检索结果-内蒙古大学图书馆

Leader Selection and Follower Association for UE-Centric Distributed learning in Future Wireless Networks

IEEE ACCESS 2024年 12卷 154160-154172页

作者： Parsaeefard, Saeedeh Roessel, Sabine Ghavamabad, Anousheh Gholami Zaus, Robert Raaf, Bernhard Apple Inc Cupertino CA 95014 USA Apple Technol Engn BV & Co KG D-80335 Munich Germany

This paper focuses on UE-centric DL algorithms where UEs initiate requests to adapt AI/ML models for better performance in dynamic environment, e.g., locally refined AI/ML models among a set of headsets or smartphones. This new setup requires selecting a set of UEs as aggregators (here called leaders) and another set as followers, where all UEs update their models based on their local data, and followers share theirs with leaders for aggregation. From a networking perspective, the first question is how to select leaders and associate followers efficiently. This results in a high dimensional mixed integer programming problem and involves internal UE state information and state information among UEs, called external state information in this paper. To address this challenge, we introduce two new indices: a Leader Internal Index (LII), which is a function of the internal states of each device, demonstrating the willingness to be a leader such as battery life and AI/hardware accelerators, and a Leader eXternal Index (LXI), which is a function of external state information among UEs, such as trust, channel condition, and any aspect relevant for associating a follower with a leader. These two indices transform the highly complex leader selection and follower association problem into a better tractable formulation. More importantly, LIIs and LXIs allow to keep the internal and external state information of this problem inside of each device without compromising users' privacy. We present the necessary constraints and objective function, propose a distributed algorithm, and explore the feasibility, challenges, and implementation within 5G and 6G networks. Our simulation results show that the performance of the distributed algorithm is only 8.9% lower compared to the optimal solution if the related threshold is adjusted efficiently. Also, the message-passing overhead of our approach is linear with the number of users while it effectively translates an NP-hard problem into a

关键词： Servers 6G mobile communication Wireless networks Adaptation models Real-time systems Data models Computational modeling machine learning algorithms Indexes Stochastic processes Distributed management Distributed machine learning (DL) algorithms fine-tuning federated learning subnetworks in 6G private networks in 6G

来源：评论

学校读者我要写书评

暂无评论

Quantum machine learning Playground

引用

IEEE COMPUTER GRAPHICS AND APPLICATIONS 2024年第5期44卷 40-53页

作者： Debus, Pascal Issel, Sebastian Tscharke, Kilian Fraunhofer Inst Appl & Integrated Secur D-85748 Garching Germany

This article introduces an innovative interactive visualization tool designed to demystify quantum machine learning (QML) algorithms. Our work is inspired by the success of classical machine learning visualization tools, such as TensorFlow Playground, and aims to bridge the gap in visualization resources specifically for the field of QML. The article includes a comprehensive overview of relevant visualization metaphors from both quantum computing and classical machine learning, the development of an algorithm visualization concept, and the design of a concrete implementation as an interactive web application. By combining common visualization metaphors for the so-called data reuploading universal quantum classifier as a representative QML model, this article aims to lower the entry barrier to quantum computing and encourage further innovation in the field. The accompanying interactive application is a proposal for the first version of a QML playground for learning and exploring QML models.

关键词： Quantum computing Logic gates Qubit machine learning Data visualization Quantum entanglement machine learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Validating Unsupervised machine learning Techniques for Software Defect Prediction With Generic Metamorphic Testing

引用

IEEE ACCESS 2024年 12卷 165155-165172页

作者： Chan, Pak Yuen Patrick Keung, Jacky City Univ Hong Kong Dept Comp Sci Hong Kong Peoples R China

In the realm of software defect prediction, unsupervised models often step in when labelled datasets are scarce, despite facing the challenge of validating models without prior knowledge of data. Addressing this, we proposed a novel approach leveraging generic metamorphic testing to validate such models effectively, bypassing the need for expert-derived metamorphic relations. Our method identifies five categories of generic metamorphic relations, further divided into twenty-one individual generic metamorphic relations, all formulated through generic Data Mutation Operators. This framework enables us to generate follow-up datasets from the source datasets, training respective software defect prediction models. By comparing predictions between the source and follow-up software defect prediction models and identifying inconsistencies, we can assess the model's sensitivity to generic metamorphic relations as a form of validation. This approach was rigorously evaluated across twenty software defect prediction models, incorporating fourteen different machine learning algorithms and twenty high-dimensional public datasets. Remarkably, the robustness of our generic MT model was confirmed, showing substantial effectiveness in validating software defect prediction models, independent of whether they were supervised or unsupervised. Software defect prediction models, using Agglomerative clustering and Density-Based Spatial Clustering of Applications with Noise algorithms, did not violate any metamorphic relation, and nineteen software defect prediction models did not significantly violate the generic metamorphic relation "Shrinkage and Expansion". Our findings suggest that employing generic metamorphic relations, especially "Shrinkage and Expansion", can universally enhance the validation of defect prediction models. Furthermore, our model can be applied to continuously monitor software defect prediction models.

