检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zhang, Qingquan Liu, Jialin Yao, Xin The Research Institute of Trustworthy Autonomous System Southern University of Science and Technology Shenzhen518055 China The Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China The School of Data Science Lingnan University Hong Kong

Multiobjective evolutionary learning (MOEL) has demonstrated its advantages of training fairer machine learning models considering a predefined set of conflicting objectives, including accuracy and different fairness measures. Recent works propose to construct a representative subset of fairness measures as optimisation objectives of MOEL throughout model training. However, the determination of a representative measure set relies on dataset, prior knowledge and requires substantial computational costs. What's more, those representative measures may differ across different model training processes. Instead of using a static predefined set determined before model training, this paper proposes to dynamically and adaptively determine a representative measure set online during model training. The dynamically determined representative set is then used as optimising objectives of the MOEL framework and can vary with time. Extensive experimental results on 12 well-known benchmark datasets demonstrate that our proposed framework achieves outstanding performance compared to state-of-the-art approaches for mitigating unfairness in terms of accuracy as well as 25 fairness measures although only a few of them were dynamically selected and used as optimisation objectives. The results indicate the importance of setting optimisation objectives dynamically during training. Copyright © 2024, The Authors. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

RIS-Assisted Passive Localization (RAPL): An Efficient Zero-Overhead Framework Using Conditional Sample Mean

arXiv

引用

arXiv 2025年

作者： Yao, Jiawei Mao, Yijie Chen, Mingzhe Hu, Ye School of Information Science and Technology ShanghaiTech University Shanghai201210 China Department of Electrical and Computer Engineering Frost Institute for Data Science and Computing University of Miami Coral GablesFL33146 United States Department of Industrial and Systems Engineering University of Miami Coral GablesFL33146 United States

Reconfigurable Intelligent Surface (RIS) has been recognized as a promising solution for enhancing localization accuracy. Traditional RIS-based localization methods typically rely on prior channel knowledge, beam scanning, and pilot-based assistance. These approaches often result in substantial energy and computational overhead, and require real-time coordination between the base station (BS) and the RIS. To address these challenges, in this work, we move beyond conventional methods and introduce a novel data-driven, multiple RISs-assisted passive localization approach (RAPL). The proposed method includes two stages, the angle-of-directions (AoDs) between the RISs and the user is estimated by using the conditional sample mean in the first stage, and then the user’s position is determined based on the estimated multiple AoD pairs in the second stage. This approach only utilizes the existing communication signals between the user and the BS, relying solely on the measurement of received signal power at each BS antenna for a set of randomly generated phase shifts across all RISs. Moreover, by obviating the need for real-time RIS phase shift optimization or user-to-BS pilot transmissions, the method introduces no additional communication overhead, making it highly suitable for deployment in real-world networks. The proposed scheme is then extended to multi-RIS scenarios considering both parallel and cascaded RIS topologies. Numerical results show that the proposed RAPL improves localization accuracy while significantly reducing energy and signaling overhead compared to conventional methods. Copyright © 2025, The Authors. All rights reserved.

关键词： Image coding

来源：评论

学校读者我要写书评

暂无评论

Apple Leaf Disease Identification Using Resnet50

Apple Leaf Disease Identification Using Resnet50

引用

Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES), International Conference on

作者： S. Karthigaiveni R. Archana Vasanth Ravi P Salma Khatoon Department of Electronics and Communication Engineering Chennai Institute of Technology Chennai Department of Artificial intelligence and Data science St. Joseph's Institute of technology OMR Chennai Department of Computer Science and Engineering Faculty of Engineering and Technology Jain Deemed to be University Jain Global Campus Department of CSE-DS MLR Institute of Technology Hyderabad India

ISBN: (数字)9798331543624

ISBN: (纸本)9798331543631

Apple leaf disease is a primary issue limiting apple yield and quality. The standard diagnostic approach requires considerable time for illness detection, causing farmers to frequently miss the optimal period for prevention and treatment. The detect of leaf diseases through leaf imagery is a vital study area in computer vision, with the primary objective being to devise an effective method for representing images of sick leaves. The efficient diagnosis and categorization of plant diseases constitutes a significant research aim in agriculture. This paper proposes a novel deep learning, ResNet. To evaluate the efficacy of the ResNet model, a number of comparative experiments were performed with leading transfer learning methodologies. This demonstrates that the proposed method is both possible and successful.

