检索结果-内蒙古大学图书馆

2024 China Automation Congress, CAC 2024

作者： Zhang, Zhenguo Cao, Yuanzhouhan Zhang, Hui Chen, Naiyue Ren, Chao Li, Yidong Key Laboratory of Big Data & Artificial Intelligence in Transportation Beijing Jiaotong University Ministry of Education China School of Computer Science and Technology Beijing Jiaotong University China College of Electronics and Information Engineering Sichuan University China

ISBN: (纸本)9798350368604

3D object detection is one of the fundamental perception tasks in autonomous driving. In recent years, perception in the Bird’s Eye View (BEV) has attracted tremendous attention due to its outstanding ability in preserving geometric cues. However, like other supervised learning tasks, BEV-based perception suffers from inadequate labeled training data. In this work, we propose the Vision BEV-MAE, a self-supervised learning approach for BEV perception from camera images. Specifically, we design a feature-level masking strategy to mask the mid-level representations, i.e., the encoded BEV features instead of directly masking input multi-view images, and reconstruct BEV features with a light-weight decoder. Our Vision BEV-MAE is independent of any geometric data such as point clouds, or any additional supervision, and can be easily implemented within any state-of-the-art BEV perception frameworks to improve the performance. We conduct experiments on benchmark dataset to validate our approach. © 2024 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Identification of coexistence of biological and non-biological aerosol particles with DAPI (4′,6-diamidino-2-phenylindole) stain

引用

Particuology 2023年第1期72卷 49-57页

作者： Ting Liu Jiaquan Zhang Junji Cao Han Zheng Changlin Zhan Hongxia Liu Lili Zhang Kai Xiao Shan Liu Dong Xiang Daizhou Zhang School of Environmental Science and Engineering Hubei Polytechnic UniversityHubei Key Laboratory of Mine Environmental Pollution Control and RemediationHuangshi 435003China Institute of Atmospheric Physics Chinese Academy of SciencesBeijing 100029China School of Computer Science and Artificial Intelligence Wuhan University of TechnologyWuhan 430063China Faculty of Environmental and Symbiotic Sciences Prefectural University of KumamotoKumamoto 862-8502Japan

The fluorescent dye 4′,6-diamidino-2-phenylindole (DAPI) has been widely used to stain microorganisms in various environment media. We applied DAPI fluorescence enumeration to airborne microorganisms and found that non-biological particles, including organic compounds, minerals, and soot, were also visible upon exposure to UV excitation under fluorescence microscope. Using laboratory-prepared biological particles as the control, we investigated the feasibility of identifying both biological and non-biological particles in the same sample with DAPI staining. We prepared biological (bacterial, fungi, and plant detritus) and non-biological (biochar, soot, mineral, metal, fly ash, salt) particles in the laboratory and enumerated the particles and their mixture with DAPI. We found that mineral particles were transparent, and biochar, soot, metals and fly ash particles were black under a filter set at excitation 350/50 nm and emission 460/50 nm bandpass (DAPI-BP), while biological particles were blue, as expected. Particles of the water-soluble salts NaCl and (NH_(4))_(2)SO_(4) were yellow under a filter set at excitation 340–380 nm and emission 425 nm long pass (DAPI-LP). Case studies with samples of dustfall, atmospheric aerosols and surface soils could allow for the quantification of the relative number of different types of particles and particles with organic matter or salt coating as well. Fluorescence enumeration with DAPI stain is thus able to identify the co-existence of biological and non-biological particles in the air, at least to the extent of those examined in this study.

关键词： 4',6-diamidino-2-phenylindole(DAPI) Biological particles Nonbiological particles Atmospheric aerosols

来源：评论

学校读者我要写书评

暂无评论

Multi-Objective Optimized Generative Adversarial Networks For Video Anomaly Detection

Multi-Objective Optimized Generative Adversarial Networks Fo...

引用

2023 China Automation Congress, CAC 2023

作者： Cao, Zhexiao Fu, Yao Wang, Tian Liu, Deyuan Wang, Jian Snoussi, Hichem Institute of Artificial Intelligence Beihang University Beijing China Changchun Institute of Optics Fine Mechanics and Physics Chinese Academy of Sciences Changchun China Institute of Artificial Intelligence Sklsde Beihang University Zhongguancun Laboratory Beijing China School of Automation Science and Electrical Engineering Beihang University Beijing China School of Computer Science Wuhan University Wuhan China University of Technology of Troyes Laboratory of Computer Science and Digital Society Troyes France