关键词： Software Predictive models machine learning Adaptation models Testing Data models machine learning algorithms Numerical models Feature extraction Mathematical models Clustering methods Defect detection Clustering machine learning metamorphic relation metamorphic testing software defect prediction validation

来源：评论

学校读者我要写书评

暂无评论

Predicting Medium-Term Stock Index Direction Using Constituent Stocks and machine learning

引用

IEEE ACCESS 2024年 12卷 84968-84983页

作者： Bareket, A. Parv, B. Babes Bolyai Univ Fac Math & Comp Sci Cluj Napoca 400347 Romania

Predicting stock index movements is challenging due to market randomness. This paper addresses the problem of predicting medium-term stock index direction, an area with limited coverage in existing literature. We propose a novel model based on machine learning algorithms that employs relative indicators of constituent stocks within an index. The objective is to identify market entry points where the likelihood of achieving a significant return threshold is higher. To achieve this, supervised binary classifiers and other machine learning techniques have been applied, setting the class label '1' for significant index rises occurring within a defined medium term of 70 trading days and the class label '0' otherwise. Three indices were investigated: Nasdaq 100, where a significant rise was defined as a 10% increase, Dow Jones Industrial Average with an 8% increase, and the German Dax at 6%. Our investigation into different methods of utilizing constituent stocks revealed that focusing on the most weighted stocks yields the most promising results across various stock indices. The proposed model dynamically selects the most effective classifiers, SVM, KNN, Voting Classifier, and RF, tailored to varying market conditions. Employing a rolling forecast method, it utilizes the relative indicators on heavily weighted stocks and the index, demonstrating accuracy up to 0.97 and F1-scores for the '1' label up to 0.90. This enhances the ability to determine the optimal timing for market entry and, crucially, when the chances for high returns are limited. Additionally, we illuminate the conditions under which the model is most effective.

关键词： Indexes Symbols machine learning Correlation Sorting Predictive models Support vector machines Stock markets Constituent stocks within an index machine learning algorithms predicting medium-term stock index direction relative indicators

来源：评论

学校读者我要写书评

暂无评论

SiO2 Nanolayer Regulated Ag@Cu Core-Shell SERS Platform Integrated machine learning for Intelligent Identification of Jujuboside A, Saikosaponin A and Timosaponin A-III

IEEE PHOTONICS JOURNAL

引用

IEEE PHOTONICS JOURNAL 2024年第4期16卷 1页

作者： Zhou, Wenying Han, Xue Wu, Yanjun Shi, Guochao Xu, Shiqi Wang, Mingli Yuan, Wenzhi Cui, Jiahao Li, Zelong Chengde Med Univ Hebei Int Res Ctr Med Engn Chengde 067000 Peoples R China Chengde Med Univ Affiliated Hosp Dept Neurol Chengde 067000 Peoples R China Yanshan Univ Sch Sci State Key Lab Metastable Mat Sci & Technol Key Lab Microstruct Mat Phys Hebei Prov Qinhuangdao 066004 Peoples R China

An effective SERS-based detection method assisted by machine learning algorithm has been developed to intelligently identify the pharmacodynamic substances in traditional Chinese medicine (TCM) which aided in the quality control and identification of TCM. In this work, the ultrasensitive grating-like core-shell Ag@SiO2@Cu@moth wing (Ag@SiO2@Cu@MW) SERS platform was explored which can precisely control the intergap distances by adjusting the thickness of the SiO2 layer. This SERS platform demonstrated reproducibility and reliability, with a low relative standard deviation (RSD) of 7.38% and an enhancement factor (EF) of 2.49 x 10(7). The optimized Ag-30@SiO2(4)@Cu-20@MW substrate were then applied in the accurately analyzing pharmacodynamic substances. Specifically, the label-free SERS analysis showed the distinct spectral features for Jujuboside A, Saikosaponin A and Timosaponin A-III. machine learning algorithms, such as principal component analysis (PCA), decision tree (DT), support vector machine (SVM), k-nearest neighbors (kNN) were employed and further in differentiating with the three pharmacodynamic substances Raman spectrum groups. These results indicate that SERS technology in combination with machine learning algorithms can not only achieve rapid and accurate detection of different types of pharmacodynamic substances, but also promote the modernization and international application of TCM.

