检索结果-内蒙古大学图书馆

19th International Conference on Ubiquitous Information Management and Communication, IMCOM 2025

作者： Agomuo, Okechukwu Clement Uzoma, Agomuo Kingsley Khan, Zohaib Otuomasirichi, Agomuo Ijeoma Muzamal, Junaid Hussain Department of Operations and Information Systems University of Utah Salt Lake City United States Center for Environmental Management and Green Energy University of Nigeria Enugu Nigeria Dept. of Software Engineering FAST NUCES Lahore Pakistan Department of Agricultural Economics University of Nigeria Enugu Nigeria Fast School of Computing Fast NUCES Lahore Pakistan

ISBN: (纸本)9798331507817

The rapid evolution of digital financial services has significantly increased the vulnerability of financial systems to fraudulent activities. Traditional machine learning models have offered substantial progress in detecting fraudulent transactions;however, they often lack adaptability and transparency, critical for dynamic financial environments and regulatory compliance. This paper introduces a novel approach that integrates Deep Reinforcement Learning (DRL) with Explainable Artificial Intelligence (XAI) to enhance fraud detection capabilities in cloud-based financial platforms. Our model, tested on the synthetic PaySim mobile money transaction dataset, leverages the adaptive nature of DRL to continuously learn and update its fraud detection strategies based on evolving transaction patterns. Concurrently, the integration of XAI provides clear, interpretable insights into the decision-making process, thus ensuring transparency and building trust. The proposed model demonstrates superior performance with an achieved accuracy of 99.5% and an F1-score of 99.0%, significantly outperforming traditional fraud detection systems. These results not only underscore the efficacy of our model in improving the accuracy of fraud detection but also highlight its capability in offering significant improvements in understanding the underlying reasons for each decision, thereby aiding compliance with financial regulations. The practical implications of this research highlight its potential to provide a robust, scalable, and transparent solution for real-time fraud detection, which is essential for safeguarding the integrity of modern financial systems. © 2025 IEEE.

关键词： Decentralized finance

来源：评论

学校读者我要写书评

暂无评论

FreqSense: Universal and Low-Latency Adversarial Example Detection for Speaker Recognition with Interpretability in Frequency Domain

FreqSense: Universal and Low-Latency Adversarial Example Det...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Yihuan Huang Yuanzhe Li Yanzhen Ren Weiping Tu Yuhong Yang Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan University National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Speaker recognition (SR) systems are particularly vulnerable to adversarial example (AE) attacks. To mitigate these attacks, AE detection systems are typically integrated into SR systems. To overcome the limitations of low detection accuracy, poor generalization, and high latency in existing schemes, this paper proposes FreqSense, an AE detection scheme based on frequency distribution features. FreqSense detects a variety of unknown AE attacks with low latency, and provides interpretability in its detection process. The basic idea of FreqSense is that AE typically introduce carefully designed noise in specific frequency bands that are associated with highly distinctive speaker identities. Therefore, leveraging the distributional variations in these frequency bands can effectively distinguish between AE and benign audio. FreqSense models frequency distribution features by integrating time-frequency transformation technology with a self-attention mechanism and employs a neural network-based classifier to distinguish between AE and benign audio. Experimental results show that FreqSense achieves an overall detection accuracy of 99.2%, surpassing state-of-the-art (SOTA) schemes by 27.2%. When confronting unknown AE attacks, FreqSense achieves a detection accuracy of 98.3% with a latency of just 0.0014 seconds.

关键词： Time-frequency analysis Accuracy Noise Speech recognition Feature extraction Acoustics Speaker recognition Low latency communication Speech processing

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Decision Management: Multi-Modal Analytics in a Health Case Study 19

Data-Driven Decision Management: Multi-Modal Analytics in a ...

