检索结果-内蒙古大学图书馆

2nd International Conference on computing and Data Analytics, ICCDA 2024

作者： Jagadeesan, S. Ramalingam, Venkadeshan Abinash, P. Ilayaraja, V. Masood, Jafar Ali Ibrahim Syed Tamil Priya, D. School of Computer Science Engineering and Information Systems Vellore Institute of Technology Vellore India UTAS-Shinas branch Department of Computing and Information Sciences Oman School of Computer Science and Engineering Vellore Institute of Technology Vellore India

ISBN: (纸本)9798331542573

Stroke and related neurological disorders are difficult to classify accurately, hence new computational approaches are needed to enhance diagnosis. In order to transform the categorization of brain strokes, this study presents Neuro-Xception, a novel framework that combines the Xception architecture with Extreme Learning Machines (ELM). The rapid learning speed and enhanced generalisation capability of ELMs are combined with the feature extraction expertise of Xception to create Neuro-Xception. Through training on large neuroimaging datasets, Neuro-Xception learns complex patterns that are essential for differentiating between different types and intensities of stroke. By means of extensive testing on various datasets, Neuro-Xception exhibits notable gains in performance compared to traditional techniques, indicating its potential to revolutionise stroke detection in medical environments. Furthermore, Neuro-Xception's scalability and flexibility are enhanced by the combination of Xception and ELMs, which makes it a viable tool for real-time clinical decision support systems and personalised medicine. This study highlights how merging Xception and ELMs can revolutionise neurological healthcare and this development could lead to more accurate and efficient diagnostic techniques for treating stroke patients. Neuro-Xception offers a potential path for increasing diagnosis accuracy and expediting timely medical intervention. It is a major step forward in the use of artificial intelligence to enhance patient outcomes and advance the profession of stroke care. © 2024 IEEE.

关键词： Personalized medicine

来源：评论

学校读者我要写书评

暂无评论

The integrated lot-sizing problem of production, remanufacturing and transportation, considering recovery targets

引用

Journal of Remanufacturing 2025年第1期15卷 127-149页

作者： Vidal, Luciana Piñeyro, Pedro Viera, Omar Department of Operations Research Institute of Computer Science (InCo) Faculty of Engineering Universidad de la República Montevideo Uruguay

This paper considers a hybrid production-remanufacturing system of a single product, composed of an original equipment manufacturer (OEM) and a set of customers/retailers, operating under collection and remanufacturing targets. For this kind of production system, we address the problem of simultaneously determining the sizes of the lots of production, remanufacturing and transportation to and from customers, in order to meet their demand on time and collect used products to be remanufactured. Set-up and unit costs are incurred for the three activities, and unit costs for holding inventory for both used and serviceable items in the OEM but also in the customers. Recovery targets are stated as lower bounds on the number of used products that must be collected and remanufactured by the OEM. We provide a mixed integer-linear programming formulation for the problem and suggest a solution procedure based on the metaheuristic of Tabu Search. We propose and evaluate several variants of the heuristic procedure by extending a well-known set of instances from the literature. The suggested procedures are compared against a state-of-the-art optimization solver, under different parameter settings of interest such as set-up costs, inventory holding costs and recovery targets. The results obtained from the numerical experimentation allow us to conclude that at least one of the variants of the proposed heuristic is effective both in cost and running time, even outperforming the optimization solver for some of the large instances. © The Author(s), under exclusive licence to Springer Nature B.V. 2025.

关键词： Closed-loop supply chain Integrated production and transportation Lot-sizing Metaheuristics Recovery targets Remanufacturing

来源：评论

学校读者我要写书评

暂无评论

COVID-19 Classification of CT Lung Images Using Intelligent Wolf Optimization Based Deep Convolutional Neural Network 1st

COVID-19 Classification of CT Lung Images Using Intelligent ...

