检索结果-内蒙古大学图书馆

Automatic Timbre Transformation using Enhanced Diffusion Model

IEEE Access 2025年 13卷 91642-91654页

作者： Wu, Cheng-Han Cheewaprakobkit, Pimpa Shih, Timothy K. Lin, Yu-Cheng Liu, Bing-Ze National Central University Department of Computer Science and Information Engineering Taoyuan City32001 Taiwan Asia Pacific International University Faculty of Information Technology Saraburi18180 Thailand Yuan-Ze University Department of Computer Science and Engineering Taoyuan City32003 Taiwan

We present a novel timbre transfer model that uses an enhanced diffusion architecture to convert music from various instruments into Erhu timbre. The Erhu, a traditional Chinese instrument, is difficult to simulate due to its rich vibrato and smooth note transitions. Existing Musical Instrument Digital Interface systems struggle to capture its nuanced dynamics. Our model integrates a Pitch Encoder, a Loudness Encoder, and a Diffusion Decoder. The encoders extract pitch features and dynamic loudness variations, guiding the decoder in generating realistic Erhu timbre. By extracting general musical features, the system generalizes to unseen input types without retraining. Evaluations based on pitch accuracy, cosine similarity, and Fréchet Audio Distance show that our model achieves 96% pitch accuracy and high fidelity in Erhu timbre reproduction. This study demonstrates the potential of diffusion-based timbre transfer models in music generation and provides new directions for future work on both music generation and timbre transfer. © 2013 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Approaches in Cybersecurity to Enhance Security in Future Network Technologies

引用

SN computer Science 2025年第4期6卷 1-18页

作者： Ahmad, Sultan Haque, Md. Alimul Abdeljaber, Hikmat A. M. Eljialy, A.E.M. Nazeer, Jabeen Mishra, B.K. Department of Computer Science College of Computer Engineering and Sciences Prince Sattam Bin Abdulaziz University Alkharj 11942 Saudi Arabia University Center for Research and Development (UCRD) Department of Computer Science and Engineering Chandigarh University Mohali Punjab Gharuan 140413 India Department of Computer Science Veer Kunwar Singh University Bihar Ara India Department of Computer Science Faculty of Information Technology Applied Science Private University Amman Jordan MEU Research Unit Middle East University Amman 11831 Jordan Department of Information Systems College of Computer Engineering and Sciences Prince Sattam Bin Abdulaziz University Alkharj 11942 Saudi Arabia Department of Physics Veer Kunwar Singh University Ara 802301 India

As technology continues to evolve rapidly, cybersecurity has become a critical global concern. The increasing sophistication of cyber threats poses significant risks to individuals, businesses, and governments. To combat these threats, cybersecurity tools play a crucial role in monitoring, detecting, and mitigating security risks in digital environments. These tools ensure data protection, prevent unauthorized access, and safeguard sensitive information. However, traditional cybersecurity approaches are struggling to keep pace with emerging cyber-attacks. In response, machine learning (ML) has emerged as a powerful solution for enhancing cybersecurity strategies. ML algorithms enable organizations to analyze large datasets, identify anomalies, and predict potential threats with greater accuracy. Cybersecurity tools, integrated with ML, act as the final line of defense against attacks such as data breaches, identity theft, and system intrusions. This research explores the application of ML in selecting and optimizing cybersecurity models for enterprise ICT systems. It also emphasizes the growing demand for skilled professionals who can develop and implement ML-based security solutions. By examining current trends and future possibilities, this study provides valuable insights into the role of ML in strengthening cybersecurity measures and enhancing overall digital protection for organizations worldwide. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Cyber security Cybercrime Data analysis ML algorithms Network security Threats

来源：评论

学校读者我要写书评

暂无评论

Multimodal Representation Learning Based on Personalized Graph-Based Fusion for Mortality Prediction Using Electronic Medical Records

引用

Big Data Mining and Analytics 2025年第4期8卷 933-950页

作者： Al-Dailami, Abdulrahman Kuang, Hulin Wang, Jianxin School of Computer Science and Engineering Central South University Hunan Provincial Key Lab on Bioinformatics Changsha410083 China Sana'a University Faculty of Computer and Information Technology Sana'a999101 Yemen