引用

19th International Conference on Ubiquitous Information Management and Communication, IMCOM 2025

作者： Agomuo, Okechukwu Clement Khan, Zohaib Otuomasirichi, Agomuo Ijeoma Uzoma, Agomuo Kingsley Muzamal, Junaid Hussain Department of Operations and Information Systems University of Utah Salt Lake City United States Dept. of Software Engineering FAST NUCES Lahore Pakistan Department of Agricultural Economics University of Nigeria Enugu Nigeria Center for Environmental Management and Green Energy University of Nigeria Enugu Nigeria Fast School of Computing Fast NUCES Lahore Pakistan

ISBN: (纸本)9798331507817

In an era where data is abundant yet underutilized, organizations across various sectors face challenges in extracting actionable insights from complex, multi-modal datasets. To address these challenges, this study proposes a versatile data analytics framework designed to enhance predictive accuracy and support informed decision-making. The framework integrates structured and unstructured data, leveraging advanced Transformer architectures to capture temporal dynamics and complex interactions within the data. In a healthcare use case, the framework demonstrated its effectiveness by achieving an Accuracy of 0.854, an F1-Score of 0.895, and an AUC-ROC of 0.930, significantly outperforming traditional models. By incorporating SHAP for interpretability, the framework ensures that its predictions are both accurate and transparent, making it a valuable tool for decision-makers. While healthcare is one application, the framework’s flexibility allows it to be adapted to a wide range of industries. Future work will focus on validating the framework across different sectors and integrating it into operational workflows to optimize decision-making and outcomes. © 2025 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Container Performance in Space Systems 25th

Container Performance in Space Systems

引用

25th International Conference on Internet computing and IoT, ICOMP 2024, and 22nd International Conference on Embedded Systems, Cyber-physical Systems, and Applications, ESCS 2024, held as part of the World Congress in Computer Science, Computer engineering and Applied computing, CSCE 2024

作者： Alamgir, Shariar M. Bohra, Dhruv L. Nguyen, Elisabeth A. Embedded and Specialized Computing Department The Aerospace Corporation El SegundoCA United States Software Architecture and Engineering Department The Aerospace Corporation El SegundoCA United States

ISBN: (纸本)9783031859229

Critical embedded software, such as spacecraft flight software, requires high reliability, efficiency, and real-time performance while being capable enough to meet application needs. The increasing prevalence of Linux, and in particular Linux containers, presents opportunities for space systems but also poses potential risks since Linux was not designed to be a real-time operating system. In this study, we conducted a variety of experiments to look at both the overhead imposed by containers and the latency experienced in Linux using various combinations of patched OS and containers running on a Raspberry Pi 4. We found that containers have little impact on CPU utilization but do incur penalties in RAM, disk storage, and startup time. We also found the unpatched Linux kernel performs well for real time;and that, while the real-time kernel patch reduces both overall and maximum latency, it can negatively impact performance, particularly on single-core systems running non-real-time tasks. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Linux

来源：评论

学校读者我要写书评

暂无评论

Heterogeneity-aware Personalized Federated Learning via Adaptive Dual-Agent Reinforcement Learning

arXiv

引用

arXiv 2025年

作者： Chen, Xi Li, Qin Cai, Haibin Wang, Ting MoE Engineering Research Center of Software/Hardware Co-design Technology and Application Shanghai Key Laboratory of Trustworthy Computing East China Normal University Shanghai200062 China

Federated Learning (FL) empowers multiple clients to collaboratively train machine learning models without sharing local data, making it highly applicable in heterogeneous Internet of Things (IoT) environments. However, intrinsic heterogeneity in clients’ model architectures and computing capabilities often results in model accuracy loss and the intractable straggler problem, which significantly impairs training effectiveness. To tackle these challenges, this paper proposes a novel Heterogeneity-aware Personalized Federated Learning method, named HAPFL, via multi-level Reinforcement Learning (RL) mechanisms. HAPFL optimizes the training process by incorporating three strategic components: 1) An RL-based heterogeneous model allocation mechanism. The parameter server employs a Proximal Policy Optimization (PPO)-based RL agent to adaptively allocate appropriately sized, differentiated models to clients based on their performance, effectively mitigating performance disparities. 2) An RL-based training intensity adjustment scheme. The parameter server leverages another PPO-based RL agent to dynamically fine-tune the training intensity for each client to further enhance training efficiency and reduce straggling latency. 3) A knowledge distillation-based mutual learning mechanism. Each client deploys both a heterogeneous local model and a homogeneous lightweight model named LiteModel, where these models undergo mutual learning through knowledge distillation. This uniform LiteModel plays a pivotal role in aggregating and sharing global knowledge, significantly enhancing the effectiveness of personalized local training. Experimental results across multiple benchmark datasets demonstrate that HAPFL not only achieves high accuracy but also substantially reduces the overall training time by 20.9%-40.4% and decreases straggling latency by 19.0%-48.0% compared to existing solutions. © 2025, CC BY.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