引用

1st International Conference on Machine Intelligence for research and Innovations, MAiTRI 2023

作者： Varma, Om Ramakisan Kalra, Mala Computer Science and Engineering Department National Institute of Technical Teachers Training and Research Chandigarh India

ISBN: (纸本)9789819981281

Chest computed tomography (CT) imaging is highly reliable and practical in diagnosing and analyzing COVID-19, mainly in the infectious region rather than reverse-transcription polymerase chain reaction (RT-PCR). The intelligent wolf optimization-deep convolutional neural network (deep CNN) classifier is proposed to classify COVID from the CT images in this research. The texture features are acquired from three different regions of the CT chest images, namely the lung region, area, and contour using the texture descriptors, viz "local binary pattern (LBP), local optimal oriented pattern (LOOP)", and ResNet-101-based features. The texture features form the input to the proposed intelligent wolf-based deep CNN classifier, which performs the COVID-19 classification. The proposed classifier achieves accuracy, sensitivity, and specificity of 85.32%, 85.74%, and 87.57%, respectively for the training–testing ratio of 80–20. The accuracy, sensitivity, and specificity of the intelligent wolf optimization-deep CNN classifier are 88.37%, 89.47%, and 91.29% respectively for the K-fold value of 10. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Stochastic Unit Commitment with High-Penetration Offshore Wind Power Generation in Typhoon Scenarios

引用

Journal of Modern Power Systems and Clean Energy 2024年第2期12卷 535-546页

作者： Yanqi Liu Dundun Liu Hongcai Zhang State Key Laboratory of Internet of Things for Smart City and Department of Electrical and Computer Engineering University of MacaoMacao 999078China University of Macao Zhuhai UM Science and Technology Research Institute ZhuhaiChina

To tackle the energy crisis and climate change,wind farms are being heavily invested in across the *** China's coastal areas,there are abundant wind resources and numerous offshore wind farms are being *** secure operation of these wind farms may suffer from typhoons,and researchers have studied power system operation and resilience enhancement in typhoon ***,the intricate movement of a typhoon makes it challenging to evaluate its spatial-temporal *** published papers only consider predefined typhoon trajectories neglecting *** address this challenge,this study proposes a stochastic unit commitment model that incorporates high-penetration offshore wind power generation in typhoon *** adopts a data-driven method to describe the uncertainties of typhoon trajectories and considers the realistic anti-typhoon mode in offshore wind farms.A two-stage stochastic unit commitment model is designed to enhance power system resilience in typhoon *** formulate the model into a mixed-integer linear programming problem and then solve it based on the computationally-efficient progressive hedging algorithm(PHA).Finally,numerical experiments validate the effectiveness of the proposed method.

关键词： Unit commitment two-stage stochastic programming offshore wind farm typhoon

来源：评论

学校读者我要写书评

暂无评论

A QOE-AWARE STRATEGY FOR ENERGY SAVING IN A FOG-BASED ENVIRONMENTAL MONITORING SYSTEM

引用

International Journal of Electrical engineering 2023年第2期30卷 43-52页

作者： Haung, Yieh-Ran Yin, Chia-Ling Liu, Jenchi Department of Computer Science and Engineering Yuan Ze University Taiwan Electronic and Optoelectronic System Research Laboratories Industrial Technology Research Institute Taiwan

In the Fog-based Environmental Monitoring System (FEMS), the frequency at which Internet of Thing (IoT) devices upload monitoring data and the frequency at which users obtain monitoring data can highly affect energy consumption, data timeliness, and user quality of experience (QoE). How to reduce energy consumption while achieving high data timeliness and user QoE is not only important but also challenging. We propose a QoE-aware strategy to schedule the frequency at which users obtain monitoring data and the frequency at which IoT devices upload monitoring data. The QoE-aware strategy sets the changing tolerance (CT) of monitoring data according to the requirements of different applications in different environments. CT indicates the sensitivity of the application to the change of the environmental data. Only when the changing rate of monitoring data exceeds the CT value set, the IoT device uploads monitoring data to the fog server. Besides, to meet the requirements of reducing data traffic and achieving high data timeliness, users can set different values of QoE Index (QI), i.e., the achievement rate for timely access, according to different environmental requirements. With the QI value, the fog server can calculate the optimal time interval (i.e., access period, AP) for users to access monitoring data. Consequently, by setting the values of CT, QI, and AP according to the requirements of different applications in different environments, the QoE-aware strategy is able to achieve the lowest energy consumption and the highest data timeliness. © 2023, Chinese institute of Electrical engineering. All rights reserved.

