Hybrid pre trained model based feature extraction for enhanced indoor scene classification in federated learning environments by Monica Dutta, Deepali Gupta, Vikas Khullar, Sapna Juneja, Roobaea Alroobaea, Pooja Sapra

“…This study proposes and implements a novel MultiData model, which integrates DL with Linear Discriminant Analysis (LDA) and Federated Learning (FL) to enhance classification performance while preserving data privacy. …”
Get full text

FedRecSys: A Federated Learning-Based Recommender System for Concept Drift Adaptation by Anagha Chaudhari, A. A. Hitham Seddig, Roshani Raut, Aliza Sarlan

“…A new field called deep learning can be used to handle large amounts of multidimensional data in different e-commerce platforms. …”
Get full text

Integrating health equity in artificial intelligence for public health in Canada: a rapid narrative review by Samantha Ghanem, Marielle Moraleja, Danielle Gravesande, Jennifer Rooney

“…After conducting title/abstract and full-text screening of articles, and consensus decision on study inclusion, the data extraction process proceeded using an extraction template. …”
Get full text

Human activity recognition system based on low-cost IoT chip ESP32 by Chao HU, Bangyan LU, Yanbing YANG, Zhe CHEN, Lei ZHANG, Liangyin CHEN

“…Human activity recognition widely exists in applications such as sports management and activity classification.The current human activity recognition applications are mainly divided into three types: camera-based, wearable device-based, and Wi-Fi awareness-based.Among them, the camera-based human activity recognition application has the risk of privacy leakage, and the wearable device-based human activity recognition application has problems such as short battery life and poor accuracy.Human activity recognition based on Wi-Fi sensing generally uses Wi-Fi network cards or software-defined radio devices to identify the rules of channel state information changes, so as to infer user activity.It does not have the problems of privacy leakage and short battery life.But Wi-Fi network cards need to rely on computers and software-defined radio platforms are expensive, which greatly limit the application scenarios of Wi-Fi sensing.Aiming at the above problems, a human activity recognition system based on the low-cost IoT chip ESP32 was proposed.Specifically, the Hampel filter and Gaussian filter were used to preprocess the channel state information obtained by ESP32.Then, the principal component analysis and discrete wavelet transform were utilized to reduce the dimension of the data.Finally, the K-nearest neighbor (KNN) algorithm was applied to classify data.The experimental results show that the system can achieve a recognition accuracy which close to the current mainstream Wi-Fi perception system (Intel 5300 network card) when only two ESP32 nodes are deployed, and the average accuracy rate for the six activities is 98.6%.…”
Get full text

Internet of Things on Banking Processes in South Africa: A Systematic Reflection on Innovations, Opportunities and Challenges by Paul Kariuki, Lizzy Oluwatoyin Ofusori, Maria Lauda Joel Goyayi

“…The study found that while the use of IoT in banking processes is still in its infancy, most banks have enhanced their customer experiences through IoT innovations, enhanced their security systems, and enhanced their data access ecosystem to improve their operational efficiency.Moreover, the banking sector is still experiencing some challenges regarding the use of IoT in its processes, such as a lack of privacy and proper storage of customer information, limited workflow management processes, and a lack of policy framework to guide the sector as far as adoption of IoT is concerned. …”
Get full text

Perspectives of Hispanic and Latinx Community Members on AI-Enabled mHealth Tools: Qualitative Focus Group Study by Stephanie A Kraft, Shaan Chopra, Miriana C Duran, Janet A Rojina, Abril Beretta, Katherine I López, Russell Javan, Benjamin S Wilfond, Margaret Rosenfeld, James Fogarty, Linda K Ko

“…We identified the following seven themes: (1) mHealth is seen as beneficial for promoting health and peace of mind; (2) some are unaware of, unfamiliar with, or uncomfortable with technology and may benefit from individualized support; (3) financial barriers limit access to mHealth; (4) practical considerations create barriers to using mHealth in daily life; (5) mHealth raises concern for overreliance on technology; (6) automated mHealth features are perceived as valuable but fallible, requiring human input to ensure accuracy; and (7) data sharing is seen as valuable for limited uses but raises privacy concerns. …”
Get full text

Healthcare professionals and the public sentiment analysis of ChatGPT in clinical practice by Lizhen Lu, Yueli Zhu, Jiekai Yang, Yuting Yang, Junwei Ye, Shanshan Ai, Qi Zhou

“…This study was divided into five steps: data collection, data cleaning, validation of relevance, sentiment analysis, and content analysis using the K-means algorithm. …”
Get full text

Enmob: Unveil the Behavior with Multi-flow Analysis of Encrypted App Traffic by Ge Mengmeng, Feng Ruitao, Liu Likun, Yu Xiangzhan, Sachidananda Vinay, Xie Xiaofei, Liu Yang

“…The efficacy of our approach was evaluated using a substantial volume of real network traffic data. …”
Get full text

