检索结果-内蒙古大学图书馆

9th International Conference on Intelligent Computing and Signal Processing, ICSP 2024

作者： Cui, Hongzhen Wang, Shichao Zhu, Xiaoyue Peng, Yunfeng School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China School of Electronics and Information Engineering Liaoning University of Technology Liaoning China

ISBN: (纸本)9798350376548

Segmentation of the right ventricle (RV) holds significant clinical implications for the assessment of cardiac function in conditions such as pulmonary hypertension. Precise delineation of the right ventricle from cardiac magnetic resonance images (CMRI) is crucial in the diagnosis of various cardiac conditions. It provides clinicians with essential information for patient evaluation, treatment planning, and subsequent rehabilitation strategies. Currently, the development of fully automated segmentation models for the right ventricle heavily relies on deep learning techniques, necessitating meticulous manual annotation of CMRI data to achieve optimal segmentation results. However, the labor-intensive nature of labeling CMRI data requires significant medical expertise and consumes considerable time and resources. In response to these challenges, this study proposes a semi-supervised multi-scale segmentation approach for the right ventricle in CMRI. The method leverages unlabeled data to enhance segmentation accuracy while minimizing the reliance on annotated data. Experimental findings demonstrate the effectiveness of the proposed method in accurately delineating the right ventricle from CMRI datasets. © 2024 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Audio Deepfake Detection using Deep Scattering Network 9

Audio Deepfake Detection using Deep Scattering Network

引用

9th International Conference on Communication and electronics Systems, ICCES 2024

作者： Avaiya, Utsav Badlani, Naman Baadkar, Rajas Talele, Kiran Sardar Patel Institute of Technology Department of Computer Engineering Mumbai India Sardar Patel Institute of Technology Department of Electronics and Telecommunication Engineering Mumbai India

ISBN: (纸本)9798350377972

The rise of audio Deepfakes has raised serious concerns about the authenticity of audio content, affecting media, politics, and cybersecurity by enabling misinformation, fraud, and identity theft. To address these challenges, we propose a novel approach to Deepfake detection using a Deep Scattering Network (DSN). Unlike traditional methods that rely on Convolutional Neural Networks (CNNs), which require massive amounts of training data, our approach leverages the Scattering Transform to capture multi-scale time-frequency features, enhancing the detection of subtle anomalies in manipulated audio while requiring significantly less data for training. Additionally, DSNs employ pre-defined multi-scale wavelet filters rather than data-driven linear filters, offering a more interpretable model while retaining a hierarchical structure. Evaluation of a publicly available dataset shows that the DSN outperforms the standard CNN-based models, particularly in scenarios with low-quality or heavily distorted audio. This research underscores the potential of scattering networks in bolstering the security and reliability of audio authentication systems. © 2024 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Harnessing Bio-Inspired Optimization and Swarm Intelligence for Energy-Aware TinyML in IoT 7

Harnessing Bio-Inspired Optimization and Swarm Intelligence ...

引用

7th International Conference on Inventive Computation Technologies, ICICT 2024

作者： Kalyanakumar, P. Pandian, S. Srinivasa Boopalan, S. Jesintha, D. Kani Krishnan, R. Santhana Muthu, A. Essaki Velammal College of Engineering And Technology Department of Information Technology Madurai India Scad College of Engineering And Technology Department of Computer Science And Engineering Cheranmahadevi India Scad College of Engineering And Technology Department of Electronics And Communication Engineering Cheranmahadevi India

