检索结果-内蒙古大学图书馆

A Survey on Evolutionary Computation Based Drug Discovery

IEEE Transactions on Evolutionary Computation 2024年第3期29卷 1-1页

作者： Yu, Qiyuan Lin, Qiuzhen Ji, Junkai Zhou, Wei He, Shan Zhu, Zexuan Tan, Kay Chen College of Computer Science and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China School of Computer Science University of Birmingham Bir-mingham UK Department of Computing The Hong Kong Poly-technic University Hong Kong Hong Kong

Drug discovery is an expensive and risky process. To combat the challenges in drug discovery, an increasing number of researchers and pharmaceutical companies recognize the benefits of utilizing computational techniques. Evolutionary computation (EC) offers promise as most drug discovery problems are essentially complex optimization problems beyond conventional optimization algorithms. EC methods have been widely applied to solve these complex optimization problems especially in lead com-pound generation and molecular virtual evaluation, substantially speeding up the process of drug discovery and development. This article presents a comprehensive survey of EC-based drug discovery methods. Particularly, a new taxonomy of the methods is provided and the advantages and limitations of the methods are reviewed. In addition, the potential future directions of EC-based drug discovery are discussed and the publicly available resources including databases and computational tools are compiled for the convenience of researchers seeking to pursue this field. IEEE

关键词： Lead compounds

来源：评论

学校读者我要写书评

暂无评论

Improving Adaptive Runoff Forecasts in data-Scarce Watersheds Through Personalized Federated Learning 27th

Improving Adaptive Runoff Forecasts in Data-Scarce Watershe...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Xie, Zaipeng Zhang, Xiangqin Wang, Yunfei Jie, Xuanyao Fang, Wenhao Cai, Yanping Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University Nanjing China College of Computer Science and Software Engineering Hohai University Nanjing China

ISBN: (纸本)9783031781827

Runoff forecasting plays a crucial role in water resource management and flood mitigation, but it often faces significant challenges due to data deficiency and decentralized datasets. Inadequate hydrological data in many watersheds hinders the development of accurate prediction models, while organizational barriers and concerns about data privacy lead to information silos, preventing effective collaborative modeling. To address these issues, we propose FedHydroDSW, a novel personalized federated learning framework for runoff forecasting in data-scarce watersheds. Our approach enables decentralized model training across multiple organizations without requiring direct data sharing, thus preserving data privacy. FedHydroDSW incorporates unique model similarity metrics and parameter adaptation methods, utilizing insights from data-rich areas to refine forecasts in data-scarce regions. Experiments on the CAMELS dataset show that FedHydroDSW significantly outperforms standalone and conventional federated learning methods, with an average 30.1% increase in NSE, and reductions of 28% in RAE and 26.6% in RMSE across multiple data-scarce basins. By enabling secure cross-silo learning, our FedHydroDSW strategy paves the way toward more equitable runoff forecasting globally. The customized training and pattern recognition techniques represent major progress in deploying federated intelligence for impactful hydrological predictions. Our code is publicly available at https://***/xyjie37/FedHydroDSW. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A Multistage Framework for Detection of Very Small Objects 23

A Multistage Framework for Detection of Very Small Objects

引用

6th International Conference on Machine Vision and Applications, ICMVA 2023

作者： Don, Duleep Rathgamage Aygun, Ramazan Karakaya, Mahmut School of Data Science and Analytics College of Computing and Software Engineering Kennesaw State University MariettaGA30060 United States Department of Computer Science College of Computing and Software Engineering Kennesaw State University MariettaGA30060 United States

ISBN: (纸本)9781450399531

Small object detection is one of the most challenging problems in computer vision. Algorithms based on state-of-the-art object detection methods such as R-CNN, SSD, FPN, and YOLO fail to detect objects of very small sizes. In this study, we propose a novel method to detect very small objects, smaller than 8×8 pixels, that appear in a complex background. The proposed method is a multistage framework consisting of an unsupervised algorithm and three separately trained supervised algorithms. The unsupervised algorithm extracts ROIs from a high-resolution image. Then the ROIs are upsampled using SRGAN, and the enhanced ROIs are detected by our two-stage cascade classifier based on two ResNet50 models. The maximum size of the images used for training the proposed framework is 32×32 pixels. The experiments are conducted using rescaled German Traffic Sign Recognition Benchmark dataset (GTSRB) and downsampled German Traffic Sign Detection Benchmark dataset (GTSDB). Unlike MS COCO and DOTA datasets, the resulting GTSDB turns out to be very challenging for any small object detection algorithm due to not only the size of objects of interest but the complex textures of the background as well. Our experimental results show that the proposed method detects small traffic signs with an average precision of 0.332 at the intersection over union of 0.3. © 2023 ACM.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Personalized Federated Learning with Feature Alignment via Knowledge Distillation 21st

Personalized Federated Learning with Feature Alignment via...

