检索结果-内蒙古大学图书馆

Chinese Automation Congress (CAC)

作者： Yazhen Zhou Shuang Shi Hongyan Liu Yonghui Zhang Ke Gu Junfei Qiao Faculty of Information Technology Beijing University of Technology Beijing China Engineering Research Center of Intelligent Perception and Autonomous Control Ministry of Education Beijing Laboratory of Smart Environmental Protection Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing Artificial Intelligence Institute

ISBN: (纸本)9781665426480

Turbidity is one main indicator of quality typically used for monitoring water pollution and water eutrophication. The monitoring technology of river water quality can be divided into contact monitoring technology based on physical sensors and non-contact monitoring technology based on remote sensing satellites. The traditional contact monitoring technology has limited monitoring spatial resolution. As a new technology, the remote sensing monitoring technology of the river can conveniently solve the above-mentioned shortcomings and realize the coverage of the whole river basin. However, due to the scarcity of remote sensing data and the measurement errors of remote sensing satellites themselves, learning-based turbidity measurement methods have weak generalization ability and thus are easily prone to produce large deviations. To effectively address such difficulty, a noise injection method is introduced into a river turbidity measurement model based on ensemble learning. To be specific, we randomly generate many noise sets and add them to the remote sensing data to make it closer to the real application scene, and then adopt the ensemble learning model to estimate river turbidity. Experiments validate that the random noise injection strategy can effectively improve the generalization performance of river turbidity measurement.

关键词： Satellites Water quality Predictive models Water pollution Rivers Pollution measurement Sensors

来源：评论

学校读者我要写书评

暂无评论

Optimization of Air Conditioning Energy Consumption Based on Indoor Comfort Degree

Optimization of Air Conditioning Energy Consumption Based on...

引用

Chinese Control and Decision Conference, CCDC

作者： Jianhui Fang Xiaoli Li Kang Wang Faculty of Information Technology Beijing University of Technology Beijing Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing Advanced Innovation Center for Future Internet Technology Beijing University of Technology Beijing China Engineering Research Center of Digital Community Ministry of Education Beijing University of Technology Beijing China

ISBN: (纸本)9781665478977

With the aggravation of energy shortage and environmental degradation, energy saving and emission reduction are imperative. Among them, the energy consumption of air conditioners accounts for a large proportion, and there is a great potential to enhance the energy consumption system of air conditioners to improve the situation. Therefore, reducing the energy consumption of air conditioners has become a hot topic of concern. However, traditional methods often ignore the requirements of indoor personnel for comfort and do not meet the actual needs. To address this problem, this paper proposes to combine thermal comfort (PMV) and air quality (IAQ) as an integrated indoor comfort level, and the genetic algorithm optimized BP neural network (GA-BP) algorithm is used to model the comfort-energy consumption, which is verified by simulation, and the results prove that the model has small error and is feasible. Based on this, the energy consumption optimization strategy is proposed to achieve the relative optimal relationship between human comfort and energy saving.

关键词： Air conditioning Energy consumption Atmospheric modeling Neural networks Predictive models Air quality Mathematical models

来源：评论

学校读者我要写书评

暂无评论

Poisoning as a Post-Protection: Mitigating Membership Privacy Leakage From Gradient and Prediction of Federated Models

引用

IEEE Transactions on Dependable and Secure computing 2025年

作者： Liu, Gaoyang Xu, Tianlong Yang, Yang Abdelmoniem, Ahmed M. Wang, Chen J., Liu Huazhong University of Science and Technology Hubei Key Laboratory of Internet of Intelligence School of Electronic Information and Communications Wuhan430074 China Simon Fraser University School of Computing Science BurnabyBCV5A 1S6 Canada Ministry of Education Key Laboratory of Intelligent Sensing System and Security China Hubei University School of Artificial Intelligence Wuhan430062 China Queen Mary University of London School of Electronic Engineering and Computer Science United Kingdom