ISBN: (纸本)9798350359299

This research investigates the integration of bio-inspired optimization and swarm intelligence principles with TinyML for the development of energy-aware Internet of Things (IoT) devices. A novel model algorithm, termed "BioSwarmML,"is introduced and evaluated against existing algorithms through comprehensive simulation analyses employing suitable metrics. The proposed framework aims to enhance energy efficiency in IoT applications by leveraging the collective intelligence derived from bio-inspired optimization and swarm behaviors. The "BioSwarmML"algorithm is designed to draw inspiration from natural processes, incorporating bio-inspired optimization techniques such as genetic algorithms, simulated annealing, and evolutionary strategies. Concurrently, swarm intelligence principles are integrated to emulate decentralized and self-organizing behaviors observed in biological systems. This amalgamation aims to optimize the energy consumption of TinyML models on IoT devices, facilitating sustainable and adaptive learning processes. Simulation analyses involve a comparative study with established algorithms, evaluating BioSwarmML based on metrics such as energy consumption, accuracy, and latency. The results demonstrate the efficacy of the proposed algorithm in achieving superior energy efficiency while maintaining competitive performance in terms of accuracy and responsiveness. The comparison sheds light on the advantages of BioSwarmML in energy-aware TinyML applications, showcasing its potential for widespread adoption in IoT ecosystems. This research contributes to the advancement of energy-efficient IoT systems by introducing a novel algorithmic paradigm that aligns with international journal standards. The proposed "BioSwarmML"model showcases a promising avenue for enhancing sustainability in TinyML-driven IoT applications, offering a valuable addition to the existing body of knowledge in the field. © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

AI drive: quantum-computational DRL framework for EHV navigational efficiency and security augmentation

引用

Optical and Quantum electronics 2024年第4期56卷 1-23页

作者： Bangroo, Ishan Shivansh Kumar, Ravi Department of Computer and Information Science Engineering University of Florida FL United States Department of Electronics and Communication Engineering Jaypee University of Engineering & Technology MP Guna India

The Q-learning approach, within deep reinforcement learning (DRL) methodology, is beneficial in multifarious tasks, one of them including enhancement of navigational tasks, shown by the DQN approach;merging Q-learning with deep neural networks is not without its challenges, particularly in situations where there is a chance of overestimating the correct value. In order to address the problems described above in the realm of electric and hybrid vehicles (EHVs), a quantum-computational adaptation that is influenced by Double Q-learning as a potential solution is proposed i.e., QED2Q-N. The enhanced version increases the efficacy of navigation by addressing the overestimates, which were included in previous editions, conceived with the intention of approximately modeling functions on a broad scale. The expansion of electric and hybrid vehicles (EHVs) toward growing autonomy, along with improvements in intelligent transportation systems (ITS), pose significant cybersecurity threats in the disciplines of vehicle automation and cooperative ITS. These underlying dangers may be found in the sectors of vehicle automation and cooperative ITS with an emphasis on the ways in which quantum-enhanced systems may assist in strengthening defenses, the use of quantum computing and deep reinforcement learning (DRL) merged together, works to bring improvement in EHV navigation accuracy and the enhancement of overall system security. The study underlines the relevance of adopting a quantum-computing technique in order to properly solve the dynamic issues associated with EHV technology. © 2024, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.

关键词： Climate change Deep reinforcement learning EHVs Quantum artificial intelligence Sustainability

来源：评论

学校读者我要写书评

暂无评论

Object Detection for Low-Illumination Scenes Based on Enhanced Yolov7 Architecture 18

Object Detection for Low-Illumination Scenes Based on Enhanc...

引用

18th International Symposium on Information Theory and Its Applications, ISITA 2024

作者： Lin, Chia Hsien Peng, Guan-Jie Lin, Chang Hong National Taiwan University of Science and Technology Department of Electronics and Computer Engineering Taipei City106 Taiwan

ISBN: (纸本)9784885523519

This article proposes a novel approach to object detection in low-illumination conditions, an area where existing methods often fall short. By recognizing the crucial role of image quality in subsequent detection accuracy, we introduce preprocessing steps involving image enhancement and restoration networks. Our detection network then focuses on enhancing both channel and spatial feature information, integrating adaptive attention mechanisms and a Transformer architecture for contextual understanding. A multi-scale fusion strategy is employed to merge these features effectively. Additionally, we implement a partial cross-stage network to facilitate CNN learning while minimizing model size. Experimental results demonstrate the superiority of our approach over previous methods, showcasing significant accuracy improvements, particularly in challenging scenarios. This work underscores the importance of addressing image quality concerns in object detection tasks, especially in low-illumination environments, and offers a promising solution with practical implications across various domains, including autonomous driving and surveillance. © 2024 The Institute of electronics, Information and Communication Engineers.

