检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Cascioli, Lorenzo Devos, Laurens Kuzelka, Ondrej Davis, Jesse Department of Computer Science KU Leuven Leuven Belgium Faculty of Electrical Engineering Czech Technical University in Prague Prague Czech Republic

Tree ensembles are one of the most widely used model classes. However, these models are susceptible to adversarial examples, i.e., slightly perturbed examples that elicit a misprediction. There has been significant research on designing approaches to construct such examples for tree ensembles. But this is a computationally challenging problem that often must be solved a large number of times (e.g., for all examples in a training set). This is compounded by the fact that current approaches attempt to find such examples from scratch. In contrast, we exploit the fact that multiple similar problems are being solved. Specifically, our approach exploits the insight that adversarial examples for tree ensembles tend to perturb a consistent but relatively small set of features. We show that we can quickly identify this set of features and use this knowledge to speedup constructing adversarial examples. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Joint Channel and Multi-User Detection Empowered with Machine Learning

引用

computers, Materials & Continua 2022年第1期70卷 109-121页

作者： Mohammad Sh.Daoud Areej Fatima Waseem Ahmad Khan Muhammad Adnan Khan Sagheer Abbas Baha Ihnaini Munir Ahmad Muhammad Sheraz Javeid Shabib Aftab College of Engineering Al Ain UniversityAbu Dhabi112612UAE Department of Computer Science Lahore Garrison UniversityLahore54792Pakistan School of Computer Science National College of Business Administration and EconomicsLahore54000Pakistan Riphah School of Computing and Innovation Faculty of ComputingRiphah International UniversityLahore54000Pakistan Pattern Recognition and Machine Learning Lab Department of Software EngineeringGachon UniversitySeongnam13557South Korea Department of Computer Science College of Science and TechnologyWenzhou Kean University325060USA Department of Computer Science Hameeda Rasheed Institute of Science and TechnologyMultan66000Pakistan

The numbers of multimedia applications and their users increase with each passing *** multi-carrier systems have been developed along with varying techniques of space-time coding to address the demand of the future generation of network *** this article,a fuzzy logic empowered adaptive backpropagation neural network(FLeABPNN)algorithm is proposed for joint channel and multi-user detection(CMD).FLeABPNN has two *** first stage estimates the channel parameters,and the second performsmulti-user *** proposed approach capitalizes on a neuro-fuzzy hybrid systemthat combines the competencies of both fuzzy logic and neural *** study analyzes the results of using FLeABPNN based on a multiple-input andmultiple-output(MIMO)receiver with conventional partial oppositemutant particle swarmoptimization(POMPSO),total-OMPSO(TOMPSO),fuzzy logic empowered POMPSO(FL-POMPSO),and FL-TOMPSO-based MIMO *** FLeABPNN-based receiver renders better results than other techniques in terms of minimum mean square error,minimum mean channel error,and bit error rate.

关键词： Channel and multi-user detection minimum mean square error multiple-input and multiple-output minimum mean channel error bit error rate

来源：评论

学校读者我要写书评

暂无评论

Privacy-Aware Artificial Intelligence with Homomorphic Encryption using Machine Learning

Privacy-Aware Artificial Intelligence with Homomorphic Encry...

引用

2023 International Conference on Sustainable Computing and Smart Systems, ICSCSS 2023

作者： Srinivasa Rao, B. Chattopadhyay, Saumitra Singh, Prashant Hazela, Bramah Sabarinathan, G. Yamini, Kalva Department of Computer Science and Engineering Bachupally Telangana Hyderabad India Graphic Era Hill University Department of Computer Science and Engineering Dehradun India Amity University Amity School of Engineering and Technology Lucknow Department of Computer Science and Engineering Uttar Pradesh India Psna College of Engineering and Technology Department of Mathematics Tamilnadu Dindigul India Sri Ramachandra Institute of Higher Education and Research Cyber Security in Computer Science and Engineering Tamilnadu Chennai India