Federated learning (FL) is a distributed learning paradigm that enables multiple clients to train a unified model without sharing their private data. However, recent works demonstrate that FL models are vulnerable to membership inference attacks (MIAs), which can infer whether a data sample was used to train a given FL model. Existing countermeasures either require far-reaching modifications of FL training process or enforce extra processing in prediction phase, yielding them unlikely to be applied well in practice. In this paper, we design a post-protection mechanism, dubbed P2-Protection, which degrades the inference performance of MIAs by simultaneously poisoning the prediction and gradient of the target FL model to reduce the privacy leakage of training data while keeping the model prediction accuracy. P2-Protection only involves one additional training round to embed the poisoned prediction and gradient into the target FL model, without requiring model retraining or training process modification. We evaluate P2-Protection and compare it with two state-of-the-art defenses against three MIAs on five realistic datasets. Experimental results show that P2-Protection outperforms the existing defenses by offering limited implement overhead and improved utility-privacy trade-off. © 2004-2012 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

GSLB: The Graph Structure Learning Benchmark 37

GSLB: The Graph Structure Learning Benchmark

引用

37th Conference on Neural Information Processing systems, NeurIPS 2023

作者： Li, Zhixun Wang, Liang Sun, Xin Luo, Yifan Zhu, Yanqiao Chen, Dingshuo Luo, Yingtao Zhou, Xiangxin Liu, Qiang Wu, Shu Yu, Jeffrey Xu Department of Systems Engineering and Engineering Management The Chinese University of Hong Kong Hong Kong Center for Research on Intelligent Perception and Computing State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China Department of Automation University of Science and Technology of China China School of Cyberspace Security Beijing University of Posts and Telecommunications China Department of Computer Science University of California Los Angeles United States Heinz College of Information Systems and Public Policy Machine Learning Department School of Computer Science Carnegie Mellon University United States

ISBN: (纸本)9781713899921

Graph Structure Learning (GSL) has recently garnered considerable attention due to its ability to optimize both the parameters of Graph Neural Networks (GNNs) and the computation graph structure simultaneously. Despite the proliferation of GSL methods developed in recent years, there is no standard experimental setting or fair comparison for performance evaluation, which creates a great obstacle to understanding the progress in this field. To fill this gap, we systematically analyze the performance of GSL in different scenarios and develop a comprehensive Graph Structure Learning Benchmark (GSLB) curated from 20 diverse graph datasets and 16 distinct GSL algorithms. Specifically, GSLB systematically investigates the characteristics of GSL in terms of three dimensions: effectiveness, robustness, and complexity. We comprehensively evaluate state-of-the-art GSL algorithms in node- and graph-level tasks, and analyze their performance in robust learning and model complexity. Further, to facilitate reproducible research, we have developed an easy-to-use library for training, evaluating, and visualizing different GSL methods. Empirical results of our extensive experiments demonstrate the ability of GSL and reveal its potential benefits on various downstream tasks, offering insights and opportunities for future research. The code of GSLB is available at: https://***/GSL-Benchmark/GSLB. © 2023 Neural information processing systems foundation. All rights reserved.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Adaptive admittance control of human-exoskeleton system using RNN optimization

Adaptive admittance control of human-exoskeleton system usin...

引用

2021 IEEE International Conference on Real-Time computing and Robotics, RCAR 2021

作者： Lian, Pengchen He, Yong Ma, Yue Liu, Jingshuai Wu, Xinyu Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen518055 China University of Chinese Academy of Sciences Beijing100049 China CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China

ISBN: (纸本)9781665436786

For wearable exoskeletons, ensuring safety and stability while reducing the effort of human lower limbs during walking remains a challenge. The level of safety can be guaranteed by constraining the exoskeleton robot to never exhibit any erratic behavior. But beyond that, the cooperative motion generated in human-exoskeleton interactions should be truly intuitive and should minimize the limitations of human performance. Therefore, this paper presented a new adaptive admittance control law, which not only ensures the stability of the lower limb exoskeleton in the constrained motion but also provides a very harmonious human-exoskeleton interaction. The proposed approach is applied to the movement of the exoskeleton containing the knee joint in the swing phase. The input of the admittance control system is the human-exoskeleton interaction force measured by one single-dimensional force sensor. The performance of the method was theoretically analyzed and discussed. Experiments were conducted in Matlab simulation environment to verify the effectiveness of aid to the swinging leg. Compared with the fixed admittance control, the adaptive admittance control system optimized by a Recurrent Neural Network(RNN) greatly improves the level of interaction between the exoskeleton and the wearer. © 2021 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

A Learning Human-Based Method For Peg-In-Hole Assembly Using ELM

A Learning Human-Based Method For Peg-In-Hole Assembly Using...

