检索结果-内蒙古大学图书馆

2022 Research, Invention, and Innovation Congress: Innovative Electricals and Electronics, RI2C 2022

作者： Mekruksavanich, Sakorn Jantawong, Ponnipa Hnoohom, Narit Jitpattanakul, Anuchit University of Phayao School of Information and Communication Technology Department of Computer Engineering Phayao Thailand Mahidol University Image Information and Intelligence Laboratory Department of Computer Engineering Faculty of Engineering Nakhon Pathom Thailand King Mongkut's University of Technology North Bangkok Intelligent and Nonlinear Dynamic Innovations Research Center Department of Mathematics Faculty of Applied Science Bangkok Thailand

ISBN: (数字)9781665473248

ISBN: (纸本)9781665473248

Smartwatches are becoming more popular for recognizing and monitoring human actions in everyday life. These wearable devices are equipped with various IMU sensors for ubiquitous data processing and recording of human physical activity data. Sensor-based human activity recognition (HAR) has risen to the top of the list of the most active research topic due to its widely real-life applications in various practical domains, such as healthcare monitoring, sports and exercise tracking, and misbehavior prevention. Many machine learning and deep learning approaches have been recently proposed to solve the problem of human activity recognition, focusing on activities of daily living. However, an exciting and challenging HAR topic deals with more complex human activities such as eating-related activities. This paper proposes a sensor-based HAR framework using data from eating-related activities recorded by a smartwatch sensor. In this framework, five d eep learning networks (CNN, LSTM, BiLSTM, Stacked LSTM, CNN-LSTM, and LSTM-CNN) are evaluated for their recognition of eating-related activities. To ensure the model's dependability, data from eating-related activities on the standard publicly available dataset WISDM-HARB are utilized to evaluate the proposed framework using state-of-the-art metrics: accuracy and confusion matrices. Experiment findings demonstrate that the S tacked LSTM model outperforms other deep learning models, achieving an accuracy of 97.37%. © 2022 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Hyperparameter Tuning in Convolutional Neural Network for Face Touching Activity Recognition using Accelerometer Data

Hyperparameter Tuning in Convolutional Neural Network for Fa...

引用

2022 Research, Invention, and Innovation Congress: Innovative Electricals and Electronics, RI2C 2022

ISBN: (数字)9781665473248

ISBN: (纸本)9781665473248

People have been encouraged to wear masks and avoid touching their faces in public as part of the new measures to prevent the spread of coronavirus 2019 (COVID-19). During the COVID-19 epidemic, few research have examined the effect of everyday living on the frequency of facial touch activity. To develop a face touching avoidance system, deep learning algorithms have been proposed and have demonstrated their amazing performance. However, an important drawback of deep learning is its extensive dependence on hyperparameters. The results of deep learning algorithms may vary depending on hyperparameters, such as the size of the filters, the number of filters, the batch size, the number of epochs, and the training optimization technique used. In this paper, we present an effective approach for hyperparameter tuning of convolutional neural networks (CNNs) for efficiently recognized face touching activities based on accelerometer data. Two hyperparameter tuning methods (Grid search and Bayesian optimization) were evaluated in order to construct the CNN with high performance. The experiment results show that Bayesian optimization can provide suitable hyperparameters for CNNs for face touching recognition with the highest accuracy of 96.61%. © 2022 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Approaches for Unobtrusive Human Activity Recognition using Insole-based and Smartwatch Sensors 3

Deep Learning Approaches for Unobtrusive Human Activity Reco...

引用

3rd International Conference on Big Data Analytics and Practices, IBDAP 2022

作者： Hnoohom, Narit Maitrichit, Nagorn Mekruksavanich, Sakorn Jitpattanakul, Anuchit Mahidol University Image Information and Intelligence Laboratory Department of Computer Engineering Faculty of Engineering Nakorn Pathom Thailand University of Phayao School of Information and Communication Technology Department of Computer Engineering Phayao Thailand King Mongkut's University of Technology North Bangkok Intelligent and Nonlinear Dynamic Innovations Research Center Department of Mathematics Faculty of Applied Science Bangkok Thailand

ISBN: (数字)9781665469388

ISBN: (纸本)9781665469388

In this digital age, human activity recognition (HAR) has been playing an increasingly important role in almost all aspects of life. Healthcare systems for monitoring the activities of daily living (ADL), security environments for automatically detecting abnormal activity and notifying the pertinent authorities, and increasing human contact with computers are all examples of HAR applications. The data collecting tools used in HAR research can also be categorized (sensors or cameras). In sensor-based HAR, various wearable sensors have been investigated for their usefulness in effectively detecting both simple and complex human activities. In this work, we studied HAR using signal data acquired from insole-based and smartwatch sensors. To achieve our research goal, we proposed a ResNeXt inspired deep learning (DL) network called HARNeXt. The proposed model was evaluated on a public data set named 19NonSense data that collected activity signal data recorded from insole-based and smartwatch sensors. In addition, we compared the proposed model to baseline DL models. The results showed that the HARNeXt outperformed other DL models and achieved the highest F1-score of 97.03%. © 2022 IEEE.

