检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Wang, Qin Wang, Xizhao Big Data Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China The Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China

Long-tail distributed data hinders the practical application of state-of-the-art deep models in computer vision. Consequently, exclusive methodologies for handling the long-tailed problem are proposed, focusing on different hierarchies. For embedding hierarchy, existing works manually augment the diversity of tail-class features for specific datasets. However, prior knowledge about datasets is not always available for practical use, which brings unsatisfactory generalization ability in human fine-turned augmentation under such circumstances. To figure out this problem, we introduce a novel model named Bilinear-Experts Network (BENet) with Self-Adaptive Sampler (SAS). This model leverages model-driven perturbations to tail-class embeddings while preserving generalization capability on head classes through a designed bilinear experts system. The designed perturbations adaptively augment tail-class space and shift the class boundary away from the tail-class centers. Moreover, we surprisingly find that SAS automatically assigns more significant perturbations to specific tail classes rather than fewer-sample classes, which is against the common assumption that fewer-sample classes deserve greater attention. Also, experiments conducted across various long-tailed benchmarks validate the comparable efficacy of proposed BENet. © 2024, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

HaLViT: Half of the Weights are Enough

HaLViT: Half of the Weights are Enough

引用

IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Onur Can Koyun Behçet Uğur Töreyin Dept. of Artificial Intelligence and Data Engineering Informatics Institute Signal Processing for Computational Intelligence Research Group (SP4CING) İstanbul Technical University İstanbul Türkiye

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

Deep learning architectures like Transformers and Convolutional Neural Networks (CNNs) have led to ground-breaking advances across numerous fields. However, their extensive need for parameters poses challenges for implementation in environments with limited resources. In our research, we propose a strategy that focuses on the utilization of the column and row spaces of weight matrices, significantly reducing the number of required model parameters without substantially affecting performance. This technique is applied to both Bottleneck and Attention layers, achieving a notable reduction in parameters with minimal impact on model efficacy. Our proposed model, HaLViT, exemplifies a parameter-efficient Vision Transformer. Through rigorous experiments on the ImageNet dataset and COCO dataset, HaLViT’s performance validates the effectiveness of our method, offering results comparable to those of conventional models.

关键词： Computer vision Conferences Computational modeling Deep architecture Transformers Pattern recognition Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Semi-Supervised Approach with Error Reflection for Echocardiography Segmentation

A Semi-Supervised Approach with Error Reflection for Echocar...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Han, Xiaoxiang Liu, Yiman Shang, Jiang Li, Qingli Chen, Jiangang Hu, Menghan Zhang, Qi Zhang, Yuqi Wang, Yan Shanghai University School of Communication and Information Engineering Shanghai China Lab Shanghai Institute for Advanced Communication and Data Science Shanghai China Shanghai Jiao Tong University Shanghai Children's Medical Center School of Medicine Department of Pediatric Cardiology Shanghai China Shanghai China East China Normal University Shanghai Key Laboratory of Multidimensional Information Processing Shanghai China

ISBN: (纸本)9798350386226

Segmenting internal structure from echocardiography is essential for the diagnosis and treatment of various heart diseases. Semi-supervised learning shows its ability in alleviating annotations scarcity. While existing semi-supervised methods have been successful in image segmentation across various medical imaging modalities, few have attempted to design methods specifically addressing the challenges posed by the poor contrast, blurred edge details and noise of echocardiography. These characteristics pose challenges to the generation of high-quality pseudo-labels in semi-supervised segmentation based on Mean Teacher. Inspired by human reflection on erroneous practices, we devise an error reflection strategy for echocardiography semi-supervised segmentation architecture. The process triggers the model to reflect on inaccuracies in unlabeled image segmentation, thereby enhancing the robustness of pseudo-label generation. Specifically, the strategy is divided into two steps. The first step is called reconstruction reflection. The network is tasked with reconstructing authentic proxy images from the semantic masks of unlabeled images and their auxiliary sketches, while maximizing the structural similarity between the original inputs and the proxies. The second step is called guidance correction. Reconstruction error maps decouple unreliable segmentation regions. Then, reliable data that are more likely to occur near high-density areas are leveraged to guide the optimization of unreliable data potentially located around decision boundaries. Additionally, we introduce an effective data augmentation strategy, termed as multi-scale mixing up strategy, to minimize the empirical distribution gap between labeled and unlabeled images and perceive diverse scales of cardiac anatomical structures. Extensive experiments on a public echocardiography dataset CAMUS, and a private clinical echocardiography dataset demonstrate the competitiveness of the proposed method. © 2024 IEEE.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Energy Consumption Prediction of Public Buildings Based on MEA-BP Neural Network 33

Energy Consumption Prediction of Public Buildings Based on M...