引用

IEEE International Conference on Real-time computing and Robotics (RCAR)

作者： Juyi Sheng Sheng Liu Bing Zhu Chi Zhu Yongsheng Ou Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China University of Chinese Academy of Sciences Beijing China Maebashi Institute of Technology Japan Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems (#2019B121205007)

This paper focuses on using sensor information to adjust the position for assembly in the presence of uncertainty error in vision. Firstly, a human demonstration of the peg-in-hole assembly is provided, and the data is collected for the next step of training. We start with a human demonstration and collect training data. A network is trained with 6D Force/Torque sensor (F/T sensor) as input and a strategy of which direction the robot end-effector needs to move as output. An algorithm using Extreme Learning Machines (ELM) search is proposed. This is a human-like method of searching for holes. We validated the effectiveness of our method on a KUKA iiwa 7 robot arm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

TransMixer: A Hybrid Transformer and CNN Architecture for Polyp Segmentation

TransMixer: A Hybrid Transformer and CNN Architecture for Po...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Yanglin Huang Donghui Tan Yuan Zhang Xuanya Li Kai Hu Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Xiangtan University Xiangtan China Affiliated Hospital of Xiangnan University Chengzhou China Baidu Inc Beijing China Key Laboratory of Medical Imaging and Artificial Intelligence of Hunan Province Xiangnan University Chenzhou China

ISBN: (数字)9781665468190

ISBN: (纸本)9781665468206

Learning how to fully extract global representations and local features is a key factor in improving the performance of polyp segmentation. In this paper, we explore the potential of combined techniques of Transformers and convolutional neural networks (CNNs) to address the challenges of polyp segmentation. Specifically, we present TransMixer, a hybrid interaction fusion architecture of the Transformer branch and the CNN branch, which is able to enhance the local details of global representations and the global context awareness of local features. To achieve this, we first bridge the semantic gap between the Transformer branch and the CNN branch through the Interaction Fusion Module (IFM), and then make full use of both respective properties to enhance polyp feature representations. After that, we further propose the Hierarchical Attention Module (HAM) to collect polyp semantic information from high-level features to gradually guide the recovery of polyp spatial information in low-level features. Quantitative and qualitative results show that the proposed model is more robust to various complex situations compared to existing methods, and achieves state-of-the-art performance in polyp segmentation.

关键词： Deep learning Bridges Semantics Context awareness Benchmark testing Transformers Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Distilled Transformers with Locally Enhanced Global Representations for Face Forgery Detection

arXiv

引用

arXiv 2024年

作者： Zhang, Yaning Li, Qiufu Yu, Zitong Shen, Linlin Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Guangdong Shenzhen518060 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Shenzhen518060 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Shenzhen518129 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Guangdong Shenzhen518060 China School of Computing and Information Technology Great Bay University Guangdong Dongguan523000 China

Face forgery detection (FFD) is devoted to detecting the authenticity of face images. Although current CNN-based works achieve outstanding performance in FFD, they are susceptible to capturing local forgery patterns generated by various manipulation methods. Though transformer-based detectors exhibit improvements in modeling global dependencies, they are not good at exploring local forgery artifacts. Hybrid transformer-based networks are designed to capture local and global manipulated traces, but they tend to suffer from the attention collapse issue as the transformer block goes deeper. Besides, soft labels are rarely available. In this paper, we propose a distilled transformer network (DTN) to capture both rich local and global forgery traces and learn general and common representations for different forgery faces. Specifically, we design a mixture of expert (MoE) module to mine various robust forgery embeddings. Moreover, a locally-enhanced vision transformer (LEVT) module is proposed to learn locally-enhanced global representations. We design a lightweight multi-attention scaling (MAS) module to avoid attention collapse, which can be plugged and played in any transformer-based models with only a slight increase in computational costs. In addition, we propose a deepfake self-distillation (DSD) scheme to provide the model with abundant soft label information. Extensive experiments show that the proposed method surpasses the state of the arts on five deepfake datasets. Copyright © 2024, The Authors. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Coordinate Descent Clustering with Trace Difference Criterion for Joint Clustering and Feature Extraction

