检索结果-内蒙古大学图书馆

作者： Nishiyama, Daiki Fukuchi, Kazuto Akimoto, Youhei Sakuma, Jun Master's Program in Computer Science Degree Programs in Systems and Information Engineering Graduate School of Science and Technology University of Tsukuba Tsukuba-shi305-8577 Japan RIKEN Center for Advanced Intelligence Project Tokyo103-0027 Japan Department of Computer Science Faculty of Engineering Information and Systems University of Tsukuba Tsukuba-shi305-8577 Japan

In real world applications of multiclass classification models, misclassification in an important class (e.g., stop sign) can be significantly more harmful than in other classes (e.g., no parking). Thus, it is crucial to improve the recall of an important class while maintaining overall accuracy. For this problem, we found that improving the separation of important classes relative to other classes in the feature space is effective. Existing methods that give a class-sensitive penalty for cross-entropy loss do not improve the separation. Moreover, the methods designed to improve separations between all classes are unsuitable for our purpose because they do not consider the important classes. To achieve the separation, we propose a loss function that explicitly gives loss for the feature space, called class-sensitive additive angular margin (CAMRI) loss. CAMRI loss is expected to reduce the variance of an important class due to the addition of a penalty to the angle between the important class features and the corresponding weight vectors in the feature space. In addition, concentrating the penalty on only the important class hardly sacrifices separating the other classes. Experiments on CIFAR-10, GTSRB, and AwA2 showed that CAMRI loss could improve the recall of a specific class without sacrificing accuracy. In particular, compared with GTSRB's second-worst class recall when trained with cross-entropy loss, CAMRI loss improved recall by 9%. © 2023 The Institute of Electronics, Information and Communication Engineers.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Interactive Text-to-Image Retrieval with Large Language Models: A Plug-and-Play Approach

arXiv

引用

arXiv 2024年

作者： Lee, Saehyung Yu, Sangwon Park, Junsung Yi, Jihun Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of

In this paper, we primarily address the issue of dialogue-form context query within the interactive text-to-image retrieval task. Our methodology, PlugIR, actively utilizes the general instruction-following capability of LLMs in two ways. First, by reformulating the dialogue-form context, we eliminate the necessity of fine-tuning a retrieval model on existing visual dialogue data, thereby enabling the use of any arbitrary black-box model. Second, we construct the LLM questioner to generate non-redundant questions about the attributes of the target image, based on the information of retrieval candidate images in the current context. This approach mitigates the issues of noisiness and redundancy in the generated questions. Beyond our methodology, we propose a novel evaluation metric, Best log Rank Integral (BRI), for a comprehensive assessment of the interactive retrieval system. PlugIR demonstrates superior performance compared to both zero-shot and fine-tuned baselines in various benchmarks. Additionally, the two methodologies comprising PlugIR can be flexibly applied together or separately in various situations. Our codes are available at https://***/Saehyung-Lee/PlugIR. © 2024, CC BY.

关键词： Content based retrieval

来源：评论

学校读者我要写书评

暂无评论

The Banking Industry is Undergoing a Digital Transformation as Part of Industrial 4.0 10

The Banking Industry is Undergoing a Digital Transformation ...

引用

10th International Conference on Smart Computing and Communication, ICSCC 2024

作者： Sardjono, Wahyu Pranata, Dewi Sagita Ramdhana, Aditya Agung Dwi BINUS Graduate Program - Master of Information Systems Management Bina Nusantara University Information Systems Management Department Jakarta11480 Indonesia Mathematical & Engineering Sciences King's College London Cyber Security Studi Program Faculty of Natural Department of Informatics West Minster Strands WC2R 2LS United Kingdom University of Airlangga Master of Management Faculty of Economics and Business Surabaya60286 Indonesia

ISBN: (纸本)9798350363104

In the current day, digital transformation is imperative;both customer demand and market competitiveness are mostly driving that trend. The fourth industrial revolution has also affected the financial sector. One difficulty that has to be addressed is the desire from customers for quick and useful services. Traditional procedures need to be replaced with digital ones. Furthermore, banking organizations will have a competitive edge in the current market if they are successful in this digital transformation process. Successful transformation, however, does not happen by accident;in fact, the likelihood of completing this change is seen to be very low, necessitating rigorous planning for a company that is ready for the future. There are several components to the preparation in question, both internal and external. In this situation, the company's ability to combine and rearrange its resources quickly is essential for adapting to the ever-changing business environment. © 2024 IEEE.

