检索结果-内蒙古大学图书馆

3rd International Conference on Machine learning and data engineering, ICMldE 2024

作者： Ardekar, Sanika Sanghani, Riddhi Nair, Sahil Karani, Ruhina Computer Engineering Department D.J. Sanghvi College of Engineering Mumbai India

This paper introduces the Whisper Of Comfort Singing Voice Conversion (WoC SVC) model, a system designed to transform lullabies sung by any voice into a similar, familiar voice, harnessing the positive impact of familiar voices on infants' development and well-being. Central to the WoC SVC model is the integration of UnivNet, an advanced neural vocoder architecture, which facilitates the generation of high-quality audio waveforms while preserving the original content and melody. The system architecture comprises essential components, including a Content Encoder for extracting mel-spectrograms and log loudness features, a Soft Content Encoder (ContentVec) for generating compact content representations, and a Speaker Embedder for capturing target voice characteristics. These representations are concatenated and processed through UnivNet to synthesize audio waveforms in a similar, familiar voice. Comparison between SOVITS SVC model and WoC SVC is made and the result is evaluated using the values from MFCC cosine similarity and PESQ scores where WoC SVC has consistently performed better. The PESQ score for WoC SVC is 1.4929 and for SOVITS SVC is 1.1348, indicating a percentage difference of approximately 31.53%. Similarly, the cosine similarity for WoC SVC is 0.9346124 and for SOVITS SVC is 0.8947109, with a percentage difference of around 4.46%. These results demonstrate that WoC SVC outperforms SOVITS SVC. © 2025 The Author(s).

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

MYSTERIOUS ACTION dETECTION by SPEEd and dISPlACEMENT ANAlYSIS in IMAGE PROCESSING 1

MYSTERIOUS ACTION DETECTION by SPEED and DISPLACEMENT ANALYS...

引用

1st IEEE International Interdisciplinary Humanitarian Conference for Sustainability, IIHC 2022

作者： Vishnupriya, S. darwin Nesakumar, A. Mounika, S. Pavithra, K.N. R.M.K. College of Engineering and Technology Department of Electronics and Communication Engineering India R.M.K. Engineering College Department of Electronics and Communication Engineering India R.M.D.Engineering College Department of Computer Science and Business System India R.M.D.Engineering College Department of Computer Science Engineering India

ISBN: (纸本)9781665456876

There are now three moving target detection algorithms: The optical flow methodology, the background difference technique, and the inter-frame difference method are all employed. The optical flow technique has the most complex algorithm and takes the longest to process data compared to other approaches. The background subtraction(BS) approach, on the other hand, is recognised for its high sensitivity to light changes. Finally, while the frame difference approach is very straightforward and quick to use, the findings are insufficiently accurate due to backdrop brightness fluctuations causing mistakes. In this paper, the objective is to discover strange actions in image processing using speed and displacement analysis. Motion is detected using Incremental and Multi-feature Tensor Subspace learning (IMTSl) Applied for Background Modeling and Subtraction. Following IMTSl Background Subtraction, different image analysis were performed on the resulting pictures for displacement estimate, followed by speed computation. The results demonstrate improved backdrop modelling and action prediction. © 2022 IEEE.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

denial of Service Attack detection and Mitigation using Ensemble based Ml in Software defined Network 3

Denial of Service Attack Detection and Mitigation using Ense...

引用

3rd International Conference on Applied Artificial Intelligence and Computing, ICAAIC 2024

作者： Sathish, N. Valarmathi, K. Nagalakshmi, R. Hema Priya, K. Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology School of Computing Tamil Nadu Chennai India Panimalar Engineering College India Srm Institute of Science and Technology Computer Science and Engineering. Ramapuram India Easwari Engineering College Department of Cse India

