检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Wang, Dui Shen, Li Luo, Yong Hu, Han Su, Kehua Wen, Yonggang Tao, Dacheng National Engineering Research Center for Multimedia Software School of Computer Science Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China Hubei Luojia Laboratory Wuhan China JD Explore Academy China School of Information and Electronics Beijing Institute of Technology China School of Computer Science and Engineering Nanyang Technological University Singapore

Federated learning aims to collaboratively train models without accessing their client’s local private data. The data may be Non-IID for different clients and thus resulting in poor performance. Recently, personalized federated learning (PFL) has achieved great success in handling Non-IID data by enforcing regularization in local optimization or improving the model aggregation scheme on the server. However, most of the PFL approaches do not take into account the unfair competition issue caused by the imbalanced data distribution and lack of positive samples for some classes in each client. To address this issue, we propose a novel and generic PFL framework termed Federated Averaging via Binary Classification, dubbed FedABC. In particular, we adopt the "one-vs-all" training strategy in each client to alleviate the unfair competition between classes by constructing a personalized binary classification problem for each class. This may aggravate the class imbalance challenge and thus a novel personalized binary classification loss that incorporates both the under-sampling and hard sample mining strategies is designed. Extensive experiments are conducted on two popular datasets under different settings, and the results demonstrate that our FedABC can significantly outperform the existing counterparts. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Genetic Algorithm with Multiple Fitness Functions for Generating Adversarial Examples

Genetic Algorithm with Multiple Fitness Functions for Genera...

引用

Congress on Evolutionary Computation

作者： Chenwang Wu Wenjian Luo Nan Zhou Peilan Xu Tao Zhu School of Computer Science and Technology University of Science and Technology of China Hefei China School of Computer Science and Technology Harbin Institute of Technology Shenzhen China School of Software Engineering University of South China Hengyang China

Studies have shown that deep neural networks (DNNs) are susceptible to adversarial attacks, which can cause misclassification. The adversarial attack problem can be regarded as an optimization problem, then the genetic algorithm (GA) that is problem-independent can naturally be designed to solve the optimization problem to generate effective adversarial examples. Considering the dimensionality curse in the image processing field, traditional genetic algorithms in high-dimensional problems often fall into local optima. Therefore, we propose a GA with multiple fitness functions (MF-GA). Specifically, we divide the evolution process into three stages, i.e., exploration stage, exploitation stage, and stable stage. Besides, different fitness functions are used for different stages, which could help the GA to jump away from the local *** are conducted on three datasets, and four classic algorithms as well as the basic GA are adopted for comparisons. Experimental results demonstrate that MF-GA is an effective black-box attack method. Furthermore, although MF-GA is a black-box attack method, experimental results demonstrate the performance of MF-GA under the black-box environments is competitive when comparing to four classic algorithms under the white-box attack environments. This shows that evolutionary algorithms have great potential in adversarial attacks.

关键词： Deep learning Image processing Computational modeling Evolutionary computation Jitter Optimization Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

A Semi-supervised Modeling Method for Dioxin Emission Prediction Based on Random Forest 5

A Semi-supervised Modeling Method for Dioxin Emission Predic...

引用

5th Asian Conference on Artificial Intelligence technology, ACAIT 2021

作者： Xu, Wen Tang, Jian Xia, Heng Zhang, Jian Yu, Wen Qiao, JunFei Beijing University of Technology Faculty of Information Technology Beijing100124 China Nanjing University of Information Science Technology School of Computer and Software 210044 China CINVESTAV-IPN National Polytechnic Institute Departamento de Control Automatico Mexico City07360 Mexico

ISBN: (纸本)9781665426305

Dioxin (DXN) is a kind of pollutants with cumulative effects in the municipal solid waste incineration (MSWI) process. Its emission concentration is difficult to detect online and in real-time, which restricts the operational optimization of the MSWI process. At the same time, it is difficult to meet actual needs through traditional supervised modeling methods because of the high time and economic cost of directly measuring DXN. Therefore, a DXN emission prediction model based on semi-supervised random forest (SSRF) is established to make full use of the unlabeled data obtained in the actual industrial process. First, the training subsets are acquired through randomly sampling the labeled data. Second, the training subsets are utilized to build multiple random forest (RF) models and pseudo-label the unlabeled data. Finally, the mixed samples composed of pseudo-labeled data and labeled data are used to train an RF model for predicting the DXN emission concentration. The proposed method is verified by the actual DXN dataset. © 2021 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Intrusion Detection Model Based on Spatiotemporal Features

