检索结果-内蒙古大学图书馆

Automated Machine Learning for Test Case Prioritization

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Romero, José Raúl Ramírez, Aurora García-Martínez, Carlos Dept. of Computer Science and Numerical Analysis University of Córdoba AN Córdoba14071 Spain Andalusian Research Institute in Data Science and Computational Intelligence University of Córdoba AN Córdoba14071 Spain

Test case prioritization (TCP) involves ordering and selecting the most relevant test cases to verify that the current functionality of a software system remains unaffected by code changes. Recently, TCP has been solved by machine learning (ML), predicting the failure probability of each test case. However, software engineers may struggle to identify and implement the most suitable predictive models for TCP. As new builds adapt the test suite being tested, the model performance may decline as these new builds are incorporated. In this study, we address these challenges by applying automated workflow composition and hyperparameter optimization. Both are considered tasks within automatic machine learning (AutoML). With this aim, our proposal employs grammar-guide genetic programming as the underlying mechanism for implementing the AutoML algorithm. Our experimental results demonstrate that our approach can adapt to the particularities of the system under test, selecting the most appropriate workflow and hyperparameters for each build. More importantly, our approach eliminates the need for testers to possess extensive knowledge of ML, while allowing them to inspect workflows to understand the evolution of the prioritization process. This research showcases the potential of AutoML in software engineering, specifically for the TCP problem. © 2023, The Authors. All rights reserved.

关键词： Genetic programming

Unique MS Lesion Identification from MRI

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Rivas, Carlos A. Zhang, Jinwei Wei, Shuwen Remedios, Samuel W. Carass, Aaron Prince, Jerry L. Image Analysis and Communications Laboratory Dept. of Electrical and Computer Engineering Johns Hopkins University BaltimoreMD21218 United States Dept. of Computer Science Johns Hopkins University BaltimoreMD21218 United States

Unique identification of multiple sclerosis (MS) white matter lesions (WMLs) is important to help characterize MS progression. WMLs are routinely identified from magnetic resonance images (MRIs) but the resultant total lesion load does not correlate well with EDSS∗;whereas mean unique lesion volume has been shown to correlate with EDSS. Our approach builds on prior work by incorporating Hessian matrix computation from lesion probability maps before using the random walker algorithm to estimate the volume of each unique lesion. Synthetic images demonstrate our ability to accurately count the number of lesions present. The takeaways, are: 1) that our method correctly identifies all lesions including many that are missed by previous methods;2) we can better separate confluent lesions;and 3) we can accurately capture the total volume of WMLs in a given probability map. This work will allow new more meaningful statistics to be computed from WMLs in brain MRIs. © 2024, CC BY.

关键词： Magnetic resonance imaging

Broadening Access to Simulations for End-Users via Large Language Models: Challenges and Opportunities 24

学校读者我要写书评

暂无评论

Broadening Access to Simulations for End-Users via Large Lan...

Proceedings of the Winter Simulation Conference

作者： Philippe J. Giabbanelli Jose J. Padilla Ameeta Agrawal Virginia Modeling Analysis and Simulation Center Old Dominion University Norfolk VA USA Dept. of Computer Science Portland State University Portland OR USA

ISBN: (纸本)9798331534202

Large Language Models (LLMs) are becoming ubiquitous to create intelligent virtual assistants that assist users in interacting with a system, as exemplified in marketing. Although LLMs have been discussed in Modeling & Simulation (M&S), the community has focused on generating code or explaining results. We examine the possibility of using LLMs to broaden access to simulations, by enabling non-simulation end-users to ask what-if questions in everyday language. Specifically, we discuss the opportunities and challenges in designing such an end-to-end system, divided into three broad phases. First, assuming the general case in which several simulation models are available, textual queries are mapped to the most relevant model. Second, if a mapping cannot be found, the query can be automatically reformulated and clarifying questions can be generated. Finally, simulation results are produced and contextualized for decision-making. Our vision for such system articulates long-term research opportunities spanning M&S, LLMs, information retrieval, and ethics.

关键词：

Meteorology Predicting Technology Based on Artificial Intelligence Algorithms

学校读者我要写书评

暂无评论

Meteorology Predicting Technology Based on Artificial Intell...

Emerging Technologies for Sustainability and Intelligent Systems (ICETSIS), ASU International Conference in

作者： Gulnara Abitova Daniyar Mukashev Elvira Aitmukhanbetova Mira Rakhimzhanova Gulzhan Uskenbayeva Korlan Kulniyazova Dept electrical engineering and computer science Binghamton University Binghamton USA Dept. of computer engineering Astana IT University Astana Kazakhstan Dept. system analysis and management L.N. Gumilyov Eurasian National University Astana Kazakhstan

The research explores the transformative impact of Artificial Intelligence in meteorology, weather forecasting. The study presented historical prediction methods overview, evolution highlighting from traditional models to advanced AI-driven systems. It delves into the integration of machine and deep learning techniques in data analysis, emphasizing technologies that significantly enhanced the accuracy and efficiency of weather predictions. Key aspects covered include the neural networks application in interpreting complex atmospheric data, the big data role in providing comprehensive training sets for AI models, the predictive analytics utilization for short-term and long-term weather forecasts. The study also examines case-study with AI implemented in weather forecasting, capability demonstrating in handling extreme weather events and climate anomalies. The study addresses the challenges and limitations faced in the meteorology AI integration, such as data quality concerns, computational requirements, and the specialized expertise need. It proposes potential solutions, future directions for research domain, suggesting a multidisciplinary approach involving meteorologists, data scientists, and AI experts. The conclusion underscores the revolutionary impact of AI-technology in meteorology, projecting how continuous advancements in AI-technology could redefine the predicting weather patterns approach. The work highlights the AI current state in weather forecasting but also sets the future innovations stage.

