检索结果-内蒙古大学图书馆

6th International Conference on Cybernetics, Cognition and Machine Learning Applications, ICCCMLA 2024

作者： Voigt, Frederic Calero, Jose Alcarez Dahal, Keshav Wang, Qi Luck, Kai Von Stelldinger, Peer University of the West of Scotland United Kingdom Hamburg University of Applied Sciences Department of Computer Science Hamburg Germany University of the West of Scotland School of Computing Engineering & Physical Sciences Paisley United Kingdom

ISBN: (纸本)9798331505790

Large language models (LLMs) have demonstrated remarkable success in the field of natural language processing (NLP). Despite their origins in NLP, these algorithms possess the theoretical capability to process any data type represented in an NLP-like format. In this study, we use stock data to illustrate three methodologies for processing regression data with LLMs, employing tokenization and contextualized embeddings. By leveraging the well-known LLM algorithm Bidirectional Encoder Representations from Transformers (BERT) [1], we apply quantitative stock price prediction methodologies to predict stock prices and stock price movements, showcasing the versatility and potential of LLMs in financial data analysis. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

CyberSCADA Network Security Analysis Model for Intrusion Detection Systems in the Smart Grid

CyberSCADA Network Security Analysis Model for Intrusion Det...

引用

作者： Efiong, John E. Akinyemi, Bodunde O. Olajubu, Emmanuel A. Aderounmu, Ganiyu A. Degila, Jules Department of Computer Science and Engineering African Centre of Excellence Obafemi Awolowo University Ile-Ife Nigeria Institute of Mathematics and Physics African Centre of Excellence in Applied Mathematics and Computer Science University of Abomey-Calavi Godomey Benin

CyberSCADA is a soft target for industrial cyber attackers. The success of such attacks on the Smart Grid can be devastating owing to the countless processes and systems that depend on the Grid for daily operations. This paper demonstrates techniques and provides insights to help detect intrusions in the mission-critical business network as they target Cyber-Physical Systems. Several Machine Learning algorithms (ML) have been implemented at different phases of the ML pipeline in the study in view of identifying suitable models for the prediction and classifications. Ensemble classifiers have been found very potent for feature extraction and model boosting. Adaboost, GradientBoost and XGboost all yielded 99% for accuracy, precision, recall and F1-Score. During Training and Testing using 75% trainSet and 25% testSet ORNL Electric Testbed dataset, both Decision Tree (DT) and K-Neighbor (KNN) yielded the Accuracy, Precision, Recall and F1-Score 99% with a Detection Rate 63% and 80% respectively. Gaussian Naïve Bayes (GNB) produced the best Detection Rate 99% though with significantly low values for other metrics. At k-fold of 10 for cross-validation, RF yielded the best accuracy 100%, followed by DT 99%, KNN 98% and LogReg 92% with low False Positive Rates. The Area under ROC Curve shows RF 99%, KNN 99%, DT 96% and LogReg 95%. DT and KNN are considered suitable for the effective classification of attacks and prediction while GNB offers better attack detection for intrusion detections in the Grid network. Adaboost, GradientBoost and XGboost are crucial in boosting performances of ML algorithms in attack classification problems. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

A stochastic MPEC approach for grid tariff design with demand-side flexibility

引用

ENERGY SYSTEMS-OPTIMIZATION MODELING SIMULATION AND ECONOMIC ASPECTS 2023年第3期14卷 707-729页

作者： Askeland, Magnus Burandt, Thorsten Gabriel, Steven A. Energy Systems SINTEF Energy Research Trondheim Norway Department of Electric Power Engineering Norwegian University of Science and Technology Trondheim Norway Workgroup for Infrastructure Policy Technical University of Berlin Berlin Germany The Energy Transportation Environment Department German Institute for Economic Research (DIW Berlin) Berlin Germany Department of Industrial Economics and Technology Management Norwegian University of Science and Technology Trondheim Norway Department of Mechanical Engineering Applied Math and Statistics Scientific Computation Program University of Maryland College Park MD USA

As the end-users increasingly can provide flexibility to the power system, it is important to consider how this flexibility can be activated as a resource for the grid. Electricity network tariffs is one option that can be used to activate this flexibility. Therefore, by designing efficient grid tariffs, it might be possible to reduce the total costs in the power system by incentivizing a change in consumption patterns. This paper provides a methodology for optimal grid tariff design under decentralized decision-making and uncertainty in demand, power prices, and renewable generation. A bilevel model is formulated to adequately describe the interaction between the end-users and a distribution system operator. In addition, a centralized decision-making model is provided for benchmarking purposes. The bilevel model is reformulated as a mixed-integer linear problem solvable by branch-and-cut techniques. Results based on both deterministic and stochastic settings are presented and discussed. The findings suggest how electricity grid tariffs should be designed to provide an efficient price signal for reducing aggregate network peaks.

