检索结果-内蒙古大学图书馆

Energy-Efficient Over-the-Air Computation in UAV-Assisted IIoT Networks

IEEE Transactions on Mobile computing 2025年

作者： Chen, Yali Sun, Sheng Liu, Min Ai, Bo Wang, Yuwei Liu, Yunhao Chinese Academy of Sciences Institute of Computing Technology Beijing100190 China Zhongguancun Laboratory Beijing China University of Chinese Academy of Sciences Beijing100049 China Beijing Jiaotong University School of Electronic and Information Engineering Beijing100044 China Zhengzhou University Henan Joint International Research Laboratory of Intelligent Networking and Data Analysis Zhengzhou450001 China Peng Cheng Laboratory Research Center of Networks and Communications Shenzhen518055 China Tsinghua University Beijing100084 China

In remote industrial internet of things (IIoT) monitoring systems, the unmanned aerial vehicle (UAV) serves as supplementary infrastructure to aggregate data from a large number of distributed sensors, and achieve industrial operation intelligence. In the wireless data aggregation process, using conventional orthogonal multiple access techniques face challenges such as scarce bandwidth, high communication latency and energy consumption. To tackle these issues, the over-the-air computation (AirComp) technique has emerged. It allows concurrent data transmissions from sensors, as well as integrates communication and computation processes, ultimately enabling fast data aggregation. However, the energy consumption issue remains unresolved. In this paper, we exploit spatial correlations among sensor measurements, and design an energy-efficient AirComp in UAV-assisted IIoT networks, where only a subset of sensors transmit data instead of all sensors. Then, we derive a closed-form expression for the mean square error (MSE) of each combination under a specific number of sensor transmissions. By jointly optimizing the UAV deployment and pre-coding coefficients of sensors, we formulate the problem of minimizing MSE for each combination of transmitted sensors. Furthermore, the MSE optimization algorithm is developed to output the average MSE of all combinations. Finally, we evaluate the average MSE and network lifetime performance of proposed scheme. © 2002-2012 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

An approach to scalability of parallel matrix multiplication algorithms 3rd

An approach to scalability of parallel matrix multiplication...

引用

3rd Annual International computing and Combinatorics Conference, COCOON 1997

作者： Wu, Xingfu National Research Center for Intelligent Computing Systems Institute of Computing Technology Chinese Academy of Sciences Beijing100080 China

ISBN: (纸本)354063357X

In this paper, we start with presenting and defining scalability of algorithm-architecture combinations based on the fixed ratio of computation time to communication cost, analyze the performance and scalability of a number of parallel matrix multiplication algorithms, and compare them with the related work. The performance analysis and the analytical scalability expressions for these algorithms show that our scalability metric is better than the isoefficiency metric. © Springer-Verlag Berlin Heidelberg 1997.

关键词： Scalability

来源：评论

学校读者我要写书评

暂无评论

Homogeneous description for heterogeneous cross-media resources

Homogeneous description for heterogeneous cross-media resour...

引用

2008 Chinese Conference on Pattern Recognition, CCPR 2008

作者： Xu, Dong Hu, Ping Li, Hua National Research Center for Intelligent Computing Systems Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China

ISBN: (纸本)9781424423163

Images, polygonal models and point clouds are three kinds of heterogeneous cross-media resources, but they can stand for the same object. We introduce two kinds of homogeneous descriptions for them. First, we find a relation between surface moment invariants and shape distribution since they both use invariant geometric primitives. This relation can provide a way to approximate surface moment invariants for point clouds. Hence, we can get the same shape description for both point clouds and polygonal models. Second, we project each 3D model in many directions and get large numbers of 2D images. Then, polygonal models and images are converted to the same data format for comparison. Homogeneous shape description makes it possible to carry out heterogeneous cross-media retrieval in pervasive environment. ©2008 IEEE.

关键词： Computers

来源：评论

学校读者我要写书评

暂无评论

3D affine moment invariants for surfaces

3D affine moment invariants for surfaces

引用

2008 Chinese Conference on Pattern Recognition, CCPR 2008

作者： Xu, Dong Li, Hua National Research Center for Intelligent Computing Systems Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China

ISBN: (纸本)9781424423163

A new kind of weighted surface moments is defined which can achieve affine invariance for unclosed surfaces. We can also select a corresponding point and build a pseudo-solid for surface and compute the affine volume moment invariants. We test the invariance of the two affine moment invariants on a 3D terrain map and a 3D face scan. The experimental result reveals that the weighted surface moment invariants are highly robust to shape deformations and numerical computation. ©2008 IEEE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

A Simplified Communication Protocol on Dawning 2000 4

A Simplified Communication Protocol on Dawning 2000

引用

4th International Conference/Exhibition on High Performance computing in the Asia-Pacific Region, HPC-Asia 2000

作者： Jie, Ma National Research Center for Intelligent Computing Systems Institute of Computing Technology Chinese Academy of Sciences Beijing100080 China

ISBN: (纸本)0769505902

Point to point latency and bandwidth are two important factors to evaluate a cluster communication system. SCP is a Simplified Communication Protocol on Dawning 2000 which is a low level communication system based on PowerPC/AIX. The latency of SCP is limited to 9.6 μs, and the peak bandwidth is reached when message length is 4 K. The paper mainly discusses the key points about the design and implementation of SCP. The paper gives the idea of improving the performance of a low level communication system by using a simplifying communication protocol, using zero memory copy, providing an efficient communication data path and balancing the work on host and NIC. Multiple services are provided to optimize the upper layers. © 2000 IEEE.

