检索结果-内蒙古大学图书馆

Congress on Evolutionary Computation

作者： Enrique Bermejo Oscar Cordón Javier Irurita Inmaculada Alemán Ángel Rubio Salvador Dept. of Computer Science and Artificial Intelligence University of Granada Granada Spain Andalusian Research Institute in Data Science and Computational Intelligence (DASCI) University of Granada Granada Spain Dept. of Legal Medicine Toxicology and Physical Anthropology University of Granada Granada Spain Catalan Institute of Human Paleoecology and Social Evolution (IPHES-CERCA) Tarragona Spain Dept. of History and History of Art Rovira i Virgili University Tarragona Spain

ISBN: (数字)9798350308365

ISBN: (纸本)9798350308372

The present study addresses the problem of semiautomatic age-at-death estimation from pubic symphysis, a crucial yet complex task in forensic anthropology. Its accuracy directly depends on the quality of the pubic bone trait labeling developed by the forensic practitioners, affected by an inherent uncertainty in their definition. As interpretability is a mandatory requirement, we propose an approach where the model design is based on evolutionary learning, considering genetic programming to frame the problem as a symbolic regression task. Additionally, ensemble learning is considered to address the challenges posed by noise, uncertainty, and conflicting annotations inherent in data collected from multiple subjects. Ensemble learning provides an effective approach to navigate these challenges by facilitating consensus-building through decision making and information fusion. Hence, observer committees are formed, comprising multiple forensic specialists with different skills and expertise which provide alternative annotations. Several ensemble configurations combining different weak learners and aggregation operators are tested to assess their effectiveness in improving accuracy and reliability in age-at-death predictions. Their performance is compared against models trained on single annotations, revealing an improvement in predictive accuracy. The obtained results also highlight the benefits of incorporating diverse perspectives to address the complexities associated with human variability and anatomical assessments.

关键词： Uncertainty Accuracy Annotations Forensics Decision making Predictive models Mathematical models

来源：评论

学校读者我要写书评

暂无评论

RSZero-CSAT: Zero-Shot Scene Classification in Remote Sensing Imagery using a Cross Semantic Attribute-guided Transformer

RSZero-CSAT: Zero-Shot Scene Classification in Remote Sensin...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Damalla Rambabu Swetha G Rajeshreddy Datla Vishnu Chalavadi C Krishna Mohan Department of Computer Science and Engineering Indian Institute of Technology Hyderabad Dept. of Space Advanced Data Processing Research Institute (ADRIN) Secunderabad India Indian Institute of Technology Tirupati India

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Zero-shot learning (ZSL) based scene classification aims to recognize unseen classes by transferring semantic information from seen classes. The applicability of ZSL for scene classification in remote sensing images becomes challenging due to the complexity of scenes. Earlier attention-based methods are ineffective for extracting discriminative region-based features within a single image. This limitation hinders their ability to achieve transferability and accurately localize object attributes, which is essential for extracting discriminative region-based features. Hence, we propose a method for zero-shot scene classification in remote sensing images using a cross-semantic attribute-guided Transformer named RSZero-CSAT. Firstly, the semantic information is acquired using shared remote sensing semantic attributes to localize object attributes that characterize discriminative region features. Then, a Transformer in RSZero-CSAT is employed to localize object attributes within visual features accurately, enhancing the effectiveness of semantic information transfer in ZSL. Specifically, the RSZero-CSAT employs a semantic attribute → visual Transformer (SAVT) and a visual → semantic attribute Transformer (VSAT) components to extract visual features guided by semantic attributes and semantic attribute features guided by visual features, respectively. Further, SAVT and VSAT mutually learn and collaborate to obtain semantically enriched visual representations, leveraging prediction-level and feature-level semantic collaborative losses for capturing crucial semantic information. Finally, the semantically enriched visual representations obtained from SAVT and VSAT are combined to facilitate visual-semantic interactions in collaboration with class semantic vectors to classify ZSL. Our experimental results demonstrate the impact of RSZero-CSAT in improving the performance of unseen classes on four scene classification benchmark datasets in remote sensing images. The code is avai

关键词： Visualization Scene classification Zero-shot learning Semantics Collaboration Benchmark testing Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Z-Number-Valued Rule-Based Classification System

