检索结果-内蒙古大学图书馆

A Text Multi-label Classification Scheme Based on Resampling and Ensemble Learning 8th

学校读者我要写书评

暂无评论

A Text Multi-label Classification Scheme Based on Resampling...

8th International Conference on Artificial Intelligence and Security , ICAIS 2022

作者： Wang, Tianhao Weng, Tianrang Ji, Jiacheng Zhong, Mingjun Zhang, Baili School of Computer Science and Engineering Southeast University Nanjing211189 China Key Laboratory of Computer Network and Information Integration in Southeast University Ministry of Education Nanjing211189 China Research Center for Judicial Big Data Supreme Count of China Nanjing211189 China Department of Computing Science University of Aberdeen AberdeenAB24 3UE United Kingdom

ISBN: (纸本)9783031067600

The medical dispute cases are professional and closely related to medicine. Therefore, the mediation of cases in practice depends heavily on similar historical cases. Multi-label classification of legal documents can efficiently filter irrelevant historical cases, which helps to recommend the similar historical cases faster and better. However, the imbalance and label symbiosis of the data set directly affect multi-label classification of legal documents. Therefore, a multi-label classification scheme based on resampling and ensemble learning is presented in this paper The scheme includes two parts: in the first part, in order to reduce the impact of label symbiosis on resampling, a resampling algorithm based on the average sparsity of the label set is proposed improve the imbalance of the data set;in the second one, a multi-label classification algorithm based on ensemble learning is proposed to train multiple base classifiers and combine each base classifier with a voting strategy of one vote. It can effectively improve the effect of multi-label classification. The experimental results show that the scheme proposed in this paper can improve the effect of multi-label classification and is not only suitable for legal documents but also applicable for other text data sets with imbalanced classes and label symbiosis problems. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Learning algorithms

FFCNet: Fourier Transform-Based Frequency Learning and Complex Convolutional network for Colon Disease Classification

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wang, Kai-Ni He, Yuting Zhuang, Shuaishuai Miao, Juzheng He, Xiaopu Zhou, Ping Yang, Guanyu Zhou, Guang-Quan Li, Shuo School of Biological Science and Medical Engineering Southeast University Nanjing China LIST Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing China The first affiliated hospital of Nanjing medical university Nanjing China Strasbourg France Department of Medical Biophysics University of Western Ontario LondonON Canada

Reliable automatic classification of colonoscopy images is of great significance in assessing the stage of colonic lesions and formulating appropriate treatment plans. However, it is challenging due to uneven brightness, location variability, inter-class similarity, and intra-class dissimilarity, affecting the classification accuracy. To address the above issues, we propose a Fourier-based Frequency Complex network (FFCNet) for colon disease classification in this study. Specifically, FFCNet is a novel complex network that enables the combination of complex convolutional networks with frequency learning to overcome the loss of phase information caused by real convolution operations. Also, our Fourier transform transfers the average brightness of an image to a point in the spectrum (the DC component), alleviating the effects of uneven brightness by decoupling image content and brightness. Moreover, the image patch scrambling module in FFCNet generates random local spectral blocks, empowering the network to learn long-range and local disease-specific features and improving the discriminative ability of hard samples. We evaluated the proposed FFCNet on an in-house dataset with 2568 colonoscopy images, showing our method achieves high performance outperforming previous state-of-the-art methods with an accuracy of 86.35% and an accuracy of 4.46% higher than the backbone. The project page with code is available at https://***/soleilssss/FFCNet. © 2022, CC BY.

关键词： Complex networks

SA Sketch: A self-adaption sketch framework for high-speed network

学校读者我要写书评

暂无评论

SA Sketch: A self-adaption sketch framework for high-speed n...

