检索结果-内蒙古大学图书馆

Combined CNN LSTM with attention for speech emotion recognition based on feature-level fusion

Multimedia Tools and applications 2024年第21期83卷 59839-59859页

作者： Liu, Yanlin Chen, Aibin Zhou, Guoxiong Yi, Jizheng Xiang, Jin Wang, Yaru Institute of Artificial Intelligence Application College of Computer and Information Engineering Central South University of Forestry and Technology Hunan Changsha410004 China Hunan Key Laboratory of Intelligent Logistics Technology Central South University of Forestry and Technology Hunan Changsha410004 China

According to the problem that emotional features cannot be well represented by a single feature and it is difficult to extract in the task of Speech Emotion Recognition (SER), we propose a Feature-Level (FL) fusion method for 9 types of acoustic features and a combined CNN-LSTM network with attention (CNN-A-LSTM). The feature vector set after feature-level fusion is used as the input of CNN-A-LSTM network, which contains prosodic features and spectral features. High-level Statistical Functions (HSFs) are also added to receive global features. The feature extraction network CNN-A-LSTM can more effectively read time-series input and extract speech emotion information. Finally, Softmax is applied as a classifier to obtain the final emotion classification results. The experiment is verified on SAVEE and CASIA datasets. The experimental results show that the method in this paper has the best effect compared with the state-of-the-art, and the accuracy rates of 94.5% and 96.7% are respectively gained on SAVEE and CASIA. The above results prove the effectiveness of the algorithm in this paper with some generalization. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2023.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Cross-Guided Attention and Combined Loss for Optimizing Gastrointestinal Visual Question Answering

Cross-Guided Attention and Combined Loss for Optimizing Gast...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Yang, Qian Liu, Lijun Yang, Xiaobing Liu, Li Peng, Wei Kunming University of Science and Technology Faculty of Information Engineering and Automation Kunming650500 China Yunnan Key Laboratory of Computer Technology Application Kunming650500 China

ISBN: (纸本)9798350386226

Medical Visual Question Answering (Med-VQA) aims at answering clinical questions related to medical imaging, providing important reference for medical imaging diagnosis. Gastrointestinal visual question answering can deeply understand and analyze gastrointestinal medical images, provides supporting information to answer questions about the diagnostic process, and improves diagnostic accuracy and efficiency. However, most existing Med-VQA can only handle simple and general questions, struggling to tackle visual question answering related to complex diseases. Therefore, this paper proposes a Med-VQA model called CACL, which uses cross-guidance and improved combined loss. The model focuses on gastrointestinal image analysis and achieves efficient and accurate feature extraction for gastrointestinal images. A cross-guided attention module is also designed to enhance the model's reasoning ability when dealing with complex cross-modal tasks. In addition, a multi-task composite loss function is designed to balance the loss of segmentation task and classification task, and improve the overall performance. Experimental results show that the proposed method can effectively improve the accuracy of gastrointestinal visual question answering. © 2024 IEEE.

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

Communication Countermeasure Strategy Decision-Making Based on Incomplete Information Game 27

Communication Countermeasure Strategy Decision-Making Based ...

引用

27th International Conference on Advanced Communications technology, ICACT 2025

作者： Liu, Jinyue Gao, Xiang Yang, Haowei Zhang, Jihao Liu, Yuhan Gong, Peng National Key Laboratory of Mechatronic Engineering and Control School of Mechatronical Engineering Beijing Institute of Technology Beijing China Institute of Computer Application Technology Norinco Group Beijing China

ISBN: (纸本)9791188428137

In modern battlefields, the stability of wireless communications is crucial for intelligence transmission, command coordination, and maintaining strategic advantage. However, with the rapid advancement of communication technologies, the electromagnetic environment has become increasingly complex, making intelligent decision-making in communication countermeasures a prominent research focus. However, most existing studies adopt deep learning and reinforcement learning methods, which require extensive data samples and computational resources. To address these limitations, this paper proposes a game-theoretic model for intelligent radio communication countermeasures under incomplete information. It quantitatively evaluates common attack and defense tactcis used in communication countermeasures and explores the mixed-strategy equilibrium of the game when both the attackers and defenders consist of multiple types. Furthermore, simulation-based comparative analyses are conducted to assess the factors influencing the utility of both the attacker and defender. The findings offer theoretical insights and decision-making support for the deployment of communication countermeasure strategies in practical military operations, contributing to significant strategic value. © 2025 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Surface flashover in 50 years:Theoretical models and competing mechanisms

引用

High Voltage 2023年第5期8卷 853-877页

作者： Zhen Li Ji Liu Yoshimichi Ohki George Chen He Gao Shengtao Li Key Laboratory of Engineering Dielectrics and Its Application Ministry of EducationHarbin University of Science and TechnologyHarbinChina State Key Laboratory of Electrical Insulation and Power Equipment Xi'an Jiaotong UniversityXi'anChina Research Institute for Materials Science and Technology Waseda UniversityShinjuku‐kuJapan School of Electronics and Computer Science University of SouthamptonSouthamptonUK

