Related references
Note: Only part of the references are listed.
Article
Engineering, Multidisciplinary
Yang Yu et al.
Summary: This study proposes a vision-based crack diagnosis method using deep convolutional neural network (DCNN) and enhanced chicken swarm algorithm (ECSA) for model training and optimization. The method is tested on image patches cropped from damaged concrete samples, and its performance is evaluated using a group of statistical evaluation indicators.
STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL
(2022)
Article
Biotechnology & Applied Microbiology
Carlo Ricciardi et al.
Summary: This study uses preoperative data of patients with femur fractures to establish models for predicting hospital length of stay (LOS). Regression analysis and classification analysis were conducted to predict overall LOS. The results show that the support vector machine is the most effective predictive model, and the mean absolute error is small for all algorithms. The use of these techniques can provide valuable support for doctors in managing orthopedic departments and resources, reducing waste and costs in healthcare.
BIOENGINEERING-BASEL
(2022)
Review
Environmental Sciences
Shahzad Ahmed et al.
Summary: This article reviews the development of Hand Gesture Recognition (HGR) using radar sensors, presenting available techniques for multi-domain hand gestures data representation and deep-learning-based algorithms. The hardware and algorithmic details of different types of radars used for HGR are discussed, along with quantitative and qualitative analysis of trends in radar-based HCI. The article also covers developed devices and applications based on gesture-recognition through radar, as well as limitations, future aspects, and research directions in the field.
Article
Chemistry, Analytical
Tsige Tadesse Alemayoh et al.
Summary: This study introduces a new method for activity recognition using smartphone data collection and deep learning classification with neural network models. The experimental results show good performance, with better performance validated on other datasets, and the practicality of the model was demonstrated in real-time testing on a computer and smartphone.
Proceedings Paper
Computer Science, Artificial Intelligence
Anton Chernyavskiy et al.
Summary: Recent advancements in neural architectures, such as Transformer, and the emergence of large-scale pre-trained models like BERT have revolutionized the field of Natural Language Processing (NLP). However, current models still have limitations in modeling certain types of information. By demonstrating and discussing these limitations, it is possible to find ways to improve model performance and explore desired enhancements for future Transformer architectures.
MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES, ECML PKDD 2021: RESEARCH TRACK, PT III
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Mohamad Wehbi et al.
Summary: This paper introduces an online handwriting recognition system based on IMUs, digitizing text with a sensor-equipped pen. The model combines convolutional and bidirectional LSTM networks, trained with Connectionist Temporal Classification loss for interpreting sensor data into words without sequence segmentation. The system achieves a character error rate of 17.97% and 17.08% on distinct test sets of seen and unseen words, respectively.
DOCUMENT ANALYSIS AND RECOGNITION, ICDAR 2021, PT III
(2021)
Article
Computer Science, Information Systems
Chaur-Heh Hsieh et al.
Summary: This paper proposes a simple and effective air-writing recognition approach based on deep convolutional neural networks, with a robust hand tracking algorithm and novel preprocessing scheme, achieving higher recognition accuracy without restrictions. The method not only reduces network complexity but also addresses some fundamental issues in isolated writing.
Proceedings Paper
Engineering, Electrical & Electronic
Masaaki Shintani et al.
Summary: This study investigates a novel technology for digitizing human handwriting, utilizing a new digital pen for real-time character recognition based on force information and sensor data. By designing a pen device with multiple tiny force sensors, and employing convolutional neural network classification and data preprocessing techniques, accurate character classification has been achieved.
2021 IEEE INTERNATIONAL CONFERENCE ON CONSUMER ELECTRONICS (ICCE)
(2021)
Article
Chemistry, Analytical
Md. Shahinur Alam et al.
Article
Engineering, Electrical & Electronic
Seong Kyu Leem et al.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2020)
Article
Chemistry, Analytical
Xin Zhang et al.
Article
Engineering, Multidisciplinary
Yang Yu et al.
STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL
(2019)
Article
Engineering, Electrical & Electronic
Shashidhar Patil et al.
JOURNAL OF SENSORS
(2016)
Proceedings Paper
Computer Science, Interdisciplinary Applications
Kazuki Tsuchida et al.
HCI INTERNATIONAL 2015 - POSTERS' EXTENDED ABSTRACTS, PT I
(2015)
Article
Automation & Control Systems
Jeen-Shing Wang et al.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2010)
Review
Computer Science, Artificial Intelligence
R Plamondon et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2000)