Article
Computer Science, Information Systems
Van Cu Pham, Nguyen Thi Dieu Linh, Tung Le, Tien Huy Nguyen, Yasuo Tan
Summary: This paper introduces an AI-driven solution for automatically generating data models from ECHONET Lite specifications, reducing the workload and improving efficiency while ensuring accuracy.
Article
Computer Science, Information Systems
Minxiao Wang, Ning Yang, Ning Weng
Summary: Machine learning-based Network Intrusion Detection Systems (NIDSs) can classify network flow behavior as benign or malicious. However, current ML-based NIDSs are insufficient to generalize in changing network environments like IoT-based smart homes. This paper proposes a novel Transformer-based IoT NIDS method that combines network traffic-based and telemetry data-based NIDSs to achieve improved intrusion detection performance.
Article
Chemistry, Analytical
Raul Gomez Ramos, Jaime Duque Domingo, Eduardo Zalama, Jaime Gomez-Garcia-Bermejo, Joaquin Lopez
Summary: The study focuses on improving the living conditions of elderly individuals living alone by developing a database using non-intrusive technology to monitor their daily activities and state. Deep learning techniques were used to develop personalized prediction models for accurate activity recognition. A data sharing algorithm was developed to enhance the model's generalizability and prevent overtraining of the neural network.
Article
Engineering, Electrical & Electronic
Ghulam Muhammad, M. Shamim Hossain, Neeraj Kumar
Summary: A remote pathology detection system based on EEG with a deep convolutional network achieved over 89% accuracy on a publicly available EEG signal database. The system was also evaluated in a cloud-based framework and showed comparable performance to using a local server.
IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS
(2021)
Article
Management
Paul Moritz Wiegmann, Felix Eggers, Henk J. de Vries, Knut Blind
Summary: Standard-setting organizations (SSOs) establish goal-directed networks for innovators to jointly shape technology and markets through standards. The preferences of SSO members in network set-ups and governance are not well understood. This study provides a more realistic indication of what firms value in SSOs based on a choice experiment with standardization professionals in the Internet of Things field.
Article
Multidisciplinary Sciences
Emily E. Haroz, Allison Ingalls, Karla Decker Sorby, Mary Dozier, Miranda P. Kaye, Michelle Sarche, Lauren H. Supplee, Daniel J. Whitaker, Fiona Grubin, Deborah Daro
Summary: This study aims to develop an expert consensus taxonomy on the essential elements used in home visiting practice that contribute to priority outcome domains. Through a Delphi approach, the research team identified 48 standard practice elements and 83 behavior change techniques, rating their importance to 10 outcome domains.
Article
Computer Science, Artificial Intelligence
Peter Langfield, Yingjing Feng, Laura R. Bear, Josselin Duchateau, Rafael Sebastian, Emma Abell, Remi Dubois, Louis Labrousse, Julien Rogier, Meleze Hocini, Michel Haissaguerre, Edward Vigmond
Summary: The study aimed to investigate the effects of high-pass filtering on RT estimation using UEs, and found that DNN outperformed the Wyatt method in most cases, resulting in significantly lower absolute error.
MEDICAL IMAGE ANALYSIS
(2021)
Article
Chemistry, Multidisciplinary
Virginia Morini, Laura Pollacci, Giulio Rossetti
Summary: The framework proposed in this paper can be used to detect echo chambers across multiple online social networks, allowing for comparative analysis of platforms and their polarization levels. While users tend to be polarized in ideology, most do not completely isolate themselves in echo chambers, with the found polarized communities proving to be stable over time.
APPLIED SCIENCES-BASEL
(2021)
Article
Construction & Building Technology
Pedro Racha-Pacheco, Jorge T. Ribeiro, Jose Afonso
Summary: This article addresses the issue of incorporating cutting-edge technologies into urban small-scale residential architecture. A methodology was conceived to research automation and information networks, and guidelines for prototype design were defined based on previous knowledge. The prototype design presented in this article contributes to sensitizing architecture professionals to the importance of integrated and systematized thinking in smart home design.
Article
Chemistry, Analytical
Ziad Hatab, Arezoo Abdi, Gregor Steinbauer, Michael Ernst Gadringer, Wolfgang Boesch
Summary: This study introduces a novel method for measuring the propagation constant of transmission lines without the need for prior calibration of a two-port vector network analyzer (VNA). By emulating multiple line standards, the method achieves accurate results. Measurements were conducted using a slab coaxial airline on three different VNAs, all yielding nearly identical results. The proposed method eliminates errors related to connection repeatability, resulting in improved broadband traceability to SI units.
Article
Automation & Control Systems
Mu-Yen Chen
Summary: This article proposes a system using beacon technology and cameras for an intelligent home monitoring system to ensure the safety of elderly people. Additionally, it enhances object readability and privacy through federated learning and privacy protection.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2022)
Article
Physics, Multidisciplinary
Yifan He, Chen Zhao, An Zeng
Summary: This paper uses 4G communication data of 1.7 million users in Shijiazhuang, a city in northern China, to investigate user mobility patterns and analyze the importance of locations in the city. The study reveals that most users prefer to live and work within the same district and identifies important locations using the weighted PageRank algorithm.
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS
(2022)
Article
Computer Science, Hardware & Architecture
Mohanad Sarhan, Siamak Layeghy, Marius Portmann
Summary: This paper proposes and evaluates standard NIDS feature sets based on the NetFlow network meta-data collection protocol and system to address the lack of standard feature sets in current NIDS datasets. The NetFlow-based NIDS feature set allows for a fair comparison of ML-based network traffic classifiers across different NIDS datasets, potentially bridging the gap between academic research and practical deployment of such systems.
MOBILE NETWORKS & APPLICATIONS
(2022)
Article
Automation & Control Systems
Sami Ben Slama, Marwan Mahmoud
Summary: This paper proposes an advanced Intelligent Home Energy Management (IHEM) approach based on reinforcement learning to achieve home demand response (DR) efficiency. The results show that the proposed optimization method reduces the monthly electricity costs by 20% compared to the Integer Linear Programming (ILP)-based HEMS method.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Chemistry, Analytical
Pedro H. A. D. de Melo, Rodrigo Sanches Miani, Pedro Frosi Rosa
Summary: This study proposes the FamilyGuard architecture to enhance the security of smart homes by detecting network traffic anomalies and simplifying the management of the home environment. The effectiveness of the architecture is validated through experiments, and an anomaly detection module based on network flow using one-class classifiers is developed.