SSRN

引用

SSRN 2023年

作者： Wang, Quan Wang, Fei Li, Zhongheng Wang, Zheng Nie, Feiping Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Shaanxi Xi’an710049 China Beijing Key Laboratory of Intelligent Space Robotic Systems Technology and Applications Beijing Institute of Spacecraft System Engineering Beijing100094 China School of Software Engineering Xi’an Jiaotong University Xi’an710049 China Northwestern Polytechnical University Shaanxi Xi’an710072 China

Joint clustering and dimensionality reduction methods are a promising solution to clustering due to its scalability to high-dimensional data. Some methods leverage trace ratio criterion and attain clusters by borrowing the K-means algorithm. However, trace ratio criterion has no close-formed solution for the discriminative projection matrix and the K-means algorithm has a limited capacity to handle the many-cluster problem. In this paper, Coordinate Descent Clustering with Trace Difference criterion (CDCTD) is proposed for joint clustering and feature extraction. Formulating the objective function as a direct trace difference criterion containing a balance parameter, CDCTD harmonizes between-cluster scatter maximization and within-cluster scatter minimization by the balance parameter. Using the direct trace difference criterion, CDCTD can straightforward solve for the discriminative projection matrix and avoid obtaining a poor discriminative projection matrix in the iterative manner when a bad cluster start is given. CDCTD uses the coordinate descent method for clustering, improving the ability to address the many-cluster problem. Extensive experiments show that CDCTD has achieved significant performance improvements compared to previous trace ratio criterion related joint clustering and feature extraction methods, and also outperformed other clustering methods in most cases. © 2023, The Authors. All rights reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Hexagonal Convolutional Neural Network for Spatial Transcriptomics Classification

Hexagonal Convolutional Neural Network for Spatial Transcrip...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Jing Gao Fa Zhang Kai Hu Xuefeng Cui Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Xiangtan University Xiangtan China Institute of Computing Technology Chinese Academy of Sciences Beijing China Key Laboratory of Medical Imaging and Artificial Intelligence of Hunan Province Xiangnan University Chenzhou China School of Medical Technology Beijing Institute of Technology Beijing China School of Computer Science and Technology Shandong University Qingdao China

ISBN: (数字)9781665468190

ISBN: (纸本)9781665468206

Recent advances in spatial transcriptomics have enabled the comprehensive measurement of transcriptional profiles while retaining the spatial contextual information. Identifying spatial domains is a critical step in the analysis of spatially resolved transcriptomics. Existing unsupervised methods perform poorly on this task owing to the large amount of noise and dropout events in the transcriptomic profiles. To address this problem, we first extend an unsupervised algorithm to a supervised learning method that can identify useful features and reduce noise hindrance. Second, inspired by the classical convolution in convolutional neural networks (CNNs), we designed a regular hexagonal convolution to compensate for the missing gene expression patterns from adjacent nodes. Compared with the graph convolution in graph neural networks (GNNs), our hexagonal convolution can preserve the relative spatial location information of different nodes in graph-structured data. Third, based on the hexagonal convolution, a novel hexagonal Convolutional Neural Network (hexCNN) is proposed for spatial transcriptomics classification. Finally, we compared the proposed hexCNN with existing methods on the DLPFC dataset. The results show that hexCNN achieves a classification accuracy of 87.2% and an average Rand index (ARI) of 78.2% (1.9% and 3.3% higher than those of GNNs).

关键词： Visualization Convolution Supervised learning Interference Spatial databases Graph neural networks 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：