检索结果-内蒙古大学图书馆

17th IEEE International Symposium on Embedded Multicore/Many-core Systems-on-Chip, MCSoC 2024

作者： Aoki, Shota Katagiri, Takahiro Ohshima, Satoshi Kawai, Masatoshi Nagai, Toru Hoshino, Tetsuya Nagoya University Graduate School of Informatics Japan Nagoya University Information Technology Center Japan Kyushu University Research Institute for Information Technology Fukuoka Japan

ISBN: (纸本)9798331530471

The unregulated utilization of Artificial Intelligence (AI) outputs, potentially leading to various societal issues, has received considerable attention. While humans routinely validate information, manually inspecting the vast volumes of AI-generated results is impractical. Therefore, automation and visualization are imperative. In this context, Explainable AI (XAI) technology is gaining prominence, aiming to streamline AI model development and alleviate the burden of explaining AI outputs to users. Simultaneously, software Auto-Tuning (AT) technology has emerged for reducing the man-hours required for performance tuning in numerical calculations. AT is a potent tool for cost reduction during parameter optimization and high-performance programming for numerical computing. The synergy between AT mechanisms and AI technology is noteworthy, with AI finding extensive applications in AT. However, applying AI to AT mechanisms introduces challenges in AI model explainability. This study focuses on XAI for AI models when integrated into two different processes for practical numerical computations: performance parameter tuning of accuracy-guaranteed numerical calculations and sparse iterative algorithm. © 2024 IEEE.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

The Digital Twin City in Enhancing Flood Evacuation Systems: Future Opportunities and Challenges

引用

IEEE Access 2025年 13卷 32371-32383页

作者： Setijadi Prihatmanto, Ary Prasetyadi, Abdurrakhman Yoganingrum, Ambar Sutriadi, Ridwan Hadiana, Ana Bandung Institute of Technology School of Electrical and Informatics Engineering Bandung40132 Indonesia National Research and Innovation Agency Research Center for Data and Information Science Bandung40231 Indonesia Bandung Institute of Technology School of Architecture Planning and Policy Development Bandung40132 Indonesia

In recent decades, the increasing frequency and severity of natural disasters have necessitated the development of more effective disaster management systems. This paper explores the potential of digital twin technology to enhance flood evacuation systems. A digital twin-city model can simulate urban environments, predict flood inundation, and identify optimal evacuation routes in real-time. The study conducts a systematic literature review to assess current advancements, evaluating the integration of 3D city models, artificial intelligence, and Internet of things sensors in flood evacuation planning. Results indicate that digital twin technology significantly improves predictive capabilities and evacuation efficiency, although data integration, model accuracy, and computational demands remain. Future research should focus on enhancing data integration, refining simulation models, improving predictive analytics, developing advanced visualization tools, and validating models across diverse environments to ensure reliability and effectiveness. © 2025 The Authors.

关键词： Digital elevation model

来源：评论

学校读者我要写书评

暂无评论

Mathematical Problem Solving in Arabic: Assessing Large Language Models 6

Mathematical Problem Solving in Arabic: Assessing Large Lang...

引用

6th International Conference on AI in Computational Linguistics, ACLing 2024

作者： Mahgoub, Abeer Khoriba, Ghada Elsabry, Elhassan Anas NLP Research Group Center for Informatics Science School of Information Technology and Computer Science Nile University Giza Egypt

This paper comprehensively evaluates the efficacy of different large language models (LLMs) in addressing mathematical challenges expressed in natural languages, mainly focusing on low-resource languages like Arabic. The main challenge of this problem is that despite the considerable size and impressive problem-solving capabilities of these models, they still require enhancements to achieve satisfactory performance for mathematical problem-solving. An LLM must be trained or fine-tuned extensively in understanding and solving mathematical problems articulated in natural language contexts. This is further complicated by the scarcity of high-quality, annotated datasets in low-resource languages. To overcome this problem, we introduce a method for generating synthetic data to address the challenge of data scarcity in Arabic. This approach includes using LLMs to create high-quality, synthetic mathematical problem datasets that can be used to augment the training process. We propose the Synthetic Data Augmentation (SDA) framework, an advanced variant of traditional data augmentation techniques explicitly tailored for mathematical problem-solving in low-resource languages. Experimental studies reveal that using synthetic data significantly improves the performance of LLMs in solving mathematical problems in Arabic. This study contributes to the field of natural language processing and provides insights into the potential of synthetic data generation to enhance LLM performance in low-resource languages. © 2024 Elsevier B.V.. All rights reserved.

