检索结果-内蒙古大学图书馆

IEEE international Conference on Orange Technologies (ICOT)

作者： Yang-Yen Ou An-Chao Tsai Pin-Yang Hsu Che-Wen Chen Jhing-Fa Wang Department of Electrical Engineering National Cheng-Kung University Tainan Taiwan International Master Program of Information Technology and Application National Pingtung University Pingtung Taiwan

ISBN: (纸本)9781665454209

In recent years, due to the impact of COVID-19 around the world, there has been a serious shortage of medical resources. In order to supplement the manpower and fear that medical staff's contact with patients will cause a breach in the epidemic, reduce the workload of nurses, and help nurses perform repetitive tasks so that nurses can concentrate more on the patient's condition. Therefore, this paper proposes M-Robot, which is a friendly interface service robot based on the Android system and can be controlled by voice, touch, and remote control in the medical care field. The system is mainly divided into two parts. One is the web server. The web server is divided into two parts: front-end and back-end. The front-end is responsible for friendly user interface management, and the back-end is for accessing the SQLite database, as well as processing speech recognition and semantic understanding in voice services. In the other part, we use TEMI robot to develop and complete the desired service. Its service content includes environment introduction, delivery service, questionnaire survey, broadcast car, scheduling reminder, follow-up record, and patient instruction video. In the voice control mode, the user can say the wake-up word to the robot and say the required service content, and the robot will execute after receiving the message; in the remote control mode, we provide a friendly web interface for remote control. As well as the information needed to manage various services.

关键词： Epidemics Service robots Speech recognition Medical services User interfaces Control systems Web servers

来源：评论

学校读者我要写书评

暂无评论

Tuberculosis Detection Based on Multiple Model Ensemble in Chest X-ray Image

Tuberculosis Detection Based on Multiple Model Ensemble in C...

引用

IEEE international Conference on Orange Technologies (ICOT)

作者： An-Chao Tsai Zhe-Guang Zhou Yang-Yen Ou I Jhing-Fa Wang International Master Program of Information Technology and Application National Pingtung University Pingtung Taiwan Department of Electrical Engineering National Cheng-Kung University Tainan Taiwan

ISBN: (纸本)9781665454209

Tuberculosis is a legal infectious lung disease, a chronic infectious disease caused by tuberculosis. The diagnosis of the confirmed person is usually judged by chest X-ray images, and the sputum smear is used to detect the presence of tuberculosis in the sputum. Screening high-risk individuals can effectively prevent the spread of tuberculosis; however, chest X-ray image interpretation and sputum testing take a long time. When infectious tuberculosis patients are found, tuberculosis has already spread. We propose a tuberculosis diagnostic triage system and a tuberculosis detection system based on preprocessing of lung image segmentation. In the tuberculosis diagnosis and triage system, AI interpretation is performed immediately after the patient's chest X-ray is taken, and abnormal tuberculosis cases are immediately listed. Lung field cropping through U-Net for classification in the form of a multiple ensemble system, including the use of EfficientNet-BO, Densenet121, and Xception. After marking abnormal lung images, we use a tuberculosis detection system to find patients with tuberculosis and use GRAD-Cam to display the image areas that are of most interest to the model, similar to a heat map, allowing us to know the model Predicting focus areas for tuberculosis. We used specificity, sensitivity, accuracy, and area under the receiver operating characteristic curve (AUROC) to evaluate the classification model performance.

关键词： Training Analytical models Sensitivity Tuberculosis Lung Medical services Predictive models

来源：评论

学校读者我要写书评

暂无评论

Distributed Flexible Job Shop Scheduling through Deploying Fog and Edge Computing in Smart Factories Using Dual Deep Q Networks

引用

Mobile Networks and applications 2024年第3期29卷 886-904页

作者： Lin, Chun-Cheng Peng, Yi-Chun Chen, Zhen-Yin Annie Fan, Yu-Hong Chin, Hui-Hsin Department of Industrial Engineering and Management National Yang Ming Chiao Tung University Hsinchu300 Taiwan International Master Program of Smart Manufacturing and Applied Information Science National Chin-Yi University of Technology Taichung411 Taiwan Department of Information Technology Overseas Chinese University Taichung407 Taiwan

