Student engagement is a well-established factor that impacts the achievement of learning outcomes in higher education and as such, it is being widely researched. This paper explores the efficacy of the Context Challenge Activity Feedback (CCAF) framework in an in-person classroom setting for third-year bachelor students in an Information Systems (IS) Security course. Adopting a quantitative research methodology, the study analyzes student surveys to evaluate the effect of the CCAF framework on aspects such as the applicability of course material to real-world scenarios, course structure and clarity, stimulation of intellectual curiosity, and overall student satisfaction. The findings reveal that a majority of students perceive the course material as highly relevant to real-world IS Security issues, indicating the framework’s effectiveness in contextualizing theoretical concepts. The course’s structure and content clarity were also well-received, with a majority of students reporting positive experiences, suggesting the framework’s success in creating a clear and engaging learning environment. However, responses regarding the stimulation of intellectual curiosity showed variability, highlighting the necessity for adaptive teaching methods to cater to diverse learning preferences. Overall, the study reports high levels of student satisfaction, underscoring the potential of the CCAF framework in enhancing learning experiences in IS Security within traditional classroom settings. The study contributes to the existing studies by providing empirical support for the application and efficacy of the CCAF framework in in-person higher education settings, particularly in a technical and rapidly evolving field like IS Security. The findings have significant implications for pedagogical practices, suggesting that innovative, student-centered approaches like CCAF can effectively enhance student engagement and educational experiences in higher education.
Wearable electrocardiogram sensors have emerged on the market but lack the technology to interpret the results with high performance. This paper explores the potential for innovation in developing a heart-based language and applying natural language processing to detect and classify dangerous arrhythmia. In the AI Cardiologist project, we propose real-time heart monitoring and alerting dangerous arrhythmia using AI-based technology using RoBERTa transformers in large language models. The focus is on analyzing the domains of medical applications and introducing new business models to exploit the technology’s results. We confirmed that foundation models for ECG records created by deep learning methods could greatly enhance precision and effectiveness of heart health monitoring and detection of atrial fibrillation, enabling better healthcare and well-being. No similar solution is available on the market outside of hospital environments, giving the project results a high potential for commercialization.
Signaling pathway analysis is a crucial approach in understanding the pharmacological mechanisms of various cell functions. This paper presents a comprehensive framework for analyzing the signaling pathways of bioactive compounds from C. sativa and their potential interactions with Alzheimer’s disease-related proteins. The study offers a new methodology utilizing a series of bioinformatics tools and databases to screen for active compounds, predict target genes, perform enrichment analysis, network analysis and molecular docking. The results reveal a significant intersection of genes between the bioactive compounds of C. sativa and Alzheimer’s disease, indicating potential therapeutic implications. Moreover, network analysis identifies key proteins involved in the interactions, highlighting the potential targets for further investigation.
To address the lack of integrated resources that combine nutritional, chemical, and semantic information, we have integrated the Recipe1M+ dataset with the USDA National Nutrient Database, FooDB, and the FoodOn ontology. This integration brings significant advantages by enriching the dataset with comprehensive information across multiple domains. By linking Recipe1M+ ingredients to the USDA database, we provide detailed nutritional profiles that enable a comprehensive analysis of recipes, supporting researchers and dietitians in developing personalized nutrition plans based on accurate nutrient data. Furthermore, incorporating FooDB enhances the dataset with in-depth chemical compositions and health effects of food constituents, facilitating research on functional foods and their role in disease prevention and health promotion. Mapping ingredients to FoodOn further expands the dataset’s semantic context, encompassing food products, production, agriculture, and environmental impacts. This integration promotes interdisciplinary research and the creation of comprehensive knowledge graphs, bridging gaps between nutrition, food science, agriculture, and health domains. Our methodology has been validated, demonstrating significantly better results with a precision of 76.25 link ).
Autism spectrum disorder (ASD) is a neurodevelopmental condition that affects the brain’s function. Electroencephalography (EEG) is a non-invasive technique that measures the electrical activity of the brain and can reveal its dynamics and information processing. We obtained the data during an eyes-opened resting state EEG recordings and it consisted of 52 children with autism (ASD) and 39 typically development (TD) children. In this study, we trained and compared 5 different classifiers for ASD and TD based on the EEG signals: the Dummy classifier, a Random Forest classifier, a K Nearest Neighbours classifier, a Support Vector Machine and an XGBoost classifier.