关键词： Data assimilation

来源：评论

学校读者我要写书评

暂无评论

A Review of the Role of ChatGPT for Clinical Decision Support Systems 5

A Review of the Role of ChatGPT for Clinical Decision Suppor...

引用

5th International IEEE Novel Intelligent and Leading Emerging Sciences Conference, NILES 2023

作者： Fawzi, Sahar Nile University Medical Informatics Research Group Center for Informatics Science Information Technology and Computer Science School Cairo Egypt

ISBN: (纸本)9798350381030

The development of artificial intelligence (AI) provided powerful assistant tools for humans in various aspects. Healthcare is rapidly evolving, with AI playing a crucial role in improving patient care. The extensive use of AI in Clinical Decision Support Systems (CDSS) enables providing real-time evidence-based recommendations to healthcare professionals at the point of Care. The AI chatbot ChatGPT proved its ability to solve several natural language processing tasks. One notable advancement is the integration of ChatGPT into Clinical Decision Support Systems. ChatGPT, despite not being healthcare-specific, can offer accurate and practical information for medical professionals and patients. It aids in diagnosis and treatment, supports decision-making, and enhances the overall accuracy and efficiency of the healthcare system. In this review, we present a selection of representative examples of ChatGPT applications in CDSS. © 2023 IEEE.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-Aware Semi-Supervised Learning for Enhanced Multi-Organ Segmentation in CT Volumes

Uncertainty-Aware Semi-Supervised Learning for Enhanced Mult...

引用

Medical Imaging 2025: Image Processing

作者： Dong, Guotai Oda, Masahiro Hayashi, Yuichiro Misawa, Kazunari Mori, Kensaku Graduate School of Informatics Nagoya University Nagoya Japan Information Technology Center Nagoya University Nagoya Japan Aichi Cancer Center Nagoya Japan Research Center for Medical Bigdata National Institute of Informatics Tokyo Japan

ISBN: (纸本)9781510685901

We propose an uncertainty-aware semi-supervised learning (SSL) strategy for multi-organ segmentation in CT volumes. CT volume segmentation is crucial for enhancing diagnostic accuracy, facilitating quantitative analysis, and enabling automation and assisted diagnosis. Previous SSL strategies have shown great performance on CT volumes by ensuring consistency between different outputs of the model. However, these methods do not address the noise and uncertainty within individual outputs, which can impact the results. Our method integrates uncertainty estimation into the SSL framework, dynamically generating masks based on the uncertainty of individual predictions. This approach not only maintains consistency between multiple outputs but also mitigates the impact of noise and uncertainty within each prediction. Under the 10% labeled data setting, comparative experiments demonstrated that our method improved segmentation performance across effectively segmented organs. Specifically, compared to the baseline, the Dice scores increased by 2.50% for the vein, 1.99% for the liver, 5.16% for the spleen, and 6.09% for the stomach, indicating the potential benefits of incorporating uncertainty estimation into the SSL framework. © 2025 SPIE.

关键词： Semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Bidirectional teaching between lightweight multi-view networks for intestine segmentation from CT volume

引用

Journal of Medical Imaging 2025年第2期12卷 024003页

作者： An, Qin Oda, Hirohisa Hayashi, Yuichiro Kitasaka, Takayuki Takimoto, Aitaro Hinoki, Akinari Uchida, Hiroo Suzuki, Kojiro Oda, Masahiro Mori, Kensaku Nagoya University Graduate School of Informatics Nagoya Japan University of Shizuoka School of Management and Information Shizuoka Japan Aichi Institute of Technology School of Information Science Toyota Japan Nagoya University Graduate School of Medicine Nagoya Japan Aichi Medical University Department of Radiology Nagakute Japan Nagoya University Information Technology Center Nagoya Japan National Institute of Informatics Research Center for Medical Bigdata Tokyo Japan