关键词： Pharmacodynamics Substrates Gratings machine learning Magnetic cores machine learning algorithms Electromagnetics Grating-like core-shell structure machine learning pharmacodynamic substances in traditional Chinese medicine SERS

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection in Logs Using Deep learning

引用

IEEE ACCESS 2024年 12卷 176124-176135页

作者： Aziz, Ayesha Munir, Kashif Natl Univ Comp & Emerging Sci FAST Sch Comp Islamabad 44000 Pakistan Arab Open Univ Fac Comp Studies Riyadh Saudi Arabia

Detection of abnormalities is important for the security and reliability of computer systems as they heavily rely on logs to detect anomalies. The logs provide general information, errors, warnings, and debugging information. Existing approaches for detecting anomalies are sometimes inaccurate due to their limitations related to log-processing leading to loss of semantic significance. Existing approaches, like Deeplog and LogAnomaly, have restrictions in detecting irregularities in log frameworks mainly in large dynamic systems. In this paper, we propose a hybrid anomaly detection technique that combines unsupervised approaches such as Self-Organizing Maps, Bert Encoders, and Autoencoders to handle these issues. The approach improves anomaly identification accuracy by employing semantic vectors obtained by the Bert Encoder to recognize patterns with autoencoders. The evaluation results show that the proposed strategy outperforms the existing methods for various types of data including system logs, network traffic, and financial transactions.

关键词： Anomaly detection Deep learning Semantics Encoding Bidirectional control Real-time systems Data models Pipelines machine learning algorithms Clustering algorithms classification unsupervised learning deep learning

来源：评论

学校读者我要写书评

暂无评论

Exploring Quantum machine learning for Enhanced Skin Lesion Classification: A Comparative Study of Implementation Methods

引用

IEEE ACCESS 2024年 12卷 104568-104584页

作者： Reka, S. Sofana Karthikeyan, H. Leela Shakil, A. Jack Venugopal, Prakash Muniraj, Manigandan Vellore Inst Technol Ctr Smart Grid Technol Sch Elect Engn Chennai 600127 India Vellore Inst Technol Sch Elect Engn Chennai 600127 India

Skin diseases affect millions of people worldwide, leading to significant healthcare burdens and challenges in diagnosis and treatment. In the past few years, machine learning techniques have demonstrated potential in assisting dermatologists with diagnosing various skin conditions. As in, conventional machine learning algorithms might encounter challenges in handling the complexity and distinction of skin disease classification tasks, primarily because of the intricate nature of medical image data with its high dimensional properties. In this work, the main analysis is done based on exploring quantum machine learning models for skin disease classification. This approach blends with the aspects of quantum computing with the conventional machine learning techniques to push the boundaries of skin disease classification. This work harnesses the HAM10000 dataset, an extensive compilation of categorized images portraying common skin lesions, to train and assess the efficacy of the proposed methodologies. Quantum computing libraries such as PennyLane and Qiskit is used in this study. Using different combination of qubit rotation encoding and decoding using three types of Pauli gates such as Pauli X, Y and Z gates are implemented and compared using proposed Quanvolutional neural network. Features extracted using MobileNet pre-trained network is used to build Quantum support vector classifier. These quantum machine learning models are compared with some well-known pre-trained models such as Resnet50, Inception-Resnet, Densenet121, DenseNet201 and MobileNet. The combination of RY qubit rotation and PauliZ gate in quantum convolution layer in Quanvolutional neural network produced the optimal classification accuracy of 82.86% more than any other models included in this study. In contrast, Quantum Support Vector Classifier produced similar classification accuracy of 72.5% with respect to pre-trained models.

关键词： Skin Diseases Accuracy Computational modeling machine learning Lesions machine learning algorithms HAM10000 dataset Qiskit quantum machine learning quanvolutional neural network quantum support vector classifier skin lesion PennyLane

来源：评论

学校读者我要写书评

暂无评论

learning vs. understanding: When does artificial intelligence outperform process-based modeling in soil organic carbon prediction?

引用

NEW BIOTECHNOLOGY 2024年 81卷 20-31页

作者： Bernardini, Luca G. Rosinger, Christoph Bodner, Gernot Keiblinger, Katharina M. Izquierdo-Verdiguier, Emma Spiegel, Heide Retzlaff, Carl O. Holzinger, Andreas FFoQSI Technopk 1 Haus D A-3430 Tulln An Der Donau Austria Univ Nat Resources & Life Sci BOKU Vienna Inst Agron Konrad Lorenz Str 24 A-3430 Tulln An Der Donau Austria Univ Nat Resources & Life Sci BOKU Vienna Inst Soil Res Peter Jordan Str 82 A-1190 Vienna Austria Univ Nat Resources & Life Sci Inst Geomatics Vienna BOKU Peter Jordan Str 82 A-1190 Vienna Austria Austrian Agcy Hlth & Food Safety AGES Inst Soil Hlth & Plant Nutr Spargelfeldstr 191 A-1226 Vienna Austria Univ Nat Resources & Life Sci BOKU Vienna Inst Forest Engn Human Ctr AI Lab Peter Jordan Str 82 A-1190 Vienna Austria

