检索结果-内蒙古大学图书馆

Human-computer Interaction, Optimization and Robotic Applications (HORA), International Congress on

作者： Mohammad Ibrhaim Al Karaki Ihab Elaff Computer Engineering Üsküdar University Istanbul Turkey Computer Science and Engineering Qatar University Doha Qatar Computer Engineering Uskudar University Istanbul Turkey

ISBN: (数字)9798331510886

ISBN: (纸本)9798331510893

This study presents a new method for computational auditory systems that models humanoid robot audition for determining the direction of a sound source and integrates it into the Arslan humanoid robot. It does this by employing artificial neural networks. With an emphasis on precision and flexibility, the study provides a workable answer for real-world applications. The encouraging outcomes confirm the system's approach's efficacy and its potential for practical uses. In order to get greater precision and flexibility in practical applications, the study also tackles some constraints. The outcomes show encouraging accuracy rates for a range of sample sizes, highlighting the suggested method's scalability and dependability.

关键词： Location awareness Industries Accuracy Service robots Computational modeling Scalability Humanoid robots Artificial neural networks Standards Optimization

来源：评论

学校读者我要写书评

暂无评论

Optimizing Diabetic Kidney Disease Diagnosis with Machine Learning: A Novel Approach

Optimizing Diabetic Kidney Disease Diagnosis with Machine Le...

引用

International Conference on Electronics, Materials engineering and Nano-Technology (IEMENTech)

作者： Vinitha G Bandi Rambabu Sathish Kumar P. J Surendran R K S. Balamurugan Department of Computer Science and Engineering Karpaga Vinayaga College of Engineering and Technology Chengalpattu Tamil Nadu India Department of Computer Science and Engineering CVR College of Engineering Hyderabad India Department of Computer Science and Engineering Panimalar Engineering College Chennai India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India

ISBN: (数字)9798331520762

ISBN: (纸本)9798331520779

Diabetic kidney disease (DKD) is a diabetic condition in which elevated blood sugar levels harm the kidney's filtering units, leading to kidney damage and potentially, kidney failure. About 700 million people effected by Diabetic Kidney Disease of whom approximately four million patients require kidney replacement therapy (KRT). The existing methods for predicting Diabetic Kidney Disease (DKD) have several drawbacks that limit their effectiveness and accuracy. Current models often rely on traditional biomarkers, such as blood glucose and urine albumin levels, which can be insufficient for early detection as they typically indicate kidney damage only after it has progressed. Proposed a novel technique by utilizing machine learning algorithm such as navie Bayes to predict the DKD in early stage leads to decrease the mortality rate. Proposed invention enhances the accuracy in disease diagnosis, which result in the score of 96.03, 94.03, 95.08 and 95.09 with precision, accuracy recall and F1-Score respectively.

关键词： Accuracy Mortality Machine learning Predictive models Data models Diabetes Glucose Medical diagnosis Kidney Diseases

来源：评论

学校读者我要写书评

暂无评论

GAN inversion and shifting: recommending product modifications to sellers for better user preference

引用

PeerJ computer science 2025年 11卷 e2553-e2553页

作者： Kumar, Satyadwyoom Sharma, Abhijith Narayan, Apurva Computer Science Netaji Subhas Institute of Technology Delhi New Delhi India Electrical and Computer Engineering University of Waterloo WaterlooON Canada Computer Science University of Western Ontario LondonON Canada

In efforts to better accommodate users, numerous researchers have endeavored to model customer behavior, seeking to comprehend how they interact with diverse items within online platforms. This exploration has given rise to recommendation systems, which utilize customer similarity with other customers or customer-item interactions to suggest new items based on the existing item catalog. Since these systems primarily focus on enhancing customer experiences, they overlook providing insights to sellers that could help refine the aesthetics of their items and increase their customer coverage. In this study, we go beyond customer recommendations to propose a novel approach: suggesting aesthetic feedback to sellers in the form of refined item images informed by customer-item interactions learned by a recommender system from multiple consumers. These images could serve as guidance for sellers to adapt existing items to meet the dynamic preferences of multiple users simultaneously. To evaluate the effectiveness of our method, we design experiments showcasing how changing the number of consumers and the class of item image used affect the change in preference score. Through these experiments, we found that our methodology outperforms previous approaches by generating distinct, realistic images with user preference higher by 16.7%, thus bridging the gap between customer-centric recommendations and seller-oriented feedback. Copyright 2025 Kumar et al. Distributed under Creative Commons CC-BY 4.0