Flexible job shop scheduling (FJSP) has garnered enormous attention within the realm of smart manufacturing, where, beyond job sequencing, the selection of machines holds considerable importance. As smart factories progress with the Internet of things (IoT) and cyber-physical systems (CPS), scheduling methodologies are advancing towards intelligent decentralization. However, with the expansion of factories, conventional cloud computing struggles to manage the substantial influx of data. To tackle this issue, this work incorporates a fog computing and edge computing framework into the distributed FJSP workstations. In this framework, the workstations each of which consists of multiple machines are categorized based on the different nature of the accommodated machines, and operate independently to reduce unnecessary information transmission, in which each machine is equipped with edge computing capacity. The fusion of fog computing and edge computing allows for the offloading of computational tasks from cloud computing, effectively reducing latency. While previous solutions for FJSP have predominantly relied on linear programming or metaheuristic algorithms, this work proposed a novel distributed approach based on a dual deep Q networks (dual DQN) architecture, integrating deep learning (DL) with reinforcement learning (RL). Within the cloud center, the initial neural network determines the machine selection rules for fog computing, while the secondary neural network decides the job dispatching rules for edge computing devices. Edge computing devices execute the schedule and provide feedback to the cloud, which refines the results through an iterative training process, so that to minimize the makespan. The experimental findings indicate that employing dual DQNs outperforms the methods of utilizing only one single machine selection rule. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Reentrant hybrid flow shop scheduling with stockers in automated material handling systems using deep reinforcement learning

引用

Computers and Industrial Engineering 2024年 189卷

作者： Lin, Chun-Cheng Peng, Yi-Chun Chang, Yung-Sheng Chang, Chun-Hsiang Department of Industrial Engineering and Management National Yang Ming Chiao Tung University Hsinchu300 Taiwan International Master Program of Smart Manufacturing and Applied Information Science National Chin-Yi University of Technology Taichung411 Taiwan

In smart factories, automated material handling system (AMHSs) replace manual material handling to increase production efficiency, in which stockers serve as the temporary storage for work-in-process inventories. Furthermore, costly machines and complex processes in advanced manufacturing lead to the need for multiple reentrant processes of the same workstation. However, previous works on scheduling problems rarely considered the function of stockers and reentrant processes, and their approaches were mostly based on metaheuristic algorithms. Recent advances in artificial intelligence enable the possibility of solving scheduling problems using deep reinforcement learning (DRL). Therefore, this work investigates the reentrant hybrid flow shop scheduling problem with stockers (RHFS2) inspired by AMHSs, and solves it by DRL. Firstly, the states, actions, and rewards of the Markov decision process for this problem are designed;and then, two deep Q network (DQN) approaches based on the actions for determining machines and jobs, respectively, are proposed. Simulation results demonstrate that our proposed DQN approaches outperform for finding better solutions of different-scale problems than classical metaheuristic algorithms. © 2024 Elsevier Ltd

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Survey on Recent applications of Artificial Intelligence and Optimization for Smart Grids in Smart Manufacturing

引用

Energies 2023年第22期16卷

作者： Hsu, Chao-Chung Jiang, Bi-Hai Lin, Chun-Cheng Department of Industrial Engineering and Management National Yang Ming Chiao Tung University Hsinchu300 Taiwan International Master Program in Smart Manufacturing and Applied Information Science National Chin-Yi University of Technology Taichung411 Taiwan

To enable highly automated manufacturing and net-zero carbon emissions, manufacturers have invested heavily in smart manufacturing. Sustainable and smart manufacturing involves improving the efficiency and environmental sustainability of various manufacturing operations such as resource allocation, data collecting and monitoring, and process control. Recently, a lot of artificial intelligence and optimization applications based on smart grid systems have improved the energy usage efficiency in various manufacturing operations. Therefore, this survey collects recent works on applications of artificial intelligence and optimization for smart grids in smart manufacturing and analyzes their features, requirements, and challenges. In addition, potential trends and further challenges for the integration of smart grids with renewable energies for smart manufacturing, applications of 5G and B5G (beyond 5G) technologies in the SG system, and next-generation smart manufacturing systems are discussed to provide references for further research. © 2023 by the authors.