关键词： Image quality

来源：评论

学校读者我要写书评

暂无评论

Dynamic Data Placement Strategy with Network Security Issues in Distributed Cloud Environment for Medical Issues: An Overview

引用

Recent Advances in computer Science and Communications 2024年第6期17卷 25-38页

作者： Pradhan, Devasis Behera, Majusha Gheisari, Mehdi Department of Electronics and Communication Engineering Acharya Institute of Technology Karnataka Bangalore560107 India School of Electronics Engineering Campus 12 KIIT deemed to be University Odisha Bhubaneswar India Department of Cognitive Computing Institute of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India

The rapid integration of distributed cloud systems in the healthcare industry has profoundly impacted the management of valuable medical data. While this advancement has significantly improved data handling, protecting sensitive healthcare information in such a complex environment remains daunting. This comprehensive study explores the crucial intersection between dynamic data placement strategies and network security concerns in distributed cloud environments, particularly healthcare. After establishing the significance and context of this research, the survey delves into the growing need to safeguard medical data within the everevolving landscape of cloud-based healthcare systems. It lays out fundamental concepts, such as dynamic data placement and network security, highlighting their unique implications in the medical domain. Ultimately, this survey sheds light on the most effective approaches for balancing dynamic data placement and network security in the healthcare sector. This research delves into examining many tactics, evaluating their effectiveness in handling delicate medical information, and presenting tangible use cases. A key focus of this investigation is the fusion of data organization and network safety within the healthcare industry. It investigates the adaptability of dynamic data positioning techniques in fortifying network security and safeguarding against potential threats unique to the healthcare sector. Case studies of the successful implementation of these strategies in healthcare establishments are also included. © 2024, Bentham Science Publishers. All rights reserved.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Predicting Land Cover Changes with Convolutional LSTM Networks: A Case Study of Chatham, Massachusetts

Predicting Land Cover Changes with Convolutional LSTM Networ...

引用

2024 IEEE International Conference on Modeling, Simulation and Intelligent Computing, MoSICom 2024

作者： Kavitha, J.C. Subitha, D. Bhandari, Divyansh Jaluka, Devesh Kumar Vellore Institute of Technology School of Computer Science and Engineering Chennai600127 India Vellore Institute of Technology School of Electronics and Engineering Chennai600127 India

ISBN: (纸本)9798331533311

Land use and land cover changes has become crucial for natural resource management and monitoring, particularly in urban planning. Remote sensing and geographical information systems analyze the changes in land use and land cover, promoting sustainability. Remote sensing images are the major data sources for land cover classification. High spatial resolution images enable more precise analysis and identification of land cover data types. However, better spatial resolution creates new challenges to the existing classification and prediction methods. This research work outlines a new model that integrates the Convolutional Neural Networks and Long Short-Term Memory network model for the prediction of dynamic changes in land cover patterns from historic satellite images. The proposed model is constructed for Chatham, Massachusetts, prediction from Google Earth timelapse imagery taken over 39 years to compile a sequence of 39 annual satellite images. The images are preprocessed to 256 × 256 pixels and image normalization ensured efficient data handling. The proposed model predicted land cover over the next three years and demonstrated the model's capacity to capture both geographical and temporal patterns in the data. Evaluation of metrics, such as the training and validation loss, showed good performance by the model. Despite some limitations in image resolution and iterative prediction, the findings show that CNN-LSTM models could be very useful for land cover forecasting, providing important guidelines for future study and practical applications in the context of environmental management. © 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

Design and Development of an Intelligent Energy Management System for a Smart Grid to Enhance the Power Quality

引用

Energy engineering 2023年第8期120卷 1747-1761页

作者： Nisha Vasudevan Vasudevan Venkatraman A.Ramkumar T.Muthukumar A.Sheela M.Vetrivel R.J.Vijaya Saraswathi F.T.Josh Department of Electrical and Electronics Engineering Kalasalingam Academy of Research and EducationTamil NaduIndia Department of Computer Science Engineering Kalasalingam Academy of Research and EducationTamil NaduIndia Department of Electrical and Electronics Engineering Kongunadu College of Engineering and TechnologyTamil NaduIndia Department of Electrical and Electronics Engineering Kongu Engineering CollegeTamil NaduIndia Department of Electrical and Electronics Engineering Narasu’s Sarathy Institute of TechnologyTamil NaduIndia Department of Electrical and Electronics Engineering Panimalar Engineering CollegeTamil NaduIndia Department of Electrical and Electronics Engineering Karunya Institute of Technology&SciencesTamil NaduIndia

