检索结果-内蒙古大学图书馆

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Raj, J. Relin Francis Sasirekha, S. Krishnan, R. Santhana Sunitha, R. Jothi, J. Nirmal Kalyanakumar, P. Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Electronics and Communication Engineering Chennai India Dhanalakshmi College of Engineering Department of Electronics and Communication Engineering Tambaram Chennai India Scad College of Engineering and Technology Department of Electronics and Communication Engineering Cheranmhadevi India Rajarajeswari College of Engineering Department of Electronics and Communication Engineering Bangalore India Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Electronics and Communication Engineering Avadi Chennai India Velammal College of Engineering and Technology Department of Information Technology Madurai India

ISBN: (纸本)9798331509828

Heart disease detection from medical images such as X-rays, CT scans, and MRIs is a critical task in the healthcare industry. In this proposed work, we explore the application of Convolutional Neural Networks (CNNs) for the classification of heart disease from these medical images. CNNs are highly effective in image-based tasks due to their ability to learn hierarchical features from raw image pixels. The proposed methodology includes the collection of medical image datasets, such as Chest X-ray and Cardiovascular Disease datasets, which are labeled based on the presence or absence of heart disease. These images are preprocessed by resizing, normalizing, and augmenting the dataset to improve model generalization. The CNN model consists of multiple convolutional layers that detect low-level features, followed by max-pooling layers to reduce dimensionality. Fully connected layers are used to combine the extracted features and make predictions, with the output layer using a sigmoid activation function for binary classification. The model is trained using the Adam optimizer and evaluated based on accuracy, precision, recall, Fl-score, and confusion matrix. The results demonstrate that the CNN-based approach outperforms traditional machine learning algorithms like SVM and Random Forest in heart disease detection, with better classification metrics and lower false positive/negative rates. Future improvements could include using advanced CNN architectures, such as VGGNet or InceptionV3, and integrating ECG signals for more accurate predictions. This work highlights the potential of CNNs for heart disease detection and lays the foundation for future research in deep learning applications for healthcare. © 2025 IEEE.

关键词： Computerized tomography

来源：评论

学校读者我要写书评

暂无评论

Harnessing Machine Learning in Dynamic Thermal Management in Embedded CPU-GPU Platforms

引用

ACM Transactions on Design Automation of Electronic Systems 2025年第2期30卷 1-32页

作者： Maity, Srijeeta Majumder, Anirban Roy, Rudrajyoti Hota, Ashish Dey, Soumyajit Computer Science and Engineering Indian Institute of Technology Kharagpur Kharagpur India Electrical Engineering Indian Institute of Technology Kharagpur Kharagpur India Electronics And Communication Engineering Indian Institute of Technology Kharagpur Kharagpur India

With increasing transistor density, modern heterogeneous embedded processors often exhibit high temperature gradients due to complex application scheduling scenarios which may have missed design considerations. In many use cases, off-chip "active"cooling solutions are considered prohibitive in such reduced form factors. Core frequency throttling by existing dynamic thermal management techniques often compromises the Quality-of-Service (QoS) and violates real-time deadlines. This necessitates the adoption of intelligent resource management that simultaneously manages both thermal and latency performance. Coupled with the complexity of modern heterogeneous multi-cores, the periodic application updates that cater to ever-changing user requirements often render model-driven thermal-aware resource allocation approaches unsuitable for heterogeneous multi-core systems. For such application-architecture scenarios, we propose a novel self-learning based resource manager using Reinforcement Learning that intelligently manipulates core frequencies and task set mappings to fulfill thermal and latency objectives. Our framework employs a data-driven system modeling technique using Gaussian Process Regression to enable efficient offline training of this learning-based resource manager to avoid challenges associated with initial online training. We evaluate the approach on a heterogeneous embedded CPU-GPU platform with real workloads and observe a significant reduction in peak operating temperature when compared to the default onboard frequency governor as well as other learning-based state-of-the-art approaches. © 2025 Copyright held by the owner/author(s).

