检索结果-内蒙古大学图书馆

IEEE Region 10 International Conference TENCON

作者： Toshiro Nunome Yoshiyuki Takada Department of En-gineering Computer Science Program Graduate School of Engineering Nagoya Institute of Technology Nagoya Japan Department of Engineering Computer Science Program Graduate School of Engineering Nagoya Institute of Technol-ogy Nagoya Japan

In this paper, we exploit caches on intermediate nodes for QoE enhancement of multi-view video and audio transmission over ICN/CCN by controlling the content request start timing of consumers. We assume the selected single viewpoint transmission method; a consumer receives video and audio streams of a requested viewpoint. We perform a simple experiment with two consumers. When the consumers play video and audio with the time difference, we assess the effect of cached content by the former consumer's request on the output quality of the latter consumer. We deal with two types of viewpoint change strategies for the former consumer, which affect the efficiency of cache utilization. From the assessment results, we see that cache utilization has an important factor in enhancing QoE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learnable upsampling bilateral grid refinement for stereo matching network 4

Learnable upsampling bilateral grid refinement for stereo ma...

引用

4th International Conference on Advanced Algorithms and Neural Networks, AANN 2024

作者： Qiu, Wenfeng Ma, Chihao Li, Jianhua Qian, Ren Zhao, Yong College of Computer Science and Technology Guizhou University Guiyang550025 China School of Electronic and Computer Engineering Shenzhen Graduate School of Peking University Shenzhen518055 China College of Artificial Intelligence and Big data Luzhou Vocational and Technical College Sichuan Luzhou646000 China

ISBN: (纸本)9781510686106

Most existing binocular stereo matching algorithms require a trade-off between accuracy and speed, unable to achieve both simultaneously. One reason lies in the complexity and variability of scenes that stereo matching tasks must handle, where disparities in heavily textured, weakly textured, and occluded areas are often difficult to infer correctly. Therefore, this paper proposes the Learnable Upsampling Bilateral Grid Refinement for Stereo Matching Network (LUGNet). Through learnable bilateral grid upsampling guided by the left image, LUGNet calculates offsets for cost volume upsampling, while simultaneously leveraging the network to automatically learn interpolation weights to accommodate features of different datasets. Ultimately, LUGNet achieves error rates comparable to high-precision networks with a parameter count of 2.6M and an inference time of 58ms. © 2024 SPIE.

关键词： Stereo image processing

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Emotion Recognition in Facial Image Using Attentive Deep Convolutional Neural Network 2

Evaluation of Emotion Recognition in Facial Image Using Atte...

引用

2nd International Conference on Information technology Research and Innovation, ICITRI 2023

作者： Aini, Nur Pardede, Hilman Ferdinandus Graduate School of Computer Science Universitas Nusa Mandiri Faculty of Technology Information Depok Indonesia Research Center for AI and Cybersecurity National Research and Innovation Agency Indonesia

ISBN: (纸本)9798350324945

Emotion recognition in facial images is a topic that has attracted many interests. Research on emotion recognition in facial images continues to face challenges such as variations of human faces due to environments or situations. Of all the techniques that have been used, the Deep Convolution Neural Network (DCNN) method reports a significant improvement compared to traditional machine learning methods. In recent years, self-attachment mechanisms have increased in popularity in DCNN, especially in Natural Language Processing. In this study, we propose to add attention networks to DCNN method to improve the performance of emotion recognition. By incorporating self-attention mechanisms into the model architecture, the network is able to recognize which facial features are most relevant for each emotion, increasing the accuracy and interpretation of the model. This study reports an accuracy of 69.55% which is 11.15% higher than using the traditional DCNN model. © 2023 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Numerical simulations on self-referential holographic data storage with built-in denoising function by self-referential holographic deep neural network

引用

Optical Review 2025年 1-12页

作者： Eto, Yuta Tomioka, Rio Takatsu, Taichi Takabayashi, Masanori Graduate School of Computer Science and Systems Engineering Kyushu Institute of Technology Iizuka Japan Faculty of Computer Science and Systems Engineering Kyushu Institute of Technology Iizuka Japan Research Center for Neuromorphic AI Hardware Kyushu Institute of Technology Wakamatsu Japan

Self-referential holography (SRH), a holographic technique that enables the recording, reading, and control of two-dimensional (2D) patterns using a one-beam geometry, can be applied to holographic data storage (HDS) and optoelectronic deep neural network (OE-DNN). Since both applications are implemented using the same optical system, they can be integrated into a single system. We propose a self-referential HDS (SR-HDS) with a built-in denoising function using a self-referential holographic deep neural network (SR-HDNN), where the quality of reconstructed datapages in HDS can be enhanced using deep neural networks (DNNs) without requiring costly electronic computers for implementation. Numerical simulations are performed to demonstrate the feasibility of the proposed method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mixed Deep Reinforcement Learning Considering Discrete-continuous Hybrid Action Space for Smart Home Energy Management

