检索结果-内蒙古大学图书馆

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Bourigault, Pauline Mandic, Danilo P. Department of Computing Imperial College London United Kingdom Department of Electronic and Electrical Engineering Imperial College London United Kingdom

ISBN: (纸本)9798350368741

We present a novel approach to anomaly detection by integrating Generalized Hyperbolic (GH) processes into kernel-based methods. The GH distribution, known for its flexibility in modeling skewness, heavy tails, and kurtosis, helps to capture complex patterns in data that deviate from Gaussian assumptions. We propose a GH-based kernel function and utilize it within Kernel Density Estimation (KDE) and One-Class Support Vector Machines (OCSVM) to develop anomaly detection frameworks. Theoretical results confirmed the positive semi-definiteness and consistency of the GH-based kernel, ensuring its suitability for machine learning applications. Empirical evaluation on synthetic and real-world datasets showed that our method improves detection performance in scenarios involving heavy-tailed and asymmetric or imbalanced distributions. https://***/paulinebourigault/GHKernelAnomalyDetect. © 2025 IEEE.

关键词： anomaly detection generalized hyperbolic processes kernel

来源：评论

学校读者我要写书评

暂无评论

XDGesture: An xLSTM-based Diffusion Model for Co-speech Gesture Generation

XDGesture: An xLSTM-based Diffusion Model for Co-speech Gest...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Zhang, Zixing Li, Jiajun Wang, Bin Liu, Yiming Zhao, Huan Schuller, Björn W. College of Computer Science and Electronic Engineering Hunan University China GLAM Department of Computing Imperial College London United Kingdom

ISBN: (纸本)9798350368741

In multimodal human-computer interaction, generating co-speech gestures is crucial for enhancing interaction naturalness and user experience. However, achieving synchronized and natural gesture sequences remains a significant challenge due to the complexity of modeling temporal dependencies across different modalities. Existing methods often rely on simple concatenation techniques, which are limited in effectively handling multimodal information. To address this issue, we propose XDGesture, a diffusion-based framework that integrates a Cross-Modal Fusion module and xLSTM. The Cross-Modal Fusion module efficiently merges information from different modalities, providing the model with rich contextual conditions. Meanwhile, xLSTM, with its enhanced memory structure and exponential gating mechanism, processes the fused multimodal data, capturing long-range dependencies between speech and gestures. This enables the generation of high-quality gesture sequences that are naturally synchronized with speech. Experimental results demonstrate that XDGesture remarkably outperforms existing baselines on multiple datasets, particularly in terms of gesture quality, naturalness, and synchronization with speech. © 2025 IEEE.

关键词： Co-speech gesture generation Diffusion model Multimodal feature fusion xLSTM

来源：评论

学校读者我要写书评

暂无评论

Enhanced Equivalent Circuit Model-Aided Broadband Single-Lossy-Single-Lossless-Layer Rasorber Design with High Selectivity

引用

IEEE Antennas and Wireless Propagation Letters 2025年第5期24卷 1080-1084页

作者： Ai, Junzhuo Hong, Juting Gao, Richard Xian-Ke Liu, Changjun Zhao, Xiang Yan, Liping Sichuan University College of Electronics and Information Engineering Chengdu610065 China Institute of High-Performance Computing A STAR Electronics and Photonics Department 138632 Singapore

This letter presents a novel broadband single-lossy-single-lossless-layer frequency selective rasorber (FSR) with high passband selectivity, facilitated by an enhanced equivalent circuit model (ECM). Leveraging the ECM method for an FSR by substituting typical LC resonant circuits with mixed series-parallel LCL resonant circuits for both the lossy and lossless FSSs, significantly enhances the passband selectivity. The intentionally introduced inductance in the lossy FSS sharpens the passband roll-off, while in the lossless FSS creates an additional transmission zero, further improving selectivity. Simulations reveal a -3 dB passband of 10.04 GHz to 10.56 GHz, with a minimum insertion loss of 0.48 dB at 10.28 GHz. The proposed FSR achieves a 139.4% fractional bandwidth, spanning from 3.61 GHz to 20.22 GHz, and maintains stable performance for both TE and TM polarizations across a wide incidence up to 55°. The agreement between simulation and measurement confirms the practical application potential of the FSR design. © 2002-2011 IEEE.

