检索结果-内蒙古大学图书馆

Maritime Unmanned Rescue System-of-Systems Design Based on Attention Transformer

学校读者我要写书评

暂无评论

Maritime Unmanned Rescue System-of-Systems Design Based on A...

IEEE International Conference on Unmanned Systems (ICUS)

作者： Wei Ding Zhenjun Ming Guoxin Wang Yan Yan Anton Van Beek Hongfei Zhan School of Mechanical Engineering Beijing Institute of Technology Beijing China Yangtze Delta Region Academy of Beijing Institute of Technology Zhejiang China Key Laboratory of Industry Knowledge & Data Fusion Technology and Application Ministry of Industry and Information Technology Beijing China Shanghai Aircraft Design and Research Institute Shanghai China

ISBN: (数字)9798350384185

ISBN: (纸本)9798350384192

When natural or man-made disasters occur at sea, a maritime unmanned rescue system-of-systems (MURSoSs), as an important guarantee for the safety of people's lives and property, has a rapid response to emergency rescue services. In the design process of MURSoSs, it is often faced with problems such as unexplainable mechanisms and inaccurate modeling due to the characteristics of multi-level coupling and irregular emergence. A design method of MURSoSs based on an attention Transformer is proposed. First, this paper decomposes the MURSoSs into a multi-level organizational structure composed of individual performance, group structure, and overall effectiveness. Second, the maritime unmanned rescue simulation environment is constructed, to obtain the multi-level evolution data of group structure and overall effectiveness under different individual performance, and the attention Transformer is used to mine the functional correlation relationship between levels. Finally, the experimental simulation prediction is carried out by using this function relationship. Taking the design of MURSoSs as an example, the results show that the constructed model accurately quantifies the correlation relationship between levels and effectively reveal the internal logic of the emergence process of maritime rescue.

关键词： Couplings Correlation Autonomous systems Disasters Design methodology Transformers Logic

Inverse extreme learning machine for learning with label proportions

学校读者我要写书评

暂无评论

Inverse extreme learning machine for learning with label pro...

IEEE International Conference on Big data

作者： Limeng Cui Jiawei Zhang Zhensong Chen Yong Shi Philip S. Yu School of Computer and Control Engineering University of Chinese Academy of Sciences Beijing China Department of Computer Science Florida State University FL USA Chinese Academy of Sciences Key Laboratory of Big Data Mining and Knowledge Management Beijing China Department of Computer Science University of Illinois at Chicago IL USA

In large-scale learning problem, the scalability of learning algorithms is usually the key factor affecting the algorithm practical performance, which is determined by both the time complexity of the learning algorithms and the amount of supervision information (i.e., labeled data). Learning with label proportions (LLP) is a new kind of machine learning problem which has drawn much attention in recent years. Different from the well-known supervised learning, LLP can estimate a classifier from groups of weakly labeled data, where only the positive/negative class proportions of each group are known. Due to its weak requirements for the input data, LLP presents a variety of real-world applications in almost all the fields involving anonymous data, like computer vision, fraud detection and spam filtering. However, even through the required labeled data is of a very small amount, LLP still suffers from the long execution time a lot due to the high time complexity of the learning algorithm itself. In this paper, we propose a very fast learning method based on inversing output scaling process and extreme learning machine, namely Inverse Extreme Learning Machine (IELM), to address the above issues. IELM can speed up the training process by order of magnitudes for large datasets, while achieving highly competitive classification accuracy with the existing methods at the same time. Extensive experiments demonstrate the significant speedup of the proposed method. We also demonstrate the feasibility of IELM with a case study in real-world setting: modeling image attributes based on ImageNet Object Attributes dataset.

