检索结果-内蒙古大学图书馆

2nd International Conference on Applied Algorithms, ICAA 2025

作者： Harshitha, Talluri Simhadri, Tanya Jaswanthi, Thadakuluru Rayvanth, N. Singh, Rimjhim Padam Department of Computer Science and Engineering Amrita School of Computing Bengaluru Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (纸本)9783031845420

With sudden proliferation in evolving Deepfake technology to manipulate media content, identity theft etc., several modern deep learning based solutions are being continuously developed for Deepfake detection, distinguishing the manipulated media. Therefore, the work presented in this paper proposes a novel and real-time MobileNetV3 based Deepfake detection model. With the fine-tuning of MobileNetV3 using additional fully connected layers and self-attention mechanism placed optimally, the proposed model proved effective in concentrating on crucial image regions over relatively lesser important features. The integration of self-attention layers had a direct impact on the model’s capacity to identify the artifacts manipulated during the generation of Deepfakes, thereby, alleviating the detection efficiency. The work also implemented and trained five widely used and recent convolutional models including XceptionNet, InceptionV3, EfficientNetB0, MobileNetV3, and InceptionResNet for best baseline model selection and comparisons against the proposed approach. The proposed model outperformed all other state-of-art models by a margin of 3% with an F-score = 98.46%. The proposed model also has minimalistic memory and time requirements supporting the real-time applicability of the model even on mobile devices. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

MULTISOURCE DUAL UNSUPERVISED DOMAIN ADAPTATION METHOD FOR REMAINING LIFE PREDICTION UNDER MULTIPLE OPERATING CONDITIONS 14

MULTISOURCE DUAL UNSUPERVISED DOMAIN ADAPTATION METHOD FOR R...

引用

14th International Conference on Quality, Reliability, Risk, Maintenance, and Safety engineering, QR2MSE 2024

作者： Zhou, Ningxu Lyu, Yi Shen, Zaichen Xiao, Xu Fan, Ruhui School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China School of Computer University of Electronic Science and Technology of China Zhongshan Institutes Zhongshan China School of Automation Guangdong University of Technology Guangzhou China

ISBN: (纸本)9781837242672

Aero engines, with their complex structures and intricate gas paths, are a crucial component of the aviation system. Traditional machine learning-based methods for predicting the remaining useful life (RUL) of rolling bearings often struggle to provide adequate feature representation and adaptive extraction due to complex operating conditions and challenges in obtaining degradation data. Given that traditional machine learning methods require substantial amounts of labeled data, they frequently fail to yield satisfactory RUL prediction results. To overcome these limitations, domain adaptation methods have been employed, facilitating the transfer of knowledge from a well-labeled source domain to an unlabeled target domain. Additionally, to augment the available data, a multisource domain transfer approach is proposed, which transfers data from multiple source domains to the target domain intended for prediction. To enhance the effectiveness of this multisource domain transfer method, a dual alignment strategy is introduced for aligning features at both the feature and semantic levels, thereby improving predictive performance. The model incorporates a convolutional neural network (CNN) and long short-term memory (LSTM) as its backbone, leveraging CNN's robust feature extraction capabilities combined with LSTM’s proficiency in processing time-dependent data. Experiments conducted on the CMAPSS dataset, along with comparisons and ablation studies against current popular multisource domain adaptation methods, demonstrate the superiority of the proposed approach. © The Institution of engineering & Technology 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Multi-Domain Graph-Enhanced Joint Intent and Slot Learning

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer science 2025年第2期52卷 374-382页

作者： Shi, Wu Yuan, Weihao Wang, Yang Dong, Yindong Xu, Gaojian School of Information and Artificial Intelligence Anhui Agricultural University Hefei230036 China School of Computer Science and Technology Xidian University Xi’an710126 China School of Engineering Anhui Agricultural University Hefei230036 China