ISBN: (纸本)9798350375190

Software-defined networking (SdN) introduces a novel networking paradigm by decoupling control logic from forwarding operations, resulting in improved network resource management and administration efficiency. However, centralized network design in SdN gives rise to significant security challenges, notably denial-of-service (doS) attacks. Attackers exploit SdN's lack of effective message-verification mechanisms to launch doS attacks by falsifying source address information. In response, this study proposes an innovative approach to Internet of Things (IoT) security leveraging software-based networks and collaborative learning. One key strategy involves partitioning the network domain into smaller subdomains, each with its own controller, facilitating the exchange of security rules among subdomains. However, this topology necessitates routing every packet through the subnet's control node. To continually monitor network traffic data and detect attacks, each controller node employs an integrated learning model. This model combines statistical insights from data streams with artificial neural networks and the Extreme Gradient Boosting Algorithm to anticipate potential attacks. Additionally, the ICOA model selects relevant characteristics for analysis. Through comprehensive performance evaluation, including empirical values, the ensemble model demonstrates superior performance compared to existing approaches. Furthermore, the study compares various models and methodologies, affirming the efficacy of the proposed strategy in accurately identifying distributed denial-of-Service (ddoS) attacks in SdNs, thereby presenting a groundbreaking approach to SdN security. © 2024 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Hyperparameters for Improved Flight delay Prediction Using Machine learning Algorithms 2

Enhancing Hyperparameters for Improved Flight Delay Predicti...

引用

2nd IEEE International Conference on Integrated Circuits and Communication Systems, ICICACS 2024

作者： Sujay, V. lalitha, S. Sreedhar, Siva Satya Omotunde, Habeeb Vijaya, S. Mery, K. Prasanna Krishna University College of Engineering and Technology Department of Computer Science and Engineering Andhra Pradesh Machilipatnam India Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of CSE Tamil Nadu Chennai India Seshadri Rao Gudlavalleru Engineering College Department of Information Technology Andhra Pradesh Gudlavalleru India College of Computer and Information Sciences Department of Information Systems Riyadh Saudi Arabia Paavai Engineering College Department of ECE Tamil Nadu Chennai India

ISBN: (纸本)9798350317558

Flight delays present major problems for the aviation sector, affecting both operational efficiency and consumer happiness. Existing prediction systems have accuracy and flexibility limitations. The study provides an advanced machine learning-based method that makes use of a large dataset, combining historical flight and meteorological information. Random Forest, Gradient Boosting, and Support Vector Machines are used in the system, with hyperparameters optimized using Random search, Bayesian, and Grid search techniques. The results show that the proposed system outperforms the existing system in terms of prediction accuracy, obtaining 95% versus 90%. Precision, recall, and F1-score all exhibit gains, highlighting the suggested system's superiority. The paper methodically describes data collection, algorithm selection, hyperparameter optimization, and model evaluation, as well as an innovative approach to flight delay prediction. To summarize, the proposed system provides a big step forward, providing a more accurate and adaptive system for improving operational efficiency and customer satisfaction in the aviation sector. © 2024 IEEE.

关键词： Customer satisfaction

来源：评论

学校读者我要写书评

暂无评论

Comparative Impact Assessement of Energy Storage Systems on Frequency Regulation with Various Operating Strategies under ABT 1

Comparative Impact Assessement of Energy Storage Systems on ...

引用

1st IEEE International Conference on Smart and Sustainable developments in Electrical engineering, SSdEE 2025

作者： Suthar, B.N. dholakiya, V.M. L.E. College Morbi Electrical Engineering Department Gujarat India L.D. College of Engineering Electrical Engineering Department Gujarat India

ISBN: (纸本)9798331542108

This paper investigates the comparative impact assessment of energy storage systems on frequency regulation with various operating strategies under Availability Based Tariff in an isolated power system having generation from thermal, wind and wave energy sources along with various energy storage systems(ESS) - Superconducting Magnetic Energy Storage (SMES), Supercapacitor Energy Storage (SCES), Redox Flow Battery (RFB), and Flywheel Energy Storage - for mitigating frequency deviations. Simulation studies in MATlAB/Simulink were conducted to evaluate key performance under dynamic operating conditions. Results reveal that SMES and RFB exhibit relatively better response with minimal overshoot (≤ 0.001 Hz), negligible undershoot, and least instantaneous settling time, making them appropriate for rapid frequency stabilization. SCES also demonstrates effective performance, albeit with slight oscillations due to its slower discharge rate. The analysis emphasizes the critical role of ESS technologies in enhancing the frequency regulation under different operating strategies under ABT. This study provides insights into the preliminary selection and integration of ESS in modern power systems, contributing to the reliable and stable grid operations amidst increasing renewable energy penetration. © 2025 IEEE.