关键词： Wearable sensors

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Human Activity Recognition Based on Smartwatch Sensors Using Branch Convolutional Neural Networks 1

引用

15th Multi-disciplinary International Conference on Artificial Intelligence, MIWAI 2022

作者： Hnoohom, Narit Maitrichit, Nagorn Mekruksavanich, Sakorn Jitpattanakul, Anuchit Image Information and Intelligence Laboratory Department of Computer Engineering Faculty of Engineering Mahidol University Nakorn Pathom Thailand Department of Computer Engineering School of Information and Communication Technology University of Phayao Phayao Thailand Intelligent and Nonlinear Dynamic Innovations Research Center Department of Mathematics Faculty of Applied Science King Mongkut’s University of Technology North Bangkok Bangkok Thailand

ISBN: (数字)9783031209925

ISBN: (纸本)9783031209918

Human activity recognition (HAR) has become a popular research topic in artificial intelligence thanks to the development of smart wearable devices. The main goal of human activity recognition is to efficiently recognize human behavior based on available data sources such as videos and images, including sensory data from wearable devices. Recently, HAR research has achieved promising results using learning-based approaches, especially deep learning methods. However, the need for high performance is still an open problem for researchers proposing new methods. In this work, we investigated the improvement of HAR by hierarchical classification based on smartwatch sensors using deep learning (DL) methods. To achieve the research goal, we introduced branch convolutional neural networks (B-CNNs) to accurately recognize human activities hierarchically and compared them with baseline models. To evaluate the deep learning models, we used a complex HAR benchmark dataset called WISDM-HARB dataset that collects smartwatch sensor data from 18 physical activities. The experimental results showed that the B-CNNs outperformed the baseline convolutional neural network (CNN) models when the hierarchical connection between classes was not considered. Moreover, the results confirmed that branch CNNs with class hierarchy improved the recognition performance with the highest accuracy of 95.84%. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A Deep Residual-based Model on Multi-Branch Aggregation for Stress and Emotion Recognition through Biosignals 19

A Deep Residual-based Model on Multi-Branch Aggregation for ...

引用

19th International Conference on Electrical Engineering/Electronics, computer, Telecommunications and information Technology, ECTI-CON 2022

作者： Mekruksavanich, Sakorn Hnoohom, Narit Jitpattanakul, Anuchit University of Phayao School of Information and Communication Technology Department of Computer Engineering Phayao Thailand Mahidol University Image Information and Intelligence Laboratory Department of Computer Engineering Faculty of Engineering Nakhon Pathom Thailand King Mongkut's University of Technology North Bangkok Intelligent and Nonlinear Dynamic Innovations Research Center Department of Mathematics Faculty of Applied Science Bangkok Thailand

ISBN: (纸本)9781665485845

Stress and emotion recognition (SER) is a rapidly growing field of study that has applications in various areas, including psychological wellbeing, rehabilitative services, athletic training, and human-computer interaction. Biological information such as the electrocardiogram (ECG), electromyography (EMG), and electrodermal activity (EDA) has been frequently utilized for the SER for learning-based approaches. This study introduces a convolutional neural network motivated by ResNeXt to facilitate multimodal awareness. The proposed model, named StressNeXt, can extract high-level insights from raw bio-signal signals and classify emotional expressions effectively. We undertake a series of investigations using a publicly released standard dataset (WESAD) to determine the optimal implementation of the proposed solution for recognizing stress and emotion. After incorporating preliminary fusion events, we examined deep learning models using 5-fold cross-validation. Our study demonstrates that the suggested technique can comprehend robust multimodal representations with an accuracy of 87.73% utilizing EDA. Additionally, the identification was designed to provide better to 99.92% by fusing with accelerometer sensor data. © 2022 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Towards a Smart Learning Environment : A Model for Smart Education using IoT and AI

Towards a Smart Learning Environment : A Model for Smart Edu...

