检索结果-内蒙古大学图书馆

5th International Conference on Smart systems and Inventive Technology, ICSSIT 2023

作者： Balakrishna, S. Arulkumar, V. Srihari, M. Rohith, Cmr Sri Krishna College of Engineering and Technology Computer Science and Business Systems Tamilnadu Coimbatore India Sgi Vellore Institute of Technology School of Computer Science and Engineering Vellore India

ISBN: (纸本)9781665474672

In the banking sector, increased digitization of the economy has forced the businesses to re-evaluate their conventional business models, which is an indication that there is a need for quick and effective change in the banking industry to meet the demands of their clients while offering safe, simple, and connected services to the generation z customers. Industrial revolution 4.0 has affected and changed the banking industry more than 1.0 and 2.0 combined. This paper discusses how the industrial revolution 4.0 has affected and changed the financial and banking sector and primarily revolves around commercial and investment banks rather than reserve banks. It provides a vivid view starting from the digital economy to digitization of banks to the latest trends in the technology incorporated by the banks, to how it has changed the financial markets, to security advancements and finally to how it has changed the banking industry and how it has affected lives. © 2023 IEEE.

关键词： Industry 4.0

来源：评论

学校读者我要写书评

暂无评论

An Efficient Technique to Prevent Data Misuse with Matrix Cipher Encryption Algorithms

引用

computers, Materials & Continua 2023年第2期74卷 4059-4079页

作者： Muhammad Nadeem Ali Arshad Saman Riaz Syeda Wajiha Zahra Ashit Kumar Dutta Moteeb Al Moteri Sultan Almotairi Department of Computing Abasyn UniversityIslamabadPakistan Department of Computer Science National University of TechnologyIslamabadPakistan Department of Computer Science and Information Systems College of Applied SciencesAlMaarefa UniversityRiyadh13713Kingdom of Saudi Arabia Department of Management Information Systems Business Administration CollegeKing Saud UniversityRiyadh11451Saudi Arabia Department of Natural and Applied Sciences Faculty of Community CollegeMajmaah UniversityMajmaah11952Saudi Arabia

Many symmetric and asymmetric encryption algorithms have been developed in cloud computing to transmit data in a secure *** cryptography is a data encryption mechanism that consists of different steps and prevents the attacker from misusing the *** paper has developed an efficient algorithm to protect the data from invaders and secure the data from *** this algorithm is applied to the cloud network,the attacker will not be able to access the *** encrypt the data,the values of the bytes have been obtained by converting the plain text to ASCII.A key has been generated using the Non-Deterministic Bit Generator(NRBG)mechanism,and the key is XNORed with plain text bits,and then Bit toggling has been *** that,an efficient matrix cipher encryption algorithm has been developed,and this algorithm has been applied to this *** capability of this algorithm is that with its help,a key has been obtained from the plain text,and only by using this key can the data be decrypted in the first steps.A plain text key will never be used for another plain *** data has been secured by implementing different mechanisms in both stages,and after that,a ciphertext has been *** the end of the article,the latest technique will be compared with different *** will be a discussion on how the present technique is better than all the other techniques;then,the conclusion will be drawn based on comparative analysis.

关键词： Symmetric cryptography ciphertext encryption decryption cloud security matrix cipher

来源：评论

学校读者我要写书评

暂无评论

Addressing the Libyan Arabic Dialect Identification: A Comparative Study of Ensemble Classification Methods 4

Addressing the Libyan Arabic Dialect Identification: A Compa...