关键词： Resonant circuits

来源：评论

学校读者我要写书评

暂无评论

Face image authentication scheme based on MTCNN and SLT

引用

Multimedia Tools and Applications 2025年 1-43页

作者： Thabit, Rasha Al-Askari, Mohanad A. Mohammed, Dunya Zeki Anaam, Elham Abdulwahab Mahmood, Zainab H. Jabbar, Dina Jamal Salih, Zahraa Aqeel Information System Department College of Computer Sciences and Information Technology University of Al-Anbar Al-Anbar Iraq Computer Engineering Department College of Engineering Al-Iraqia University Baghdad Iraq Electronic and Communications Engineering Department College of Engineering Gilgamesh University Baghdad Iraq Faculty of Computing and Informatics Multimedia University Selangor Cyberjaya Malaysia Department of Cybersecurity Engineering College of Information Engineering Al-Nahrain University Baghdad Iraq Electrical Engineering Technical Collage Middle Technical University Baghdad Iraq Department of Business Administration Alamaal University College Baghdad Iraq

DeepFakes and face image manipulation methods have been widely distributed in the last few years and several techniques have been presented to check the authenticity of the face image and detect manipulation if exists. Most of the available manipulation detection techniques have been successfully applied to reveal one type of manipulation under specific conditions, however, many limitations and challenges can be encountered in this field. To overcome some limitations and challenges, this paper presents a new face image authentication (FIA) scheme based on Multi-Task Cascaded Conventional Neural Networks (MTCNN) and watermarking in Slantlet transform (SLT) domain. The proposed FIA scheme has three main algorithms that are face detection and selection, embedding, and extraction algorithms. Different block sizes have been used to divide the image into non-overlapping blocks followed by classifying them into two groups that are blocks from face area (FA) and blocks from the remaining area (RA) of the image. In the embedding algorithms, the authentication information is generated from FA blocks and embedded in the RA blocks. In the extraction algorithms, the embedded information is extracted from RA blocks and compared with the calculated data from FA blocks to reveal manipulations and localize the manipulated blocks if exist. Extensive experiments have been conducted to evaluate the performance of the proposed FIA scheme for different face images. The experimental work included tests for payload, capacity, visual quality, time complexity, and localization of manipulations. The results proved the efficiency of the proposed scheme in detecting and localizing different face image manipulations such as attributes attacks, retouching attacks, expression swap, face swap, and morphing attacks. The proposed scheme overcomes many limitations and it is 100% accurate in localizing the tampered blocks which makes it a better candidate for practical applications. © The Author(s), un

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Safe Spaces Analysis for Mental Health 12th

Safe Spaces Analysis for Mental Health

引用

12th International Conference on Recent Trends in computing, ICRTC 2024

作者： Kelawala, Harsh Shah, Zeal Selvaraj, P. Department of Computing Technologies College of Engineering and Technology Faculty of Engineering and Technology SRM Institute of Science and Technology Kattankulathur 603203 India

ISBN: (纸本)9789819789450

Mental health is a paramount concern in contemporary urban environments, necessitating comprehensive approaches to understanding its determinants and formulating effective interventions. This research project adopts a multifaceted methodology to explore the factors influencing mental well-being in urban areas, specifically focusing on cities within Gujarat. By integrating Geographic Information Systems (GIS) technology and predictive modeling techniques, we analyze various socio-environmental factors spanning air quality, noise pollution, green space availability, educational attainment, population density, income levels, and employability. At the same time, the GIS approach encompasses all major cities across India, the Random Forest algorithm is tailored specifically to the cities of Gujarat, reflecting the unique socio-geographical context of the region. Through rigorous data analysis and visualization, we identify spatial patterns and correlations, enabling the identification of areas most vulnerable to mental health challenges and prioritizing targeted interventions. This work presents our research's methodology, findings, and implications, offering valuable insights for policymakers and stakeholders striving to cultivate safe and supportive urban environments conducive to optimal mental health outcomes. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Where Do We Go From Here? Strategies for Expanding Access to Undergraduate engineering in a Post-SFFA Environment

