检索结果-内蒙古大学图书馆

Deepfake Audio Detection for Urdu Language Using Deep Neural Networks

IEEE Access 2025年 13卷 97765-97778页

作者： Ahmad, Omair Khan, Muhammad Sohail Jan, Salman Khan, Inayat University of Engineering and Technology Department of Computer Software Engineering Mardan Pakistan Arab Open University Faculty of Computer Studies A’Ali732 Bahrain University of Engineering and Technology Department of Computer Science Mardan Pakistan

Audio Deepfakes, which are highly realistic fake audio recordings driven by AI tools that clone human voices, With Advancements in Text-Based Speech Generation (TTS) and Vocal Conversion (VC) technologies have enabled it easier to create realistic synthetic and imitative speech, making audio Deepfakes a common and potentially dangerous form of deception. Well-known people, like politicians and celebrities, are often targeted. They get tricked into saying controversial things in fake recordings, causing trouble on social media. Even kids’ voices are cloned to scam parents into ransom payments, etc. Therefore, developing effective algorithms to distinguish Deepfake audio from real audio is critical to preventing such frauds. Various Machine learning (ML) and Deep learning (DL) techniques have been created to identify audio Deepfakes. However, most of these solutions are trained on datasets in English, Portuguese, French, and Spanish, expressing concerns regarding their correctness for other languages. The main goal of the research presented in this paper is to evaluate the effectiveness of deep learning neural networks in detecting audio Deepfakes in the Urdu language. Since there’s no suitable dataset of Urdu audio available for this purpose, we created our own dataset (URFV) utilizing both genuine and fake audio recordings. The Urdu Original/real audio recordings were gathered from random youtube podcasts and generated as Deepfake audios using the RVC model. Our dataset has three versions with clips of 5, 10, and 15 seconds. We have built various deep learning neural networks like (RNN+LSTM, CNN+attention, TCN, CNN+RNN) to detect Deepfake audio made through imitation or synthetic techniques. The proposed approach extracts Mel-Frequency-Cepstral-Coefficients (MFCC) features from the audios in the dataset. When tested and evaluated, Our models’ accuracy across datasets was noteworthy. 97.78% (5s), 98.89% (10s), and 98.33% (15s) were remarkable results for the RNN+LSTM

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Improving agility in projects using machine learning algorithm

引用

Multimedia Tools and Applications 2024年第38期83卷 85987-86005页

作者： Varun, Janani Karthika, R.A. Department of Computer Science and Engineering Vels Institute of Science Technology and Advanced Studies Chennai India Department of Computer Science and Engineering Saveetha School of Engineering SIMATS Chennai India

All the software products developed will need testing to ensure the quality and accuracy of the product. It makes the life of testers much easier when they can optimize on the effort spent and predict defects for the upcoming modules in the Agile era. The functionality being discussed in this paper is to predict the defects using Random Forest Algorithm. Predictive analytics draws on information from the past to create forecasts about the outcomes of future events. Product team always have the difficulty in delivering the product as per schedule. As we are in the agile era, the requirement keeps changing and team is unsure on upcoming releases. Prediction helps the team to focus on the complex and error prone modules in upcoming releases. The Predictive analytics model designed, can predict defects with an accuracy rate of 88% with the help of historical data. By predicting, testers can focus on the module where there are a greater number of defects predicted by the model and left shift the delivery. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Predictive analytics

来源：评论

学校读者我要写书评

暂无评论

Geometric Relationship Analysis among the Velocity Ellipsoids of a Serial Robot according to the Combination of Additional Extra Inputs

引用

Journal of Institute of Control, Robotics and Systems 2023年第1期29卷 48-56页

作者： Kim, Sungbok Division of Computer Engineering Hankuk University of Foreign Studies Korea Republic of