引用

International Symposium on Advanced Electrical and Communication Technologies (ISAECT)

作者： Amine Dehbi Abdellah Bakhouyi Rachid Dehbi Mohamed Talea Laboratory of Information Processing (LTI) Faculty of Sciences Ben M’Sick Hassan II University Casablanca Morocco Laboratory of Computer Science (LIS) Faculty of Sciences Aïn Chock Hassan II University Casablanca Morocco

ISBN: (数字)9798331529987

ISBN: (纸本)9798331529994

Smart education has become a hallmark of information and communication technology in education (ICTE). The continuous introduction of new technologies into learning environments aims to enable learners to develop and enhance their skills, leading to improved learning outcomes. Technologies such as the Internet of Things (IoT), Generative AI, and mobile technology are among the latest to be integrated into educational infrastructures and systems. These smart technologies offer personalized content creation, automate administrative tasks, and enhance student engagement through adaptive interactions. However, despite the promising benefits, challenges such as security and privacy concerns, the need for robust infrastructure, and ongoing technical support must be addressed. This paper proposes a comprehensive model for implementing smart education technologies, addressing these challenges. The proposed model serves as a blueprint for educational institutions aiming to leverage modern technologies to create smarter, more efficient learning environments.

关键词： Training Adaptation models Technological innovation Privacy Generative AI Data security Educational technology information and communication technology Internet of Things Stakeholders

来源：评论

学校读者我要写书评

暂无评论

Refined LSTM Network for Sensor-based Human Activity Recognition in Real World Scenario 13

Refined LSTM Network for Sensor-based Human Activity Recogni...

引用

13th IEEE International Conference on Software Engineering and Service science, ICSESS 2022

作者： Mekruksavanich, Sakorn Jantawong, Ponnipa Hnoohom, Narit Jitpattanakul, Anuchit University of Phayao School of Information and Communication Technology Department of Computer Engineering Phayao Thailand Faculty of Engineering Mahidol University Image Information and Intelligence Laboratory Department of Computer Engineering Nakhon Pathom Thailand King Mongkut's University of Technology North Bangkok Intelligent and Nonlinear Dynamic Innovations Research Center Department of Mathematics Faculty of Applied Science Bangkok Thailand

ISBN: (数字)9781665410328

ISBN: (纸本)9781665410311

Sensor-based identification of human actions is an essential field of study in ubiquitous computing. This aims to facilitate the assessment or understanding of current occurrences and their context based on sensor signals. Activity recognition is employed in surveillance systems, patient health monitoring, and many other systems involving the interaction between human and intelligent wearable devices, including smartphones and smartwatches. The primary objective of this study work is to identify human behavior in the actual world. We proposed an improved long short-term memory network called RLSTM that uses a squeeze-and-excitation module to efficiently identify human actions and enhance action identification systems' interpretation. A publicly available real-world dataset known as REALWORLD16 was used to train and validate the model five times to analyze the proposed network. The proposed RLSTM achieved the highest accuracy of 98.04% and F1-score of 97.76%, as determined by several investigations. © 2022 IEEE.

关键词： Wearable sensors

来源：评论

学校读者我要写书评

暂无评论

Moment Centralization based Gradient Descent Optimizers for Convolutional Neural Networks

arXiv

引用

arXiv 2022年

作者： Sadu, Sumanth Dubey, Shiv Ram Sreeja, S.R. Computer Vision Group Department of Computer Science and Engineering Indian Institute of Information Technology Andhra Pradesh Sri City India Computer Vision and Biometrics Laboratory Indian Institute of Information Technology Uttar Pradesh Allahabad India Department of Computer Science and Engineering Indian Institute of Information Technology Andhra Pradesh Sri City India

Convolutional neural networks (CNNs) have shown very appealing performance for many computer vision applications. The training of CNNs is generally performed using stochastic gradient descent (SGD) based optimization techniques. The adaptive momentum-based SGD optimizers are the recent trends. However, the existing optimizers are not able to maintain a zero mean in the first-order moment and struggle with optimization. In this paper, we propose a moment centralization-based SGD optimizer for CNNs. Specifically, we impose the zero mean constraints on the first-order moment explicitly. The proposed moment centralization is generic in nature and can be integrated with any of the existing adaptive momentum-based optimizers. The proposed idea is tested with three state-of-the-art optimization techniques, including Adam, Radam, and Adabelief on benchmark CIFAR10, CIFAR100, and TinyImageNet datasets for image classification. The performance of the existing optimizers is generally improved when integrated with the proposed moment centralization. Further, The results of the proposed moment centralization are also better than the existing gradient centralization. The analytical analysis using the toy example shows that the proposed method leads to a shorter and smoother optimization trajectory. The source code is made publicly available at https://***/sumanthsadhu/MC-optimizer. Copyright © 2022, The Authors. All rights reserved.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Efficient Visual Recognition:A Survey on Recent Advances and Brain-inspired Methodologies

