检索结果-内蒙古大学图书馆

IEEE International Symposium on Information (IT) in Medicine and Education, ITME

作者： Xianpiao Tang Pengyun Hu Dewei Yu Daoxun Xia School of Big Data and Computer Science Guizhou Normal University Guiyang China Guizhou Key Laboratory of Information and Computing Science Guizhou Normal University Guiyang China Engineering Laboratory for Applied Technology of Big Data in Education Guizhou Normal University Guiyang China

Facial expression recognition is the ability to interpret human feelings from facial features. Teachers can use it to visualize the state of emotion and estimate students' learning effects to take corresponding intervention strategies to improve teaching. The current technology has shortcomings such as network performance degradation and feature information loss, which cannot meet the needs of sentiment analysis of student feedback. Therefore, RFMNet, a novel network model based on deep learning theory, is proposed in this paper. Featuring higher extraction ability, it is conducive to accurately analysing students' expressions. First of all, this model introduces a relation-aware global attention (RGA) module to better integrate the more discriminative expression features in the image and achieve more refined sentiment analysis. Second, the Mish activation function and the focal loss function are employed. The Mish activation function is introduced to avoid disappearing feature information due to neuron deactivation when the ReLU gradient is 0. The model achieves an average recognition accuracy of 89.62%, as confirmed through a sequence of trials conducted on the public dataset FERPlus. The model helps achieve intelligent processing of teaching information and obtaining real-time feedback by detecting, extracting, and analysing the students' facial expressions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ReMax: a simple, effective, and efficient reinforcement learning method for aligning large language models 24

ReMax: a simple, effective, and efficient reinforcement lear...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Ziniu Li Tian Xu Yushun Zhang Zhihang Lin Yang Yu Ruoyu Sun Zhi-Quan Luo School of Data Science The Chinese University of Hong Kong Shenzhen and Shenzhen Research Institute of Big Data National Key Laboratory for Novel Software Technology Nanjing University and Polixir.ai School of Data Science The Chinese University of Hong Kong Shenzhen National Key Laboratory for Novel Software Technology Nanjing University and Polixir.ai and Pazhou Laboratory Huangpu School of Data Science The Chinese University of Hong Kong Shenzhen and China Shenzhen International Center For Industrial and Applied Mathematics and Shenzhen Research Institute of Big Data

Reinforcement Learning from Human Feedback (RLHF) is key to aligning Large Language Models (LLMs), typically paired with the Proximal Policy Optimization (PPO) algorithm. While PPO is a powerful method designed for general reinforcement learning tasks, it is overly sophisticated for LLMs, leading to laborious hyper-parameter tuning and significant computation burdens. To make RLHF efficient, we present ReMax, which leverages 3 properties of RLHF: fast simulation, deterministic transitions, and trajectory-level rewards. These properties are not exploited in PPO, making it less suitable for RLHF. Building on the renowned REINFORCE algorithm, ReMax does not require training an additional value model as in PPO and is further enhanced with a new variance reduction technique. ReMax offers several benefits over PPO: it is simpler to implement, eliminates more than 4 hyper-parameters in PPO, reduces GPU memory usage, and shortens training time. ReMax can save about 46% GPU memory than PPO when training a 7B model and enables training on A800-80GB GPUs without the memory-saving offloading technique needed by PPO. Applying ReMax to a Mistral-7B model resulted in a 94.78% win rate on the AlpacaEval leaderboard and a 7.739 score on MT-bench, setting a new SOTA for open-source 7B models. These results show the effectiveness of ReMax while addressing the limitations of PPO in LLMs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning Self-Supervised Vision Transformers from Scratch for Aerial Person Re- Identification

Learning Self-Supervised Vision Transformers from Scratch fo...

引用

IEEE International Symposium on Information (IT) in Medicine and Education, ITME

作者： Houfu Peng Lili Xu Xing Lu Daoxun Xia School of Big Data and Computer Science Guizhou Normal University Guiyang China Guizhou Key Laboratory of Information and Computing Science Guizhou Normal University Guiyang China Engineering Laboratory for Applied Technology of Big Data in Education Guizhou Normal University Guiyang China

