检索结果-内蒙古大学图书馆

8th International Conference on information technology, InCIT 2024

作者： Nugroho, Erdhi Widyarto Mustafid Bayuaji, Luhur Diponegoro University Semarang Indonesia International University Faculty of Data Science and Information Technology Inti Nilai Malaysia Universitas Budi Luhur Faculty of Information Technology Jakarta Indonesia

ISBN: (纸本)9798350366303

The method for validating blockchain consensus has progressed from the initial Proof of Work (PoW) system implemented by Bitcoin to the Byzantine Fault Tolerance (BFT) family. At present, the Federated Byzantine Agreement (FBA) is under development due to its superior speed, higher throughput, and greater openness in comparison to PoW and Practical Byzantine Fault Tolerance (PBFT). FBA primarily relies on the Quorum Slice, or a cluster of validator nodes. The trust among the validator nodes forms the basis for this group's formation. A validator node's degree of reputation directly correlates with its level of trust among the public. *** provides an index that serves as a benchmark for evaluating the reputation level. This index is generated by computing the mathematical mean of six factors. One problem with this reputation index is that its findings lack fairness due to the presence of validator nodes that lack a quorum set but still achieve a high index score. Furthermore, the lack of diversity in the index values poses challenges in establishing rankings. The objective of this paper is to create a reputation evaluation model for FBA validator nodes by EigenTrust as a viable option for calculating the reputation index and addressing the index problems at ***. The methodology in this paper entails gathering data from the *** API over a period of three months, mapping the validator nodes according to the quorum set, and executing the EigenTrust procedure. The result is a reputation evaluation model for FBA validator nodes using EigenTrust, which provides a more equitable and straightforward ranking of reputation assessment outcomes compared to the *** index.. © 2024 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Systematic Assessment of Factual Knowledge in Large Language Models

Systematic Assessment of Factual Knowledge in Large Language...

引用

2023 Findings of the Association for Computational Linguistics: EMNLP 2023

作者： Luo, Linhao Vu, Thuy-Trang Phung, Dinh Haffari, Gholamreza Department of Data Science and AI Faculty of Information Technology Monash University Australia

ISBN: (纸本)9798891760615

Previous studies have relied on existing question-answering benchmarks to evaluate the knowledge stored in large language models (LLMs). However, this approach has limitations regarding factual knowledge coverage, as it mostly focuses on generic domains which may overlap with the pretraining data. This paper proposes a framework to systematically assess the factual knowledge of LLMs by leveraging knowledge graphs (KGs). Our framework automatically generates a set of questions and expected answers from the facts stored in a given KG, and then evaluates the accuracy of LLMs in answering these questions. We systematically evaluate the state-of-the-art LLMs with KGs in generic and specific domains. The experiment shows that ChatGPT is consistently the top performer across all domains. We also find that LLMs performance depends on the instruction finetuning, domain and question complexity and is prone to adversarial context. © 2023 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

Surface Defect Detection Algorithm for PCB Based on Improved YOLOv8 8

Surface Defect Detection Algorithm for PCB Based on Improved...

引用

8th International Conference on Electrical, Mechanical and Computer Engineering, ICEMCE 2024

作者： Ai, Yan Ye, TingDong City University of Macau Faculty of Data Science China Guangdong Industry Polytechnic University Faculty of Information Technology GuangZhou China

ISBN: (纸本)9798331506230

With the rapid development of the electronics industry, printed circuit boards (PCBs) play a crucial role in electronic products. However, traditional methods for PCB defect detection suffer from low efficiency and insufficient accuracy. To address this issue, this paper proposes an improved YOLO algorithm for PCB defect detection. In the field of PCB defect detection, due to the dense components and complex wiring on PCBs, traditional detection methods struggle to accurately and quickly identify various types of defects. This study aims to improve upon the traditional YOLO algorithm by introducing a new dual-layer routing attention mechanism and a feature extraction module, which enhances the ability to extract features of PCB defects. Additionally, the algorithm's loss function, Shape-IoU, has been optimized to better accommodate the shape characteristics of PCB defects, thereby improving both detection accuracy and recall rate. Experimental results demonstrate that the improved YOLO algorithm exhibits higher performance in PCB defect detection. Compared to traditional methods, the detection accuracy has increased by 2%, and the detection speed has improved by 3%, providing a more effective technical means for quality control in the PCB production process. © 2024 IEEE.

