检索结果-内蒙古大学图书馆

International Conference on Data engineering

作者： Rongwei Xu Guanfeng Liu Yan Wang Xuyun Zhang Kai Zheng Xiaofang Zhou School of Computing Macquarie University Australia School of Computer Science and Engineering University of Electronic Science and Technology of China China Department of Computer Science and Engineering Hong Kong University of Science and Technology China

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

Trust plays an essential role in an individual's decision-making. Traditional trust prediction models rely on pairwise correlations to infer potential relationships between users. However, in the real world, interactions between users are usually complicated rather than pairwise only. Hypergraphs offer a flexible approach to modeling these complex high-order correlations (not just pairwise connections), since hypergraphs can leverage hyperedeges to link more than two nodes. However, most hypergraph-based methods are generic and cannot be well applied to the trust prediction task. In this paper, we propose an Adaptive Hypergraph Network for Trust Prediction (AHNTP), a novel approach that improves trust prediction accuracy by using higher-order correlations. AHNTP utilizes Motif-based PageRank to capture high-order social influence information. In addition, it constructs hypergroups from both node-level and structure-level attributes to incorporate complex correlation information. Furthermore, AHNTP leverages adaptive hypergraph Graph Convolutional Network (GCN) layers and multilayer perceptrons (MLPs) to generate comprehensive user embeddings, facilitating trust relationship prediction. To enhance model generalization and robustness, we introduce a novel supervised contrastive learning loss for optimization. Extensive experiments demonstrate the superiority of our model over the state-of-the-art approaches in terms of trust prediction accuracy.

关键词： Adaptation models Correlation Adaptive systems Accuracy Social networking (online) Contrastive learning Predictive models

来源：评论

学校读者我要写书评

暂无评论

Unveiling Emotions from EEG: A GRU-Based Approach

arXiv

引用

arXiv 2023年

作者： Johari, Sarthak Meedinti, Gowri Namratha Delhibabu, Radhakrishnan Joshi, Deepak Computing Science and Engineering Indraprastha Institute of Information Technology New Delhi India School of Computing Science and Engineering Vellore Institute of Technology Vellore India Centre for Biomedical Engineering Indian Institute of Technology New Delhi India

Emotion recognition from EEG data is a vital research domain in affective computing. This study investigates the effectiveness of the Gated Recurrent Unit (GRU) algorithm, a variant of Recurrent Neural Networks (RNNs), in predicting emotional states using EEG signals. Our publicly available dataset consists of EEG recordings from participants exposed to stimuli eliciting positive, neutral, and negative emotions, alongside resting neutral data. We preprocess the EEG data using artifact removal, bandpass filters, and normalization techniques for optimal feature extraction. Leveraging the GRU’s ability to capture temporal dependencies, our model achieved impressive results with perfect accuracy on the validation set. Comparing our GRU model with other machine learning approaches, the Extreme Gradient Boosting Classifier achieved the highest accuracy. Our analysis using the confusion matrix unveiled valuable insights into model performance, facilitating accurate emotion classification. This research contributes to the advancement of affective computing and highlights the potential of deep learning models like GRUs in emotion recognition. Our findings offer novel avenues for human-computer interaction and understanding emotional states from brainwave activity. © 2023, CC BY.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

The Challenge of Adversarial Machine Learning in the Context of Smart Homes

The Challenge of Adversarial Machine Learning in the Context...

