☆ 4.7 Article

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

BIOSENSORS-BASEL (2022)

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, Interdisciplinary Applications

Progress of Human Action Recognition Research in the Last Ten Years: A Comprehensive Survey

Pawan Kumar Singh et al.

Summary: This survey provides an overview of the various approaches proposed for Human Action Recognition (HAR) in the past decade, focusing mainly on the development of methods for unimodal HAR using concepts of machine learning and deep learning models. It also includes discussions on different feature extractors, majorly used video and still-image datasets, and offers insights into future work scope.

ARCHIVES OF COMPUTATIONAL METHODS IN ENGINEERING (2022)

添加到收藏夹

Article Engineering, Electrical & Electronic

Real-Time Human Activity Recognition Using Conditionally Parametrized Convolutions on Mobile and Wearable Devices

Xin Cheng et al.

Summary: Deep learning has become an important research trend in human activity recognition (HAR), but traditional deep learning methods are computationally expensive for real-time recognition on mobile and wearable devices. This paper proposes a computation efficient CNN using conditionally parametrized convolution for real-time HAR on such devices, achieving state-of-the-art accuracy without compromising computation cost.

IEEE SENSORS JOURNAL (2022)

添加到收藏夹

Article Engineering, Multidisciplinary

COFE-Net: An ensemble strategy for Computer-Aided Detection for COVID-19

Avinandan Banerjee et al.

Summary: The paper introduces a robust deep learning ensemble framework called COFE-Net for COVID-19 screening from chest X-rays and CT scans in Computer-Aided Detection (CADe). By leveraging fuzzy logic principles and Transfer Learning, the proposed method effectively combines decision scores from three state-of-the-art CNNs, showing superiority over empirical ensemble methods. The dynamic refactoring of classifier ensemble weights based on confidence scores for coalition of inputs is the chief advantage of the proposed biomedical measurement strategy.

MEASUREMENT (2022)

添加到收藏夹

Article Chemistry, Analytical

Human Activity Recognition Based on Residual Network and BiLSTM

Yong Li et al.

Summary: This paper proposes a deep learning model based on residual block and bi-directional LSTM for extracting spatial and temporal features of human activity data and performing human activity recognition. Experimental results show that the proposed model achieves high accuracy and outperforms other models.

SENSORS (2022)

添加到收藏夹

Article Computer Science, Information Systems

AHAR: Adaptive CNN for Energy-Efficient Human Activity Recognition in Low-Power Edge Devices

Nafiul Rashid et al.

Summary: This research introduces an adaptive convolutional neural network for energy-efficient human activity recognition on low-power edge devices. The proposed method outperforms traditional approaches in terms of energy efficiency while maintaining comparable performance.

IEEE INTERNET OF THINGS JOURNAL (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Deep Temporal Conv-LSTM for Activity Recognition

Mohd Halim Mohd Noor et al.

Summary: The study introduces a novel deep temporal Conv-LSTM architecture to enhance activity recognition by considering both the temporal characteristics of sensor data and the relationship of sliding windows. Experimental evaluation demonstrates the architecture's capability in accurately modeling the temporal relationship of activity windows and the impact of window size selection on recognition accuracy. The proposed deep temporal Conv-LSTM architecture achieves a high accuracy score of 0.916, outperforming existing state-of-the-art methods.

NEURAL PROCESSING LETTERS (2022)

添加到收藏夹

Article Computer Science, Software Engineering

A multibranch CNN-BiLSTM model for human activity recognition using wearable sensor data

Sravan Kumar Challa et al.

Summary: This paper proposes a hybrid CNN-BiLSTM network for HAR, which automatically extracts features from raw sensor data and allows the model to learn local features and long-term dependencies. Different filter sizes capture various temporal local dependencies to improve the feature extraction process. Experiment results show that the proposed model outperforms other methods with high accuracies on benchmark datasets.

VISUAL COMPUTER (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

CGA: a new feature selection model for visual human action recognition

Ritam Guha et al.

Summary: The paper proposes a novel feature selection model named CGA, which utilizes cooperative genetic algorithm to extract important features from a large feature set, leading to improved classification accuracy and reduced time requirement. Experiments show significant enhancement in overall classification accuracy with only a small portion of the original feature vector considered.

NEURAL COMPUTING & APPLICATIONS (2021)

添加到收藏夹

Article Computer Science, Theory & Methods

Multi-input CNN-GRU based human activity recognition using wearable sensors

Nidhi Dua et al.

Summary: Human Activity Recognition (HAR), an important research area, has seen a surge in interest due to the development of a deep neural network model that automates feature extraction and activity classification, achieving high accuracy without requiring manual feature extraction.

COMPUTING (2021)

添加到收藏夹

Article Computer Science, Information Systems

Transfer learning with fine tuning for human action recognition from still images

Saikat Chakraborty et al.

Summary: This study tackles the challenging task of still image-based human action recognition using transfer learning and data augmentation techniques. The proposed model outperforms benchmark results on datasets known for confusing action classes and occlusions. Class imbalance is deliberately introduced to explore the robustness of the model, showing significant improvements in performance.

MULTIMEDIA TOOLS AND APPLICATIONS (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 Engineering, Electrical & Electronic

MMHAR-EnsemNet: A Multi-Modal Human Activity Recognition Model

Avigyan Das et al.