This paper presents an in-depth analysis of the geometric relationship among the velocity ellipsoids of a serial robot according to the combination of additional extra inputs. In this paper, one or more extra inputs are added to a non-redundant or redundant serial robot, and no assumption is made on the linear independency of the additional extra inputs. First, in the case of one additional input, the relationship of two velocity ellipsoids before and after the addition of extra input is expressed by means of the freezing of the extra input, which defines a constraint hyperplane in the output space. Using the constraint hyperplane, the geometric relationship between two velocity ellipsoids with zero and one extra input is obtained. Second, the case of two additional inputs is treated as the addition of extra input twice in a row, and two constraint hyperplanes corresponding to the freezing of the two extra inputs are defined. Using the two constraint hyperplanes, the geometric relationship among three velocity ellipsoids with zero, one, two extra inputs is obtained. It is shown that the resulting geometric relationship should change depending on the linear independency of the two extra inputs. Third, the analysis for the case of two extra input is extended to the case of r≥3 additional inputs, which is treated as the addition of extra input r times in a row. Using r constraint hyperplanes corresponding to the freezing of the r extra inputs, the geometric relationship among (r+1) velocity ellipsoids with zero up to r extra inputs is identified. It is shown that the inclusion relationship between two velocity ellipsoids before and after the addition of r extra inputs should change depending on the linear independency of the r extra inputs. Fourth, simulation results of planar and spatial serial robots are provided to illustrate the varying geometric relationship among the velocity ellipsoids of a serial robot according to the combination of additional extra inputs. ©

关键词： Freezing

来源：评论

学校读者我要写书评

暂无评论

Efficient Computation of the Allowable Control Input Range for a Delivery Quadrotor Aircraft Under the Constraint of Thrust

引用

Journal of Institute of Control, Robotics and Systems 2023年第4期29卷 339-346页

作者： Kim, Sungbok Division of Computer Engineering Hankuk University of Foreign Studies Korea Republic of

In this paper, an efficient method of computing the allowable control input range of a quadrotor aircraft is presented, which can be used for flight control under the constraint of thrust due to a given delivery object. For a quadrotor aircraft, the squares of the angular velocity of four rotors are considered as the actuation input, and the resulting thrust and three torques applied to the vehicle are considered as the control input, and the relationship between the actuation input and the control input can be approximated by a linear mapping. The entire actuation input range of a quadrotor aircraft is defined as a cube in the 4-dimensional actuation space, and the thrust requirement, which varies depending on the weight of a given delivery object, is expressed as a hyperplane in the 4-dimensional actuation space. Then, the allowable acuation input range of a quadrotor aircraft is obtained as the intersection of the entire actuation input range (the 4-dimensional cube) and the actuation space thrust constraint (the 3-dimensional hyperplane). Finally, through the linear mapping of the obtained allowable actuation input range into the 4-dimensional control space, the allowable control input range of a quadrotor aircraft under the control space thrust constraint can be determined as a 3-dimensional polyhedron. © ICROS 2023.

关键词： Aircraft

来源：评论

学校读者我要写书评

暂无评论

Algebraic and Geometric Analysis of Ordinary and Orthogonal Distance Least Squares Solutions to an Overdetermined Linear System

引用

Journal of Institute of Control, Robotics and Systems 2023年第3期29卷 191-201页

作者： Kim, Sungbok Division of Computer Engineering Hankuk University of Foreign Studies Korea Republic of

In this paper, we make an in-depth analysis on the ordinary least-squares solution and the orthogonal distance least-squares solution to an overdetermined linear system, having the number n of constraints greater than the number m of unknowns. Using the barycentric coordinate, algebraic and geometric analysis is made for the case of n = 2 and m = 3, yielding a constraint triangle, and for the case of n = 3 and m = 4, yielding a constraint tetrahedron. First, for an n-dimensional overdetermined system, the ordinary least squares solution that minimizes the sum of the squares of m residuals and the orthogonal distance least squares solution that minimizes the sum of the squares of m orthogonal distances are formulated. Next, for the cases of n = 2 and m = 3, and n = 3 and m = 4, the following analysis is made: The relationship between the ordinary least-squares solution and the centroid of the constraint triangle/tetrahedron is identified, the changing pattern of the ordinary least-squares solution due to the scaling of an overdetermined system is examined, and the relationship between the orthogonal distance least squares solution and the symmedian point of the constraint triangle/tetrahedron is identified. Finally, to demonstrate the applicability of the ordinary least-squares and the orthogonal distance least-squares solutions, the velocity estimation of a mobile robot using a polygonal array of optical mice is provided. © ICROS 2023.