引用

Journal of Modern Power Systems and Clean Energy 2022年第3期10卷 743-754页

作者： Chao Huang Hongcai Zhang Long Wang Xiong Luo Yonghua Song IEEE State Key Laboratory of Internet of Things for Smart City University of MacaoMacao S.A.R.China School of Computer and Communication Engineering University of Science and Technology BeijingBeijing 100083China Shunde Graduate School University of Science and Technology BeijingFoshan 528399China State Key Laboratory of Internet of Things for Smart City and Department of Electrical and Computer Engineering University of MacaoMacao S.A.R.China

This paper develops deep reinforcement learning(DRL)algorithms for optimizing the operation of home energy system which consists of photovoltaic(PV)panels,battery energy storage system,and household ***-free DRL algorithms can efficiently handle the difficulty of energy system modeling and uncertainty of PV ***,discretecontinuous hybrid action space of the considered home energy system challenges existing DRL algorithms for either discrete actions or continuous ***,a mixed deep reinforcement learning(MDRL)algorithm is proposed,which integrates deep Q-learning(DQL)algorithm and deep deterministic policy gradient(DDPG)*** DQL algorithm deals with discrete actions,while the DDPG algorithm handles continuous *** MDRL algorithm learns optimal strategy by trialand-error interactions with the ***,unsafe actions,which violate system constraints,can give rise to great *** handle such problem,a safe-MDRL algorithm is further *** studies demonstrate that the proposed MDRL algorithm can efficiently handle the challenge from discrete-continuous hybrid action space for home energy *** proposed MDRL algorithm reduces the operation cost while maintaining the human thermal comfort by comparing with benchmark algorithms on the test ***,the safe-MDRL algorithm greatly reduces the loss of thermal comfort in the learning stage by the proposed MDRL algorithm.

关键词： Demand response deep reinforcement learning discrete-continuous action space home energy management safe reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Mobile Application for Haircut Art Community 2

Mobile Application for Haircut Art Community

引用

2nd International Conference on Artificial Intelligence and Smart Energy, ICAIS 2022

作者： Fahmi, Hilal Nugroho, Muhammad Ivan Setiawan, Kristian Daniel Gary, Vittorio Moedjiono, Sardjoeni Warnars, Harco Leslie Hendric Spits School of Information Systems Bina Nusantara University Information Systems Department Jakarta11480 Indonesia Budi Luhur University Faculty of Information Technology Computer Science Department Jakarta Indonesia Bina Nusantara University Binus Graduate Program - Computer Science Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9781665400527

The haircut art community is a community that is interested in the art of hair or hair-related issues and information. This haircut art community has several members, but they need the application of technology to support their hobby as a community. In this mobile application, a system where users can make transactions connected to the haircut community has been proposed. Users can make online appointments with barbers' haircuts, make online payments, engage with forums, and get information about the barbershop community. In addition, this mobile app will allow people in the community to sell and buy anything related to haircuts. In addition, it is hoped that it can be used as an income opportunity for people who have expertise in the art of barbering. This application is implemented using visual studio and MySQL database for the database. This application is modeled using use case diagrams to describe its business processes and class diagrams to describe the database design. © 2022 IEEE.

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

Analyzing the Impact of Deep Learning Approaches on Real-Time Data Analysis in Machine Learning

Analyzing the Impact of Deep Learning Approaches on Real-Tim...

引用

2023 International Conference on Power Energy, Environment and Intelligent Control, PEEIC 2023

作者： Deepti Nalluri, Mounika Mupparaju, Chinna Babu Rongali, Aruna Sri Dhar, Sohong Ajitha, P. Sloan School of Management Mit United States Computer Information Systems Murray State University United States University of Central Missouri Computer Science warrensburg United States University of the Cumberlands Graduate Doctoral Information Technology Information Technology Emphasis/Information Technology United States Azure Microsoft United States Library & Information Science Jadavpur University India School of Computing Sathyabama Institute of Science and Technology Chennai India

ISBN: (纸本)9798350357769

Deep learning is a powerful subset of synthetic intelligence, and it has the potential to significantly enhance the skills of machine getting to know. it's miles primarily based on the idea of artificial neural networks, which might be laptop fashions that are capable of gaining knowledge of from records and making decisions, just like the manner a human mind works. Deep mastering isn't the same as traditional system mastering algorithms in that it can technique complex inputs with multiple layers of abstraction, main to greater accurate evaluation. Deep studying algorithms are capable of unexpectedly examine raw facts and generate styles, making them perfect for actual-time statistics analysis. Deep studying is capable of as it should be predicting behaviors and trends, which may be used to optimize procedures and enhance operational efficiencies. Deep studying models can also be used for automated fault detection and predictive renovation, permitting businesses to count on and prevent capacity troubles. Additionally, deep mastering models frequently offer quicker consequences than other device studying or conventional techniques, as well as permitting an extra diploma of control over the resolution of the data being analyzed. This has widespread implications for real-time programs, such as medical diagnostics, independent automobiles, and manufacturing monitoring. © 2023 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Frequency Bandwidth Reduction of High-Frequency Intra-Body Propagation Characteristics Used for Attacker's Touch Detection in Fingerprint Authentication 12

Frequency Bandwidth Reduction of High-Frequency Intra-Body P...

