检索结果-内蒙古大学图书馆

Towards Efficient Short-Range Pair Interaction on Sunway Many-Core Architecture

Journal of computer Science & technology 2021年第1期36卷 123-139页

作者： Jun-Shi Chen Hong An Wen-Ting Han Zeng Lin Xin Liu School of Computer Science and Technology University of Science and Technology of ChinaHefei 230026China National Research Center of Parallel Computer Engineering and Technology Beijing 100080China

The short-range pair interaction consumes most of the CPU time in molecular dynamics(MD)*** inherent computation sparsity makes it challenging to achieve high-performance kernel on the emerging many-core *** this paper,we present a highly efficient short-range force kernel on the Sunway,a novel many-core architecture with many unique *** parallel efficiency of this algorithm on the Sunway many-core processor is strongly limited by the poor data locality and write *** enhance the data locality,we adopt a super cluster based neighbor list with an appropriate granularity that fits in the local memory of computing *** the absence of a low overhead locking mechanism,using data-privatization force array is a more feasible method to avoid write conflicts,but results in the large overhead of data *** adopt a dual-slice partitioning scheme for both hardware resources and computing tasks,which utilizes the on-chip data communication to reduce data reduction overhead and provide load ***,we exploit the single instruction multiple data(SIMD)parallelism and perform instruction reordering of the force kernel on this many-core *** experimental results show that the optimized force kernel obtains a performance speedup of 226x compared with the reference implementation and achieves 20%of peak flop rate on the Sunway many-core processor.

关键词： molecular dynamics sunway many-core pair interaction parallel algorithm

来源：评论

学校读者我要写书评

暂无评论

Graph attention based on contextual reasoning and emotion-shift awareness for emotion recognition in conversations

引用

Complex & Intelligent Systems 2025年第7期11卷 1-20页

作者： Yang, Juan Wei, Puling Du, Xu Shen, Jun College of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Hubei Province Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan China National Engineering Research Center for E‑Learning Central China Normal University Wuhan China School of Computing and Information Technology University of Wollongong NSW Australia

Emotion recognition in conversations has recently emerged as a hot research topic owing to its increasingly important role in developing intelligent empathy services. Thoroughly exploring the conversational context and accurately capturing emotion-shift information are highly crucial for accurate emotion recognition in conversations. However, existing studies generally failed to fully understand the complex conversational context due to their insufficient capabilities in extracting and integrating emotional cues. Moreover, they mainly focused on the speaker’s emotion inertia while paying less attention to explore multi-perspective emotion-shift patterns. To address these limitations, this study proposes a novel multimodal approach, namely, GAT-CRESA (Graph ATtention based on Contextual Reasoning and Emotion-Shift Awareness). Specifically, the multi-turn global contextual reasoning module iteratively performs contextual perception and cognitive reasoning for efficiently understanding the global conversational context. Then, GAT-CRESA explores emotion-shift information among utterances from both the speaker-dependent and the global context-based perspectives. Next, the emotion-shift awareness graphs are constructed for extracting significant local-level conversational context, where edge relations are determined by the learnt emotion-shift labels. Finally, the outputs of graphs are concatenated for final emotion recognition. The loss of emotion prediction task is combined together with those of two perspective’s emotion-shift learning for guiding the training process. Experimental results show that our GAT-CRESA achieves new state-of-art records with 72.77% ACC and 72.81% wa-F1 on IEMOCAP, and 65.44% ACC and 65.04% wa-F1 on MELD, respectively. The ablation results also indicate the effectiveness and rationality of each component in our approach.