ISBN: (纸本)9798350303759

The objective of video anomaly detection is to distinguish events within videos that deviate from expected normal behavior. An effective anomaly detection model requires strong spatio-temporal feature extraction capabilities to capture both appearance and motion information from the video. We utilize a generative adversarial networks model to perform anomaly detection by predicting future frame. The model is trained with multi-objective loss function for appearance and motion constraints. We introduce multi-objective optimization algorithm to guarantee the convergence of training objectives, including intensity loss, gradient loss for appearance constraints, optical flow loss for motion constraints and adversarial loss for adversarial training. By ensuring corresponding generative outcome for both normal events to confirm to expectation and anomaly events not to do so, we obtain an anomaly detection model with satisfying experimental result on video anomaly detection datasets, showing the success of the proposed training strategy. © 2023 IEEE.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Optimizing fairness and accuracy: a Pareto optimal approach for decision-making

引用

AI and Ethics 2024年第2期5卷 1743-1756页

作者： Nagpal, Rashmi Shahsavarifar, Rasoul Goyal, Vaibhav Gupta, Amar Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology Cambridge USA Artificial Intelligence Risk Consulting Ernst & Young LLP EY Tower Toronto Canada Don Bosco School Park Circus India

In the era of data-driven decision-making, ensuring fairness and equality in machine learning models has become increasingly crucial. Multiple fairness definitions have been brought forward to evaluate and mitigate unintended fairness-related harms in real-world applications, with little research on addressing their interactions with each other. This paper explores the application of a Minimax Pareto-optimized solution to optimize individual and group fairness at individual and group levels on the Adult Census Income dataset as well as on the German Credit dataset. The objective of training a classification model with a multi-objective loss function is to achieve fair outcomes without compromising utility objectives. We investigate the interplay of different fairness definitions, including definitions of performance consistency and traditional group and individual fairness measures, amongst each other coupled with performance. The results presented in this paper highlight the feasibility of incorporating several fairness considerations into machine learning models, which can be applied to use cases with multiple sensitive features and attributes that characterize real-world applications. This research is a valuable step toward building responsible and transparent machine learning systems that can be incorporated into critical decision-making processes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Independent Vector Analysis Based Blind Interference Reduction and Signal Recovery for MIMO IoT Green Communications

引用

China Communications 2022年第7期19卷 79-88页

作者： Zhongqiang Luo Mingchun Li Chengjie Li School of Automation and Information Engineering Sichuan University of Science and EngineeringYibin 644000China Artificial Intelligence Key Laboratory of Sichuan Province Sichuan University of Science and EngineeringYibin 644000China School of School of Computer Science and Technology Southwest Minzu UniversityChengdu 610041China

In application to time convolutive mixing model or frequency domain blind separation model for wireless receiving applications,frequency domain independent component analysis(FDICA)has been a very popular method but with adverse random permutation ambiguity *** order to solve this inherent problem in FDICA assisted multiple-input multiple-output orthogonal frequency-division multiplexing(MIMO-OFDM)based the Internet of Thing(IoT)systems,this paper proposes an new detection mechanism,named independent vector analysis(IVA),for realizing blind adaptive signal recovery in MIMO IoT green communication to reduce inter-carrier interference(ICI)and multiple access interference(MAI).IVA jointly implements separation work for different frequency bin data while the FDICA deals with it *** IVA,the dependencies of frequency bins can be exploited in mitigating the random permutation *** addition,multivariate prior distributions are employed to preserve the inter-frequency dependencies for individual sources,which can result in separation performance *** results and analysis corroborate the effectiveness of the proposed method.

关键词： independent vector analysis blind source separation MIMO green communications

来源：评论

学校读者我要写书评

暂无评论

Smart Contract Vulnerability Detection Based on Mixed Channel Attention 36

Smart Contract Vulnerability Detection Based on Mixed Channe...

引用

36th International Conference on Software Engineering and Knowledge Engineering, SEKE 2024

作者： Wang, Jiao Ran Zeng, Cheng Ba, Kai Yang Quan, Qing Yu Wang, Yi Feng School of Computer Science and Information Engineering Hubei University Wuhan China School of Artificial Intelligence Hubei University Wuhan China School of Cyberspace Security Hubei University Wuhan China Key Laboratory of Intelligence Sensing System and Security Hubei University Ministry of Education Wuhan China