In recent years, person re-identification (Re-ID) as a widely studied computer vision task, has reached a saturation state under closed-world setting, which encourages researchers to further explore more realistic scenarios. Among them, person Re- Idin aerial imagery is proposed and improved due to its unique practical importance in public security. However, since the aerial person images are taken by unmanned aerial vehicles (UAV s), influenced by camera height and angle of view, there are more serious problems such as weak appearance feature and occlusion than ground person images. Most of the current state-of-the-art person Re-ID methods on closed-world datasets are based on local convolution neural network, and hardly works well when applying them to aerial person Re- Idtasks directly. In this paper, we improve the emerging vision transformer (ViT) and apply it to the person Re- Idin aerial imagery. It should be noted that a large amount of data is required to be pretrained for ViTs to achieve competitive performance. Considering the limitations of data, computing power and flexibility in practical scenarios, we improve the pre-training process based on self-supervised learning, and achieve training ViTs from scratch with limited data. Specifically, in pre-training stage, the self-supervised paradigm based on parameter instance discrimination is applied to capture feature alignment and instance similarity, which alleviates the data-hungry of ViTs caused by the lack of inductive bias. Extensive comparative evaluation experiments are conducted on the aerial Re- Iddataset. Our method achieves a Rank-1 accuracy of 65.29% and a mean average precision (mAP) of 57.31%, which proves its effectiveness in aerial person Re-ID tasks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Triangular Stable Node Network based on Self-supervised Learning for personalized prediction

A Triangular Stable Node Network based on Self-supervised Le...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Liu, Qing Gao, Qian Fan, Jun Zhang, Zhiqiang Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center National Supercomputer Center in Jinan Qilu University of Technology Shandong Academy of Sciences Jinan250014 China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology Shandong Academy of Sciences Jinan250353 China Shandong Provincial Key Laboratory of Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science Jinan250014 China China Telecom Digital Intelligence Techonology Co Ltd. No.1999 Shunhua road Shandong Jinan250101 China

ISBN: (纸本)9798350368741

In recent years, research has illuminated the potency of implicit data processing in enhancing user preferences. Nevertheless, barriers remain in breaking through the constraints of implicit information. This study aims to bridge this gap by firstly constructing a triangular stable node network model, tailored to manage implicit information with precision. Recognizing the challenge of pinpointing novel structures within large-scale graphs, we propose SLTSNN-a triangular stable node network based on self-supervised learning for personalized prediction. SLTSNN innovates by maximizing mutual information between graph-level and patch-level representations, while augmenting graph representations through extended enhanced representations. Additionally, it incorporates triangular data associations and introduces a triangular allocation attention network, which emphasizes strongly correlated preference features among similar users. Furthermore, SLTSNN employs contrastive learning to maximize mutual information between graph vectors and hidden representations, distinguishing between high-order global and local representations. The model's effectiveness in enhancing user preferences and capturing new graph structures is evidenced by its performance on hit rate and normalized discounted cumulative gain metrics across three datasets. © 2025 IEEE.

关键词： graph contrastive learning graph neural networks recommender systems self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

PP-LDG: A Medical Privacy-Preserving Labeled data Generation Framework

PP-LDG: A Medical Privacy-Preserving Labeled Data Generation...

引用

Medical Artificial Intelligence (MedAI), IEEE International Conference on

作者： Haoxiang Yuan Xiaochen Yuan Xiuli Bi Weisheng Li Guoyin Wang Bin Xiao Chongqing Key Laboratory of Image Cognition School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing China Faculty of Applied Sciences Macao Polytechnic University Macao China Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education Chongqing China

ISBN: (数字)9798350377613

ISBN: (纸本)9798350377620

The rapid development of deep learning has led to an increasing demand for data. However, such data are scarce in many fields and often contain private and sensitive information, such as medical images. The fact that data owners are unwilling to share these high-privacy data further exacerbates the scarcity of data. A prevalent research direction is to combine differential privacy and image generation, by which we can obtain a large amount of synthetic data with a similar distribution to the original dataset, and that synthetic dataset does not compromise the privacy of the original dataset. However, these methods cannot provide labels for the generated data, limiting the subsequent uses of the data. To solve the problem, we propose a generic privacy-preserving labeled data generation framework named PP-LDG. It is the first data publishing framework to generate labeled data while not disclosing the privacy of original data. We theoretically demonstrate that our proposed framework can provide strict privacy guarantees with differential privacy and demonstrate the effectiveness of the synthetic dataset obtained from the framework under practical privacy budgets through extensive experiments.

