☆ 4.7 Article

Abnormal sitting posture recognition based on multi-scale spatiotemporal features of skeleton graph

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE (2023)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Computer Science, Artificial Intelligence

Human activity recognition based on multienvironment sensor data

Yang Li et al.

Summary: With the development of artificial intelligence and the broad application of sensors, human activity recognition (HAR) technologies based on noninvasive environmental sensors have received extensive attention and have shown great application value. This study proposes a method for single user's daily behavior recognition in multitenant smart home scenarios, which can adaptively constrain sensor noise and improve recognition accuracy.

INFORMATION FUSION (2023)

添加到收藏夹

Article Engineering, Biomedical

Arrhythmia classification algorithm based on multi-head self-attention mechanism

Yue Wang et al.

Summary: This paper proposes an arrhythmia classification algorithm based on multi-head self-attention mechanism. It preprocesses the ECG signals using wavelet transform and designs a linear projection layer and position encoding-based spatiotemporal characterization method. Experimental results show that this algorithm achieves high classification accuracy.

BIOMEDICAL SIGNAL PROCESSING AND CONTROL (2023)

添加到收藏夹

Article Engineering, Biomedical

A deep learning based 2-dimensional hip pressure signals analysis method for sitting posture recognition

Zhe Fan et al.

Summary: Abnormal sitting postures can lead to various health issues for adolescents, making the research on intelligent monitoring technology for identifying irregular sitting postures significant. This paper proposes a method based on hip pressure analysis to accurately recognize sitting postures. By using a pressure sensor array and deep convolutional neural network, the method achieves high accuracy and proves its effectiveness over computer vision methods.

BIOMEDICAL SIGNAL PROCESSING AND CONTROL (2022)

添加到收藏夹

Article Chemistry, Physical

Knitted self-powered sensing textiles for machine learning-assisted sitting posture monitoring and correction

Yang Jiang et al.

Summary: This paper presents a self-powered sitting position monitoring vest based on triboelectric nanogenerators (TENGs) that achieve accurate real-time posture recognition. The vest utilizes a knitted structure and sensor arrays to recognize different sitting postures and provide feedback, while ensuring comfortability during long-term wearing.

NANO RESEARCH (2022)

添加到收藏夹

Article Physics, Multidisciplinary

Dietary Nutritional Information Autonomous Perception Method Based on Machine Vision in Smart Homes

Hongyang Li et al.

Summary: This paper proposes a dietary nutritional information autonomous perception method based on machine vision in smart homes, and utilizes the YOLOv5 algorithm for food recognition and nutritional composition calculation. The test results show that this method has high accuracy and robustness.

ENTROPY (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

SelfMatch: Robust semisupervised time-series classification with self-distillation

Huanlai Xing et al.

Summary: This study introduces a powerful semisupervised deep learning model SelfMatch, which combines supervised learning, unsupervised learning, and self-distillation techniques. Experimental results demonstrate that SelfMatch performs exceptionally well on 35 widely used UCR2018 datasets compared to various semisupervised and supervised algorithms.

INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS (2022)

添加到收藏夹

Article Chemistry, Physical

A transient dual-type sensor based on MXene/cellulose nanofibers composite for intelligent sedentary and sitting postures monitoring

Haizhou Huang et al.

Summary: This study reports a flexible, degradable, highly sensitive dual-type sensor for monitoring sedentary and sitting postures in real-time, which is of great significance for preventing cardiovascular disease and musculoskeletal disorders.

CARBON (2022)

添加到收藏夹

Article Mathematical & Computational Biology

An Intelligent Cost-Efficient System to Prevent the Improper Posture Hazards in Offices Using Machine Learning Algorithms

Jehangir Arshad et al.

Summary: This research proposes an intelligent and cost-efficient system for detecting improper sitting postures. By using machine learning classification techniques and various sensors, the system achieves enhanced accuracy in posture detection, helping to avoid the harmful effects and potential fatal risks of prolonged improper posture.

COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE (2022)

添加到收藏夹

Article Engineering, Electrical & Electronic

An Efficient Federated Distillation Learning System for Multitask Time Series Classification

Huanlai Xing et al.

Summary: This article proposes an efficient federated distillation learning system (EFDLS) for multitask time series classification (TSC). It introduces two novel components: a feature-based student-teacher (FBST) framework and a distance-based weights matching (DBWM) scheme. Experimental results demonstrate that EFDLS outperforms other federated learning algorithms in multiple datasets and achieves higher mean accuracy compared to a single-task baseline.

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT (2022)

添加到收藏夹

Article Engineering, Electrical & Electronic

Sitting Posture Recognition Using a Spiking Neural Network

Jianquan Wang et al.