引用

12th IEEE Global Conference on Consumer Electronics, GCCE 2023

作者： Tomura, Shunichi Yamada, Koki Yoshida, Takahiro Tokyo University of Science Graduate School of Engineering Department of Electrical Engineering Tokyo Japan Tokyo University of Agriculture and Technology Department of Electrical Engineering and Computer Science Tokyo Japan Tokyo University of Science Faculty of Engineering Department of Electrical Engineering Tokyo Japan

ISBN: (纸本)9798350340181

In previous studies, we have proposed the attacker's touch detection method in fingerprint authentication using high-frequency intra-body propagation characteristics to detect attacks in that an attacker holds the user's finger/wrist and presses the user's finger to a fingerprint scanner. However, the previous method used a wide range of frequency bands from 300 kHz to 10 MHz, and this caused problems in the circuit scale, cost, and size of the device in development for practical use. Therefore, we searched effective frequency bands and applied K-nearest neighbor with data augmentation in this study. As results, we achieved a 99.1 % touch detection rate with a single frequency and a 99.9 % touch detection rate with a combination of two frequencies. We achieved a significant reduction in the frequency bandwidth of the propagation characteristics. © 2023 IEEE.

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

Multilabel Machine Learning System for Predicting Gender and Age Group from Human Gait 2

Multilabel Machine Learning System for Predicting Gender and...

引用

2nd IEEE International Conference on Interdisciplinary Approaches in technology and Management for Social Innovation, IATMSI 2024

作者： Qomariyah, Nunung Nurul Nurul Fajar, Ahmad Yono, Vincent Kazakov, Dimitar Bina Nusantara University School of Computing and Creative Arts Computer Science Department Jakarta11480 Indonesia Bina Nusantara University Binus Graduate Program Information System Management Information Systems Management Department Jakarta11480 Indonesia University of York Computer Science Department YO10 5GH United Kingdom

ISBN: (纸本)9798350360523

This paper explores the development of a multilabel machine learning system for predicting both gender and age from human gait patterns. Gait analysis, a non-intrusive method of identifying subtle nuances in human movement, has proven to be a rich source of information related to demographic characteristics. The research extends beyond traditional single-label classification approaches, adopting a multilabel framework to simultaneously predict gender and age *** study evaluates various multilabel machine learning algorithms, with the Random k-labeLsets (RAKEL) algorithm demonstrating superior performance in predicting gender and age labels from human gait datasets. The accuracy of the algorithm can reach up to 87%. We also compared the multilabel approach with several multiclass algorithms such as Decision Tree, Random Forest, Gradient Boosting, K-Neighbors and XGBoost. However, when we also considering the training time, Classifier Chain algorithm showed the best trade off with the accuracy of 86% and the training time is twice faster than the RAKEL algorithm. © 2024 IEEE.

关键词： Gait analysis

来源：评论

学校读者我要写书评

暂无评论

Hawkeye: A Dynamic and Stateless Multicast Mechanism with Deep Reinforcement Learning 42

Hawkeye: A Dynamic and Stateless Multicast Mechanism with De...

引用

42nd IEEE International Conference on computer Communications, INFOCOM 2023

作者： Lu, Lie Li, Qing Zhao, Dan Yang, Yuan Luan, Zeyu Zhou, Jianer Jiang, Yong Xu, Mingwei Tsinghua University Tsinghua Shenzhen International Graduate School Shenzhen China Department of Mathematics and Theories Shenzhen China Tsinghua University Department of Computer Science and Technology Beijing China Southern University of Science and Technology Institute of Future Networks Shenzhen China

ISBN: (纸本)9798350334142

Multicast traffic is growing rapidly due to the development of multimedia streaming. Lately, stateless multicast protocols, such as BIER, have been proposed to solve the excessive routing states problem of traditional multicast protocols. However, the high complexity of multicast tree computation and the limited scalability for concurrent requests still pose daunting challenges, especially under dynamic group membership. In this paper, we propose Hawkeye, a dynamic and stateless multicast mechanism with deep reinforcement learning (DRL) approach. For real-time responses to multicast requests, we leverage DRL enhanced by a temporal convolutional network (TCN) to model the sequential feature of dynamic group membership and thus is able to build multicast trees proactively for upcoming requests. Moreover, an innovative source aggregation mechanism is designed to help the DRL agent converge when faced with a large amount of multicast requests, and relieve ingress routers from excessive routing states. Evaluation with real-world topologies and multicast requests demonstrates that Hawkeye adapts well to dynamic multicast: it reduces the variation of path latency by up to 89.5% with less than 12% additional bandwidth consumption compared with the theoretical optimum. © 2023 IEEE.

关键词： Reinforcement learning

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：