☆ 4.3 Article

Resource-Efficient Continual Learning for Sensor-Based Human Activity Recognition

ACM TRANSACTIONS ON EMBEDDED COMPUTING SYSTEMS (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 Engineering, Electrical & Electronic

Human Activity Recognition Machine With an Anchor-Based Loss Function

Lei Jin et al.

Summary: Recently, Human Activity Recognition (HAR) based on sensors using deep learning networks has gained popularity due to its wide application. However, the inter-personal variability in human activity data poses challenges to both closed-set classification and open-set problem. In this study, we propose a framework that incorporates a loss function of Euclidean distance and a high-dimensional embedding layer to extract discriminative features. We also define two types of open-set problems and propose corresponding solutions. Experimental results demonstrate that our method significantly improves the performance of the models.

IEEE SENSORS JOURNAL (2022)

添加到收藏夹

Article Automation & Control Systems

A Visual-Based Gesture Prediction Framework Applied in Social Robots

Bixiao Wu et al.

Summary: This paper proposes a gesture prediction system that uses hand joint coordinate features collected by the Leap Motion to predict dynamic hand gestures. The model is applied to the NAO robot to verify the effectiveness of the proposed method.

IEEE-CAA JOURNAL OF AUTOMATICA SINICA (2022)

添加到收藏夹

Article Computer Science, Information Systems

MDLdroidLite: A Release-and-Inhibit Control Approach to Resource-Efficient Deep Neural Networks on Mobile Devices

Yu Zhang et al.

Summary: Mobile deep learning (MDL) is a privacy-preserving learning paradigm with unique features like continual learning and low-latency inference. This paper introduces MDLdroidLite, an on-device deep learning framework that optimizes model structures and parameter adaptation mechanisms to achieve resource efficiency and fast training.

IEEE TRANSACTIONS ON MOBILE COMPUTING (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

A Continual Learning Survey: Defying Forgetting in Classification Tasks

Matthias De Lange et al.

Summary: This article introduces the application of artificial neural networks in continual learning, focusing on task incremental classification. It proposes a new framework for continually evaluating the stability-plasticity trade-off of the network and performs experimental comparisons of 11 state-of-the-art continual learning methods, evaluating their strengths and weaknesses by considering different benchmark datasets.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2022)

添加到收藏夹

Article Engineering, Electrical & Electronic

A Novel Attention-Based Convolution Neural Network for Human Activity Recognition

Ge Zheng

Summary: In this paper, a novel deep learning model named LGSTNet is proposed for Human Activity Recognition (HAR) by utilizing Convolution Neural Networks (CNN) and the attention mechanism to extract local and global spatial-temporal features from sensory data. LGSTNet outperforms eight existing well-known models in terms of recognition accuracy on the WISDM and UCI-HAR datasets, achieving high performance and robustness.

IEEE SENSORS JOURNAL (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, Information Systems

Continual learning in sensor-based human activity recognition: An empirical benchmark analysis

Saurav Jha et al.

Summary: This paper investigates the application of continual learning techniques in the HAR field and proposes an evaluation framework. Through empirical analysis, it reveals the applicability of these techniques, while also pointing out future research directions for HAR systems.

INFORMATION SCIENCES (2021)

添加到收藏夹

Article Computer Science, Theory & Methods

Deep Learning for Sensor-based Human Activity Recognition: Overview, Challenges, and Opportunities

Kaixuan Chen et al.

Summary: This study explores the impact of sensor devices and the Internet of Things on sensor-based activity recognition, discusses the role of deep learning methods in addressing recognition challenges, and provides an overview of current research progress and future directions.

ACM COMPUTING SURVEYS (2021)

添加到收藏夹

Article Computer Science, Theory & Methods

A Survey on Deep Learning for Human Activity Recognition

Fuqiang Gu et al.

Summary: This study provides a comprehensive survey on recent advances and challenges in human activity recognition (HAR) with deep learning, highlighting the lack of in-depth research on deep learning methods in HAR.

ACM COMPUTING SURVEYS (2021)

添加到收藏夹

Article Computer Science, Information Systems

A Survey of On-Device Machine Learning: An Algorithms and Learning Theory Perspective

Sauptik Dhar et al.