Summary: This article introduces a new deep learning model named MMHAR-EnsemNet, utilizing four different modalities for sensor-based Human Activity Recognition. The model combines outputs from skeleton data, RGB images, accelerometer and gyroscope data to enhance the performance of HAR.

IEEE SENSORS JOURNAL (2021)

添加到收藏夹

Article Engineering, Electrical & Electronic

A New Framework for Smartphone Sensor-Based Human Activity Recognition Using Graph Neural Network

Riktim Mondal et al.

Summary: Automatic human activity recognition through computing devices is a challenging yet widely applicable research topic. While deep neural network models like CNN do not require additional feature extraction, they demand significant time and resources for training. To address these issues, a fast Graph Neural Network model has been proposed, achieving nearly 100% recognition accuracy.

IEEE SENSORS JOURNAL (2021)

添加到收藏夹

Article Engineering, Electrical & Electronic

Layer-Wise Training Convolutional Neural Networks With Smaller Filters for Human Activity Recognition Using Wearable Sensors

Yin Tang et al.

Summary: The research introduces a lightweight CNN model using Lego filters for HAR tasks, achieving higher accuracy and reducing memory and computation cost. Experimental results show that this Lego CNN model is smaller, faster, and more accurate than traditional CNN. Moreover, the model does not rely on special network structures and has application potential in ubiquitous and wearable computing.

IEEE SENSORS JOURNAL (2021)

添加到收藏夹

Article Engineering, Electrical & Electronic

Human Activity Recognition Based on Wearable Sensor Using Hierarchical Deep LSTM Networks

LuKun Wang et al.

CIRCUITS SYSTEMS AND SIGNAL PROCESSING (2020)

添加到收藏夹

Article Computer Science, Hardware & Architecture

Deep Learning Models for Real-time Human Activity Recognition with Smartphones

Shaohua Wan et al.

MOBILE NETWORKS & APPLICATIONS (2020)

添加到收藏夹

Article Computer Science, Information Systems

Deep-Learning-Enhanced Human Activity Recognition for Internet of Healthcare Things

Xiaokang Zhou et al.

IEEE INTERNET OF THINGS JOURNAL (2020)

添加到收藏夹

Article Computer Science, Information Systems

EnsemConvNet: a deep learning approach for human activity recognition using smartphone sensors for healthcare applications

Debadyuti Mukherjee et al.

MULTIMEDIA TOOLS AND APPLICATIONS (2020)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

A Lightweight Deep Learning Model for Human Activity Recognition on Edge Devices

Preeti Agarwal et al.

INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND DATA SCIENCE (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, Artificial Intelligence

Feature learning for Human Activity Recognition using Convolutional Neural Networks A case study for Inertial Measurement Unit and audio data

Federico Cruciani et al.

CCF TRANSACTIONS ON PERVASIVE COMPUTING AND INTERACTION (2020)

添加到收藏夹

Article Chemistry, Analytical

Coarse-Fine Convolutional Deep-Learning Strategy for Human Activity Recognition

Carlos Aviles-Cruz et al.

SENSORS (2019)

添加到收藏夹

Article Automation & Control Systems

A Novel Semisupervised Deep Learning Method for Human Activity Recognition

Qingchang Zhu et al.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2019)

添加到收藏夹

Article Computer Science, Information Systems

Efficient Human Activity Recognition Solving the Confusing Activities Via Deep Ensemble Learning

Ran Zhu et al.

IEEE ACCESS (2019)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Real-time human activity recognition from accelerometer data using Convolutional Neural Networks

Andrey Ignatov

APPLIED SOFT COMPUTING (2018)

添加到收藏夹

Article Engineering, Electrical & Electronic

Sequential Human Activity Recognition Based on Deep Convolutional Network and Extreme Learning Machine Using Wearable Sensors

Jian Sun et al.

JOURNAL OF SENSORS (2018)

添加到收藏夹

Article Engineering, Multidisciplinary

Deep Residual Bidir-LSTM for Human Activity Recognition Using Wearable Sensors

Yu Zhao et al.

MATHEMATICAL PROBLEMS IN ENGINEERING (2018)

添加到收藏夹

Article Chemistry, Analytical

MBOSS: A Symbolic Representation of Human Activity Recognition Using Mobile Sensors

Kevin G. Montero Quispe et al.

SENSORS (2018)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Human activity recognition with smartphone sensors using deep learning neural networks

Charissa Ann Ronao et al.

EXPERT SYSTEMS WITH APPLICATIONS (2016)

添加到收藏夹

Article Engineering, Multidisciplinary

Significance of non-parametric statistical tests for comparison of classifiers over multiple datasets

Pawan Kumar Singh et al.

INTERNATIONAL JOURNAL OF COMPUTING SCIENCE AND MATHEMATICS (2016)

添加到收藏夹

Proceedings Paper Computer Science, Cybernetics

A Deep Learning Approach to Human Activity Recognition Based on Single Accelerometer

Yuqing Chen et al.

2015 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC 2015): BIG DATA ANALYTICS FOR HUMAN-CENTRIC SYSTEMS (2015)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Statistical validation of multiple classifiers over multiple datasets in the field of pattern recognition

Pawan Kumar Singh et al.

INTERNATIONAL JOURNAL OF APPLIED PATTERN RECOGNITION (2015)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.