Summary: The study developed a smart chair system to recognize sitting behaviors and guide users towards proper sitting postures, achieving a prediction precision of 88.52% for 15 sitting postures through a spiking neural network and encoding algorithm.

IEEE SENSORS JOURNAL (2021)

添加到收藏夹

Article Engineering, Electrical & Electronic

Single Image Depth Map Estimation for Improving Posture Recognition

Jiaqing Liu et al.

Summary: The proposed method presents a unified framework for human posture recognition by estimating depth map from single color images, involving depth map estimation stage and recognition stage. By processing the estimated depth map, the recognition performance based on color images is improved for robust posture recognition.

IEEE SENSORS JOURNAL (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

A federated learning system with enhanced feature extraction for human activity recognition

Zhiwen Xiao et al.

Summary: This paper presents a federated learning system for human activity recognition, HARFLS, which includes a perceptive extraction network (PEN) that extracts features through a feature network and a relation network. Compared to other systems, it achieves higher recognition accuracy, especially on the WISDM and PAMAP2 datasets.

KNOWLEDGE-BASED SYSTEMS (2021)

添加到收藏夹

Article Chemistry, Analytical

Smartphone-Based Human Sitting Behaviors Recognition Using Inertial Sensor

Vikas Kumar Sinha et al.

Summary: This study used the inertial sensor built in smartphones to monitor unhealthy sitting behaviors of office workers. By changing human posture, selecting features, and combining machine learning classifiers, the overall accuracy was significantly improved.

SENSORS (2021)

添加到收藏夹

Article Engineering, Electrical & Electronic

A portable sitting posture monitoring system based on a pressure sensor array and machine learning

Xu Ran et al.

Summary: The study introduced a portable sitting posture monitoring system that can recognize user's sitting posture in real time and provide feedback. By using a pressure sensor array to collect data and implementing machine learning algorithms for seven sitting postures recognition. The system achieved optimal balance between hardware resource consumption and classification accuracy.

SENSORS AND ACTUATORS A-PHYSICAL (2021)

添加到收藏夹

Article Environmental Sciences

Worker Perspectives on Incorporating Artificial Intelligence into Office Workspaces: Implications for the Future of Office Work

Yoko E. Fukumura et al.

Summary: This study explored office workers' views on including AI in their office workspace and found that participants shared perspectives related to preferences and concerns regarding communication and interactions with the technology, as well as the dualistic nature of a system that collects large amounts of data. Additionally, the study revealed an overarching discussion related to the intersections of AI with the complexity of work performance.

INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH (2021)

添加到收藏夹

Article Nanoscience & Nanotechnology

Ultrasensitive and Wearable Carbon Hybrid Fiber Devices as Robust Intelligent Sensors

Yunfeng Hu et al.

Summary: A method for fabricating highly sensitive carbon hybrid fibers is reported, resulting in sensors with high performance for monitoring human physiological signals and preventing cervical spondylosis and lumbar disc herniation. The well-designed fiber structure exhibits excellent properties, such as high gauge factor and fast response time, making it suitable for real-time human-machine controlling systems.

ACS APPLIED MATERIALS & INTERFACES (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Detection of sitting posture using hierarchical image composition and deep learning

Audrius Kulikajevas et al.

Summary: In this paper, a novel deep recurrent hierarchical network (DRHN) model based on MobileNetV2 is proposed to address occlusion problems in human posture detection, achieving higher flexibility and accuracy. The DRHN network accepts RGB-Depth frame sequences and produces semantically related posture states, achieving 91.47% accuracy at a 10 fps rate for sitting posture recognition.

PEERJ COMPUTER SCIENCE (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Sitting posture detection and recognition of aircraft passengers using machine learning

Wenzhe Cun et al.

Summary: This study focused on the relationship between aircraft passengers' sitting postures and discomfort, identifying eight types of sitting postures using machine learning methods and achieving a classification rate of 89.26% with the support vector machine.

AI EDAM-ARTIFICIAL INTELLIGENCE FOR ENGINEERING DESIGN ANALYSIS AND MANUFACTURING (2021)

添加到收藏夹

Proceedings Paper Engineering, Electrical & Electronic

Smart Cushion Based on Pressure Sensor Array for Human Sitting Posture Recognition

Liangqi Yuan et al.

Summary: The smart cushion, designed based on a pressure sensor array, is able to recognize human sitting postures with a high accuracy of 0.978. It takes comfort into consideration while striving for both accurate sitting posture recognition and visualization application development.

2021 IEEE SENSORS (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

OpenPose: Realtime Multi-Person 2D Pose Estimation Using Part Affinity Fields

Zhe Cao et al.

