检索结果-内蒙古大学图书馆

7th IEEE Advanced Information technology, Electronic and Automation Control Conference, IAEAC 2024

作者： Lv, Zhenhuai Beijing University of Technology Beijing Engineering Research Center for IoT Software and Systems Beijing China

ISBN: (纸本)9798350339161

As an important problem in the field of computer vision, facial expression recognition has been widely used in many fields such as human-computer interaction and emotion recognition. This paper proposes a dual-branch parallel facial expression recognition network that integrates Convolutional Neural Network (CNN) and Transformer. By consolidating local and global information obtained from the dual branches, the network effectively combines subtle local variations and overall contextual features of facial expressions. The fused feature representation demonstrates enhanced representativeness and discriminative power, leading to a notable improvement in facial expression recognition accuracy. In addressing the challenges posed by inter-class similarity and annotation ambiguity, the Erasing Attention Consistency (EAC) mechanism is employed. This mechanism effectively prevents the model from memorizing noisy samples, thereby enhancing robustness against noisy labels. Additionally, the focal loss function is utilized to rectify imbalances within data samples. Experiments conducted on RAF-DB datasets with labels containing noise reveal that the proposed methodology achieves accuracies of 87.65% and 86.05% at 10% and 20% noise rate, respectively. This substantiates the effectiveness of the proposed approach. © 2024 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Energy-efficient and Latency-optimal Task Offloading Strategies for Multi-user in Edge Computing 7

Energy-efficient and Latency-optimal Task Offloading Strateg...

引用

7th IEEE Advanced Information technology, Electronic and Automation Control Conference, IAEAC 2024

作者： Zhang, Xiaobo Huang, Zhangqin Yang, Huapeng Huang, Ling Beijing University of Technology Beijing Engineering Research Center for IoT Software and Systems Beijing China

ISBN: (纸本)9798350339161

Compute-intensive and latency-sensitive applications place stringent demands on mobile devices in terms of computational power and task latency. Edge computing is a promising technique to alleviate the computational constraints of mobile terminals and reduce their energy consumption through computation offloading. This paper proposes a two-tier task offloading framework for multi-user multi-server edge IoT scenarios, comprehensively considering factors such as task offloading decision, network channel allocation, edge server computational resources, device transmission power, and the size of the task offloading data volume, and constructing a multi-user task offloading Optimization problem model. In the process of solving the optimization problem, a Combining GA and PSO Computation offloading Algorithm (CGPCA) is proposed for solving the model. Finally, the convergence of the algorithm is verified through simulation experiments, and the experimental results show that the proposed algorithm in this study can effectively reduce the task offloading delay and energy consumption, and improve the quality of end-user service compared with other existing algorithms. © 2024 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Resource Allocation Strategies for Cloud-Edge-End Collaboration in Heterogeneous Edge Computing 7

Resource Allocation Strategies for Cloud-Edge-End Collaborat...

引用

7th World Conference on Computing and Communication Technologies, WCCCT 2024

作者： Zhang, Xiaobo Huang, Zhangqin Huang, Ling Yang, Huapeng Beijing University of Technology Beijing Engineering Research Center for IoT Software and Systems Beijing China

ISBN: (纸本)9798350372328

With the continuous innovation of information technology, the Internet of Everything (IoE) is gradually being realized, and more IoT application scenarios have increasingly urgent requirements for high-performance computing and low-latency response. To address the bottleneck of insufficient computing power and energy constraints of terminal devices, edge computing can effectively enhance the task processing capability of terminal devices and improve service quality. However, existing edge computing network architectures, which often provide a single edge server computing capability based on terrestrial networks, cannot meet the task offloading requirements of terminal devices in ubiquitous network environments. This paper designs a cloud-edge-end collaboration space-air-ground integration multi-layer edge computing network architecture (CEEC-SAGIN), and based on this architecture, a heterogeneous network system of terminal devices, multi-layer edge computing services and cloud computing services are constructed. Then, a task processing model is constructed with the optimization objective of minimizing the task processing delay of the system, taking into account the task offloading ratio, computational resources and transmission resources involved in the task processing process of the terminal devices of the system. Further, a multi-layer task offloading and resource allocation algorithm (MTORA) is proposed to realize the optimal allocation of resources in system task processing. Finally, simulation experiments show that the CEEC-AGIN architecture proposed in this paper can meet the requirements of more applications, and the proposed model can improve the system task processing efficiency by up to roughly 15% and reduce the system task processing latency by up to approximately 10% compared with other resource allocation strategies. © 2024 IEEE.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Understanding interfacial engineering of surface functionalized boron nitride nanosheets within thermal interface materials

