检索结果-内蒙古大学图书馆

Federated Conference on computer science and Information Systems (FedCSIS)

作者： Francisco Herrera Dept. of Computer Science and Artificial Intelligence Andalusian Institute of Data Science and Computational Intelligence (DaSCI) University of Granada Spain

ISBN: (数字)9788396960160

ISBN: (纸本)9798350359718

The emergence of deep learning at the beginning of the last decade has driven the advancement of complex models, culminating in the development of large language models and generative AI. These models represent the summit of size and complexity. Explainability should be an option that plays a key role in enabling understandable the AI-assisted decision-making and ensuring accountability. This contribution delves into the complexities of explainable artificial intelligence (XAI) through various perspectives, considering the extensive and growing body of literature. Our discussion begins by addressing the challenges posed by complex data, models, and high-risk scenarios. Given the rapid growth of the field, it is essential to tackle the criticisms and challenges that emerge as it matures, requiring thorough exploration. This contribution explores them, along with three aspects that may shed light on them. First, it is focused on the lack of definitional cohesion, examining how and why is defined XAI from the perspectives of audience and understanding. Second, it explores XAI explanations, bridging the gap between complex AI models and human understanding. Third, it is crucial to consider how to analyze and evaluate the maturity level of explainability, from a triple dimension, practicality, governance and auditability.

关键词： Deep learning computer science Explainable AI Generative AI Large language models Computational modeling Decision making data models Complexity theory

来源：评论

学校读者我要写书评

暂无评论

Research Concept Link Prediction via Graph Convolutional Network 8

Research Concept Link Prediction via Graph Convolutional Net...

引用

8th International Conference on Big data and Information Analytics, BigDIA 2022

作者： Wang, Xiangyu Chen, Lyuzhou Lyu, Derui Ban, Taiyu Guan, Yifeng Chen, Qiuju School of Data Science Ustc Hefei China School of Computer Science and Technology Ustc Hefei China Dept. Electronic Engineering and Information Science Ustc Hefei China

ISBN: (数字)9781665487962

ISBN: (纸本)9781665487962

As interdisciplinary research develops, numerous publications are uploaded to the research community. This makes researchers spend a lot of time searching for valuable information. Some methods have been proposed to provide more accurate recommendations, such as domain terminology-based or graph pattern-based methods. However, due to the continuous emergence of new research concepts and new research fields, it is difficult to apply it to practical tasks. To tackle these issues, this paper constructs the research keywords of different publications into a topological network, and then predicts the possibility of connection between different keywords. To analyze the associations between research concepts, graph convolution technology are employed to design method. It could provide domain-independent recommendations for the relevance of research concepts. Experiments demonstrate that the proposed method can predict associations between research concepts more effectively than traditional methods. © 2022 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Enhancing Interpretability, Reliability and Trustworthiness: Applications of Explainable Artificial Intelligence in Medical Imaging, Financial Markets, and Sentiment Analysis

Enhancing Interpretability, Reliability and Trustworthiness:...

引用

International Conference on Electronics, computers and Artificial Intelligence (ECAI)

作者： Kriti Srivastava Afreen Sorathiya Jinal Mehta Vineet Chotaliya Dept. of Computer Science & Engineering (Data Science) SVKM’S Dwarkadas J Sanghvi College of Engineering Mumbai India