引用

Journal of Quantum Computing 2021年第3期3卷 107-118页

作者： Linbei Wang Zaoyu Tao Lina Wang Yongjun Ren Changwang School of Honors Nanjing University of Information Science and TechnologyNanjingChina School of Artificial Intelligence Nanjing University of Information Science and TechnologyNanjingChina School of Computer and Software Nanjing University of Information Science and TechnologyNanjingChina

With the accelerating process of social informatization,our personal information security and Internet sites,etc.,have been facing a series of threats and ***,well-developed neural network has seen great advancement in natural language processing and computer vision,which is also adopted in intrusion *** this research,a hybrid model integrating Multi-Scale Convolutional Neural Network and Long Short-term Memory Network(MSCNN-LSTM)is designed to conduct the intrusion ***-Scale Convolutional Neural Network(MSCNN)is used to extract the spatial characteristics of data *** Long Short-term Memory Network(LSTM)is responsible for processing the temporal *** data set used in this experiment is KDDCUP99 with different probability distributions in the training set and test set involving some newly emerging attack types,making the data more *** a result,this type of data set is widely applied in the simulation experiment of intrusion *** this experiment,the assessment indices such as the accuracy rate,recall rate and F1 score are introduced to check the performance of this model.

关键词： Intrusion detection deep learning Multi-Scale Convolutional Neural Network Long Short-Term Memory Network

来源：评论

学校读者我要写书评

暂无评论

Stochastic Approximation Approaches to Group Distributionally Robust Optimization and Beyond

arXiv

引用

arXiv 2023年

作者： Zhang, Lijun Bai, Haomin Zhao, Peng Yang, Tianbao Zhou, Zhi-Hua National Key Laboratory for Novel Software Technology Nanjing University China School of Artificial Intelligence Nanjing University China Department of Computer Science and Engineering Texas A&M University College Station United States

This paper investigates group distributionally robust optimization (GDRO) with the goal of learning a model that performs well over m different distributions. First, we formulate GDRO as a stochastic convex-concave saddle-point problem, which is then solved by stochastic mirror descent (SMD) with m samples in each iteration, and attain a nearly optimal sample complexity. To reduce the number of samples required in each round from m to 1, we cast GDRO as a two-player game, where one player conducts SMD and the other executes an online algorithm for non-oblivious multi-armed bandits, maintaining the same sample complexity. Next, we extend GDRO to address scenarios involving imbalanced data and heterogeneous distributions. In the first scenario, we introduce a weighted variant of GDRO, enabling distribution-dependent convergence rates that rely on the number of samples from each distribution. We design two strategies to meet the sample budget: one integrates non-uniform sampling into SMD, and the other employs the stochastic mirror-prox algorithm with mini-batches, both of which deliver faster rates for distributions with more samples. In the second scenario, we propose to optimize the average top-k risk instead of the maximum risk, thereby mitigating the impact of outlier distributions. Similar to the case of vanilla GDRO, we develop two stochastic approaches: one uses m samples per iteration via SMD, and the other consumes k samples per iteration through an online algorithm for non-oblivious combinatorial semi-bandits. Copyright © 2023, The Authors. All rights reserved.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Large Language Model for science: A Study on P vs. NP

arXiv

引用

arXiv 2023年

作者： Dong, Qingxiu Dong, Li Xu, Ke Zhou, Guangyan Hao, Yaru Sui, Zhifang Wei, Furu Microsoft Research United States School of Computer Science Peking University China State Key Lab of Software Development Environment Beihang University China Department of Mathematics and Statistics Beijing Technology and Business University China

