☆ 4.8 Article

Multiresolution Fusion Convolutional Network for Open Set Human Activity Recognition

IEEE INTERNET OF THINGS JOURNAL (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 Automation & Control Systems

Multi-ResAtt: Multilevel Residual Network With Attention for Human Activity Recognition Using Wearable Sensors

Mohammed A. A. Al-qaness et al.

Summary: This study developed a deep learning architecture based on a multi-level residual network for human activity recognition, which improved recognition accuracy through model integration and feature extraction, and was evaluated and compared on multiple datasets, showing significant performance.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2023)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Collective Decision for Open Set Recognition

Chuanxing Geng et al.

Summary: This paper introduces a novel collective decision method for open set recognition, aiming to achieve new class discovery simultaneously. By slightly modifying the Hierarchical Dirichlet process, a collective decision-based OSR framework (CD-OSR) is proposed, which does not require defining the decision threshold.

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING (2022)

添加到收藏夹

Article Computer Science, Information Systems

Human Activity Recognition for Elderly People Using Machine and Deep Learning Approaches

Ahatsham Hayat et al.

Summary: This paper focuses on assisting elderly people by monitoring their activities using gyroscope and accelerometer data collected from a smart phone. Various machine learning and deep learning algorithms are utilized for human activity recognition, and the impact of cross-validation on the data is demonstrated.

INFORMATION (2022)

添加到收藏夹

Article Engineering, Multidisciplinary

Human activity recognition in IoHT applications using Arithmetic Optimization Algorithm and deep learning

Abdelghani Dahou et al.

Summary: This paper presents a novel Human Activity Recognition (HAR) system that utilizes optimization algorithms to improve performance and resource usage. The proposed model achieved competitive performance on three public datasets.

MEASUREMENT (2022)

添加到收藏夹

Article Chemistry, Analytical

Dynamic Segmentation of Sensor Events for Real-Time Human Activity Recognition in a Smart Home Context

Houda Najeh et al.

Summary: This paper investigates real-time human activity recognition based on streaming sensors, by incorporating dynamic event windowing and sensor correlation to recognize activities and record events. A real case study using the Aruba dataset from the CASAS database is conducted, and the results show that the proposed approach can effectively segment different activities.

SENSORS (2022)

添加到收藏夹

Article Computer Science, Information Systems

GRU with Dual Attentions for Sensor-Based Human Activity Recognition

Jianguo Pan et al.

Summary: This paper presents a method for human activity recognition using a Gate Recurrent Units (GRU) network that combines channel attention and temporal attention. By mitigating sensor data bias with channel attention, and capturing important motion moments and aggregating temporal features with GRU and temporal attention, this method achieves higher classification accuracy on datasets without I.I.D., while reducing model parameters and resource consumption.

ELECTRONICS (2022)

添加到收藏夹

Article Chemistry, Analytical

Ensem-HAR: An Ensemble Deep Learning Model for Smartphone Sensor-Based Human Activity Recognition for Measurement of Elderly Health Monitoring

Debarshi Bhattacharya et al.

Summary: This study proposes an ensemble of deep learning-based classification models for predicting human activity, achieving high accuracy in biomedical measurements.

BIOSENSORS-BASEL (2022)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Wearable Sensor-Based Human Activity Recognition with Hybrid Deep Learning Model

Yee Jia Luwe et al.

Summary: Mobile devices have become an essential part of daily life, and the development of wearable sensor technology, particularly the 1D-CNN-BiLSTM model, has shown promising results in human activity recognition.

INFORMATICS-BASEL (2022)

添加到收藏夹

Article Biochemical Research Methods

Assessing Impact of Sensors and Feature Selection in Smart-Insole-Based Human Activity Recognition

Luigi D'Arco et al.

Summary: This study proposes an improved smart insole-based HAR system and investigates the impact of data segmentation, sensors used, and feature selection on HAR. The findings suggest that combining inertial sensors and pressure sensors achieves the highest accuracy.

METHODS AND PROTOCOLS (2022)

添加到收藏夹

Article Health Care Sciences & Services

Human Activity Recognition Based on Embedded Sensor Data Fusion for the Internet of Healthcare Things

Mohamed E. Issa et al.

Summary: Nowadays, the use of embedded sensors in smart handheld devices, such as smartphones and smartwatches, for healthcare purposes has become a popular research topic. This study focuses on applying the concept of Internet of Healthcare Things (IoHT) to handle sensory data fusion for human activities and gestures. The developed human activity recognition (HAR) model shows superior performance compared to other models in the literature for the same dataset, with an average accuracy of 98.7%.

