检索结果-内蒙古大学图书馆

A Smart CIoT with Secure Healthcare Framework Using Optimized Deep Recuperator Neural Network Long Short-Term Memory

引用

IEEE Internet of Things Journal 2024年第6期11卷 10551-10562页

作者： Narmatha, C. Manimurugan, S. Karthikeyan, P. University of Tabuk Faculty of Computers and Information Technology Tabuk71491 Saudi Arabia Oakland University Department of Electrical and Computer Engineering RochesterMI112345 United States National Chung Cheng University Department of Computer Science and Information Engineering Chiayi62102 Taiwan RV University School of Computer Science and Engineering Bengaluru560059 India

The healthcare system currently relies on the facility to store and process large amounts of health data, supported by efficient management. The Internet of Things (IoT) has driven the growth of Adroit Healthcare, which has vast data processing capabilities and extensive data collection. The consumer IoT (CIoT), also known as the IoT in the context of individual use cases, is dominated by personal healthcare applications. The remarkable expansion of the CIoT can be attributed to the extensive embrace of wearable technology, facilitating everyday monitoring of vital health indicators like blood pressure, heart rate, and respiration rate. However, the CIoT raises concerns about data security, confidentiality, and customer trust. This study proposes an integrating blockchain and deep learning (DL) approach to promote responsible use of CIoT. The study develops an Intelligent IoT (IIoT) and healthcare diagnostic model, named BT-PWO-DRNN-LSTM, using blockchain technology and Prairie Wolf optimization-based deep recuperator neural network (DRNN) and long short-term memory (LSTM). The BT-PWO-DRNN-LSTM approach includes three key processes: 1) encrypted transactions;2) cryptographic hash feature;and 3) medical diagnosis. The PWO technique is used for secure communication of medical images, the neighborhood catalogue disposition (NCD) technique is used in the cryptographic hash feature operation (CHFO), and the DL approach is employed as a classification algorithm for diagnosing disorders. The use of PWO methodology for secure healthcare communication and optimal parameter fine-tuning highlights the originality of the study. The BT-PWO-DRNN-LSTM prototype showed positive results with high sensitivity, specificity, and accuracy during the diagnostic process. © 2014 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Motion Retargeting from Human in Video to 3D Characters with Different Skeleton Topology 4

Motion Retargeting from Human in Video to 3D Characters with...

引用

4th International Conference on Consumer Electronics and computer engineering, ICCECE 2024

作者： Guo, Hao Li, Shujie Jia, Wei Hefei University of Technology Department of Computer Science and Information Engineering Hefei China

ISBN: (纸本)9798350384062

Motion retargeting from videos to 3D virtual character is a challenging task in computer vision and computer graphics. A solution is first to extract the 3D motion sequences from videos using human pose estimation algorithm and then retarget to 3D virtual character by skeleton motion retargeting algorithm. However, manual skeleton mapping is often necessary because of the difference in skeleton topology between pose estimation and 3D virtual character, introducing uncertainty and potentially compromising the semantics of the original motion. Additionally, the results of pose estimation contain noise while existing skeleton motion retargeting algorithms do not consider the influence of noise inputs in their design. In response to the above issues, we propose a novel motion retargeting framework and introduce a new motion retargeting network named CTBRnet (Combined Transformer Bi-LSTM Retargeting network). The framework leverages existing algorithm to generate paired training data, providing supervision to CTBRnet and enabling CTBRnet to learn potential skeleton mapping. The framework utilizes human motion videos as input and generates retargeting results for virtual characters, which are driven by joint rotations aligned with the virtual character's skeletal topology. Our proposed network combines transformer and Bi-LSTM, effectively capturing stable high-dimensional motion features from noisy results of pose estimation in both global and local perspectives. The experimental results show that our framework can achieve motion retargeting from videos to 3D virtual character with different skeleton topology, and compared with existing skeleton motion retargeting networks, CTBRnet reduces joint position errors while enhancing the smoothness. © 2024 IEEE.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Optimized Power Allocation in Downlink NOMA with Imperfect Successive Interference Cancellation

Optimized Power Allocation in Downlink NOMA with Imperfect S...