关键词： Fog

来源：评论

学校读者我要写书评

暂无评论

PythonSaga: Redefining the Benchmark to Evaluate Code Generating LLMs

PythonSaga: Redefining the Benchmark to Evaluate Code Genera...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Yadav, Ankit Beniwal, Himanshu Singh, Mayank Department of Computer Science and Engineering Lingo Research Group Indian Institute of Technology Gandhinagar India

ISBN: (纸本)9798891761681

Driven by the surge in code generation using large language models (LLMs), numerous benchmarks have emerged to evaluate these LLMs capabilities. We conducted a large-scale human evaluation of HumanEval and MBPP, two popular benchmarks for Python code generation, analyzing their diversity and difficulty. Our findings unveil a critical bias towards a limited set of programming concepts, neglecting most of the other concepts entirely. Furthermore, we uncover a worrying prevalence of easy tasks that can inflate model performance estimations. To address these limitations, we propose a novel benchmark, PythonSaga, featuring 185 hand-crafted prompts in a balanced representation of 38 programming concepts across diverse difficulty levels. The robustness of our benchmark is demonstrated by the poor performance of existing Code-LLMs. The code and data set are openly available to the NLP community at https://***/PythonSaga/PythonSaga. © 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

Does the Order Matter? Curriculum Learning over Languages 30

Does the Order Matter? Curriculum Learning over Languages

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Ranaldi, Leonardo Pucci, Giulia Freitas, Andrè Idiap Research Institute Martigny Switzerland Department of Computer Science University of Manchester United Kingdom Department of Computing Science University of Aberdeen United Kingdom

ISBN: (纸本)9782493814104

Curriculum Learning (CL) has been emerged as an effective technique for improving the performances and reducing the cost of pre-training Large Language Models (LLMs). The efficacy of CL demonstrated in different scenarios is in the training LLMs by organizing examples from the simplest to the most complex. Although improvements have been shown extensively, this approach was used for pre-training, leaving novel fine-tuning approaches such as instruction-tuning unexplored. In this paper, we propose a novel complexity measure to empower the instruction-tuning method using the CL paradigm. To complement previous works, we propose cognitively motivated measures to determine the complexity of training demonstrations used in the instruction-tuning paradigm. Hence, we experiment with the proposed heuristics first in English and then in other languages. The downstream results show that delivering training examples by complexity ranking is also effective for instruction tuning, as it improves downstream performance while reducing costs. Furthermore, the technique can be easily transferred to languages other than English, e.g., Italian and French, without any adaptation, maintaining functionality and effectiveness. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of LSTM Models on Sentiment Analysis 6

A Comparative Study of LSTM Models on Sentiment Analysis

引用

6th International Conference on Computational Intelligence and Networks, CINE 2024

作者： Choudhury, Ritabrata Roy Dey, Soumik Paul, Prithwineel Kalinga Institute of Industrial Technology School of Computer Engineering Odisha Bhubaneswar India Institute of Engineering & Management University of Engineering & Management Centre of Excellence for Quantum Computing Department of Computer Science and Engineering West Bengal Kolkata India

ISBN: (纸本)9798331516796

In this paper, we conduct a comparative analysis of LSTM (Long Short-Term Memory) architectures, including GPU LSTM and Convolutional LSTM, for sentiment analysis tasks on an e-commerce dataset. The evaluation is based on precision, recall, and F1-score metrics for classifying positive and negative sentiments in product reviews. Both GPU LSTM and Convolutional LSTM models demonstrate strong performance in classifying positive sentiments. Moreover, these models achieve high precision, recall, and F1-score. However, they struggle with negative sentiment classification, exhibiting zero precision, recall, and F1-score for this class. Overall, both models achieve an accuracy of 0.97, indicating their effectiveness in sentiment analysis tasks. Furthermore, our study underscores the importance of further research to enhance the ability of the LSTM model to classify negative sentiments in e-commerce datasets accurately. © 2024 IEEE.