HEALTHCARE (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Triple Cross-Domain Attention on Human Activity Recognition Using Wearable Sensors

Yin Tang et al.

Summary: Efficiently identifying activities of daily living (ADL) is crucial for improving sports tracking and healthcare applications. Existing attention mechanisms in sensor-based human activity recognition (HAR) have achieved remarkable performance, but they overlook the cross-interaction between different dimensions. This paper proposes a triplet cross-dimension attention method that captures the interaction between sensor dimension, temporal dimension, and channel dimension, leading to improved classification performance.

IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

A survey on video-based Human Action Recognition: recent updates, datasets, challenges, and applications

Preksha Pareek et al.

Summary: This paper discusses various machine learning and deep learning techniques used for Human Action Recognition (HAR) from 2011 to 2019, investigates the characteristics of public datasets, and introduces various action recognition techniques and their applications.

ARTIFICIAL INTELLIGENCE REVIEW (2021)

添加到收藏夹

Article Engineering, Electrical & Electronic

CNN-Based Multistage Gated Average Fusion (MGAF) for Human Action Recognition Using Depth and Inertial Sensors

Zeeshan Ahmad et al.

Summary: In this paper, a novel Multistage Gated Average Fusion (MGAF) network is proposed to extract and fuse features from all layers of Convolutional Neural Network (CNN) using Gated Average Fusion (GAF) network, improving Human Action Recognition (HAR) using depth and inertial sensors. Experimental results show that the proposed MGAF outperforms previous fusion methods in terms of recognition accuracy while being more computationally efficient.

IEEE SENSORS JOURNAL (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Deep High-Resolution Representation Learning for Visual Recognition

Jingdong Wang et al.

Summary: The High-Resolution Network (HRNet) maintains high-resolution representations and exchanges information across resolutions, resulting in superior performance in various applications such as human pose estimation, semantic segmentation, and object detection.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Recent Advances in Open Set Recognition: A Survey

Chuanxing Geng et al.

Summary: This paper provides a comprehensive survey of existing open set recognition techniques, covering various aspects such as related definitions, models representations, datasets, evaluation criteria, and algorithm comparisons. It also briefly analyzes the relationships between OSR and its related tasks, highlights the limitations of existing approaches, and points out some promising subsequent research directions in this field.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2021)

添加到收藏夹

Article Chemistry, Analytical

Out-of-Distribution Detection of Human Activity Recognition with Smartwatch Inertial Sensors

Philip Boyer et al.

Summary: Out-of-distribution (OOD) data, representing activity classes not included in the training data of ML algorithms, pose a challenge for accurate classification. In our study, traditional algorithms outperformed deep learning approaches in detecting OOD in HAR time series datasets, highlighting the importance of leveraging engineered statistical features for OOD detection.

SENSORS (2021)

添加到收藏夹

Article Computer Science, Information Systems

ST-DeepHAR: Deep Learning Model for Human Activity Recognition in IoHT Applications

Mohamed Abdel-Basset et al.

Summary: The study introduces a supervised dual-channel model that combines LSTM and attention mechanism for temporal fusion, and introduces an adaptive channel-squeezing operation to optimize the performance of HAR.

IEEE INTERNET OF THINGS JOURNAL (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Sequential Weakly Labeled Multiactivity Localization and Recognition on Wearable Sensors Using Recurrent Attention Networks

Kun Wang et al.

Summary: The article introduces a recurrent attention network for handling sequential weakly labeled multiactivity recognition and location tasks, effectively inferring multiple activity types and determining specific locations of each target activity, as well as reducing the burden of manual labeling.

IEEE TRANSACTIONS ON HUMAN-MACHINE SYSTEMS (2021)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Hierarchical Self Attention Based Autoencoder for Open-Set Human Activity Recognition

M. Tanjid Hasan Tonmoy et al.

Summary: Wearable sensor technology presents challenges in human activity recognition, particularly in understanding spatial and temporal dependencies. Existing closed-set recognition models may struggle to predict unseen activities which can occur due to sensor malfunctions or subject disabilities. By adopting an open-set recognition approach, a hierarchical self-attention model is proposed to improve performance and detect unknown activities in activity recognition. The model also generates explainable attention maps for feature selection and proves to be robust in handling noise and variability in sensor signals.

ADVANCES IN KNOWLEDGE DISCOVERY AND DATA MINING, PAKDD 2021, PT III (2021)

添加到收藏夹

Article Engineering, Electrical & Electronic

Real-Time Human Activity Recognition System Based on Capsule and LoRa

Leixin Shi et al.