关键词： Bilevel problem Grid tariffs mathematical program with equilibrium constraints (MPEC) Uncertainty

来源：评论

学校读者我要写书评

暂无评论

Selection of Electrical Distribution System using SVAS based Einstein Averaging Operator 4

Selection of Electrical Distribution System using SVAS based...

引用

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

作者： Joshi, B.P. Sachdeva, Shweta Pant, Sangeeta Goyal, Shweta Kumar, Anuj Kharayat, Pushpendra Singh Department of Mathematics Graphic Era Hill University Bhimtal263136 India Department of Computer Science & Enggineering Graphic Era Hill University Bhimtal263136 India Dev Bhoomi Uttarakhand University School of Engineering and Computing Uttarakhand Dehradun India Department of Applied Sciences Pune Maharashtra Lavale412115 India Graphic Era Deemed to Be University Department of Electrical Engineering Dehradun248002 India School of Computer Science Engg. & Applications Akrudi Maharashtra Pune411044 India

ISBN: (纸本)9798350360165

The contribution of this study is to present the Einstein Weighted Averaging Operator (EWAO) based on the Einstein Sum (ES) under the Single-Valued Ambiguous Set (SVAS) information, which is termed as 'SVASEA'. The SVAS theory (SVAST) was offered to address ambiguity as the generalization of fuzzy set (FS). It is powerful than the FS and Intuitionistic FS due to four different degrees of memberships. Then, to apply the SVASea operator to real life problems, a framework is presented to include it in the information fusion of decision making (DM) process. Moreover, the selection of Electrical Distribution System (EDS) is carried out using the proposed operator and proposed framework to show its applicability. The obtained results and comparative analysis show the feasibility and validity of the SVASEA operator. © 2024 IEEE.

关键词： Information fusion

来源：评论

学校读者我要写书评

暂无评论

LLaMA-Based Models for Aspect-Based Sentiment Analysis 14

LLaMA-Based Models for Aspect-Based Sentiment Analysis

引用

14th Workshop on Computational Approaches to Subjectivity, Sentiment, and Social Media Analysis, WASSA 2024

作者： Šmíd, Jakub Přibáň, Pavel Král, Pavel Department of Computer Science and Engineering University of West Bohemia Faculty of Applied Sciences Czech Republic NTIS – New Technologies for the Information Society Univerzitní 2732/8 Pilsen301 00 Czech Republic

ISBN: (纸本)9798891761568

While large language models (LLMs) show promise for various tasks, their performance in compound aspect-based sentiment analysis (ABSA) tasks lags behind fine-tuned models. However, the potential of LLMs fine-tuned for ABSA remains unexplored. This paper examines the capabilities of open-source LLMs fine-tuned for ABSA, focusing on LLaMA-based models. We evaluate the performance across four tasks and eight English datasets, finding that the fine-tuned Orca 2 model surpasses state-of-the-art results in all tasks. However, all models struggle in zero-shot and few-shot scenarios compared to fully fine-tuned ones. Additionally, we conduct error analysis to identify challenges faced by fine-tuned models. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Optimal Deep Dense Convolutional Neural Network Based Classification Model for COVID-19 Disease

引用

computers, Materials & Continua 2022年第1期70卷 2031-2047页

作者： A.Sheryl Oliver P.Suresh A.Mohanarathinam Seifedine Kadry Orawit Thinnukool Department of Computer Science and Engineering St.Joseph’s College of Engineering600119ChennaiIndia Department of Computer Science and Engineering KPR Institute of Engineering and TechnologyCoimbatore641407India Faculty of Engineering Karpagam Academy of Higher EducationCoimbatore641021India Faculty of Applied Computing and Technology Noroff University CollegeKristiansand4608Norway Research Group of Embedded Systems and Mobile Application in Health Science College of ArtsMedia and TechnologyChiang Mai UniversityChiang Mai50200Thailand