引用

Machine Intelligence Research 2022年第5期19卷 366-411页

作者： Yang Wu Ding-Heng Wang Xiao-Tong Lu Fan Yang Man Yao Wei-Sheng Dong Jian-Bo Shi Guo-Qi Li Applied Research Center Laboratory Tencent Platform and Content Group Shenzhen 518057China School of Automation Science and Engineering Faculty of Electronic and Information EngineeringXi′an Jiaotong UniversityXian710049China School of Artificial Intelligence Xidian UniversityXi'an 710071China Division of Information Science Nara Institute of Science and TechnologyNara 6300192Japan Peng Cheng Laboratory Shenzhen 518000China Department of Computer and Information Science University of PennsylvaniaPhiladelphia PA19104-6389USA Institute of Automation Chinese Academy of SciencesBeijing 100190China University of Chinese Academy of Sciences Beijing 100190China

Visual recognition is currently one of the most important and active research areas in computer vision,pattern recognition,and even the general field of artificial *** has great fundamental importance and strong industrial needs,particularly the modern deep neural networks(DNNs)and some brain-inspired methodologies,have largely boosted the recognition performance on many concrete tasks,with the help of large amounts of training data and new powerful computation *** recognition accuracy is usually the first concern for new progresses,efficiency is actually rather important and sometimes critical for both academic research and industrial ***,insightful views on the opportunities and challenges of efficiency are also highly required for the entire *** general surveys on the efficiency issue have been done from various perspectives,as far as we are aware,scarcely any of them focused on visual recognition systematically,and thus it is unclear which progresses are applicable to it and what else should be *** this survey,we present the review of recent advances with our suggestions on the new possible directions towards improving the efficiency of DNN-related and brain-inspired visual recognition approaches,including efficient network compression and dynamic brain-inspired *** investigate not only from the model but also from the data point of view(which is not the case in existing surveys)and focus on four typical data types(images,video,points,and events).This survey attempts to provide a systematic summary via a comprehensive survey that can serve as a valuable reference and inspire both researchers and practitioners working on visual recognition problems.

关键词： Visual recognition deep neural networks(DNNS) brain-inspired methodologies network compression dynamic inference survey

来源：评论

学校读者我要写书评

暂无评论

Answering Diverse Questions via Text Attached with Key Audio-Visual Clues

arXiv

引用

arXiv 2024年

作者： Ye, Qilang Yu, Zitong Liu, Xin The School of Computing and Information Technology Great Bay University Dongguan523000 China The School of Computer Science and Engineering Chongqing University of Technology Chongqing401300 China The Computer Vision and Pattern Recognition Laboratory Lappeenranta-Lahti University of Technology LUT Lappeenranta53850 Finland

Audio-visual question answering (AVQA) requires reference to video content and auditory information, followed by correlating the question to predict the most precise answer. Although mining deeper layers of audio-visual information to interact with questions facilitates the multimodal fusion process, the redundancy of audio-visual parameters tends to reduce the generalization of the inference engine to multiple question-answer pairs in a single video. Indeed, the natural heterogeneous relationship between audiovisuals and text makes the perfect fusion challenging, to prevent high-level audio-visual semantics from weakening the network’s adaptability to diverse question types, we propose a framework for performing mutual correlation distillation (MCD) to aid question inference. MCD is divided into three main steps: 1) firstly, the residual structure is utilized to enhance the audio-visual soft associations based on self-attention, then key local audio-visual features relevant to the question context are captured hierarchically by shared aggregators and coupled in the form of clues with specific question vectors. 2) Secondly, knowledge distillation is enforced to align audiovisual-text pairs in a shared latent space to narrow the cross-modal semantic gap. 3) And finally, the audio-visual dependencies are decoupled by discarding the decision-level integrations. We evaluate the proposed method on two publicly available datasets containing multiple question-and-answer pairs, i.e., Music-AVQA and AVQA. Experiments show that our method outperforms other state-of-the-art methods, and one interesting finding behind is that removing deep audio-visual features during inference can effectively mitigate overfitting. The source code is released at http://***/rikeilong/MCD-forAVQA. © 2024, CC BY.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：