关键词： Smart power grids

来源：评论

学校读者我要写书评

暂无评论

Joint green dynamic order batching and picker routing problem using PSO with global worst experience

引用

Applied Soft Computing 2024年 154卷

作者： Lin, Chun-Cheng Peng, Yi-Chun Kang, Jia-Rong Department of Industrial Engineering and Management National Yang Ming Chiao Tung University Hsinchu300 Taiwan International Master Program of Smart Manufacturing and Applied Information Science National Chin-Yi University of Technology Taichung411 Taiwan Department of Information Management Tatung University Taipei104 Taiwan

With the increasing importance of various countries’ initiatives on reducing carbon emissions (e.g., carbon border adjustment mechanism, CBAM), intelligent order picking systems have assisted electronic retailers in realizing a green supply chain. Previous studies on picker routing operations focused on adopting offline static customer order information to carry out operational decisions. However, in practice, the customer order information is updated dynamically;and high-efficiency warehouse layouts have been increasingly concerned. Therefore, this study creates a mixed-integer programming model for minimizing both the total carbon footprint and the total penalty cost for delayed orders in the joint order batching and picker routing problem with dynamic arriving orders and shipping time constraints in a high-efficiency fishbone warehouse layout. To solve this complex problem, a particle swarm optimization algorithm that integrates the swarm's previous global and local worst experiences and a migration mechanism is further proposed to increase solution quality and computing efficiency. In addition, a three-dimensional space for the warehouse floorplan and shipping time constraints is designed to divide orders into batches to address the constraints. Theoretical analysis of this algorithm is conducted, and experimental analysis shows that this algorithm finds superior solutions than current practical strategies, to offer a valuable reference for carbon emission reduction in greening warehousing. © 2024 Elsevier B.V.

关键词： Carbon footprint

来源：评论

学校读者我要写书评

暂无评论

Optimal deployment of private 5G multi-access edge computing systems at smart factories: Using hybrid crow search algorithm

引用

Journal of Network and Computer applications 2024年 227卷

作者： Lin, Chun-Cheng Deng, Der-Jiunn Hsieh, Li-Tsung Pan, Pei-Tzu Department of Industrial Engineering and Management National Yang Ming Chiao Tung University Hsinchu300 Taiwan International Master Program of Smart Manufacturing and Applied Information Science National Chin-Yi University of Technology Taichung411 Taiwan Department of Computer Science and Information Engineering National Changhua University of Education Changhua500 Taiwan

In smart factories, an increasing number of mobile intelligent devices are deployed to meet the growing demands for flexible manufacturing. These devices, equipped with various sensors, synchronize a substantial amount of data with cloud servers for real-time monitoring and control. Fifth generation mobile networks (5G) combined with multi-access edge computing (MEC) provide the capabilities for multiple connections, large-scale data transmission, and efficient response times, becoming the mainstream network architectures for the needs. Additionally, with the emerging trend of energy-saving, recent works have addressed energy consumption as a significant cost factor. However, most previous studies tended to focus solely on cloud servers, neglecting energy consumption at edge computing and underestimating the impact of heterogeneous mobile device. As the scope of smart factory networks continues to expand, the challenges become increasingly critical. This study presents a private 5G MEC system architecture tailored for smart panel factories. The concerned problem is formulated as an integer programming model, which determines deployment locations and quantities for MEC servers and 5G small cells, including picocells and femtocells, so as to minimize the overall deployment costs while meeting the constraints of connectivity, capacity, latency, coverage, serviceability, and energy consumption. Since the edge server deployment problem is NP-hard, this study further proposes a hybrid metaheuristic algorithm, CSAVNS, which combines the strengths of crow search algorithm (CSA) and variable neighborhood search (VNS). In the global search phase of CSA, the VNS local search is introduced to enhance the algorithm's capabilities. Experimental analysis demonstrates that the proposed CSAVNS outperforms other algorithms in terms of solution solving capabilities. © 2024 Elsevier Ltd

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

How Good is ChatGPT at Audiovisual Deepfake Detection: A Comparative Study of ChatGPT, AI Models and Human Perception

arXiv

引用

arXiv 2024年

作者： Shahzad, Sahibzada Adil Hashmi, Ammarah Peng, Yan-Tsung Tsao, Yu Wang, Hsin-Min The Social Networks and Human-Centered Computing Program Taiwan International Graduate Program Academia Sinica Taipei Taiwan The Department of Computer Science National Chengchi University Taipei Taiwan The Institute of Information Systems and Applications National Tsing Hua University Hsinchu Taiwan The Research Center for Information Technology Innovation Academia Sinica Taipei Taiwan The Institute of Information Science Academia Sinica Taiwan