In this work, we use large language models (LLMs) to augment and accelerate research on the P versus NP problem, one of the most important open problems in theoretical computer science and mathematics. Specifically, we propose Socratic reasoning, a general framework that promotes in-depth thinking with LLMs for complex problem-solving. Socratic reasoning encourages LLMs to recursively discover, solve, and integrate problems while facilitating self-evaluation and refinement. Our pilot study on the P vs. NP problem shows that GPT-4 successfully produces a proof schema and engages in rigorous reasoning throughout 97 dialogue turns, concluding "P ≠ NP", which is in alignment with (Xu and Zhou, 2023). The investigation uncovers novel insights within the extensive solution space of LLMs, shedding light on LLM for science. Copyright © 2023, The Authors. All rights reserved.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

GMap Results for OAEI 2021 16

GMap Results for OAEI 2021

引用

16th International Workshop on Ontology Matching, OM 2021

作者： Li, Weizhuo Zhou, Shiqi Ji, Qiu Lu, Bingjie School Of Modern Posts Nanjing University Of Posts And Telecommunications China School Of Computer Science And Engineering Southeast University Nanjing China Zhejiang Lab HangZhou China State Key Laboratory For Novel Software Technology Nanjing University China

GMap is an alternative probabilistic scheme for ontology matching, which combines the sum-product network and the noisy-or model. More precisely, we employ the sum-product network to encode the similarities based on the set of individuals and disjointness axioms. The noisy-or model is utilized to encode the probabilistic matching rules, which describe the influences among entity pairs across ontologies. This paper briefly introduces GMap and its results of two tracks (i.e., Conference, Anatomy) on OAEI 2021. Copyright © 2021 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

Feature Aggregating Network with Inter-Frame Interaction for Efficient Video Super-Resolution

Feature Aggregating Network with Inter-Frame Interaction for...

引用

IEEE International Conference on Data Mining (ICDM)

作者： Yawei Li Zhao Zhang Suiyi Zhao Jicong Fan Haijun Zhang Mingliang Xu School of Computer Science and Information Engineering Hefei University of Technology Hefei China Key Laboratory of Knowledge Engineering with Big Data (Ministry of Education) & Intelligent Interconnected Systems Laboratory of Anhui Province Hefei University of Technology Hefei China Yunnan Key Laboratory of Software Engineering Kunming China Shenzhen Research Institute of Big Data Shenzhen China School of Data Science The Chinese University of Hong Kong Shenzhen China Department of Computer Science Harbin Institute of Technology Shenzhen China School of Computer and Artificial Intelligence Zhengzhou University Zhengzhou China

Video super-resolution (VSR) on mobile devices aims to restore high-resolution frames from their low-resolution counterparts, satisfying the requirements of performance, FLOPs and latency. On one hand, partial feature processing, as a classic and acknowledged strategy, is developed in current studies to reach an appropriate trade-off between FLOPs and accuracy. However, the splitting of partial feature processing strategy are usually performed in a blind manner, thereby reducing the computational efficiency and performance gains. On the other hand, current methods for mobile platforms primarily treat VSR as an extension of single-image super-resolution to reduce model calculation and inference latency. However, lacking inter-frame information interaction in current methods results in a suboptimal latency and accuracy trade-off. To this end, we propose a novel architecture, termed Feature Aggregating Network with Inter-frame Interaction (FANI), a lightweight yet considering frame-wise correlation VSR network, which could achieve real-time inference while maintaining superior performance. Our FANI accepts adjacent multi-frame low-resolution images as input and generally consists of several fully-connection-embedded modules, i.e., Multi-stage Partial Feature Distillation (MPFD) for capturing multi-level feature representations. Moreover, considering the importance of inter-frame alignment, we further employ a tiny Attention-based Frame Alignment (AFA) module to promote inter-frame information flow and aggregation efficiently. Extensive experiments on the well-known dataset and real-world mobile device demonstrate the superiority of our proposed FANI, which means that our FANI could be well adapted to mobile devices and produce visually pleasing results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

TFE-HMM: Combining state transitions and price trends for stock price forecasting

引用

Expert Systems with Applications 2025年 288卷

作者： Xu Yuan Yi Guo Shaokui Gu Jiaqiang Wang Ange Qi Shijin Li Liang Zhao School of Software Technology Dalian University of Technology Dalian China School of Computer Science Fudan University Shanghai China