关键词： Gallium nitride

来源：评论

学校读者我要写书评

暂无评论

Bill safe: intelligent forgery detection with CNN and upgrade sand cat swarm optimization

引用

Discover Computing 2025年第1期28卷 1-26页

作者： Chakraborty, Debjani Computer Science and Engineering Narula Institute of Technology West Bengal Kolkata India

In recent days, there’s been a rise in billing fraud, including invoice fraud, credit card fraud, and online payment fraud, with fraudsters using various tactics to trick individuals and businesses. While the security methods are often fails to address high-speed digital forgery techniques. To address this limitation in this research we present an advanced approach for detecting tampering and preventing forgery in customers retail billing and receipts using the AI tool such as convolutional neural networks (CNN), updated sand cat swarm optimization (USCSO) and gray-level co-occurrence matrix (GLCM). The utilization of the CNN hyperparameter tuning with USCSO, that outperforming standard optimizations like Adam and SGD. With the use of feature extraction, classification, and image preparation (such as skeletonization, color conversion, and scaling), the approach can accurately differentiate between authentic and fraudulent documents. The model’s resilience to various document type and forgery tactics is confirmed by extensive testing on the SROIE dataset and a private dataset of 5000 images. A CNN, optimized by USCSO, classifies these features, achieving 97.1% accuracy, 97.3% precision, and 97.5% recall in detecting fake text, outperforming traditional CNN and SVM techniques. © The Author(s) 2025.

关键词： Convolutional neural network (CNN) Customer retail bill Forgery Sand cat swarm optimization (SCSO) Tamper detection

来源：评论

学校读者我要写书评

暂无评论

HASTIKA: hate speech and target identification in Kannada-English code-mixed text

引用

Language Resources and Evaluation 2025年 1-46页

作者： Kavatagi, Sanjana Rachh, Rashmi Department of Computer Science and Engineering Visvesvaraya Technological University Karnataka Belagavi India

In the modern era, the widespread use of social media has facilitated connections among millions of people worldwide. However, these platforms have also been exploited for spreading hate speech, particularly in multilingual contexts. The informal nature of these platforms enables the use of regional languages, leading to code-mixed text. While this linguistic flexibility fosters freedom of expression, it also contributes to the rampant spread of hate speech, posing significant societal challenges. Identifying hate speech in low-resource Kannada-English code-mixed text is challenging due to the scarcity of annotated corpora. To address this gap, the authors introduce HASTIKA (Hate Speech and Target Identification in Kannada-English Code-Mixed Text), a gold-standard corpus specifically designed for hate speech detection and target identification. It consists of 8,058 YouTube comments, annotated for binary classification “Hate" and “Non-hate" and fine-grained categorization into “Gender", “Political", “Religion", “Geo-political", “Violence", and “Others", marking a significant contribution as the first dataset exclusively tailored for this purpose. Topic modeling techniques were applied to uncover latent themes. Benchmark experiments show that fastText, which captures word-level features, achieves 0.7529 accuracy for binary classification and 0.6042 for multi-class classification, while BERT, excelling in sentence-level feature extraction, attains 0.8054 and 0.6819 accuracy, respectively. This research provides a foundational resource for hate speech detection in Kannada-English code-mixed text and underscores the importance of linguistic and contextual information in developing robust classification models. © The Author(s), under exclusive licence to Springer Nature B.V. 2025.

关键词： Code-mixing Corpus building Hate speech Kannada-English code-mixed text Low resource Social networks

来源：评论

学校读者我要写书评

暂无评论

Automated Seizure Detection and Diagnosis using Cascaded Reflection Equivariant Visual Attention Quantum Neural Network with Dung Beetle Optimization Algorithm Applied to EEG Signals 3

Automated Seizure Detection and Diagnosis using Cascaded Ref...

