检索结果-内蒙古大学图书馆

Proceedings of the 55th Annual IEEE/ACM International Symposium on Microarchitecture

作者： Xueliang Li Zhuobin Shi Junyang Chen Yepang Liu National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China College of Computer Science and Software Engineering Shenzhen University China Research Institute of Trustworthy Autonomous Systems Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation and Department of Computer Science and Engineering Southern University of Science and Technology China

ISBN: (纸本)9781665462723

In the age of AI, mobile architectures such as smartphones are still "cold machines"; machines do not feel. If the architecture is able to feel users' feelings and runtime user experience (UX), it will accordingly adapt performance/energy to find the optimal system-operating state that consumes the least energy to satisfy users. In this paper, we will utilize users' facial expressions (FEs) to learn their runtime UX. We know that FEs are the natural and direct way for humans to convey their emotions and feelings. Our study reveals that FEs also reflect UX. Our research for the first time quantifies the link between FEs and UX. Leveraging this link, the architecture will be able to use the front camera to see FEs and feel users' UX. Based on UX, the architecture can appropriately provision computing resources. We propose Vi-energy system to realize the above idea. Our evaluation shows that Vi-energy reduces energy consumption by 52.9% at maximum and secures UX.

关键词：

来源：评论

学校读者我要写书评

暂无评论

How to Design a R-D Model for UAV Video Transmission? 15

How to Design a R-D Model for UAV Video Transmission?

引用

15th IEEE International Conference on Wireless Communications and Signal Processing, WCSP 2023

作者： Yu, Zongyang Yang, Peng Cao, Xianbin Zheng, Dezhi Quek, Tony Q. S. Oliver Wu, Dapeng Beihang University School of Electronic Information Engineering Beijing China Peng Cheng Laboratory Department of Mathematics and Theories Shenzhen China Beijing Institute of Technology Advanced Research Institute of Multidisciplinary Sciences Beijing China Singapore University of Technology and Design Information Systems Technology and Design Singapore City University of Hong Kong Department of Computer Science Kowloon Hong Kong

ISBN: (纸本)9798350324662

Unmanned aerial vehicle (UAV) video transmission has been extensively applied in many crucial fields. However, the problem of designing a rate-distortion (R-D) model for UAV video transmission, which is essential for theoretical analysis of video coding and optimization of video transmission quality, is under-studied. The designed R-D model is desired to be simple, accurate, and generic owing to the limited capability of the UAV. Observing the key role of transformed residuals in the R-D model, this paper elaborately discusses the modeling of the transformed residual distribution and proposes an estimation algorithm to estimate the statistical parameter of the distribution. Specifically, considering the stringent requirements for low complexity and high generalization capability, we first design a linear parameter estimator by mining and analyzing UAV video statistical characteristics. Further, we develop a bias update scheme to improve the accuracy of the estimator. Test results on multiple real video sequences taken by UAVs show that the proposed estimation algorithm is more accurate than benchmarks. © 2023 IEEE.

关键词： expectation maximization algorithm R-D model rate control video coding Video transmission

来源：评论

学校读者我要写书评

暂无评论

JavaBench: A Benchmark of Object-Oriented Code Generation for Evaluating Large Language Models

arXiv

引用

arXiv 2024年

作者： Cao, Jialun Chen, Zhiyong Wu, Jiarong Cheung, Shing-Chi Xu, Chang Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong Guangzhou HKUST Fok Ying Tung Research Institute Guangzhou China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China