引用

2024 International Conference on Advances in computing Research on Science engineering and technology, ACROSET 2024

作者： Preethi Kishor Shivathya, S. Chandrasekar, T. Madhavi, Banala Balaji, L. Balamurali, Arvind School of Computing and Information Technology Reva University Department of Csit Bangalore India Canara Engineering College Department of Cse Mangalore India Kalasalingam Academy of Research and Education Department of Business Administration Virudhnagar India Mlr Institute of Technology Department of Csit Hyderabad India Sagunthala R&d Institute of Science and Technology Department of Ec Chennai India Rajalakshmi Engineering College Department of Ece Chennai India

ISBN: (纸本)9798350388800

Smart homes are more safe, convenient, and automated than ever, changing how we interact with them. As these systems employ machine learning increasingly, aggressive machine learning is a concern. This article describes three ways to safeguard smart homes from dangerous individuals. Robust Net Guard, Secure Sense, Ethical Guardian. Robust Net Guard begins these approaches. It strengthens smart home machine learning models by adding safety layers to deep neural networks. This improves model accuracy and resistance to unwanted modifications. The second smart home security method is Secure Sense. Finding suspicious activity and real-time monitoring let it identify and stop security threats rapidly. The final method is Ethical Guardian. It prioritizes ethics and ensures fairness, transparency, and accountability in smart home machine learning models. It addresses prejudice, interpretability, and morality to moralize smart homes. This research compares these three approaches in accuracy, precision, memory, F1 Score, and computer work. Results are shown using line charts and box graphs. These evaluations help us understand each plan's merits and downsides and prepare for future smart home system assaults. As smart home technology evolves, robust, moral machine learning models are needed. This paper addresses hostile machine learning challenges in smart home technology, contributing to the safety, privacy, and moral debate. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Review of detection, prediction and treatment of fluid loss events

引用

Arabian Journal of Geosciences 2024年第1期18卷 1-20页

作者： Amish, Mohamed Khodja, Mohamed School of Computing Engineering and Technology Robert Gordon University Aberdeen UK Sonatrach/Algerian Petroleum Institute Boumerdes Algeria Algerian Academy of Science and Technology Villa “Rais Hamidou” Algiers Algeria

Lost circulation has the potential to cause formation damage, wellbore instability and a blowout. Many methods have been introduced, but there is no industry-wide solution available to predict lost circulation due to some constraints in the field. It is essential to predict the onset of loss of circulation to mitigate its effects, reduce operational costs and prevent the risk to people and the environment. A wide range of methods, techniques and treatments, including environmentally friendly materials, are reviewed to mitigate the loss of circulation. Conventional and intelligent methods are presented for detecting and predicting lost circulation events. Using oil field data such as fluid parameters, drilling parameters and geological parameters, artificial intelligence can predict fluid losses using supervised machine learning (ML). Several ML models for predicting fluid loss are reviewed in this paper, and other possible applications are discussed. The sample size, field location, input and output features, performance and ML algorithms are extracted. The paper provides an inclusive presentation of the ML workflow for fluid loss prediction and is anticipated to help and support both drilling engineering practitioners and researchers in the resolution of drilling challenges, with recommendations for future development.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Distributed Strategy Design for Free-in and Free-out Aggregative Games

引用

IEEE Transactions on Automatic Control 2025年

作者： Liu, Yuxuan Ye, Maojiao Ding, Lei Han, Qing-Long Nanjing University of Science and Technology School of Automation Nanjing210094 China Nanjing University of Posts and Telecommunications Institute of Advanced Technology Nanjing210023 China Swinburne University of Technology School of Science Computing and Engineering Technologies MelbourneVIC3122 Australia

This paper proposes a new aggregative game model over Free-in and Free-out (FIFO) networks, in which each player can freely join and leave the network at its timing and aims to minimize its total cost during its active period. To enable the players to make self-beneficial decisions in such a dynamic environment, it is assumed that the players can locally store and exchange the historical action information. Based on the stored information, a distributed strategy is established, in which each player updates its action by a dual averaging method. In order to prevent excessive storage requirements, a storage mechanism is designed so that only the information generated from a certain historical time horizon is retained. The performance of the proposed strategy is evaluated by the static regret, which quantifies player's loss between the actual cost and the cost with the fixed best response during its active period. It is shown that the upper bound of each player's static regret grows sub-linearly under local diminishing step-sizes, indicating that the proposed strategy performs as well as choosing the best stationary action in hindsight for the long-term players. Finally, a simulation study on energy consumption games is given to verify the effectiveness of the developed methods. © 1963-2012 IEEE.

