检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Cai, Ruichu Huang, Haiqin Jiang, Zhifan Li, Zijian Zhou, Changze Liu, Yuequn Liu, Yuming Hao, Zhifeng School of Computer Science Guangdong University of Technology China Peng Cheng Laboratory Shenzhen China Machine Learning Department Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates Shantou University China

Current methods for time series forecasting struggle in the online scenario, since it is difficult to preserve long-term dependency while adapting short-term changes when data are arriving sequentially. Although some recent methods solve this problem by controlling the updates of latent states, they cannot disentangle the long/short-term states, leading to the inability to effectively adapt to nonstationary. To tackle this challenge, we propose a general framework to disentangle long/short-term states for online time series forecasting. Our idea is inspired by the observations where short-term changes can be led by unknown interventions like abrupt policies in the stock market. Based on this insight, we formalize a data generation process with unknown interventions on short-term states. Under mild assumptions, we further leverage the independence of short-term states led by unknown interventions to establish the identification theory to achieve the disentanglement of long/short-term states. Built on this theory, we develop a Long Short-Term Disentanglement model (LSTD) to extract the long/short-term states with long/short term encoders, respectively. Furthermore, the LSTD model incorporates a smooth constraint to preserve the long-term dependencies and an interrupted dependency constraint to enforce the forgetting of short-term dependencies, together boosting the disentanglement of long/short-term states. Experimental results on several benchmark datasets show that our LSTD model outperforms existing methods for online time series forecasting, validating its efficacy in real-world applications. Copyright © 2025, The Authors. All rights reserved.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Deep learning-Powered Edge Analytics for IoT-based Sensor Networks 2

Deep Learning-Powered Edge Analytics for IoT-based Sensor Ne...

引用

2nd International Conference on machine learning and Autonomous Systems, ICMLAS 2025

作者： Karthikeyan, M. Saravana Subramani, Ponnusamy Selvam, M. Panneer Sworna Kokila, M.L. Vijayalakshmi, R. Sundaravadivel, P. Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Avadi Department of Computer Science and Engineering Chennai India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Physics Chennai India Sona College of Technology Department of Electrical and Electronics Engineering Salem India School of Computing SRM Institute of Science and Technology Kattankulathur Faculty of Engineering and Technology Department of Computing Technologies Chennai India Velammal College of Engineering and Technology Department of Computer Science and Engineering Madurai India Saveetha Engineering College Department of Artificial Intelligence and Machine Learning Chennai India

ISBN: (纸本)9798331505745

The rapid expansion of loT-based sensor networks has necessitated the development of efficient edge analytics frameworks to process vast amounts of data in real time while minimizing computational overhead. Deep learning-powered edge computing has emerged as a transformative approach, enhancing data processing capabilities at the network edge while addressing constraints related to latency, bandwidth, and energy consumption. This study introduces a novel algorithm, Lightweight AI Model Compression for Energy-Efficient IoT Edge Devices (LiteEdgeAI), designed to optimize deep learning models for resource-constrained edge environments. The proposed method employs quantization, pruning, and knowledge distillation techniques to achieve significant reductions in model size and computational complexity while maintaining high inference accuracy. To validate the efficiency of LiteEdgeAI, a comparative simulation analysis was conducted against existing state-of-the-art algorithms using key performance metrics such prediction accuracy, energy efficiency and computational complexity. Experimental results demonstrated that LiteEdgeAI outperformed baseline models. The findings highlight the potential of LiteEdgeAI in enabling scalable, low-power, and real-time edge intelligence for IoT-based sensor networks. © 2025 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Estimation of Response Time with Neural Networks in Cloud Computing System

Estimation of Response Time with Neural Networks in Cloud Co...

引用

Advances in computer science, Electrical, Electronics, and Communication Technologies (CE2CT), International Conference on

作者： Rajesh More Sanjna Suresh Sathish Kumar Veerappampalayam Easwaramoorthy Haider Ali Rizvi Kannan Kunnathully Sahil K. Gupta Departmen of AIML Cloudwerx Wordwide Hyderabad Department of Computer Science and Engineering Amrita Vishwa Vidyapeetham Coimbatore School of Engineering and Technology Sunway University Selangor Darul Ehsan Malaysia Department of Artificial Intelligence and Machine Learning Yogananda School of Artificial Intelligence Shoolini University Department of Research Veltech University Chennai Department of Computer Science and Engineering Tula's Institute Dehradun India