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

PixNet for early diagnosis of COVID-19 using CT images

引用

Multimedia Tools and Applications 2025年第10期84卷 8179-8203页

作者： Pravin, Sheena Christabel Rohith, G. V, Kiruthika Saranya, J. Latha, B. Vigneshwar, K.R. Krishna, S. Vamsi Nambirajan, Hemkumar Sumitra, Y. School of Electronics Engineering Vellore Institute of Technology Chennai India Rajalakshmi Engineering College Chennai India

Globally, COVID-19 has impacted severely the healthcare systems and the patients as well. Reverse Transcription-Polymerase Chain Reaction (RT-PCR) tests can be effectively supplemented with computed tomography images. Recent research on CT-based screening found that COVID-19 infection is linked to abnormalities in chest Computed Tomography (CT). However, it is difficult to distinguish these from the general abnormalities that are caused in the lungs. Although COVID-19 RT-PCR testing is exceedingly precise, its sensitivity varies based on the sampling technique and the period as well. Some studies have even shown that RT-PCR testing displays very low COVID-19 sensitivity. This motivated the authors to propose a new deep-learning model called PixNet that can detect positive and negative cases accurately. We compared the effectiveness of the proposed model against several state-of-the-art models trained on CT images. On analysis, it is found that the proposed model displays 96% classification accuracy in diagnosing COVID-19 infection. The proposed algorithm automatically detects the infection owing to COVID-19 from CT scan images, which may be an effective screening tool for Clinicians. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Effective Chirp Modulation communication System Design for LEO Satellite IoT

引用

IEEE Internet of Things Journal 2025年第11期12卷 16962-16976页

作者： Zhao, Wenqing Zhang, Haozhe Zou, Jun Liu, Guangzu Shu, Feng Nanjing University of Science and Technology School of Electronic and Optical Engineering Nanjing China Hainan University School of Information and Communication Engineering Haikou China

The high-dynamic Doppler frequency offset presents great challenges to communications in the Low-Earth Orbit (LEO) satellite Internet of Things (IoT) scenarios, including the high complexity receiver synchronization algorithm, frequency tracking capability and high receiver sensitivity. In this paper, we propose an effective communication system architecture based on chirp modulation for LEO satellite IoT with reference to LoRa system. Our approach introduces an improved chirp modulation based on Low-Rate Optimization (LRO) with specified frequency interval and a CRC-assisted decoding scheme. Simulation results show that the proposed optimal LRO factor can improve the spectral efficiency. Furthermore, we propose a low complexity synchronization algorithm and LRO-based frequency tracking strategy. The simulation results confirm the feasibility of the proposed communication system for LEO satellite IoT, which demonstrates robust performance under high-dynamic Doppler frequency offsets. © 2014 IEEE.

关键词： Chirp modulation

来源：评论

学校读者我要写书评

暂无评论

Hybrid EXGBStackQoE Classifier and Stackelberg Game-Theoretic Approaches for Enhanced QoE in Video Services Over 5G Wireless Networks

引用

IEEE Access 2025年 13卷 70269-70281页

作者： Ajeyprasaath, K.B. Pandu, Vetrivelan Vellore Institute of Technology School of Electronics Engineering Chennai600127 India

Video streaming applications have experienced significant growth in recent years, driving an increase in global internet traffic. This rapid expansion underscores the critical need to ensure a high Quality of Experience (QoE) for users, as subpar video QoE can result in considerable financial losses for telecommunication providers. Traditional approaches, such as the Mean Opinion Score (MOS), while widely used for assessing QoE, are inherently subjective and require significant manual effort. This research addresses these limitations by introducing an advanced framework integrating multiple models and methodologies to enhance video QoE in 5G networks. The proposed framework features a novel Hybrid EnhancedXGBStackQoE (EXGBStackQoE) analytical model that applies a two-level stacking technique combined with 5-fold cross-validation to mitigate overfitting. At the initial level, various machine learning (ML) models are trained using the entire dataset, while the subsequent level leverages meta-features generated from the initial predictions to improve overall accuracy. This hybrid model demonstrates an accuracy improvement of 5–7% compared to traditional models, establishing a new standard in QoE evaluation. Additionally, the framework incorporates a Stackelberg Game-based Software-Defined Networking (SbSG) model designed for efficient data offloading in 5G Macro Base Stations (MBS). This model employs economic incentives and traffic load balancing to strategically select users for offloading, prioritizing those with lower QoS based on the Received Signal Strength Indicator (RSSI). By optimizing data distribution between MBS and Heterogeneous Networks (HetNets), the SbSG model enhances both network throughput and service quality. This comprehensive framework addresses critical challenges in video QoE optimization, providing a robust and automated solution tailored to the demands of next-generation networks. © 2013 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Clustered OLSR routing and FPGA parameter analysis for mobile ad hoc communication