关键词：

Exploring Dependence of Subject-Specific Training Strategies for EEG Based Brain-computer Interfaces

学校读者我要写书评

暂无评论

Exploring Dependence of Subject-Specific Training Strategies...

IEEE Southeastcon

作者： T. Warren de Wit Vineetha Menon Thomas Davis Dept. of Computer Science University of Alabama Huntsville Huntsville USA Human Systems Integration Division DEVCOM Data and Analysis Center Huntsville USA

Design and deployment of brain-computer interface enabled assistive systems poses many practical questions, including the decision of whether to use a pretrained model or to customize a model to each unique end-user. In this work, we apply this question to the application domain of a passive brain- controlled drone for use in disaster relief and hostage rescue situations. A six-class intent (e.g. EEG) recognition experiment is performed with 42 subjects. This pilot study explores and evaluates the effects of subject-specific (“customized”) versus subject- independent (“uncustomized”) modeling approaches. Based on experimental validation, we present our discussions on the observed pros and cons of each training strategy. In this study, it was noted that the uncustomized training approach had the best target detection performance with a reduction in variance. Additionally, its deployment readiness attribute make it a more relevant and feasible option for our intended use case.

关键词：

Broadening Access to Simulations for End-Users via Large Language Models: Challenges and Opportunities

学校读者我要写书评

暂无评论

Broadening Access to Simulations for End-Users via Large Lan...

Simulation Winter Conference

ISBN: (数字)9798331534202

ISBN: (纸本)9798331534219

关键词： Ethics Codes Large language models Virtual assistants Simulation Machine vision Decision making Information retrieval

BROADENING ACCESS TO SIMULATIONS FOR END-USERS VIA LARGE LANGUAGE MODELS: CHALLENGES AND OPPORTUNITIES

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Giabbanelli, Philippe J. Padilla, Jose J. Agrawal, Ameeta Virginia Modeling Analysis and Simulation Center Old Dominion University NorfolkVA United States Dept. of Computer Science Portland State University PortlandOR United States

关键词： Structured Query Language

Regularised Diffusion–Shock Inpainting

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Schaefer, Kristina Weickert, Joachim Mathematical Image Analysis Group Dept. of Mathematics and Computer Science Saarland University E1.7 Saarbrücken66041 Germany

We introduce regularised diffusion–shock (RDS) inpainting as a modification of diffusion–shock inpainting from our SSVM 2023 conference paper. RDS inpainting combines two carefully chosen components: homogeneous diffusion and coherence-enhancing shock filtering. It benefits from the complementary synergy of its building blocks: The shock term propagates edge data with perfect sharpness and directional accuracy over large distances due to its high degree of anisotropy. Homogeneous diffusion fills large areas efficiently. The second order equation underlying RDS inpainting inherits a maximum–minimum principle from its components, which is also fulfilled in the discrete case, in contrast to competing anisotropic methods. The regularisation addresses the largest drawback of the original model: It allows a drastic reduction in model parameters without any loss in quality. Furthermore, we extend RDS inpainting to vector-valued data. Our experiments show a performance that is comparable to or better than many inpainting methods based on partial differential equations and related integrodifferential models, including anisotropic processes of second or fourth order. Copyright © 2023, The Authors. All rights reserved.

关键词： Diffusion

Diffusion–Shock Inpainting

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Schaefer, Kristina Weickert, Joachim Mathematical Image Analysis Group Dept. of Mathematics and Computer Science Saarland University E1.7 Saarbrücken66123 Germany

We propose diffusion–shock (DS) inpainting as a hitherto unexplored integrodifferential equation for filling in missing structures in images. It combines two carefully chosen components that have proven their usefulness in different applications: homogeneous diffusion inpainting and coherence-enhancing shock filtering. DS inpainting enjoys the complementary synergy of its building blocks: It offers a high degree of anisotropy along an eigendirection of the structure tensor. This enables it to connect interrupted structures over large distances. Moreover, it benefits from the sharp edge structure generated by the shock filter, and it exploits the efficient filling-in effect of homogeneous diffusion. The second order equation that underlies DS inpainting inherits a continuous maximum–minimum principle from its constituents. In contrast to other attractive second order inpainting equations such as edge-enhancing anisotropic diffusion, we can guarantee this property also for the proposed discrete algorithm. Our experiments show a performance that is comparable to or better than many linear or nonlinear, isotropic or anisotropic processes of second or fourth order. They include homogeneous diffusion, biharmonic interpolation, TV inpainting, edge-enhancing anisotropic diffusion, the methods of Tschumperlé and of Bornemann and März, Cahn–Hilliard inpainting, and Euler’s elastica. Copyright © 2023, The Authors. All rights reserved.

关键词： Diffusion