Surface flashover is a devastating electronic avalanche along the gas–solid interface when a high electric field is applied,which is a potential issue that threatens the safe operations of advanced power electronic,electrical,and spacecraft ***,the underlying physical mechanisms for surface flashover development are still under investigation owing to the complex charge transport processes through the gas phase,solid phase,and gas–solid *** this study,the history of surface flashover theory in the last 50 years is introduced,and several key questions are reviewed from the perspective of the competing mechanisms of charge transport:the role of each phase in a surface flashover,the origin of surface charging,and effects of traps in solid on surface ***,some suggestions involve charge transport processes in each phase,and their correlations are put forward,and a predictable‘charge transport competitive flashover model’is proposed by clarifying the competing mechanisms of charge transport processes through multiple *** study summarises the history and hot topics of physical mechanisms of surface flashover proposed based on classic and recent progress and offers promising routes for developing a more precise surface flashover theory and improving surface flashover performances.

关键词： flash transport charge

来源：评论

学校读者我要写书评

暂无评论

A Blind Batch Encryption and Public Ledger-Based Protocol for Sharing Sensitive Data

引用

China Communications 2024年第1期21卷 310-322页

作者： Zhiwei Wang Nianhua Yang Qingqing Chen Wei Shen Zhiying Zhang School of Computer Sciences Nanjing University of Posts and TelecommunicationsNanjing 210023China Dept.of Intelligent Science and Information Law East China University of Political Science and LawShanghai 201620China Key Laboratory of Computational Science and Application of Hainan Province Hainan Normal UniversityHaikou 571158China State Key Laboratory of Public Big Data Guizhou UniversityGuizhou 550025China Yunnan Key Laboratory of Blockchain Application Technology Yunnan Innovation Research Institute of Beijing University of Aeronautics and AstronauticsKunming 650233

For the goals of security and privacy preservation,we propose a blind batch encryption-and public ledger-based data sharing protocol that allows the integrity of sensitive data to be audited by a public ledger and allows privacy information to be *** owners can tightly manage their data with efficient revocation and only grant one-time adaptive access for the fulfillment of the *** prove that our protocol is semanticallly secure,blind,and secure against oblivious requesters and malicious file *** also provide security analysis in the context of four typical attacks.

关键词： blind batch encryption data sharing onetime adaptive access public ledger security and privacy

来源：评论

学校读者我要写书评

暂无评论

StoryLLaVA: Enhancing Visual Storytelling with Multi-Modal Large Language Models 31

StoryLLaVA: Enhancing Visual Storytelling with Multi-Modal L...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Yang, Li Xiao, Zhiding Huang, Wenxin Zhong, Xian Hubei Key Laboratory of Big Data Intelligent Analysis and Application School of Computer Science and Information Engineering Hubei University China Hubei Key Laboratory of Transportation Internet of Things School of Computer Science and Artificial Intelligence Wuhan University of Technology China

ISBN: (纸本)9798891761964

The rapid development of multi-modal large language models (MLLMs) has positioned visual storytelling as a crucial area in content creation. However, existing models often struggle to maintain temporal, spatial, and narrative coherence across image sequences and frequently lack the depth and engagement of human-authored stories. To address these challenges, we propose Story with Large Language and Vision Assistant (StoryLLaVA), a novel framework for enhancing visual storytelling. Our approach introduces a Topic-Driven Narrative Optimizer (TDNO) that improves both the training data and MLLM models by integrating image descriptions, topic generation, and GPT-4-based refinements. Furthermore, we employ a preference-based ranked story sampling method that aligns model outputs with human storytelling preferences through positive-negative pairing. These two phases of the framework differ in their training methods: the former uses supervised fine-tuning, while the latter incorporates reinforcement learning with positive and negative sample pairs. Experimental results demonstrate that StoryLLaVA outperforms current models in visual relevance, coherence, and fluency, with LLM-based evaluations confirming the generation of richer and more engaging narratives. The enhanced dataset and model are available at https://***/XxxZzD/StoryLLaVA. © 2025 Association for Computational Linguistics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EPRFL:An Efficient Privacy-Preserving and Robust Federated Learning Scheme for Fog Computing

引用

China Communications 2025年第4期22卷 202-222页

作者： Ke Zhijie Xie Yong Syed Hamad Shirazi Li Haifeng School of Computer Technology and Application Qinghai UniversityXining 810016China School of Computer and Information Science Qinghai Institute of TechnologyXining 810016China Guangdong Key Laboratory of Blockchain Security Guangzhou UniversityGuangzhou 510006China Department of Information Technology Hazara UniversityBaffa 21110Pakistan Qinghai Provincial Key Laboratory of Big Data in Finance and Artificial Intelligence Application Technology Xining 810016China