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： Jagadeeswari, B. Ranjitham, G. Parida, Prasanta Kumar Guganathan, L. Bengalur, Megha D. Bharath Institute of Higher Education and Research Department of Computer Science and Engineering Tamil Nadu Chennai India Sri Krishna College of Engineering and Technology Department of Electronics and Communication Engineering Tamil Nadu Coimbatore India Kiit University School of Rural Management Odisha Bhubaneswar India Saveetha School of Engineering Department of Physics Thandalam Tamil Nadu Chennai India Presidency University Department of Computer Science and Engineering Karnataka Bengaluru India

ISBN: (纸本)9798331509675

Automated seizure detection and diagnosis for EEG signals refers to using deep learning algorithms and computational methods to analyze electroencephalogram data, identifying patterns that indicate epileptic seizures. We can assert that these systems speed up the process of correct diagnosis reducing the differentiation between the seizures and normal brain activity, thus improving the overall clinical work and patients' outcomes. Conventional techniques fail to give precise and rapid results relating to complicated patterns of seizures. To address these challenges;this study introduces the Cascaded Reflection Equivariant Visual Attention Quantum Neural Network with Dung Beetle Optimization Algorithm (CasREVAQNNet+DBOA) framework for automated seizure detection and diagnosis in EEG signals. The proposed method leverages the CHB-MIT dataset, with initial preprocessing performed using Gradient Domain Guided Filtering (GDGF) to enhance critical EEG patterns. Feature extraction is carried out using DenseNet-121, which facilitates the effective representation of significant EEG characteristics. For classification, the Cascaded Reflection Equivariant Visual Attention Quantum Neural Network (CasREVAQNNet) is utilized, with performance further optimized by the Dung Beetle Optimization Algorithm (DBOA) to ensure accurate and reliable seizure detection (SD). The CasREVAQNNet+DBOA framework is implemented in Python and evaluated on the CHB-MIT dataset. The proposed approach yields excellent outcomes: accuracy of 99.8% and specificity of 98.6% which are significantly higher in contrast to the current techniques. The outcomes of the suggested method enhance accuracy, reduce false detection rates, and accelerate diagnosis, making it a potentially useful tool for reliable and efficient seizure detection in clinical practice. © 2025 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Machine Learning Algorithms for Disease Prediction using Medical Datasets 3

Comparative Analysis of Machine Learning Algorithms for Dise...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Roopa, C. Latha, R.S. Dhavamani, M. Bommisrilekkhaa, G. Angel Shalini, P. Dhanyajothi, R. Department of Computer Science and Engineering Kongu Engineering College Tamilnadu Erode India Department of Artificial Intelligence Kongu Engineering College Tamilnadu Erode India Department of Mathematics Kongu Engineering College Tamilnadu Erode India

ISBN: (纸本)9798331527549

Application of machine learning in the analysis of medical data can be said to be one of the current transformations happening within the healthcare fraternity. This paper highlights several ways in which various machine learning techniques can be used for gaining valuable insight into disparate types of medical data, such as patient records or genetic information, toward further clinical decision-making with a view to better prediction of diseases or strategies related to personalized medicine. The study critically evaluated various algorithms by considering their performances, suitability with regard to certain medical datasets they would be set upon to analyze, and to interpret the performance, particularly within the supervised learning frameworks. It talks about methodologies through which feature selection can take place to make sure that there is effective model development. Consequential applications in early disease detection as well as the optimization of their treatments are further emphasized, representing great potential for massive improvements in their recovery outcomes. The results highlight how far reaching data-driven approaches can affect the future of healthcare. It is envisioned that, with the use of such methods, the paper foresees a paradigm shift in disease diagnosis and treatment for personalized medical care and improved health outcomes. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

3D Physical Layer Secure Transmission for UAV-Assisted Mobile Communications Without Locations of Eavesdroppers 18th

3D Physical Layer Secure Transmission for UAV-Assisted Mobi...

引用

18th International Conference on Wireless Artificial Intelligent Computing Systems and Applications, WASA 2024

作者： Yu, Wenlu Li, Jianqiang Fan, Xin Wang, Guopeng Li, Guangkai Luo, Chuanwen Hong, Yi Chen, Ting School of Information Science and Technology Beijing Forestry University Beijing100083 China National Computer Network Emergency Response Technical Team/Coordination Center of China Beijing100029 China Zhejiang Ocean University Zhoushan316022 China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu611731 China