关键词： Electronics industry

来源：评论

学校读者我要写书评

暂无评论

Uncertainty propagation in the internet of things

引用

Discover Internet of Things 2024年第1期4卷 1-20页

作者： Pal, Shantanu Khalifa, Sara Miller, Dimity Dedeoglu, Volkan Dorri, Ali Ramachandran, Gowri Moghadam, Peyman Kusy, Brano Jurdak, Raja The School of Information Technology Faculty of Science Engineering and Built Environment Deakin University MelbourneVIC 3125 Australia The School of Information Systems Faculty of Science Queensland University of Technology BrisbaneQLD4000 Australia The School of Electrical Engineering and Robotics Faculty of Engineering Queensland University of Technology BrisbaneQLD4000 Australia The Distributed Sensing Systems Group Data61 CSIRO PullenvaleQLD 4069 Australia The School of Computer Science Faculty of Science Queensland University of Technology BrisbaneQLD 4000 Australia The CSIRO Robotics Data61 CSIRO PullenvaleQLD 4069 Australia

The Internet of Things (IoT) detects context through sensors capturing data from dynamic physical environments, in order to inform automation decisions within cyber physical systems (CPS). Diverse types of uncertainty in the IoT pipeline can propagate within and across nodes, involving complex interactions with security, privacy, and trust that remain largely unexplored. This paper conducts an in-depth analysis of the types of uncertainties in IoT and how they propagate within IoT nodes and networks. We consider adversarial uncertainty in the context of distributed IoT networks to capture perturbations due to malicious actors in the network that can influence IoT security, privacy and trust. We examine the propagation of adversarial uncertainty and well-known uncertainty types, namely aleatoric and epistemic uncertainty, within the five distinct stages of sensing, communication, storage, processing and decision-making in an IoT pipeline, across network layer boundaries, and across nodes within an IoT network. Using this mapping, we analyse the interactions between the uncertainty types and their propagation, and security, privacy, and trust in IoT. Based on this analysis, we discuss guidelines and considerations for mitigating uncertainty in IoT through a smart grid use case study. © The Author(s) 2024.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

MEDICINE RECOMMENDER SYSTEM BASED ON SEMANTIC AND MULTI-CRITERIA FILTERING

引用

Interdisciplinary Journal of information, Knowledge, and Management 2023年 18卷 435-457页

作者： Shambour, Qusai Yousef Al-Zyoud, Mahran Abu-Shareha, Ahmad Adel Abualhaj, Mosleh Department of Software Engineering Faculty of Information Technology Al-Ahliyya Amman University Amman Jordan Department of Networks and Cybersecurity Faculty of Information Technology Al-Ahliyya Amman University Amman Jordan Department of Data Science and Artificial Intelligence Faculty of Information Technology Al-Ahliyya Amman University Amman Jordan

Aim/Purpose: This study aims to devise a personalized solution for online healthcare platforms that can alleviate problems arising from information overload and data sparsity by providing personalized healthcare services to patients. The primary focus of this paper is to develop an effective medicine recommendation approach for recommending suitable medications to patients based on their specific medical conditions. Background: With a growing number of people becoming more conscious about their health, there has been a notable increase in the use of online healthcare platforms and e-services as a means of diagnosis. As the internet continues to evolve, these platforms and e-services are expected to play an even more significant role in the future of healthcare. For instance, WebMD and similar platforms offer valuable tools and information to help manage patients' health, such as searching for medicines based on their medical conditions. Nonetheless, patients often find it arduous and time-consuming to sort through all the available medications to find the ones that match their specific medical conditions. To address this problem, personalized recommender systems have emerged as a practical solution for mitigating the burden of information overload and data sparsity-related issues that are frequently encountered on online healthcare platforms. Methodology: The study utilized a dataset of MC ratings obtained from WebMD, a popular healthcare website. Patients on this website can rate medications based on three criteria, including medication effectiveness, ease of use, and satisfaction, using a scale of 1 to 5. The WebMD MC rating dataset used in this study contains a total of 32,054 ratings provided by 2,136 patients for 845 different medicines. The proposed HSMCCF approach consists of two primary modules: a semantic filtering module and a multi-criteria filtering module. The semantic filtering module is designed to address the issues of data sparsity and new item prob

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

The Impact of Generative Artificial Intelligence on Learning: A Case Study at the University of Petra 2

The Impact of Generative Artificial Intelligence on Learning...