ISBN: (数字)9798350371154

ISBN: (纸本)9798350371161

In today’s technological era, as AI systems become more integral to critical decision-making, the importance of Explainable Artificial Intelligence (XAI) has become more pronounced. It addresses the challenge of understanding complex machine learning and deep learning models, ensuring transparency, interpretability, and accountability. This research paper provides a comprehensive analysis of XAI, focusing on its significance, methodologies, challenges, and future prospects. Theoretical foundations of XAI are elucidated, clarifying key concepts such as interpretability, transparency, and accountability. We differentiate between model-agnostic and model-specific XAI methods, outlining their strengths and limitations. A range of recent XAI techniques, including Local Interpretable Model-agnostic Explanations (LIME), SHapley Additive exPlanations (SHAP), and Gradient-weighted Class Activation Mapping (Grad-CAM), are scrutinized. Through case studies in Healthcare (Pneumonia Classification), Finance (Stock Price Prediction), and Entertainment (Sentiment Analysis), we demonstrate how XAI enhances the understandability and trustworthiness of AI systems. Additionally, a comparative study of all three methods on all three case studies has been conducted, and the results are compared. Challenges such as scalability issues and ethical considerations, including biases and fairness, are discussed. Looking ahead, we offer insights into future XAI research trajectories, aiming to foster public trust and shape a future where AI systems are both intelligent and comprehensible.

关键词： Sentiment analysis Ethics Pneumonia Explainable AI Decision making Finance Entertainment industry

来源：评论

学校读者我要写书评

暂无评论

Early Detection Of Parkinson’s Disease Using Machine And Deep Learning Models

Early Detection Of Parkinson’s Disease Using Machine And De...

引用

International Conference on Electronics, computers and Artificial Intelligence (ECAI)

作者： Afreen Sorathiya Jinal Mehta Hetangi Rathod Nilesh Marathe Dept. of Computer Science & Engineering (Data Science) SVKM’S Dwarkadas J Sanghvi College of Engineering Mumbai India

ISBN: (数字)9798350371154

ISBN: (纸本)9798350371161

Parkinson’s disease (PD) represents significant challenges in early detection, often relying on subjective clinical assessments and costly imaging procedures, leading to low accuracy rates, especially in detecting PD at its early stages. This research investigates the transformative potential of machine learning and deep learning algorithms in PD detection and diagnosis. Leveraging a diverse dataset comprising vocal fundamental frequency measurements, nonlinear dynamical complexity measures, and image data, we explore various Machine Learning (ML) and Deep Learning (DL) models. Our findings reveal promising accuracies across different models with DenseNet121 achieving a maximum accuracy of ${9 6 . 6 7 \%}$ for image data and hybrid architectures like 1D CNN-GRU achieving ${9 4 . 8 7 \%}$ accuracy for vocal data. Furthermore, the study identifies key limitations and challenges associated with each model, emphasizing the need for continued refinement and innovation. This research contributes to advancing PD diagnosis, offering potential improvements in patient outcomes and paving the way for more accessible and effective diagnostic solutions.

关键词： Deep learning Accuracy Computational modeling computer architecture data models Vectors Frequency measurement

来源：评论

学校读者我要写书评

暂无评论

OSDA-ST: Advancing Open Set Domain Adaptation Through Selective Thresholding in Remote Sensing

OSDA-ST: Advancing Open Set Domain Adaptation Through Select...

引用

2024 IEEE International Conference on Big data, Bigdata 2024

作者： Wang, Andy Gomes, Rahul Rozario, Papia F. University of Wisconsin Madison School of Computer Data & Information Sciences MadisonWI United States University of Wisconsin-Eau Claire Department of Computer Science Eau Claire United States University of Wisconsin-Eau Claire Dept. of Geography and Anthropology Eau ClaireWI United States

ISBN: (纸本)9798350362480

Segmenting and classifying satellite and aerial images is a crucial task for understanding various environmental, urban, and agricultural phenomena in remote sensing. Traditional segmentation methods often rely on large, labeled datasets, which can be challenging to obtain for every possible domain or geographic region. Unsupervised Domain adaptation (UDA) attempts to solve this problem by transferring pixel-wise semantic knowledge from a labeled source domain to an unlabeled target domain. However, current UDA methods for remote sensing assume a corresponding label space between domains, which is often unrealistic in real-world scenarios where the target domain may contain novel or unknown classes that are absent in the source domain. This paper addresses the limitations associated with Open-Set Domain Adaptation for Semantic Segmentation (OSDA-SS) by proposing OSDA-ST, a framework performing max-logit score (MLS) thresholding, source-only pretraining, and a dynamic source selection score for unknown class estimation. We test these modifications on the remote sensing dataset of Potsdam and Vaihingen for the first time. Compared to state of the art, our methods achieved 39.9 H-score, a significant improvement of 5.82% and 7% on average. Results indicate that these modifications are successful in reducing misclassification of pseudo-labels thereby providing an adaptive approach to thresholding as compared to previous state of the art. © 2024 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Analyzing Effects of Fake Training data on the Performance of Deep Learning Systems