引用

21st Pacific Rim International Conference on Artificial Intelligence, PRICAI 2024

作者： Qi, Guangfei Qu, Zhihao Lyu, Shen-Huan Jia, Ninghui Ye, Baoliu Key Laboratory of Water Big Data Technology of Ministry of Water Resources College of Computer Science and Software Engineering Hohai University Nanjing China National Key Laboratory for Novel Software Technology Nanjing University Nanjing China

ISBN: (纸本)9789819601189

Personalized Federated Learning (PFL) has gained significant attention for its ability to handle heterogeneous data effectively. Parameter decoupling is a typical approach to PFL. It decouples the model into a feature extractor and a classifier head, where the feature extractor is trained collaboratively to learn a common representation and the classifier head is personalized for local data. Since local training only learns personalized feature information and ignores global information, the generalization ability of the feature extractor is limited. To improve the performance of the local model, a feasible approach is to make the local feature extractor more generalized. However, prior work requires the transmission of additional feature data beyond the transmission of model parameters, which leads to privacy leakage and higher communication overhead. To address these shortcomings, we propose a PFL algorithm with feature alignment via knowledge distillation, named PFAKD. PFAKD enhances the training of local feature extractors by explicitly aligning each sample’s local features with global features, providing more detailed guidance. Meanwhile, it avoids additional communication overhead and the risk of privacy leakage. We conduct extensive experiments in heterogeneous data scenarios. PFAKD outperforms other state-of-the-art methods by up to 4.35% in terms of model accuracy. Our code is available at https://***/fei0829/PFAKD. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A Pre-selected Local Weighted Method for Improving the Performance of LMKNN Classifier 6

A Pre-selected Local Weighted Method for Improving the Perfo...

引用

6th IEEE International Conference on Power, Intelligent Computing and Systems, ICPICS 2024

作者： Zhang, Yuzhi Guan, Ziyan Xiong, Chen School of Aeronautic Science and Engineering Beihang University Beijing China School of Big Data & Software Engineering Chongqing University Chongqing China School of Computer Science Xi'an Jiaotong University City College Xi'an China

ISBN: (纸本)9798350374315

The K-nearest neighbor (KNN) algorithm and its variant Local Mean K-nearest neighbor (LMKNN) have been widely used in the field of data mining due to their simplicity and intuition. However, these methods have limitations when dealing with unbalanced datasets and edge samples, such as sensitivity to the choice of nearest neighbor size and degradation of classification performance for outlier points. To address these issues, this paper proposes a pre-selected locally weighted mean K-nearest neighbor (PLWMKNN) algorithm, which aims to improve the performance of LMKNN through an advanced pre-selection mechanism and a weighted average method. PLWMKNN firstly pre-selects favorable classes as the nearest neighbors based on the distance weights, and then computes the weighted center vectors of each class to classify them by the minimum distance principle. Through experimental validation on four real datasets, PLWMKNN shows significant performance improvement over traditional KNN and LMKNN for unbalanced datasets. Our results demonstrate the effectiveness of the PLWMKNN algorithm in improving classification accuracy and robustness, especially when dealing with extremely unbalanced datasets. © 2024 IEEE.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

Multi-layer network embedding on scc-based network with motif

引用

Digital Communications and Networks 2024年第3期10卷 546-556页

作者： Lu Sun Xiaona Li Mingyue Zhang Liangtian Wan Yun Lin Xianpeng Wang Gang Xu Department of Communication Engineering Institute of Information Science TechnologyDalian Maritime UniversityDalian116026China Key Laboratory of Big Data Intelligent Computing Chongqing University of Posts and TelecommunicationsChongqing400065China Key Laboratory for Ubiquitous Network and Service Software of Liaoning Province DUT School of Software Technology&DUT-RU International School of Information Science and EngineeringDalian University of TechnologyDalian 116620China College of Information and Communication Engineering Harbin Engineering UniversityHarbin 150001China School of Information and Communication Engineering Hainan UniversityHaikou 570228China State Key Laboratory of Millimeter Waves School of Information Science and EngineeringSoutheast UniversityNanjing 210096China