引用

第33届中国控制与决策会议

作者： Shuai Wang Hongyan Ma Jiaming Dou Yongxue Ye Jingjian Yang Beijing Key Laboratory of Intelligent Processing for Building Big Data Beijing University of Civil Engineering and Architecture National Virtual Simulation Experimental Center for Smart City Education Institute of Distributed Energy Storage Safety Big Data

ISBN: (纸本)9781665431293

data mining technology is often adopted in construction engineering to provide relevant information and reference basis for public building energy consumption *** paper proposes an optimization algorithm applying back propagation(BP) neural network and mind evolutionary algorithm(MEA) to establish a model to predict building energy *** main weather data are used as inputs to the BP neural network and daily electricity consumption is used as an *** MEA is employed to optimise the structure of the network and to predict the energy consumption of *** results demonstrate that the optimized BP neural network has higher fitting accuracy,and the predicted load value is more consistent with the actual value.

关键词： Building energy consumption BP neural network Mind evolutionary algorithm

来源：评论

学校读者我要写书评

暂无评论

Brain-inspired artificial intelligence research: A review

引用

Science China(Technological Sciences) 2024年第8期67卷 2282-2296页

作者： WANG GuoYin BAO HuaNan LIU Qun ZHOU TianGang WU Si HUANG TieJun YU ZhaoFei LU CeWu GONG YiHong ZHANG ZhaoXiang HE Sheng Chongqing Key Laboratory of Computational Intelligence Chongqing University of Posts and TelecommunicationsChongqing 400065China Key Laboratory of Cyberspace Big Data Intelligent Security Chongqing University of Posts and TelecommunicationsChongqing 400065China College of Computer and Information Science Chongqing Normal UniversityChongqing 401331China State Key Laboratory of Brain and Cognitive Science Institute of BiophysicsChinese Academy of SciencesBeijing 100101China School of Psychological and Cognitive Sciences Peking UniversityBeijing 100871China State Key Laboratory of Multimedia Information Processing School of Computer SciencePeking UniversityBeijing 100871China Department of Computer Science School of ElectronicsInformation and Electrical EngineeringShanghai Jiao Tong UniversityShanghai 200240China Faculty of Electronic and Information Engineering Xi’an Jiaotong UniversityXi’an 710049China The Center for Research on Intelligent Perception and Computing Institute of AutomationChinese Academy of SciencesBeijing 100190China Institute of Biophysics Chinese Academy of SciencesBeijing 100101China

Artificial intelligence(AI) systems surpass certain human intelligence abilities in a statistical sense as a whole, but are not yet the true realization of these human intelligence abilities and behaviors. There are differences, and even contradictions, between the cognition and behavior of AI systems and humans. With the goal of achieving general AI, this study contains a review of the role of cognitive science in inspiring the development of the three mainstream academic branches of AI based on the three-layer framework proposed by David Marr, and the limitations of the current development of AI are explored and analyzed. The differences and inconsistencies between the cognition mechanisms of the human brain and the computation mechanisms of AI systems are analyzed. They are found to be the cause of the differences and contradictions between the cognition and behavior of AI systems and humans. Additionally, eight important research directions and their scientific issues that need to focus on braininspired AI research are proposed: highly imitated bionic information processing, a large-scale deep learning model that balances structure and function, multi-granularity joint problem solving bidirectionally driven by data and knowledge, AI models that simulate specific brain structures, a collaborative processing mechanism with the physical separation of perceptual processing and interpretive analysis, embodied intelligence that integrates the brain cognitive mechanism and AI computation mechanisms,intelligence simulation from individual intelligence to group intelligence(social intelligence), and AI-assisted brain cognitive intelligence.

关键词： artificial intelligence cognitive science brain science intelligence science large language model

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Performance to Detecting Topic Shift of Large Language Models: A Study 9

Evaluating the Performance to Detecting Topic Shift of Large...

