检索结果-内蒙古大学图书馆

4th International Conference on Advanced Intelligent Technologies, ICAIT 2023

作者： Niu, Sihan Zhou, Yifan Li, Zhikai Huang, Shuyao Zhou, Yujun Department of Computer Science Johns Hopkins University BaltimoreMD United States Department of Electrical and Computer Engineering Johns Hopkins University BaltimoreMD United States School of Computer Engineering and Science Shanghai University Shanghai China School of Information Sciences University of Illinois Urbana-Champaign ChampaignIL United States

ISBN: (纸本)9789819732098

This paper presents a unique solution to challenges in medical image processing by incorporating an adaptive curve grey wolf optimization (ACGWO) algorithm into neural network backpropagation. Neural networks show potential in medical imaging but suffer from issues like overfitting and lack of interpretability due to imbalanced and scarce data. Traditional grey wolf optimization (GWO) also has its drawbacks, such as a lack of population diversity and premature convergence. This paper addresses these problems by introducing an adaptive algorithm, enhancing the standard GWO with a sigmoid function. This algorithm was extensively compared to four leading algorithms using six well-known test functions, outperforming them effectively. Moreover, by utilizing the ACGWO, we increase the robustness and generalization of the neural network, resulting in more interpretable predictions. Applied to the publicly accessible Cleveland Heart Disease dataset, our technique surpasses ten other methods, achieving 86.8% accuracy, indicating its potential for efficient heart disease prediction in the clinical setting. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Medical image processing

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Machine Learning Methods for Diagnosing Autism Spectrum Disorder Using Multimodal data: A Survey

Unsupervised Machine Learning Methods for Diagnosing Autism ...

引用

2022 International Conference on Computational science and Computational Intelligence, CSCI 2022

作者： Roy, Antika Rivas, Pablo Tayba, Mahee Noor School of Eng. and Computer Science Baylor University Dept. of Computer Science United States Baylor University Department of Computer Science United States

ISBN: (纸本)9798350320282

The neurodevelopmental disorder known as autism spectrum disorder (ASD) is becoming increasingly pervasive worldwide. It can be categorized when a person struggles to interact and communicate socially and also exhibits repetitious behaviors and interests. Although early intervention is crucial and may have long-term advantages in the lives of people with ASD, diagnosing ASD is difficult due to its heterogeneous characteristics and a large number of data from various aspects such as genetic, behavioral, electronic health records, and many other domains. This review paper offers an in-depth assessment of papers that use the most commonly used unsupervised machine learning techniques in ASD, such as 'k-means clustering' and 'Hierarchical clustering.' This research aims to identify and highlight the most recent unsupervised machine learning advances in the ASD literature while also attempting to highlight the significant contributions and limits of the selected works to provide insight for future researchers. © 2022 IEEE.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Sentimental Technique Implementation on Textual data 6

Sentimental Technique Implementation on Textual Data

引用

6th International Conference on Contemporary Computing and Informatics, IC3I 2023

作者： Karthik, Baggam Sai Bharat, Dhavileswarapu N.S.S.V.V. Durga Alam, Md Afroz Sai, Bandari Tharun Rana, Mrinalini Sharma, Smita Yadav, Suman Avdhesh School of Computer Science and Engineering Lovely Professional University Punjab Kapurthala India Amity School of Engineering and Technology Department of Computer Science and Engineering Amity University Uttar Pradesh Greater Noida India

ISBN: (纸本)9798350304480

The increasing amount of real-time or near-real-time data in the big data age provides organizations with opportunities to make data-driven decisions. However, social media data, such as that generated by Twitter, is typically unstructured and difficult to manage. This paper proposes an efficient text data pre-processing approach and develops an algorithm for training decision tree, random forest, SVM, and logistic regression classifiers on a dataset. The algorithm weights the sentiment score based on the hashtag and cleaned text weights, and the most efficient data pre-processing strategy is identified using a novel technology called the hash vectorizer. The effectiveness of the algorithm is tested against manually sorted sentiments and sentiments created before text data pre-processing, and the resultsshow its accuracy is comparable to human-annotated feelings. This research contributes to the existing body of knowledge by providing a precise method for cleaning social media data and a new approach to sentiment analysis. © 2023 IEEE.