引用

Science China Materials 2025年第4期68卷 1300-1302页

作者： Gaojie Han Yuezhan Fengg Changyu Shen State Key Laboratory of Structural Analysis Optimization and CAE Software for Industrial EquipmentNational Engineering Research Center for Advanced Polymer Processing TechnologyZhengzhou UniversityZhengzhou 450002China

The continuous miniaturization and high-power development of electronic devices have given rise to severe interface thermal issues,which urgently demand highly thermally conductive thermal interface materials(TIMs)to ... 详细信息

关键词： interfacial engineering heat accumulation interface thermal issueswhich thermal interface materials surface functionalized boron nitride nanosheets electronic devices thermal conductivity

来源：评论

学校读者我要写书评

暂无评论

Effect of boundary conditions on shakedown analysis of heterogeneous materials

引用

Applied Mathematics and Mechanics(English Edition) 2024年第1期45卷 39-68页

作者： Xiuchen GONG Yinghao NIE Gengdong CHENG Kai LI State Key Laboratory of Structural Analysis Optimization and CAE Software for Industrial EquipmentInternational Research Center for Computational MechanicsDepartment of Engineering MechanicsDalian University of TechnologyDalian 116023Liaoning ProvinceChina

The determination of the ultimate load-bearing capacity of structures made of elastoplastic heterogeneous materials under varying loads is of great importance for engineering analysis and design. Therefore, it is necessary to accurately predict the shakedown domains of these materials. The static shakedown theorem, also known as Melan's theorem, is a fundamental method used to predict the shakedown domains of structures and materials. Within this method, a key aspect lies in the construction and application of an appropriate self-equilibrium stress field(SSF). In the structural shakedown analysis, the SSF is typically constructed by governing equations that satisfy no external force(NEF) boundary conditions. However, we discover that directly applying these governing equations is not suitable for the shakedown analysis of heterogeneous materials. researchers must consider the requirements imposed by the Hill-Mandel condition for boundary conditions and the physical significance of representative volume elements(RVEs). This paper addresses this issue and demonstrates that the sizes of SSFs vary under different boundary conditions, such as uniform displacement boundary conditions(DBCs), uniform traction boundary conditions(TBCs), and periodic boundary conditions(PBCs). As a result, significant discrepancies arise in the predicted shakedown domain sizes of heterogeneous materials. Built on the demonstrated relationship between SSFs under different boundary conditions, this study explores the conservative relationships among different shakedown domains, and provides proof of the relationship between the elastic limit(EL) factors and the shakedown loading factors under the loading domain of two load vertices. By utilizing numerical examples, we highlight the conservatism present in certain results reported in the existing literature. Among the investigated boundary conditions, the obtained shakedown domain is the most conservative under ***, utilizing PBCs to

关键词： heterogeneous material self-equilibrium stress field(SSF) shakedown analysis effect of boundary conditions

来源：评论

学校读者我要写书评

暂无评论

Multilayer Perceptron (MLP)-based Path Loss Prediction Modeling for LoRa Signals 4

Multilayer Perceptron (MLP)-based Path Loss Prediction Model...