关键词： Training Calibration Support vector machines Supervised learning Visualization Optimization

Fully-convolutional intensive feature flow neural network for text recognition

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Zhang, Zhao Tang, Zemin Zhang, Zheng Wang, Yang Qin, Jie Wang, Meng School of Computer Science and Technology Soochow University China Key Laboratory of Knowledge Engineering with Big Data Ministry of Education School of Computer and Information Hefei University of Technology Hefei China Bio-Computing Research Center Harbin Institute of Technology Shenzhen518055 China Inception Institute of Artificial Intelligence Abu Dhabi United Arab Emirates

The Deep Convolutional Neural Networks (CNNs) have obtained a great success for pattern recognition, such as recognizing the texts in images. But existing CNNs based frameworks still have several drawbacks: 1) the traditaional pooling operation may lose important feature information and is unlearnable;2) the traditional convolution operation optimizes slowly and the hierarchical features from different layers are not fully utilized. In this work, we address these problems by developing a novel deep network model called Fully-Convolutional Intensive Feature Flow Neural Network (IntensiveNet). Specifically, we design a further dense block called intensive block to extract the feature information, where the original inputs and two dense blocks are connected tightly. To encode data appropriately, we present the concepts of dense fusion block and further dense fusion operations for our new intensive block. By adding short connections to different layers, the feature flow and coupling between layers are enhanced. We also replace the traditional convolution by depthwise separable convolution to make the operation efficient. To prevent important feature information being lost to a certain extent, we use a convolution operation with stride 2 to replace the original pooling operation in the customary transition layers. The recognition results on large-scale Chinese string and MNIST datasets show that our IntensiveNet can deliver enhanced recognition results, compared with other related deep models. Copyright © 2019, The Authors. All rights reserved.

关键词： Convolution

Explicit Unsupervised Feature Selection Based on Structured Graph and Locally Linear Embedding

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Miao, Jianyu Zhao, Jingjing Yang, Tiejun Fan, Chao Tian, Yingjie Shi, Yong Xu, Mingliang School of Artificial Intelligence and Big Data Henan University of Technology Zhengzhou450001 China College of Information Science and Engineering Henan University of Technology Zhengzhou450001 China School of Economics and Management University of Chinese Academy of Sciences Beijing100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing100190 China School of Computer and Artificial Intelligence Zhengzhou University Zhengzhou450001 China

Numerous redundant and irrelevant features, and outliers are usually contained in high-dimensional data whose presence, if ignored, can bring detrimental effects on the performance of data processing tasks. Feature selection as a trending topic in a great deal of domains has been greatly concerned, which can effectively deal with noise and outlier. In this work, we propose a novel unsupervised method that unifies the explicit feature selective matrix learning and structured graph learning into a framework. An explicit selection matrix only consisting of 0 and 1 are designed, which can be integrated into locally linear embedding, and can be effectively and efficiently solved with closed-form solution. Furthermore, we take into account the local consistency between the samples so that the low dimensional manifold structures of samples can be preserved to a better degree. Instead of using the pre-defined similarity matrix to construct graph, we make use of the way of learning to obtain the adaptive graph. Besides, for the purpose of exploiting the cluster structure of data, we impose a rank constraint on the graph. Notably, both explicit selection matrix and intrinsic structure are learned in low-dimensional feature subspace, and thus the proposed methodology is more straightforward. We present an effective and efficient algorithm for the resulting problem based on alternative optimization strategy, and establish its convergence and computational complexity analysis results. Extensive experiments verify that our proposed approach can significantly outperform advanced methods. © 2023, The Authors. All rights reserved.

关键词： Matrix algebra

ReconBoost: Boosting Can Achieve Modality Reconcilement

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Hua, Cong Xu, Qianqian Bao, Shilong Yang, Zhiyong Huang, Qingming Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores a novel multi-modal alternating learning paradigm pursuing a reconciliation between the exploitation of uni-modal features and the exploration of cross-modal interactions. This is motivated by the fact that current paradigms of multi-modal learning tend to explore multi-modal features simultaneously. The resulting gradient prohibits further exploitation of the features in the weak modality, leading to modality competition, where the dominant modality overpowers the learning process. To address this issue, we study the modality-alternating learning paradigm to achieve reconcilement. Specifically, we propose a new method called ReconBoost to update a fixed modality each time. Herein, the learning objective is dynamically adjusted with a reconcilement regularization against competition with the historical models. By choosing a KL-based reconcilement, we show that the proposed method resembles Friedman's Gradient-Boosting (GB) algorithm, where the updated learner can correct errors made by others and help enhance the overall performance. The major difference with the classic GB is that we only preserve the newest model for each modality to avoid overfitting caused by ensembling strong learners. Furthermore, we propose a memory consolidation scheme and a global rectification scheme to make this strategy more effective. Experiments over six multi-modal benchmarks speak to the efficacy of the method. We release the code at https://***/huacong/ReconBoost. Copyright © 2024, The Authors. All rights reserved.