关键词： Deep learning Differential privacy Accuracy Limiting Image synthesis Publishing data collection Synthetic data Biomedical imaging Image classification

来源：评论

学校读者我要写书评

暂无评论

Interplays of liver fibrosis-associated microRNAs:Molecular mechanisms and implications in diagnosis and therapy

引用

Genes & Diseases 2023年第4期10卷 1457-1469页

作者： Hong Li Tingli Liu Yongchun Yang William C.Cho Robin J.Flynn Majid Fasihi Harandi Houhui Song Xuenong Luo Yadong Zheng State Key Laboratory of Veterinary Etiological Biology Key Laboratory of Veterinary Parasitology of Gansu ProvinceLanzhou Veterinary Research InstituteChinese Academy of Agricultural SciencesLanzhouGansu 730046China Key Laboratory of Applied Technology on Green-Eco-Healthy Animal Husbandry of Zhejiang Province Zhejiang Provincial Engineering Laboratory for Animal Health Inspection&Internet TechnologyZhejiang International Science and Technology Cooperation Base for Veterinary Medicine and Health ManagementChina-Australia Joint Laboratory for Animal Health Big Data AnalyticsCollege of Animal Science and Technology&College of Veterinary Medicine of Zhejiang A&F UniversityHangzhouZhejiang 311300China Department of Clinical Oncology Queen Elizabeth HospitalHong Kong SAR 999077China Department of Infection Biology Institute of Infection and Global HealthUniversity of LiverpoolLiverpool L35RFUK Graduate Studies Office Department of ResearchInnovation and Graduate StudiesWaterford Institute of TechnologyX91 K0EKIreland Research Center for Hydatid Disease in Iran Kerman University of Medical SciencesKerman ***Iran

microRNAs(miRNAs)are a class of non-coding functional small RNA composed of 21e23 nucleotides,having multiple associations with liver ***-associated miRNAs are roughly classified into pro-fibrosis or anti-fibrosis *** former is capable of activating hepatic stellate cells(HSCs)by modulating pro-fibrotic signaling pathways,mainly including TGF-b/SMAD,WNT/b-catenin,and Hedgehog;the latter is responsible for maintenance of the quiescent phenotype of normal HSCs,phenotypic reversion of activated HSCs(aHSCs),inhibition of HSCs proliferation and suppression of the extracellular matrix-associated gene ***,several miRNAs are involved in regulation of liver fibrosis via alternative mechanisms,such as interacting between hepatocytes and other liver cells via exosomes and increasing autophagy of ***,understanding the role of these miRNAs may provide new avenues for the development of novel interventions against hepatic fibrosis.

关键词： Diagnosis Hepatic stellate cell Liver fibrosis miRNA Therapy

来源：评论

学校读者我要写书评

暂无评论

LSN:Long-Term Spatio-Temporal Network for Video Recognition

LSN:Long-Term Spatio-Temporal Network for Video Recognition

引用

作者： Zhenwei Wang Wei Dong Bingbing Zhang Jianxin Zhang School of Computer Science and Engineering Dalian Minzu University SEAC Key Laboratory of Big Data Applied Technology Dalian Minzu University Institute of Machine Intelligence and Bio-Computing Dalian Minzu University School of Information and Communication Engineering Dalian University of Technology

Although recurrent neural networks(RNNs) are widely leveraged to process temporal or sequential data,they have attracted too little attention in current video action recognition ***,this work attempts to model the long-term spatio-temporal information of the video based on a variant of RNN,i.e.,higher-order ***,we propose a novel long-term spatio-temporal network(LSN) for solving this video task,the core of which integrates the newly constructed high-order ConvLSTM(HO-ConvLSTM) modules with traditional2D convolutional ***,each HO-Conv LSTM module consists of an accumulated temporary state(ATS) module as well as a standard Conv LSTM module,and several previous hidden states in the ATS module are accumulated to one temporary state that will enter the standard Conv LSTM to determine the output together with the current *** HO-Conv LSTM module can be inserted into different stages of the 2D convolutional neural network(CNN) in a plug-andplay manner,thus well characterizing the long-term temporal evolution at various spatial *** results on three commonly used video benchmarks demonstrate that the proposed LSN model can achieve competitive performance with the representative models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-Channel Hypergraph Convolution Group Recommendation with Member Information Enhancement 25

Multi-Channel Hypergraph Convolution Group Recommendation wi...