关键词： Plant diseases Accuracy Limiting Prevention and mitigation Transfer learning Feature extraction Mobile handsets Reliability Standards Residual neural networks

来源：评论

学校读者我要写书评

暂无评论

Temporal-Guided Spiking Neural Networks for Event-Based Human Action Recognition

arXiv

引用

arXiv 2025年

作者： Yang, Siyuan Lu, Shilin Wang, Shizheng Er, Meng Hwa Zheng, Zengwei Kot, Alex C. School of Electrical and Electronic Engineering Nanyang Technological University Singapore College of Computing and Data Science Nanyang Technological University Singapore Institute of Microelectronics Chinese Academy of Sciences China Department of Computer Science and Computing Zhejiang University City College China

This paper explores the promising interplay between spiking neural networks (SNNs) and event-based cameras for privacy-preserving human action recognition (HAR). The unique feature of event cameras in capturing only the outlines of motion, combined with SNNs’ proficiency in processing spatiotemporal data through spikes, establishes a highly synergistic compatibility for event-based HAR. Previous studies, however, have been limited by SNNs’ ability to process long-term temporal information, essential for precise HAR. In this paper, we introduce two novel frameworks to address this: temporal segment-based SNN (TS-SNN) and 3D convolutional SNN (3D-SNN). The TS-SNN extracts long-term temporal information by dividing actions into shorter segments, while the 3D-SNN replaces 2D spatial elements with 3D components to facilitate the transmission of temporal information. To promote further research in event-based HAR, we create a dataset, FallingDetection-CeleX, collected using the high-resolution CeleX-V event camera (1280 × 800), comprising 7 distinct actions. Extensive experimental results show that our proposed frameworks surpass state-of-the-art SNN methods on our newly collected dataset and three other neuromorphic datasets, showcasing their effectiveness in handling long-range temporal information for event-based HAR. Copyright © 2025, The Authors. All rights reserved.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Modeling PROTAC Degradation Activity with Machine Learning

arXiv

引用

arXiv 2024年

作者： Ribes, Stefano Nittinger, Eva Tyrchan, Christian Mercado, Rocío Department of Computer Science and Engineering Section for Data Science and AI Chalmers University of Technology Chalmersplatsen 4 Gothenburg412 96 Sweden BioPharmaceuticals R&D AstraZeneca Pepparedsleden 1 Mölndal431 83 Sweden

PROTACs are a promising therapeutic modality that harnesses the cell’s built-in degradation machinery to degrade specific proteins. Despite their potential, developing new PROTACs is challenging and requires significant domain expertise, time, and cost. Meanwhile, machine learning has transformed drug design and development. In this work, we present a strategy for curating open-source PROTAC data and an open-source deep learning tool for predicting the degradation activity of novel PROTAC molecules. The curated dataset incorporates important information such as pDC50 , Dmax , E3 ligase type, POI amino acid sequence, and experimental cell type. Our model architecture leverages learned embeddings from pretrained machine learning models, in particular for encoding protein sequences and cell type information. We assessed the quality of the curated data and the generalization ability of our model architecture against new PROTACs and targets via three tailored studies, which we recommend other researchers to use in evaluating their degradation activity models. In each study, three models predict protein degradation in a majority vote setting, reaching a top test accuracy of 80.8% and 0.865 ROC AUC, and a test accuracy of 62.3% and 0.604 ROC AUC when generalizing to novel protein targets. Our results are not only comparable to state-of-the-art models for protein degradation prediction, but also part of an open-source implementation which is easily reproducible and less computationally complex than existing approaches. © 2024, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Discovering Personalized Characteristic Communities in Attributed Graphs

Discovering Personalized Characteristic Communities in Attri...

引用

International Conference on data engineering

作者： Yudong Niu Yuchen Li Panagiotis Karras Yanhao Wang Zhao Li School of Computing and Information Systems Singapore Management University Singapore Department of Computer Science University of Copenhagen Copenhagen Denmark School of Data Science and Engineering East China Normal University Shanghai China Zhejiang Lab Hangzhou China

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

What is the widest community in which a person exercises a strong impact? Although extensive attention has been devoted to searching communities containing given individuals, the problem of finding their unique communities of influence has barely been examined. In this paper, we study the novel problem of Characteristic cOmmunity Discovery (COD) in attributed graphs. Our goal is to identify the largest community, taking into account the query attribute, in which the query node has a significant impact. The key challenge of the COD problem is that it requires evaluating the influence of the query node over a large number of hierarchically structured communities. We first propose a novel compressed COD evaluation approach to accelerate the influence estimation by eliminating redundant computations for overlapping communities. Then, we further devise a local hierarchical reclustering method to alleviate the skewness of hierarchical communities generated by global clustering for a specific query attribute. Extensive experiments confirm the effectiveness and efficiency of our solutions to COD: they find characteristic communities better than existing community search methods by several quality measures and achieve up to 25 x speedups against well-crafted baselines.

关键词： Estimation Search problems data engineering

来源：评论

学校读者我要写书评

暂无评论

LEARN: Selecting Samples Without Training Verification for Communication-Efficient Vertical Federated Learning

LEARN: Selecting Samples Without Training Verification for C...