关键词： Commerce

来源：评论

学校读者我要写书评

暂无评论

Optimal Selection of Hybrid Renewable Energy System Using Multi-Criteria Decision-Making Algorithms

引用

Computers, Materials & Continua 2021年第8期68卷 2001-2027页

作者： Hegazy Rezk Irik Z.Mukhametzyanov Mujahed Al-Dhaifallah Hamdy A.Ziedan College of Engineering at Wadi Addawaser Prince Sattam Bin Abdulaziz UniversityAl-Kharj11911KSA Department of Electrical Engineering Faculty of EngineeringMinia UniversityMinia61517Egypt Center for Strategic and Interdisciplinary Research Ufa Federal Research Centre of the Russian Academy of SciencesUfa450054Republic of BashkortostanRussia Department of Systems Engineering King Fahd University of Petroleum&MineralsDhahran31261KSA Department of Electrical Engineering Faculty of EngineeringAssiut UniversityAssiut71518Egypt

Several models of multi-criteria decision-making(MCDM)have identified the optimal alternative electrical energy sources to supply certain load in an isolated region in Al-Minya City,*** load demand consists of water pumping system with a water desalination *** options containing three different power sources:only DG,PV-B system,and hybrid PV-DG-B,two different sizes of reverse osmosis(RO)units;RO-250 and RO-500,two strategies of energy management;load following(LF)and cycle charging(CC),and two sizes of DG;5 and 10 kW were taken into *** attributes,including operating cost,renewable fraction,initial cost,the cost of energy,excess energy,unmet load,breakeven grid extension distance,and the amount of CO_(2),were used during the evaluation *** estimate these parameters,HOMER®software was employed to perform both the simulation and optimization *** different weight estimation methods were considered;no priority of criteria,based on a pairwise comparisons matrix of the criteria,CRITIC-method,and entropy-based *** main findings(output results)confirmed that the optimal option for the case study was hybrid PV-DG-B with the following specification:5 kW DG,RO-500,and load following control *** this condition,the annual operating cost and initial costs were$5546 and$161022,respectively,whereas the cost of energy was 0.077$/*** excess energy and unmet loads were 40998 and 2371 kWh,*** breakeven grid extension distance and the amount of CO_(2) were 3.31 km and 5171 kg per year,*** with DG only,the amount of CO_(2) has been sharply reduced by 113939 kg per year.

关键词： Al-Minya city(Egypt) energy efficiency multi-criteria decision-making optimization renewable energy reverse osmosis units

来源：评论

学校读者我要写书评

暂无评论

Modular Safety-Critical Control of Legged Robots

arXiv

引用

arXiv 2023年

作者： Tosun, Berk Samur, Evren Graduate Program in Systems and Control Engineering Bogazici University Istanbul Turkey Department of Mechanical Engineering Bogazici University Istanbul Turkey

Safety concerns during the operation of legged robots must be addressed to enable their widespread use. Machine learning-based control methods that use model-based constraints provide promising means to improve robot safety. This study presents a modular safety filter to improve the safety of a legged robot, i.e., reduce the chance of a fall. The prerequisite is the availability of a robot that is capable of locomotion, i.e., a nominal controller exists. During locomotion, terrain properties around the robot are estimated through machine learning which uses a minimal set of proprioceptive signals. A novel deep-learning model utilizing an efficient transformer architecture is used for the terrain estimation. A quadratic program combines the terrain estimations with inverse dynamics and a novel exponential control barrier function constraint to filter and certify nominal control signals. The result is an optimal controller that acts as a filter. The filtered control signal allows safe locomotion of the robot. The resulting approach is generalizable, and could be transferred with low effort to any other legged system. Copyright © 2023, The Authors. All rights reserved.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