ISBN: (纸本)9783031714665

The flexibility and cost-effectiveness of unmanned aerial vehicles (UAVs) in a wide range of scenarios have made them indispensable tools for mobile communications. However, UAV communications are also facing increasing security threats, especially in open spaces where they are vulnerable to potential eavesdroppers. In this paper, we employ an extra UAV as a cooperative jammer to enhance UAV-to-ground communication security by sending artificial noise to effectively resist passive eavesdroppers. Unlike previous work, we focus on the dynamic scenario where the source UAV and the ground user move simultaneously. In this scenario, we propose a joint optimization algorithm of trajectory and power for the jamming UAV to obtain the optimal jamming strategy. Due to the absence of eavesdroppers’ locations, the goal of the optimization is to maximize a secure region. Numerical results demonstrate that our optimization algorithm can significantly enlarge the secure region compared to randomly selecting a position of the jamming UAV. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Jamming

来源：评论

学校读者我要写书评

暂无评论

A technical assessment of latent diffusion for Alzheimer's Disease progression

A technical assessment of latent diffusion for Alzheimer's D...

引用

Medical Imaging 2025: Image Processing

作者： McMaster, Elyssa Puglisi, Lemuel Gao, Chenyu Krishnan, Aravind R. Saunders, Adam M. Ravi, Daniele Beason-Held, Lori L. Resnick, Susan M. Zuo, Lianrui Moyer, Daniel Landman, Bennett A. Department of Electrical and Computer Engineering Vanderbilt University NashvilleTN United States Department of Computer Science University of Catania Catania Italy School of Physics Engineering and CS University of Hertfordshire United Kingdom Laboratory of Behavioral Neuroscience National Institute on Aging National Institutes of Health BaltimoreMD United States Department of Computer Science Vanderbilt University NashvilleTN United States

ISBN: (纸本)9781510685901

Latent Diffusion Models (LDMs) introduce exciting opportunities in medical imaging, from disease progression prediction to interpolation to generate entire datasets of rare data. The stochastic nature of generative models makes it challenging to validate their outputs and assess their robustness across diverse datasets. BrLP, a state-of-the-art LDM for T1-weighted (T1w) images that incorporates auxiliary brain volume information, has been evaluated on Alzheimer's Disease (AD) progression, and achieves structural similarity index (SSIM) of 0.91 ± 0.03. In this work, we conducted a pilot study of the BrLP model using the Baltimore Longitudinal Study of Aging (BLSA) dataset. Our objectives are to (1) evaluate the model performance on an external dataset using pretrained image-based and brain image-based metrics such as mean squared error (MSE), similarity index, and mean absolute error (MAE) between conditional and unconditional brain regions;and (2) determine if a harmonization step, in addition to the proposed model's preprocessing steps, is required to improve performance. We found that the BrLP is robust to T1w imaging scanner effects, and harmonization is not required. However, there exists a bias toward a younger population compared to the BLSA cohort (BrLP reported 0.91 ± 0.03 SSIM in a cohort with age range 74 ±7 years;SSIM in our experiment is 0.91 ± 0.03 in cognitively normal subjects with age range 79.47 years ± 7.35 and AD cohort 0.90 ± 0.012 with age range 83.73 years ± 6.01). Interestingly, when the model's input was changed to simulate AD progression instead of normal aging, a higher SSIM of 0.91 ± 0.0012 was achieved compared to a ground truth non-AD scan, suggesting a potential mismatch. However, the resulting lower conditional volume regions function as expected. The model's architecture shows promise for longitudinal T1w imaging studies. © 2025 SPIE.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

Enhancing Forest Image Segmentation in Aerial Images using Deep Learning

引用

Procedia computer science 2025年 258卷 2760-2766页

作者： Manasi pal Mohit Kushwaha Jaytrilok Choudhary Manish Pandey Dhirendra Pratap Singh Department of Computer Science and Engineering MANIT Bhopal Madhya Pradesh India (462003)

Forest cover segmentation is required for monitoring and managing forest ecosystem, yet due to the heterogeneous and complex nature of forest landscape it poses several challenges. This study explores and evaluates the performance of latest deep-learning architectures, focusing on semantic image segmentation using DeepResNet-U architecture. We utilized an extensive dataset of HD aerial images having detailed and diverse forest cover information. After training, testing and validating our model we determined their accuracy and efficiency. A comprehensive analysis demonstrated an impressive performance of DeepResNet-U model with an IoU of 0.7813, dice loss of 0.1229 and overall accuracy of 0.8771. The proposed method turned out to outperform other standard models due to the incorporation of residual connections and hence proved to be a better approach to improve feature extraction and gradient flow.

关键词： DeepResNet-U residual connection aerial imagery forest cover segmentation deforestation

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：