关键词： Linear systems

来源：评论

学校读者我要写书评

暂无评论

Deep Neural Network Empowered Movie Recommender System Using Hesitant Fuzzy Bi Objective Clustering

引用

Journal of The Institution of Engineers (India): Series B 2024年 1-11页

作者： Shrivastava, Vineet Kumar, Suresh Department of Computer Science and Engineering Manav Rachna International Institute of Research and Studies Haryana Faridabad India

The movie recommender system is a highly influential and practical tool that assists individuals in efficiently choosing films to watch. Although recommender systems have been extensively used in academic research for various objectives, such as suggesting movies and recommending books, there has been a lack of focus on providing personalized movie recommendations for individual users. This research presents a new method for recommending movies that combines the Hesitant Fuzzy Clustering technique with a Convolutional Spiking Neural Network Movie Recommender System. The first phase entails obtaining input data from benchmark datasets such as MovieLens 100 K and MovieLens 1 M. These datasets are analysed using Ternary Pattern and Discrete Wavelet Transforms along with Hesitant Fuzzy Bi-objective Clustering technique to choose clusters depending on the retrieved attributes. After that, recommendation of movies uses a Deep Convolutional Spiking Neural Network to forecast user preferences. The efficiency of the proposed model is specifically compared to recent existing methods, like the Multi-Model Trust Based Movie Recommender Scheme (MT-ML-MRS) and the Graph-Dependent Hybrid Movie Recommendation Scheme (GHRS-MRS), particularly for movie recommendations. The results demonstrate a substantial enhancement, as the suggested model achieves 2.30% and 4.71% greater accuracy for MovieLens 100 k and MovieLens 1 M datasets respectively. The proposed system shows significant improvement over some traditional recommendation models indicating avenues for future research in scalable and intricate systems. © The Institution of Engineers (India) 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Autism spectrum disorder prediction system using machine learning and deep learning

引用

International Journal of Applied Systemic studies 2024年第2期11卷 159-173页

作者： Sharma, Anshu Tanwar, Poonam School of Computer Science and Engineering Manav Rachna International Institute of Research and Studies Haryana Faridabad121002 India

Autism spectrum disease (ASD) is a neuro developmental illness that is both complicated and degenerative. A majority of known approaches use autism detection observation schedule (ADOS), pattern recognition, etc. to detect ASD with a small dataset, resulting in high accuracy but low generality. In this research, an ASD detection hybrid model is presented which is works on two different types of datasets. Firstly, behavioural datasets which works on logistic regression technique and secondly, facial dataset which works on based on convolutional neural network (CNN) Classifier in order to predict whether a person is suffering from autism or not. The suggested hybrid model which works on behavioural and facial dataset of a person beats state-of-the-art approaches in terms of accuracy, according to simulation findings. The proposed hybrid model had an average accuracy of 88% for the logistic regression model while it achieved an accuracy of 82.76% for the CNN model. © 2024 Inderscience Enterprises Ltd.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Multi-label Text Classification on Textcnn fused Bilstm with Attention Mechanism

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer Science 2025年第2期52卷 524-532页

作者： Duan, Aihua Raga, Rodolfo C. Computer Science at the College of Computing and Information Technologies National University Manila1008 Philippines College of Computer Studies and Engineering José Rizal University Mandaluyong City1550 Philippines

This paper proposed a deep learning model for multi-label text classification to effectively manage and utilize the network text information and realize the automatic labeling of text content. The neural network word vector model GloVe is used to obtain the semantic features of the text data. The model fusion of recurrent neural network and convolutional neural network is performed, and the attention mechanism is introduced into BiLSTM to form the BiLSTM_Attention neural network model. Experimental results show that the BiLSTM_Attention model structure combines the advantages of the TextCNN model and can better understand the semantic information. The Attention mechanism is more reasonable for text feature extraction, so the model focuses on the features that contribute more to the text classification task, and the classification effect is better. © (2025), (International Association of Engineers). All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Suppression and synchronization of chaos in uncertain time-delay physical system

