检索结果-内蒙古大学图书馆

Low-Rate Non-Intrusive Appliance Load Monitoring Based on Graph Signal Processing

学校读者我要写书评

暂无评论

Low-Rate Non-Intrusive Appliance Load Monitoring Based on Gr...

International Conference on Security, Pattern Analysis, and Cybernetics (SPAC)

作者： Bing Zhang Shengjie Zhao Qingjiang Shi Rongqing Zhang The Key Laboratory of Embedded System and Service Computing of Ministry of Education Tongji University Shanghai China School of Software Engineering The Key Laboratory of Embedded System and Service Computing of Ministry of Education Tongji University Shanghai China School of Software Engineering Tongji University Shanghai China

ISBN: (数字)9781728159287

ISBN: (纸本)9781728159294

Thanks to the large-scale smart meters deployments around the world, non-intrusive appliance load monitoring (NILM) is receiving popularity. It aims to disaggregate the total electricity load of a home into individual appliances without resorting to any specific appliance power monitors. NILM is worthy of broad attention owing to its facilitation in energy savings. This paper regards NILM as a classification task and proposes a two-step method based on graph signal processing (GSP). In the first step, a smoothest solution is obtained by minimizing the regularization term. In the second step, gradient projection method, which uses the obtained minimizer as a start point, is adopted to optimize the while objective function, where NILM is regarded as a constrained nonlinear programming problem. The experiment results based on the open-access data set REDD clearly demonstrate that the proposed GSP-based method achieves improved performance compared with other state-of-the-art low-rate NILM approaches.

关键词： domestic appliances gradient methods graph theory nonlinear programming power system measurement signal processing smart meters Smart meters Power system measurements signal processing Nonlinear Programming gradient methods Graph theory Appliances load monitoring

Traffic flow prediction model based on deep belief network and genetic algorithm

学校读者我要写书评

暂无评论

Traffic flow prediction model based on deep belief network a...

作者： Zhang, Yaying Huang, Guan Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai200092 China

Traffic flow prediction plays an indispensable role in the intelligent transportation system. The effectiveness of traffic control and management relies heavily on the prediction accuracy. The authors propose a model based on deep belief networks (DBNs) to predict the traffic flow. Moreover, they use Fletcher-Reeves conjugate gradient algorithm to optimise the fine-tuning of model's parameters. Since the traffic flow has various features at different times such as weekday, weekend, daytime and nighttime, the hyper-parameters of the model should adapt to the time. Therefore, they employ the genetic algorithm to find the optimal hyper-parameters of DBN models for different times. The dataset from Caltrans Performance Measurement system was used to evaluate the performance of their models. The experimental results demonstrate that the proposed model achieved better performance in different times. © The Institution of Engineering and Technology 2018.

关键词： Genetic algorithms

A New One-Class Classification Method with Multiple Encoder-Decoder Pairs for Images

学校读者我要写书评

暂无评论

A New One-Class Classification Method with Multiple Encoder-...

International Conference on Intelligent Human-Machine systems and Cybernetics, IHMSC

作者： Dongxiang Chen Chungang Yan Mimi Wang Department of Electronics and Information Engineering Tongji University The Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai China

One of the main destinations of image classification methods is to screen out the images belonging to the target class (positive) and identify the images of other classes (negative). Although most classifiers are trained on both positive samples and negative samples, in reality, negative samples are often unavailable. One-class classifiers trained only on positive samples, are proposed to solve this problem. However, how to train effectively a classifier remains a daunting challenge. Considering the success of deep learning in the field of computer vision in recent years, we propose a one-class classification model for images based on convolutional neural network (CNN). The model consists of two parts of networks with different responsibilities. The network of the first part works as the discriminator, used to identify whether the images are positive. The networks of the second part, each of which consists of an encoder-decoder pair work as the guiders of the discriminator. They guide the discriminator to learn what images it should identify to be negative. Different encoder-decoder pairs can restore images to different degrees. Images restored to different degrees can be used to train the discriminator. The discriminator learns that images under a specific restored degree don't belong to the target class. The experiment results on CIFAR-10 show that our method can achieve good performance, with less difficulty in training than the GAN-based counterparts'.