Stock price prediction, a fundamental task in the field of quantitative investing, has garnered widespread attention and deep research from scholars, investors, and governmental institutions. However, traditional prediction methods that directly model and forecast numerical values are not only prone to the influence of noise and outliers but also often fail to capture the underlying state information within time series data and the transition dynamics between these states. To address this issue, we propose a Temporal Feature-Enhanced Gaussian Hidden Markov Model (TFE-HMM). Based on the traditional Gaussian Hidden Markov Model, the proposed model utilizes trend information from historical stock data to construct a Hidden Markov Chain. The derived hidden states are combined with stock price fluctuations to form new temporal features, and reliable neighbors are identified through the calculation of weighted mixed similarity. Subsequently, the price fluctuations of each identified neighbor are weighted and aggregated to produce the final prediction result. Unlike traditional Gaussian Hidden Markov Models, the proposed TFE-HMM simultaneously incorporate both the state information of stock price changes and the price fluctuation data, enhancing the representational capacity of the temporal features. Additionally, the introduction of an optimal distance selection strategy improves the model’s prediction stability and accuracy. We evaluated the proposed model on multiple real-world stock datasets, and the experimental results demonstrate that TFE-HMM significantly outperforms existing prediction methods in terms of accuracy, recall, precision, F1 score and investment returns, making it particularly suitable for stock price prediction tasks. Ablation studies further validate the effectiveness of the proposed model.

关键词： Gaussian hidden Markov model (Gaussian HMM) Optimal distance selection State transitions Stock price prediction Temporal features Weighted mixed similarity

来源：评论

学校读者我要写书评

暂无评论

Acupuncture State Detection at Zusanli (ST-36) Based on Scalp EEG and Transformer

引用

IEEE Journal of Biomedical and Health Informatics 2025年第6期29卷 4023-4034页

作者： Wenhao Rao Meiyan Xu Haochen Wang Weicheng Hua Jiayang Guo Yongheng Zhang Haibin Zhu Ziqiu Zhou Jiawei Xiong Jianbin Zhang Yijie Pan Peipei Gu Duo Chen School of Artificial Intelligence and Information Technology Nanjing University of Chinese Medicine Nanjing China Department of Computer Science and the Institute of Human Factors Engineering Minnan Normal University Zhangzhou China National Institute for Data Science in Health and Medicine Xiamen University Xiamen China China Mobile Group Jiangsu Company Ltd Sihong Branch Suqian China Second Affiliated Hospital of Nanjing University of Chinese Medicine Nanjing University of Chinese Medicine Nanjing China Department of Computer Science and Technology Tsinghua University Beijing China Eastern Institute for Advanced Study Eastern Institute of Technology Ningbo China College of Software Engineering Zhengzhou University of Light Industry Zhengzhou China

In clinical acupuncture practice, needle twirling (NT) and needle retention (NR) are strategically combined to achieve different therapeutic effects, highlighting the importance of distinguishing between different acupuncture states. Scalp EEG has been proven significantly relevant to brain activity and acupuncture stimulation. In this work, we designed an acupuncture paradigm to collect scalp EEG to study the differences in EEG changes during different acupuncture states. Since deep learning (DL) has been increasingly used in EEG analysis, we propose the Acupuncture Transformer Detector (ATD), a model based on Convolutional Neural Networks (CNN) and Transformer technology. ATD encapsulates the local and global features of EEG under the acupuncture states of Zusanli acupoint (ST-36) in an end-to-end classification framework. The experiment results from 28 healthy participants show that the proposed model can efficiently classify the EEG in different states, with an accuracy of $85.47\pm 0.73\%$ . In this study, time-frequency analysis revealed that power changes were mainly confined to the delta frequency band under different acupuncture states. Brain topography revealed that ST-36 was activated primarily on the left frontal and parieto-occipital areas. This method provides new ideas for automatic recognition of acupuncture status from the perspective of DL, offering new solutions for standardizing acupuncture procedures.

关键词： Acupuncture Electroencephalography Transformers Convolutional neural networks Needles Brain modeling Medical diagnostic imaging Training Temperature measurement Feature extraction

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：