引用

4th International Conference on Artificial Intelligence, Robotics, and Communication, ICAIRC 2024

作者： Jiang, Fan Huang, Zhangqin Huang, Ling Yan, Huangyi Beijing University of Technology Beijing Engineering Research Center for IoT Software and Systems Beijing China

ISBN: (纸本)9798331531225

With the rapid development of Internet of Things (IoT) technology, Low Power Wide Area Network (LPWAN) has become a key enabler for connecting large-scale devices. LoRa technology plays a pivotal role in IoT due to its excellent anti-interference ability and long-range transmission capabilities. However, environmental factors, terrain, and building occlusion significantly impact the propagation and loss of path of LoRa signals, which in turn affect network coverage and communication quality. Therefore, accurately predicting the path loss of LoRa signals is crucial for effective network optimization and troubleshooting. In this study, we propose a path loss prediction model based on a multilayer perceptron (MLP), integrating the Okumura model path loss as a reference feature and comparing it with traditional empirical models. The experimental results demonstrate that the MLP model effectively learns complex nonlinear relationships, improving the accuracy of prediction. Through 10-fold cross-validation and testing various neuron configurations, it is found that the MLP model with 20 neurons (MLP20) performs best, yielding the lowest root mean square error (RMSE). Compared to the traditional Okumura Hata model, the MLP model shows significant advantages in prediction accuracy and stability. This study not only takes advantage of the theoretical strengths of the Okumura model but also enhances the adaptability to complex environmental factors through MLP, providing a new solution for LoRa network optimization. © 2024 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Transaction transmission model for blockchain channels based on non-cooperative games

引用

Science China(Information Sciences) 2023年第1期66卷 97-114页

作者： Peiyun ZHANG Chenxi LI Mengchu ZHOU Wenjun HUANG Abdullah ABUSORRAH Omaimah O.BAMASAG Engineering Research Center of Digital Forensics of Ministry of Education School of Computer and SoftwareNanjing University of Information Science and Technology School of Computer and Information Anhui Normal University Department of Electrical and Computer Engineering New Jersey Institute of Technology Center of Research Excellence in Renewable Energy and Power Systems Department of Electrical and Computer Engineering Faculty of Engineering and K.A.CARE Energy Research and Innovation CenterKing Abdulaziz University Department of Computer Science Faculty of Computing and Information Technology Center of Excellence in Smart Environment Research King Abdulaziz University

In blockchain networks, transactions can be transmitted through channels. The existing transmission methods depend on their routing information. If a node randomly chooses a channel to transmit a transaction, the transmission may be aborted due to insufficient funds(also called balance) or a low transmission rate. To increase the success rate and reduce transmission delay across all transactions, this work proposes a transaction transmission model for blockchain channels based on non-cooperative game *** balance, channel states, and transmission probability are fully considered. This work then presents an optimized channel transaction transmission algorithm. First, channel balances are analyzed and suitable channels are selected if their balance is sufficient. Second, a Nash equilibrium point is found by using an iterative sub-gradient method and its related channels are then used to transmit transactions. The proposed method is compared with two state-of-the-art approaches: Silent Whispers and Speedy Murmurs. Experimental results show that the proposed method improves transmission success rate, reduces transmission delay,and effectively decreases transmission overhead in comparison with its two competitive peers.

关键词： Blockchain channel transaction transmission channel balance channel state channel transmission probability non-cooperative game

来源：评论

学校读者我要写书评

暂无评论

Personality Enhanced Emotion Generation Modeling for Dialogue Systems

引用

COGNITIVE COMPUTATION 2024年第1期16卷 293-304页

作者： Liu, Zhiqiang Jia, Wenchao Zhou, Yutong Xu, Biqi Liu, Zhiqiang Wu, Zhuoyi College of Data Science and Application Inner Mongolia University of Technology Hohhot 010080 Inner Mongolia China Inner Mongolia Autonomous Region Engineering & Technology Research Centre of Big Data Based Software Service Hohhot 010080 Inner Mongolia China

Emotion plays a crucial role in human communication, as it adds depth and richness to conversations. In recent years, there has been growing interest in developing conversation systems with the ability to generate emotions. However, to create more engaging and realistic interactions, it is essential to consider the influence of personality on emotion generation. This paper proposes a novel approach that combines personality modeling with emotion generation for conversation systems. By incorporating personality traits into the emotion generation process, we aim to create more personalized and contextually appropriate emotional responses. Drawing from BigFive model and emotion computation techniques, our model takes into account individual differences in personality to generate emotions that align with each user's unique characteristics. Experiments show that combining emotion modeling with personality in a dialogue system helps improve the performance of emotion generation models. Additionally, it is also verified that our approach outperforms other baselines on several metrics.

