检索结果-内蒙古大学图书馆

Online Multicast Traffic engineering for Multi-View Videos With View Synthesis in SDN

IEEE/ACM Transactions on Networking 2024年第4期32卷 2778-2793页

作者： Chiang, Sheng-Hao Wang, Chih-Hang Yang, De-Nian Liao, Wanjiun Chen, Wen-Tsuen Institute of Information Science Academia Sinica Taipei City115201 Taiwan Graduate Institute of Communication Engineering National Taiwan University Taipei City106319 Taiwan Institute of Information Science and the Research Center for Information Technology Innovation Academia Sinica Taipei City115201 Taiwan National Taiwan University Department of Electrical Engineering Taipei City106319 Taiwan National Tsing Hua University Department of Computer Science Hsinchu300044 Taiwan

Multi-view videos (MVV) have emerged to provide users with immersively interactive experiences with 3D multimedia content. Compared with traditional 2D videos, MVV offers multiple view angles to avoid generating occluded regions from a single viewpoint and allows users to receive different view angles, which consume much higher bandwidth. In this paper, we leverage multicast and view synthesis to effectively reduce the number of transmitted views and total bandwidth consumption in software-defined content delivery networks (SD-CDN). By exploiting the SDN architecture, SD-CDN can optimize traffic engineering and the selection of multi-view sources to serve users. We formulate a new optimization problem, Online Multicast with View Synthesis (OMVS), prove the NP-hardness, and design an online algorithm with the ideas of View Popularity Cost Ratio, View Watching Possibility, and synthesis tree, to achieve the tightest competitive ratio. The experiment on real networks and implementation in an experimental SDN manifest that the proposed algorithm outperforms state-of-the-art algorithms regarding the total cost, bandwidth consumption, synthesis quality, and link and node utilization. © 2024 IEEE.

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

A weighted multivariate fuzzy time series method for multiple output high-dimensional time series forecasting in IoT applications

A weighted multivariate fuzzy time series method for multipl...

引用

2024 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2024

作者： Bitencourt, Hugo Vinicius De Oliveira Lucas, Patricia Orang, Omid Silva, Petronio Guimaraes, Frederico Gadelha Universidade Federal de Minas Gerais Graduate Program in Electrical Engineering Belo Horizonte31270-901 Brazil Instituto Federal Do Norte de Minas Gerais Salinas Brazil Universidade Federal de Minas Gerais Department of Computer Science Belo Horizonte31270-901 Brazil Instituto Federal Do Norte de Minas Gerais Januária Brazil

ISBN: (纸本)9798350374575

In Internet of Things (IoT) applications, data flows are continuous streams of high-dimensional time series that aggregate various data sources. In this context, decision-making processes frequently encompass multiple factors and criteria that demand forecasting these time series. This paper introduces MO-WMVFTS, a novel multiple-input multiple-output (MIMO) fuzzy time series (FTS) method for tackling this complex scenario. MO-WMVFTS is a hybrid forecasting method that fuses weighted multivariate FTS (WMVFTS) with embedding transformations, designed for IoT applications. To assess the performance of the proposed method, it was applied to the prediction of energy consumption in smart homes and air quality in smart cities. Here, three real-world datasets are used to assess the validity of our proposed approach, and the results obtained are highly competitive when compared to other existing methods. © 2024 IEEE.

关键词： Smart homes

来源：评论

学校读者我要写书评

暂无评论

Evaluating Conveyor Belt Health With Signal Processing Applied to Inertial Sensing

Evaluating Conveyor Belt Health With Signal Processing Appli...

引用

2023 Symposium on Internet of Things, SIoT 2023

作者： Matos, Saulo Neves Coletti, Otavio Ferracioli Filho, Fernando Ugucioni De Carvalho, Ricardo C. C. L. Pinto, Thomas V. B. De Barros, Luiz G. D. Ranieri, Caetano Mazzoni Lopes, Bruno Eduardo Ueyama, Jo Pessin, Gustavo Institute of Mathematics and Computer Science University of Sao Paulo Brazil Sao Carlos School of Engineering University of Sao Paulo Brazil Vale Institute of Technology Ouro Preto Brazil Universidade Federal of Minas Gerais Graduate Program in Electrical Engineering MG Belo Horizonte Brazil Vale -SA Vitoria Brazil