SSRN

引用

SSRN 2022年

作者： Li, Yangxue Herrera-Viedma, Enrique Pérez, Ignacio Javier Barragán-Guzmán, Mónica Morente-Molinera, Juan Antonio Andalusian Research Institute in Data Science and Computational Intelligence Dept. of Computer Science and AI University of Granada Granada18071 Spain Department of Electrical and Computer Engineering Faculty of Engineering King Abdulaziz University Jeddah21589 Saudi Arabia

The fuzzy rule-based classification system (FRBCS) is a popular tool in classification problems due to its interpretability and comprehensibility. As an extension of fuzzy numbers, the concept of Z-number is a more appropriate formal structure to describe uncertain and partially reliable information. A Z-number is an ordered pair of fuzzy numbers, where the second fuzzy number describes the reliability of the first one. As a result of its representation capability, it can receive better classification results. However, there is still a gap in the application of Z-numbers to classification problems due to its high computation complexity. To take advantage of the Z-number, we design a simple way to make Z-numbers apply to classification problems. Using the second fuzzy number to adjust the first fuzzy number to fit the unevenly distributed data. Then we create a Z-number-valued if-then rule by extending the fuzzy if-then rule. In addition, a Z-number-valued rule-based classification system (ZRBCS) is developed, including two main processes: rules generation and new pattern classification. Compared to the classic fuzzy rule-based system, the proposed system can cover more information that can improve classification results. We evaluated the proposed method on 20 datasets to compare its learning and predictive abilities against the classic fuzzy rule-based system. The results demonstrate the Z-number-valued rule-based classification system is superior to the fuzzy rule-based classification system. © 2022, The Authors. All rights reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

2D LiDAR-Based Eucalyptus Tree Measurement and Monitoring System using Mobile Application

2D LiDAR-Based Eucalyptus Tree Measurement and Monitoring Sy...

引用

13th International Electrical engineering Congress, iEECON 2025

作者： Vanna-Iampikul, Pruek Boonnateephisit, Visutr Limsoontharakul, Somphop Moonrinta, Jednipat Dailey, Matthew Ekpanyapong, Mongkol Burapha University Department of Electrical Engineering Chonburi Thailand School of Engineering and Technology Asian Institute of Technology Pathumthani Thailand Prince of Songkla University Dept. Computational Science Songkhla Thailand Computer Science Field of Study School of Engineering and Technology Asian Institute of Technology Pathumthani Thailand Information & Communication Tech. School of Engineering and Technology Asian Institute of Technology Pathumthani Thailand School of Engineering and Technology Asian Institute of Technology Dept. of Industrial Systems Engineering Pathumthani Thailand

ISBN: (纸本)9798331543952

LiDAR technology has rapidly advanced, offering highly accurate solutions for tree geometry estimation, which is particularly valuable in agriculture and forestry. Its ability to capture precise 2D and 3D data has revolutionized tree detection and measurement. In Eucalyptus plantations, continuous monitoring is critical to maximizing growth, enhancing paper production, and mitigating environmental damage. However, existing solutions face challenges in real-time monitoring due to factors such as parasitic interference, low-light conditions, and uneven terrain. In this work, we present a novel, end-to-end framework that enhances Eucalyptus tree measurement and monitoring. Our framework significantly improves data collection efficiency by allowing measurements at walking speed, reducing measurement distance by 50% compared to traditional manual approaches. This system integrates 2D-LiDAR with additional environmental sensors to extract key tree parameters, including circumference, position, and tree count. The collected data is stored in real-time and uploaded to a centralized server for further analysis. Experimental evaluations across 160 trees, under five distinct farm conditions, demonstrate that our system achieves 89% accuracy in tree diameter estimation and 98.5% accuracy in tree counting, significantly outperforming traditional methods. These results establish our framework as a highly effective solution for improving the accuracy and efficiency of tree monitoring in challenging environments. © 2025 IEEE.

关键词： Deforestation

来源：评论

学校读者我要写书评

暂无评论

2D LiDAR-Based Eucalyptus Tree Measurement and Monitoring System using Mobile Application

2D LiDAR-Based Eucalyptus Tree Measurement and Monitoring Sy...