关键词： Dialogue system Emotion generation Personality Anthropomorphism

来源：评论

学校读者我要写书评

暂无评论

Polyzwitterionic cross-linked double network hydrogel electrolyte enabling high-stable Zn anode

引用

Nano research 2024年第6期17卷 5278-5287页

作者： Mengyu Shi Junlong Zhang Guochuan Tang Ben Wang Sen Wang Xiaoxian Ren Guojie Li Weihua Chen Chuntai Liu Changyu Shen State Key Laboratory of Structural Analysis Optimization and CAE Software for Industrial EquipmentNational Engineering Research Center for Advanced Polymer Processing TechnologyZhengzhou UniversityZhengzhou 450002China College of Chemistry and Green Catalysis Center Zhengzhou UniversityZhengzhou 450001China Research Institute of Interdisciplinary Science and School of Materials Science and Engineering Dongguan University of TechnologyDongguan 523808China

Zn metal anode suffers from dendrite issues and passive byproducts,which severely plagues the practical application of aqueous Zn metal ***,a polyzwitterionic cross-linked double network hydrogel electrolyte composed of physical crosslinking(hyaluronic acid)and chemical crosslinking(synthetic zwitterionic monomer copolymerized with acrylamide)is introduced to overcome these *** the one hand,highly hydrophilic physical network provides an energy dissipation channel to buffer stress and builds a H_(2)O-poor interface to avoid side *** the other hand,the charged groups(sulfonic and imidazolyl)in chemical crosslinking structure build anion/cation transport channels to boost ions’kinetics migration and regulate the typical solvent structure[Zn(H_(2)O)_(6)]^(2+)to R-SO_(3)^(−)[Zn(H_(2)O)_(4)]^(2+),with uniform electric field distribution and significant resistance to dendrites and parasitic *** on the above functions,the symmetric zinc cell exhibits superior cycle stability for more than 420 h at a high current density of 5 mA·cm^(−2),and Zn||MnO_(2)full cell has a reversible specific capacity of 150 mAh·g^(−1)after 1000 cycles at 2 C with this hydrogel ***,the pouch cell delivers impressive flexibility and cyclability for energy-storage applications.

关键词： Zn anode dendrites parasitic reactions polyzwitterion double network hydrogel electrolyte

来源：评论

学校读者我要写书评

暂无评论

Dlpp-Net: Degradation Location Prior Prediction Network for Image Restoration 6

Dlpp-Net: Degradation Location Prior Prediction Network for ...

引用

6th ACM International Conference on Multimedia in Asia, MMAsia 2024

作者： Liu, Yongjian Zhang, Shunwei Xu, Jinyu Li, Jiachen Ma, Yanchun Xie, Qing Wuhan University of Technology Wuhan China Engineering Research Center of Intelligent Service Technology for Digital Publishing Ministry of Education Wuhan China Wuhan Vocational College of Software and Engineering Wuhan China Hubei Engineering Research Center for Intelligent Detection and Identification of Complex Parts Wuhan China

ISBN: (纸本)9798400712739

Image restoration aims to reconstruct the latent high-quality image by removing its degradation factors. Despite the promising performance achieved by previous traditional models and deep learning-based methods, the explicit use of degradation location information within the corrupted input has been overlooked, limiting their ability to effectively target and restore degraded regions. To this end, we propose a degradation location prior prediction network (Dlpp-Net), its degradation prior prediction module (DPPM) can capture prior information about degraded regions using a recurrent architecture. To further improve the validity of this prior information, we develop a prior modulation module (PMM) that enhances the network's focus on degraded areas and delivers more valuable reference information. Comprehensive experiments demonstrate that our Dlpp-Net performs competitively against state-of-the-art algorithms on 7 datasets across 3 image restoration tasks, including image desnowing, image deraining, and image motion deblurring. © 2024 Copyright held by the owner/author(s).

关键词： Restoration

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：