关键词： Aggregative game distributed strategy FIFO network

来源：评论

学校读者我要写书评

暂无评论

An Optimized Weighted Node Ranking Scheme for Channel Assignment in Wireless Mesh Networks using the Genetic Algorithm

An Optimized Weighted Node Ranking Scheme for Channel Assign...

引用

2021 International Conference on Data Science and Its Applications, ICoDSA 2021

作者： Ismael, Bahaa Muneer Ngadi, Asri Bin Sharif, Johan Bin Mohamad University Technology Malaysia School of Computing Facility of Engineering Johor Bahru Malaysia

ISBN: (纸本)9781665443036

The widespread of Internet of Things (IoT) increases the reliance on Multi-Radio Wireless Mesh Networks (MR-WMN). This kind of networks provides a support to many IoT applications like smart grids, intelligent transportation systems and health monitoring systems. Therefore, the Quality of Service (QoS) becomes of great importance. This can be achieved by assigning the channels among links within the WMNs in a way that improvs the network throughput and capacity while maintaining a fair resource allocation. Although several studies have tried to make such trade-off, they overlook the dynamic nature of WMNs. Such dynamicity is resulted from user mobility which causes rapid changes in network topology and invalids the channel assignment that is currently in place. The static calculation of different network parameters involved in the channel assignment becomes invalid which leads to unfair channel allocation. As such, this study addresses the compatibility issue by bringing about a dynamic approach for weighing the network parameters calculation relying on the current state of the topology. The study proposes a Genetic Algorithm-Based Node Weighting scheme for channel assignment in the WMN (GA-WNR-CA). If a change is happened, the proposed algorithm can adapt and recalculate the weights accordingly. Weights calculation is carried out intelligently using the Genetic Algorithm that search for the optimal value. Once calculated, the network parameters are updated, and based on which the need for new assignment is determined. The experimental results show that the proposed algorithm outperformed those that have been proposed by related works, which conforms the efficacy of the dynamic approach adopted by the algorithm. © 2021 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Weakly-Supervised Anomaly Detection for Multimodal Data Distributions

Weakly-Supervised Anomaly Detection for Multimodal Data Dist...

引用

IEEE International Conference on Signal Processing, Communications and computing (ICSPCC)

作者： Xu Tan Junqi Chen Sylwan Rahardja Jiawei Yang Susanto Rahardja School of Marine Science and Technology Northwestern Poly technical University Xi'an China School of Computing University of Eastern Finland Kuopio Finland Department of Computing University of Turku Turku Finland Engineering Cluster Singapore Institute of Technology Singapore

ISBN: (数字)9798350366556

ISBN: (纸本)9798350366563

Weakly-supervised anomaly detection can outper-form existing unsupervised methods with the assistance of a very small number of labeled anomalies, which attracts increasing attention from researchers. However, existing weakly-supervised anomaly detection methods are limited as these methods do not factor in the multimodel nature of the real-world data distribution. To mitigate this, we propose the Weakly-supervised Variational-mixture-model-based Anomaly Detector (WVAD). WVAD excels in multimodal datasets. It consists of two components: a deep variational mixture model, and an anomaly score estimator. The deep variational mixture model captures various features of the data from different clusters, then these features are delivered to the anomaly score estimator to assess the anomaly levels. Experimental results on three real-world datasets demonstrate WVAD's superiority.

关键词： Mixture models Detectors Signal processing Feature extraction Data models Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

A Review on Leveraging Language Agnostic Automated Text Data Augmentation with Explainable Semantic Integrity

A Review on Leveraging Language Agnostic Automated Text Data...