引用

Advances in engineering Education 2025年第3期12卷 7-15页

作者： Berhane, Bruk Slay, Kelly E. Smith, Paige E. School of Universal Computing Construction and Engineering Education STEM Transformation Institute Florida International University United States Peabody College Vanderbilt University United States Women in Engineering University of Maryland United States

来源：评论

学校读者我要写书评

暂无评论

Evolution Analysis of Network Attack and Defense Situation Based on Game Theory

引用

Computers, Materials & Continua 2025年第4期83卷 1475-1494页

作者： Haiyan Sun Chenglong Shao Jianwei Zhang Kun Wang Wanwei Huang College of Software Engineering Zhengzhou University of Light IndustryZhengzhou450007China Intelligent Computing Power Research Department Zhengzhou Xinda Advanced Technology Research InstituteZhengzhou450007China

To address the problem that existing studies lack analysis of the relationship between attack-defense game behaviors and situation evolution from the game perspective after constructing an attack-defense model,this paper proposes a network attack-defense game model(ADGM).Firstly,based on the assumption of incomplete information between the two sides of the game,the ADGM model is established,and methods of payoff quantification,equilibrium solution,and determination of strategy confrontation results are ***,drawing on infectious disease dynamics,the network attack-defense situation is defined based on the density of nodes in various security states,and the transition paths of network node security states are ***,the network zero-day virus attack-defense behaviors are analyzed,and comparative experiments on the attack-defense evolution trends under the scenarios of different strategy combinations,interference methods,and initial numbers are conducted using the NetLogo simulation *** experimental results indicate that this model can effectively analyze the evolution of the macro-level network attack-defense situation from the micro-level attack-defense *** instance,in the strategy selection experiment,when the attack success rate decreases from 0.49 to 0.29,the network destruction rate drops by 11.3%,in the active defense experiment,when the interference coefficient is reduced from 1 to 0.7,the network destruction rate decreases by 7%,and in the initial node number experiment,when the number of initially infected nodes increases from 10 to 30,the network destruction rate rises by 3%.

关键词： Network attack-defense situation evolution zero-day virus NetLogo

来源：评论

学校读者我要写书评

暂无评论

Artificial intelligence-inspired comprehensive framework for desertification prediction

International Journal of Cognitive Computing in Engineering

引用

International Journal of Cognitive computing in engineering 2025年 6卷 462-476页

作者： Alsubai, Shtwai Mosleh, Mogeeb A.A. Al-Hadhrami, Suheer A. Bhatia, Munish College of Computer Engineering and Sciences Prince Sattam bin Abdulaziz University Alkharj Saudi Arabia Faculty of Engineering & Computing University of Science & Technology Aden Yemen Faculty of Engineering and Information Technology Taiz Univeristy Taiz Yemen Department of Computer Engineering College of Engineering Al Mukalla Hadhramout Yemen Department of Computer Applications National Institute of Technology Kurukshetra India

Desertification greatly affects land deterioration, farming efficiency, economic growth, and health, especially in Gulf nations. Climate change has worsened desertification, making developmental issues in the area even more difficult. This research presents an enhanced framework utilizing the Internet of Things (IoT) for ongoing monitoring, data gathering, and analysis to evaluate desertification patterns. The framework utilizes Bayesian Belief Networks (BBN) to categorize IoT data, while a low-latency processing method on edge computing platforms enables effective detection of desertification trends. The classified data is subsequently analyzed using an Artificial Neural Network (ANN) optimized with a Genetic Algorithm (GA) for forecasting decisions. Using cloud computing infrastructure, the ANN-GA model examines intricate data connections to forecast desertification risk elements. Moreover, the Autoregressive Integrated Moving Average (ARIMA) model is employed to predict desertification over varied time intervals. Experimental simulations illustrate the effectiveness of the suggested framework, attaining enhanced performance in essential metrics: Temporal Delay (103.68 s), Classification Efficacy—Sensitivity (96.44 %), Precision (95.56 %), Specificity (96.97 %), and F-Measure (96.69 %)—Predictive Efficiency—Accuracy (97.76 %) and Root Mean Square Error (RMSE) (1.95 %)—along with Reliability (93.73 %) and Stability (75 %). The results of classification effectiveness and prediction performance emphasize the framework's ability to detect high-risk zones and predict the severity of desertification. This innovative method improves the comprehension of desertification processes and encourages sustainable land management practices, reducing the socio-economic impacts of desertification and bolstering at-risk ecosystems. The results of the study hold considerable importance for enhancing regional efforts in combating desertification, ensuring food security, and formulatin