Purpose: We present a semi-supervised method for intestine segmentation to assist clinicians in diagnosing intestinal diseases. Accurate segmentation is essential for planning treatments for conditions such as intestinal obstruction. Although fully supervised learning performs well with abundant labeled data, the complexity of the intestine s spatial structure makes labeling time-intensive, resulting in limited labeled data. We propose a 3D segmentation network with a bidirectional teaching strategy to enhance segmentation accuracy using this limited dataset. Method: The proposed semi-supervised method segments the intestine from computed tomography (CT) volumes using bidirectional teaching, where two backbones with different initial weights are trained simultaneously to generate pseudo-labels and employ unlabeled data, mitigating the challenge of limited labeled data. Intestine segmentation is further complicated by complex spatial features. To address this, we propose a lightweight multi-view symmetric network, which uses small-sized convolutional kernels instead of large ones to reduce parameters and capture multi-scale features from diverse perceptual fields, enhancing learning ability. Results: We evaluated the proposed method with 59 CT volumes and repeated all experiments five times. Experimental results showed that the average Dice of the proposed method was 80.45%, the average precision was 84.12%, and the average recall was 78.84%. Conclusions: The proposed method can effectively utilize large-scale unlabeled data with pseudo-labels, which is crucial in reducing the effect of limited labeled data in medical image segmentation. Furthermore, we assign different weights to the pseudo-labels to improve their reliability. From the result, we can see that the method produced competitive performance compared with previous methods. © The Authors.

关键词： Semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Challenges and Opportunities in Deep Learning Driven Fashion Design and Textiles Patterns Development 8th

Challenges and Opportunities in Deep Learning Driven Fashi...

引用

8th International Conference on Modelling and Development of Intelligent Systems, MDIS 2022

作者： Simian, Dana Husac, Felix Faculty of Sciences Research Center in Informatics and Information Technology Lucian Blaga University of Sibiu Sibiu Romania

ISBN: (纸本)9783031270338

Creative industries were thought to be the most difficult avenue for Computer Science to enter and to perform well at. Fashion is an integral part of day to day life, one necessary both for displaying style, feelings and conveying artistic emotions, and for simply serving the purely functional purpose of keeping our bodies warm and protected from external factors. The Covid-19 pandemic has accelerated several trends that had been forming in the clothing and textile industry. With the large-scale adoption of Artificial Intelligence (AI) and Deep Learning technologies, the fashion industry is at a turning point. AI is now in charge of supervising the supply chain, manufacturing, delivery, marketing and targeted advertising for clothes and wearable and could soon replace designers too. Clothing design for purely digital environments such as the Metaverse, different games and other on-line specific activities is a niche with a huge potential for market growth. This article wishes to explain the way in which Big Data and Machine Learning are used to solve important issues in the fashion industry in the post-Covid context and to explore the future of clothing and apparel design via artificial generative design. We aim to explore the new opportunities offered to the development of the fashion industry and textile patterns by using of the generative models. The article focuses especially on Generative Adversarial Networks (GAN) but also briefly analyzes other generative models, their advantages and shortcomings. To this regard, we undertook several experiments that highlighted some disadvantages of GANs. Finally, we suggest future research niches and possible hindrances that an end user might face when trying to generate their own fashion models using generative deep learning technologies. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Textile industry

来源：评论

学校读者我要写书评

暂无评论

Complete Security Analysis on Event-Based Dynamic Protocol for Constrained IoT Device 12

Complete Security Analysis on Event-Based Dynamic Protocol f...

引用

12th International Conference on information and Communication technology, ICoICT 2024

作者： Pahlevi, Rizka Reza Hasegawa, Hirokazu Yamaguchi, Yukiko Shimada, Hajime Graduate School of Informatics Nagoya University Nagoya Japan Center for Strategic Cyber Resilience Research and Development National Institute of Informatics Tokyo Japan Information Technology Center Nagoya University Nagoya Japan

ISBN: (纸本)9798350363432

Authentication protocols have become essential for Internet of Things (IoT) devices. Developing a secure authentication protocol has become more challenging due to the constraints of IoT devices. However, event-based dynamic protocols promise lightweight and secure authentication. Nevertheless, it is necessary to thoroughly evaluate an authentication protocol, considering both protocol validation and physical aspects to closely simulate the real environment of IoT devices. We used the Tamarin Prover to evaluate the protocol validation, specifically executability, session secrecy, authentication secrecy, and historical authentication secrecy. Additionally, we assessed IoT devices implementing the event-based dynamic protocol for side channel attacks, node tempering, and cloning attacks. Our findings indicate that the event-based dynamic protocol is valid in terms of executability, session secrecy, authentication secrecy, and historical secrecy, thus confirming its claim of being secure. However, we discovered vulnerabilities in the authentication properties of the device firmware, making it susceptible to side channel and node tempering attacks. These vulnerabilities stem from the lack of necessary confidential properties. By exploiting these weaknesses, we were able to decrypt messages from the IoT device. Furthermore, we have successfully uploaded the original firmware to unofficial devices, and it runs properly on them. Therefore, while the event-based dynamic protocol itself is secure, it is prone to physical attacks. Moreover, we discuss potential solutions to completely secure the authentication process for the event-based dynamic protocol, addressing the identified vulnerabilities and ensuring robust protection against physical attacks. © 2024 IEEE.