关键词： Decision tree Hashing Vectorizer Hybrid model Logistic Regression Random Forest Sentimental Analysis SVM

来源：评论

学校读者我要写书评

暂无评论

SAV-SE: Scene-aware Audio-Visual Speech Enhancement with Selective State Space Model

引用

IEEE Journal on Selected Topics in Signal Processing 2025年第4期19卷 623-634页

作者： Qian, Xinyuan Gao, Jiaran Zhang, Yaodan Zhang, Qiquan Liu, Hexin Garcia, Leibny Paola Li, Haizhou University of Science and Technology Beijing School of Computer and Communication Engineering Beijing100083 China University of New South Wales School of Electrical Engineering and Telecommunications Sydney2052 Australia Nanyang Technological University College of Computing and Data Science Singapore Singapore Johns Hopkins University CLSP and HLT-COE United States Chinese University of HongKong Guangdong Provincial Key Laboratory of Big Data Computing Shenzhen518172 China Shenzhen Research Institute of Big data Shenzhen51872 China

Speech enhancement plays an essential role in various applications, and the integration of visual information has been demonstrated to bring substantial advantages. However, the majority of current research concentrates on the examination of facial and lip movements, which can be compromised or entirely inaccessible in scenarios where occlusions occur or when the camera view is distant. Whereas contextual visual cues from the surrounding environment have been overlooked: for example, when we see a dog bark, our brain has the innate ability to discern and filter out the barking noise. To this end, in this paper, we introduce a novel task, i.e. Scene-aware Audio-Visual Speech Enhancement SAV-SE. To our best knowledge, this is the first proposal to use rich contextual information from synchronized video as auxiliary cues to indicate the type of noise, which eventually improves the speech enhancement performance. Specifically, we propose the VC-S $^{2}$ E method, which incorporates the Conformer and Mamba modules for their complementary strengths. Extensive experiments are conducted on public MUSIC, AVSpeech and AudioSet datasets, where the results demonstrate the superiority of VC-S $^{2}$ E over other competitive methods. We will make the source code publicly available. Project demo page: https://***/ © 2007-2012 IEEE.

关键词： Speech enhancement

来源：评论

学校读者我要写书评

暂无评论

Particle Swarm Optimization-based Agent Negotiation Framework to Support Shared Decision-Making

Journal of Network Intelligence

引用

Journal of Network Intelligence 2023年第3期8卷 758-775页

作者： Chen, Xin Lu, Ping Lin, Kai-Biao Zeng, Jia-Ying Department of Computer Science and Technology Xiamen University of Technology Xiamen361024 China School of Economic and Management Xiamen University of Technology Xiamen361024 China

Shared decision-making (SDM) is a process by which patients and doctors make medical decisions together based on clinical evidence. It balances risk and expected outcomes with the preferences and values of patients. However, SDM is rarely employed in practice. Part of the reason for this is that the decision-making process is complex, takes long time, and the number of healthcare professionals trained in these techniques is limited. In this study, we first simplify the SDM preference negotiation problem as a multi-objective optimization (MOO) problem with bilateral treatment preferences. Then, we attempt to solve the MOO using an agent negotiation technique for bilateral MOO. We therefore propose a particle swarm optimization-based SDM-automated negotiation framework (PSOAN) that provides decision support for doctors and patients was pro-posed. The experimental results show that PSOAN obtains more overall satisfaction than other existing models by 11.1%–11.6%, indicating that it achieves higher social welfare. In addition, it reduces the satisfaction gap to 31.9%–34% and promotes social equity. It takes only 7.8 rounds to reach an agreement on average, which requires less than 1 minute. In summary, the proposed model can effectively improve agreement satisfaction and social welfare for both parties while reducing the time and space costs required for negotiation. The designed negotiation framework has bright future to assist and promote the implementation of SDM for both doctors and patients, and deserves more intensive studies. © 2023 ISSN 2414-8105 (Online).

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Enhanced Privacy and Security Maintenance to Preserve Bigdata using Cipher Policy 7

Enhanced Privacy and Security Maintenance to Preserve BigDat...