ISBN: (纸本)9798350329438

Conveyor belts are commonly used in the mining industry for efficient material transport. However, they are prone to failures such as idler anomalies, belt tears, and misalignment. Current monitoring systems only evaluate the conveyor or idle belt's condition at the installation point. This study proposes a method to detect faults in conveyor belts, specifically idler anomalies and belt deviation, using two IMUs installed at the lateral extremities of the belt to evaluate its health along its route. In a reduced-scale conveyor belt, we conducted experiments by collecting gyroscopes and accelerometer data in various scenarios, including normal conditions and anomaly situations. We modified the idlers' physical structure or changed the belt tracks to create these scenarios. We used similarity analysis techniques to compare the data collected and performed statistical hypothesis analysis to observe the influence of the anomaly scenarios on the gyroscope and accelerometer data. We used Dynamic Time Warping (DTW) for gyroscope data to compare ground truth with anomaly scenarios. For the acceleration data, we performed vibration analysis by converting the time domain data to the frequency using Fast Fourier Transform (FFT) and evaluating the difference in spectral density between the reference and anomaly data. Statistical hypothesis analysis revealed that anomaly scenar-ios influenced the gyroscope x-axis and z-axis more. According to the spectral density analysis of the accelerometer, it was revealed that belt misalignment on the y-axis may be detected. © 2023 IEEE.

关键词： Belt conveyors

来源：评论

学校读者我要写书评

暂无评论

CLeAR: continual learning on algorithmic reasoning for human-like intelligence 23

CLeAR: continual learning on algorithmic reasoning for human...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Bong Gyun Kang HyunGi Kim Dahuin Jung Sungroh Yoon Interdisciplinary Program in Artificial Intelligence Seoul National University Department of Electrical and Computer Engineering Seoul National University Interdisciplinary Program in Artificial Intelligence Seoul National University and Department of Electrical and Computer Engineering Seoul National University

Continual learning (CL) aims to incrementally learn multiple tasks that are presented sequentially. The significance of CL lies not only in the practical importance but also in studying the learning mechanisms of humans who are excellent continual learners. While most research on CL has been done on structured data such as images, there is a lack of research on CL for abstract logical concepts such as counting, sorting, and arithmetic, which humans learn gradually over time in the real world. In this work, for the first time, we introduce novel algorithmic reasoning (AR) methodology for continual tasks of abstract concepts: CLeAR. Our methodology proposes a one-to-many mapping of input distribution to a shared mapping space, which allows the alignment of various tasks of different dimensions and shared semantics. Our tasks of abstract logical concepts, in the form of formal language, can be classified into Chomsky hierarchies based on their difficulty. In this study, we conducted extensive experiments consisting of 15 tasks with various levels of Chomsky hierarchy, ranging from in-hierarchy to inter-hierarchy scenarios. CLeAR not only achieved near zero forgetting but also improved accuracy during following tasks, a phenomenon known as backward transfer, while previous CL methods designed for image classification drastically failed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Stability Analysis of Speed Control Systems for Variable Speed Wind Power Generation Systems Using SRG and Capacitor-Less AC-AC Converters

Stability Analysis of Speed Control Systems for Variable Spe...

引用

International Conference on Renewable Energy Research and Applications (ICRERA)

作者： Haozheng Jia Kazuhiro Ohyama Engineering Master's Program of Electrical Engineering Graduate School Fukuoka Institute of Technology Higashi-ku Fukuoka Japan Department of Electrical Engineering Faculty of Engineering Fukuoka Institute of Technology Higashi-ku Fukuoka Japan

ISBN: (数字)9798350375589

ISBN: (纸本)9798350375596

This paper extends previous work on simulation models of switched reluctance generators (SRG) by demonstrating that selecting appropriate proportional-integral (PI) gain settings enables rapid adaptation to wind speed variations, thereby ensuring system stability. The study shows that employing continuously varying gains provides a detailed understanding of the system's dynamic performance, offering insights into the effects of different gain profiles on stability. The transient responses induced by changes in PI gain are effectively mitigated through the introduction of a compensatory signal derived from the system's maximum transient response. Alternatively, it has been demonstrated that a gain with a smooth transition profile, such as one based on a Bessel curve, achieves a comparable stabilizing effect by eliminating transient phenomena and improving response smoothness. These measures collectively enhance the system's stability and robustness, making the control framework more adaptable to dynamic conditions and offering practical insights for the design of wind power generation systems. The findings highlight the potential of these methods to optimize energy conversion and improve the operational reliability of SRG-based systems under varying wind speeds.

关键词： Transient response Renewable energy sources System dynamics Wind speed Velocity control Switches Wind power generation Stability analysis Robustness Transient analysis

来源：评论

学校读者我要写书评

暂无评论

Threshold-Based Electroencephalography Brain-computer Interface for Robot Arm Control

Threshold-Based Electroencephalography Brain-Computer Interf...