ISBN: (数字)9798331518578

ISBN: (纸本)9798331518585

Resource allotment, responsiveness, connection, research of unexplored assets, related resource modeling, and asset scheduling are just a few of the numerous factors and concerns that need to be considered to enhance cloud computing efficiency. The functionality of the cloud has a significant impact on the propagation of cloud architecture. Consequently, it is important to determine the components that influence cloud function to analyze it. Response duration is the primary aspect that significantly affects cloud computation functioning, according to the research. The response duration assistance is among the numerous different variables that may be used to organize resource applications. artificial neural networks (ANNs) were employed as a technique for evaluating the parameter of pursuit, and a fork-join framework or an architecture with demand partitioning was selected as the queuing paradigm. As a result, this study suggests a load-managing method depending on cloud demand response duration using the ARIMA Estimation of Response Duration Method. The fundamental concept is to employ ARIMA methods to estimate the future response duration, providing a more efficient method of allocating resources with limited values. The results of the investigation demonstrated that the estimations were more precise compared to those that had been recently established. The results of the study indicate that estimation is an outstanding path for load balance and has possibility and value for load balance with displayed response duration. Additionally, the suggested method makes it feasible to acquire estimations for a wider range of cloud structure functioning signs compared to earlier feasible and also to extend the evaluation of the cloud platform to the instance of a structure with a non-Poisson data flow and non-exponential assistance duration.

关键词： computer science Cloud computing Processor scheduling Estimation computer architecture artificial neural networks Load management Scheduling Demand response Time factors

来源：评论

学校读者我要写书评

暂无评论

Congestion Control Routing Scheme for WSN using AI Technologies 3

Congestion Control Routing Scheme for WSN using AI Technolog...

引用

3rd International Conference on Electrical, Electronics, Information and Communication Technologies, ICEEICT 2024

作者： Basha, S.K. Mahaboob Gurumoorthi, E. Beulah, E. Mercy Kesavan, R. Kalaiselvan, S.A. Kumar, Lenin Tkr College of Engineering and Technology Department of Computer Science and Engineering Telangana India Cmr College of Engineering & Technology Department of Computer Science and Engineering Telangana India Vel Tech Multi Tech Dr. Rangarajan Dr.Sakunthala Engineering College Department of Computer Science and Engineering Chennai Avadi India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science and Engineering Chennai India Rajalakshmi Engineering College Department of Artificial Intelligence and Machine Learning Chennai India Vignan Institute of Technology and Sciences Department of Electronics Communication and Engineering Telangana India

ISBN: (纸本)9798350369083

An essential part of wireless sensor networks (WSN) is managing congestion, which occurs when the amount of traffic exceeds the combined or individual capacities of the underlying channel. As a result, developing more advanced methods to prevent, detect, and alleviate congestion requires particular considerations. In order to obtain the highest throughput, these strategies must take into account the limited resources of the WSN. Dedicated congestion control strategies and routing protocols that help in congestion detection as well as management are two of the many methods that have been created in recent years. As a means of avoiding congestion, the sink node in the previous designs would reset the topology and reduce bulk traffic. In this article, we lay the groundwork for WSNs and AI, the latter of which will try to prevent congestion in WSNs from the get-go and the former of which will try to minimize the spread of impending congestion by rerouting traffic. An integral part of modern life, artificial intelligence (AI) allows us to create self-governing systems. It is possible to enhance performance and reliability by making use of several sophisticated AI approaches. Better network management and routing in WSN may be the outcome of studying the AI algorithm used by WSN, leading to a more dependable network. Here we'll take a look at several AI algorithms that have found their way into WSNs, and we'll talk about how these algorithms might help WSNs overcome their challenges and become more reliable and efficient. Additionally, artificial intelligence has often been disregarded in these networks because of limitations on data processing as well as power consumptions. Thanks to AI, WSN is now lightning fast, error-free, as well as effective in almost every way. Using AI methods in nodes of wireless sensors for congestion aware routes is the goal of this work. © 2024 IEEE.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

Quantum Gradient Class Activation Map for Model Interpretability

Quantum Gradient Class Activation Map for Model Interpretabi...

引用

IEEE Workshop on Signal Processing Systems (SIPS)

作者： Hsin-Yi Lin Huan-Hsin Tseng Samuel Yen-Chi Chen Shinjae Yoo Department of Mathematics and Computer Science Seton Hall University South Orange NJ USA Artificial Intelligence & Machine Learning Department Brookhaven National Laboratory Upton NY USA Wells Fargo New York NY USA

ISBN: (数字)9798350373752

ISBN: (纸本)9798350373769

Quantum machine learning (QML) has recently made significant advancements in various topics. Despite the successes, the safety and interpretability of QML applications have not been thoroughly investigated. This work proposes using Variational Quantum Circuits (VQCs) for activation mapping to enhance model transparency, introducing the Quantum Gradient Class Activation Map (QGrad-CAM). This hybrid quantum-classical computing framework leverages both quantum and classical strengths and gives access to the derivation of an explicit formula of feature map importance. Experimental results demonstrate significant, fine-grained, class-discriminative visual explanations generated across both image and speech datasets.