In recent years, machine learning (ML) algorithms have gained substantial recognition for ecological modeling across various temporal and spatial scales. However, little evaluation has been conducted for the prediction of soil organic carbon (SOC) on small data sets commonly inherent to long-term soil ecological research. In this context, the performance of ML algorithms for SOC prediction has never been tested against traditional processbased modeling approaches. Here, we compare ML algorithms, calibrated and uncalibrated process-based models as well as multiple ensembles on their performance in predicting SOC using data from five long-term experimental sites (comprising 256 independent data points) in Austria. Using all available data, the ML-based approaches using Random forest and Support vector machines with a polynomial kernel were superior to all process-based models. However, the ML algorithms performed similar or worse when the number of training samples was reduced or when a leave-one-site-out cross validation was applied. This emphasizes that the performance of ML algorithms is strongly dependent on the data-size related quality of learning information following the well-known curse of dimensionality phenomenon, while the accuracy of process-based models significantly relies on proper calibration and combination of different modeling approaches. Our study thus suggests a superiority of ML-based SOC prediction at scales where larger datasets are available, while processbased models are superior tools when targeting the exploration of underlying biophysical and biochemical mechanisms of SOC dynamics in soils. Therefore, we recommend applying ensembles of ML algorithms with process-based models to combine advantages inherent to both approaches.

关键词： Artificial intelligence Comparison of model performance machine learning algorithms Modeling Model ensembles Process -based models Soil organic carbon

来源：评论

学校读者我要写书评

暂无评论

Analyzing Social Exchange Motives With Theory-Driven Data and machine learning

引用

IEEE ACCESS 2024年 12卷 2135-2149页

作者： Igwe, Kevin Durrheim, Kevin Univ Johannesburg Fac Humanities Dept Psychol ZA-2092 Johannesburg South Africa

This study investigated the capability of machine learning to analyze and predict individuals' motives within an experimental game context. Although humans predict the motives of others to respond appropriately, these motives often overlap and are difficult to tease apart in social exchange contexts. An act of reciprocated favor, for example, could equally be motivated by parochial altruism as by self-interest, and human attributions of motives are notoriously biased. Can machine learning effectively predict motives and offer insights into how individuals prioritize overlapping motives? We analyzed motives in an experimental social exchange game using a Multilayer Perceptron (MLP), Decision Tree (DT), Random Forest (RF), Gaussian Naive Bayes (GNB), K-Nearest Neighbor (KNN), Support Vector Classifier (SVC), Logistic Regression (LR), and a novel combination of Clustering and Hidden Markov Model (C-HMM). The accuracy, precision, recall, and f1-score were compared in two phases: Phase 1, where individuals focus on a single motive, and Phase 2, where individuals consider multiple motives when making decisions in social exchange. With accuracies of 86.96%, 67.31%, and 70.74% for each class of motives tested in Phase 1, C-HMM outperformed the other models. LR demonstrated the best performance, with an accuracy of 45.57% in Phase 2. Further analysis shows that the strength of relationships with ingroup members is a reliable predictor of reciprocation motives. Our model can be extended to nudging prosocial behavior in human-agent collaborations.

关键词： machine learning Games Hidden Markov models Videos Psychology machine learning algorithms Task analysis motive prediction social exchange intent prediction

来源：评论

学校读者我要写书评

暂无评论

DDoS Attack Detection on Cloud Computing Services using algorithms of machine learning: Survey

DDoS Attack Detection on Cloud Computing Services using Algo...

引用

International Conference on Computing Methodologies and Communication (ICCMC)

作者： Chilla Sathvika Vuyyuru Satwika Yarrapothu Sruthi Maddali Geethika Suneetha Bulla Swathi K Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram India

Nowadays cloud computing services have become the most popular internet-based computing and many organizations use their services. Due to this, many cyber-attacks are happening in the cloud. One of those attacks is the Distributed-Denial-Of-Service (DDoS) attack. It floods unreal traffic, hence troubles the availability of the resources. This article is about DDoS attacks and detection of DDoS attacks using machine learning. There are many famous machine learning algorithms such as naïve bayes, random forest, support vector machines etc. These machine learning algorithms can be used to detect the DDoS attacks on doud. There are several datasets available for the researchers to test their proposed models which include NSL-KDD, ICDX, CIDDS-001, CICIDS 2017 etc. This paper presents a detailed study on different machine learning based techniques proposed by various authors to detect the DDoS attack in the cloud environment. A brief explanation has been provided on the available datasets and further discussed about the general methodology.

关键词： Support vector machines Cloud computing machine learning algorithms Heuristic algorithms Organizations Denial-of-service attack 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：