引用

7th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2023

作者： Jadhav, Dattatraya Arun Thatipudi, Jayendra Gopal Thakur, Vibha Nagendar, Y. Lakshmi, K. Mohana Sharma, Smita Keystone School of Engineering Department of Electronic and Telecommunication Pune India University of North Texas Department of Computer Science United States Sharda University Department of Computer Science India Sr University School of Computer Science & Artificial Intelligent Telangana Warangal India Cmr Technical Campus Ece Department Telangana Medchal Hyderabad Kandlakoya India Ies University Department of Computer Science and Engg. M.P. Bhopal India

ISBN: (纸本)9798350341485

As the use of big data in cloud computing continues to increase at an exponential rate, privacy concerns have emerged as a major concern. Every person and business should make data protection a top priority. Security risks may arise during transmission from client to cloud server. Cloud computing technology makes it possible for mobile clients to access the large data stores. With the use of a unified parallel and distributed encryption and decryption system, mobile clients and cloud computing may be made more secure. The security of older systems, such as those that rely on plaintext on the cloud, is questionable at best. Dynamic data Encryption Strategy (DDES) is the suggested approach that aims to improve the effectiveness of privacy safeguards. The Dynamic Encryption Determination (DED) method was designed to dynamically alternate data packages for encryptions under varying time restrictions, and it was the primary algorithm underpinning the DDES paradigm. Our suggested solution utilizes privacy categorization techniques to selectively encrypt data while working within time limitations. Utilizing a selective encryption strategy while still meeting the necessary execution time constraints, this method aims to increase the privacy protection scope. Our experimental results assess DDES's performance and demonstrate the privacy boost. © 2023 IEEE.

关键词： data privacy

来源：评论

学校读者我要写书评

暂无评论

Hidden or Inferred: Fair Learning-to-Rank with Unknown Demographics 24

Hidden or Inferred: Fair Learning-to-Rank with Unknown Demog...

引用

Proceedings of the 2024 AAAI/ACM Conference on AI, Ethics, and Society

作者： Oluseun Olulana Kathleen Cachel Fabricio Murai Elke Rundensteiner Data Science Program Worcester Polytechnic Institute Worcester MA Data Science Program Worcester Polytechnic Institute Worcester MA and Computer Science Department Worcester Polytechnic Institute Worcester MA

As learning-to-rank models are increasingly deployed for decision-making in areas with profound life implications, the FairML community has been developing fair learning-to-rank (LTR) models. These models rely on the availability of sensitive demographic features such as race or sex. However, in practice, regulatory obstacles and privacy concerns protect this data from collection and use. As a result, practitioners may either need to promote fairness despite the absence of these features or turn to demographic inference tools to attempt to infer them. Given that these tools are fallible, this paper aims to further understand how errors in demographic inference impact the fairness performance of popular fair LTR strategies. In which cases would it be better to keep such demographic attributes hidden from models versus infer them? We examine a spectrum of fair LTR strategies ranging from fair LTR with and without demographic features hidden versus inferred to fairness-unaware LTR followed by fair re-ranking. We conduct a controlled empirical investigation modeling different levels of inference errors by systematically perturbing the inferred sensitive attribute. We also perform three case studies with real-world datasets and popular open-source inference methods. Our findings reveal that as inference noise grows, LTR-based methods that incorporate fairness considerations into the learning process may increase bias. In contrast, fair re-ranking strategies are more robust to inference errors. All source code, data, and experimental artifacts of our experimental study are available here: https://***/sewen007/***

关键词：

来源：评论

学校读者我要写书评

暂无评论

Feature Importance Identification for Time Series Classifiers

Feature Importance Identification for Time Series Classifier...