Multimodal deepfakes involving audiovisual manipulations are a growing threat because they are difficult to detect with the naked eye or using unimodal deep learning-based forgery detection methods. Audiovisual forensic models, while more capable than unimodal models, require large training datasets and are computationally expensive for training and inference. Furthermore, these models lack interpretability and often do not generalize well to unseen manipulations. In this study, we examine the detection capabilities of a large language model (LLM) (i.e., ChatGPT) to identify and account for any possible visual and auditory artifacts and manipulations in audiovisual deepfake content. Extensive experiments are conducted on videos from a benchmark multimodal deepfake dataset to evaluate the detection performance of ChatGPT and compare it with the detection capabilities of state-of-the-art multimodal forensic models and humans. Experimental results demonstrate the importance of domain knowledge and prompt engineering for video forgery detection tasks using LLMs. Unlike approaches based on end-to-end learning, ChatGPT can account for spatial and spatiotemporal artifacts and inconsistencies that may exist within or across modalities. Additionally, we discuss the limitations of ChatGPT for multimedia forensic tasks. © 2024, CC BY.

关键词： Audiovisual

来源：评论

学校读者我要写书评

暂无评论

Impact of Social Media Marketing Towards Purchase Intention of Green Cosmetics in Indonesia

Impact of Social Media Marketing Towards Purchase Intention ...

引用

international Conference on ICT For Smart Society (ICISS)

作者： Lim Sanny Jessica Gabriella Ludony Kezia Chandra Glory Aguzman Rianto Nurcahyo Melvin M. Ninal Management Department BINUS Business School Master Program Bina Nusantara University Jakarta Indonesia Management Department BINUS Business School Undergraduate Program Bina Nusantara University Jakarta Indonesia International Business Management Department BINUS Business School Undergraduate Program Bina Nusantara University Jakarta Indonesia Information Technology St. Paul University Surigao Phillippines

This research aims to find out the effect of social media and green brand knowledge on its purchase intention through attitude as intervening variable. The method used in this research is quantitative method, by using nonprobability sampling - purposive sampling technique and multiple regression analysis. Researchers spread questionnaires to 211 respondents and use path analysis to determine the influence between variables. The results of this research are significantly: social media affect attitude, green brand knowledge affect attitude, attitude doesn't affect green cosmetics purchase intention, social media doesn't affect green cosmetics purchase intention, green brand knowledge affects green cosmetics purchase intention, social media doesn't affect green cosmetics purchase intention through attitude, and green brand knowledge doesn't affect green cosmetics purchase intention through attitude.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AV-Lip-Sync+: Leveraging AV-HuBERT to Exploit Multimodal Inconsistency for Video Deepfake Detection

arXiv

引用

arXiv 2023年

作者： Shahzad, Sahibzada Adil Hashmi, Ammarah Peng, Yan-Tsung Tsao, Yu Wang, Hsin-Min The Social Networks and Human-Centered Computing Program Taiwan International Graduate Program Academia Sinica Taipei11529 Taiwan The Department of Computer Science National Chengchi University Taipei11605 Taiwan The Institute of Information Systems and Applications National Tsing Hua University Hsinchu30013 Taiwan The Research Center for Information Technology Innovation Academia Sinica Taipei11529 Taiwan The Institute of Information Science Academia Sinica Taipei11529 Taiwan

Multimodal manipulations (also known as audiovisual deepfakes) make it difficult for unimodal deepfake detectors to detect forgeries in multimedia content. To avoid the spread of false propaganda and fake news, timely detection is crucial. The damage to either modality (i.e., visual or audio) can only be discovered through multi-modal models that can exploit both pieces of information simultaneously. Previous methods mainly adopt uni-modal video forensics and use supervised pre-training for forgery detection. This study proposes a new method based on a multi-modal self-supervised-learning (SSL) feature extractor to exploit inconsistency between audio and visual modalities for multi-modal video forgery detection. We use the transformer-based SSL pre-trained Audio-Visual HuBERT (AV-HuBERT) model as a visual and acoustic feature extractor and a multi-scale temporal convolutional neural network to capture the temporal correlation between the audio and visual modalities. Since AV-HuBERT only extracts visual features from the lip region, we also adopt another transformer-based video model to exploit facial features and capture spatial and temporal artifacts caused during the deepfake generation process. Experimental results show that our model outperforms all existing models and achieves new state-of-the-art performance on the FakeAVCeleb and DeepfakeTIMIT datasets. © 2023, CC BY.

关键词： Audio acoustics

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：