作者： Zhu, Haiting Zhang, Yuan Zhang, Lu He, Gaofeng Liu, Linfeng Liu, Ning School of Internet of Things Nanjing University of Posts and Telecommunications Nanjing China School of Information Engineering Nanjing University of Finance and Economics Nanjing China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing China School of Computer Science and Technology Nanjing University of Posts and Telecommunications Nanjing China

Sketch is a compact data structure used to summarize data streams. It is widely used in the measurement of network traffic, and its accuracy is higher than traditional methods. Currently, there are some typical sketches: Count-Min Sketch, CU Sketch, and Count Sketch. According to the characteristics of network traffic, we propose a new sketch framework called Self-Adaption Sketch, which is combined Sketch with Bloom Filter. In the framework, the sketch is created dynamically and the memory space is adjusted timely according to the network traffic by using the concept carrying. Our experiment results showed that the space utilization and accuracy are significantly improved while the throughput of self-adaption sketch is maintained at a relatively good level. © 2020 John Wiley & Sons, Ltd.

关键词： HIgh speed networks

Hybrid Attentional Memory network for Computational drug repositioning

学校读者我要写书评

暂无评论

arXiv 2020年

作者： He, Jieyue Yang, Xinxing Gong, Zhuo Zamit, Lbrahim School of Computer Science and Engineering Key Lab of Computer Network & Information Integration MOE Southeast University Nanjing210018 China

Background: Drug repositioning is designed to discover new uses of known drugs, which is an important and efficient method of drug discovery. Researchers only use one certain type of Collaborative Filtering (CF) models for drug repositioning currently, like the neighborhood based approaches which are good at mining the local information contained in few strong drug-disease associations, or the latent factor based models which are effectively capture the global information shared by a majority of drug-disease associations. Few researchers have combined these two types of CF models to derive a hybrid model with the advantages of both of them. Besides, the cold start problem has always been a major challenge in the field of computational drug repositioning, which restricts the inference ability of relevant models. Results: Inspired by the memory network, we propose the Hybrid Attentional Memory network (HAMN) model, a deep architecture combines two classes of CF model in a nonlinear manner. Firstly, the memory unit and the attention mechanism are combined to generate the neighborhood contribution representation to capture the local structure of few strong drug-disease associations. Then a variant version of the autoencoder is used to extract the latent factor of drugs and diseases to capture the overall information shared by a majority of drug-disease associations. In that process, ancillary information of drugs and diseases can help to alleviate the cold start problem. Finally, in the prediction stage, the neighborhood contribution representation is combined with the drug latent factor and disease latent factor to produce the predicted value. Comprehensive experimental results on two real data sets show that our proposed HAMN model is superior to other comparison models according to the AUC, AUPR and HR indicators. Conclusions: Through the performance on two real-world data sets, we believe that the proposed model can effectively alleviate the cold start problem in th

关键词： Collaborative filtering

Better Pseudo-label: Joint Domain-aware Label and Dual-classifier for Semi-supervised Domain Generalization

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wang, Ruiqi Qi, Lei Shi, Yinghuan Gao, Yang State Key Laboratory for Novel Software Technology Nanjing University Nanjing China National Institute of Healthcare Data Science Nanjing University Nanjing China School of Computer Science and Engineering Key Lab of Computer Network and Information Integration Ministry of Education Southeast University Nanjing China

With the goal of directly generalizing trained model to unseen target domains, domain generalization (DG), a newly proposed learning paradigm, has attracted considerable attention. Previous DG models usually require a sufficient quantity of annotated samples from observed source domains during training. In this paper, we relax this requirement about full annotation and investigate semisupervised domain generalization (SSDG) where only one source domain is fully annotated along with the other domains totally unlabeled in the training process. With the challenges of tackling the domain gap between observed source domains and predicting unseen target domains, we propose a novel deep framework via joint domain-aware labels and dual-classifier to produce high-quality pseudo-labels. Concretely, to predict accurate pseudo-labels under domain shift, a domain-aware pseudo-labeling module is developed. Also, considering inconsistent goals between generalization and pseudo-labeling: former prevents overfitting on all source domains while latter might overfit the unlabeled source domains for high accuracy, we employ a dual-classifier to independently perform pseudo-labeling and domain generalization in the training process. When accurate pseudo-labels are generated for unlabeled source domains, the domain mixup operation is applied to augment new domains between labeled and unlabeled domains, which is beneficial for boosting the generalization capability of the model. Extensive results on publicly available DG benchmark datasets show the efficacy of our proposed SSDG method. Copyright © 2021, The Authors. All rights reserved.

