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
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
Health Care Sciences & Services
Seok-Ho Yun, Hyeon-Joo Kim, Jeh-Kwang Ryu, Seung-Chan Kim
Summary: In this study, a smartwatch-based wearable system was proposed to classify squat motions with fine-grained classification. Deep neural network-based models and a baseline method (random forest) were used for experiments. The bidirectional GRU/LSTMs with an attention mechanism and the arm posture of hands on waist achieved the best test accuracy (F1-score) of 0.854 (0.856). The attention-based models learned features from complex multivariate time-series motion signals more efficiently, as shown by the clustered distributions of high-dimensional embeddings in latent space.
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
Computer Science, Artificial Intelligence
J. A. Garcia-Pulido, G. Pajares, S. Dormido
Summary: Unmanned aerial vehicles (UAVs) require additional support during the last phase of landing, for which a cognitive computing-based perception system is proposed in this study. This system utilizes on-board camera and intelligence to recognize the specially designed target, allowing the UAVs to land on the platform. The proposed method outperforms existing strategies, especially in the use of color information, as demonstrated in the test with 800 images captured by a smartphone onboard a quad-rotor UAV.
COGNITIVE COMPUTATION
(2023)
Review
Oncology
Socrate Pallio, Stefano Francesco Crino, Marcello Maida, Emanuele Sinagra, Vincenzo Francesco Tripodi, Antonio Facciorusso, Andrew Ofosu, Maria Cristina Conti Bellocchi, Endrit Shahini, Giuseppinella Melita
Summary: Endoscopic ultrasound is a valuable technique for evaluating subepithelial lesions and determining their malignancy. Gastrointestinal Stromal Tumors (GISTs) require differential diagnosis due to their potential malignant behavior. Conventional endoscopic ultrasound may have difficulties distinguishing GISTs from other subepithelial lesions, but recent advancements in enhanced modalities and artificial intelligence systems have improved diagnostic accuracy.
Article
Computer Science, Information Systems
Juan Jesus Ojeda-Castelo, Maria de las Mercedes Capobianco-Uriarte, Jose Antonio Piedra-Fernandez, Rosa Ayala
Summary: Gesture recognition is an ideal means of interaction that allows users to avoid contact with surfaces, making it safe and hygienic. Despite being researched for many years, it has not replaced keyboards and mice. Deep learning has made significant advancements in gesture recognition, offering the potential for it to become a viable option for daily user interaction.
Review
Engineering, Biomedical
Habib Zaidi, Issam El Naqa
Summary: The past decade has seen a growing interest in quantitative molecular imaging using ML/DL techniques, covering various steps from basic principles to obtaining quantitatively accurate PET data. This includes algorithms for denoising or correcting physical degrading factors, as well as quantifying tracer uptake and metabolic tumor volume for treatment monitoring or radiation therapy planning and response prediction. Challenges and opportunities for the adoption of ML/DL approaches in multimodality imaging are also discussed in this review.
ANNUAL REVIEW OF BIOMEDICAL ENGINEERING, VOL 23, 2021
(2021)
Review
Green & Sustainable Science & Technology
Sandhya Sharma, Kazuhiko Sato, Bishnu Prasad Gautam
Summary: Artificial intelligence (AI) has been increasingly used in the environmental sector, particularly in wildlife acoustic monitoring. A literature review shows that AI techniques have been widely employed in this field, with a focus on birds and mammals. The most commonly used AI algorithm, Convolutional Neural Network, has shown to be more accurate and beneficial than previous methods for categorizing acoustic data. This highlights the great potential of AI in advancing our understanding of wildlife populations and ecosystems, but further research is needed to fully realize its capabilities and develop improved algorithms.
Article
Psychology, Multidisciplinary
Meisam Gordan, Ong Zhi Chao, Saeed-Reza Sabbagh-Yazdi, Lai Khin Wee, Khaled Ghaedi, Zubaidah Ismail
Summary: This paper explores the relationship between the use of advanced computational intelligence and the development of Structural Health Monitoring (SHM) solutions. It develops Artificial Intelligence (AI)-based algorithms for damage assessment using a lab-scale composite bridge deck structure.
FRONTIERS IN PSYCHOLOGY
(2022)
Article
Engineering, Electrical & Electronic
Hoanglong Dang, Hyejin Park, Sangshin Kwak, Seungdeog Choi
Summary: The reliability of electronic converters in industrialized areas is crucial, with capacitors being a critical component. This study proposes an estimation scheme using source current to assess capacitor health status and employs various advanced techniques to achieve this.
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
Radiology, Nuclear Medicine & Medical Imaging
Yuko Nakamura, Toru Higaki, Yukiko Honda, Fuminari Tatsugami, Chihiro Tani, Wataru Fukumoto, Keigo Narita, Shota Kondo, Motonori Akagi, Kazuo Awai
Summary: This review examines the use of advanced imaging techniques such as dual-energy CT, perfusion CT, and artificial intelligence for the precise characterization of liver tumors, treatment response quantification, and overall survival rate prediction in hepatocellular carcinoma (HCC) patients. The advantages and disadvantages of conventional hepatic dynamic CT imaging are discussed, along with the clinical applications and limitations of dual-energy and perfusion CT in the context of HCC. Additionally, the utility of artificial intelligence-based methods for diagnosing HCC is explored.
Editorial Material
Computer Science, Artificial Intelligence
Lei Chen, Xiangmin Zhou, Xiaochun Yang, Timos Sellis
Summary: The rapid growth of online service platforms has changed the way users conduct daily activities, and recommendation has become a key method for understanding users and promoting services. Effective recommendation of online items is particularly important in e-commerce and online media. However, there are still many challenges in this field, such as context discovery, user behavior influence, and big data management, which require new solutions using AI and Big Data techniques.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2023)