Predicting mortality risk in the Intensive Care Unit (ICU) using Electronic Medical Records (EMR) is crucial for identifying patients in need of immediate attention. However, the incompleteness and the variability of EMR features for each patient make mortality prediction challenging. This study proposes a multimodal representation learning framework based on a novel personalized graph-based fusion approach to address these challenges. The proposed approach involves constructing patient-specific modality aggregation graphs to provide information about the features associated with each patient from incomplete multimodal data, enabling the effective and explainable fusion of the incomplete features. Modality-specific encoders are employed to encode each modality feature separately. To tackle the variability and incompleteness of input features among patients, a novel personalized graph-based fusion method is proposed to fuse patient-specific multimodal feature representations based on the constructed modality aggregation graphs. Furthermore, a MultiModal Gated Contrastive Representation Learning (MMGCRL) method is proposed to facilitate capturing adequate complementary information from multimodal representations and improve model performance. We evaluate the proposed framework using the large-scale ICU dataset, MIMIC-III. Experimental results demonstrate its effectiveness in mortality prediction, outperforming several state-of-the-art methods. © 2018 Tsinghua University Press.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

MAVEN: Multi-modal Attention for Valence-Arousal Emotion Network

arXiv

引用

arXiv 2025年

作者： Ahire, Vrushank Shah, Kunal Khan, Mudasir Nazir Pakhale, Nikhil Sookha, Lownish Rai Ganaie, M.A. Dhall, Abhinav Department of Computer Science and Engineering Indian Institute of Technology Punjab Ropar India Faculty of Information Technology Monash University Melbourne Australia

—This paper introduces MAVEN (Multi-modal Attention for Valence-Arousal Emotion Network), a novel architecture for dynamic emotion recognition through dimensional modeling of affect. The model uniquely integrates visual, audio, and textual modalities via a bi-directional cross-modal attention mechanism with six distinct attention pathways, enabling comprehensive interactions between all modality pairs. Our proposed approach employs modality-specific encoders to extract rich feature representations from synchronized video frames, audio segments, and transcripts. The architecture’s novelty lies in its cross-modal enhancement strategy, where each modality representation is refined through weighted attention from other modalities, followed by self-attention refinement through modality-specific encoders. Rather than directly predicting valence-arousal values, MAVEN predicts emotions in a polar coordinate form, aligning with psychological models of the emotion circumplex. Experimental evaluation on the Aff-Wild2 dataset demonstrates the effectiveness of our approach, with performance measured using Concordance Correlation Coefficient (CCC). The multistage architecture demonstrates superior ability to capture the complex, nuanced nature of emotional expressions in conversational videos, advancing the state-of-the-art (SOTA) in continuous emotion recognition in-the-wild. Code can be found at: https://***/Vrushank-Ahire/MAVEN_8th_ABAW. © 2025, CC BY.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Synergizing vision transformer with ensemble of deep learning model for accurate kidney stone detection using CT imaging

引用

Alexandria engineering Journal 2025年 127卷 357-373页

作者： Alzughaibi, Arwa Alanazi, Adwan A. Alshahrani, Mohammed Hilali Jaghdam, Ines Hassaballa, Abaker A. Applied college Taibah University Madinah Saudi Arabia Department of Computer Science and Information College of Computer Science and Engineering University of Hail Hail Saudi Arabia Department of Computer Sciences Applied College Najran University Najran66462 Saudi Arabia Department of Computer Science and Information Technology Applied College Princess Nourah bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia Center for Scientific Research and Entrepreneurship Northern Border University Arar73213 Saudi Arabia Department of Mathematics Faculty of Science Northern Border University Arar73213 Saudi Arabia

The disease of Kidney stones is a risky disease for individuals all over the world. Many people with kidney stones in the early phase do not detect it as an illness, and it harms the organ gradually. Precise analysis of kidney illness is vital, as it is a major health concern that needs accurate detection for appropriate and effective treatment. CT scans are one of the most extensively accessible imaging models, and they are employed for effective diagnosis. Deep learning (DL) techniques are gradually identified as beneficial tools for analyzing illness in the medical field. However, present techniques employing deep networks often meet low accuracy and overfitting challenges, demanding further alteration for optimum performance. This study presents a Leveraging Flying Foxes Optimization with an Ensemble of Deep Learning for Accurate Kidney Stone Detection (LFFOEDL-AKSD) technique in CT scans. The presented LFFOEDL-AKSD technique mainly focuses on detecting kidney stones using CI imaging. At first, the presented LFFOEDL-AKSD technique applies the pre-processing phase, which involves image resizing for uniform CT scan dimensions and data augmentation through transformations like rotation and flipping to reduce overfitting, sobel filtering (SF) sharpens edges, and the data is separated into training, validation, and testing sets for model development. The presented LFFOEDL-AKSD technique employs the swin transformer (ST) model for the feature extraction method. Furthermore, the majority voting ensemble of three DL approaches, such as the graph convolutional network (GCN), temporal convolutional network (TCN), and three-dimensional convolutional autoencoder (3D-CAE) approaches, are employed to increase the precision and reliability of the kidney stone recognition. Finally, the presented LFFOEDL-AKSD technique implements the flying foxes optimization (FFO) approach for the hyperparameter tuning involved in the ensemble learning models. An extensive experiment is conduct