引用

International Electrical engineering Congress (iEECON)

作者： Pruek Vanna-Iampikul Visutr Boonnateephisit Somphop Limsoontharakul Jednipat Moonrinta Matthew Dailey Mongkol Ekpanyapong Department of Electrical Engineering Burapha University Chonburi Thailand School of Engineering and Technology Asian Institute of Technology Pathumthani Thailand Dept. Computational Science Prince of Songkla University Songkhla Thailand Computer Science Field of Study School of Engineering and Technology Asian Institute of Technology Pathumthani Thailand Information & Communication Tech. School of Engineering and Technology Asian Institute of Technology Pathumthani Thailand Dept. of Industrial Systems Engineering School of Engineering and Technology Asian Institute of Technology Pathumthani Thailand

ISBN: (数字)9798331543952

ISBN: (纸本)9798331543969

关键词： Geometry Accuracy Laser radar Plantations Estimation Vegetation Production Real-time systems Time measurement Monitoring

来源：评论

学校读者我要写书评

暂无评论

An improved machine learning model for data analysis in Big-data environment 15

An improved machine learning model for data analysis in Big-...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Temara, Sheetal Samanthapudi, Sagar Varma Rohella, Piyush Gupta, Ketan Kiruthiga, T. University of the Cumberlands Dept of Computer & Information Sciences WilliamsburgKY United States The Polis Center Indiana University Purdue University Indianapolis Applied Data Science IndianapolisIN United States Payments &commerce GoDaddy EdmondsWA United States University of The Cumberlands Dept. of Information Technology WilliamsburgKY United States Vetri Vinayaha College of Engineering and Technology Department of Ece Tamil Nadu Trichy India

ISBN: (纸本)9798350370249

This technical abstract offers an outline of the ability of artificial Intelligence (AI) and device studying (ML) answers for managing leverage threats in banking. Leverage is a key element in banking danger management, as it could expose the organization to disproportionate liabilities if left unchecked. AI and ML may be used to automate the tracking system of leverage hazards, allowing extra correct and welltimed identification and management of exposures. The abstract examines how AI/ML-driven solutions can leverage to be had facts to detect subtle modifications in leverage through the years, combining techniques from supervised and unsupervised ML to generate actionable insights. It then opinions viable implementation fashions and capacity challenges and gives first-rate practices for a hit implementation. The summary concludes that AI/ML-driven hazard management structures offer a promising new approach to leverage threat management inside the banking sector. In addition, research is warranted on this location. © 2024 IEEE.

关键词： Actionable Automate Disproportionate Management Technical

来源：评论

学校读者我要写书评

暂无评论

Conformal Uncertainty Quantification of Electricity Price Predictions for Risk-Averse Storage Arbitrage

arXiv

引用

arXiv 2024年

作者： Alghumayjan, Saud Xu, Bolun Yi, Ming Dept. of Earth and Environmental Engineering Columbia University New YorkNY10027 United States Data Science Institute Columbia University New YorkNY10027 United States

This paper proposes a risk-averse approach to energy storage price arbitrage, leveraging conformal uncertainty quantification for electricity price predictions. The method addresses the significant challenges posed by the inherent volatility and uncertainty of real-time electricity prices, which create substantial risks of financial losses for energy storage participants relying on future price forecasts to plan their operations. The framework comprises a two-layer prediction model to quantify real-time price uncertainty confidence intervals with high coverage. The framework is distribution-free and can work with any underlying point prediction model. We evaluate the quantification effectiveness through storage price arbitrage application by managing the risk of participating in the real-time market. We design a risk-averse policy for profit-maximization of energy storage arbitrage to find the safest storage schedule with very minimal losses. Using historical data from New York State and synthetic price predictions, our evaluations demonstrate that this framework can achieve good profit margins with less than 35% purchases. © 2024, CC BY-NC-ND.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Uncovering the Benefits of Machine Learning for Automating Financial Regulatory Tasks

Uncovering the Benefits of Machine Learning for Automating F...

引用

2024 International Conference on E-Mobility, Power Control and Smart Systems, ICEMPS 2024

作者： Samanthapudi, Sagar Varma Rohella, Piyush Temara, Sheetal Gupta, Ketan Dhanasekaran, S. The Polis Center Indiana University Purdue University Indianapolis Applied Data Science IndianapolisIN United States Payments & Commerce GoDaddy EdmondsWA United States University of The Cumberlands Dept of Computer & Information Sciences WilliamsburgKY United States University of The Cumberlands Dept. of Information Technology WilliamsburgKY United States Sri Eshwar College of Engineering Department of Ece Tamil Nadu Coimbatore India

