This research presents a novel approach to detecting epileptic seizures leveraging the strengths of Machine Learning (ML) and Deep Learning (DL) algorithms in EEG signals. Epileptic seizures are neurological events with distinctive features found in Electroencephalography (EEG) that lend considerable credibility to researchers. Machine Learning (ML) and Deep learning (DL) algorithms have emerged as powerful feature extraction and classification tools in EEG signal analysis. Many studies have converted the EEG signals into either images and /or calculated time-frequency domain features and performed classification. This study focuses on classifying time-series data representation of EEG signals with machine learning-based classifiers by tuning parameters and deep learning-based One-Dimensional Convolutional Neural Network (1D CNN) methods. The primary objective is not only to determine the optimal classifier but also to emphasize critical metrics such as sensitivity, precision, and accuracy, which are critical in medical investigations, particularly for the early detection of diseases and patient care optimization. The UCI Epileptic Seizure Recognition dataset used in this study consists of time-series data points extracted from the EEG signals. The dataset has been preprocessed and fed to the classifiers, namely Extreme Gradient Boosting (XGBoost), TabNet, Random Forest (RF), One Dimensional Convolutional Neural Network, and achieved encouraging accuracies of 98%, 96%, 98%, and 99%, respectively. The proposed 1D-CNN model performed better than other state-of-the-art models concerning accuracy, sensitivity, precision, and recall.

This study aims to examine information technology students' perceptions toward the use of virtual reality technology, their behavioral intention to use such technology for educational purposes, and the relationship between their perceptions toward the use of virtual reality technology and their behavioral intention to use virtual reality technology for educational purposes. The study used a descriptive and cross-sectional survey research design. The data collection tool was developed based on the second Unified Theory of Acceptance and Use of Technology UTAUT2 framework. Data were collected from participants using an online questionnaire. The number of participants was 147 undergraduate information technology students. The results showed that the participants had variations in their perceptions of virtual reality technology. The results showed that participants had positive perceptions of hedonic motivation and effort expectancy concerning the use of virtual reality. However, the students had close to neutral perceptions of performance expectancy, social influence, facilitating conditions, price value, and habits concerning the use of virtual reality. Furthermore, the results showed that the students had a positive behavioral intention to use virtual reality for educational purposes. Part of students' positive behavioral intention to use virtual reality for educational purposes can be ascribed to their perceptions of effort expectancy, performance expectancy, social influence, hedonic motivation, price value, facilitating conditions, and habits concerning the use of virtual reality. Students' perceptions of performance expectancy concerning virtual reality had the greatest effect on their behavioral intention to use virtual reality for educational purposes. Based on the findings, a set of recommendations was provided.

Many designed systems have shown the potential of virtual reality (VR) to greatly transform autism treatment studies. Indeed, the literature shows that treatment via VR is appropriate for effective and repeatable training, without the intense anxiety, allowing trainees to recognize and modulate errors as they occur. This study evaluates the effectiveness of a new VR-based learning environment designed to safely practice and rehearse the daily activities related to the school world in children affected with autism. A total of nine children with autism actively enrolled in the study to learn and test their street crossing skills and social attention. Incremental change of difficulty levels has been added to the designed environment to generalize real-world situations, this includes overlaid distraction audio and increased vehicles intensity and speed. In order to enhance the learning experience, the real-time feedback is given according to the participant’s behavior, additionally, post processing profile is given for analysis purpose, where the participant’s behavior can be reviewed by parents and therapist to determine whether the participant’s mistakes are in decision making or focusing attention. The Wilcoxon signed-rank test for a single sample was used to test the change in the skills of participants with autism after using the educationally and therapeutically VR technology compared to a baseline. As a result, significant effects were found on the behavioral measures indicating that the VR-based learning environment is promoting a positive and informative learning environment.

Clinical text classification of electronic medical records is a challenging task. Existing electronic records suffer from irrelevant text, misspellings, semantic ambiguity, and abbreviations. The approach reported in this paper elaborates on machine learning techniques to develop an intelligent framework for classification of the medical transcription dataset. The proposed approach is based on four main phases: the text preprocessing phase, word representation phase, features reduction phase and classification phase. We have used four machine learning algorithms, support vector machines, naïve bayes, logistic regression and k-nearest neighbors in combination with different word representation models. We have applied the four algorithms to the bag of words, to TF-IDF, to word2vec. Experimental results were evaluated based on precision, recall, accuracy and F1 score. The best results were obtained with the combination of the k-NN classifier, and the word represented by Word2vec achieving an accuracy of 92% to correctly classify the medical specialties based on the transcription text.

Enhancing information security has become a necessary and comprehensive cybersecurity mission. In today's landscape, operating systems and software have become more secure, leading attackers to exploit the human element as a means to breach organizational information systems. As the frequency and sophistication of cyber-attacks targeting unsuspecting personnel continue to rise, the significance of the human factor in information security management cannot be understated. Effective security awareness is crucial in countering these attacks that exploit human vulnerabilities, aiming to mitigate security risks. This study focuses on the development of an interdisciplinary training and educational model specifically designed for human resources to elevate their understanding of cybersecurity protocols. The research proposes a professional framework encompassing various methodologies to heighten security awareness, including online training materials, contextual training, and embedded training. The findings reveal that a combination of delivery methods outperforms a singular approach, resulting in heightened security awareness among individuals. Through implementing this comprehensive training model, organizations can bolster their information security posture by empowering employees with the knowledge and skills necessary to effectively combat evolving cyber threats.

Breast cancer continues to be a substantial worldwide health concern, affecting millions of individuals each year; this emphasizes the critical nature of early detection in order to enhance patient prognoses. The present study aims to assess the classification performance of three convolutional neural network (CNN) architectures-visual geometry group 19 (VGG19), AlexNet, and residual network 50 (ResNet50)-with respect to breast cancer detection in medical images. Thorough assessments, encompassing metrics such as accuracy, precision, recall, and F-score, were undertaken to evaluate the diagnostic performance of the models. ResNet50 consistently outperforms other models, as evidenced by its highest accuracy and F-score. The research highlights the significant importance of carefully choosing suitable architectures for medical image analysis, with a specific focus on the detection of breast cancer. In addition, it demonstrates the capacity of deep learning models, such as ResNet50, to improve the diagnosis of breast cancer with exceptional precision and sensitivity, which is critical for reducing the occurrence of false positives and negatives in clinical environments. In addition, computational efficiency is taken into account; AlexNet is recognized as the most efficient model, which is advantageous in environments with limited resources. This study advances medical image processing by demonstrating the potential of CNNs in the detection of breast cancer. The results of this study establish a fundamental basis for sub- sequent inquiries and suggest approaches to improve timely detection and treatment, which will ultimately be advantageous for both patients and healthcare professionals.