关键词： Capacitor storage

来源：评论

学校读者我要写书评

暂无评论

IoT and Tele-Communication Networks: Opportunities for Industry 4.0 15

IoT and Tele-Communication Networks: Opportunities for Indus...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Chattopadhyay, Saumitra Parveen, H. Summia Manwal, Manika Shukla, Rishi Prakash Ragini, Y.P. Pawar, Vikas V. Graphic Era Hill University Computer Science and Engineering Uttarakhand Dehradun248002 India Sri Eshwar College of Engineering Department of Computer Science Engineering Tamil Nadu Coimbatore641202 India Graphic Era Deemed to be University Computer Science and Engineering Uttarakhand Dehradun India Jaipuriya Institute of Management Jaipur India Saveetha University Saveetha School of Engineering Department of Biosciences Chennai India Dr. D Y Patil Vidyapeeth Centre for Online Learning Pune India

ISBN: (纸本)9798350370249

The Fourth business Revolution, called industry ***, has introduced tremendous improvements inside the manufacturing and different industries, mixing net of things (Iota) and tile-conversation networks. Iota refers to the connection of physical gadgets consisting of machines, gadgets, and sensors thru the internet, permitting actual-time records series and communiqué. Tele-communiqué networks, on the other hand, facilitate the transmission of information among related devices. The combination of Iota and tile-communication networks has created several opportunities for industry 4.0. First of all, it allows for real-time tracking and faraway manipulate of machines, ensuing in advanced performance and productiveness. That is feasible thru the usage of sensors that collect statistics and send it to the cloud, where it may be accessed and analyzed in actual-time. It also enables predictive upkeep, where the statistics collected from machines can be used to prevent capacity breakdowns, decreasing downtime and costs⋯ © 2024 IEEE.

关键词： breakdowns industries machines opportunities Revolution

来源：评论

学校读者我要写书评

暂无评论

Target driven Autoencoder: A Supervised learning Approach for Tumor Segmentation 4

Target Driven Autoencoder: A Supervised Learning Approach fo...

引用

4th International Conference on Emerging Systems and Intelligent Computing, ESIC 2024

作者： das, Abhishek Mohapatra, Saumendra Kumar Pattanaik, Rakesh Kumar Tripathy, Balaram Patra, Gyana Ranjan Mohanty, Mihir Narayan Centurion University of Technology and Management Department of Computer Science Engineering Odisha Paralakhemundi India Shri Shri University Department of Computer Science Engineering Odisha Cuttack India Dnr College of Engineering and Technology Department of Electronics and Communication Engineering Andhra Pradesh Bhimavaram India S.K.D.A.V. Government Polytechnic Department of Electronics and Telecommunication Engineering Odisha Rourkela India Iter Department of Electronics and Communication Engineering Odisha Bhubaneswar India

ISBN: (纸本)9798350349856

A particular kind of neural network called an autoencoder (AE) is trained to discover a reduced and effective representation (encoding) of input data. In most of the applications of AE, it is found that this model has been used for generating the same images in compressed form. AE has also been used for encoding the images and signals. In this work, a supervised autoencoder is designed that is trained with both input images and corresponding targets that are also the images. This allows the model to learn a mapping from the input image to the target image specifically for segmentation. The proposed method is verified and trained with brain MRI images and segmented tumors. The dice score obtained in this method is 98.43% in producing segmented tumors. © 2024 IEEE.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Prairie dog Optimization (IPdO) and deep Auto-Neural Network (dANN) based IdS for WSN Security

Iraqi Journal for Computer Science and Mathematics

引用

Iraqi Journal for computer Science and Mathematics 2023年第4期4卷 30-42页

作者： Hemanand, d. Mohankumar, P. Kumar, N. Manoj Vaitheki, S. Saranya, P. Thiruverkadu Tamil Nadu Chennai600077 India School of Computer Science and Engineering VIT University Tamil Nadu Vellore632014 India Department of Electrical and Electronics Engineering Panimalar Engineering College Tamil Nadu Chennai600123 India Department of Electronics and communication Engineering P.S.R.R.College of Engineering Taminadu Sivakasi626140 India Department of Mathematics Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Tamil Nadu Chennai600062 India