Interconnection of all things challenges the traditional communication methods,and Semantic Communication and Computing(SCC)will become new *** is a challenging task to accurately detect,extract,and represent semantic information in the research of SCC-based *** previous research,researchers usually use convolution to extract the feature information of a graph and perform the corresponding task of node ***,the content of semantic information is quite *** graph convolutional neural networks provide an effective solution for node classification tasks,due to their limitations in representing multiple relational patterns and not recognizing and analyzing higher-order local structures,the extracted feature information is subject to varying degrees of ***,this paper extends from a single-layer topology network to a multi-layer heterogeneous topology *** Bidirectional Encoder Representations from Transformers(BERT)training word vector is introduced to extract the semantic features in the network,and the existing graph neural network is improved by combining the higher-order local feature module of the network model representation network.A multi-layer network embedding algorithm on SCC-based networks with motifs is proposed to complete the task of end-to-end node *** verify the effectiveness of the algorithm on a real multi-layer heterogeneous network.

关键词： Semantic communication and computing Multi-layer network Graph neural network Motif

来源：评论

学校读者我要写书评

暂无评论

Convolutional Neural Network Based QoS Prediction with Dimensional Correlation 18th

Convolutional Neural Network Based QoS Prediction with Dime...

引用

18th International Conference on Green, Pervasive, and Cloud Computing, GPC 2023

作者： Cao, Weihao Cheng, Yong Xue, Shengjun Dai, Fei School of Software Nanjing University of Information Science and Technology Nanjing210044 China College of Big Data and Intelligent Engineering Southwest Forestry University Kunming650224 China

ISBN: (纸本)9789819998951

In recent years, massive services that provide similar functions continue to emerge. Since services sensitive to latency and throughput are often expected to have high Quality of Service (QoS), how to accurately predict QoS has become a challenging issue. Some current deep learning (DL) based approaches usually simply concatenate the embedding vectors, without considering the correlation between embedding dimensions. Besides, the high-order feature interactions are not sufficiently learned. To this end, this paper proposes a Convolutional Neural Network based QoS prediction model with Dimensional Correlation, named QPCN. First, the two dimensional interaction features is explicitly obtained by modeling the embedding vectors. Then, the convolutional neural network is utilized to perform feature extraction and complete QoS prediction. Compared with the fully connected network, QPCN can build a deeper model and learn high-order features. In addition, the parameters of QPCN are significantly reduced, which will reduce the time and energy consumption of inference. The effectiveness of QPCN is validated by experiments on a real-world dataset. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Real-World Wireless Network Modeling and Optimization:From Model/data-Driven Perspective

引用

Chinese Journal of Electronics 2022年第6期31卷 991-1012页

作者： LI Yang ZHANG Shutao REN Xiaohui ZHU Jianhang HUANG Jiajie HE Pengcheng SHEN Kaiming YAO Zhiqiang GONG Jie CHANG Tsunghui SHI Qingjiang LUO Zhiquan Shenzhen Research Institute of Big Data Pengcheng Lab School of Science and Engineering The Chinese University of Hong Kong (Shenzhen) College of Mathematics and Computational Sciences Xiangtan University School of Computer Science and Engineering Sun Yat-Sen University School of Software Engineering Tongji University

With the rapid development of the fifth-generation wireless communication systems, a profound revolution in terms of transmission capacity, energy efficiency, reliability, latency, and connectivity is highly expected to support a new batch of industries and applications. To achieve this goal, wireless networks are becoming extremely dynamic, heterogeneous, and complex. The modeling and optimization for the performance of realworld wireless networks are extremely challenging due to the difficulty to predict the network performance as a function of network parameters, and the prohibitively huge number of parameters to optimize. The conventional network modeling and optimization approaches rely on drive test, trial-and-error, and engineering experience,which are labor intensive, error-prone, and far from optimal. On the other hand, while the research community has spent significant efforts in understanding the fundamental limits of radio channels and developing physical layer techniques to operate close to it, very little is known about the performance limits of wireless networks, where millions of radio channels interact with one another in complex manners. This paper reviews the very recent mathematical and learning based techniques for modeling and optimizing the performance of real-world wireless networks in five aspects, including channel modeling, user demand and traffic modeling, throughput modeling and prediction, network parameter optimization, and IRS empowered performance optimization, and also presents the corresponding notable performance gains.