ISBN: (纸本)9798350333602

Along with the expansion of machine learning (ML) applications, the amount of data required to create predictions increases. Big-data ML has always been limited by off-chip memory capacity and computational speed. Considerably, privacy is one of the limitations of big data, which can be solved by homomorphic encryption (HE). Due to the combination of HE and ML, the multi-party privacy-protected ML suggested in this research may assist numerous users in doing artificial intelligence (AI) without disclosing private data. The technique may train common models in situations of data abuse, particularly in private data protection. The model trained using the ML technique named Artificial Neural Network (ANN) has a similar impact to the model developed using all data on a single computer, according to experiments using the algorithm. The gradient data is simply transmitted by all parties, and homomorphic procedures in the main computing system combine the gradient data. Besides, the optimal key is selected using the significance of the Lion Algorithm (LA). After homomorphic procedures, the learning model is modified depending on the new gradient data. © 2023 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Assessing the Effects of Blackhole Attacks on MANET Reliability and Security

Assessing the Effects of Blackhole Attacks on MANET Reliabil...

引用

2024 International Conference on Decision Aid sciences and Applications, DASA 2024

作者： Ahmed, Amjed Abbas Fadhil, Saif Aamer Najim, Ali Hamza Ali Alheeti, Khattab M. Mohd Satar, Nurhizam Safie Abdallah Hashim, Aisha Hassan Center for Cyber Security Faculty of Information Science and Technology Universiti Kebangsaan Malaysia Bangi Malaysia Department of Computer Techniques Engineering Baghdad Iraq Department of Computer Technical Engineering Baghdad10011 Iraq College of Computer and Information Technology Computer Networking Systems Department University of Anbar Anbar Iraq Bangi43600 Malaysia International Islamic University Malaysia Faculty of Engineering Department of Electrical and Computer Engineering Selangor Malaysia

ISBN: (纸本)9798350369106

Mobile Ad Hoc Networks (MANETs) are characterized by some important attributes, including infrastructure, mobile, and dynamic nature, which makes them have vast applications in different areas of computer networks. The black hole attack falls among the strongly criticized security threats within the framework of the MANETs. This deceptive behavior captures data packets from a source destined for the malicious node and then declines them when they are received. This paper comprehensively reviews prior studies done to analyze and mitigate black hole attacks in MANETs. Besides this, we will conduct a comparative analysis of the research above projects. The present paper extends prior work by actually performing the black hole assault simulations in a MANETs environment. This is done with the aid of the NS2 simulator and the Ad Hoc On-Demands Distance Vector (AODV) routing protocol. In this study, the black hole attack is analyzed and the consequences of the attack are assessed in terms of the system performance and security. We analyze crucial parameters like end-to-end latency, PDR, packet drop, and throughput to evaluate the consequences of this assault. From our results derived from the analysis of our simulations, we aim to present substantial points to do with the impacts of blackhole attacks on MANETs. In this way, our goal is to participate in the perpetually evolving efforts aimed at enhancing the security and reliability of such dynamic networks. © 2024 IEEE.

关键词： Mobile ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Realizing the Potential of Metaverse to Revolutionize the Future of Healthcare 2

Realizing the Potential of Metaverse to Revolutionize the Fu...

引用

2nd International Conference on Cyber Resilience, ICCR 2024

作者： Ishtaiwi, Abdelraouf Hadi, Wael Al-Qerem, Ahmad University Of Petra Department Of Data Science And Artificial Intelligence Amman Jordan University Of Petra Department Of Information Security Amman Jordan Zarqa University Faculty Of Information Technology Computer Science Department Zarqa Jordan