ISBN: (纸本)9798350394399

Machine Learning (ML) gives the ability to automate economic regulatory responsibilities in terms of price savings and more green process control. Current advances in ML have enabled the improvement of models that may interpret complicated sets of facts and automate the technique of extracting the preferred facts from these records. The development of such models gives a price-effective and efficient opportunity to greater luxurious and time-consuming guide labor. Moreover, these fashions are capable of perceiving and correctly categorizing data to ensure information accuracy and compliance with regulatory policies. It allows the company to adhere to policies without human oversight, lowering each value and time constraints. It will be further prolonged to other factors of the enterprise by making use of unsupervised fashions and fashions advanced on switch learning, together with deep learning. Those models allow the automation of responsibilities inclusive of assessing the threat associated with investments or transactions, facilitating the development of quicker and more knowledgeable techniques. Ordinary, the usage of ML fashions for financial law automatization processes is precious for decreasing price and time constraints and making sure of compliance. Through leveraging the ability of ML, financial institutions can take advantage of extra internal manner efficiency and statistics accuracy with fewer risks. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Investigating the Role of AI in Personalized Consumer Banking Experiences

Investigating the Role of AI in Personalized Consumer Bankin...

引用

2024 International Conference on E-Mobility, Power Control and Smart Systems, ICEMPS 2024

作者： Rohella, Piyush Temara, Sheetal Samanthapudi, Sagar Varma Gupta, Ketan Suganyadevi, K. Payments & Commerce GoDaddy EdmondsWA United States University of The Cumberlands Dept of Computer & Information Sciences WilliamsburgKY United States The Polis Center Indiana University Purdue University Indianapolis Applied Data Science IndianapolisIN United States University of The Cumberlands Dept. of Information Technology WilliamsburgKY United States Sri Eshwar College of Engineering Department of Ece Tamil Nadu Coimbatore India

ISBN: (纸本)9798350394399

This research examines the function of synthetic Intelligence in developing customized purchaser banking reviews. Artificial Intelligent -based total gear is increasingly being followed to offer consumers customized banking reports. Studies into the use of AI in this context will tell the layout of future banking products and services. The primary intention of this research is to understand the modern technological and personal adoption developments related to Artificial Intelligent and customized banking reviews. Particularly, this study will identify the modern use cases of Artificial Intelligent in personalized banking, look into clients' attitudes and motivations towards Artificial Intelligent -enabled banking experiences, and discover the ability possibilities and challenges related to utilizing Artificial Intelligent in growing individualized banking studies for purchasers. Additionally, the role of ethical issues in implementing and the use of Artificial Intelligent in personalized consumer banking experiences may be evaluated. This study is crucial for presenting a better understanding of the function of Artificial Intelligent in developing personalized and moral consumer banking experiences. © 2024 IEEE.

关键词： Motivation

来源：评论

学校读者我要写书评

暂无评论

Training Physics- Informed Neural Networks via Multi-Task Optimization for Traffic Density Prediction

Training Physics- Informed Neural Networks via Multi-Task Op...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Bo Wang A. K. Qin Sajjad Shafiei Hussein Dia Adriana-Simona Mihaita Hanna Grzybowska Dept. of Computing Technologies Swinburne University of Technology Melbourne Australia Dept. of Civil and Construction Engineering Swinburne University of Technology Melbourne Australia Data Science Institute University of Technology Sydney Sydney Australia Simulation Group Data 61|CSIRO Sydney Australia

Physics-informed neural networks (PINN s) are a newly emerging research frontier in machine learning, which incorporate certain physical laws that govern a given data set, e.g., those described by partial differential equations (PDEs), into the training of the neural network (NN) based on such a data set. In PINN s, the NN acts as the solution approximator for the PDE while the PDE acts as the prior knowledge to guide the NN training, leading to the desired generalization performance of the NN when facing the limited availability of training data. However, training PINNs is a non-trivial task largely due to the complexity of the loss composed of both NN and physical law parts. In this work, we propose a new PINN training framework based on the multi-task optimization (MTO) paradigm. Under this framework, multiple auxiliary tasks are created and solved together with the given (main) task, where the useful knowledge from solving one task is transferred in an adaptive mode to assist in solving some other tasks, aiming to uplift the performance of solving the main task. We implement the proposed framework and apply it to train the PINN for addressing the traffic density prediction problem. Experimental results demonstrate that our proposed training framework leads to significant performance improvement in comparison to the traditional way of training the PINN.

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：