关键词： Convolutional LSTM E-commerce F1-score GPU LSTM LSTM Precision Recall Sentiment Analysis

来源：评论

学校读者我要写书评

暂无评论

Incorporating Artificial Intelligence Powered Immersive Realities to Improve Learning using Virtual Reality (VR) and Augmented Reality (AR) Technology 3

Incorporating Artificial Intelligence Powered Immersive Real...

引用

3rd International Conference on applied Artificial Intelligence and computing, ICAAIC 2024

作者： Balushi, Jasim Sharki Ghulam Al Jabri, Malak Ibrahim Ahmed Al Palarimath, Suresh Maran, Pyingkodi Thenmozhi, K. Balakumar, C. Univesity of Technology and Applied Sciences College of Computing and Information Sciences Information Technology Department Salalah Oman Kongu Engineering College Department of Computer Applications Erode India Department of Computer Science Bengaluru India Karpagam Academy of Higher Education Department of Computer Science Coimbatore India

ISBN: (纸本)9798350375190

This study analyzes the transformative potential of combining artificial intelligence (AI) with immersive technologies, specifically virtual reality (VR) and augmented reality (AR), to elevate educational outcomes significantly. The synergy of AI and immersive technologies presents a unique opportunity to enhance students' motivation, memory retention, and comprehension of complex subjects, creating a distinct and impactful learning experience. The research comprehensively explores the current understanding of the effectiveness of VR and AR in educational settings, placing special emphasis on their applications in diverse fields such as science, Technology, engineering, And Mathematics (STEM), medicine, language acquisition, and the development of interpersonal skills. Beyond highlighting the immense potential, the study acknowledges and addresses the obstacles that include the costs associated with equipment, training, and content creation. It underscores the importance of collaborative efforts among technology suppliers, educators, and content producers to overcome these challenges effectively. By recognizing and navigating these hurdles, the study aims to provide practical insights for educational institutions and policymakers, advocating for the integration of AI-powered immersive technology to enhance the overall learning experience for students. The findings underscore the transformative impact of such technologies, emphasizing their role in shaping the future of education and preparing students for the dynamic challenges of the modern world. © 2024 IEEE.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Investigation of Decentralized Autonomous Blockchain Enabled Platform for Crowd Funding

Investigation of Decentralized Autonomous Blockchain Enabled...

引用

2024 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication, IConSCEPT 2024

作者： Rajmohan, R. Kumar, T. Ananth Vijai, M. SRM Institute of Science and Technology Department of Computing Technologies Tamil Nadu Kattankulathur India IFET College of Engineering Department of Computer Science and Engineering Tamil Nadu India

ISBN: (纸本)9798331540685

This research presents a way to crowdfunding that improves security, trust, and transparency in the process by utilizing smart contracts and blockchain technology. The method gives contributors a significant say in project choices by utilizing tokenization and decentralized autonomous organizations (DAOs). The report places special emphasis on how important fraud prevention, transparency, and identity verification are in the crowdfunding environment. A thorough case study demonstrates the advantages of decentralization, transparency, and security in the context of a decentralized equity crowdfunding process. It highlights how blockchain-based crowdfunding might change the crowdfunding industry and emphasizes its disruptive potential. There is potential for both project creators and backers in this paradigm change towards decentralization and transparency, which also has wider ramifications for the digital age finance ecosystem. The proposed system is implemented as a web application and integrated with the Ethereum and meta mask platforms for simulation. © 2024 IEEE.

关键词： Decentralized finance

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：