关键词： Location awareness Visualization Quantum advantage Computational modeling Conferences machine learning Signal processing Safety Quantum circuit Integrated circuit modeling

来源：评论

学校读者我要写书评

暂无评论

Collaborative and Integrated Platform to Support Distributed Manufacturing System Using a Service-Oriented Approach Based on Cloud Computing Paradigm

Collaborative and Integrated Platform to Support Distributed...

引用

2025 IEEE International Conference on Computational, Communication and Information Technology, ICCCIT 2025

作者： Nainwal, Ankita Sharma, Vishal Varshney, Neeraj Shirish Boob, Nandini Reddy, N.V. Uma Reddy, K. Jyothsna Graphic Era Deemed to Be University Department of Computer Science & Engineering Dehradun India Lovely Professional University Phagwara India GLA University Department of Computer Engineering and Applications Mathura India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamilnadu Chennai India New Horizon College of Engineering Department of Artificial Intelligence & Machine Learning Bangalore India MLR Institute of Technology Department of CSE-AI&ML Telangana Hyderabad India

ISBN: (纸本)9798331512965

Increasing interest in distributed manufacturing systems is a result of the dynamic nature of today's business environment and with that comes the popularity of their use. This has given rise in the interest in distributed manufacturing systems. The indirect consequence of this has led to much higher use of distributed manufacturing systems. A large number of production processes, dispersed across a multitude of locations geographically separate, must be controlled and integrated in order to achieve production agility, flexibility and efficiency of costs. In our most recent project, we developed an integrated, collaborative manufacturing platform, the centerpiece of which was LAYMOD. To address the issues posed by such systems, this research presents a collateral and integrated platform based on a service oriented approach that can operate within the cloud computing paradigm. These systems present problems which the study is conducted in order to solve. Utilising the features of cloud computing, it aims to serve as a platform in solving process coordination and hence improving efficiency and scalability of distant manufacturing processes and potential real time communications among various stake holders. Furthermore, statistical research on the rates of platform module adoption in different settings provides specifics of (a) use patterns of some platform modules and (b) what capabilities are provided by some platform modules. When extrapolated to a wider size, our work is applied towards the creation of collaborative and integrated platforms for a number of the various manufacturing processes which are currently in use. © 2025 IEEE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Analysis of classification and clustering techniques for ambient AQI using machine learning algorithms 4

Analysis of classification and clustering techniques for amb...

引用

4th International Conference on Smart Systems and Inventive Technology, ICSSIT 2022

作者： Senthil Kumar, R. Arulanandham, Anidha Arumugam, Suresh Dinesh, G. Thirukkumaran, R. Subashmoorthy, R. Department of Computer Science and Engineering New Horizon College of Engineering Marathalli Bengaluru India Department of Artificial Intelligence and Machine Learning New Horizon College of Engineering Marathalli Bengaluru India Department of Computer Science and Engineering New Horizon College of Engineering Bengaluru India Department of Mathematics Amrita Vishwa Vidyapeetham University Coimbatore India

ISBN: (纸本)9781665401180

The ambient air quality index impacts people's health. The air quality index of any place is measured and analyzed in everyday routine. The AQI information helps the people to know and causes of the major pollutants. The objective of the proposed study on the classifications and cluster of ambient air quality index of south Indian cities This dataset about the pollutants information for analysis is considered the last six years' data from 2015 to 2020. Various data preprocessing techniques are applied on datasets for handling missing values and range normalization used on the features. Feature selection used the Person Correlation with the ranker search algorithm to evaluate the worth of attributes and the class variable. A detailed analysis was performed using various classification algorithms such as the Naive Bayesian model and Bayes network model, the regression models such as support vector regression, logistic regression, and multilayer perceptron model, the instance-based models such as KNN and locally weighted regression, the ensemble models such as Bagging and Boosting model and Tree-based models such as J48 and Random forest are used. From the clustering technique, k-means clustering and EM clustering were used for the analysis. Results display a comparative analysis on all the experimented techniques based on the various terms such as accuracy, RMSE, and time to build the model. WEKA-3.8.5 Tool is used for preprocessing and implementation of the machine learning models and the accuracy comparison is discussed. © 2022 IEEE

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

An Optimized Hybrid Deep learning and IoT-Enabled Health System in Retina Image Analysis for Blindness Detection

An Optimized Hybrid Deep Learning and IoT-Enabled Health Sys...