Summary: This work presents a real-time approach to detect the 2D pose of multiple people in an image, achieving high accuracy and real-time performance regardless of the number of people in the image. By refining PAFs separately, both runtime performance and accuracy are significantly improved. Additionally, the first combined body and foot keypoint detector reduces inference time and maintains accuracy compared to running them sequentially.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2021)

添加到收藏夹

Article Mathematics, Applied

Gradient estimation algorithms for the parameter identification of bilinear systems using the auxiliary model

Feng Ding et al.

JOURNAL OF COMPUTATIONAL AND APPLIED MATHEMATICS (2020)

添加到收藏夹

Article Sport Sciences

Posture and Physical Activity Detection: Impact of Number of Sensors and Feature Type

Qu Tang et al.

MEDICINE & SCIENCE IN SPORTS & EXERCISE (2020)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Human posture recognition based on multiple features and rule learning

Weili Ding et al.

INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS (2020)

添加到收藏夹

Review Medicine, General & Internal

The prevalence and risk factors of work-related musculoskeletal disorders among adults in Ethiopia: a study protocol for extending a systematic review with meta-analysis of observational studies

Tsiwaye Gebreyesus et al.

SYSTEMATIC REVIEWS (2020)

添加到收藏夹

Article Computer Science, Artificial Intelligence

3D PostureNet: A unified framework for skeleton-based posture recognition

Jianbo Liu et al.

PATTERN RECOGNITION LETTERS (2020)

添加到收藏夹

Proceedings Paper Automation & Control Systems

A Wearable Multisensor Posture Detection System

Rinki Gupta et al.

PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON INTELLIGENT COMPUTING AND CONTROL SYSTEMS (ICICCS 2020) (2020)

添加到收藏夹

Article Computer Science, Information Systems

Dietary Composition Perception Algorithm Using Social Robot Audition for Mandarin Chinese

Zhidong Su et al.

IEEE ACCESS (2020)

添加到收藏夹

Article Engineering, Electrical & Electronic

Screen-Printed Piezoresistive Sensors for Monitoring Pressure Distribution in Wheelchair

Jawad Ahmad et al.

IEEE SENSORS JOURNAL (2019)

添加到收藏夹

Article Computer Science, Information Systems

Novel IoT-Based Privacy-Preserving Yoga Posture Recognition System Using Low-Resolution Infrared Sensors and Deep Learning

Munkhjargal Gochoo et al.

IEEE INTERNET OF THINGS JOURNAL (2019)

添加到收藏夹

Article Automation & Control Systems

The innovation algorithms for multivariable state-space models

Feng Ding et al.

INTERNATIONAL JOURNAL OF ADAPTIVE CONTROL AND SIGNAL PROCESSING (2019)

添加到收藏夹

Proceedings Paper Materials Science, Multidisciplinary

Sitting Posture Recognition Based on Human Body Pressure and CNN

Wenjun Liu et al.

ADVANCES IN MATERIALS, MACHINERY, ELECTRONICS III (2019)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Sitting Posture Recognition in Real-Time Combined with Index Map and BLS

Wanting Sun et al.

3RD INTERNATIONAL CONFERENCE ON INNOVATION IN ARTIFICIAL INTELLIGENCE (ICIAI 2019) (2019)

添加到收藏夹

Proceedings Paper Computer Science, Theory & Methods

The development of a wearable biofeedback trainer to increase quality of sitting posture

Rezki Riandy et al.

2ND INTERNATIONAL CONFERENCE ON DATA AND INFORMATION SCIENCE (2019)

添加到收藏夹

Article Sport Sciences

Reliable recognition of lying, sitting, and standing with a hip-worn accelerometer

H. Vaha-Ypya et al.

SCANDINAVIAN JOURNAL OF MEDICINE & SCIENCE IN SPORTS (2018)

添加到收藏夹

Article Chemistry, Analytical

Convolutional Neural Network-Based Embarrassing Situation Detection under Camera for Social Robot in Smart Homes

Guanci Yang et al.

SENSORS (2018)

添加到收藏夹

Article Chemistry, Analytical

A Scene Recognition and Semantic Analysis Approach to Unhealthy Sitting Posture Detection during Screen-Reading

Weidong Min et al.

SENSORS (2018)

添加到收藏夹

Article Orthopedics

Psoas Morphology Differs between Supine and Sitting Magnetic Resonance Imaging Lumbar Spine: Implications for Lateral Lumbar Interbody Fusion

Aaron J. Buckland et al.

ASIAN SPINE JOURNAL (2018)

添加到收藏夹

Article Computer Science, Information Systems

Four-joint motion data based posture classification for immersive postural correction system

Kyeong-Ri Ko et al.

MULTIMEDIA TOOLS AND APPLICATIONS (2017)

添加到收藏夹

Article Clinical Neurology

Association between sitting and occupational LBP

Angela Maria Lis et al.

EUROPEAN SPINE JOURNAL (2007)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.