关键词： Image recognition

A parameter-independent algorithm of finding maximum clique with Seidel continuous-time quantum walks

学校读者我要写书评

暂无评论

iScience 2024年第2期27卷 108953页

作者： Li, Xi Chen, Xiao Hu, Shouwei Xu, Juan Liu, Zhihao School of Computer Science and Engineering Southeast University No.2 Sipailou District Nanjing 210096 Jiangsu China Key Laboratory of Computer Network and Information Integration (Southeast University) Ministry of Education No.2 Southeast University Road Jiangning District Nanjing 211189 Jiangsu China College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics No.29 Junjun Dadao Jiangning District Nanjing 210016 Jiangsu China Collaborative Innovation Center of Novel Software Technology and Industrialization No.29 Junjun Dadao Jiangning District Nanjing 210023 Jiangsu China

The maximum clique (MC) problem holds significance in network analysis. Quantum-based algorithms have recently emerged as promising approaches for this problem. However, these algorithms heavily depend on parameters of quantum system and vary significantly for different graphs. In order to tackle this issue, we initially demonstrate that continuous-time quantum walks (CTQW) driven by the Seidel matrix offer valuable insights into the clique structure of graphs, outperforming the CTQW driven by adjacency matrix. Specifically, we conduct an in-depth analysis for CTQW of 4 types of graphs, meticulously calculating the amplitudes associated with different vertices. Our findings consistently reveal that vertices belonging to MC exhibit the highest intensity at the largest frequency component of the probability amplitude for these types of graphs. Considering the varying intensities, we propose a parameter-independent algorithm for determining the MC. We compare our algorithm with a typical quantum-based algorithm, the results indicate that our algorithm exhibits greater stability. © 2024 The Authors

关键词： Physics Quantum physics

Deep Attention-guided Graph Clustering with Dual Self-supervision

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Peng, Zhihao Liu, Hui Jia, Yuheng Hou, Junhui The Department of Computer Science City University of Hong Kong Kowloon999077 Hong Kong The School of Computing & Information Sciences Caritas Institute of Higher Education Hong Kong The School of Computer Science and Engineering Southeast University Nanjing210096 China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education China

Existing deep embedding clustering methods fail to sufficiently utilize the available off-the-shelf information from feature embeddings and cluster assignments, limiting their performance. To this end, we propose a novel method, namely deep attention-guided graph clustering with dual self-supervision (DAGC). Specifically, DAGC first utilizes a heterogeneity-wise fusion module to adaptively integrate the features of the autoencoder and the graph convolutional network in each layer and then uses a scale-wise fusion module to dynamically concatenate the multi-scale features in different layers. Such modules are capable of learning an informative feature embedding via an attention-based mechanism. In addition, we design a distribution-wise fusion module that leverages cluster assignments to acquire clustering results directly. To better explore the off-the-shelf information from the cluster assignments, we develop a dual self-supervision solution consisting of a soft self-supervision strategy with a Kullback-Leibler divergence loss and a hard self-supervision strategy with a pseudo supervision loss. Extensive experiments on nine benchmark datasets validate that our method consistently outperforms state-of-the-art methods. Especially, our method improves the ARI by more than 10.29% over the best baseline. The code will be publicly available at https://***/ZhihaoPENG-CityU/DAGC. Copyright © 2021, The Authors. All rights reserved.