引用

9th International Conference on Intelligent Computing and Signal processing, ICSP 2024

作者： Tian, Pingfang Liu, Deting Department of Computer Science and Technology Wuhan University of Science and Technology Wuhan430065 China Institute of Scientific and Technical Information of China The Key Laboratory of the Rich Media Knowledge Organisation and Service of Digital Publishing Content Beijing100038 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan China Big Data Science and Engineering Research Institute Wuhan University of Science and Technology Wuhan430065 China

ISBN: (纸本)9798350376548

Topic shift detection aims to identify whether there is a change in the current topic of conversation or if a change is needed. The study found previous work did not evaluate the performance of large language models like ChatGPT on the task of topic shift. Therefore, this paper's main task and innovation lie in analyzing ChatGPT's performance on topic shift detection. To provide a more comprehensive evaluation, we conducted topic shift detection tasks on ChatGPT from three aspects: single utterances, adjacent utterances, and contextual levels. Additionally, to gauge the performance of large language models, we conducted experiments on multiple small-scale models and compared the results of the two models. Experimental results on the publicly available English TIAGE dataset showed that small-scale models exhibited lower recall in all three aspects, while ChatGPT performed better in the recall. This suggests that compared to small-scale models, large models are more capable of accurately detecting topic shifts. However, large models also exhibited lower precision, indicating that while ChatGPT can recognize content differences in utterances, its judgment on whether these different contents belong to the same topic is poor. © 2024 IEEE.

关键词： adjacent utterances level ChatGPT contextual level single utterances level topic shift detection

来源：评论

学校读者我要写书评

暂无评论

SAR Moving Target Segmentation and Removal Based on Deep Learning 8th

SAR Moving Target Segmentation and Removal Based on Deep L...

引用

8th EAI International Conference on Machine Learning and Intelligent Communications, MLICOM 2023

作者： Wu, Yifan Qi, Xiyu Huang, Lijia Zhang, Bingchen Yan, Lili Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China Key Laboratory of Technology in Geo-Spatial Information Processing and Application System Aerospace Information Research Institute Chinese Academy of Sciences Beijing100190 China Aerospace Information Research Institute Chinese Academy of Sciences Beijing100190 China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing100190 China China Centre for Resources Satellite Data and Application Beijing100094 China

ISBN: (纸本)9783031717154

Synthetic Aperture Radar (SAR) stands as an integral part of advanced remote sensing technology. Nevertheless, practical applications experience inevitable disturbances from moving target noise, compromising both image integrity and target detection performance. This paper introduces a pioneering approach reliant on deep learning principles for the elimination of moving target noise within SAR imaging. Firstly, we use the Back-Projection (BP) algorithm to form the foundational images from echo signals. Employing the Unet network, we subsequently acquire a segmentation map of the moving target noise. By subtracting this segmented noise map from the original image, we succeed in the effective erasure of moving targets, yielding a resultant image devoid of moving target noise. Experimental validation demonstrates that our method can effectively remove moving target noise and yield SAR images that solely contain static scenes. © ICST institute for Computer Sciences, Social Informatics and Telecommunications engineering 2024.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Design of a clever carbon monoxide monitoring system

Design of a clever carbon monoxide monitoring system

引用

Chinese Control and Decision Conference, CCDC

作者： Yanxi Cao Hongyan Ma Yingda Zhang Wei He School of Electrical and Information Engineering Beijing University of Civil Engineering and Architecture Beijing China School of Electrical and Information Engineering Institute of Distributed Energy Storage Safety Big Data Beijing Key Laboratory of Intelligent Processing for Building Big Data Beijing University of Civil Engineering and Architecture Beijing China

Carbon monoxide is a colorless and odorless gas that is extremely dangerous. Carbon monoxide cannot be accurately detected or eliminated by the senses in high concentrations in the body under relatively airtight conditions. As a result, the human body can only inhale it passively. Carbon monoxide inhalation can deplete the body's oxygen supply, causing symptoms such as nausea, dizziness, headaches, and, in severe cases, death. In response to the event's insidiousness, urgency, and gravity. Simultaneously, because the current carbon monoxide monitoring system is not portable, it is proposed to design a microcontroller as the core, with a concentration collection module, a wireless transmission module, an LCD module, and so on. Interact with information between intelligent monitoring systems via wireless transmission module and mobile phone APP. The system consists of a microcontroller, concentration acquisition module, wireless transmission module, and LCD display module. And the performance of the system is tested by changing the environmental conditions, while a control test is conducted. The results show that the system has a fast and stable transmission rate, small size, and wireless monitoring function. Users can be informed of environmental conditions via their mobile phones, providing early warning and quick alarms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Energy Efficiency Maximization in RISs-Assisted UAVs-Based Edge Computing Network Using Deep Reinforcement Learning