LarTap: A Luminance-aware Framework with Text-correlation Priors for Multi-Exposure Image Fusion

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Wang, Enlong Li, Jiawei Yan, Tiantian Lei, Jia Zhou, Shihua Wang, Bin Liu, Jinyuan Kasabov, Nikola K. Dalian University Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education School of Software Engineering Dalian116622 China University of the Science and Technology Beijing School of Computer and Communication Engineering Beijing100083 China Xi’an Jiaotong University School of Software Engineering Shaanxi Xi’an710049 China Dalian Univer sity of Technology School of Mechanical Engineering Dalian116024 China Auckland University of Technology Knowledge Engineering and Discovery Research Institute Auckland1061 New Zealand

Conventional imaging devices often struggle to produce high-dynamic-range (HDR) images that accurately represent natural scenes. To overcome this limitation, multi-exposure image fusion (MEF) techniques have been introduced as a viable solution. Existing MEF approaches aim to enhance performance by optimizing or searching architectures. However, they face challenges in precise feature extraction and scene reconstruction, leading to distortion in the fused images. Additionally, most methods do not adequately address luminance variations across different image regions, which may result in the loss of essential details. To address these challenges, we present a novel luminance-aware MEF framework that integrates text-correlation priors (LarTap). By embedding textual information into fusion process, the proposed framework enhances content extraction and comprehension. Specifically, it consist of two key components: the text-image correlation network (N1) and the multi-exposure fusion network (N2). First, N1 performs correlation training to achieve a holistic alignment between text and image pairs. Its iterative vision encoders (VEs) generate text-correlated prior knowledge to facilitate the fusion process in N2. Second, N2 leverages these priors for scene reconstruction and dynamically adjusts luminance based on comparative perception. Extensive experiments on multiple datasets demonstrate that LarTap outperforms state-of-the-art methods. © 1991-2012 IEEE.

关键词： Image correlation

来源：评论

学校读者我要写书评

暂无评论

Learning with Open-world Noisy Data via Class-independent Margin in Dual Representation Space

arXiv

引用

arXiv 2025年

作者： Pan, Linchao Gao, Can Zhou, Jie Wang, Jinbao College of Computer Science and Software Engineering Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China

Learning with Noisy Labels (LNL) aims to improve the model generalization when facing data with noisy labels, and existing methods generally assume that noisy labels come from known classes, called closed-set noise. However, in real-world scenarios, noisy labels from similar unknown classes, i.e., open-set noise, may occur during the training and inference stage. Such open-world noisy labels may significantly impact the performance of LNL methods. In this study, we propose a novel dual-space joint learning method to robustly handle the open-world noise. To mitigate model overfitting on closed-set and open-set noises, a dual representation space is constructed by two networks. One is a projection network that learns shared representations in the prototype space, while the other is a One-Vs-All (OVA) network that makes predictions using unique semantic representations in the class-independent space. Then, bi-level contrastive learning and consistency regularization are introduced in two spaces to enhance the detection capability for data with unknown classes. To benefit from the memorization effects across different types of samples, class-independent margin criteria are designed for sample identification, which selects clean samples, weights closed-set noise, and filters open-set noise effectively. Extensive experiments demonstrate that our method outperforms the state-of-the-art methods and achieves an average accuracy improvement of 4.55% and an AUROC improvement of 6.17% on CIFAR80N. Copyright © 2025, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Big-Moe: Bypassing Isolated Gating For Generalized Multimodal Face Anti-Spoofing

Big-Moe: Bypassing Isolated Gating For Generalized Multimoda...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Yingjie Ma Zitong Yu Xun Lin Weicheng Xie Linlin Shen College of Computer Science and Software Engineering Shenzhen University Great Bay University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Provincial Key Laboratory of Intelligent Information Processing

