Article
Engineering, Biomedical
Hygor Vinicius Pereira Martins, Joao Antonio Palma Setti, Cayley Guimaraes, Daniel Prado Campos
Summary: This study proposed an open-source myoelectric robotic hand orthosis prototype to support people with neuromuscular disorders in performing activities of daily living (ADLs). The prototype achieved a high accuracy of 90% in real-time tests with three everyday objects. The open-source format provides other researchers a starting point to develop an orthosis for in-home rehabilitation that actively assists in ADLs.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Computer Science, Artificial Intelligence
Alessandra De Paola, Salvatore Gaglio, Andrea Giammanco, Giuseppe Lo Re, Marco Morana
Summary: Modern smart environments present challenges in designing intelligent algorithms to assist users, such as trajectory recommendations and itinerary planning in the face of diverse points of interest. A multi-agent itinerary suggestion system is proposed to address these challenges, utilizing reinforcement learning to provide high-quality suggestions and overcome issues like cold-start and preference elicitation. Real-life deployments have shown the effectiveness of the approach in scenarios such as smart campuses and theme parks.
CAAI TRANSACTIONS ON INTELLIGENCE TECHNOLOGY
(2021)
Article
Computer Science, Artificial Intelligence
Shanu K. Rakesh, Manish Shrivastava
Summary: Swarm robotics is a field inspired by natural swarms, aiming to study swarm intelligence and collaboration. This paper proposes a fault-tolerant pattern formation algorithm, and through simulations and experiments, it demonstrates the algorithm's ability to successfully form and maintain geometric patterns in the presence of faulty agents.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Automation & Control Systems
Yuming Li, Wei Zhang, Yanyan Liu, Rudong Jing, Changsong Liu
Summary: This paper proposes an object detection model based on DETR for fire and smoke detection, which simplifies the detection pipeline and builds an end-to-end detector. By adding a normalization-based attention module in the feature extraction stage and using multiscale deformable attention in the encoder-decoder structure, the model achieves improved detection performance while reducing complexity.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2022)
Article
Computer Science, Information Systems
Silvio Barra, Salvatore M. Carta, Alessandro Giuliani, Alessia Pisu, Alessandro Sebastian Podda, Daniele Riboni
Summary: This article introduces an AI-based system for football match annotation, which utilizes a mixed user interface to annotate football matches and processes players' motor performance using machine learning algorithms. The experimental results of the system demonstrate its effectiveness in real-world adoption scenarios.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Engineering, Biomedical
Carmen Camara, Pedro Peris-Lopez, Masoumeh Safkhani, Nasour Bagheri
Summary: The study introduces an innovative identification technique using electrocardiograms and musical features, achieving high accuracy in identity verification by converting ECGs into audio files and extracting features.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2022)
Review
Multidisciplinary Sciences
Joel Serey, Miguel Alfaro, Guillermo Fuertes, Manuel Vargas, Claudia Duran, Rodrigo Ternero, Ricardo Rivera, Jorge Sabattin
Summary: The purpose of this study is to summarize the PR and DL artificial intelligence methods developed for data management in the last six years. Content analysis was used as the methodology, with 186 references considered and 120 selected for the literature review. The study provides an overview of the applications, challenges, advantages, and disadvantages of PR/DL methods in data management, as well as emerging research trends and future research paths.
Article
Chemistry, Multidisciplinary
Van-Nhan Tran, Suk-Hwan Lee, Hoanh-Su Le, Ki-Ryong Kwon
Summary: Our research proposes a high-performance DeepFake detection model with a focus on reducing overfitting issues, which is a common problem affecting model quality. Testing on two datasets, our model achieved an AUC of 0.958 and F1-score of 0.9243 on the DFDC dataset, compared to the SOTA model which achieved 0.972 AUC and 0.906 F1-score, and on the Celeb-DF v2 dataset with an AUC of 0.978 and F1-score of 0.9628.