引用

2nd International Conference on Cyber Resilience, ICCR 2024

作者： El-Khalili, Nuha Al-Nashashibi, May Al-E'mari, Salam University Of Petra Faculty Of Information Technology Software Engineering Department Amman Jordan University Of Petra Faculty Of Information Technology Data Science & Artificial Intelligence Department Amman Jordan University Of Petra Faculty Of Information Technology Information Security Department Amman Jordan

ISBN: (纸本)9798350394962

Recently, a noticeable trend of using Generative Artificial Intelligence (GAI) within the educational field has raised interest to study the shape and impact of this utilization. This study investigates the opinions of information technology (IT) undergraduate students about the utilization of GAI during the learning process, focusing on their perception of the quality of produced information, challenges and concerns while using it, how they utilize it during learning, and long-term impact of using GAI. An electronic survey was distributed as a Google from to undergraduate students from five IT programs at the University of Petra. The results of 122 students revealed that 82% use GAI while learning. The main use of GAI (80% of respondents) was for solving programming problems, while 66% of respondents use GAI to write reports and express their ideas. The majority 86% of participants evaluate the presented information from GAI before using them, since they believe that sometimes the information is incorrect. 89% of respondents believe that they can learn from GAI tools, however, 95% of them feel it is necessary to train them on the proper utilization of GAI in education, and, 76% think that regulations must be released about the acceptable use of GAI. © 2024 IEEE.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Improving Robustness of CLIP by Adversarial Training Enhanced by Brain Activity

Improving Robustness of CLIP by Adversarial Training Enhance...

引用

2025 International Workshop on Advanced Imaging technology, IWAIT 2025

作者： Nakajima, Tasuku Maeda, Keisuke Togo, Ren Ogawa, Takahiro Haseyama, Miki Graduate School of Information Science and Technology Hokkaido University Japan Data-Driven Interdisciplinary Research Emergence Department Hokkaido University Japan Faculty of Information Science and Technology Hokkaido University Japan

ISBN: (数字)9781510688131

ISBN: (纸本)9781510688124

Contrastive Language-Image Pre-training (CLIP) is vulnerable to adversarial attacks which cause misclassification by subtle modifications undetectable to the human *** adversarial training strengthens CLIP models against such attacks, it often degrades their accuracy on clean *** tackle this challenge, we propose a novel defense strategy that leverages human brain activity *** proposed method combines features of brain activity with those of adversarial examples, which enhances the robustness of CLIP while maintaining high accuracy on clean *** results demonstrate the effectiveness of our method for the accurate retrieval of clean and adversarial *** results highlight the potential ability of brain data to overcome the existing challenges of adversarial defense in foundation models. © 2024 SPIE.

关键词： Brain Functional magnetic resonance imaging Adversarial training Education and training data modeling Neuroimaging Defense and security Feature extraction Semantics Image processing

来源：评论

学校读者我要写书评

暂无评论

Enhanced Framework for Generating Counterfactual Images with Sophisticated Caption and Inversion-free Image Editing

Enhanced Framework for Generating Counterfactual Images with...

引用

2025 International Workshop on Advanced Imaging technology, IWAIT 2025

作者： Li, Xiang Togo, Ren Maeda, Keisuke Ogawa, Takahiro Haseyama, Miki Graduate School of Information Science and Technology Hokkaido University Japan Faculty of Information Science and Technology Hokkaido University Japan Data-Driven Interdisciplinary Research Emergence Department Hokkaido University Japan