Summary: The predominant paradigm for using machine learning models on a device is to train a model in the cloud and perform inference using the trained model on the device. However, with increased interest in on-device learning, there is a need for a comprehensive survey from a device-agnostic perspective to understand the state of the art and future research directions. This survey reformulates the problem of on-device learning as resource constrained learning, allowing for a fair comparison of tools, techniques, and algorithms from various research areas.

ACM TRANSACTIONS ON INTERNET OF THINGS (2021)

添加到收藏夹

Article Computer Science, Information Systems

Continual Activity Recognition with Generative Adversarial Networks

Juan Ye et al.

Summary: Continual learning is a challenging research topic in human activity recognition, and extending activity models to adapt to changing activity routines is crucial. The HAR-GAN system, utilizing Generative Adversarial Networks (GAN), effectively addresses this challenge and demonstrates satisfactory empirical results on four datasets.

ACM TRANSACTIONS ON INTERNET OF THINGS (2021)

添加到收藏夹

Article Engineering, Civil

Enhancing Data-Driven Algorithms for Human Pose Estimation and Action Recognition Through Simulation

Dennis Ludl et al.

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2020)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Evolving models for incrementally learning emerging activities

Juan Ye et al.

JOURNAL OF AMBIENT INTELLIGENCE AND SMART ENVIRONMENTS (2020)

添加到收藏夹

Article Computer Science, Information Systems

Improving Cross-Subject Activity Recognition via Adversarial Learning

Clayton Frederick Souza Leite et al.

IEEE ACCESS (2020)

添加到收藏夹

Proceedings Paper Computer Science, Information Systems

Improving Resource Efficiency of Deep Activity Recognition via Redundancy Reduction

Clayton Frederick Souza Leite et al.

PROCEEDINGS OF THE 21ST INTERNATIONAL WORKSHOP ON MOBILE COMPUTING SYSTEMS AND APPLICATIONS (HOTMOBILE'20) (2020)

添加到收藏夹

Article Computer Science, Information Systems

Sensor-based Detection and Classification of Soccer Goalkeeper Training Exercises

Juan Haladjian et al.

ACM TRANSACTIONS ON INTERNET OF THINGS (2020)

添加到收藏夹

Article Gerontology

Advanced Sensing and Human Activity Recognition in Early Intervention and Rehabilitation of Elderly People

Lisa Schrader et al.

JOURNAL OF POPULATION AGEING (2020)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Deep learning for sensor-based activity recognition: A survey

Jindong Wang et al.

PATTERN RECOGNITION LETTERS (2019)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Dendritic Neuron Model With Effective Learning Algorithms for Classification, Approximation, and Prediction

Shangce Gao et al.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2019)

添加到收藏夹

Article Computer Science, Hardware & Architecture

A Smartphone-Enabled Fall Detection Framework for Elderly People in Connected Home Healthcare

Mohammad Mehedi Hassan et al.

IEEE NETWORK (2019)

添加到收藏夹

Article Chemistry, Analytical

A Novel Human Activity Recognition and Prediction in Smart Home Based on Interaction

Yegang Du et al.

SENSORS (2019)

添加到收藏夹

Article Computer Science, Information Systems

Human Activity Recognition Based on Motion Sensor Using U-Net

Yong Zhang et al.

IEEE ACCESS (2019)

添加到收藏夹

Article Computer Science, Information Systems

InnoHAR: A Deep Neural Network for Complex Human Activity Recognition

Cheng Xu et al.

IEEE ACCESS (2019)

添加到收藏夹

Proceedings Paper Computer Science, Hardware & Architecture

Understanding and Improving Recurrent Networks for Human Activity Recognition by Continuous Attention

Ming Zeng et al.

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

添加到收藏夹

Article Chemistry, Analytical

Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition

Francisco Javier Ordonez et al.

SENSORS (2016)

添加到收藏夹

Article Chemistry, Analytical

mDurance: A Novel Mobile Health System to Support Trunk Endurance Assessment

Oresti Banos et al.

SENSORS (2015)

添加到收藏夹

Article Computer Science, Artificial Intelligence

The Opportunity challenge: A benchmark database for on-body sensor-based activity recognition

Ricardo Chavarriaga et al.

PATTERN RECOGNITION LETTERS (2013)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.