Code generation benchmarks such as HumanEval are widely adopted to evaluate LLMs’ capabilities. However, after consolidating the latest 24 benchmarks, we noticed three significant imbalances. First, imbalanced programming language. 95.8% of benchmarks involve Python, while only 5 benchmarks involve Java, resulting in an insufficient understanding of LLMs’ capability to generate Java code. Second, imbalanced code granularity. Function-/statement-level benchmarks account for over 83.3% of benchmarks. Only a mere handful extends to class-/project-levels, and all are limited to Python. Third, lacking advanced features. Existing benchmarks primarily assess basic coding skills (e.g., variables, operators, and control structures), while overlooking advanced Object-Oriented Programming (OOP) features (i.e., encapsulation, inheritance, and polymorphism). Considering the prevalence of these advanced features in real-world Java project development, constructing benchmarks to test LLMs on handling OOP features is necessary. To fill these gaps, we propose JavaBench, a project-level Java benchmark that exercises OOP features. It comprises four Java projects with 389 methods in 106 Java classes. The test coverage is up to 92%, and JavaBench is attested by 282 undergraduate students, reaching a 90.93/100 average score (i.e., pass rate against the test suite), ensuring the quality of documentation, code skeleton, and tests. To better evaluate LLM’s capability against JavaBench, we introduce a systematic evaluation design covering three context settings and five synthesis strategies at two granularities using three hierarchical metrics. Our extensive experiment yields several interesting findings. First, we noticed that regarding project-level Java programming, LLMs are far behind undergraduate students (no project can be correctly completed by any studied LLMs, and at most 41.17% Pass@5 in a more relaxed evaluation). Second, using method signature as prompt context may strike an ide

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Hybrid Variational Autoencoder for Collaborative Filtering 25

Hybrid Variational Autoencoder for Collaborative Filtering

引用

25th IEEE International Conference on computer Supported Cooperative Work in Design, CSCWD 2022

作者： Liu, Jinxin Xiao, Yingyuan Zhu, Ke Zheng, Wenguang Hsu, Ching-Hsien Tianjin University of Technology Engineering Research Center of Learning-Based Intelligent System Ministry of Education Tianjin China Tianjin University of Technology Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin China Asia University Department of Computer Science and Information Engineering Taichung Taiwan

ISBN: (纸本)9781665405270

In recent years, Variational AutoEncoder (VAE) based methods have made many important achievements in the field of collaborative filtering recommendation system. VAE is a kind of Bayesian model which combines latent variable model with variational inference, but its optimization is often troubled by posterior collapse. By comparing the optimization process of VAE and ordinary autoencoder, we observe that the mismatch between poorly optimized encoder and decoder with too strong characterization capabilities makes it difficult to learn the mapping from the data manifold to the parameterized graph. Since the learning of a posteriori network corresponds to the encoder, we think that the problem of a posteriori collapse can be alleviated by balancing the encoder and decoder better. Therefore, we proposed Hy-VAE, which combines conventional VAE with deterministic autoencoder, and has the advantages of both VAE and deterministic autoencoder. Experiments on three real-world recommendation data sets show that our method alleviates the posterior crash problem in VAE and improves the recommendation performance. © 2022 IEEE.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Image Classification and Segmentation for Estimating Calories of Food 10

Image Classification and Segmentation for Estimating Calorie...

引用

10th International Conference on Digital Arts, Media and Technology and 8th ECTI Northern Section Conference on Electrical, Electronics, computer and Telecommunications engineering, ECTI DAMT and NCON 2025

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

ISBN: (纸本)9798331543273

Accurate estimation of calorie content in meals is essential for promoting healthy dietary practices and supporting healthcare efforts. However, the lack of nutritional knowledge poses challenges for individuals in estimating the calorie content of foods. This study aims to develop a deep learning-based model for estimating the calorie content of real foods through image classification and segmentation techniques. Image classification was employed to identify various one-dish Thai menus, while image segmentation categorized food components into fats, carbohydrates, and proteins. A new dataset, consisting of 15 one-dish Thai menus, was created using a combination of publicly available datasets (THFOOD-50 and FoodyDudy) and self-collected images. Nutritional analysis was based on the Thai nutritional table from the Bureau of Nutrition, department of Health, Ministry of Public Health. We compared the performance of YOLOv5x, YOLOv8x, and YOLOv9e on the ThaiFood dataset using identical hyperparameters. The results showed that YOLOv8x achieved the highest mAP@0.5 of 0.883, with an accuracy of 0.829 and a recall of 0.902. YOLOv5x closely followed with a mAP@0.5 of 0.881, an accuracy of 0.822, and a recall of 0.945. YOLOv9e demonstrated competitive performance, achieving a mAP@0.5 of 0.846, an accuracy of 0.775, and a recall of 0.91. These findings highlight YOLOv8x as the most suitable model for Thai food classification and detection tasks under the evaluated conditions. © 2025 IEEE.