ISBN: (数字)9781510688131

ISBN: (纸本)9781510688124

The training process of classification models is commonly based on real-world data and models may learn certain spurious relationships, leading to an over-reliance on features not directly relevant to the *** this paper, we propose a novel framework for generating counterfactual *** framework enables us to confirm whether classification models are sensitive to changes in the features under *** have introduced the latest caption and image generator, which enables better counterfactual image generation as well as more efficient *** results show that the counterfactual images generated by our method have superior feature perturbation capabilities, which allows us to assess the robustness of the classification model more *** main improvements our framework offers over existing methods are the generation of higher-quality counterfactual images and the reduction of the computational cost of this process. © 2024 SPIE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Real-Time Classification of Dog Breeds Using the M5StickV 7

Real-Time Classification of Dog Breeds Using the M5StickV

引用

7th International Conference of Computer and Informatics Engineering, IC2IE 2024

作者： Putri, Desy Purnami Singgih Prasetyo, Eko Wahyu Buana, Putu Wira Udayana University Faculty of Engineering Department of Information Technology Bali Indonesia Bunda Mulia University Faculty of Information and Desain Department of Data Science Jakarta Indonesia

ISBN: (纸本)9798331505530

The accurate classification of dog breeds is a challenging task due to the subtle differences between breeds and the computational limitations of portable devices. Despite advancements in deep learning, there is a gap in the literature regarding the deployment of efficient and accurate models on resource-constrained embedded systems. This study addresses this gap by investigating the classification of nine dog breeds using a dataset of 1,080 images, processed through the MobileNetV1 architecture. The focus is on implementing this model within the M5StickV embedded system, a compact and portable device. The images underwent pre-processing, including resizing to 224 by 224 pixels and background removal. Transfer learning with Sipeed was utilized to fine-tune the model, which was subsequently converted to a Keras-compatible format for deployment. The resulting model demonstrated high accuracy (0.9833) and precision (0.9840), underscoring its robust performance. However, a slight delay in the classification process suggests the need for further optimization. This study highlights the potential of integrating advanced deep learning models with embedded systems for real-time, portable image classification, offering applications in pet identification and other fields. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Facial Image-Based Autism Detection:A Comparative Study of Deep Neural Network Classifiers

引用

Computers, Materials & Continua 2024年第1期78卷 105-126页

作者： Tayyaba Farhat Sheeraz Akram Hatoon SAlSagri Zulfiqar Ali Awais Ahmad Arfan Jaffar Faculty of Computer Science and Information Technology The Superior UniversityLahore54600Pakistan Intelligent Data Visual Computing Research(IDVCR) Faculty of Computer Science and Information TechnologyThe Superior UniversityLahore54600Pakistan Information Systems Department College of Computer and Information SciencesImam Mohammad Ibn Saud Islamic University(IMSIU)Riyadh12571Saudi Arabia School of Computer Science and Electronic Engineering(CSEE) University of EssexWivenhoe ParkColchesterCO43SQUK

Autism Spectrum Disorder(ASD)is a neurodevelopmental condition characterized by significant challenges in social interaction,communication,and repetitive *** and precise ASD detection is crucial,particularly in regions with limited diagnostic resources like *** study aims to conduct an extensive comparative analysis of various machine learning classifiers for ASD detection using facial images to identify an accurate and cost-effective solution tailored to the local *** research involves experimentation with VGG16 and MobileNet models,exploring different batch sizes,optimizers,and learning rate *** addition,the“Orange”machine learning tool is employed to evaluate classifier performance and automated image processing capabilities are utilized within the *** findings unequivocally establish VGG16 as the most effective classifier with a 5-fold cross-validation ***,VGG16,with a batch size of 2 and the Adam optimizer,trained for 100 epochs,achieves a remarkable validation accuracy of 99% and a testing accuracy of 87%.Furthermore,the model achieves an F1 score of 88%,precision of 85%,and recall of 90% on test *** validate the practical applicability of the VGG16 model with 5-fold cross-validation,the study conducts further testing on a dataset sourced fromautism centers in Pakistan,resulting in an accuracy rate of 85%.This reaffirms the model’s suitability for real-world ASD *** research offers valuable insights into classifier performance,emphasizing the potential of machine learning to deliver precise and accessible ASD diagnoses via facial image analysis.

关键词： Autism Autism Spectrum Disorder(ASD) disease segmentation features optimization deep learning models facial images classification

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：