MigroGrid(MG)has emerged to resolve the growing demand for *** because of its inconsistent output,it can result in various power quality(PQ)*** is a problem that is becoming more and more important for the reliability of power systems that use renewable energy ***,the employment of nonlinear loads will introduce harmonics into the system and,as a result,cause distortions in the current and voltage waveforms as well as low power quality issues in the supply ***,this research focuses on power quality enhancement in the MG using hybrid shunt ***,the performance of the filter mainly depends upon the design,and stability of the *** efficiency of the proposed filter is enhanced by incorporating an enhanced adaptive fuzzy neural network(AFNN)*** performance of the proposed topology is examined in a MATLAB/Simulink environment,and experimental findings are provided to validate the effectiveness of this ***,the results of the proposed controller are compared with Adaptive Fuzzy Back-Stepping(AFBS)and Adaptive Fuzzy Sliding(AFS)to prove its superiority over power quality improvement in *** the analysis,it can be observed that the proposed system reduces the total harmonic distortion by about 1.8%,which is less than the acceptable limit standard.

关键词： Artificial intelligence resistive inductive load shunt hybrid filter smart grid adaptive fuzzy back-stepping power factor

来源：评论

学校读者我要写书评

暂无评论

Enhanced Secure Communication in Wireless Sensor Networks: Quantum Key Distribution with KIRSAN Gate 5

Enhanced Secure Communication in Wireless Sensor Networks: Q...

引用

5th International Conference on electronics and Sustainable Communication Systems, ICESC 2024

作者： Manivannan, Kirankumar Vivekanandan, M. Saranya, G. Kumaran, K. School of Electronics Engineering Vellore Institute of Technology Chennai campus India School of Computer Science and Engineering Vellore Institute of Technology Chennai campus India

ISBN: (纸本)9798350379945

Sensor nodes are integral to wireless sensor networks (WSNs) but their deployment across various locations exposes their communications to potential monitoring. Key challenges include message protection and node identification, necessitating efficient mechanisms for key distribution and management, especially in large-scale networks. Quantum cryptography, specifically quantum key distribution (QKD), offers a method to securely establish keys over short distances, leveraging principles like garbage output reduction and quantum communication for enhanced security. To address these issues, reversible logic gates, such as the newly developed © 2024 IEEE.

关键词： Quantum cryptography

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence-Based Secured Smart Mirror Control Systems with Enhanced Vehicle and Signboard Detection 11th

Artificial Intelligence-Based Secured Smart Mirror Control S...

引用

11th EAI International Conference on Advancement of Science and technology, ICAST 2023

作者： Sanjay, S. Nithish Soorya, S.S. Vengatesh, R. Prakasam, P. Annamalai, Pushparaghavan School of Electronics Engineering Vellore Institute of Technology Vellore India Faculty of Electrical and Computer Engineering Bahirdar University Bahir Dar Ethiopia

ISBN: (纸本)9783031641503

Vehicle accidents have a significant impact on society, and they have a number of detrimental repercussions on individuals, families, and communities. Vehicles are an essential part of everyone’s daily lives in the modern world;therefore, it is very important to drive them in a cautious manner to prevent accidents. A side mirror is very important equipment in a vehicle as it helps drivers with a view of the area behind and to the sides of the vehicle. The proposed work focuses on the enhancement of artificial intelligence (AI)-based automatic side mirror folding systems in addition with vehicle and signboard detection as driver alert measures. The system proposed inspects authorized persons with the help of face detection and fingerprint verification applications provided via individual phones. The signboard detection helps the driver to notice signboards to make necessary adjustments in very crowded traffic areas, and vehicle detection helps the driver to drive in a cautious manner, specifically when taking turns in highly congested areas with the help of Internet of Things (IOT) applications. The system checks for the presence of signboards, monitors the surroundings, and supervises the security of the vehicle using face detection and android app-based fingerprint verification. The proposed AI-based method achieved the 95.5% testing accuracy for unregistered persons with the help of face detection and fingerprint verification. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Mirrors

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：