引用

Applied Mathematics(A Journal of Chinese Universities) 2024年第3期39卷 416-437页

作者： Israr Ahmad Muhammad Shafiq Department of Preparatory Studies Centre University of Technology and Applied SciencesNizwaOman Department of Electrical and Computer Engineering Sultan Qaboos UniversityOman

The mechanical horizontal platform(MHP)system exhibits a rich chaotic *** chaotic MHP system has applications in the earthquake and offshore *** article proposes a robust adaptive continuous control(RACC)*** investigates the control and synchronization of chaos in the uncertain MHP system with time-delay in the presence of unknown state-dependent and time-dependent *** closed-loop system contains most of the nonlinear terms that enhance the complexity of the dynamical system;it improves the efficiency of the *** proposed RACC approach(a)accomplishes faster convergence of the perturbed state variables(synchronization errors)to the desired steady-state,(b)eradicates the effect of unknown state-dependent and time-dependent disturbances,and(c)suppresses undesirable chattering in the feedback control *** paper describes a detailed closed-loop stability analysis based on the Lyapunov-Krasovskii functional theory and Lyapunov stability *** provides parameter adaptation laws that confirm the convergence of the uncertain parameters to some constant *** computer simulation results endorse the theoretical findings and provide a comparative performance.

关键词： chaotic horizontal platform system chaos suppression chaos synchronization robust adaptive control Lyapunov stability theory

来源：评论

学校读者我要写书评

暂无评论

Ensemble of Deep Learning with Crested Porcupine Optimizer Based Autism Spectrum Disorder Detection Using Facial Images

引用

computers, Materials & Continua 2025年第5期83卷 2793-2807页

作者： Jagadesh Balasubramani Surendran Rajendran Mohammad Zakariah Abeer Alnuaim Department of Computer Science and Engineering Saveetha School of EngineeringSaveetha Institute of Medical and Technical SciencesChennai602105Tamil NaduIndia Department of Computer Science and Engineering College of Applied Studies and Community ServiceKing Saud UniversityP.O.Box 22459Riyadh11495Saudi Arabia

Autism spectrum disorder(ASD)is a multifaceted neurological developmental condition that manifests in several *** all autistic children remain undiagnosed before the age of *** problems affecting face features are often associated with fundamental brain *** facial evolution of newborns with ASD is quite different from that of typically developing *** recognition is very significant to aid families and parents in superstition and *** facial features from typically developing children is an evident manner to detect children analyzed with ***,artificial intelligence(AI)significantly contributes to the emerging computer-aided diagnosis(CAD)of autism and to the evolving interactivemethods that aid in the treatment and reintegration of autistic *** study introduces an Ensemble of deep learning models based on the autism spectrum disorder detection in facial images(EDLM-ASDDFI)*** overarching goal of the EDLM-ASDDFI model is to recognize the difference between facial images of individuals with ASD and normal *** the EDLM-ASDDFI method,the primary level of data pre-processing is involved by Gabor filtering(GF).Besides,the EDLM-ASDDFI technique applies the MobileNetV2 model to learn complex features from the pre-processed *** the ASD detection process,the EDLM-ASDDFI method uses ensemble techniques for classification procedure that encompasses long short-term memory(LSTM),deep belief network(DBN),and hybrid kernel extreme learning machine(HKELM).Finally,the hyperparameter selection of the three deep learning(DL)models can be implemented by the design of the crested porcupine optimizer(CPO)*** extensive experiment was conducted to emphasize the improved ASD detection performance of the EDLM-ASDDFI *** simulation outcomes indicated that the EDLM-ASDDFI technique highlighted betterment over other existing models in terms of numerous performance measures.

关键词： Autism spectrum disorder ensemble learning crested porcupine optimizer facial images computeraided diagnosis

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：