引用

4th IEEE International Maghreb Meeting of the Conference on sciences and Techniques of Automatic Control and computer Engineering, MI-STA 2024

作者： Ghumeid, Najah A. Essgaer, Mansour Sebha University Faculty of Sciences Computer Science Department Sebha Libya Sebha University Faculty of Information Technology Information Systems Department Sebha Libya

ISBN: (纸本)9798350372632

Dialect identification presents a challenging task within the realm of Natural Language Processing. The growing utilization of Arabic dialects in written form, particularly on social media platforms, has created new demands for accurate identification of these dialects. In multilingual datasets, distinguishing the Libyan Arabic dialect from neighboring Arabic dialects has emerged as a crucial goal. To address this, we conducted experiments using different lengths of word n-gram features to determine the most suitable combination of word n-grams and term frequency-inverse document frequency. Our aim was to capture contextual information effectively while mitigating linguistic similarities between Arabic dialects of neighboring countries. The QCRI Arabic Dialects Identification dataset was employed, and we evaluated the performance of three ensemble tree-based classification methods: Random Forest, Gradient Boost Machine, and eXtreme Gradient Boosting. The evaluation, based on the f-measure metric, yielded respective scores of 68%, 37%, and 52% for Random Forest, Gradient Boost Machine, and eXtreme Gradient Boosting. These results underscore the effectiveness of our approach in identifying the Libyan Arabic dialect and highlight the potential of ensemble tree-based methods in Arabic dialect identification tasks. © 2024 IEEE.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Photonics Applications and Web Engineering – WILGA 2024

Photonics Applications and Web Engineering – WILGA 2024

引用

Photonics Applications in Astronomy, Communications, Industry, and High Energy Physics Experiments 2024

作者： Romaniuk, Ryszard S. Smolarz, Andrzej Wójcik, Waldemar Warsaw University of Technology Institute of Electronic Systems Poland Lublin University of Technology Faculty of Electrical Engineering and Computer Science Poland

ISBN: (数字)9781510685796

ISBN: (纸本)9781510685789

Wilga 2024 Summer Symposium on Photonics Applications and Web Engineering was the 52th edition of the research and technical meetings series. Traditionally, the annual series of technical conferences and topical sessions lasted the whole week. They usually were split to one winter meeting in January and one or two summer events in May/June, and in September. The Covid epidemic and the war in Ukraine has changed a lot. The hybrid meetings were held in Wilga resort near Warsaw, owned by the Warsaw University of Technology. Now the meetings since 2022 were shifted to Lublin. Nearly 100 participants took part in all of the Wilga 2022 events, most of them being young researchers active in all aspects of photonics, electronics and ICT science and technology. Over 60 participants took part in Wilga 2024 meetings. Wilga Symposium embraces hardware and software technologies associated with photonics like optics, optical engineering, optoelectronics, electronics and electrical engineering, mechatronics, chemical and material engineering, applied physics, industrial solutions and applications. Around 50 papers were presented during Wilga 2024, oral and poster. Out of this number, some papers chosen by authors are published in this volume of Proc. SPIE mostly related to photonics. The major change was that during Wilga 2020, 2021, 2022 and 2024 Symposia, during summer editions, no traditional large young researcher sessions at large were possible to be organized. We hope that this will change and Wilga 2025 will return to a good tradition to organize concurrent social research sessions full of young researchers like was during Wilga 2019 and earlier. © 2024 SPIE.

关键词： Photonic devices

来源：评论

学校读者我要写书评

暂无评论

Improving AutoML for LLMs via Knowledge-Based Meta-Learning 7

Improving AutoML for LLMs via Knowledge-Based Meta-Learning

引用

7th Doctoral Symposium on Natural Language Processing, NLP-DS 2024

作者： Estevanell-Valladares, Ernesto Luis Faculty of Mathematics and Computer Science University of Havana Cuba Natural Language Processing and Information Systems Group University of Alicante Spain

Recent advancements in Large Language Models (LLMs) such as BERT, GPT-4, and T5 have revolutionized the field of Natural Language Processing (NLP), unlocking numerous applications. However, finetuning these models for specific tasks remains a complex and resource-intensive process, often relying heavily on expert knowledge. This research proposes integrating meta-learning into Automatic Machine Learning (AutoML) systems to optimize LLM fine-tuning and pipeline construction. We hypothesize that knowledge-based meta-learning can overcome the inefficiencies of current AutoML approaches by embedding expert-derived heuristics into the optimization process. Our methodology involves compiling extensive LLM usage data, training meta-learning estimators, and integrating these into the AutoGOAL AutoML framework. By doing so, we aim to reduce computational costs and enhance the efficiency of LLM-based NLP applications. The proposed system will be evaluated against traditional AutoML methods and human experts on various text classification tasks to validate its effectiveness. This research can further democratize NLP by making advanced LLM capabilities more accessible and efficient. © 2024 Copyright for this paper by its authors.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

WanderGenie: A Smart Guide for Immersive Tourism through Generative AI 2

WanderGenie: A Smart Guide for Immersive Tourism through Gen...