arXiv

引用

arXiv 2023年

作者： Seth, Pratinav Bhandari, Akshat Lakara, Kumud Dept. of Data Science and Computer Applications Dept. of Computer Science and Engineering Manipal Institute of Technology Manipal Academy of Higher Education Manipal India

Deep learning models frequently suffer from various problems such as class imbalance and lack of robustness to distribution shift. It is often difficult to find data suitable for training beyond the available benchmarks. This is especially the case for computer vision models. However, with the advent of Generative Adversarial Networks (GANs), it is now possible to generate high-quality synthetic data. This synthetic data can be used to alleviate some of the challenges faced by deep learning models. In this work we present a detailed analysis of the effect of training computer vision models using different proportions of synthetic data along with real (organic) data. We analyze the effect that various quantities of synthetic data, when mixed with original data, can have on a model's robustness to out-of-distribution data and the general quality of predictions. © 2023, CC BY.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Sustainable Energy Efficient Routing Protocol using Chimp algorithm and SOM for Underwater Wireless Sensor Networks

Sustainable Energy Efficient Routing Protocol using Chimp al...

引用

2023 International Conference on Recent Advances in science and Engineering Technology, ICRASET 2023

作者： Philip Paul Arunodhayam, T. Vadde, Akhil Raj Kumar, Thimmampali Prasanna Silas, Salaja Gandu, Shalem Preetham Harshith Kumar, Chamarti Karunya Institute of Technology and Sciences Dept. of Computer Science and Engineering Coimbatore India College of Engineering and Computing George Mason University Data Analytics Engineering VA Fairfax22030 United States

ISBN: (纸本)9798350306927

Underwater Wireless Sensor Networks (UWSNs) are increasingly being used for various applications, such as environmental monitoring, underwater exploration, and oceanographic research. protocols that consume less energy for underwater wireless sensor networks (UWSNs) are still a difficult undertaking because of the harsh conditions present underwater and the restricted battery capacity of the sensor nodes. This research paper proposes an optimized multi-Hop routing protocol using Chimp Optimization and Self-Organizing Map (SOM). The proposed technique is compared with three popular routing protocols - AODV, DSDV, and DSR in terms of network lifetime and packet delivery ratio. Chimp Optimization algorithm as well as SOM are used to improve network performance. The findings indicate that the put-forward technique exceeds the performance of existing routing protocols, as it increases network lifetime, PDR and PLR while decreasing packet loss ratio. The network lifetime of the put-forward technique is 1039.42 seconds, which is higher than AODV, DSDV, and DSR. Similarly, the PDR of the proposed technique is 97.38%, which is comparatively higher than the three routing protocols. Moreover, the PLR of the proposed technique is 2.62%, which is much lower than AODV, DSDV, and DSR. The proposed technique based on Chimp Optimization and SOM can effectively optimize the multi-Hop routing protocol in underwater wireless sensor networks to achieve sustainable energy efficiency, thus providing important insights for researchers and practitioners to enhance the performance of underwater wireless sensor networks. © 2023 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Detection of Pre Shoplifting Suspicious Behavior Using Deep Learning 16

Detection of Pre Shoplifting Suspicious Behavior Using Deep ...