Comprehension of spoken language is essential in dialog systems, as it supports two fundamental tasks: intent classification and slot filling. At present, federated modeling methodologies prevail in the domain of spoken language comprehension. Nevertheless, current models encounter constraints in accurately representing the interrelations among activities and utilizing cross-domain semantic data. This study introduces the Multi-Domain Graph-Enhanced Joint Intent and Slot Learning (MDG-JISL) paradigm to tackle these difficulties. MDG-JISL amalgamates a pre-trained BERT model with a self-trained FastText model to create superior sentence-level and word-level representations. A syntactic dependency tree is employed to create graph structures among words, which are subsequently refined by the implementation of a Graph Convolutional Network (GCN) to more effectively capture relationship properties. A Conditional Random Field (CRF) model is utilized for decoding, enhancing the model’s efficacy in natural language processing tasks. Experimental findings indicate that MDG-JISL attains remarkable performance on cross-domain datasets, with Slot(F1), Intent (Acc), and Overall (Acc) metrics of 98.7%, 98.4%, and 92.4%, respectively. The results validate the model’s efficacy in intent classification and slot filling. © (2025), (International Association of Engineers). All rights reserved.

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

A novel and proposed triad machine learning-based framework for the prognosis of Huntington’s disease

引用

International Journal of Information Technology (Singapore) 2024年第4期16卷 2603-2610页

作者： Deepak, Shashikant Ojha, Ananta Acharjya, Kalyan Mishra, Reshmi Gantra, Amit Kalaiarasan, C. Upadhyay, Ramakant Walke, Suchita Department of UGDX ATLAS SkillTech University Mumbai India Department of Computer Science and Information Technology Jain (Deemed-to-be-University) Karnataka Bengaluru India Maharishi School of Engineering and Technology MUIT Lucknow India Department of Biotechnology Noida Institute of Engineering and Technology UP Greater Noida India Department of Computer Science and Engineering Parul Institute of Engineering and Technology Gujarat Vadodara India Department of Computer Science and Engineering Presidency University Karnataka Bengaluru India Department of Computer Science Sanskriti University UP Mathura India Department of Computer Engineering Pillai College of Engineering and Technology Mumbai University Mumbai India

A hereditary condition known as Huntington's Disease (HD) results in the gradual degeneration of brain nerve cells, impairing a person's capacity for speech, walking, and reasoning. Owing to its severity, novel strategies are crucial for the creation of techniques that support the accurate categorization of this illness. This research proposes a tripartite machine learning-based framework that uses gait dynamics and temporal parameter extraction to predict the prognosis of Huntington's illness. Phases including data pre-processing, feature extraction, classification, and projected output are included in the suggested triad method. The proposed framework uses a triad combination of classifiers for classification: Support vector machines (SVM), K-nearest neighbor (KNN), and Naïve Bayes (NB). The suggested framework's effectiveness is assessed by comparing it to current machine learning classifiers using parameters from the public repository on the dynamics of gait in neurodegenerative diseases. The experimental results show that the triad classifiers employed in the proposed approach are able to achieve higher accuracy (85.45%), higher sensitivity (78.37%) and higher specificity (76.55%) than the existing classifiers used in the recent studies. © The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： Gait dynamics Huntington’s disease KNN Machine learning (ML) NB SVM

来源：评论

学校读者我要写书评

暂无评论

Modeling of Virtual Characters in the Animation Design Instructional System Based on Deep Learning

引用

computer-Aided Design and Applications 2024年第S10期21卷 256-270页

作者： Hao, Gang Cao, Ling Xiao, Zhenghong School of Computer Science Guangdong Polytechnic Normal University Guangdong Guangzhou510665 China Information Engineering School Guangzhou Vocational College of Technology & Business Guangdong Guangzhou511442 China

With the growth of computer technology, 3D animation character modeling technology has become an important part in the field of animation production. However, the traditional modeling method needs a lot of time and manpower, which becomes the bottleneck in the animation production process. This article introduces an animation design instructional system based on deep learning (DL), which involves the technology of animation role CAD modeling. The system can use DL algorithm to model automatically, which provides a convenient and efficient animation role modeling platform for learners. This article introduces the implementation stage of the algorithm in detail, and verifies the effectiveness and feasibility of the algorithm through simulation results. The results show that this method has high precision and low error. The error is reduced by more than 25%, and the highest precision can reach 97.66%. The algorithm can well restore the shape and details of animated characters, and has high precision and robustness. The animation design instructional system can provide valuable technical support and instructional tools for animation industry and education, which is helpful to improve the efficiency of animation production and reduce the cost. © 2024 U-turn Press LLC.