引用

International Journal of electronics Letters 2025年第2期13卷 227-237页

作者： Kumar, Arvind Kumar, Adesh Agrawal, Anurag Vijay Department of Electrical and Electronics Engineering School of Advanced Engineering UPES Dehradun India Department of Electronics and Communication Engineering Bhagwant Institute of Technology (U.P.) 251315 Muzaffarnagar India

The research letter emphasises the hardware chip design of homogeneous clustered optimised link state routing (HMC-OLSR) protocol for Mobile Ad-hoc Networks (MANET). The homogeneously distributed clustering allows for parallel processing and distributes the burden evenly among the clusters to reduce the network complexity and computational time. The chip design is evaluated based on field programmable gate array (FPGA) performance metrics for the proposed HMC-OLSR protocol, which significantly reduced hardware utilisation by 27.45%, 48.8% of slices, 28.71%, 55.82% of flip-flops, 8.35%, 13.60% of look-up tables (LUTs), and 36.4% of input/output blocks (IoBs) compared to existing OLSR and destination-Sequenced distance vector (DSDV) protocols, respectively. The recommended protocol also outperformed OLSR and DSDV routing protocols in FPGA timing constraints such as minimum time before the clock, maximum time after the clock, and minimum propagation period. The novelty of the work is in the incorporation of an FPGA-integrated scalable network design that surpasses maximum throughput, packet delivery ratio (PDR), minimum power consumption, end-to-end delay, and control overhead. © 2025 Informa UK Limited, trading as Taylor & Francis Group.

关键词： FPGA MANET node and routing OLSR

来源：评论

学校读者我要写书评

暂无评论

Wav2Lip Bridges communication Gap: Automating Lip Sync and Language Translation for Indian Languages

引用

IEEE Access 2025年 13卷 72906-72917页

作者： Venkataraghavan, Vaishnavi Sivapatham, Shoba Kar, Asutosh Vellore Institute of Technology School of Electronics Engineering Chennai600127 India Vellore Institute of Technology Centre for Advanced Data Science Chennai600127 India Dr B R Ambedkar National Institute of Technology Electronics and Communication Engineering Punjab Jalandhar144011 India

Translating spoken speech in videos from one language to another is known as audio-visual translation (AVT). This paper describes the implementation of an automated AVT and lip-synced dubbing application. It addresses the difficulty of synchronizing mouth movements with translated speech by building a web application that synthesizes the speaker’s lip movements to match translated audio. Using ASR models, the speech from the source video is converted to text, translated into several languages, and then automatically synthesized into speech in the target language. A lip synchronization model, Wav2Lip, is used to alter the mouth movements in the video to correspond to the target language. We compare our work with two wellknown ASR systems: Wav2vec 2.0 and Google Speech Recognition. Wav2vec 2.0 performs better with the lesser average WER% of 15.38 and is used in our final web application. The performance of the video dubbing component is discussed with the generated speech in Tamil, Telugu, Hindi, and English, and we determine that our generated videos outperform the existing ones. Our proposed AVT application is user-friendly for a wide variety of speakers, utilizing readily available TTS systems instead of training on an individual speaker’s voice. © 2013 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Deep learning countermeasures for detecting replay speech attacks: a review

引用

International Journal of Speech technology 2025年第1期28卷 39-51页

作者： Veesa, Suresh Singh, Madhusudan Department of Electronics and Communication Engineering National Institute of Technology Nagaland Chumukedima Nagaland Dimapur797103 India