Summary: This paper proposes a real-time human activity recognition system based on capsule and LoRa, addressing deficiencies in HAR systems. Experimental results show that the proposed framework outperforms CNN and RNN, enabling real-time HAR based on intelligent sensor devices in specific scenarios.

IEEE SENSORS JOURNAL (2021)

添加到收藏夹

Review Computer Science, Artificial Intelligence

Non-intrusive human activity recognition and abnormal behavior detection on elderly people: a review

Athanasios Lentzas et al.

ARTIFICIAL INTELLIGENCE REVIEW (2020)

添加到收藏夹

Article Computer Science, Artificial Intelligence

A body sensor data fusion and deep recurrent neural network-based behavior recognition approach for robust healthcare

Md. Zia Uddin et al.

INFORMATION FUSION (2020)

添加到收藏夹

Article Computer Science, Information Systems

A Novel IoT-Perceptive Human Activity Recognition (HAR) Approach Using Multihead Convolutional Attention

Haoxi Zhang et al.

IEEE INTERNET OF THINGS JOURNAL (2020)

添加到收藏夹

Article Engineering, Electrical & Electronic

The Layer-Wise Training Convolutional Neural Networks Using Local Loss for Sensor-Based Human Activity Recognition

Qi Teng et al.

IEEE SENSORS JOURNAL (2020)

添加到收藏夹

Article Engineering, Multidisciplinary

A Novel Multichannel Dilated Convolution Neural Network for Human Activity Recognition

Yingjie Lin et al.

MATHEMATICAL PROBLEMS IN ENGINEERING (2020)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Learning a Neural-network-based Representation for Open Set Recognition

Mehadi Hassen et al.

PROCEEDINGS OF THE 2020 SIAM INTERNATIONAL CONFERENCE ON DATA MINING (SDM) (2020)

添加到收藏夹

Article Computer Science, Information Systems

Human Activity Recognition Based on Gramian Angular Field and Deep Convolutional Neural Network

Hongji Xu et al.

IEEE ACCESS (2020)

添加到收藏夹

Article Computer Science, Information Systems

SensCapsNet: Deep Neural Network for Non-Obtrusive Sensing Based Human Activity Recognition

Cuong Pham et al.

IEEE ACCESS (2020)

添加到收藏夹

Article Computer Science, Information Systems

LSTM-CNN Architecture for Human Activity Recognition

Kun Xia et al.

IEEE ACCESS (2020)

添加到收藏夹

Article Computer Science, Information Systems

Learning-Aided User Identification Using Smartphone Sensors for Smart Homes

Zhen Qin et al.

IEEE INTERNET OF THINGS JOURNAL (2019)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Open-set human activity recognition based on micro-Doppler signatures

Yang Yang et al.

PATTERN RECOGNITION (2019)

添加到收藏夹

Article Computer Science, Artificial Intelligence

The joint use of sequence features combination and modified weighted SVM for improving daily activity recognition

Bilal M'hamed Abidine et al.

PATTERN ANALYSIS AND APPLICATIONS (2018)

添加到收藏夹

Proceedings Paper Computer Science, Hardware & Architecture

On Attention Models for Human Activity Recognition

Vishvak S. Murahari et al.

ISWC'18: PROCEEDINGS OF THE 2018 ACM INTERNATIONAL SYMPOSIUM ON WEARABLE COMPUTERS (2018)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Multi-sensor fusion in body sensor networks: State-of-the-art and research challenges

Raffaele Gravina et al.

INFORMATION FUSION (2017)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Weightless neural networks for open set recognition

Douglas O. Cardoso et al.

MACHINE LEARNING (2017)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Densely Connected Convolutional Networks

Gao Huang et al.

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) (2017)

添加到收藏夹

Article Engineering, Electrical & Electronic

Decision-tree-based human activity classification algorithm using single-channel foot-mounted gyroscope

M. W. McCarthy et al.

ELECTRONICS LETTERS (2015)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images

Anh Nguyen et al.

2015 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2015)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Toward Open Set Recognition

Walter J. Scheirer et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2013)

添加到收藏夹

Article Engineering, Biomedical

A Comparison of Feature Extraction Methods for the Classification of Dynamic Activities From Accelerometer Data

Stephen J. Preece et al.

IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING (2009)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Sensor-based abnormal human-activity detection

Jie Yin et al.

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING (2008)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.