引用

Asia-Pacific Conference on Intelligent Robot Systems (ACIRS)

作者： Muhammad Ilhamdi Rusydi Elita Amrina Yoan Winata Salisa 'Asyarina Ramadhani Riko Nofendra Electrical Engineering Department Engineering Faculty Program of Engineer Professional Education Graduate School Universitas Andalas Padang Indonesia Industrial Engineering Department Engineering Faculty Program of Engineer Professional Education Graduate School Universitas Andalas Padang Indonesia Electrical Engineering Department Engineering Faculty Universitas Andalas Padang Indonesia

Brain-computer Interface (BCI) is a technique that uses real-time brain impulses to connect with and control external devices. BCI provides a new method for controlling external devices by translating brain signals into computer commands, facilitating the daily lives of people with disabilities and enhancing their ability to exhibit expected behavior. A Brain-computer Interface (BCI) system based on Electroencephalography (EEG) was built to control the robotic arm. The EEG signals utilized included both eyes blinking, the right eye, the left eye, and the jaw contraction. EEG data were recorded from seven healthy subjects. The threshold approach is used to classify EEG signals, with the feature employed being the amplitude of the EEG signal. The highest threshold value for the blinking signal was 0.6 mV with an accuracy of 97.9%, while the best threshold value for jaw contraction was 0.4 mV with an accuracy of 93.34 percent. The healthy, inexperienced participants took part in system testing. The total results of testing each robot movement yielded an overall success rate of 84.52 percent. Therefore, it was determined that the system could facilitate the operation of the length robot even if the user lacked prior experience with EEG-based systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Deep Convolutional Neural Network-Based Tattoo Detection

Evaluation of Deep Convolutional Neural Network-Based Tattoo...

引用

Inteligencia Ambiental, Ingeniería de Software y Salud Electrónica y Móvil (AmITIC), V Congreso Internacional en

作者： E. Jiménez-Delgado C. Quesada-López A Méndez-Porras A Lara-Petitdemange J Alfaro-Velasco Graduate Program in Computer Science and Informatics University of Costa Rica Computer Engineering Department Technological Institute of Costa Rica School of Computer Science and Informatics University of Costa Rica

ISBN: (数字)9798350364538

ISBN: (纸本)9798350364545

In this study, two deep learning models for automatic tattoo detection were analyzed; a modified Convolutional Neural Network (CNN) and pre-trained ResNet-50 model. In order to achieve this, ResNet-50 uses transfer learning with fine-tuning. The purpose of this study was to evaluate the accuracy, precision, recall, F1-score, and computational efficiency of the system being considered. To augment the dataset included 1000 photos that were equally divided between those showing tattoos and those that did not show tattoos. A k-fold cross-validation approach was employed in training and testing the models. Although custom CNNs are effective, utilizing pre-trained ones like ResNet-50 can offer even better outcomes. Specifically, ResNet-50 attained a higher accuracy (0.86 compared to 0.79), precision (0.85 versus 0.78), recall (0.91 against 0.86), and F1-score (0.91 vis-a-vis 0.86) as compared to custom CNNs. In selecting these models for examination, two main motivations were considered. The first motivation is to see whether transfer learning with a pre-trained ResNet-50 model does well when compared with a customized CNN designed specifically for tattoo detection. Secondly,the intent of this study is to know what advantages can be derived from each approach and their demerits too. Furthermore, it seeks to determine if transfer learning can provide an alternative in contrast to the common CNN techniques with regards to precision and computational efficiency. In this research, two models will be evaluated in order to answer the question of what is better for tattoo detection: transfer learning or designing custom architectures.

关键词： Training Analytical models Accuracy Computational modeling Transfer learning computer architecture Real-time systems Computational efficiency Convolutional neural networks Tuning

来源：评论

学校读者我要写书评

暂无评论

Blockchain and API Development to Improve Relational Database Integrity and System Interoperability

引用

Procedia computer Science 2023年 216卷 151-160页

作者： Andhika Naafi Ramadhan Kharisma Naufal Pane Kun Rifki Wardhana Suharjito Computer Science Department School of Computer Science Bina Nusantara University Jakarta 11480 Indonesia Industrial Engineering Department BINUS Graduate Program – Master of Industrial Engineering Bina Nusantara University Jakarta 11480 Indonesia

Technological developments have resulted in a trend of cryptocurrencies that use a technology called blockchain to create and record all transactions made into a digital ledger. Along with the emergence of the trend of cryptocurrencies, this development has also resulted in crimes that hit the digital world, such as data leakage and cyber espionage. This threat can be prevented by applying blockchain technology to the database that has been used. Therefore, we need a system that can facilitate the use of blockchain technology and can process data from an existing relational database into a blockchain-based database. The system developed in this study was built with the FastAPI framework that uses the Python programming language and the React framework that uses the Javascript programming language. This system was tested using Katalon and Wireshark software to perform throughput testing and man-in-the-middle attacks. Evaluation of this system is assessed based on the average throughput time and also the results of Wireshark packet capture. The system designed in this research is expected to help overcome interoperability problems when using blockchain and improve relational database integrity. The results of the test show that the system is safe from man-in-the-middle attacks while sending data through API and has a faster throughput time than BigchainDB system by 4.151 seconds.