Federated learning(FL)is a distributed machine learning paradigm that excels at preserving data privacy when using data from multiple *** combined with Fog Computing,FL offers enhanced capabilities for machine learning applications in the Internet of Things(IoT).However,implementing FL across large-scale distributed fog networks presents significant challenges in maintaining privacy,preventing collusion attacks,and ensuring robust data *** address these challenges,we propose an Efficient Privacy-preserving and Robust Federated Learning(EPRFL)scheme for fog computing ***,we first propose an efficient secure aggregation strategy based on the improved threshold homomorphic encryption algorithm,which is not only resistant to model inference and collusion attacks,but also robust to fog node ***,we design a dynamic gradient filtering method based on cosine similarity to further reduce the communication *** minimize training delays,we develop a dynamic task scheduling strategy based on comprehensive *** analysis demonstrates that EPRFL offers robust security and low *** experimental results indicate that EPRFL outperforms similar strategies in terms of privacy preserving,model performance,and resource efficiency.

关键词： federated learning fog computing internet of things privacy-preserving robustness

来源：评论

学校读者我要写书评

暂无评论

Research on Environmental Perception Based on YOLOv8 and LiDAR Data Fusion 4

Research on Environmental Perception Based on YOLOv8 and LiD...

引用

4th IEEE International Conference on Information technology, Big Data and Artificial Intelligence, ICIBA 2024

作者： Luo, ZhenHong Li, HuiLing Li, Ting Liu, Jie Guangxi Vocational Normal University School of Computer and Information Engineering Nanning China Key Laboratory of Application Technology of Intelligent Connected Vehicle Nanning China

ISBN: (纸本)9798350363586

To enhance the sensing capability of driverless cars in complex dynamic scenarios, a fusion method of radar and depth camera is emphasized and a technical framework for integrating multi-source sensors is proposed. A YOLOv8 neural network detection model combined with a self-attention network structure is first used to achieve correct recognition and depth estimation of vehicles and pedestrians, then further distance data of dynamic environment is acquired by M10P LiDAR, and finally information from D435i camera and radar information are fused by matrix projection. In the experiments, the conventional YOLOv8 model was compared to the YOLOv8 model enhanced with self-attention, the camera and LIDAR measurements were evaluated against the fusion results. The experimental results demonstrate that the new model significantly improves the confidence and stability of target detection, while the fused distance measurements are more accurate than those from individual sensors. © 2024 IEEE.

关键词： Sensor data fusion

来源：评论

学校读者我要写书评

暂无评论

Research on Model Predictive Control-Based Feedback Strategies for Autonomous Driving 6

Research on Model Predictive Control-Based Feedback Strategi...

引用

6th IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference, IMCEC 2024

作者： Li, Ting Xu, Xianxia Liu, Xuejuan Liu, Jie Guangxi Vocational Normal University School of Computer and Information Engineering Nanning China Key Laboratory of Application Technology of Intelligent Connected Vehicle Nanning China

ISBN: (纸本)9798350316520

To address the issues of control stability and safety in autonomous vehicles, this study focuses on research related to Model Predictive Control (MPC) algorithms and algorithm optimization. By leveraging MPC control algorithms and system dynamics techniques, we have achieved stable autonomous driving. Simulation experiments based on Model Predictive Control have been conducted to validate the feasibility and effectiveness of MPC algorithms for feedback control in autonomous driving. Two distinct simulation scenarios have been designed to verify the MPC algorithm's performance under different road conditions. The results indicate that the MPC algorithm effectively enhances the control stability and safety of autonomous driving vehicles. © 2024 IEEE.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

Accelerating local SGD for non-IID data using variance reduction

引用

Frontiers of computer Science 2023年第2期17卷 73-89页

作者： Xianfeng LIANG Shuheng SHEN Enhong CHEN Jinchang LIU Qi LIU Yifei CHENG Zhen PAN Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of ChinaHefei 230027China Ant Financial Services Group Hangzhou 310000China Department of Computer Science and Engineering Hong Kong University of Science and TechnologyHong Kong 999077China

Distributed stochastic gradient descent and its variants have been widely adopted in the training of machine learning models,which apply multiple workers in *** them,local-based algorithms,including Local SGD and FedAvg,have gained much attention due to their superior properties,such as low communication cost and ***,when the data distribution on workers is non-identical,local-based algorithms would encounter a significant degradation in the convergence *** this paper,we propose Variance Reduced Local SGD(VRL-SGD)to deal with the heterogeneous *** extra communication cost,VRL-SGD can reduce the gradient variance among workers caused by the heterogeneous data,and thus it prevents local-based algorithms from slow convergence ***,we present VRL-SGD-W with an effectivewarm-up mechanism for the scenarios,where the data among workers are quite *** from eliminating the impact of such heterogeneous data,we theoretically prove that VRL-SGD achieves a linear iteration speedup with lower communication complexity even if workers access non-identical *** conduct experiments on three machine learning *** experimental results demonstrate that VRL-SGD performs impressively better than Local SGD for the heterogeneous data and VRL-SGD-W is much robust under high data variance among workers.

关键词： distributed optimization variance reduction local SGD federated learning non-IID data

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：