ISBN: (纸本)9798350394962

The emergence of metaverse technology, underpinned by virtual reality, augmented reality, and artificial intelligence, holds profound implications for transforming healthcare. This paper reviews the current applications of metaverse in medical education and training, mental healthcare, remote patient monitoring, surgical procedures, and biomedical research. It analyzes the challenges around adopting this technology, spanning technical limitations, ethical dilemmas, threats to privacy, and regulatory gaps. Finally, it proposes strategies and future directions to harness the metaverse's potential to increase healthcare access, efficiency, personalization and democratization. This encompasses research on innovative use cases, developing ethical governance frameworks, and policy reforms to incentivize equitable metaverse adoption across the healthcare ecosystem. A nuanced, evidence-based approach can enable the metaverse to usher a new paradigm of patient-centric healthcare delivery. © 2024 IEEE.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Legal Contract Analysis and Risk Assessment Using Pre-Trained Legal-T5 and Law-GPT 3

Legal Contract Analysis and Risk Assessment Using Pre-Traine...

引用

3rd International Conference on Integrated Circuits and Communication Systems, ICICACS 2025

作者： Poornima, A. Nagaraja, K.V. Venugopalan, Manju Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Bengaluru India Amrita School of Engineering Amrita Vishwa Vidyapeetham Department of Mathematics Bengaluru India

ISBN: (纸本)9798331508456

The need for effective solutions in reviewing, risk identification, and compliance management of complex legal contracts has remained a critical challenge. This research explores how modern machine learning models like Legal T5, and Law GPT can automate contract analysis and improve review accuracy. Legal T5 summarizes the complex legal documents while Law GPT captures the critical risks. K-Means clustering was used to improve the contract segmentation by grouping similar clauses for a structured risk assessment. Tested on the CUAD dataset, the system's text summarizing findings showed coherence and a strong semantic similarity of 0.78, ensuring that the final summaries retained significant legal importance. The model achieved an average precision of 0.85, recall of 0.77, and F1-score of 0.80 across various risk categories. The findings prove that Legal T5, along with clustering, improves contract analysis with the ability to provide a context and structure-aware summary with better identification of risks. © 2025 IEEE.

关键词： Risk management

来源：评论

学校读者我要写书评

暂无评论

Understanding Interpersonal Conflict Types and their Impact on Perception Classification 5

Understanding Interpersonal Conflict Types and their Impact ...

引用

5th Workshop on Natural Language Processing and Computational Social science, NLPCSS 2022, Held at the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022

作者： Welch, Charles Plepi, Joan Neuendorf, Béla Flek, Lucie Lab Department of Mathematics and Computer Science University of Marburg Germany Germany

ISBN: (纸本)9781959429203

Studies on interpersonal conflict have a long history and contain many suggestions for conflict typology. We use this as the basis of a novel annotation scheme and release a new dataset of situations and conflict aspect annotations. We then build a classifier to predict whether someone will perceive the actions of one individual as right or wrong in a given situation. Our analyses include conflict aspects, but also generated clusters, which are human validated, and show differences in conflict content based on the relationship of participants to the author. Our findings have important implications for understanding conflict and social norms. © 2022 Association for Computational Linguistics.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Damage Assessment and Recovery in Fog-based Computing Systems

Damage Assessment and Recovery in Fog-based Computing System...

引用

2022 International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies, 3ICT 2022

作者： Thoumi, Sergio Haraty, Ramzi A. Lebanese American University Department of Computer Science and Mathematics Beirut Lebanon

ISBN: (数字)9781665451932

ISBN: (纸本)9781665451932

Technological improvements have been exponential in the last two decades. The advancements in networking, fog computing, and artificial intelligence have allowed us to implement the "Internet of Things"starting from small sensors connected to the Internet to enormous "smart cities". However, what is common in all of these improvements is that without data, and more precisely correct data, they would be useless. For example, machine learning training and results will be useless once a malicious or affected transaction is done because it can spread throughout the entire database. The need for data integrity made scholars research different phases of data security such as detection, prevention, and recovery. In this paper, we present an effective damage assessment and recovery algorithm in fog based systems that shortens crucial downtime caused by the recovery process after an attack. © 2022 IEEE.