引用

IEEE Conference on Global Communications (GLOBECOM)

作者： Tong Liu Feng Lyu Jun Ma Yongheng Deng Jiayin Chen Qilong Tan Yaoxue Zhang Big Data Institute Central South University Changsha China School of Computer Science and Engineering Central South University Changsha China Hunan Energy Big Data Intelligence Limited Changsha China Department of Computer Science and Technology BNRist Tsinghua University Beijing China Department of Electrical and Computer Engineering The University of British Columbia Vancouver BC Canada

In the classical vertical federated learning (VFL) framework, feature maps and corresponding gradient information of all samples are transferred between the server and clients, which causes a significant communication burden. Therefore, to enable efficient VFL in resource-constrained wireless networks, we propose to select a part of the samples from the large training set to train models with minimal accuracy degradation. To this end, we propose LEARN, i.e., seLecting Efficient sAmples without tRaining verificatioN, to select efficient training samples for VFL. Particularly, LEARN integrates two major components named label distribution smoothing and feature center-based vertical sample filtering. The number of samples selected for each class is determined by the label distribution smoothing mechanism. Then the feature center-based vertical sample filtering component calculates the features centers and performs sample selection based on the distance between the samples and their corresponding feature center. Extensive experiments under various settings are carried out to corroborate the efficacy and robustness of LEARN.

关键词：

来源：评论

学校读者我要写书评

暂无评论

XTSFormer: Cross-Temporal-Scale Transformer for Irregular-Time Event Prediction in Clinical Applications 39

XTSFormer: Cross-Temporal-Scale Transformer for Irregular-Ti...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Xiao, Tingsong Xu, Zelin He, Wenchong Xiao, Zhengkun Zhang, Yupu Liu, Zibo Chen, Shigang Thai, My T. Bian, Jiang Rashidi, Parisa Jiang, Zhe Department of Computer and Information Science and Engineering University of Florida GainesvilleFL United States Department of Biostatistics and Health Data Science Indiana University IndianapolisIN United States Regenstrief Institute IndianapolisIN United States J. Crayton Pruitt Family Department of Biomedical Engineering University of Florida GainesvilleFL United States

ISBN: (纸本)157735897X

Adverse clinical events related to unsafe care are among the top ten causes of death in the U.S. Accurate modeling and prediction of clinical events from electronic health records (EHRs) play a crucial role in patient safety enhancement. An example is modeling de facto care pathways that characterize common step-by-step plans for treatment or care. However, clinical event data pose several unique challenges, including the irregularity of time intervals between consecutive events, the existence of cycles, periodicity, multi-scale event interactions, and the high computational costs associated with long event sequences. Existing neural temporal point processes (TPPs) methods do not effectively capture the multi-scale nature of event interactions, which is common in many real-world clinical applications. To address these issues, we propose the cross-temporal-scale transformer (XTSFormer), specifically designed for irregularly timed event data. Our model consists of two vital components: a novel Feature-based Cycle-aware Time Positional Encoding (FCPE) that adeptly captures the cyclical nature of time, and a hierarchical multi-scale temporal attention mechanism, where different temporal scales are determined by a bottom-up clustering approach. Extensive experiments on several real-world EHR datasets show that our XTSFormer outperforms multiple baseline methods. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

An Exploration of Interpolation - Machine Learning Model for Climate Model Downscaling Under the Limitation of data Quantity

An Exploration of Interpolation - Machine Learning Model for...

引用

International Technical Conference o Circuits/Systems, computers and Communications (ITC-CSCC)

作者： Chotirose Prathom Paskorn Champrasert Data Science Consortium Faculty of Engineering Chiang Mai University Chiang Mai Thailand Department of Computer Engineering Faculty of Engineering Chiang Mai University Chiang Mai Thailand

In order to response to climate change, climate model is essential for future prediction, which is advantage for adaptation planning. With the fact that the output of the climate model is in a coarse spatial resolution, it is poorly representing data on local level and requires a downscaling process to increase its resolution. To perform the downscaling, high amount of historical observed data is necessary for calibrating the model output. However, the data may not be available in some area, also Thailand. To overcome the limitation of data Quantity, four combination methods between two interpolation (Inverse Distance Weight and Triangular Irregular Network) and two machine learning models (Artificial Neural Network and Gradient Boosting Regression Tree) are experimented to explore the proper one for downscaling data on Thailand area. By considering the performance of both interpolation and machine learning model, the combination between Inverse Distance Weight and Artificial Neural Network shows the best performance in down scaling process under data Quantity limitation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Path optimization method for the sign problem caused by the fermion determinant

引用

Physical Review D 2025年第9期111卷 094503-094503页

作者： Kazuki Hisayoshi Kouji Kashiwa Yusuke Namekawa Hayato Takase Department of Computer Science and Engineering Faculty of Information Engineering Fukuoka Institute of Technology Fukuoka 811-0295 Japan Education and Research Center for Artificial Intelligence and Data Innovation Hiroshima University Hiroshima 730-0053 Japan

The path optimization method with machine learning is applied to the one-dimensional massive lattice Thirring model, which has the sign problem caused by the fermion determinant. This study aims to investigate how the path optimization method works for the sign problem. We show that the path optimization method successfully reduces statistical errors and reproduces the analytic results. We also examine an approximation of the Jacobian calculation in the learning process and show that it gives consistent results with those without an approximation.

关键词：

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：