引用

2nd International Conference on Computational Intelligence and Network systems, CINS 2024

作者： Barvin, D.S. Rajan, Anitha Amaithi Rajan, Arun Amaithi Department of Computer Science Business Systems Francis Xavier Engineering College Tamil Nadu Tirunelveli627011 India Department of Computer Science and Engineering College of Engineering Guindy Anna University Tamil Nadu Chennai600025 India

ISBN: (纸本)9798331504106

Tourism encourages cultural interaction, economic growth, and global connectivity, improving both travelers and host communities. Due to the shortage of accessible and competent guides, travelers often miss out on the rich history and cultural value of the areas they visit, leading to a shallow understanding of these sites. To bridge this knowledge gap, this article proposes WanderGenie: A Smart Guide for Immersive Tourism through Generative AI to enhance the visitor experience at popular places where traditional guides are unavailable. The system leverages image processing and RFID technology to recognize landmarks and provide travelers with real-time as well as detailed information about the spots they visit. The system ensures accurate landmark identification by strategically inserting RFID tags at precise spots. Upon detecting a landmark, the system shows relevant content through visual displays and audio outputs, creating an immersive and participatory experience. Acting as a kind virtual assistant, WanderGenie answers tourist’s queries, improving their understanding and appreciation of the attractions they experience by utilizing Generative AI technology. This concept solves the shortage of guides while raising the quality of the tourist experience by making historical, cultural, and architectural knowledge more accessible. The proposed system has been designed, implemented, and validated successfully. ©2024 IEEE.

关键词： Tourism

来源：评论

学校读者我要写书评

暂无评论

Smart Contract Evaluation By Multi-Criteria Analysis: Selection Challenges And Open Issues, a Review 3

Smart Contract Evaluation By Multi-Criteria Analysis: Select...

引用

3rd International Conference on Emerging Smart Technologies and Applications, eSmarTA 2023

作者： Alshahrani, Norah M. Kiah, M.L. Mat Zaidan, B.B. University of Malaya Faculty of Computer Science & It Department of Computer Systems & Technology Kuala Lumpur Malaysia King Khalid University Department of Computer Science Abha Saudi Arabia University of Malaya Faculty of Computer Science & It Department of Computer System & Technology Kuala Lumpur Malaysia Future Technology Research Center National Yunlin University of Science and Technology Douliou Yunlin Taiwan

ISBN: (纸本)9798350305333

Smart contracts have received increasing attention in recent years for their potential to enable decentralized and automated transactions in various fields, including finance, supply chain management, and real estate. However, selecting and evaluating the appropriate smart contract for a specific application remains challenging due to the large number of available options and various criteria that need to be considered. This paper discusses the challenges and open issues in selecting and evaluating appropriate smart contracts for various applications. It proposes multi-criteria analysis (MCA) to evaluate and compare different options based on multiple criteria. The study aims to provide a comprehensive review of the current state-of-the-art in the field by considering various criteria used in the selection process, such as security, scalability, and performance. The review covers the challenges associated with critical criteria for smart contract selection, including security, privacy, efficiency, scalability, and regulatory concerns. Additionally, the paper presents various criteria used in different domains/groups to carry out various blockchain- related tasks, such as operational function, asset management, mitigation, analysis, communications, planning, and others. The criteria vary from one person to another and from application to application, and the importance level of the criteria is subjective. The paper highlights the need for more research on smart contract platforms' long-term performance and scalability and more comprehensive and objective evaluation methods for MCA of smart contract selection. © 2023 IEEE.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

MFOOD-70: Moroccan Food Dataset for Food Image Recognition Towards Glycemic Index Estimation 8th

MFOOD-70: Moroccan Food Dataset for Food Image Recognition ...