关键词： Contextual reasoning Emotion recognition in conversations (ERC) Emotion-shift Graph attention

来源：评论

学校读者我要写书评

暂无评论

Hybrid Digital-Analog Semantic Communications

引用

IEEE Journal on Selected Areas in Communications 2025年

作者： Xie, Huiqiang Qin, Zhijin Han, Zhu Letaief, Khaled B. Jinan University College of Information Science and Technology Guangzhou China Tsinghua University Department of Electronic Engineering Beijing100084 China State Key Laboratory of Space Network and Communications Beijing100084 China Beijing National Research Center for Information Science and Technology Beijing100084 China University of Houston Department of Electrical and Computer Engineering Houston United States The Hong Kong University of Science and Technology Department of Electronic and Computer Engineering Hong Kong Hong Kong

Digital and analog semantic communications (SemCom) face inherent limitations such as data security concerns in analog SemCom, as well as leveling-off and cliff-edge effects in digital SemCom. In order to overcome these challenges, we propose a novel SemCom framework and a corresponding system called HDA-DeepSC, which leverages a hybrid digitalanalog approach for multimedia transmission. This is achieved through the introduction of analog-digital allocation and fusion modules. To strike a balance between data rate and distortion, we design new loss functions that take into account long-distance dependencies in the semantic distortion constraint, essential information recovery in the channel distortion constraint, and optimal bit stream generation in the rate constraint. Additionally, we propose denoising diffusion-based signal detection techniques, which involve carefully designed variance schedules and sampling algorithms to refine transmitted signals. Through extensive numerical experiments, we will demonstrate that HDA-DeepSC exhibits robustness to channel variations and is capable of supporting various communication scenarios. Our proposed framework outperforms existing benchmarks in terms of peak signal-to-noise ratio and multi-scale structural similarity, showcasing its superiority in semantic communication quality. © 1983-2012 IEEE.

关键词： Digital communication systems

来源：评论

学校读者我要写书评

暂无评论

FedHM: Efficient federated learning for heterogeneous models via low-rank factorization

引用

Artificial Intelligence 2025年 344卷

作者： Yao, Dezhong Pan, Wanning Shi, Yuexin O'Neill, Michael J. Dai, Yutong Wan, Yao Zhao, Peilin Jin, Hai Sun, Lichao National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China University of North Carolina Chapel Hill United States Lehigh University United States Tencent AI Lab China

One underlying assumption of recent Federated Learning (FL) paradigms is that all local models share an identical network architecture. However, this assumption is inefficient for heterogeneous systems where devices possess varying computation and communication capabilities. The presence of such heterogeneity among devices negatively impacts the scalability of FL and slows down the training process due to the existence of stragglers. To this end, this paper proposes a novel federated compression framework for heterogeneous models, named FedHM, distributing the heterogeneous low-rank models to clients and then aggregating them into a full-rank global model. Furthermore, FedHM significantly reduces communication costs by utilizing low-rank models. Compared with state-of-the-art heterogeneous FL methods under various FL settings, FedHM is superior in the performance and robustness of models with different sizes. Additionally, the convergence guarantee of FL for heterogeneous devices is first theoretically analyzed. © 2025 The Authors

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A Lookup Table for Deficiency Number Calculation in Mahjong

A Lookup Table for Deficiency Number Calculation in Mahjon...

引用

29th International Conference on Technologies and Applications of Artificial Intelligence, TAAI 2024

作者： Tang, Shih-Chieh Chen, Jr-Chang Wu, I-Chen Department of Computer Science National Yang Ming Chiao Tung University Hsinchu Taiwan Department of Computer Science and Information Engineering National Taipei University New Taipei City Taiwan Research Center for Information Technology Innovation Academia Sinica Taipei Taiwan

ISBN: (纸本)9789819645886

In the game of Mahjong, the deficiency number is an important metric to judge the quality of a given hand. Calculating this number on-the-fly using traditional methods, such as depth-first search, is time consuming. In this paper, we propose a formula for the deficiency number and design a greedy method to build a lookup table in advance, allowing for more efficient calculations. While using these tables, we introduce two methods to handle some special cases, named hidden tiles and pseudo-meld prioritization. By applying these methods, we ensure the correctness when using these tables. The experimental results show a speedup of 121.2 times compared to VeryLongCat and 6868.9 times compared to Botzone. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Deficiency Number Lookup Table Mahjong