关键词： Nutrition

来源：评论

学校读者我要写书评

暂无评论

Image Classification and Segmentation for Estimating Calories of Food

Image Classification and Segmentation for Estimating Calorie...

引用

International ECTI Northern Section Conference on Electrical, Electronics, computer and Telecommunications engineering (ECTI-NCON)

作者： Udomkan Chanthanuwatkun Anuchit Jitpattanakul Narit Hnoohom Department of Computer Engineering Image Information and Intelligence Laboratory Faculty of Engineering Mahidol University Nakhon Pathom Thailand Department of Mathematics Intelligent and Nonlinear Dynamic Innovations Research Center Faculty of Applied Science King Mongkut’s University of Technology North Bangkok Thailand

ISBN: (数字)9798331543273

ISBN: (纸本)9798331543280

关键词： Proteins Image segmentation Accuracy Estimation Fats Public healthcare Image classification

来源：评论

学校读者我要写书评

暂无评论

An Anomaly Detection System Based on Clustering and Fuzzy Set Theory in VANETs 8th

An Anomaly Detection System Based on Clustering and Fuzzy Se...

引用

8th International Workshop on Soft Computing Applications, SOFA 2018

作者： Kuchaki Rafsanjani, Marjan Fatemidokht, Hamideh Balas, Valentina Emilia Batth, Ranbir Singh Department of Computer Science Faculty of Mathematics and Computer Shahid Bahonar University of Kerman Kerman Iran Department of Applied Mathematics Young Research Society Shahid Bahonar University of Kerman Kerman Iran Department of Automatics and Applied Software Faculty of Engineering Aurel Vlaicu University of Arad Arad Romania School of Computer Science and Engineering Lovely Professional University Jalandhar India

ISBN: (纸本)9783030521899

In vehicular ad hoc network (VANET), which is considered as a type of mobile ad hoc network (MANET), communication occurs between neighbor vehicles and also roadside equipment and vehicles. Due to the characteristics of VANET, there are chances of a number possible attack in this network. In this paper, an anomaly detection system that uses clustering and fuzzy set theory to defend the Denial of Service (DoS) attack is presented. Results of simulation represent that the proposed algorithm arrives to the high detection rate. © 2021, Springer Nature Switzerland AG.

关键词： Fuzzy set theory

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to ‘Device-to-device communication in 5G heterogeneous network based on game-theoretic approaches: A comprehensive survey’ [J. Netw. Comput., Volume 238, June 2025, 104152] (Journal of Network and computer Applications (2025) 238, (S1084804525000499), (10.1016/***.2025.104152))

引用

Journal of Network and computer Applications 2025年 239卷

作者： Ahmad, Rana Zeeshan Rizwan, Muhammad Yousuf, Muhammad Jehanzaib Khan, Mohammad Bilal Almadhor, Ahmad Gadekallu, Thippa Reddy Abbas, Sidra Department of Information Technology University of Sialkot Sialkot Pakistan College of Science and Engineering University of Derby United Kingdom Software Research Institute Athlone Institute of Technology Ireland School of Electronic Engineering Xidian University Xidian China Department of Computer Engineering and Networks College of Computer and Information Science Jouf University Sakaka Saudi Arabia The College of Mathematics and Computer Science Zhejiang A&F University Hangzhou311300 China Division of Research and Development Lovely Professional University Phagwara India Centre of Research Impact and Outcome Chitkara University Institute of Engineering and Technology Chitkara University Punjab Rajpura140401 India Department of Computer Science COMSATS University Islamabad Sahiwal Pakistan

The authors regret the mistake in affiliation of Author Sidra Abbas. The correct affiliation is as follows: Sidra Abbasdepartment of computer science, COMSATS University Islamabad, Sahiwal, Pakistansidraabbas@***:sidr...

