepsy Prediction from Electroencephalogram Signals

Advanced Health Science and Technology Journal · مجلد 2 (1) · 63-72

Abstract Background: Well over 65 million people throughout the world suffered from epilepsy, a common neurological illness. The success rate of standard medical interventions, including medication and surgery, is <30%. On the other hand, seizure prevention methods involving prompt therapeutic interventions are possible with early seizure prediction. Effective and highly accurate epilepsy prediction is still a challenge, despite experts’ best efforts. Aims and Objectives: We present the Particle Swarm Optimized–Convolutional Neural Network and Long Short Term Memory (PSO CNN LSTM) model for electroencephalogram (EEG) signal categorization to support epilepsy diagnosis. Materials and Methods: For EEG classification, we acquire EEG samples from the Bonn dataset that has been used in many reliable studies, which contains five categories of EEG signals, including both normal and epileptic samples. The dataset is preprocessed by removing artifacts and noise. The Short Time Fourier Transform method is subsequently employed for converting the EEG signals into spectrogram images. The postulated PSO CNN LSTM model and other deep learning models, such as CNN and CNN LSTM, employed these spectrogram images as inputs. MATLAB software was implemented for training and verifying models. Results and Conclusions: The studies’ findings revealed that the suggested PSO CNN LSTM model performs better than the other models, with an accuracy of 96% as opposed to 84% and 94%, respectively.

epileptic seizure predictionseizure predictionEEGEEG classification
ورقة مؤتمروصول مغلق20232استشهاد· Semantic Scholar

Classification of Fluid Filled Abnormalities In Retinal Optical Coherence Tomography Images Using Chicken Swarm Optimized Deep Learning Classifier

International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME) · 1-8

Optical Coherence Tomography is a noncontact, non-invasive imaging regarded as the best diagnostic approach when compared to other imaging techniques. It provides convenience along with high resolution and is an indispensable tool utilized for the retinal disease diagnosis in clinical practice. Among retinal diseases, the vision loss is very common caused because of deficit or excess of fluid within the retinal layers. High risk for vision loss occurs due to such damages or deformations in the layers of retina. To tackle this, a deep learning approach is opted for diagnosing fluid filled abnormalities in retinal OCT images. The input image is enhanced by means of CLAHE approach and the retinal layer is segmented for the extraction and selection of relevant features. Gabor filter is adopted for the feature extraction and the selected features are further classified by RNN classifier whose parameters are trained by CSO approach. The utilized RNN provides dynamic system modelling and real-time big data classification. The proposed CSO efficiently trains the RNN parameters with increased accuracy and less time complexity .The NEH OCT image dataset is used in MATLAB to validate the proposed approach. The obtained results demonstrate the efficacy of the proposed approach with an accuracy of 95% and reduced processing time of 545.4s.

optical coherence tomographychicken swarm optimizationrecurrent neural networksretinal layer segmentation
ورقة مؤتمروصول مغلق20231استشهاد· Semantic Scholar

Portable Smart Non Invasive system for the Detection of Glucose in human blood

International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME) · مجلد 211 · 1-5

A person who has diabetes mellitus, also called as diabetes and it has a high blood sugar level. The pancreas produces a hormone insulin, which regulates blood glucose levels. Diabetes is brought on by inadequate insulin production. If the issue is not resolved, it can result in heart issues and other catastrophic repercussions. To diagnose diabetes, a variety of invasive methods are available. To obtain the thermal image of the palm for this research, we are using thermal camera as well as near-infrared (NIR) technology. The captured thermal image and the data from the detector was read and processed by the raspberry pi module. The Internet of things (IoT) web page displaying the received data from the sensor system. Anytime that is necessary, the stored data can be retrieved and examined. The created sensor system is side-effect-free, portable, and simple to use.

blood glucose detectiondiabetes mellitusnon-invasive glucose monitoringinfrared thermography