来源：评论

学校读者我要写书评

暂无评论

Multi-view User Preference Modeling for Personalized Text-to-Image Generation

引用

IEEE Transactions on Multimedia 2025年

作者： Zhang, Huaiwen Wu, Tianci Wei, Yinwei Inner Mongolia University College of Computer Science China National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian China Inner Mongolia Key Laboratory of Mongolian Information Processing Technology Hohhot010021 China Shandong University School of Software Jinan China

Personalized text-to-image generation aims to synthesize images tailored to individual user preferences. Existing methods primarily generate customized content using a few reference images, which often struggle to mine user preferences from historical records, and thus fail to synthesize truly personalized content. In addition, it is difficult to directly incorporate the extracted feature of user preferences into the feature space of the generation model, since there exists a considerable gap between them. In this paper, we propose a novel multi-view personalized text-to-image generation method based on the diffusion model, named MVP-Diffusion, which learns instance- and user-level preferences from historical records and integrates them into the generation model. For instance-level user preference modeling, we employ a chain-of-thought prompting strategy to deduce preference keywords and integrate them into input prompts with the aid of a large language model. For user-level preference modeling, we construct a learnable embedding for each user to capture more comprehensive preferences by analyzing their historical records. An adaptive user preference fusion module is proposed to inject user preferences into the generation model via a set of learnable parameters. Experimental results demonstrate that the proposed method significantly enhances the personalization of the generated images compared to the other personalized text-to-image generation methods. © 1999-2012 IEEE.

关键词： Large Language Model Multi-view Personalized Text-to-image Generation

来源：评论

学校读者我要写书评

暂无评论

Exploring an InGaN Micro-LED structure for optimum IQE operating on low current condition through simulation study

引用

International Journal of Modern Physics B 2025年第6期39卷

作者： Hung, Wen-Ching Chang, Sheng-Po Chang, Shoou-Jinn Kuo, Hao-Chung Chen, Jyh-Chen Department of Mechanical Engineering National Central University Jhongli City32001 Taiwan Department of Microelectronics Engineering National Kaohsiung University of Science and Technology Kaohsiung City88157 Taiwan Department of Electrical Engineering Institute of Microelectronics National Cheng Kung University No. 1 Ta Hseuh Road Tainan City70101 Taiwan Department of Photonics College of Electrical and Computer Engineering National Yang Ming Chiao Tung University Hsinchu30010 Taiwan Semiconductor Research Center Hon Hai Research Institute Taipei11492 Taiwan

Light-emitting diodes (LEDs) are key components in display applications. The quantum efficiency of GaN/InGaN LEDs has been enhanced, leading to advancements in indoor and outdoor RGB LED display applications. White LED backlights are commonly used in displays due to the increased efficiency of InGaN LEDs. Despite efficiency, lifespan and image retention issues, OLED displays are utilized in high-end mobile phones to meet market expectations for screen response time and color saturation. Micro-LED RGB full-color displays have the potential to dominate the next-generation display market, driven by the increasing demands for resolution, power consumption and response time. Micro-LEDs are becoming smaller, reaching sizes of 50μm or even smaller, to meet the high-resolution requirements of displays. They offer higher contrast, brightness and faster response speeds. This research utilizes numerical simulations to develop a model for radiative and nonradiative recombination in InGaN semiconductor materials. The aim is to investigate the internal quantum efficiency (IQE) of various chip sizes, quantum well counts, well thicknesses and electron block layers under low current densities. The research reveals that the optimal structure is a single quantum well with an electron block layer (EBL), which can increase IQE from 53.85% to 80.9% at 0.01A/cm2 under low current density conditions, with a decrease in the number of quantum wells to one. The IQE efficiency improvement is 27.05%. © 2025 World Scientific Publishing Company.