关键词：

CSformer: Bridging Convolution and Transformer for Compressive Sensing

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Ye, Dongjie Ni, Zhangkai Wang, Hanli Zhang, Jian Wang, Shiqi Kwong, Sam The Department of Computer Science City University of Hong Kong 999077 Hong Kong The Department of Computer Science & Technology Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai Institute of Intelligent Science and Technology Tongji University Shanghai200092 China The School of Electronic and Computer Engineering Peking University Shenzhen Graduate School Shenzhen518055 China The Peng Cheng Laboratory Shenzhen518052 China The City University of Hong Kong Shenzhen Research Institute Shenzhen518057 China

Convolution neural networks (CNNs) have succeeded in compressive image sensing. However, due to the inductive bias of locality and weight sharing, the convolution operations demonstrate the intrinsic limitations in modeling the long-range dependency. Transformer, designed initially as a sequence-to-sequence model, excels at capturing global contexts due to the self-attention-based architectures even though it may be equipped with limited localization abilities. This paper proposes CSformer, a hybrid framework that integrates the advantages of leveraging both detailed spatial information from CNN and the global context provided by transformer for enhanced representation learning. The proposed approach is an end-to-end compressive image sensing method, composed of adaptive sampling and recovery. In the sampling module, images are measured block-by-block by the learned sampling matrix. In the reconstruction stage, the measurement is projected into dual stems. One is the CNN stem for modeling the neighborhood relationships by convolution, and the other is the transformer stem for adopting global self-attention mechanism. The dual branches structure is concurrent, and the local features and global representations are fused under different resolutions to maximize the complementary of features. Furthermore, we explore a progressive strategy and window-based transformer block to reduce the parameter and computational complexity. The experimental results demonstrate the effectiveness of the dedicated transformer-based architecture for compressive sensing, which achieves superior performance compared to state-of-the-art methods on different datasets. Copyright © 2021, The Authors. All rights reserved.

关键词： Compressed sensing

Finite time anti-synchronization of complex-valued neural networks with bounded asynchronous time-varying delays

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Liu, Xiwei Li, Zihan Department of Computer Science and Technology Tongji University Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai201804 China

In this paper, we studied the finite time anti-synchronization of master-slave coupled complex-valued neural networks (CVNNs) with bounded asynchronous time-varying delays. With the decomposing technique and the generalized {ξ, ∞}-norm, several criteria for ensuring the finite-time anti-synchronization are obtained. The whole anti-synchronization process can be divided into two parts: first, the norm of each error state component will change from initial values to 1 in finite time, then from 1 to 0 in fixed time. Therefore, the whole time is finite. Finally, one typical numerical example is presented to demonstrate the correctness of our obtained results. key words: Anti-synchronization, asynchronous, complex-valued neural network, finite time, time-varying delay Copyright © 2019, The Authors. All rights reserved.

关键词： Time varying control systems

Joint resource management for MC-NOMA: A deep reinforcement learning approach

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wang, Shaoyang Lv, Tiejun Ni, Wei Beaulieu, Norman C. Guo, Y. Jay Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing100876 China Sydney2122 Australia Beijing Key Laboratory for Network System Architecture and Convergence School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing100876 China Global Big Data Technologies Centre University of Technology Sydney UltimoNSW2007 Australia

This paper presents a novel and effective deep reinforcement learning (DRL)-based approach to addressing joint resource management (JRM) in a practical multi-carrier non-orthogonal multiple access (MC-NOMA) system, where hardware sensitivity and imperfect successive interference cancellation (SIC) are considered. We first formulate the JRM problem to maximize the weighted-sum system throughput. Then, the JRM problem is decoupled into two iterative subtasks: subcarrier assignment (SA, including user grouping) and power allocation (PA). Each subtask is a sequential decision process. Invoking a deep deterministic policy gradient algorithm, our proposed DRL-based JRM (DRL-JRM) approach jointly performs the two subtasks, where the optimization objective and constraints of the subtasks are addressed by a new joint reward and internal reward mechanism. A multi-agent structure and a convolutional neural network are adopted to reduce the complexity of the PA subtask. We also tailor the neural network structure for the stability and convergence of DRL-JRM. Corroborated by extensive experiments, the proposed DRL-JRM scheme is superior to existing alternatives in terms of system throughput and resistance to interference, especially in the presence of many users and strong inter-cell interference. DRL-JRM can flexibly meet individual service requirements of users. © 2021, CC BY.