关键词： Machine learning

Generating Action-conditioned Prompts for Open-vocabulary Video Action Recognition 24

学校读者我要写书评

暂无评论

Generating Action-conditioned Prompts for Open-vocabulary Vi...

32nd ACM International Conference on Multimedia, MM 2024

作者： Jia, Chengyou Luo, Minnan Chang, Xiaojun Dang, Zhuohang Han, Mingfei Wang, Mengmeng Dai, Guang Dang, Sizhe Wang, Jingdong School of Computer Science and Technology MOEKLINNS Lab Xi'an Jiaotong University Shaanxi Xi'an China University of Science and Technology of China Anhui Hefei China School of Computer Science and Technology Xi'an Jiaotong University Shaanxi Xi'an China ReLER Lab AAII University of Technology Sydney SydneyNSW Australia Zhejiang University of Technology College of Computer Science and Technology China SGIT AI Lab State Grid Corporation of China Beijing China Baidu Inc Beijing China United Arab Emirates Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University Xi'an710049 China SGIT AI Lab State Grid Corporation of China China School of Computer Science and Technology Ministry of Education Key Laboratory of Intelligent Networks and Network Security Xi'an Jiaotong University Xi'an710049 China

ISBN: (纸本)9798400706868

Exploring open-vocabulary video action recognition is a promising venture, which aims to recognize previously unseen actions within any arbitrary set of categories. Existing methods typically adapt pretrained image-text models to the video domain, capitalizing on their inherent strengths in generalization. A common thread among such methods is the augmentation of visual embeddings with temporal information to improve the recognition of seen actions. Yet, they compromise with standard less-informative action descriptions, thus faltering when confronted with novel actions. Drawing inspiration from human cognitive processes, we argue that augmenting text embeddings with human prior knowledge is pivotal for open-vocabulary video action recognition. To realize this, we innovatively blend video models with Large Language Models (LLMs) to devise Action-conditioned Prompts. Specifically, we harness the knowledge in LLMs to produce a set of descriptive sentences that contain distinctive features for identifying given actions. Building upon this foundation, we further introduce a multi-modal action knowledge alignment mechanism to align concepts in video and textual knowledge encapsulated within the prompts. Extensive experiments on various video benchmarks, including zero-shot, few-shot, and base-to-novel generalization settings, demonstrate that our method not only sets new SOTA performance but also possesses excellent interpretability. © 2024 ACM.

关键词： Embeddings

OSGI-based system for power quality monitoring and evaluation

学校读者我要写书评

暂无评论

International Agricultural engineering Journal 2017年第4期26卷 263-269页

作者： Yu, Lina Zhang, Ganghong Niu, Boya Gao, Wanlin Huang, Liangji Zhao, Long Wang, Yan Lin, Kequan Zuo, Min Institute of Semiconductor Chinese Academy of Sciences Beijing100083 China Key Laboratory of Agricultural Informatization Standardization Ministry of Agriculture Beijing100083 China Beijing Key Laboratory of Big Data Technology for Food Safety Beijing Technology and Business University 100048 China College of Information and Computer Engineering Northeast Forestry University Harbin150040 China College of Information and Electrical Engineering China Agricultural University Beijing100083 China School of Microelectronics University of Chinese Academy of Sciences Beijing100049 China