关键词： Life on land Climate action Desertification Internet of things Artificial neural network

来源：评论

学校读者我要写书评

暂无评论

Deep ensemble model for skin cancer classification with improved feature set

引用

Multimedia Tools and Applications 2025年第10期84卷 7599-7626页

作者： Burada, Sreedhar Manjunathswamy, B.E. Kumar, M. Sunil Department of Computer Science and Engineering Don Bosco Institute of Technology Karnataka Bengaluru560074 India Department of Computer Science and Engineering School of Computing Mohan Babu University Sree Vidyanikethan Engineering College Andhra Pradesh Tirupati517102 India

Early identification of skin cancer is mandatory to minimize the worldwide death rate as this disease is covering more than 30% of mortality rates in young and adults. Researchers are in the move of proposing advanced models for the accurate classification of skin disease. This paper introduces a novel skin cancer detection model under the stages of preprocessing, feature extraction, classification as well as segmentation. The given input is first preprocessed via Gaussian filtering. Subsequently, the Deep learning model termed as ‘U-net’ is used for the segmentation process. Afterward, the extraction of the feature set including features like Improved Center symmetric Local Binary Pattern (ICS-LBP), Local Gradient Pattern (LGP), Median binary pattern (MBP) is performed. Classification takes place using Deep Ensemble Model based on the extracted features, that includes BiGRU, Deep Maxout, and Improved Deep Convolutional Neural Network (CNN), respectively. Also, as the hyperparameter tuning of the classification model enhances the performance, this work introduces a new Hybrid Atom and Arithmetic Operation Algorithm (HAAOA) algorithm for tuning the optimal weights of the Bi-GRU (Bi-directional Gated Recurrent Unit) and Deep Maxout model. At last, the validation of the proposed work is performed through different performance measures by comparing it with different algorithms. Accordingly, accuracy of the adopted method at 90th learning percentage is 93.56%, which is (~) 82.63%, 85.15%, 84.98%, 83.66% and 83.42% better than AOA, ASO, BWO, BMO and DO, respectively. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Dynamic Pricing Models in E-Commerce: Exploring Machine Learning Techniques to Balance Profitability and Customer Satisfaction

引用

IEEE Access 2025年 13卷 72994-73002页

作者： Guo, Xiaochen Zhang, Lei Management School of Anhui Business and Technology College Hefei230041 China Anhui Business and Technology College School of Information Engineering Hefei230041 China University of Technology MARA College of Computing Informatics and Mathematics Selangor Shah Alam40450 Malaysia

This research investigates the application of Recurrent Neural Networks (RNNs), specifically Long Short-Term Memory (LSTM) networks, paired with gradient-based optimization techniques for dynamic pricing in e-commerce. The primary objective is to develop a pricing model that effectively balances profitability with customer satisfaction by leveraging sequential data, such as time-series and customer behavior patterns. The approach utilizes LSTM’s ability to capture long-term dependencies in sequential data, while optimization methods like Stochastic Gradient Descent (SGD) enhance model convergence and performance. Key findings include the superior predictive accuracy of LSTM-based models over traditional approaches like Linear Regression and Decision Trees, particularly in real-time data updates and price elasticity scenarios. Additionally, the analysis revealed that LSTM models could efficiently adapt pricing strategies in response to market dynamics, significantly improving profitability while maintaining customer satisfaction. This study provides valuable insights into the application of advanced machine learning techniques in e-commerce pricing. The results suggest that LSTM-based dynamic pricing models could optimize revenue generation, offering substantial implications for pricing strategy development in modern retail environments. Future work may explore hybrid models and multi-objective optimization techniques to further refine these models. © 2013 IEEE.

关键词： User experience

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：