关键词： Resource allocation

Large-scale video compression： recent advances and challenges

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2018年第5期12卷 825-839页

作者： Tao TIAN Hanli WANG Department of Computer Science and Technology Tongji University Shanghai 201804 China Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai 200092 China Shanghai Engineering Research Center of Industrial Vision Perception & Intelligent Computing Shanghai 200092 China

The evolution of social network and multimedia technologies encourage more and more people to generate and upload visual information, which leads to the generation of large-scale video data. Therefore, preeminent compression technologies are highly desired to facilitate the storage and transmission of these tremendous video data for a wide variety of applications. In this paper, a systematic review of the recent advances for large-scale video compression （LSVC） is presented. Specifically, fast video coding algorithms and effective models to improve video compression efficiency are introduced in detail, since coding complexity and compression efficiency are two important factors to evaluate video coding approaches. Finally, the challenges and fu- ture research trends for LSVC are discussed.

关键词： large-scale video compression fast video coding compression efficiency

Multi-granularity ensemble sample selection and label correction for classification with noisy labels

学校读者我要写书评

暂无评论

Applied Soft computing 2025年 180卷

作者： Kecan Cai Hongyun Zhang Witold Pedrycz Duoqian Miao Chaofan Chen Department of Computer Science and Technology Tongji University Shanghai 201804 PR China Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai 201804 PR China Department of Electrical and Computer Engineering University of Alberta Edmonton AB T6G 2R3 Canada Systems Research Institute Polish Academy of Sciences 00-901 Warsaw Poland Istinye University Faculty of Engineering and Natural Sciences Department of Computer Engineering Sariyer/Istanbul Turkiye

Sample selection is crucial in classification tasks with noisy labels, yet most existing sample selection methods rely on a single criterion. These approaches often face challenges, including low purity of selected clean samples, and underfitting due to an insufficient number of selected clean training samples. To address these challenges, this paper proposes GNet-SSLC, a novel multi-granularity network framework that integrates multiple criteria ensemble sample selection (SS) and multiple views label correction (LC). In the SS phase, this paper proposes a metric learning-based dual k-Nearest Neighbor (k-NN) sample selection method. This method first uses corrected soft labels from the initial k-NN round to guide the selection of clean samples in the subsequent k-NN round. To further enhance selection accuracy, we combine this dual k-NN approach with a small loss sample selection technique through a voting mechanism. This multiple criteria ensemble method addresses the issues of low purity and instability inherent in single criterion approaches. In the LC phase, this paper designs a multiple views label correction framework that generates high-quality pseudo-labels for selected noisy samples. A key innovation of the framework is the design of a regularized contrastive learning loss, which optimizes the semi-supervised learning process by leveraging multiple views of training samples. The additional inclusion of training samples with high-quality pseudo-labels can effectively mitigate underfitting caused by a limited number of clean training samples. Experimental results on both synthetic and real-world noisy datasets indicate that GNet-SSLC enhances the purity and stability of the selected clean samples, and significantly improves classification performance. The enhancement is particularly notable with high noise rate dataset, such as CIFAR-100 dataset with 80% noise rate, achieving a 19.3% increase in classification accuracy compared to the baseline method.

关键词： Image classification Label correction Multi-granularity Noisy label Sample selection

Hierarchical attention generative adversarial networks for cross-domain sentiment classification

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Zhang, Yuebing Miao, Duoqian Wang, Jiaqi Department of Computer Science and Technology Tongji University Shanghai China Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai China

Cross-domain sentiment classification (CDSC) is an importance task in domain adaptation and sentiment classification. Due to the domain discrepancy, a sentiment classifier trained on source domain data may not works well on target domain data. In recent years, many researchers have used deep neural network models for cross-domain sentiment classification task, many of which use Gradient Reversal Layer (GRL) to design an adversarial network structure to train a domain-shared sentiment classifier. Different from those methods, we proposed Hierarchical Attention Generative Adversarial Networks (HAGAN) which alternately trains a generator and a discriminator in order to produce a document representation which is sentimentdistinguishable but domain-indistinguishable. Besides, the HAGAN model applies Bidirectional Gated Recurrent Unit (Bi-GRU) to encode the contextual information of a word and a sentence into the document representation. In addition, the HAGAN model use hierarchical attention mechanism to optimize the document representation and automatically capture the pivots and non-pivots. The experiments on Amazon review dataset show the effectiveness of HAGAN. Copyright © 2019, The Authors. All rights reserved.

关键词： Generative adversarial networks