引用

Self Sustainable artificial intelligence Systems (ICSSAS), International Conference on

作者： J Yamini T Kanimozhi A Jenefa K Bagyalakshmi K Aarthi P Dhivya Department of Artificial Intelligence and Machine learning Kalaignar Karunanidhi Institute of Technology Coimbatore India Department of Artificial Intelligence and Data Science Sri Eshwar College of Engineering Coimbatore India Department of Computer Science and Engineering PPG Institute of Technology Coimbatore India Department of Mathematics SNS College of Technology Coimbatore India Department of Artificial Intelligence and Data Science Kalaignar Karunanidhi Institute of Technology Coimbatore India Department of Computer Science and Engineering Bannari Amman Institute of Technology Erode India

ISBN: (数字)9798350368413

ISBN: (纸本)9798350368420

Early signs of blind identification and retina disorder in retina image has become prominent. Deep learning techniques are used to improve the accuracy in detecting pathological conditions from the retina images. However, the models have some challenges such as suboptimal feature extraction and inefficient filtering methods. Most of the traditional methods often result in overfitting and under fitting, thus decreasing the generalizability and robustness of the model. The proposed hybrid approach combines bilateral filtering with Convolutional Neural Networks (CNN). In this approach, bilateral filtering acts as a pre-processing technique to enhance image quality by reducing noise and preserving edges for the correct extraction of features. The CNN is applied for feature extraction and it is used to self-learn complex patterns from filtered images. The proposed approach gives an accuracy of $95.65 \%$ with a loss of 0.18 without overfitting and underfitting.

关键词： Optical filters Accuracy Filtering Noise Predictive models Retina Feature extraction Convolutional neural networks Diseases Overfitting

来源：评论

学校读者我要写书评

暂无评论

The Effective Way of using machine learning Classifier Technique to Predict the Heart Muscle Condition 4

The Effective Way of using Machine Learning Classifier Techn...

引用

4th IEEE International Conference on Advance Computing and Innovative Technologies in Engineering, ICACITE 2024

作者： Vimal, V.R. Joany, R.M. Rao, Kolli Himantha Krishnammal, P. Muthu Rashid, Zakhara Abdel Hassan Safi, Hassn Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Chennai Thandalam India Sathyabama Institute of Science and Technology Department of Ece Chennai India Saveetha Engineering College Institute of Cse Department of Artificial Intelligence and Machine Learning India Vitap University School of Electronics Engineering Andhra Pradesh Amaravati India National University of Science and Technology College of Technical Engineering Dhi Qar64001 Iraq Al-Farahidi University Baghdad Iraq

ISBN: (纸本)9798350360165

Free-text is categorised into predetermined groups in text classification, a crucial field of machine learning. Due to its many uses, such as sentiment analysis, topic labelling, language identification, and spam filtering, it has attracted a great deal of study interest. Ontologies and machine learning give the knowledge of data relations or patterns, which greatly increases the text categorization efficiency. The goal of this study is to diagnose myocardial infraction among patients by machine learning classifiers. The code that goes with the created approach is meant to be flexible and work with any text categorization system. In this research, we present an improved architecture that makes use of ontology to improve the efficacy of text categorization and diagnose myocardial infraction. In particular, we provide a novel ontology-driven text categorization technique that leverages the extensive semantic data from the Disease Ontology (DOID). We examine previous research and argue that ontology-based text categorization strategies are better than traditional techniques in a number of criteria, including as F-measure, Accuracy, Precision, and Recall. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Optimal kernel choice for score function-based causal discovery 24

Optimal kernel choice for score function-based causal discov...

引用

Proceedings of the 41st International Conference on machine learning

作者： Wenjie Wang Biwei Huang Feng Liu Xinge You Tongliang Liu Kun Zhang Mingming Gong School of Mathematics and Statistics The University of Melbourne Australia and Department of Machine Learning Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates Halicioğlu Data Science Institute (HDSI) University of California San Diego School of Computing and Information Systems The University of Melbourne Australia Huazhong University of Science and Technology China School of Computer Science Faculty of Engineering The University of Sydney Australia Department of Machine Learning Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates and Department of Philosophy Carnegie Mellon University

Score-based methods have demonstrated their effectiveness in discovering causal relationships by scoring different causal structures based on their goodness of fit to the data. Recently, Huang et al. (2018) proposed a generalized score function that can handle general data distributions and causal relationships by modeling the relations in reproducing kernel Hilbert space (RKHS). The selection of an appropriate kernel within this score function is crucial for accurately characterizing causal relationships and ensuring precise causal discovery. However, the current method involves manual heuristic selection of kernel parameters, making the process tedious and less likely to ensure optimality. In this paper, we propose a kernel selection method within the generalized score function that automatically selects the optimal kernel that best fits the data. Specifically, we model the generative process of the variables involved in each step of the causal graph search procedure as a mixture of independent noise variables. Based on this model, we derive an automatic kernel selection method by maximizing the marginal likelihood of the variables involved in each search step. We conduct experiments on both synthetic data and real-world benchmarks, and the results demonstrate that our proposed method outperforms heuristic kernel selection methods.

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：