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

In the domain of facial recognition security, multimodal Face Anti-Spoofing (FAS) is essential for countering presentation attacks. However, existing technologies encounter challenges due to modality biases and imbalances, as well as domain shifts. Our research introduces a Mixture of Experts (MoE) model to address these issues effectively. We identified three limitations in traditional MoE approaches to multimodal FAS: (1) Coarse-grained experts’ inability to capture nuanced spoofing indicators; (2) Gated networks’ susceptibility to input noise affecting decision-making; (3) MoE’s sensitivity to prompt tokens leading to overfitting with conventional learning methods. To mitigate these, we propose the Bypass Isolated Gating MoE (BIG-MoE) framework, featuring: (1) Fine-grained experts for enhanced detection of subtle spoofing cues; (2) An isolation gating mechanism to counteract input noise; (3) A novel differential convolutional prompt bypass enriching the gating network with critical local features, thereby improving perceptual capabilities. Extensive experiments on four benchmark datasets demonstrate significant generalization performance improvement in multimodal FAS task. The code is released at https://***/murInJ/BIG-MoE.

关键词： Convolutional codes Sensitivity Convolution Face recognition Noise Logic gates Feature extraction Security Speech processing Overfitting

来源：评论

学校读者我要写书评

暂无评论

High-Fidelity Editable Portrait Synthesis with 3D GAN Inversion

High-Fidelity Editable Portrait Synthesis with 3D GAN Invers...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Jindong Xie Jiachen Liu Yupei Lin Jinbao Wang Xianxu Hou Linlin Shen Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University School of Information Engineering Guangdong University of Technology Guangzhou China Guangdong Provincial Key Laboratory of Intelligent Information Processing School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

The 3D generative adversarial network (GAN) inversion converts an image into 3D representation to attain high-fidelity reconstruction and facilitate realistic image manipulation within the 3D latent space. However, previous approaches face challenges regarding the trade-off between the reconstruction ability and editability. That is, reversing a real-world image to a low-dimensional latent code would inevitably lead to information loss, and achieving a near-perfect reconstruction using high-rate triplane representation often limits the ability to manipulate the image freely in the latent space. To address these issues, we propose a novel latent conditioning encoder-based framework with the alignment between the low-dimensional latent and high-dimensional triplane. A non-semantic guided editing strategy bridges the intrinsic relation between the latent condition and triplane generation, making it possible to edit the high-dimensional representation by latent manipulation. As a result, our method can achieve high-fidelity reconstruction and editing simultaneously by directly controlling the latent code. Experimental results demonstrate that our approach excels in reconstruction and editing quality compared to previous 3D inversion methods. Furthermore, our method can also edit even real faces with large poses and out-of-domain cases.

关键词： Bridges Three-dimensional displays Codes Signal processing Generative adversarial networks Vectors Acoustics Speech processing Image reconstruction Faces

来源：评论

学校读者我要写书评

暂无评论

The Impact of Transformer Models and Regression Algorithms on Automated Short Answer Grading

The Impact of Transformer Models and Regression Algorithms o...

引用

Advances in Electrical, computing, Communication and Sustainable Technologies (ICAECT), International Conference on

作者： Abhijith. N. Nampoothiri M. G. Thushara Pradeesh. N Anand Krishna K. R Abhai Santhosh Abhijith Kumar S Suryan Kumar Department of Computer Science and Applications Amrita School of Computing Amrita Vishwa Vidyapeetham Amritapuri India Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Amritapuri India Omnex Software Solutions Pvt. Ltd Chennai India

ISBN: (数字)9798350356236

ISBN: (纸本)9798350356243

Grading short answer questions in higher education often poses significant challenges due to its subjective nature and time-consuming process. As educational institutions expand, the need for efficient and objective grading solutions becomes critical. This paper investigates the use of machine learning and natural language processing to automate the evaluation of short answer responses. Our study employs a two-phase methodology: first, several transformer models—including BERT, Sentence-BERT, T5, Genism, and XLNet—are used to transform text into numerical representations. In the second phase, various regression techniques, such as Linear Regression, Support Vector Machine (SVM), Random Forest, and AdaBoost, are applied to these representations to estimate scores. Our findings indicate that the combination of the BERT model with Random Forest performs the best, demonstrating superior accuracy with the lowest error metrics. This optimal model pairing is proposed for integration into the Ample Learning Management System (LMS) to enhance grading efficiency and provide quicker, more reliable feedback. The significant implications of this research provides teachers with a robust tool for automated grading, which can enhance the educational experience by delivering timely and accurate evaluations.

关键词： Support vector machines Measurement Accuracy Education Forestry Transforms Transformers Numerical models Reliability Random forests

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：