Early diagnosis and detection are important tasks in controlling the spread of COVID-19.A number of Deep Learning techniques has been established by researchers to detect the presence of COVID-19 using CT scan images and ***,these methods suffer from biased results and inaccurate detection of the ***,the current research article developed Oppositional-based Chimp Optimization Algorithm and Deep Dense Convolutional Neural Network(OCOA-DDCNN)for COVID-19 prediction using CT images in IoT *** proposed methodology works on the basis of two stages such as pre-processing and ***,CT scan images generated from prospective COVID-19 are collected from open-source system using IoT *** collected images are then preprocessed using Gaussian *** filter can be utilized in the removal of unwanted noise from the collected CT scan ***,the preprocessed images are sent to prediction *** this phase,Deep Dense Convolutional Neural Network(DDCNN)is applied upon the pre-processed *** proposed classifier is optimally designed with the consideration of Oppositional-basedChimp Optimization Algorithm(OCOA).This algorithm is utilized in the selection of optimal parameters for the proposed ***,the proposed technique is used in the prediction of COVID-19 and classify the results as either COVID-19 or *** projected method was implemented in MATLAB and the performances were evaluated through statistical *** proposed method was contrasted with conventional techniques such as Convolutional Neural Network-Firefly Algorithm(CNN-FA),Emperor Penguin Optimization(CNN-EPO)*** results established the supremacy of the proposed model.

关键词： Deep learning deep dense convolutional neural network covid-19 CT images chimp optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Geometric Spanning Trees Minimizing the Wiener Index 1

引用

18th International Symposium on Algorithms and Data Structures, WADS 2023

作者： Abu-Affash, A. Karim Carmi, Paz Luwisch, Ori Mitchell, Joseph S. B. Software Engineering Department Shamoon College of Engineering Beer-Sheva84100 Israel Department of Computer Science Ben-Gurion University Beer-Sheva84105 Israel Department of Applied Mathematics and Statistics Stony Brook University Stony BrookNY United States

ISBN: (数字)9783031389061

ISBN: (纸本)9783031389054

The Wiener index of a network, introduced by the chemist Harry Wiener [30], is the sum of distances between all pairs of nodes in the network. This index, originally used in chemical graph representations of the non-hydrogen atoms of a molecule, is considered to be a fundamental and useful network descriptor. We study the problem of constructing geometric networks on point sets in Euclidean space that minimize the Wiener index: given a set P of n points in Rd, the goal is to construct a network, spanning P and satisfying certain constraints, that minimizes the Wiener index among the allowable class of spanning networks. In this work, we focus mainly on spanning networks that are trees and we focus on problems in the plane (d= 2 ). We show that any spanning tree that minimizes the Wiener index has non-crossing edges in the plane. Then, we use this fact to devise an O(n4) -time algorithm that constructs a spanning tree of minimum Wiener index for points in convex position. We also prove that the problem of computing a spanning tree on P whose Wiener index is at most W, while having total (Euclidean) weight at most B, is NP-hard. Computing a tree that minimizes the Wiener index has been studied in the area of communication networks, where it is known as the optimum communication spanning tree problem. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Atoms

来源：评论

学校读者我要写书评

暂无评论

Agent-based modeling (ABM) for urban neighborhood energy systems: literature review and proposal for an all integrative ABM approach

引用

Energy Informatics 2022年第Suppl 4期5卷 55页

作者： Vuthi, Petrit Peters, Irene Sudeikat, Jan Competence Center for Renewable Energy and Energy Efficiency Hamburg University of Applied Sciences Hamburg20099 Germany HafenCity University of Hamburg Technical Urban Infrastructure Systems Hamburg20457 Germany Department of Computer Science of the Faculty of Engineering and Computer Science Hamburg University of Applied Sciences Hamburg20099 Germany

