Article
Automation & Control Systems
Lucia Cascone, Michele Nappi, Fabio Narducci, Ignazio Passero
Summary: The article discusses the development of VPepper, a virtual replica of the Pepper robot, and its interaction with smart objects in a smart home environment. Through the use of digital twin, machine learning procedures can be seamlessly transferred between the virtual replica and the physical robot. The practical application shows promising opportunities for simulation accuracy and machine learning instruments in real settings.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2022)
Article
Computer Science, Information Systems
George A. Oguntala, Yim Fun Hu, Ali A. S. Alabdullah, Raed A. Abd-Alhameed, Muhammad Ali, Doanh K. Luong
Summary: The proposed framework integrates passive RFID tags' RSSI to obtain detailed activity profiling, and employs key indices of position, orientation, mobility, and degree of activities to guide reliable clinical management decisions. A two-layer, fully connected sequence LSTM RNN model is utilized to extract features from sensor data and classify activities, achieving an accuracy of 98.18%. This framework is suitable for smart health and smart homes, providing a pervasive sensing environment for the elderly, persons with disabilities, and chronic illnesses.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Computer Science, Software Engineering
Ana Cholakoska, Hristijan Gjoreski, Valentin Rakovic, Daniel Denkovski, Marija Kalendar, Bjarne Pfitzner, Bert Arnrich
Summary: Given the rapid expansion and widespread adoption of the Internet of Things, it is important to establish secure interaction between devices without compromising performance. Machine learning techniques have been used to improve anomaly detection in these networks, but they often result in poor performance and compromised privacy. Federated learning (FL) has been introduced to address these issues, enabling devices to collaboratively train and evaluate a shared model while keeping personal data on site. This article investigates the performance of FL compared to deep learning (DL) in network intrusion detection in ambient assisted living environments, and demonstrates comparable performances with improved data privacy and security.
IEEE INTERNET COMPUTING
(2023)
Article
Computer Science, Information Systems
Jie Wan, MingSong Li, Michael J. OGrady, Xiang Gu, Munassar A. A. H. Alawlaqi, Gregory M. P. OHare
Summary: Real-time activity recognition is essential for smart homes, but is currently dominated by the research community using machine learning and AI techniques. Research mainly relies on pre-segmented data, which may not be sufficient for assistive paradigms dependent on smart technologies.
IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTING
(2021)
Article
Computer Science, Artificial Intelligence
Paris Her, Logan Manderle, Philipe A. Dias, Henry Medeiros, Francesca Odone
Summary: Effective assisted living environments require the ability to understand how occupants interact. This paper focuses on gaze tracking in multi-camera assisted living environments. A neural network regressor is used to estimate gaze based on relative facial keypoints. The method also provides uncertainty predictions for each gaze estimate, which are used within a tracking framework. Experimental results show that the proposed method outperforms state-of-the-art methods and generates accurate and temporally stable gaze predictions.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2023)
Article
Computer Science, Artificial Intelligence
C. L. Oguego, J. C. Augusto, M. Springett, M. Quinde, C. James-Reynolds
Summary: Preferences play a crucial role in decision-making, and understanding preference management is key to developing systems that guide user choices. By exploring argumentation techniques and implementing them in real-life scenarios, this study validates the effectiveness of argumentation in handling conflicting preferences and inconsistencies. The system implemented in this study not only manages conflicting situations in smart homes, but also interacts with external data sources to provide personalized suggestions to users based on their preferences.
APPLIED ARTIFICIAL INTELLIGENCE
(2021)
Article
Computer Science, Hardware & Architecture
G. Vallathan, A. John, Chandrasegar Thirumalai, SenthilKumar Mohan, Gautam Srivastava, Jerry Chun-Wei Lin
Summary: This paper proposes a novel deep learning-based method for predicting abnormal events and notifying users in an IoT environment, aiming to protect children from abuse.