引用

16th IIAI International Congress on Advanced Applied Informatics, IIAI-AAI 2024

作者： Shrestha, Sujan Taniguchi, Yoji Tanaka, Tetsuo Graduate school of Engineering Kanagawa Institute of Tehnology Course of Information and computer sciences Atsugi Japan Daiichi Institute of Technology Artificial Intelligence and Data Science Department of Information Tokyo Japan Kanagawa Institute of Technology Faculty of Information Technology Dept. of Information and Computer Sciences Atsugi Japan

ISBN: (纸本)9798350377903

Shoplifting presents a significant challenge for retailers, leading to substantial financial losses and security concerns. Current surveillance systems effectively identify shoplifting incidents postoccurrence;however, the capability to detect and prevent such activities preemptively remains limited. This research focuses on identifying behaviors that likely precede shoplifting events. To this end, we introduce a novel benchmark dataset, specifically designed for the early detection of suspicious behavior that may lead to shoplifting. This dataset is curated by selecting and segmenting relevant sequences from the UCF101-Crime dataset, encompassing suspicious behavior, actual shoplifting incidents, and normal activities. Our approach addresses the limitations of existing datasets where the brief duration of shoplifting events may skew neural network performance. The dataset includes clips of only a few seconds each, for which we propose a robust neural network architecture combining the strengths of convolutional neural networks (CNN) for efficient feature extraction and Bidirectional long short-term memory (BiLSTM) networks for capturing temporal dependencies within action sequences. Our model achieves an impressive classification accuracy of 86.21 % on the newly created dataset. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Software Effort Estimation with Ant Colony Optimization Algorithm and Fuzzy-Neural Networks

Enhancing Software Effort Estimation with Ant Colony Optimiz...

引用

Distributed Computing and High Performance Computing (DCHPC), International Conference on

作者： Mahnaz Afshari Taghi Javdani Gandomani Data Science Research Group Shahrekord University Shahrekord Iran Dept. computer science shahrekord university Shahrekord Iran

Software effort estimation remains a persistent challenge and requires serious attention in the early stages of software project management. Inherent uncertainties arising from incomplete and inaccurate requirements pose a significant barrier to reliable estimations. Despite numerous efforts and various techniques proposed for cost estimation, the pursuit of improving estimation accuracy remains essential. In response to this challenge, this study introduces a novel model that integrates an Adaptive Neuro-Fuzzy Inference System with the Ant Colony Optimization algorithm. The model is further compared with well-known evolutionary algorithms such as Differential Evolution, Genetic Algorithm, Artificial Neural Network, and Particle Swarm Optimization. Applying the proposed model to popular software effort estimation datasets, including Albrecht, Desharnais, and Kemerer, demonstrates its superiority over the mentioned algorithms. The improved estimation provided by this model can assist software project managers in better project cost estimation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

RadChain Connect: Integration Between Blockchain and FreeRADIUS for Secure Authentication in Wi-Fi Networks/Web Environment 39

RadChain Connect: Integration Between Blockchain and FreeRAD...

引用

39th International Conference on Information Networking, ICOIN 2025

作者： Hoffmann, Eduardo Freitas Machado, Caciano Westphall, Carla Merkle Federal University of Santa Catarina Dept. of Computer Science and Statistics Santa Catarina Brazil Federal University of Rio Grande do Sul Data Processing Center Porto Alegre Brazil

ISBN: (纸本)9798331506940

User authentication in web environments and Wi-Fi networks is crucial due to the increase in fraud and invasions. Traditional methods, such as WPA2-PSK, have vulnerabilities, making the use of more secure solutions necessary. RadChain Connect is a proposal that combines blockchain with FreeRADIUS and self-sovereign identity, aiming to provide an efficient authentication system. Initially, it focuses on web authentication in universities, enhancing security at login. In the future, there are plans to expand the solution to Wi-Fi networks, leveraging the versatility of FreeRADIUS and the security of the EAP protocol. © 2025 IEEE.

关键词： Wi-Fi

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：