引用

8th International Conference on Smart City Applications, SCA 2023

作者： Mansouri, Merieme Benabdellah Chaouni, Samia Jai Andaloussi, Said Ouchetto, Ouail Computer Science and Systems Laboratory Faculty of Sciences Ain Chock Km 8 Route El Jadida Casablanca20000 Morocco

ISBN: (纸本)9783031538230

Food image recognition and nutritional analysis, in particular glycemic index (GI), play a crucial role in understanding the impact of diet on human health and the management of chronic diseases such as diabetes. Deep learning, a subset of machine learning, has proven to be a powerful tool in this field. It enables precise recognition of foods from images and provides valuable information on their nutritional content. A food dataset is key to achieving accurate food recognition using deep learning. To the best of this paper’s knowledge, no Moroccan food dataset has been created to handle food image recognition and glycemic index estimation of Moroccan foods. This paper presents a new Moroccan food dataset and a method for food image recognition and nutritional analysis, particularly food glycemic index estimation. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

Roll Call Tracking System for Education Sectors Using Face Recognition System 3

Roll Call Tracking System for Education Sectors Using Face R...

引用

3rd International Conference on Power, Energy, Control and Transmission systems, ICPECTS 2022

作者： Prabhu, D. Dhivyadharshini, K. Lokeswari, S. Pavithra Devi, T. Chennai Department of Computer Science and Business Systems Chennai India

ISBN: (纸本)9781665462754

A motion-based attendance system that assists in the recording and management of attendance without physical contact can be used in schools, institutions and colleges. Modern classrooms are equipped with various smart devices that have supporting software to improve the classrooms. However, it is often seen that precious time in the classroom is wasted on taking attendance, or the class may face various interruptions due to late entries of students, and this attendance procedure is done repeatedly. Conventional methods for attendance taking are by calling students' names by sensor-based card (RFID sensor) or biometric fingerprint-based attendance system, but all of these methods are inefficient as they can't tell whether the student has attended the full class or not. Thus, there is a need for an attendance management system which is totally motion based will assist the faculties and institute in marking the presence of the student attendance. © 2022 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

DistriBlock: Identifying adversarial audio samples by leveraging characteristics of the output distribution 40

DistriBlock: Identifying adversarial audio samples by levera...

引用

40th Conference on Uncertainty in Artificial Intelligence, UAI 2024

作者： Pizarro, Matías B.P. Kolossa, Dorothea Fischer, Asja Faculty of Computer Science Ruhr University Bochum Germany Electronic Systems of Medical Engineering Technische Universität Berlin Germany

Adversarial attacks can mislead automatic speech recognition (ASR) systems into predicting an arbitrary target text, thus posing a clear security threat. To prevent such attacks, we propose DistriBlock, an efficient detection strategy applicable to any ASR system that predicts a probability distribution over output tokens in each time step. We measure a set of characteristics of this distribution: the median, maximum, and minimum over the output probabilities, the entropy of the distribution, as well as the Kullback-Leibler and the Jensen-Shannon divergence with respect to the distributions of the subsequent time step. Then, by leveraging the characteristics observed for both benign and adversarial data, we apply binary classifiers, including simple threshold-based classification, ensembles of such classifiers, and neural networks. Through extensive analysis across different state-of-the-art ASR systems and language data sets, we demonstrate the supreme performance of this approach, with a mean area under the receiver operating characteristic curve for distinguishing target adversarial examples against clean and noisy data of 99% and 97%, respectively. To assess the robustness of our method, we show that adaptive adversarial examples that can circumvent DistriBlock are much noisier, which makes them easier to detect through filtering and creates another avenue for preserving the system’s robustness. © 2024 Proceedings of Machine Learning Research. All rights reserved.

关键词： Adversarial machine learning

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：