Dimensionality and dynamics for next-generation artificial neural networks

Patterns

引用

Patterns 2025年

作者： Wang, Ge Fan, Feng-Lei Department of Biomedical Engineering Department of Electrical Computer and Systems Engineering Department of Computer Science Center for Computational Innovations Biomedical Imaging Center Center for Biotechnology and Interdisciplinary Studies Rensselaer Polytechnic Institute TroyNY United States Department of Data Science City University of Hong Kong Kowloon Hong Kong

The recent awarding of the Nobel Prize in Physics to Geoffrey E. Hinton and John J. Hopfield highlights their profound impact on artificial neural networks. In this perspective, we explore how their foundational insights can drive the advancement of next-generation artificial intelligence (AI) models. We propose expanding beyond conventional architectures by introducing dimensionality through intra-layer links and dynamics via feedback loops. Network height and additional dimensions, alongside traditional width and depth, enhance learning capabilities, while entangled loops across scales induce emergent behaviors akin to phase transitions in physics. We discuss how these principles extend beyond transformers, fostering a new paradigm of intelligence inspired by physics-driven models and biological cognition mechanisms. © 2025 The Author(s)

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

An Examination of the Possible Application of Artificial Intelligence Audit Process in Organizations 6

An Examination of the Possible Application of Artificial Int...

引用

6th International Conference on Cybernetics and Intelligent System, ICORIS 2024

作者： Sardjono, Wahyu Pranata, Dewi Sagita Isamesal, Muhammad Information Systems Management Department BINUS Graduate Program Bina Nusantara University Jakarta11480 Indonesia Cyber Security Studi Program Department of Informatics Faculty of Natural Mathematical & Engineering Sciences King’s College London West Minster WC2R 2LS United Kingdom Management Department Faculty of Economics and Busines Universitas of Airlangga Surabaya10430 Indonesia

ISBN: (纸本)9798331539603

This study investigates how artificial intelligence (AI) can transform audit processes, including how AI can be used in businesses to execute non-technical audit tasks and what effect this will have on those tasks. A qualitative case study methodology is used in the research design to give detailed insights into how AI is being adopted by businesses. This study aims to analyze the aspects that impact AI implementation from the viewpoints of managers, auditors, and other stakeholders. The findings show that artificial intelligence (AI) has a great deal of promise for non-technical audit procedures in businesses. AI can automate tedious jobs, evaluate large data sets to identify hazards and enhance teamwork and communication. These developments may lead to increased productivity, maybe better audit quality, and more effective processes. But there are still difficulties. Data quality is essential to the success of AI integration, and auditors may exhibit bias in favor of human professionals. Careful thought must also be given to ethical issues about transparency and possible job displacement. All things considered, this study adds significant knowledge to both the academic literature and real-world auditing applications. It improves our comprehension of the function of AI in the industry and provides useful information for people involved in information technology development, audit, and legislation. © 2024 IEEE.

关键词： Data quality

来源：评论

学校读者我要写书评

暂无评论

AI-Powered Precision: Revolutionizing Skin Cancer Detection with Advanced Machine Learning 6

AI-Powered Precision: Revolutionizing Skin Cancer Detection ...

引用

6th IEEE Novel Intelligent and Leading Emerging Sciences Conference, NILES 2024

作者： Abd-Elaziz, Mariam M. Elshafie, Basma M. Abdullah, Hagar Gerges, Karen Y. Ghanem, Ingy A. Fouad, Khaled M. El-Ghamry, Amir Moawad, Ibrahim F. El-Metwally, Sara New Mansoura University Faculty of Computer Science and Engineering Dakahlia Egypt Mansoura University New Mansoura University Faculty of Engineering Computer and Communication Program Faculty of Computer Science and Engineering Egypt Benha University Information Systems Faculty of Computers and Artificial Intelligence Egypt Mansoura University New Mansoura University Faculty of Computer and Information Sciences Faculty of Computer Science and Engineering Egypt School of Engineering and Computer Science University of Hertfordshire Gaf Egypt Ain Shams University Faculty of Computer and Information Sciences Cairo Egypt College of Computer Science and Engineering Taibah University Department of Artificial Intelligence Medina42353 Saudi Arabia