引用

2022 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2022

作者： Meng, Han Wagner, Christian Triguero, Isaac Lab United Kingdom School of Computer Science Nottingham United Kingdom DaSCI Andalusian Institute in Data Science and Computational Intelligence University of Granada Department of Computer Science and Artificial Intelligence Granada Spain

ISBN: (数字)9781665452588

ISBN: (纸本)9781665452588

Time series classification is a challenging research area where machine learning techniques such as deep learning perform well, yet lack interpretability. Identifying the most important features for such classifiers provides a pathway to improving their interpretability. Several Feature Importance (FI) identification methods remove the contributions of features, i.e. observations at certain time steps of, from the input and evaluate the change in the classification result to measure the importance of features. As time series features cannot simply be deleted, current techniques generally rely on replacing features with constant or random values. While effective, this approach risks unexpected results in the classification and thus feature importance estimation-as the replacements used may be different to what the classifier encountered in the training phase. This is referred to as the Out-Of-Distribution problem. The OOD problem has been recognised in image and language models but have not received much attention in the context of time series classification. This work addresses the OOD problem in FI identification for time series classifiers. Specifically, we propose a method based on Conditional Variational Autoencoder to generate possible sets of within-distribution inputs, which are used to evaluate feature importance through marginalisation. Experiments on publicly accessible datasets are carried out showing that the method identifies the most important features with higher accuracy than existing methods, providing the basis for improved explainability of time series classifiers. © 2022 IEEE.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Enhancing Customer Experience through AI-Powered Personalization: A data science Perspective in E-Commerce

Enhancing Customer Experience through AI-Powered Personaliza...

引用

2024 International Conference on Communication, computer sciences and Engineering, IC3SE 2024

作者： Thakur, Hardeo Kumar Singh, Jagendra Saxena, Ayushi Bhaskar, Deepali Singh, Amarendra Pratap Garg, Pramod Kumar School Of Computer Science Engineering & Technology Bennett University Greater Noida India Sanskar College Of Engineering And Technology Department Of Computer Science Ghaziabad India Dr Kedar Nath Modi Institute Of Engineering And Technology Department Of Business Administration Modinagar India

ISBN: (纸本)9798350366846

The intent of this research is to explore the application of advanced machine learning technologies to improve personalization within the e-commerce field. As the number of online shopping platforms is growing rapidly, the ability to provide the users with personalized inferences and optimal experiences is becoming crucial. By applying artificial intelligence and machine learning technologies, such as deep learning and reinforcement learning, the present research explores the creation of an intelligent recommendation system that can understand the preferences and behavior of an individual. The process of building different machine learning models, such as Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN), and Deep Reinforcement Learning (DRL), will be analyzed to investigate their capability to predict the future responses. Therefore, the study aims to define the criteria for evaluating their performance in terms of optimized decision-making and personalization within online shopping environments. Additional goals of the research include the investigation of the effect of feature engineering and preprocessing on their performance and the study of the implications and best strategies related to their deployment within the actual environments of e-commerce. By attaining these goals, the present study seeks to provide the reader with valuable insights and recommendations symbiotic for these types of business. © 2024 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

***: A Benchmark for Evaluating Questioning Capability in Education for Large Language Models

arXiv

引用

arXiv 2024年

作者： Chen, Yuyan Wu, Chenwei Yan, Songzhou Liu, Panjun Zhou, Haoyu Xiao, Yanghua Shanghai Key Laboratory of Data Science School of Computer Science Fudan University China Electrical Engineering and Computer Science Department University of Michigan United States School of Computer Science Beijing Institute of Technology China

Teachers are important to imparting knowledge and guiding learners, and the role of large language models (LLMs) as potential educators is emerging as an important area of study. Recognizing LLMs’ capability to generate educational content can lead to advances in automated and personalized learning. While LLMs have been tested for their comprehension and problem-solving skills, their capability in teaching remains largely unexplored. In teaching, questioning is a key skill that guides students to analyze, evaluate, and synthesize core concepts and principles. Therefore, our research introduces a benchmark to evaluate the questioning capability in education as a teacher of LLMs through evaluating their generated educational questions, utilizing Anderson and Krathwohl’s taxonomy across general, monodisciplinary, and interdisciplinary domains. We shift the focus from LLMs as learners to LLMs as educators, assessing their teaching capability through guiding them to generate questions. We apply four metrics, including relevance, coverage, representativeness, and consistency, to evaluate the educational quality of LLMs’ outputs. Our results indicate that GPT-4 demonstrates significant potential in teaching general, humanities, and science courses;Claude2 appears more apt as an interdisciplinary teacher. Furthermore, the automatic scores align with human perspectives. © 2024, CC BY.

关键词： Problem solving

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：