关键词：

来源：评论

学校读者我要写书评

暂无评论

Atomistic Behavior of Deformed Au Thin Film during the Indentation Process 4

Atomistic Behavior of Deformed Au Thin Film during the Inden...

引用

4th International Conference on Innovative research in Applied science, engineering and Technology, IRASET 2024

作者： Ou-Khouya, Abdelkarim Mes-Adi, Hassane Taoufiki, Meryem Ibrahim, Imane Ait El Harfouf, Amin Herbazi, Rachid Tahiri, Mohamed Khouribga National School Of Applied Sciences Sultan Moulay Slimane University Process Engineering Computer Science And Mathematics Laboratory Khouribga25000 Morocco Sultan Moulay Slimane University Faculty Of Sciences And Techniques Sustainable Development Laboratory Beni-Mellal Morocco Mohamed V University Laboratory Of Condensed Matter And Interdisciplinary Sciences Cnrst Labeled Research Unit Faculty Of Sciences Departement Of Physics Rabat Morocco University Of Sultan Moulay Slimane Polydisciplinary Faculty Of Khouribga Department Of Physics Khouribga Morocco Tangier Morocco

ISBN: (纸本)9798350309508

In this study, we investigate the mechanical properties of gold (Au) materials using molecular dynamics simulations. In this simulation, the nanoindentation process was performed to analyze the deformation defects and hardness properties of Au under different indentation velocities. The results suggest that the deformation behavior of the Au specimen was affected by different indentation velocities. These findings were confirmed by examining the load-displacement curve, which indicated elastic deformation through the appearance of a linear load-displacement relationship at low indentation velocities. In contrast, plastic deformation was identified by the presence of intensified serrations in the load-displacement curve at higher indentation velocities. Under such conditions, the hardness exhibited minimal variation when the indenter velocity increased from 5 mls to 10 mls. However, a significant increase in hardness was noted when the indentation velocity was further raised to 15 mls. © 2024 IEEE.

关键词： Molecular dynamics

来源：评论

学校读者我要写书评

暂无评论

Optimising Event-Driven Spiking Neural Network with Regularisation and Cutoff

arXiv

引用

arXiv 2023年

作者： Wu, Dengyu Jin, Gaojie Yu, Han Yi, Xinping Huang, Xiaowei Department of Computer Science University of Liverpool Liverpool United Kingdom National Mobile Communications Research Laboratory Southeast University Nanjing China State Key Laboratory of Computer Science Institute of Software CAS Beijing China Department of Electrical Engineering Chalmers University of Technology Gothenburg Sweden

Spiking neural network (SNN), as the next generation of artificial neural network (ANN), offer a closer mimicry of natural neural networks and hold promise for significant improvements in computational efficiency. However, the current SNN is trained to infer over a fixed duration, overlooking the potential of dynamic inference in SNN. In this paper, we strengthen the marriage between SNN and event-driven processing with a proposal to consider a cutoff in SNN, which can terminate SNN anytime during inference to achieve efficient inference. Two novel optimisation techniques are presented to achieve inference efficient SNN: a Top-K cutoff and a regularisation. The proposed regularisation influences the training process, optimising SNN for the cutoff, while the Top-K cutoff technique optimises the inference phase. We conduct an extensive set of experiments on multiple benchmark frame-based datasets, such as CIFAR10/100, Tiny-ImageNet, and event-based datasets, including CIFAR10-DVS, N-Caltech101 and DVS128 Gesture. The experimental results demonstrate the effectiveness of our techniques in both ANN-to-SNN conversion and direct training, enabling SNNs to require 1.76 to 2.76 × fewer timesteps for CIFAR-10, while achieving 1.64 to 1.95× fewer timesteps across all event-based datasets, with near-zero accuracy loss. These findings affirms the compatibility and potential benefits of our techniques in enhancing accuracy and reducing inference latency when integrated with existing methods. Code available: https://***/Dengyu-Wu/SNNCutoff © 2023, CC BY.

关键词： Computational efficiency

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：