Traditionally, the systems of power quality monitoring and evaluation are usually designed using Client/Server (C/S) two-layer structure. However, with the development of IT and J2EE technology, power quality monitoring and evaluation system, which is based on Browser/Server (B/S) mode and J2EE enterprise structure, has been gradually replacing the software system of traditional C/S structure. Though this mode has solved many practical problems, especially, in the process of system applications when real-time requirements and data communication processing capacity are more essential than the other factors, there are still some limitations such as low efficiency of code execution and lack of supporting for processing bottom layer data. In order to solve these problems, this paper introduces Open Services Gateway Initiative (OSGi) framework specification, integrating dynamic components technology and ideas of OSGi microkernel into power quality monitoring and evaluation system based upon J2EE. It improved the efficiency of program-code execution in the process of power quality monitoring data collection and processing. It also solved problems of slow processing speed of massive data calculation, analysis, storage, and over time of front-end application displaying. © 2017, Asian Association for Agricultural engineering. All rights reserved.

关键词： Efficiency

Multi-Temporal Relationship Inference in Urban Areas

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Shuangli Zhou, Jingbo Liu, Ji Xu, Tong Chen, Enhong Xiong, Hui School of Computer Science and Technology University of Science and Technology of China Baidu Research China Business Intelligence Lab Baidu Research China Big Data Lab Baidu Research China School of Computer Science and Technology University of Science and Technology of China State Key Laboratory of Cognitive Intelligence China Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China State Key Laboratory of Cognitive Intelligence China The Department of Computer Science and Engineering The Hong Kong University of Science and Technology China

Finding multiple temporal relationships among locations can benefit a bunch of urban applications, such as dynamic offline advertising and smart public transport planning. While some efforts have been made on finding static relationships among locations, little attention is focused on studying time-aware location relationships. Indeed, abundant location-based human activities are time-varying and the availability of these data enables a new paradigm for understanding the dynamic relationships in a period among connective locations. To this end, we propose to study a new problem, namely multi-Temporal relationship inference among locations (Trial for short), where the major challenge is how to integrate dynamic and geographical influence under the relationship sparsity constraint. Specifically, we propose a solution to Trial with a graph learning scheme, which includes a spatially evolving graph neural network (SEENet) with two collaborative components: spatially evolving graph convolution module (SEConv) and spatially evolving self-supervised learning strategy (SE-SSL). SEConv performs the intra-time aggregation and inter-time propagation to capture the multifaceted spatially evolving contexts from the view of location message passing. In addition, SE-SSL designs time-aware self-supervised learning tasks in a global-local manner with additional evolving constraint to enhance the location representation © 2023, CC BY.

关键词： Location

Analysis of 5G academic Network based on graph representation learning method

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Li, Xiaoming Xu, Guangquan Yu, Wei Jiao, Pengfei Song, Xiangyu Zhejiang Yuexiu University of Foreign Languages School of International Business Shaoxing China Shaoxing Key Laboratory of Intelligent Monitoring and Prevention of Smart City Shaoxing China School of Big Data School of Big Data Qingdao Huanghai University Qingdao China College of Intelligence and Computing Tianjin University Tianjin China School of IT Faculty of Science Engineering and Built Environment Deakin University GeelongVIC3220 Australia

With the rapid development of 5th Generation Mobile Communication Technology (5G), the diverse forms of collaboration and extensive data in academic social networks constructed by 5G papers make the management and analysis of academic social networks increasingly challenging. Despite the particular success achieved by representation learning in analyzing academic and social networks, most present presentation learning models focus on maintaining the first-order and second-order similarity of nodes. They rarely possess similar structural characteristics of spatial independence in the network. This paper proposes a Low-order Network representation Learning Model (LNLM) based on Non-negative Matrix Factorization (NMF) to solve these problems. The model uses the random walk method to extract low-order features of nodes and map multiple components to a low-dimensional space, effectively maintaining the internal correlation between members. This paper verifies the performance of this model, conducts comparative experiments on four test datasets and four real network datasets through downstream tasks such as multi-label classification, clustering, and link prediction. Comparing eight mainstream network representation learning models shows that the proposed model can significantly improve the detection efficiency and learning methods and effectively extract local and low-order features of the network. © 2021, CC BY.

关键词： Non-negative matrix factorization