JOURNAL OF SUPERCOMPUTING
(2021)
Article
Chemistry, Analytical
Bruna Maria Vittoria Guerra, Micaela Schmid, Giorgio Beltrami, Stefano Ramat
Summary: Human Action Recognition (HAR) is an evolving field that has impacts on various domains, including Ambient Assisted Living (AAL). This study proposes a monitoring system that detects dangerous situations by classifying human postures using Artificial Intelligence (AI) solutions. The analysis shows that the LSTM approach has better suitability and achieves higher performance compared to the MLP approach.
Article
Chemistry, Analytical
Caetano Mazzoni Ranieri, Scott MacLeod, Mauro Dragone, Patricia Amancio Vargas, Roseli Aparecida Francelin Romero
Summary: Global demographic projections showing an aging population have driven research on Ambient Assisted Living, focusing on smart homes and social robots. This paper addresses the recognition of heterogeneous daily living activities in home environments using data from videos, wearable IMUs, and ambient sensors. The study introduces a Deep Learning framework for multimodal activity recognition in collaboration with the HWU-USP dataset, demonstrating improved accuracy results through the integration of ambient sensor data.
Article
Multidisciplinary Sciences
Wiktoria Wilkowska, Julia Offermann, Susanna Spinsante, Angelica Poli, Martina Ziefle
Summary: This study investigated the technology acceptance and privacy perceptions of sensor-based applications implemented in private environments. The results showed that participants recognized the benefits of these technologies but had limited intention to use them. They highly valued their privacy and considered the collection of data in intimate spaces as problematic.
Article
Engineering, Environmental
Ke Min, Shuyu Hao, Yue Lin, Dawei Lu, Yifan Lv, Weican Zhang, Nan Ji, Qian Liu, Guibin Jiang
Summary: This study developed a label-free and sensitive method for detecting black carbon particles in the human brain and found that the concentration of black carbon was extremely low or absent in the brain samples. More research is needed to understand the neurotoxic risks of particulate pollution.
ENVIRONMENTAL SCIENCE & TECHNOLOGY LETTERS
(2023)
Article
Computer Science, Information Systems
Mohannad Babli, Jaime A. Rincon, Eva Onaindia, Carlos Carrascosa, Vicente Julian
Summary: The study proposed a deliberation architecture for ambient intelligence healthcare applications, aiming to provide comfort to stressed seniors in assisted living homes. By designing a deliberation function, it achieved context-aware dynamic human-robot interaction, perception, planning capabilities, reactivity, and environment awareness.
HUMAN-CENTRIC COMPUTING AND INFORMATION SCIENCES
(2021)
Review
Health Care Sciences & Services
Mladjan Jovanovic, Goran Mitrov, Eftim Zdravevski, Petre Lameski, Sara Colantonio, Martin Kampel, Hilda Tellioglu, Francisco Florez-Revuelta
Summary: This study presents a scoping review of AI models in Ambient Assisted Living (AAL), analyzing the specific models used, target domains, technology, and concerns from the end-user perspective. The findings provide insights for the development, deployment, and evaluation of future intelligent AAL systems.
JOURNAL OF MEDICAL INTERNET RESEARCH
(2022)
Article
Geriatrics & Gerontology
Helena Temkin-Greener, Yunjiao Mao, Yue Li, Brian McGarry
Summary: The objective of this study was to develop an approach for identifying Medicare beneficiaries residing in US assisted living communities. The researchers used multiple data sources, including a national directory of licensed assisted living communities, US addresses and their associated ZIP+4 codes, and Medicare enrollment and beneficiary files. The study identified characteristics of Medicare beneficiaries living in assisted living communities and validated the approach through comparisons with other beneficiary cohorts.
JOURNAL OF THE AMERICAN MEDICAL DIRECTORS ASSOCIATION
(2023)
Review
Computer Science, Information Systems
Mohamed-Amine Choukou, Taylor Shortly, Nicole Leclerc, Derek Freier, Genevieve Lessard, Louise Demers, Claudine Auger
Summary: This study aims to explore the acceptance evaluation of AALT technologies in rehabilitation contexts. A total of 51 AALTs dedicated to various rehabilitation contexts were identified, with focus on monitoring OAs' activities and environmental changes. Although older adults intend to use and perceive the usefulness of AALTs, they still have concerns and hesitation about adopting the technology, suggesting the need for more comprehensive and standardized methodologies in assessing AALT acceptance.