关键词： Light emitting diodes

来源：评论

学校读者我要写书评

暂无评论

Semantic Data Augmentation for Few-Shot Biomedical Named Entity Recognition

Semantic Data Augmentation for Few-Shot Biomedical Named Ent...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Ying Zhang Weihua Wang College of Computer Science Inner Mongolia University Hohhot China National and Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Hohhot China Inner Mongolia Key Laboratory of Multilingual Artificial Intelligence Technology Hohhot China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Biomedical Named Entity Recognition (BioNER) aims to identify and classify entities in biomedical text. This task struggles with data scarcity due to limited annotated data. Although data augmentation is effective, existing methods fail to handle the complex semantic mappings on biomedical terminology, which results in the generated samples lacking semantic diversity. In this paper, we propose a data augmentation method to create semantically diverse and coherent training samples for few-shot BioNER. The method utilizes the Unified Medical Language System (UMLS) for entity replacement and combines with a Masked Language Model (MLM) to generate contextually relevant words. Experimental results show that our method improves BioNER performance in few-shot scenarios. Compared to all baseline models, our method achieves an average F1 score improvement of 7.6% and 11.6% on the NCBI and JNLPBA datasets, respectively. Our source code and data are available at https://***/ABC8184/SDA

关键词： Training Terminology Biological system modeling Source coding Unified modeling language Semantics Named entity recognition Signal processing Data augmentation Speech processing

来源：评论

学校读者我要写书评

暂无评论

Fine-tuned deep transfer learning: an effective strategy for the accurate chronic kidney disease classification

引用

PeerJ computer Science 2025年 11卷 e2800-e2800页

作者： Khan, Zeshan Aslam Waqar, Muhammad Khan, Hashir Ullah Chaudhary, Naveed Ishtiaq Khan, Abeer T.M.A. Ishtiaq, Iqra Khan, Farrukh Aslam Raja, Muhammad Asif Zahoor Electrical and Computer Engineering International Islamic University Islamabad Pakistan International Graduate Institute of Artificial Intelligence National Yunlin University of Science and Technology Yunlin Taiwan Future Technology Research Center National Yunlin University of Science and Technology Yunlin Taiwan Rawal Institute of Health Sciences Rawalpindi Pakistan Technological University Dublin Dublin Ireland Center of Excellence in Information Assurance King Saud University Riyadh Saudi Arabia

Kidney diseases are becoming an alarming concern around the globe. Premature diagnosis of kidney disease can save precious human lives by taking preventive measures. Deep learning demonstrates a substantial performance in various medical disciplines. Numerous deep learning approaches are suggested in the literature for accurate chronic kidney disease classification by compromising on architectural complexity, classification speed, and resource constraints. In this study, deep transfer learning is exploited by incorporating unexplored yet effective variants of ConvNeXt and EfficientNetV2 for accurate and efficient classification of chronic kidney diseases. The benchmark computed tomography (CT)-based kidney database containing 12,446 CT scans of kidney tumor, stone cysts, and normal patients is utilized to train the designed fine-tuned networks. However, due to the highly imbalanced distribution of images among classes, the operation of data trimming is exploited for balancing the number of CT scans in each class, which is essential for designing an unbiased predictive network. By utilizing fine-tuned pre-trained models for our specific task, the training time is reduced leading to a computationally inexpensive solution. After the comprehensive hyperparameters tuning with respect to changes in learning rates, batch sizes, and optimizers, it is depicted that the designed fine-tuned EfficientNetV2B0 network of 23.8 MB in size with only 6.2 million architectural parameters shows substantial diagnostic performance by achieving a generalized test accuracy of 99.75% on balanced CT kidney database. Furthermore, the designed fine-tuned EfficientNetV2B0 attains high precision, recall, and F1-score of 99.75%, 99.63%, and 99.75%, respectively. Moreover, the final fine-tuned EfficientNetV2B0 ensures its scalability by achieving an impressive diagnostic accuracy of 99.73% on the test set of the original CT kidney dataset as well. Through the extensive evaluation of the proposed t

关键词： computerized tomography

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

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Qing Liu Qian Gao Jun Fan Zhiqiang Zhang 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) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science Jinan China China Telecom Digital Intelligence Techonology Co Ltd Jinan China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

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.

关键词： Measurement Bridges Contrastive learning Signal processing Data processing Vectors Space exploration Resource management Speech processing Mutual information

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：