关键词： Authentication Protocol

来源：评论

学校读者我要写书评

暂无评论

Survey and Analysis of NFT and Blockchain Technologies for Developing Agricultural Product Trading Systems 20

Survey and Analysis of NFT and Blockchain Technologies for D...

引用

20th International Joint Conference on Computer Science and Software Engineering, JCSSE 2023

作者： Phunsa, Suwichai Noiumkar, Preecha Chomsiri, Thawatchai Mahasarakham University Digital Contents for Development Research Unit Faculty of Informatics Department of Creative Media Mahasarakham Thailand Mahasarakham University Research Center of Information Technology for the Future Faculty of Informatics Department of Information Technology Mahasarakham Thailand

ISBN: (纸本)9798350300505

In this research, we have surveyed NFT technology and Blockchain technology. We have analyzed both technologies to apply them in the agricultural product trading to benefit farmers the most. We have examined the strengths of NFT and NFT Marketplace to find ways to utilize these strengths in agricultural product trading. Additionally, we have identified various obstacles and suggested solutions. From the research, we have found that agricultural product trading through NFT Marketplace can provide benefits such as transparency, allowing buyers and sellers to verify the relevant transactions, the number of trades, the initial purchase price, and the final selling price. Moreover, the NFT's ownership information cannot be forged as they are on the Blockchain. By integrating the system with the community enterprise, the government's support, and using crypto seed phrases and private keys tied to accounts, farmers can receive KYC (Know Your Customer) and prevent fraud. Furthermore, NFT Marketplace can show sales transactions of each product category, which can help farmers understand market demand and popularity. Additionally, buyers can choose popular and trustworthy sellers (farmers) based on transaction history. © 2023 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Privacy Preserving Framework for Distributed Association Rule Mining in Healthcare Databases

引用

Computers, Materials & Continua 2023年第2期74卷 4119-4133页

作者： Hasanien K.Kuba Mustafa A.Azzawi Saad M.Darwish Oday A.Hassen Ansam A.Abdulhussein University of Information Technology and Communication(UOITC) Baghdad10081Iraq Accenture Ling Karan TRXKuala Lumpur55188Malaysia Department of Information Technology Institute of Graduate Studies and ResearchUniversity of Alexandria21526Egypt Ministry of Education Wasit Education DirectorateKut52001Iraq Information Technology Center Iraqi Commission for Computers and InformaticsBaghdad10081Iraq

It is crucial,while using healthcare data,to assess the advantages of data privacy against the possible *** from several sources must be combined for use in many data mining *** medical practitioner may use the results of association rule mining performed on this aggregated data to better personalize patient care and implement preventive ***,numerous heuristics(e.g.,greedy search)and metaheuristics-based techniques(e.g.,evolutionary algorithm)have been created for the positive association rule in privacy preserving data mining(PPDM).When it comes to connecting seemingly unrelated diseases and drugs,negative association rules may be more informative than their positive *** is well-known that during negative association rules mining,a large number of uninteresting rules are formed,making this a difficult problem to *** this research,we offer an adaptive method for negative association rule mining in vertically partitioned healthcare datasets that respects users’*** applied approach dynamically determines the transactions to be interrupted for information hiding,as opposed to predefining *** study introduces a novel method for addressing the problem of negative association rules in healthcare data mining,one that is based on the Tabu-genetic optimization *** search is advantageous since it removes a huge number of unnecessary rules and item *** using benchmark healthcare datasets prove that the discussed scheme outperforms state-of-the-art solutions in terms of decreasing side effects and data distortions,as measured by the indicator of hiding failure.

关键词： Distributed data mining evolutionary computation sanitization process healthcare informatics

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：