关键词： Fog computing

来源：评论

学校读者我要写书评

暂无评论

Development of Additive Manufacturing Design Based on Machine Learning: A Biomedical Engineering Approach 1

Development of Additive Manufacturing Design Based on Machin...

引用

1st International Conference on Advances in computer science, Electrical, Electronics, and Communication Technologies, CE2CT 2025

作者： Khan, Akbar Valivarthi, Dharma Teja Banik, Shampa Kakkad, Ashish Sujatha, B. Acharya, Deepak Nimra College of Engineering and Technology ECE Department Andhra Pradesh Vijayawada India Tek Leaders TX United States Dhaka Bangladesh Marwadi University Faculty of Physiotherapy Rajkot India Department of Computer Science and Engineering Tamilnadu Tiruchengode India The University of Alabama in Huntsville Department of computer science United States

ISBN: (纸本)9798331518578

Additive manufacturing (AM) is a versatile and complex manufacturing technique that is extensively employed in the production of personalized biopolymer-orientated items and sophisticated medical architecture. One of the most developed AM techniques is selective laser melting (SLM), which uses a laser as an energy resource to completely melt successive layers of granular resources. SLM produces titanium-oriented alloys that are highly biocompatible and have exceptionally excellent physical qualities, which have led to their widespread usage in biomedical uses. An artificial neural network-based optimizing approach was established to enhance the standard of Ti-6Al-4V SLM-based parts and assist manufacturing professionals in selecting optimum process settings. The approach relates 4 primary procedure settings to two target characteristics of the part. To improve the system's accuracy throughout neural network training, several techniques were employed to address undesirable issues. The denseness and surface hardness values of the system's R2 of 99 percent demonstrated its effectiveness. After that, a selection system was developed that lets users select the best process variables for manufactured goods whose attributes satisfy particular user requirements. The optimum part quality produced by tests using the ideal process variables suggested by the optimizing approach was almost the same as those specified by the user, with only 0.9 to 4.4 percent of mistakes at the high, significantly confirming the system's dependability. © 2025 IEEE.

关键词： Titanium alloys

来源：评论

学校读者我要写书评

暂无评论

CrisisHateMM: Multimodal Analysis of Directed and Undirected Hate Speech in Text-Embedded Images from Russia-Ukraine Conflict

CrisisHateMM: Multimodal Analysis of Directed and Undirected...

引用

2023 IEEE/CVF Conference on computer Vision and Pattern Recognition Workshops, CVPRW 2023

作者： Bhandari, Aashish Shah, Siddhant B. Thapa, Surendrabikram Naseem, Usman Nasim, Mehwish Delhi Technological University Department of CSE India Virginia Tech Department of Computer Science United States School of Computer Science The University of Sydney Australia School of Physics Mathematics and Computing The University of Western Australia Australia College of Science and Engineering Flinders University Australia

ISBN: (纸本)9798350302493

Text-embedded images are frequently used on social media to convey opinions and emotions, but they can also be a medium for disseminating hate speech, propaganda, and extremist ideologies. During the Russia-Ukraine war, both sides used text-embedded images extensively to spread propaganda and hate speech. To aid in moderating such content, this paper introduces CrisisHateMM, a novel multimodal dataset of over 4,700 text-embedded images from the Russia-Ukraine conflict, annotated for hate and non-hate speech. The hate speech is annotated for directed and undirected hate speech, with directed hate speech further annotated for individual, community, and organizational targets. We benchmark the dataset using unimodal and multimodal algorithms, providing insights into the effectiveness of different approaches for detecting hate speech in text-embedded images. Our results show that multimodal approaches outperform unimodal approaches in detecting hate speech, highlighting the importance of combining visual and textual features. This work provides a valuable resource for researchers and practitioners in automated content moderation and social media analysis. The CrisisHateMM dataset and codes are made publicly available at https://***/aabhandari/CrisisHateMM. © 2023 IEEE.

关键词： Modal analysis

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：