Wireless sensor networks (WSNs) are targets of intrusion, which seeks to make these networks less capable of performing their duties or even completely eradicate them. The Intrusion detection System (IdS) is highly important for WSN, since it aids in the identification and detection of harmful attacks that impair the network's regular functionality. In order to strengthen the security of WSN, several machine learning and deep learning approaches are employed in the traditional works. However, its main drawbacks are computational burden, system complexity, poor network performance outcomes, and high false alarms. Therefore, the goal of this study is to develop an intelligent IdS framework for significantly enhancing WSN security through the use of deep learning model. Here, the min-max normalization and data discretization operations are carried out to produce the preprocessed dataset. Then, an Intelligent Prairie dog Optimization (IPdO) algorithm is used to reduce the dimensionality of features by identifying the best optimal solution with a higher convergence rate. Moreover, a deep Auto-Neural Network (dANN) based classification method is used to properly forecast the class of data with less false alarms and higher detection rate. For evaluation, a thorough analysis is conducted to evaluate the performance and detection results of the proposed IPdO-dANN model. © 2023 Authors.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

deep Fake detection for Preventing Audio and Video Frauds Using Advanced deep learning Techniques 6

Deep Fake Detection for Preventing Audio and Video Frauds Us...

引用

6th IEEE International Conference on Recent Advances in Intelligent Computational Systems, RAICS 2024

作者： Vaidya, Anusha O. dangore, Monika Borate, Vishal Kisan Raut, Nutan Mali, Yogesh Kisan Chaudhari, Ashvini Trinity Academy of Engineering E & T C Department Pune India G.H Raisoni Institute of Engineering and Management Aiml Department India Dr D Y Patil College of Engineering & Innovation Computer Engineering Department Pune India G.H Raisoni College of Engineering and Management Aiml Department India Nmims Center for Distance & Online Education Pune India

ISBN: (纸本)9798350381689

deepfakes allow for the automated gen- eration of fake video content, often accomplished through the use of generative adversarial networks. To address the increasing issue of deepfakes, this study focuses on constructing a model that incorporates advanced techniques. The researchers combined the ResNeXt, long Short-Term Memory (lSTM), and ResNet architectures, selecting them based on their effectiveness in handling complex visual data and capturing temporal dependencies. Prior to detection, the dataset underwent pre-processing using the Multi-Task Cascaded Convolutional Neural Network (MTCNN), which facilitated the accurate extraction of facial regions. Importantly, the study evaluated the model across three diverse and significant datasets: the Face Forensics++ dataset (FF-dF), the Celeb-dF dataset, and the Facebook deepfake detection Challenge (dFdC) dataset. This comprehensive evaluation en- sured the model's ability to generalize and its suitability for real-world scenarios, as demonstrated by its exceptional detection accuracy. The combination of models employed in this study yielded highly accurate results and remained robust in the face of evolving deepfake technology. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Efficient Feature Extraction Methods for Enhancing Analysis of lecture Videos

Efficient Feature Extraction Methods for Enhancing Analysis ...

引用

2024 IEEE International Conference on Innovation and Novelty in engineering and Technology, INNOVA 2024

作者： Kaur, Preet Chandan Ragha, leena Department of Computer Engineering Ramrao Adik Institute of Technology Dr. D.Y. Patil Deemed to be University Nerul Navi Mumbai India Department of Computer Science and Engineering BLDEA’s V.P. Dr. P.G. Halakatti College of Engineering and Technology Karnataka India

ISBN: (纸本)9798331505134

Feature extraction informs fundamental computer vision and pattern recognition research. Examines how to obtain useful features from raw datasets, such as images or video frames. This stage is crucial in identifying images, recognizing objects, and analyzing frames. Effortless and accurate feature extraction may enhance machine learning models when there is a lot of visual input. Video lectures with slides, text, and diagrams can benefit from feature extraction. A study will compare video lecture analysis feature extraction algorithms and identify research gaps. We will use our survey methods to compare the performance of seven representative feature extraction algorithms: Shape local Binary Texture (SlBT), local Optimal Oriented Pattern (lOOP), local Vector Pattern (lVP), Scale-Invariant Feature Transform (SIFT), Speeded-Up Robust Features (SURF), Gabor Filters, and local Binary Patterns (lBP). SlBT and lOOP have the highest accuracy (90%), while lBP holds the lowest (85%). SIFT and SURF are widely scalable but slower to compute. Gabor and lBP filters are quick, but inaccurate and scalable. The survey found that SlBT, lOOP, and lVP are better feature extraction methods for video educational processing than others. © 2024 IEEE.

关键词： Gabor filters

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：