关键词： Embeddings

Barrier Offset Varying-Parameter Dynamic Learning network for Solving Dual-Arms Human-Like Behavior Generation

学校读者我要写书评

暂无评论

IEEE Transactions on Cognitive and Developmental Systems 2025年

作者： Zhang, Zhijun Zhang, Mingyang Guo, Jinjia He, Haotian School of Automation Science and Engineering South China University of Technology Guangzhou510640 China Key Library of Autonomous Systems and Network Control Ministry of Education China Jiangxi Thousand Talents Plan Nanchang University Nanchang330031 China Guangzhou510335 China Shaanxi Provincial Key Laboratory of Industrial Automation School of Mechanical Engineering Shanxi University of Technology Hanzhong723001 China School of Information Science and Engineering Changsha Normal University Changsha410100 China School of Automation Science and Engineering Institute of Artificial Intelligence and Automation Guangdong University of Petrochemical Technology Maoming525000 China School of Computer Science and Engineering Jishou University Jishou416000 China

Enabling robots to imitate human actions and perform tasks with high precision while avoiding potential obstacles in the environment can effectively enhance the interaction between social robots and humans. In this paper, to achieve higher precision trajectory tracking and obstacle avoidance for dual-arm humanoid robots, the barrier offset varying-parameter dynamic learning neural (BOVDL) network method is proposed and applied to dual-arm humanoid behavior generation scheme. To do so, a dual-arms humanoid robot model is set up, and transformed into a constrained time-varying quadratic programming (TVQP) problem. Secondly, by using lagrangian multiplier method and Karush-Kuhn-Tuchker condition, the inequality constrained TVQP is converted as a time-varying equation with a barrier parameter. Thirdly, a varying-parameter dynamic learning network is presented to solve the time-varying equation with a barrier parameter. computer simulation experiments are conducted to verify the feasibility, accuracy, and safety of the proposed BOVDL network method. Experimental results show that all 14 joints of the humanoid robot's arms are within the motion range of each real human arm's physical constraints. The maximum position error and velocity error between the desired trajectory and the actual trajectory of the end effector are less than 10-6m magnitude and 10-7m magnitude, respectively, representing a reduction of 5 orders of magnitude compared to the traditional varying-parameter convergent-differential neural network. Furthermore, the proposed method also enables the dual-arm humanoid robot to avoid collisions with obstacles while performing tasks, demonstrating the superiority of the proposed BOVDL network scheme. © 2016 IEEE.

关键词： Anthropomorphic robots

Motion Estimation and Spatiotemporal Tensor Enhanced Representation for 4D-CBCT Image Reconstruction

学校读者我要写书评

暂无评论

Motion Estimation and Spatiotemporal Tensor Enhanced Represe...

International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)

作者： Jin Liu Yanqin Kang Guirui Liu College of Computer and Information Anhui Polytechnic University Wuhu China Key Laboratory of Computer Network and Information Integration (Southeast University) Ministry of Education Nanjing China

ISBN: (数字)9780738105451

ISBN: (纸本)9781665422994

Four dimensional Cone-Beam Computed Tomography (4D-CBCT) has great value for motion management in radiotherapy. But high quality 4D-CBCT image reconstruction is difficult to achieve because of the lacked of projections at each phase, which result aliasing artifacts. In this work, we propose a novel joint motion estimation and spatiotemporal tensor enhanced representation (MESTER) approach for 4D-CBCT image reconstruction. To tackle the under-sampling problem of 4D-CBCT imaging, we employ spatiotemporal tensor enhanced sparse representation which tries to explore the spatiotemporal coherence of the patient anatomy in 4D data, by using inter-phase deformation vector fields (DVFs). In this approach, we divide the motion compensated 4D-CBCT images into 4D block in a non-local window and clustering similar spatiotemporal patches to a 5th-order tensor group. Then the spatiotemporal tensor dictionary sparsity representation on the tensor group is incorporated into the reconstruction cost function. The numerical simulation and preclinical data are performed to evaluate and validate the performance of this approach. Qualitative and quantitative results show that the proposed approach achieved improved image quality with less artifacts and better recovery of details.

关键词： Image reconstruction Tensors Mathematical model Spatiotemporal phenomena TV Motion estimation Minimization