关键词： 3D modeling

来源：评论

学校读者我要写书评

暂无评论

A DISCRETIZING LEVENBERG-MARQUARDT SCHEME FOR SOLVING NONLIEAR ILL-POSED INTEGRAL EQUATIONS

引用

Journal of Computational Mathematics 2022年第5期40卷 686-710页

作者： Rong Zhang Hongqi Yang School of Mathematics and Computer Science Gannan Normal UniversityGanzhou 341004China Guangdong Province Key Laboratory of Computational Science School of Computer Science and EngineeringSun Yat-sen UniversityGuangzhou 510275China

To reduce the computational cost,we propose a regularizing modified LevenbergMarquardt scheme via multiscale Galerkin method for solving nonlinear ill-posed *** results for the regularizing modified Levenberg-Marquardt scheme for the solution of nonlinear ill-posed problems have been *** on these results,we propose a modified heuristic parameter choice rule to terminate the regularizing modified Levenberg-Marquardt *** imposing certain conditions on the noise,we derive optimal convergence rates on the approximate solution under special source *** results are presented to illustrate the performance of the regularizing modified Levenberg-Marquardt scheme under the modified heuristic parameter choice.

关键词： The regularizing Levenberg-Marquardt scheme Multiscale Galerkin methods Nonlinear ill-posed problems Heuristic parameter choice rule Optimal convergence rate.

来源：评论

学校读者我要写书评

暂无评论

Assessing Degradation Levels of Palm Leaf Manuscripts with Random Forest Using Gabor Features 8th

Assessing Degradation Levels of Palm Leaf Manuscripts with R...

引用

8th IFIP TC 12 International Conference on computer, Communication and Signal Processing, ICCCSP 2024

作者： Kowshik, Achyuta Siva Sai Sindhur, Ambati Sai Reddy, Annem Gnaneswara Ganesh, Manasa Sivan, Remya Pati, Peeta Basa Department of Computer Science and Engineering Amrita School of Computing Bengaluru Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (纸本)9783031736162

This experiment focuses on employing machine learning techniques to create an automated system for classifying palm leaf manuscripts into three distinct categories based on their degradation levels: good, bad, and medium. The study collects a wide range of palm leaf samples at different degradation levels. Using advanced machine learning algorithms and an efficient feature extraction method, a model is created that accurately classifies palm leaves by level of degradation. The research incorporates Gabor feature extraction and statistical classifiers to train the extracted features. The classifiers used are k-Nearest Neighbor (k-NN), Support Vector Machine (SVM), Multi-Layer Perceptron (MLP), Logistic Regression (LR), Random Forest (RF), Decision Tree (DT), Naive Bayes (NB), XG Boost (XGB), and Ada Boost (AB). After employing SMOTE, normalization, and feature selection, RF obtained the highest mean accuracy of 87.25% and a standard deviation of 0.08 in comparison with the other classifiers. © IFIP International Federation for Information Processing 2025.

关键词： Random forests

来源：评论

学校读者我要写书评

暂无评论

Multiclass Classification of Insect Bites Using Deep Learning Techniques 3rd

Multiclass Classification of Insect Bites Using Deep Learnin...