引用

Big data Mining and Analytics 2024年第4期7卷 1065-1083页

作者： Chuanwen Luo Jian Zhang Jianxiong Guo Yi Hong Zhibo Chen Shuyang Gu School of Information Science and Technology Beijing Forestry UniversityBeijing 100083Chinaand also with the Engineering Research Center for Forestry-Oriented Intelligent Information Processing of National Forestry and Grassland AdministrationBeijing 100083China Advanced Institute of Natural Sciences Beijing Normal UniversityZhuhai 519087Chinaand also with the Guangdong Key Lab of AI and Multi-Modal Data ProcessingBNU-HKBU United International CollegeZhuhai 519087China Department of Computer Information Systems Texas A&M University-Central TexasKilleenTX 76549USA

Edge Computing(EC)pushes computational capability to the Terrestrial Devices(TDs),providing more efficient and faster computing *** Aerial Vehicles(UAVs)equipped with EC servers can be flexibly deployed,even in complex terrains,to provide mobile computing services at all ***,UAVs can establish an air-to-ground line-of-sight link with TDs to improve the quality of communication ***,the UAV-to-TD link may be obstructed by ground obstacles such as buildings or trees,leading to sub-optimal data transmission *** surmount this issue,Reconfigurable Intelligent Surfaces(RISs)emerge as a promising technology capable of intelligently reflecting signals to enhance communication quality between UAVs and *** this paper,we consider the RISs-assisted multi-UAVs collaborative edge Computing Network(RUCN)in urban environment,in which we study the computational offloading *** goal is to maximize the overall energy efficiency of UAVs by jointly optimizing the flight duration and trajectories of UAVs,and the phase shifts of *** is worth noting that this problem has been formally established as ***,we propose the Deep Deterministic Policy Gradients based UAV Trajectory and RIS Phase shift optimization algorithm(UTRP-DDPG)to solve this complex optimization *** results of extensive numerical experiments show that the proposed algorithm outperforms the other benchmark algorithms under various parameter ***,the UTRP-DDPG algorithm improves the UAV energy efficiency by at least 2%compared to DQN algorithm.

关键词： edge computing computing offloading Unmanned Aerial Vehicle(UAV) Reconfigurable Intelligent Surface(RIS) deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Research on energy consumption prediction of public buildings based on improved support vector machine

Research on energy consumption prediction of public building...

引用

Chinese Control and Decision Conference, CCDC

作者： Liyao Yang Hongyan Ma Yingda Zhang Shengyan Li School of Electrical and Information Engineering Beijing University of Civil Engineering and Architecture Beijing China School of Electrical and Information Engineering Institute of Distributed Energy Storage Safety Big Data Beijing Key Laboratory of Intelligent Processing for Building Big Data Beijing University of Civil Engineering and Architecture Beijing China

An improved support vector machine model for energy consumption prediction is proposed to achieve efficient energy saving in buildings. In this paper, firstly, a gray correlation analysis model is used to measure the correlation between temperature, humidity, sunlight and other factors and building energy consumption. Secondly, the sparrow search algorithm (SSA) is introduced to optimize the penalty coefficient c and kernel function parameter g of the support vector machine, and then the SSA-SVM energy consumption prediction model is established. Finally, the experimental results are analyzed by comparing with the data derived from the support vector machine prediction (SVM) model and BP neural network energy consumption prediction. The experimental results show that compared with SVM and BP neural network, the prediction results of SSA-SVM model perform better in error index, indicating that the energy consumption prediction of SSA-SVM model has higher prediction accuracy; the maximum relative error of SSA-SVM prediction model is 0.0514, and the maximum relative errors of the other two models are greater than 0.55, indicating that SSA-SVM model has a higher degree of reliability.

关键词：

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：