APPLIED SCIENCES-BASEL
(2021)
Article
Business
Jo Ann Oravec
Summary: An assortment of attacks and aggressive behaviors towards AI-enhanced robots have recently emerged. This paper explores how the emotions and motivations involved in these attacks are framed and how the incidents are presented in social media and traditional broadcast channels. The paper argues that understanding the emotions and motivations of robot attackers can be helpful in mitigating anti-robot activities and suggests using hate crime characterizations in discourse and legislative efforts. It also highlights the role of social media in disseminating videos and narrative accounts of robot attacks.
TECHNOLOGICAL FORECASTING AND SOCIAL CHANGE
(2023)
Article
Computer Science, Artificial Intelligence
Hojjat Abdollahi, Mohammad H. Mahoor, Rohola Zandie, Jarid Siewierski, Sara H. Qualls
Summary: This paper presents recent research on integrating artificial emotional intelligence in a social robot and examines the effectiveness of the robot in engaging older adults. The study shows that both empathic and non-empathic versions of the robot have a positive effect on the users' reported mood. However, users perceive the empathic version as more engaging and likable based on measures of spoken words and exit survey analysis.
IEEE TRANSACTIONS ON AFFECTIVE COMPUTING
(2023)
Article
Medicine, General & Internal
Enrico Checcucci, Pietro Piazzolla, Giorgia Marullo, Chiara Innocente, Federico Salerno, Luca Ulrich, Sandro Moos, Alberto Quara, Gabriele Volpi, Daniele Amparore, Federico Piramide, Alexandru Turcan, Valentina Garzena, Davide Garino, Sabrina De Cillis, Michele Sica, Paolo Verri, Alberto Piana, Lorenzo Castellino, Stefano Alba, Michele Di Dio, Cristian Fiori, Eugenio Alladio, Enrico Vezzetti, Francesco Porpiglia
Summary: This research presents a groundbreaking solution utilizing convolutional neural networks (CNNs) to forecast instances of intraoperative bleeding during robot-assisted radical prostatectomy (RARP) and promptly notify the surgeon. The software, called BLAIR, achieved over 90% accuracy in predicting bleeding events, demonstrating the potential of AI in assisting surgeons during interventions. This study exemplifies the positive impact AI applications can have on surgical procedures.
JOURNAL OF CLINICAL MEDICINE
(2023)
Article
Computer Science, Artificial Intelligence
Victor Corsino, Jose Manuel Gilperez, Luis Herrera
Summary: The analysis of numerical sequences in intelligence tests is important for evaluating AI systems. KitBit, a new computational model, uses a reduced set of algorithms to build a predictive model and find patterns in numerical sequences. The model performs well in IQ tests and other complex cases, solving problems quickly. Additionally, KitBit's algorithms have been applied to the OEIS database, discovering patterns in a large number of sequences and predicting the next terms.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Chemistry, Multidisciplinary
Mohammed Ghazal, Maha Yaghi, Abdalla Gad, Gasm El Bary, Marah Alhalabi, Mohammad Alkhedher, Ayman S. El-Baz
Summary: This study aims to design a system that assists the elderly and people of determination in shopping activities, including retrieving items from high shelves and self-checkout, using advanced barcode detection and artificial intelligence technology with high accuracy and real-time efficiency. Additionally, the system integrates an anti-theft feature to enhance the security of the shopping process.
APPLIED SCIENCES-BASEL
(2021)
Review
Chemistry, Multidisciplinary
Karolina Kudelina, Toomas Vaimann, Bilal Asad, Anton Rassolkin, Ants Kallaste, Galina Demidova
Summary: This paper reviews the fault diagnostic techniques based on machine learning, highlighting the increasing capability of using cloud computation for processing faulty data and the potential of utilizing mathematical models of electrical machines for training AI algorithms in the era of industry 4.0.
APPLIED SCIENCES-BASEL
(2021)
Article
Automation & Control Systems
Laura Gemmell, Lucy Wenham, Sabine Hauert
Summary: The study explores the inequalities in robotics and artificial intelligence education and how to ensure the success of education in this field. It found that education needs to be provided at different levels for those designing RAI, working with RAI, and the general public. Overcoming preconceptions and co-designing education with communities are crucial for successful education initiatives.
ADVANCED INTELLIGENT SYSTEMS
(2021)