引用

3rd International Conference on Machine Vision and Augmented Intelligence, MAI 2023

作者： Sushma, K.V.N.D. Pande, Sagar Dhanraj School of Computer Science and Engineering VIT-AP University Andhra Pradesh Amaravati India Pune India

ISBN: (纸本)9789819743582

Many people suffer due to insect bites every year and it may even be life-threatening sometimes. Insect bites and stings come in different shapes and sizes and itchy red colors, and it might be a difficult task to accurately identify which bite is caused by which insect. On different skin, it may be in different colors or textures. This task may be even challenging for researchers and doctors. Analysis of insect bites is crucial for treatment and disease prevention. Deep learning (DL) algorithms have demonstrated promising gains in a variety of image identification applications in recent years. To enable automatic identification and classification of insect species, this study explores the use of DL algorithms for multi-class classification of insect bites. The main purpose of the paper is to propose a model that classifies insect bites on human skin using deep learning algorithms aiming to classify the insect bites more accurately. This paper first tried to classify whether the given image is a skin or any type of object and received an accuracy of 95% using pre-trained inception-v3 and for insect bite classification a proposed VINMOBCONCAT (hybrid model) received an accuracy of 93%. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive End-to-End Solution for Web Security with Cryptography, Multi-Factor Authentication, and Secure Communication 3

A Comprehensive End-to-End Solution for Web Security with Cr...

引用

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

作者： Kumar, Kanderi Johith Sai, Kandlapalli Aravind Reddy, Adapala Dharshan Reddy, Chinthamreddy Pranay Daiwik Rajagopal, Shinu M. Dept. of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (纸本)9798331527549

In today’s digital landscape, securing sensitive information has become an essential priority in the modern digital era for both individuals and organizations. This project introduces a comprehensive web application that integrates advanced encryption and decryption functionalities alongside multifactor authentication (MFA) and secure payment processing. The application supports various cryptographic algorithms, including AES, DES, Triple DES, Blowfish, etc., allowing users to securely encrypt and decrypt data through dedicated routes accessed over secure HTTPS connections. To further enhance security, robust multifactor authentication mechanisms, such as OTP-based challenge-response and QR-code-enabled 2FA, have been implemented to prevent unauthorized access to sensitive operations. The platform also incorporates PGP encryption powered by Keybase, enabling users to securely exchange encrypted emails. Additionally, a secure payment gateway is integrated using Stripe, ensuring sensitive payment data is encrypted and handled safely. With a strong focus on data integrity, user privacy, and modern web security standards, this project delivers an all-encompassing solution for safeguarding sensitive information and facilitating secure communication. By addressing common vulnerabilities and security risks, the platform stands as a reliable and scalable tool for data protection. © 2025 IEEE.

关键词： Authentication Protocol

来源：评论

学校读者我要写书评

暂无评论

Classifying Lung Cancer Disease Using Random Forest Algorithm 4

Classifying Lung Cancer Disease Using Random Forest Algorith...

引用

4th International Conference on Innovative Practices in Technology and Management, ICIPTM 2024

作者： Madaan, Vijay Sharma, Neha Chauhan, Rahul Joshi, Kireet Kumar, Bura Vijay Sunil, G. Chitkara University Institute of Engineering & Technology Chitkara University Punjab Rajpura India Graphic Era Deemed to Be University Computer Science & Engineering Uttarakhand Dehradun India Sr University School of Computer Science and Artificial Intelligence Warangal India Sr University School of Computer Science & Artificial Intelligence Warangal India

ISBN: (纸本)9798350307757

Through the use of a Random Forest Classifier and the utilization of a varied dataset, this research presents a machine learning model that is targeted at the early diagnosis of lung cancer. An outstanding overall accuracy of 97% is shown by the model, which demonstrates its capacity to properly identify between those who have lung cancer and those who do not have lung cancer. Underscoring the model's skill in limiting false positives and assuring exact identification of positive cases, precision measures suggest a significant accuracy of 0.98 for Class 1 (Lung Cancer). This demonstrates the model's ability to effectively identify positive instances. To provide a complete approach, the model takes into account important characteristics such as age, smoking status, and anxiety levels. The high recall of 0.99 for Class 1 indicates that the model is efficient in catching the majority of lung cancer cases, which is essential for administering timely therapies. This study contributes to the current improvements in healthcare by offering a viable tool for the early diagnosis of lung cancer and perhaps improving the results for patients. © 2024 IEEE.

关键词： Diseases

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：