INTERNATIONAL JOURNAL OF MEDICAL INFORMATICS
(2021)
Article
Automation & Control Systems
Victor Casamayor-Pujol, Bernat Gaston, Sergio Lopez-Soriano, Abdussalam A. Alajami, Rafael Pous
Summary: This article presents a simple solution using an autonomous ground robot with a radio frequency identification payload to estimate the location of products in a retail store. The model used is designed to be simple and versatile, while achieving accurate location estimations. The research results show that the model performs well in different environments and meets the business requirements of the retail industry.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2022)
Article
Chemistry, Analytical
Golshan Famitafreshi, Muhammad Shahwaiz Afaqui, Joan Melia-Segui
Summary: This paper investigates the use of solar energy harvesting technology to improve energy efficiency in IoT medical devices. A new algorithm for energy consumption mitigation is proposed, reducing energy consumption while maintaining the required Quality of Service. This research is significant for integrating energy harvesting technology in IoT.
Article
Green & Sustainable Science & Technology
Lukasz Pasko, Maksymilian Madziel, Dorota Stadnicka, Grzegorz Dec, Anna Carreras-Coch, Xavier Sole-Beteta, Lamprini Pappa, Chrysostomos Stylios, Daniele Mazzei, Daniele Atzeni
Summary: This article presents the results of a self-assessment study conducted among students in the field of Internet of Things (IoT), Artificial Intelligence (AI), and Edge Computing (EC). The study reveals the students' level of knowledge and skills in specific areas, which can be useful for the industry to assess available competences in the labor market. It also provides universities with insights into areas of competency gaps and preferred teaching methods in AI, IoT, and EC.
Review
Computer Science, Information Systems
Anna Carreras-Coch, Joan Navarro, Carles Sans, Agustin Zaballos
Summary: Emergency situations require continuous communication between different teams and devices, but conventional communication technologies may become unusable during disasters. This paper aims to review the challenges of emergency communications and proposes a heterogeneous communication architecture for emergency situations.
Article
Engineering, Electrical & Electronic
Jon Lejarreta-Andres, Joan Melia-Segui, Rahul Bhattacharyya, Xavier Vilajosana, Sanjay E. Sarma
Summary: This study analyzes the RFID signal during the fabric drying process to find classifiable patterns. The preliminary results show better performance for meander tag antennas and high accuracy and F1 scores when classifying cotton and polyester fabrics. The proposed method has the potential to achieve low-cost unassisted bulk fabric identification, which can help automate recycling processes and support circular economy policies in the textile industry.
IEEE SENSORS JOURNAL
(2022)
Review
Chemistry, Analytical
Dorota Stadnicka, Jaroslaw Sep, Riccardo Amadio, Daniele Mazzei, Marios Tyrovolas, Chrysostomos Stylios, Anna Carreras-Coch, Juan Alfonso Merino, Tomasz Zabinski, Joan Navarro
Summary: This study investigates and identifies the current problems and needs of the industry from an educational perspective, aiming to facilitate the digital transformation of manufacturing. The findings highlight the importance of developing a taxonomy that includes industrial problems and their technological solutions, as well as the need to enhance the education and training of engineers and researchers.
Article
Chemistry, Analytical
Eduardo Perez, Raul Parada, Carlos Monzo
Summary: This paper proposes a hybrid network that combines wireless personal access network (WPAN) and low power wide access network (LPWAN) communication for the development of a global emergency system with low energy consumption, wide communication range, and low service costs.