引用

25th IEEE International Conferences on High Performance Computing and Communications, 9th International Conference on data Science and Systems, 21st IEEE International Conference on Smart City and 9th IEEE International Conference on Dependability in Sensor, Cloud and big data Systems and Applications, HPCC/DSS/SmartCity/DependSys 2023

作者： Chen, Tianhao Gao, Qian Fan, Jun Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Shandong Jinan250014 China Qilu University of Technology Shandong Academy of Sciences Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Shandong Jinan250353 China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Shandong Jinan250014 China China Telecom Digital Intelligence Techonology Co Ltd Shandong Jinan250101 China

ISBN: (纸本)9798350330014

Group recommendation involves comprehensively considering various aspects, including members and items, to predict the overall interests of a group and recommend suitable items through a recommendation system. With the rapid evolution of the Internet, online group activities have become increasingly prevalent, making group recommendation a highly discussed topic within the realm of recommendation systems. However, current research in group recommendation still confronts the following challenges. Firstly, a predominant portion of group recommendation research focuses solely on aggregating group-level information, neglecting the valuable contribution of higher-order member-level insights to group recommendation. Moreover, some aggregation strategies overly prioritize fairness, thereby disregarding common real-world patterns. Secondly, previous studies have primarily relied on aggregating individual member interests to establish group preferences, lacking a holistic consideration of group dynamics. To tackle these challenges, this study introduces an innovative approach by implementing multi-channel hypergraph convolution within the member perspective. This approach aims to effectively extract higher-order insights from members by utilizing a member information enhancement module. By establishing group interconnections based on similarity and employing an adaptive fusion network to amalgamate multiple viewpoints, a final representation is derived. Experimental results demonstrate that our proposed model surpasses baseline models by 3% to 4% in terms of hit rate and accuracy, validating the efficacy of our approach. © 2023 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Social-enhanced recommendation using graph-based contrastive learning 25

Social-enhanced recommendation using graph-based contrastive...

引用

作者： Xue, Peng Gao, Qian Fan, Jun Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Shandong Jinan250014 China Qilu University of Technology Shandong Academy of Sciences Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Shandong Jinan250353 China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Shandong Jinan250014 China China Telecom Digital Intelligence Techonology Co Ltd Shandong Jinan250101 China

ISBN: (纸本)9798350330014

The social network-based recommendation model use social network information to mitigate data sparsity issues and improve the accuracy of recommendation models. However, In most social network-based recommendation algorithms, the social neighbors' contributions are difficult to distinguish from the central user's, neglecting hidden correlations in social infor-mation. In order to solve this problem, this paper presents a graph-based contrastive learning framework for social-enhanced recommendation (SoGCLR) that utilizes implicit social information captured by a new social relation attention mechanism, en-rich user representations, and improve model robustness through graph-based contrastive learning. Specifically, the paper captures the degree of contribution of each neighbor in the social graph to the central user through a social relation attention layer, thus obtaining hidden correlations in social information, and further integrates this with user information in the user-item interaction graph to enrich user representations. In addition, the paper incorporates graph-based contrastive learning into the recommendation task using cross-layer contrastive learning, calculating contrastive loss and mapping nodes with similar but different exposure rates to nearby regions to mitigate exposure bias issues. Results from Ciao and Epinions demonstrate that SoGCLR reduces RMSE and MAE by 1.33% to 1.84% compared with baseline models. © 2023 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Tunable optical multistability created by a single cavity field in an atom-cavity system

引用

Optics Express 2025年第11期33卷 22997-23007页

作者： Liyong Wang Wenyi Zhang Yinxue Zhao Guoshu Wang Yu Liu Jiajia Du Department of Applied Physics College of Science Wuhan University of Science and Technology Wuhan 430081 China wangliyong@*** Wuhan Social Work Polytechnic Wuhan 430079 China Chongqing College of Mobile Communication Chongqing 401520 China Chongqing Key Laboratory of Public Big Data Security Technology Chongqing 401420 China Chongqing University of Post and Telecommunications Chongqing 400065 China dujj@***

A tunable optical multistability scheme based on a single cavity field coupled with two separate atomic transitions in an atom-cavity system is proposed and demonstrated. Under the collective strong coupling condition, optical multistability is triggered by a transmitting signal field coupled into the cavity without extra assistant light or magnetic fields. The created optical multistability curve and threshold can be tuned flexibly by system parameters in a broadband range. Moreover, a certain bistability region of the system is further split into two bistability regions due to destructive quantum interference when a weak control field is added. Compared to traditional optical multistabilities created by two or more light fields, the proposed optical multistability scheme may be designed as passive all-optical logical devices since it is compact and easy to miniaturize. The proposed scheme is useful for manufacturing integrated applications of multi-state all-optical logic devices and constructing basic elements of all-optical communication networks.

关键词： Bistability Destructive interference Information processing Light matter interactions Optical fields Optical media

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：