Automatic speaker verification (ASV) systems are widely accepted for biometric authentication in real-time applications. However, such ASV systems need robust protection against well-known replay attacks, especially for highly sensitive applications. This study provides a detailed overview of existing deep learning based solutions developed for replay attack detection task. Convolution neural network architectures are most widely explored for countermeasure development. In this study, existing deep learning frameworks are categorized into four groups, namely, spectrogram based deep neural networks (DNN), handcraft features based DNN, source features based DNN and end-to-end DNN frameworks. They have demonstrated notable performances in replay speech detection context. However, their generalisation remains questionable due to the potential challenges posed by unknown types of replay attacks in the future. The study highlights that excitation source features explorations in DNN framework are limited. The study also discussed few existing Gaussian mixture model (GMM) based excitation source explorations, indicating better results may be obtained over existing solutions, using alternative source features based GMM/DNN methods in future. Hence, excitation source information (either implicit or explicit form) may be further explored with GMM/DNN methods. The study concludes with a discussion on potential of excitation source information in replay detection context, following with possible future directions using source information. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Hot Deformation Characteristics and Tool Wear Morphology of GH4169 Super Alloy: A Frugal Usage of Cryogenic Cooling During Turning Process

引用

Journal of The Institution of Engineers (India): Series D 2025年 1-13页

作者： Vinod, B. Sudhakiran, P. Reddy, S. Sunil Kumar Pasupulati, Baburao Department of Mechanical Engineering Siddharth Institute of Engineering & Technology Puttur India Department of Electronics and Communication Engineering New Horizon College of Engineering Bangalore India Department of Electrical and Electronics Engineering Veltech Rangarajan Dr. Sagunthala R & D Institute of Science and Technology Avadi India

Demand for nickel-based superalloys has increased significantly in the automotive industry because of their great potential to reduce the weight of components and improve efficiency. The present study aims to improve the tribological performance and tool lifespan of the GH4169 alloy through machining, focusing specifically on the potential benefits of using cryogenic cooling. It has better wear and mechanical properties to make this alloy more competitive and viable. Hence, the experiments are conducted under liquid nitrogen (LN2), carbon dioxide (CO2), and minimum quantity lubrication (MQL) conditions. The critical tool wear factors have been investigated. The test results proved that cryogenic cooling with the inclusion of MQL helps improve tool life with better tribological characteristics. Furthermore, a hot deformation test was also performed to identify the material’s behavior. The results indicate that flow curves led to smooth regions controlled at low-temperature and high-strain rates. The formation of DRX structures in the processing map is crucial to improving the mechanical properties of these cast components. The Brinell hardness of nickel-based alloys improved after using cooling conditions. Applying the minimum quantity of lubrication cooling conditions exhibits a high hardness of 498 BHN, a 41% increase compared to other conditions. © The Institution of Engineers (India) 2025.

关键词： Strain rate

来源：评论

学校读者我要写书评

暂无评论

Fake Face Detection Based on Fusion of Spatial Texture and High-Frequency Noise

引用

Chinese Journal of electronics 2025年第1期34卷 212-221页

作者： Dengyong Zhang Feifan Qi Jiahao Chen Jiaxin Chen Rongrong Gong Yuehong Tian Lebing Zhang Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation School of Computer and Communication Engineering Changsha University of Science and Technology School of Computer and Communication Engineering Changsha University of Science and Technology Changsha Social Work College Changkuangao Beijing Technology Co. Ltd. School of Computer and Artificial Intelligence Huaihua University

The rapid development of the Internet has led to the widespread dissemination of manipulated facial images, significantly impacting people's daily lives. With the continuous advancement of Deepfake technology, the generated counterfeit facial images have become increasingly challenging to distinguish. There is an urgent need for a more robust and convincing detection method. Current detection methods mainly operate in the spatial domain and transform the spatial domain into other domains for analysis. With the emergence of transformers, some researchers have also combined traditional convolutional networks with transformers for detection. This paper explores the artifacts left by Deepfakes in various domains and, based on this exploration, proposes a detection method that utilizes the steganalysis rich model to extract high-frequency noise to complement spatial features. We have designed two main modules to fully leverage the interaction between these two aspects based on traditional convolutional neural networks. The first is the multi-scale mixed feature attention module, which introduces artifacts from high-frequency noise into spatial textures, thereby enhancing the model's learning of spatial texture features. The second is the multi-scale channel attention module, which reduces the impact of background noise by weighting the features. Our proposed method was experimentally evaluated on mainstream datasets, and a significant amount of experimental results demonstrate the effectiveness of our approach in detecting Deepfake forged faces, outperforming the majority of existing methods.

关键词： Deepfakes Adaptation models Attention mechanisms Noise Transforms Transformers Feature extraction Internet Convolutional neural networks Faces

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：