关键词： network parameter optimization telecommunication computing optimisation mathematical techniques wireless channels performance optimization learning based techniques telecommunication traffic mathematical analysis physical layer techniques channel modeling wireless network modeling fifth generation wireless communication systems learning (artificial intelligence) model-data-driven perspective IRS empowered performance optimization radio channels traffic modeling radio networks

来源：评论

学校读者我要写书评

暂无评论

Research on Deep Learning-Based Algorithms for Medical Image Characterisation 2

Research on Deep Learning-Based Algorithms for Medical Image...

引用

2nd International Conference on data science and Information System, ICDSIS 2024

作者： Yu, Yunxia Qi, Zhiyong Xu, Ling Zhou, Xiong Jingchu University Of Technology Big Data Research Center Jingmen China College Of Computer Science Wuhan Vocational College Of Software And Engineering Wuhan China Shayang People's Hospital Jingmen China

ISBN: (纸本)9798350381665

Lung disease is a worldwide health problem, and accurate image diagnosis of lung disease is crucial for patient treatment and management. In recent years, deep learning has made significant progress in the field of medical image analysis, in which Graph Neural Networks (GNNs), as a special deep learning model, show great potential in lung disease diagnosis. In this study, we propose a graph neural network-based model for lung disease diagnosis, aiming to automate the analysis of lung images and lesion detection. First, we represent the lung images as a graph structure, where each pathogenic region represents a node in the graph. Then, the adjacency matrix and node features of the graph are constructed, and the image is subjected to feature extraction and representation learning using a graph neural network, which enables the model to capture the structural and contextual information in the image. To further improve the performance of the model, we introduce multilayer graph convolution and multilayer perceptron to enhance the sensitivity and differentiation ability of the graph neural network for lung lesions. We conducted experimental evaluations based on publicly available lung image datasets and compared them with traditional machine learning methods as well as other deep learning models. The experimental results show that the proposed graph neural network model achieves excellent performance on the lung disease diagnosis task. © 2024 IEEE.

关键词： Multilayers

来源：评论

学校读者我要写书评

暂无评论

Deep Learning in Automatic Recognition of Mongolian Compound Nouns 5

Deep Learning in Automatic Recognition of Mongolian Compound...

引用

5th IEEE International Conference on Pattern Recognition and Machine Learning, PRML 2024

作者： Si, Ha La, Du Ding, Yang College of Computer Science and Information Engineering Hohhot Minzu College Hohhot China College of Computer Science and Technology Inner Mongolia Normal University Hohhot China School of Software and Big Data Inner Mongolia Electronic Information Vocational Technical College Hohhot China

ISBN: (纸本)9798350355925

Mongolian compound nouns often become the vehicle for the creation of new concepts and terms due to their diverse combinations and flexible expressive power. In the field of natural language shallow syntactic analysis, the recognition of Mongolian compound nouns plays an important role, and its performance will directly affect the processing effect of related research. In the current academic research, the research on automatic recognition of Mongolian compound nouns is still insufficient, especially in the automatic recognition of Mongolian compound nouns using deep learning technology, which is almost in a blank state. In this study, we firstly construct a Mongolian compound noun annotated corpus, and on the basis of the constructed annotated corpus, we propose a Mongolian compound noun automatic recognition model based on deep learning for the fact that there is no deep learning method for recognising Mongolian compound nouns at present. The model takes Conditional Random Field (CRF) as the basic framework to make full use of contextual information by considering the joint probability distribution of the whole sequence. During the model construction process, the TextCNN model is incorporated and by designing a multi-scale convolutional kernel, the model is able to effectively capture the local features of Mongolian compound nouns. The experimental results show that the automatic Mongolian compound noun recognition model based on deep learning proposed in this study performs well on the Mongolian compound noun recognition task, with an F1 value of 93.40%. © 2024 IEEE.

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：