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

CLIMS++: Cross Language Image Matching with Automatic Context Discovery for Weakly Supervised Semantic Segmentation

引用

International Journal of Computer Vision 2025年 1-20页

作者： Xie, Jinheng Deng, Songhe Hou, Xianxu Luo, Zhaochuan Shen, Linlin Huang, Yawen Zheng, Yefeng Shou, Mike Zheng Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China Show Lab National University of Singapore Singapore Singapore School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University Suzhou China Department of Computer Science Wenzhou-Kean University Wenzhou China Jarvis Research Center Tencent YouTu Lab Shenzhen China

While promising results have been achieved in weakly-supervised semantic segmentation (WSSS), limited supervision from image-level tags inevitably induces discriminative reliance and spurious relations between target classes and background regions. Thus, Class Activation Map (CAM) usually tends to activate discriminative object regions and falsely includes lots of class-related backgrounds. Without pixel-level supervisions, it could be very difficult to enlarge the foreground activation and suppress those false activation of background regions. In this paper, we propose a novel framework of Cross Language Image Matching with Automatic Context Discovery (CLIMS++), based on the recently introduced Contrastive Language-Image Pre-training (CLIP) model, for WSSS. The core idea of our framework is to introduce natural language supervision to activate more complete object regions and suppress class-related background regions in CAM. In particular, we design object, background region, and text label matching losses to guide the model to excite more reasonable object regions of each category. In addition, we propose to automatically find spurious relations between foreground categories and backgrounds, through which a background suppression loss is designed to suppress the activation of class-related backgrounds. The above designs enable the proposed CLIMS++ to generate a more complete and compact activation map for the target objects. Extensive experiments on PASCAL VOC 2012 and MS COCO 2014 datasets show that our CLIMS++ significantly outperforms the previous state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhanced Large Language Models for Effective Screening of Depression and Anxiety

arXiv

引用

arXiv 2025年

作者： Liu, June M. Gao, Mengxia Sabour, Sahand Chen, Zhuang Huang, Minlie Lee, Tatia M.C. State Key Laboratory of Brain and Cognitive Sciences The University of Hong Kong Hong Kong Laboratory of Neuropsychology and Human Neuroscience The University of Hong Kong Hong Kong The CoAI group DCST Institute for Artificial Intelligence State Key Lab of Intelligent Technology and Systems Beijing National Research Center for Information Science and Technology Tsinghua University Beijing China

Depressive and anxiety disorders are widespread, necessitating timely identification and management. Recent advances in Large Language Models (LLMs) offer potential solutions, yet high costs and ethical concerns about training data remain challenges. This paper introduces a pipeline for synthesizing clinical interviews, resulting in 1,157 interactive dialogues (PsyInterview), and presents EmoScan, an LLM-based emotional disorder screening system. EmoScan distinguishes between coarse (e.g., anxiety or depressive disorders) and fine disorders (e.g., major depressive disorders) and conducts high-quality interviews. Evaluations showed that EmoScan exceeded the performance of base models and other LLMs like GPT-4 in screening emotional disorders (F1-score=0.7467). It also delivers superior explanations (BERTScore=0.9408) and demonstrates robust generalizability (F1-score of 0.67 on an external dataset). Furthermore, EmoScan outperforms baselines in interviewing skills, as validated by automated ratings and human evaluations. This work highlights the importance of scalable data-generative pipelines for developing effective mental health LLM tools. © 2025, CC BY-NC-SA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Balanced Multi-view Clustering

arXiv

引用

arXiv 2025年

作者： Li, Zhenglai Wang, Jun Tang, Chang Zhu, Xinzhong Zhang, Wei Liu, Xinwang Faculty of data science City University of Macau 999078 China School of computer National University of Defense Technology Changsha410073 China School of computer China University of Geosciences Wuhan430074 China College of Mathematics Physics and Information Engineering Zhejiang Normal University Jinhua China Research Institute of Ningbo Cixing Co. Ltd Ningbo China Qilu University of Technology Shandong Academy of Sciences China Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan250000 China