ISBN: (纸本)1891706594

As blockchain technology progresses, the deployment of smart contracts has become increasingly prevalent. Despite their growing popularity, smart contracts introduce substantial security risks and vulnerabilities. Present detection methodologies predominantly analyze the entirety of a contract’s source code, a process that tends to indiscriminately extract uniform features, leading to inadequate detection capabilities. Addressing these concerns, we propose a novel vulnerability detection method for smart contracts, predicated on a mixed channel attention mechanism. This approach focuses on extracting multifaceted features from pivotal code segments of smart contracts, utilizing a combination of spatial and frequency domain channel attention mechanisms. These mechanisms dynamically modulate the weights of feature channels during visualization, allowing the model to allocate greater emphasis to features of higher significance and enhance feature differentiation. This strategy is instrumental in capturing salient information within the data, thereby augmenting the model’s performance and accuracy. Empirical results substantiate that our proposed method substantially surpasses the baseline model, evidencing improvements of 5.55%, 5.42%, and 5.49% in the detection of timestamp vulnerabilities, and 4.12%, 4.29%, and 4.20% in the identification of reentrancy vulnerabilities, respectively. Our method offers a significant advancement in the efficacy of smart contract vulnerability detection and presents valuable implications for future research. © 2024 Knowledge Systems Institute Graduate School. All rights reserved.

关键词： channel attention key code slicing multiple features smart contracts vulnerability detection

来源：评论

学校读者我要写书评

暂无评论

An Efficient Multi-band Infrared Small Objects Detection Approach for Low-Altitude artificial intelligence of Thing

引用

IEEE Internet of Things Journal 2025年第12期12卷 20757-20772页

作者： Peng, Yuhuai Wang, Jing Wang, Wenqian Liu, Lei Atiquzzaman, Mohammed Guizani, Mohsen Dustdar, Schahram Northeastern University School of Computer Science and Engineering Shenyang110819 China Zhiyuan Research Institute Hangzhou310024 China Northeastern University School of Computer Science and Engineering Shenyang110819 China Xidian University State Key Laboratory of Integrated Service Networks Xi'an710071 China University of Oklahoma School of Computer Science NormanOK73019 United States Mohamed Bin Zayed University of Artificial Intelligence Department of Machine Learning Masdar United Arab Emirates Technische Universität Wien Distributed Systems Group Vienna1040 Austria

As a cutting-edge technology of low-altitude artificial intelligence of Thing (AIoT), UAV object detection significantly enhances the surveillance services capabilities of low-altitude AIoT. However, the difficulty of object detection is exacerbated by the high proportion of small and obscure objects in the captured images. To address the mentioned challenges, we present an efficient multi-band infrared small object detection approach for low-altitude intelligent surveillance services. Firstly, we propose the Multi-band infrared Image Fusion algorithm based on Cascade-GAN (MIF-CGAN), which produces fused images with high information entropy and high contrast. Then, the Transformer-based Multi-scale Dense Small Object Detection (MsDSOD) algorithm is proposed. The algorithm consists of the Global-Local Object Detection (G-LOD) network, the Object Dense Area Extraction (O-DAE) module, and the Weighted Boxes Fusion (WBF) module. It extracts small objects features at different scales from infrared images and fuses the global and local detection results to accurately identify small objects in dense scenes. Furthermore, compared to the traditional algorithms, the mean Average Precision (mAP) of MsDSOD is improved by 0.80% and the Average Precision in small object detection (APs) is improved by 0.72%. The proposed algorithm is optimally suited to deal with complex scenes with dense small objects and background occlusion. © 2014 IEEE.

关键词： Infrared imaging

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Learning Based on Information Geometry

Few-Shot Learning Based on Information Geometry

引用

2023 China Automation Congress, CAC 2023

作者： Chen, Jiacheng Fu, Yao Wang, Tian Liu, Deyuan Wang, Jian Snoussi, Hichem Institute of Artificial Intelligence Beihang University Beijing China Changchun Institute of Optics Fine Mechanics and Physics Chinese Academy of Sciences Changchun China Institute of Artificial Intelligence Sklsde Beihang University Zhongguancun Laboratory Beijing China School of Automation Science and Electrical Engineering Beihang University Beijing China School of Computer Science Wuhan University Wuhan China University of Technology of Troyes Laboratory of Computer Science and Digital Society Troyes France

ISBN: (纸本)9798350303759

Few-shot classification, as the name suggests, is a very challenging task where only a few training examples are available for each category. Extensive research has been done to solve the problem of the high cost of labeling a large number of samples. A recent research strategy is to find similarity measures between query sets and support sets for judgment. Recently, information geometry techniques have been applied in deep learning research, which explores the relationships and properties between probability distributions by treating them as geometric objects and using geometric tools. Based on information geometry, this paper characterizes differences in the geometric properties of images as differences in probability distributions. Assume that the data satisfies a multivariate Gaussian distribution and that different images are considered as different points on the manifold according to the parameters that characterize the probability distribution of the images. We measure the similarity between different images by the geodesic and validate three methods for estimating the geodesic on a neural network model with 64 neurons at four levels and improve the model performance by Firth bias. The GM, GMF, KM, and KMF methods are validated in the resnet-12 and resnet-18 frameworks using a meta-learning approach on the miniImageNet and CUB datasets, respectively. The experiments show that the models trained by the above four algorithms have good performance and have advantages over the classical algorithms. © 2023 IEEE.

