Page 42 - tech fest 2025 ב״ש חוברת תקצירים

42
Detection and Classification of Epileptic Seizures Based on EEG Signals and Machine Learning
CS-A-05
Nikol Sigal; nikol1234534@gmail.com Ronen Yakobov; ronen0902@gmail.com
Advisor: Prof. Shlomo Greenberg
SCE - Shamoon College of Engineering, Be’er-Sheva
EEG (electroencephalogram) signals reflect brain activity but are mixed with noise caused by environmental factors. Detection of epileptic seizures in real-time in a noisy environment is a challenging goal. This project aimed to develop a deep neural network (DNN) model for classifying EEG signals in order to detect various kind of epileptic seizures. We developed an efficient algorithm based on machine learning and DNN which was able to accurately detect and predict different epileptic seizures.
Keywords: DNN, EEG, epileptic seizures, machine learning
Detecting Chameleons in Twitter
CS-A-06
Ran Matan; ranmatan11@gmail.com Shelli Dadon; shelludadon@gmail.com
Advisor: Dr. Aviad Elyashar
SCE - Shamoon College of Engineering, Be’er-Sheva
In the modern digital era, social networks have become a central tool for communication, information sharing, and self-expression. However, these platforms are often exploited by malicious actors seeking to harm innocent users. This project explored the phenomenon of chameleons on social networks – cases where individuals significantly alter their behavior or even adopt new identities for malicious purposes. First, we proposed a machine-learning framework that continuously monitors user activity over time, recording every behavioral change. This resulted in a comprehensive dataset, from which meaningful features and patterns can be extracted to help identify users who may be shifting their identity. Further analysis can provide insights into the underlying causes of such transformations, including malicious intent.
Keywords: detection, identity changes, machine learning, natural learning processing, social networks, user behavior