关键词： Flying foxes optimization Ensemble deep learning Kidney stone detection CI imaging Swin transformer

来源：评论

学校读者我要写书评

暂无评论

What Drives the Use of Generative Artificial Intelligence to Promote Educational Sustainability? Evidence from SEM-ANN Approach

引用

TechTrends 2025年 1-15页

作者： Arpaci, Ibrahim Al-Emran, Mostafa Al-Qaysi, Noor Al-Sharafi, Mohammed A. Management Information Systems College of Business Administration Gulf University for Science and Technology Mishref Kuwait Department of Software Engineering Faculty of Engineering and Natural Sciences Bandirma Onyedi Eylul University Balikesir Turkey Department of Computer Science and Engineering College of Informatics Korea University Seoul 02841 South Korea Faculty of Engineering & IT The British University in Dubai Dubai United Arab Emirates Engineering Technical College Al-Bayan University Baghdad Iraq Information and Communication Technology Research Group Scientific Research Center Al-Ayen University Thi-Qar Iraq IRC for Finance and Digital Economy KFUPM Business School King Fahd University of Petroleum & Minerals Dhahran Saudi Arabia

The literature on generative “Artificial Intelligence” (AI) in education primarily focuses on its immediate benefits and applications, such as personalized learning, student engagement, and content generation. However, there is a notable absence of empirical research concerning the holistic use of generative AI within educational institutions and its long-term impact on educational sustainability. This study investigates the factors that predict the use of generative AI and its subsequent influence on educational sustainability. This study enhanced the extended “Unified Theory of Acceptance and Use of technology” (UTAUT-2) by including personal innovativeness as an external variable and educational sustainability as an outcome. A hybrid methodology, integrating “Structural Equation Modeling” (SEM) and “Artificial Neural Network” (ANN), was used to evaluate the research model using data collected from 1,011 university students. The SEM analysis confirmed all hypotheses. Specifically, a positive relationship was found between use behavior and educational sustainability. These results show that the combined variables collectively account for 63% and 66% of the variance in use behavior and educational sustainability, respectively. The sensitivity analysis identified habit as the most important predictor of use behavior. The findings offer both theoretically important and practically valuable implications for designing user-centered AI integration in education. © Association for Educational Communications & technology 2025.

关键词： Artificial intelligence Educational sustainability SEM-ANN UTAUT-2

来源：评论

学校读者我要写书评

暂无评论

Selfish-Free Influential Nodes Detection in Mobile Social Networks

Selfish-Free Influential Nodes Detection in Mobile Social Ne...

引用

Advanced Innovations in Smart Cities (ICAISC), International Conference on

作者： Doaa AbdelMohsen Tamer Abdelkader Mohamed Hamdy Khaled ElBahnasy Faculty of Computer and Information Sciences Ain Shams University Cairo Egypt Faculty of Computer Science and Engineering Galala Unversity Suez Egypt Faculty of Computing and Information Technology King Abdul Aziz University Jeddah International College KSA

ISBN: (数字)9798331506995

ISBN: (纸本)9798331507008

Mobile networks where users group in communities based on their interests, and disseminate data mainly to their community using their mobile devices, are called Mobile Social Networks (MSN). However, the efficiency of data dissemination becomes a challenging problem in these networks. Using influential users can improve the efficiency of data dissemination. An influential user should have an effective activity on the network and influence other users. The participation behavior of nodes in the network dramatically affects the detection process of influential nodes. Self-sufficient nodes who selectively participate in the dissemination of data in the network may reduce the influence of the other nodes. This paper proposes detecting influential nodes that consider the negative effects of selfish behavior. The performance analysis of the proposed selfish-free influential node detection protocol is presented by comparing it to another one that does not consider the selfishness problem. This comparison shows that the proposed protocol achieves efficiency up to 30% in a environment of selfish behavior.

关键词： Performance evaluation Technological innovation Protocols Social networking (online) Smart cities Data dissemination Mobile handsets Performance analysis Mobile ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Android Malware Detection via Hybrid Lion-Bee Optimization with Bi-Directional Recurrent Neural Network 3

Android Malware Detection via Hybrid Lion-Bee Optimization w...