Energy-aware federated learning for secure edge computing in 5G-enabled IoT networks by Milad Rahmati

“…Abstract The rapid expansion of 5G-enabled IoT networks has intensified the need for efficient, secure, and privacy-preserving machine learning models that can operate in decentralized edge environments. …”
Get full text

A framework reforming personalized Internet of Things by federated meta-learning by Linlin You, Zihan Guo, Chau Yuen, Calvin Yu-Chian Chen, Yan Zhang, H. Vincent Poor

“…However, with the introduction of laws and regulations about data security and privacy protection, centralized solutions, which require data to be collected and processed directly on a central server, become impractical for personalized Internet of Things to train Artificial Intelligence models for a variety of domain-specific scenarios. …”
Get full text

iScene: An interpretable framework with hierarchical edge services for scene risk identification in 6G internet of vehicles by Wuchang Zhong, Siming Wang, Rong Yu

“…However, the performance of existing risk identification approaches is heavily limited by the imbalanced historical data and the poor model interpretability. Meanwhile, the large processing delay and the potential privacy leakage threat also restrict their application. …”
Get full text

Enhanced Federated Learning Framework based on Deep Learning and Neutrosophic Set for Android Malware Classification by Mohamed Refaat Abdellah, Hasan H. Oudah, Ahmed Mohamed Ahmed Badawy, Mohamed AbdElFattah AbdElFattah M Hassan, Shady Ahmed Bedier, Ahmed A. Metwaly, Mohamed eassa, Ahmed Abdelhafeez

“…Due to the requirement for massive volumes of data aggregation, traditional centralized machine learning (ML) techniques for malware detection face challenges with data sharing, computational complexity, and privacy. …”
Get full text

Promoting mental health in the age of new digital tools: balancing challenges and opportunities of social media, chatbots, and wearables by Julien Coelho, Julien Coelho, Florian Pécune, Jean-Arthur Micoulaud-Franchi, Jean-Arthur Micoulaud-Franchi, Bernard Bioulac, Pierre Philip, Pierre Philip

“…Nonetheless, these technologies introduce challenges including privacy issues, data security, and equitable access to digital resources, raising a new class of rights to protect mental privacy, guard against algorithm bias, and prevent personality-changing manipulations. …”
Get full text

Research on health information avoidance behavior and influencing factors of cancer patients—an empirical analysis based on structural equation modeling by Rui Zhu, Hui Zhao, Yun Yun, Yue Zhao, Weixian Wang, Lingmeng Wang, Wenjie Hou, Fuzhi Wang

“…Methods A face-to-face electronic questionnaire was used to collect data. Applying a chi-square test and multivariate logistic regression model to analyze the role of different socio-demographic factors in influencing health information avoidance behavior of cancer patients; applying structural equation modeling to analyze the role mechanism of health information avoidance behavior of cancer patients. …”
Get full text

Appling A Hybrid Encryption Algorithm in Cloud Computing‎ by Esraa Alobaydi, Muna Jawhar

“…The rapid digital development has led to a steady increase in the use of cloud storage as a ‌primary means of saving and sharing data and files. …”
Get full text

Leveraging AI to Investigate Child Maltreatment Text Narratives: Promising Benefits and Addressable Risks by Wilson Lukmanjaya, Tony Butler, Sarah Cox, Oscar Perez-Concha, Leah Bromfield, George Karystianis

“…However, when applying such methods, it is useful to have a framework on which to base approaches to the data. …”
Get full text

AI-Enhanced Disaster Management: A Modular OSINT System for Rapid Automated Reporting by Klaus Schwarz, Kendrick Bollens, Daniel Arias Aranda, Michael Hartmann

“…Through our case studies on Hurricane Harvey and the 2023 Turkey earthquake, we show how complex tasks can be quickly broken down with ODET while achieving a score of up to 89% using the AlignScore metric. ODET enables compliance with Berkeley protocol requirements by ensuring data privacy and using privacy-preserving processing methods. …”
Get full text

Legal regulation of the application of information management technologies (on the example of the transport industry) by E. Yu. Serbinenko, O. A. Dmitrieva

“…This article discusses the importance of legal regulation in the use of management information technologies. It examines the current legal framework for the use of these technologies and highlights the need for further regulation to protect privacy and security. …”
Get full text

The role of artificial intelligence in education among college instructors: Palestine Technical University Kadoorie as a case study by Reham Salhab

“…A phenomenological approach as well was conducted to gather information for the qualitative data. Semi-structured interviews with 17 participants were performed with college instructors who use AI in their teaching. …”
Get full text

Explainable Video Topics for Content Taxonomy: A Multimodal Retrieval Approach to Industry-Compliant Contextual Advertising by Waruna de Silva, Anil Fernando

“…To this end, transformer-based architectures, specifically BERTopic, computer vision techniques, and large language models were used to extract sets of topics from visual and textual video data automatically and systematically. …”
Get full text