关键词： Probability distributions

来源：评论

学校读者我要写书评

暂无评论

Extinction Chains Reveal Intermediate Phases Between the Safety and Collapse in Mutualistic Ecosystems

引用

Engineering 2024年第12期43卷 89-98页

作者： Guangwei Wang Xueming Liu Ying Xiao Ye Yuan Linqiang Pan Xiaohong Guan Jianxi Gao Hai-Tao Zhang The MOE Engineering Research Center of Autonomous Intelligent Unmanned Systems State Key Laboratory of Digital Manufacturing Equipment and TechnologySchool of Artificial Intelligence and AutomationHuazhong University of Science and TechnologyWuhan 430074China Guangdong HUST Industrial Technology Research Institute Huazhong University of Science and TechnologyDongguan 523808China Guangdong Provincial Engineering Technology Center of Autonomous Unmanned Vessels Dongguan 523808China MOE Key Laboratory of Intelligent Networks and Network Security&State Key Laboratory of Manufacturing Systems Xi’an Jiaotong UniversityXi’an 710049China Tsinghua National Laboratory of Information Science and Technology Department of AutomationTsinghua UniversityBeijing 100084China Department of Computer Science Rensselaer Polytechnic InstituteTroyNY 12180USA

Ecosystems are undergoing unprecedented persistent deterioration due to unsustainable anthropogenic human activities,such as overfishing and deforestation,and the effects of such damage on ecological stability are *** recent advances in experimental and theoretical studies on regime shifts and tipping points,theoretical tools for understanding the extinction chain,which is the sequence of species extinctions resulting from overexploitation,are still lacking,especially for large-scale nonlinear networked *** this study,we developed a mathematical tool to predict regime shifts and extinction chains in ecosystems under multiple exploitation situations and verified it in 26 real-world mutualistic networks of various sizes and *** discovered five phases during the exploitation process:safe,partial extinction,bistable,tristable,and collapse,which enabled the optimal design of restoration strategies for degraded or collapsed *** validated our approach using a 20-year dataset from an eelgrass restoration ***,we also found a specific region in the diagram spanning exploitation rates and competition intensities,where exploiting more species helps increase *** computational tool provides insights into harvesting,fishing,exploitation,or deforestation plans while conserving or restoring the biodiversity of mutualistic ecosystems.

关键词： Complex system Network science Overexploitation Regime shift Metastability

来源：评论

学校读者我要写书评

暂无评论

Investigating the EEG Embedding by Visualization 19th

Investigating the EEG Embedding by Visualization

引用

19th EAI International Conference on Heterogeneous Networking for Quality, Reliability, Security and Robustness, QShine 2023

作者： Wen, Yongcheng Mo, Jiawei Hu, Wenxin Liang, Feng Artificial Intelligence Research Institute Shenzhen MSU-BIT University Shenzhen China Guangdong-Hong Kong-Macao Joint Laboratory for Emotional Intelligence and Pervasive Computing Shenzhen MSU-BIT University Shenzhen China School of Computer Science and Engineering Central South University Changsha China

ISBN: (纸本)9783031651250

Visualizing EEG data helps clinical doctors and neuroscientists discover potential patterns and abnormalities before further mathematical analysis. Encoding complex EEG data into low-dimension embeddings and visualizing the points in 3-dimension axes with colors can help users quickly recognize some EEG properties. We apply contrastive learning in both self-supervised and supervised manners to extract the time-domain EEG features within different time window sizes. The color points tend to cluster into clouds based on their related classes and graph readers can roughly distinguish people’s emotions and identities directly by inspecting the graphs. With self-supervised encoders where the generated embeddings are supposed to be used for general tasks, the visualization method can also uncover the value of the original input features extracted from raw EEG data. The source code is available at: https://***/liangfengsid/visContrastive. © ICST Institute for computer sciences, Social Informatics and Telecommunications Engineering 2024.

关键词： Contrastive Learning

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：