引用

Advanced Research in computing (ICARC), International Conference on

作者： Sarith Wijesundera Suresh Michael Peiris Department of Computer Science and Engineering University of Westminster London UK School of Computing Informatics Institute of Technology Colombo Sri Lanka

ISBN: (数字)9798331530983

ISBN: (纸本)9798331530990

Data Augmentation (DA) is an effective strategy to increase model generalisation. In Natural Language Processing (NLP), DA remains in its early stages, primarily due to the inherent sensitivity of textual data, which complicates the augmentation process. These complexities are further increased in multilingual contexts, as DA techniques effective in one language may not yield comparable results in others. As a result, manually identifying optimal DA techniques that preserve semantic integrity and are language agnostic remains a significant challenge. It emphasises the necessity for automating the text DA process with Explainable Artificial Intelligence (XAI), which offers a promising approach by calculating word importance scores to effectively guide the augmentation. In this paper, a comprehensive review of existing approaches in auto-text DA is presented, beginning with an exploration of the concept of auto-text DA, followed by a discussion on its cross-lingual applications, and concluding with the integration of XAI for semantic preservation. The paper highlights the critical need for further research to enhance the effectiveness and applicability of XAI in auto-text DA, enabling its use across diverse languages.

关键词： Sensitivity Explainable AI Reviews Semantics Transfer learning Data augmentation Search problems Natural language processing Multilingual Optimization

来源：评论

学校读者我要写书评

暂无评论

Infer and Adapt: Bipedal Locomotion Reward Learning from Demonstrations via Inverse Reinforcement Learning

Infer and Adapt: Bipedal Locomotion Reward Learning from Dem...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Feiyang Wu Zhaoyuan Gu Hanran Wu Anqi Wu Ye Zhao School of Computational Science and Engineering Georgia Institute of Technology Atlanta GA USA Woodruff School of Mechanical Engineering Georgia Institute of Technology Atlanta GA USA College of Computing Georgia Institute of Technology Atlanta GA USA

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Enabling bipedal walking robots to learn how to maneuver over highly uneven, dynamically changing terrains is challenging due to the complexity of robot dynamics and interacted environments. Recent advancements in learning from demonstrations have shown promising results for robot learning in complex environments. While imitation learning of expert policies has been well-explored, the study of learning expert reward functions is largely under-explored in legged locomotion. This paper brings state-of-the-art Inverse Reinforcement Learning (IRL) techniques to solving bipedal locomotion problems over complex terrains. We propose algorithms for learning expert reward functions, and we subsequently analyze the learned functions. Through nonlinear function approximation, we uncover meaningful insights into the expert’s locomotion strategies. Furthermore, we empirically demonstrate that training a bipedal locomotion policy with the inferred reward functions enhances its walking performance on unseen terrains, highlighting the adaptability offered by reward learning.

关键词： Legged locomotion Training Robot motion Imitation learning Reinforcement learning Approximation algorithms Robot learning

来源：评论

学校读者我要写书评

暂无评论

Collaborative Fair-is-Better Filtering for Implicit Feedback

引用

Procedia Computer Science 2024年 246卷 1498-1507页

作者： Hoang V. Dong Huu-Quang Nguyen Hoang D. Nguyen Duc-Trong Le School of Computing and Information Systems Singapore Management University Singapore University of Engineering and Technology Vietnam National University Hanoi University College Cork Cork Ireland

With the wide adoption of recommender systems, fairness has increasingly become a critical topic in many applications, such as e-commerce, job search, and online entertainment. Collaborative filtering is susceptible to unfair recommendations for users from sensitive groups due to the non-negligible presence of biases. Whereas recent work mostly concerned fairness with the explicit ratings, we propose fairness-awareness recommendation models, referred to as CFBF, for implicit feedback (e.g., clicks, views, or purchases), which are ubiquitous in today’s context. This paper considers sensitive attributes, such as gender and age, in both disjoined and combined manners to investigate the models’ unfairness. We discuss several fairness metrics for implicit feedback recommendations based on Spearman’s rank correlation and Kendal Tau. Comprehensive experiments on Movielens and LastFM show that CFBF significantly improves user groups’ fairness with comparable and even better ranking performance.

关键词： Collaborative filtering fairness implicit feedback

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：