关键词： Blockchai Cybercrim Database Interoperability

来源：评论

学校读者我要写书评

暂无评论

DSPI - Dual Semantic Parsing Image: A Robust Person Representation for Person Re-Identification

DSPI - Dual Semantic Parsing Image: A Robust Person Represen...

引用

International Conference on Communications and Electronics, ICCE

作者： Dau Anh Dung Yasuhiro Nakamura Department of Information and Mathematical Sciences Graduate School of Science and Engineering National Defense Academy Yokosuka Japan Department of Computer Science School of Electrical and Computer Engineering National Defense Academy Yokosuka Japan

ISBN: (数字)9798350379792

ISBN: (纸本)9798350379808

One method to significantly enhance the performance of Person-ReID models is to leverage segmentation models to extract semantic parsing information, thus emphasizing the characteristics of human body parts. Studies employing this approach typically utilize CNN architectures as the backbone of Person-ReID, integrating human semantic parsing information into the output of the backbone model, resulting in substantial performance improvement. However, Transformer architectures, utilizing self-attention mechanisms and employing different image data processing techniques from CNN architectures, necessitate a direct integration method for human semantic parsing information into the model’s input. In this study, we propose a novel, simple, and highly adaptable method for integrating human semantic parsing information into input data, called Dual Semantic Parsing Image (DSPI). In this method, a pre-trained segmentation model is employed to extract human pixels from the background and create a new foreground image. The DSPI is formed by horizontally merging the foreground image with the original image, which serves as the input image for the Re-ID model. Our study demonstrates that the Person Re-ID Backbone model ViT+DSPI achieves 93.1% Rank-1 accuracy and 91.1% mAP in the same-domain test of DukeMTMC-ReID, thus attaining state-of-the-art performance. Additionally, significant performance enhancements were observed in cross-domain tests.

关键词： Degradation Adaptation models Image segmentation Electric potential Semantics Merging Transformers

来源：评论

学校读者我要写书评

暂无评论

Gender-Based Bimodal Analysis of Speech and Text in Non-Contextual Emotion Recognition

Gender-Based Bimodal Analysis of Speech and Text in Non-Cont...

引用

Informatics International Conference (BTS-I2C), Beyond Technology Summit on

作者： Abby Rasya Angkasa Amalia Zahra Wai-Keung Fung Computer Science Department BINUS Graduate Program - Master of Computer Science Jakarta Indonesia Engineering Department Cardiff Metropolitan University - Cardiff School of Technologies Cardiff United Kingdom

ISBN: (数字)9798331508579

ISBN: (纸本)9798331508586

Emotion recognition can help human-computer interactions by enabling systems to respond empathetically and adapt to users' emotional conditions. This capability improves user experience, supporting the development of a more intuitive and emotionally responsive communication system. This study analyzes a bimodal approach based on gender (male and female) to recognize emotions without contextual information in dialogue analysis. Utilizing the Multimodal EmoryNLP dataset extracted from the TV series Friends with acted speech, we focused on four primary emotions: Angry, Neutral, Joy, and Scared. The model used in this study for text classification is RoBERTa, and wav2vec 2.0 is used for audio feature extraction with the Bi-LSTM model for classification. The experiment results using weighted F1-score reveal that data augmentation enhanced the performance of analyzing the original dataset from 0.46% to 0.52% and the male dataset from 0.43% to 0.51 %. In comparison, the female dataset remained consistent at 0.46%. The weighted F1-score and Unweighted Averaged Recall (UAR) from the male dataset are higher, 51 % and 48%, respectively, than those from the female dataset, 46% and 47%, respectively. Gender-based analysis indicated that male and female datasets exhibited distinct performance patterns, highlighting variations in emotional expression and recognition between genders. These findings underscore the effectiveness of multimodal strategies in emotion recognition and suggest that gender-specific factors play a significant role in enhancing classification performance. While these results highlight performance trends, further validation through repeated trials and statistical analyses could provide stronger generalizations and insights into gender-based differences.

关键词： Emotion recognition TV Statistical analysis Text categorization Speech recognition Linguistics Feature extraction Data augmentation Market research User experience

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：