Multi-view clustering (MvC) aims to integrate information from different views to enhance the capability of the model in capturing the underlying data structures. The widely used joint training paradigm in MvC is potentially not fully leverage the multi-view information, since the imbalanced and under-optimized view-specific features caused by the uniform learning objective for all views. For instance, particular views with more discriminative information could dominate the learning process in the joint training paradigm, leading to other views being under-optimized. To alleviate this issue, we first analyze the imbalanced phenomenon in the joint-training paradigm of multi-view clustering from the perspective of gradient descent for each view-specific feature extractor. Then, we propose a novel balanced multi-view clustering (BMvC) method, which introduces a view-specific contrastive regularization (VCR) to modulate the optimization of each view. Concretely, VCR preserves the sample similarities captured from the joint features and view-specific ones into the clustering distributions corresponding to view-specific features to enhance the learning process of view-specific feature extractors. Additionally, a theoretical analysis is provided to illustrate that VCR adaptively modulates the magnitudes of gradients for updating the parameters of view-specific feature extractors to achieve a balanced multi-view learning procedure. In such a manner, BMvC achieves a better trade-off between the exploitation of view-specific patterns and the exploration of view-invariance patterns to fully learn the multi-view information for the clustering task. Finally, a set of experiments are conducted to verify the superiority of the proposed method compared with state-of-the-art approaches on eight benchmark MvC datasets. The demo code of this work is publicly available at https://***/guanyuezhen/BMvC. Copyright © 2025, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Environment-Driven Online LiDAR-Camera Extrinsic Calibration

arXiv

引用

arXiv 2025年

作者： Huang, Zhiwei Li, Jiaqi Zhong, Ping Fan, Rui The Department of Control Science & Engineering The College of Electronics & Information Engineering Tongji University Shanghai201804 China The School of Computer Science and Engineering Central South University Hunan Changsha410083 China The National Key Laboratory of Science and Technology on Automatic Target Recognition National University of Defense Technology Hunan Changsha410073 China The Department of Control Science & Engineering The College of Electronics & Information Engineering Shanghai Research Institute for Intelligent Autonomous Systems The State Key Laboratory of Intelligent Autonomous Systems Frontiers Science Center for Intelligent Autonomous Systems Tongji University Shanghai201804 China The National Key Laboratory of Human-Machine Hybrid Augmented Intelligence Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Shaanxi Xi’an710049 China

LiDAR-camera extrinsic calibration (LCEC) is the core for data fusion in computer vision. Existing methods typically rely on customized calibration targets or fixed scene types, lacking the flexibility to handle variations in sensor data and environmental contexts. This paper introduces EdO-LCEC, the first environment-driven, online calibration approach that achieves human-like adaptability. Inspired by the human perceptual system, EdO-LCEC incorporates a generalizable scene discriminator to actively interpret environmental conditions, creating multiple virtual cameras that capture detailed spatial and textural information. To overcome cross-modal feature matching challenges between LiDAR and camera, we propose dual-path correspondence matching (DPCM), which leverages both structural and textural consistency to achieve reliable 3D-2D correspondences. Our approach formulates the calibration process as a spatial-temporal joint optimization problem, utilizing global constraints from multiple views and scenes to improve accuracy, particularly in sparse or partially overlapping sensor views. Extensive experiments on real-world datasets demonstrate that EdO-LCEC achieves state-of-the-art performance, providing reliable and precise calibration across diverse, challenging environments. Copyright © 2025, The Authors. All rights reserved.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

DMSACNN: Deep Multiscale Attentional Convolutional Neural Network for EEG-Based Motor Decoding

引用

IEEE Journal of Biomedical and Health Informatics 2025年 PP卷 PP页

作者： Liu, Ke Xing, Xin Yang, Tao Yu, Zhuliang Xiao, Bin Wang, Guoyin Wu, Wei Chongqing University of Posts and Telecommunications School of Computer Science and Technology Chongqing400065 China Chongqing University of Posts and Telecommunications Key Laboratory of Big Data Intelligent Computing China Chongqing University of Posts and Telecommunications Key Laboratory of Cyberspace Big Data Intelligent Security of Ministry of Education China South China University of Technology College of Automation Science and Engineering Guangzhou510641 China Chongqing Normal University National Center for Applied Mathematics in Chongqing Chongqing401331 China Shanghai Jiao Tong University School of Medicine Songjiang Hospital Songjiang Research Institute Shanghai Key Laboratory of Emotions and Affective Disorders Shanghai201600 China

Objective: Accurate decoding of electroencephalogram (EEG) signals has become more significant for the brain-computer interface (BCI). Specifically, motor imagery and motor execution (MI/ME) tasks enable the control of external devices by decoding EEG signals during imagined or real movements. However, accurately decoding MI/ME signals remains a challenge due to the limited utilization of temporal information and ineffective feature selection methods. Methods: This paper introduces DMSACNN, an end-to-end deep multiscale attention convolutional neural network for MI/ME-EEG decoding. DMSACNN incorporates a deep multiscale temporal feature extraction module to capture temporal features at various levels. These features are then processed by a spatial convolutional module to extract spatial features. Finally, a local and global feature fusion attention module is utilized to combine local and global information and extract the most discriminative spatiotemporal features. Main results: DMSACNN achieves impressive accuracies of 78.20%, 96.34% and 70.90% for hold-out analysis on the BCI-IV-2a, High Gamma and OpenBMI datasets, respectively, outperforming most of the state-of-the-art methods. Conclusion and significance: These results highlight the potential of DMSACNN in robust BCI applications. Our proposed method provides a valuable solution to improve the accuracy of the MI/ME-EEG decoding, which can pave the way for more efficient and reliable BCI systems. The source code for DMSACNN is available at https://***/xingxin-99/***. © 2025 IEEE.

关键词： Convolutional neural networks

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：