Advancing the energy transition in real-world urban settings is attracting interest within interdisciplinary research communities. New challenges for local energy balancing arise particularly in urban neighborhoods where densely populated buildings are facing the needs of the heat transition, an increasing use of battery-electric vehicles and an expansion of renewable energies. Agent-based modeling (ABM) is a suitable approach for addressing various interlinked aspects like market mechanisms and processes, technology adoption, different stakeholder roles and the formulation of policy measures. In this work, we analyze peer-reviewed, open-access literature on ABM for energy neighborhoods and discuss key modeling aspects like model purpose and outcome, the logic of agents and decision-making, the treatment of space and time, and empirical grounding. These ABM allow the study of local market mechanisms, local renewable energy generation, microgrids, the unfolding of heat transition, neighborhood mobility and the evaluation of policies like regulation and financial incentives. We find a lack of integrated neighborhood energy assessments that simultaneously look at the different energy forms and applications: heating, electricity, and mobility. We present a consolidated ABM concept that integrates these sectors. Thus, our work contributes to the advancement of ABM and to the understanding of how to promote the transition to a decarbonized society in urban settings. © 2022, The Author(s).

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

High-throughput study of the anomalous Hall effect

引用

npj Computational Materials 2023年第1期9卷 767-774页

作者： JakubŽelezný Yuta Yahagi Carles Gomez-Olivella Yang Zhang Yan Sun Institute of Physics Czech Academy of SciencesCukrovarnická1016200 Praha 6Czech Republic Department of Applied Physics Tohoku UniversitySendaiMiyagiJapan Department of Physics and Astronomy University of Tennessee KnoxvilleKnoxvilleTN 37996USA Min H.Kao Department of Electrical Engineering and Computer Science University of TennesseeKnoxvilleTN 37996USA Shenyang National Laboratory for Materials Science Institute of Metal ResearchChinese Academy of SciencesShenyang 110016China

Despite its long history,the anomalous Hall continues to attract attention due to its complex origins,its connection to topology,and its use as a probe of magnetic *** this work we investigate the anomalous Hall effect in 2871 ferromagnetic materials using an automatic high-throughput calculation *** analyze general properties of the effect,such as its reliance on spin-orbit coupling strength and *** materials with the largest anomalous Hall effect,we find that symmetry-protected band degeneracies in the non-relativistic electronic structure,such as mirror symmetry-protected nodal lines,are typically responsible for the large ***,we examine the dependence of the anomalous Hall effect on magnetization direction and demonstrate deviations from the commonly assumed expression j^(AHE)~M×E.

关键词： effect symmetry protected

来源：评论

学校读者我要写书评

暂无评论

DeepSight: Enhancing Deepfake Image Detection and Classification through Ensemble and Deep Learning Techniques 5

DeepSight: Enhancing Deepfake Image Detection and Classifica...

引用

5th International Conference on Image Processing and Capsule Networks, ICIPCN 2024

作者： Manju, T. Kalarani, S. St. Joseph's Institute of Technology Information Technology Tamil Nadu Chennai India PSG Institute of Technology and Applied Research Department of Computer Science and Engineering Tamil Nadu Coimbatore India

ISBN: (纸本)9798350367171

in today's digital age, deepfake images poses a significant threat to multimedia content authenticity and integrity. Detecting and classifying deepfake images with high accuracy is crucial to addressing this growing challenge. Deepfake images, generated using advanced machine learning techniques, have become a significant concern due to their potential to deceive individuals and manipulate information. This paper presents DeepSight, an innovative approach that combines ensemble learning techniques with deep learning models to enhance deepfake image detection and classification. DeepSight leverages the diversity of multiple classifiers trained on distinct feature representations extracted from the input image data. The framework begins with an initial assessment to determine whether the image has been manipulated. Subsequently, the image goes through deep feature extraction using Convolutional Neural Networks (CNNs). The resulting feature vectors are then classified using Random Forest, KNearest Neighbors, and XGBoost, with hyper-parameter optimization. Experimental evaluations on benchmark datasets demonstrate DeepSight's superior performance compared to state-of-the-art methods, achieving higher accuracy and robustness across various deepfake generation techniques and quality levels. Notably, DeepSight achieves the highest accuracy of 97.5% when utilizing DenseNet and XGBoost. Overall, DeepSight represents a significant advancement in deepfake image detection and classification. It provides a reliable solution to address deceptive visual content in digital environments. © 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：