Article
Computer Science, Artificial Intelligence
Fernando Sevilla Martinez, Raul Parada, Jordi Casas-Roma
Summary: Autonomous driving and the machine learning models used for it have become increasingly important and complex, leading to a significant carbon footprint. This study introduces two different training approaches and compares their impact on carbon emissions. The new training method reduces training time by 38 times and decreases carbon emissions by 96%.
ADVANCED ENGINEERING INFORMATICS
(2023)
Article
Engineering, Electrical & Electronic
Cristina Villar Miguelez, Victor Monzon Baeza, Raul Parada, Carlos Monzo
Summary: Global warming has increased uncertainty in managing traditional water supply systems, highlighting the need for smart management. This study aims to design a solution for renewing and securing critical water supply infrastructure within the scope of Industry 4.0 for Smart Cities. It analyzes renewal requirements, applicable use cases, and proposes an IoT-based solution for critical infrastructure in urban environments.
Article
Engineering, Aerospace
Raul Parada, Victor Monzon Baeza, David N. Barraca-Ibort, Carlos Monzo
Summary: Wireless broadband coverage has reached 95% globally, but is expected to remain stable in the coming years, posing challenges for remote areas. In response, we propose a low-cost, green-based nanosatellite system to provide complete coverage in hard-to-reach areas using long-range communication. The system is flexible and can be customized according to user requirements, with successful validation through experiments.
Article
Computer Science, Information Systems
Golshan Famitafreshi, M. Shahwaiz Afaqui, Joan Melia-Segui
Summary: The crisis of energy supplies has led to the need for sustainability in technology, especially in the IoT paradigm. This paper presents a simulation-based study on the integration of energy harvesting technologies into Wi-Fi networks in an e-Health environment. Optimization algorithms utilizing reinforcement learning methods are introduced to reduce network energy consumption while maintaining the required QoS. The results show significant energy savings and demonstrate the feasibility of using smaller solar cells in IoT devices, enhancing the flexibility of energy harvesting techniques. This research opens up new possibilities for energy harvesting integration in IoT, particularly in contexts with restricted QoS environments.
Proceedings Paper
Engineering, Electrical & Electronic
Raul Parada, Francisco Vazquez-Gallego, Roshan Sedar, Ricard Vilalta
Summary: To enhance road safety, modern vehicles are equipped with smart sensors and V2X communication technologies to exchange data with other vehicles and road infrastructure. By deploying a Collision Avoidance service on a mobile edge computing platform, low latency detection and localization of road hazards can be achieved.
2022 IEEE 95TH VEHICULAR TECHNOLOGY CONFERENCE (VTC2022-SPRING)
(2022)
Article
Computer Science, Information Systems
Abdussalam A. Alajami, Guillem Moreno, Rafael Pous
Summary: This paper discusses the simulation of RFID readers for robots in the context of Industry 4.0, presenting the design of an RFID system plugin based on ROS and Gazebo, as well as the probabilistic model behind the plugin. The paper demonstrates the flexibility of the simulator for use on various robot platforms and compares simulation and experimental results in navigating environments with RFID tags.
Proceedings Paper
Computer Science, Information Systems
Joan Melia-Segui, Imanol Rojas, Jon Lejarreta-Andres, Xavier Vilajosana
Summary: Digitization is important for the development of Industry 4.0. This article proposes a cost-efficient method for sensing high temperatures using standard UHF RFID sensors, achieving a temperature prediction with only 1.5% error.
2022 IEEE INTERNATIONAL CONFERENCE ON RFID (IEEE RFID 2022)
(2022)
Article
Remote Sensing
Abdussalam A. Alajami, Guillem Moreno, Rafael Pous
Summary: This article discusses the issue of autonomous navigation for UAVs in indoor map-less environments while performing an inventory mission. It proposes a solution of using RFID technology with UAVs and introduces a RFID-based stigmergic and obstacle avoidance navigation system (RFID-SOAN) for indoor UAVs. Through experiments, it is proven that the proposed UAV is able to estimate the time needed to read RFID tags accurately and efficiently, and cover only areas with RFID tags, making it more efficient than traditional navigation methods.