ISBN: (纸本)9798350378511

Skin cancer's increasing incidence rates necessitate advanced diagnostic tools. This research uses MobileNet architecture to develop an enhanced system for skin cancer detection. MobileNet's efficient CNN architecture, combined with Keras for model lifecycle management and TensorFlow for real-time inference, forms the foundation of this study. Using 10,015 dermatoscopic pictures from seven different classifications of skin cancer in the HAM10000 dataset, the methodology includes several key stages: image preprocessing to correct illumination and adjust resolution, data augmentation to balance the dataset, and model training using Transfer Learning. The MobileNet model was trained over 50 epochs with a comprehensive architecture incorporating multiple specialized layers. By combining large-scale data analysis and adaptive learning, this methodology demonstrates The revolutionary possibilities of AI and ML in improving skin cancer diagnostics and public health outcomes. Keywords Skin Cancer Detection, Dermatoscopic Images, Machine Learning, Deep Learning © 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

Generator Subadditive Functions for Mixed-Integer programs

arXiv

引用

arXiv 2024年

作者： Olivares, Gustavo Ivan Angulo Kocuk, Burak Ramirez, Diego Moran A. Department of Industrial and Systems Engineering Pontificia Universidad Católica de Chile Santiago7820436 Chile Industrial Engineering Program Sabancı University Istanbul34956 Turkey Industrial and Systems Engineering Department Rensselaer Polytechnic Institute TroyNY12180-3590 United States

For equality-constrained linear mixed-integer programs (MIP) defined by rational data, it is known that the subadditive dual is a strong dual and that there exists an optimal solution of a particular form, termed generator subadditive function. Motivated by these results, we explore the connection between Lagrangian duality, subadditive duality and generator subadditive functions for general equality-constrained MIPs where the vector of variables is constrained to be in a monoid. We show that strong duality holds via generator subadditive functions under certain conditions. For the case when the monoid is defined by the set of all mixed-integer points contained in a convex cone, we show that strong duality holds under milder conditions and over a more restrictive set of dual functions. Finally, we provide some examples of applications of our results. © 2024, CC BY.

关键词： Mixed-integer linear programming

来源：评论

学校读者我要写书评

暂无评论

Assessment of the Statistical Performance of Chemical Transport Model Studies in India

ACS ES&T Air

引用

ACS ES&T Air 2024年第12期1卷 1519-1530页

作者： Rishi Shandilya Pranav Chaudhari Srinidhi Balasubramanian Environmental Science and Engineering Department Indian Institute of Technology Bombay Mumbai India 400 076 Interdisciplinary Program in Climate Studies Indian Institute of Technology Bombay Mumbai India 400 076

India’s public health is seriously endangered by air pollution and linked to ∼0.8–0.98 million and 0.17 million premature deaths annually from chronic exposure to particulate matter (PM2.5) and ozone, respectively. Air quality forecasting tools are needed to assess the spatiotemporal variability of air pollutants and evaluate the impact of potential mitigation measures. Gridded concentrations of PM2.5and ozone are typically derived from first principle models called Chemical Transport Models (CTMs). Widespread application of CTMs, particularly for regulatory purposes, requires an understanding of model performance in comparison with observation data. A landscape approach that systematically reviews CTM model predictions and proposes benchmarks for assessing model performance can offer a way forward to build confidence in CTM-backed forecasting tools. Following similar efforts in the United States and China, we systematically shortlisted and examined model performance outcomes for 46 CTM studies reporting PM2.5and ozone predictions in India between 2008 and 2023. The reported statistical metrics for each pollutant (normalized mean bias (NMB), normalized mean error (NME), coefficient of correlation (r), and index of agreement (IOA) were rank ordered to identify two types of benchmarks: “goals” (highest achievable model accuracy based on top one-third performing studies) and “criteria” (typical model accuracy based on the top two-third performing studies). The identified goal performance for PM2.5was 17% (NMB), 34% (NME), and 0.67 (r), and ozone was 14% (NMB), 43% (NME), and 0.89 (r). These benchmarks are less restrictive than those reported for the United States and China. This highlights the need for the CTM community to coalesce around a common set of practices in evaluating CTMs. Additionally, complementary efforts in developing representative emissions inventories and including air pollution data from the expanding observational networks are required to update suc

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：