引用

3rd International Conference on Integrated Circuits and Communication Systems, ICICACS 2025

作者： Rajeyyagari, Sivaram Elfaki, Mohamed Ahmed Rashid, Khan Asif Bala, B. Kiran Reyad, Omar College of Computing and Information Technology Shaqra University Department of Computer Science Shaqra Saudi Arabia K.Ramakrishnan College of Engineering Department of Ai and Ds Trichy India College of Computing and Information Technology Shaqra University Shaqra Saudi Arabia Faculty of Computers and Artificial Intelligence Sohag University Sohag Egypt

ISBN: (纸本)9798331508456

The number of malicious programs that target the Android OS has significantly expanded with the rise in mobile device usage. It is crucial to identify, prevent, and defeat Android malware assaults since they have long presented a severe threat to Android apps. The emergence of secure Android app ecosystem depends on recognizing and classifying harmful applications into groups are similar to another. Malware families can be categorized in order to recognize harmful activity and to systematically spot dangerous-patterns. Thus, the study suggests a hybrid strategy that combines the attributes discovered from doing static and dynamic malware assessment for enhanced identification and categorization of Android malware. This method more effectively addresses the issue of studying, identifying Android malware. The feature extracted from image sections utilizing the hybrid lion and artificial bee colony (HL-ABC) optimization. RNN were used to classify the retrieved features. Each segment of a malware image file served as a test case for the categorization performance. This is contrasted with other current ways to show the effectiveness of the suggested strategy. Comparing the suggested model to other approaches, the study's findings demonstrate its effectiveness in identifying and classifying Android malware. © 2025 IEEE.

关键词： Android malware

来源：评论

学校读者我要写书评

暂无评论

RAFA-Net: Region Attention Network for Food Items and Agricultural Stress Recognition

IEEE Transactions on AgriFood Electronics

引用

IEEE Transactions on AgriFood Electronics 2025年第1期3卷 121-133页

作者： Bera, Asish Krejcar, Ondrej Bhattacharjee, Debotosh Birla Institute of Technology and Science Department of Computer Science and Information Systems Pilani333031 India University of Hradec Kralove Center for Basic and Applied Science Faculty of Informatics and Management Hradec Kralove50003 Czech Republic Skoda Auto University Mlada Boleslav29301 Czech Republic Universiti Teknologi Malaysia Malaysia Japan International Institute of Technology Kuala Lumpur81310 Malaysia Jadavpur University Department of Computer Science and Engineering Kolkata700032 India

Deep convolutional neural networks (CNNs) have facilitated remarkable success in recognizing various food items and agricultural stress. A decent performance boost has been witnessed in solving the agro-food challenges by mining and analyzing region-based partial feature descriptors. Also, computationally expensive ensemble learning schemes fusing multiple CNNs have been studied in earlier works. This work proposes a region attention scheme for modeling long-range dependencies by building a correlation among different regions within an input image. The attention method enhances feature representation by learning the usefulness of context information from complementary regions. Spatial pyramidal pooling and average pooling pairs aggregate partial descriptors into a holistic representation. Both pooling methods establish spatial and channelwise relationships without incurring extra parameters. A context gating scheme is applied to refine the descriptiveness of weighted attentional features, which is relevant for classification. The proposed region attention network for food items and agricultural stress recognition method, dubbed RAFA-Net, has been experimented on three public food datasets, and has achieved state-of-the-art performances with distinct margins. The highest top-1 accuracy of RAFA-Net is 91.69%, 91.56%, and 96.97% on the UECFood-100, UECFood-256, and MAFood-121 datasets, respectively. In addition, better accuracies have been achieved on two benchmark agricultural stress datasets. The best top-1 accuracies on the Insect Pest (IP-102) and PlantDoc-27 plant disease datasets are 92.36%, and 85.54%, respectively;implying RAFA-Net's generalization capability. © 2023 IEEE.

关键词： Plant diseases

来源：评论

学校读者我要写书评

暂无评论

C2PD: Continuity-Constrained Pixelwise Deformation for Guided Depth Super-Resolution

arXiv

引用

arXiv 2025年

作者： Kang, Jiahui Cai, Qing Tan, Runqing Liu, Yimei Liu, Zhi Faculty of Computer Science and Technology Ocean University of China China School of Information Science and Engineering Shandong University China

Guided depth super-resolution (GDSR) has demonstrated impressive performance across a wide range of domains, with numerous methods being proposed. However, existing methods often treat depth maps as images, where shading values are computed discretely, making them struggle to effectively restore the continuity inherent in the depth map. In this paper, we propose a novel approach that maximizes the utilization of spatial characteristics in depth, coupled with human abstract perception of real-world substance, by transforming the GDSR issue into deformation of a roughcast with ideal plasticity, which can be deformed by force like a continuous object. Specifically, we firstly designed a cross-modal operation, Continuity-constrained Asymmetrical Pixelwise Operation (CAPO), which can mimic the process of deforming an isovolumetrically flexible object through external forces. Utilizing CAPO as the fundamental component, we develop the Pixelwise Cross Gradient Deformation (PCGD), which is capable of emulating operations on ideal plastic objects (without volume constraint). Notably, our approach demonstrates state-of-the-art performance across four widely adopted benchmarks for GDSR, with significant advantages in large-scale tasks and generalizability. Copyright © 2025, The Authors. All rights reserved.

关键词： Pixels

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：