引用

2024 IEEE Region 10 Conference, TENCON 2024

作者： Biswas, Soumik Bera, Debasish Indian Institute of Information Technology Department of Electronics and Communication Engineering Kalyani India Indian Institute of Information Technology Department of Computer Science and Engineering Kalyani India

ISBN: (纸本)9798350350821

It is expected that physical-layer security will finally thrive to provide an extra layer of defence for a variety of devices in next-generation 6G wireless communication. In this work, physical-layer security using non-orthogonal multiple access (NOMA) with single-input-single-output (SISO) assumptions are considered where the users and eavesdroppers are spatially uniformly deployed. The channels between the transmitter (base station (BS)) and the NOMA users and eavesdroppers are considered to be independent Nakagami-m. We analyse the secrecy sum rate (SSR) of the NOMA system in the case of imperfect successive interfere cancellation (SIC) and propose an optimised power allocation scheme with minimised transmit power requirement to satisfy the Quality of Service (QoS) for all legitimate users. Closed-form solutions for the SSR are also derived. The performance of the proposed schemes has been evaluated both by analysis and by simulations. Results are evaluated for a wide range of the signal-to-noise ratio (SNR). © 2024 IEEE.

关键词： Channel state information

来源：评论

学校读者我要写书评

暂无评论

Gannet Optimization Algorithm Enhanced by Quasi-Affine Transformation Algorithm and Its Application in 3D Coverage of Wireless Sensor Network

Journal of Network Intelligence

引用

Journal of Network Intelligence 2024年第1期9卷 69-87页

作者： Peng, Yun-Feng Chu, Shu-Chuan Wang, Ru-Yu Zhao, Jia Pan, Jeng-Shyang School of Computer Science Northeast Electric Power University Jilin132012 China College of Computer Science and Engineering Shandong University of Science and Technology Qingdao266590 China School of Information Engineering Nanchang Institute of Technology Nanchang330099 China Department of Information Management Chaoyang University of Technology Taichung41349 Taiwan

The gannet optimization algorithm (GOA) is an effective group intelligence algorithm inspired by the foraging behavior of gannets. Despite its merits, considerable potential exists for enhancing its exploration and convergence capabilities. A gannet optimization algorithm improved by the quasi-affine transformation evolutionary algorithm, restart strategy, and elite selection strategy (QRE-GOA) is proposed in this paper. The algorithm employs the quasi-affine transformation evolutionary algorithm (QUATRE) to matrix the gannet optimization algorithm to search for optimal solutions more accurately. The use of a restart strategy and elite selection can be more effective in preventing the algorithm from falling into local optimal solutions. Comparative experiments were conducted using the CEC2017 benchmark series. A detailed analysis was conducted, we per-formed a detailed analysis to check the accuracy and convergence speed of the algorithm search in different dimensions. Subsequently, a comprehensive analysis was undertaken to assess the accuracy and convergence speed of the algorithm’s search process across various dimensions. The experimental statistical results show that the new algorithm has stronger exploration ability and better convergence ability than the original algorithm. In addition, this paper focuses on process justification so that the experimental results are reliable, trustworthy, and interpretable. Finally, the newly proposed QRE-GOA algorithm is deployed to address the 3D Coverage challenge in Wireless Sensor Networks. Experimental findings unequivocally demonstrate the superior performance of QRE-GOA. These results, underscore its potential for addressing existing limitations in optimization methods. © 2024, Taiwan Ubiquitous information CO LTD. All rights reserved.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

A Novel 3D InceptionNet Model: Architecture and Applications in Hyperspectral Brain Image Classification 8

A Novel 3D InceptionNet Model: Architecture and Applications...

引用

8th IEEE International Conference on information and Communication technology, CICT 2024

作者： Singh, Raj Bahadur Datta, Aloke The Lnm Institute of Information Technology Department of Computer Science and Engineering Jaipur India

ISBN: (纸本)9798331531539

Glioblastoma is an aggressive type of brain cancer with a high mortality rate. Early and accurate glioblastoma detection is crucial for timely and effective treatment. Hyperspectral Imaging (HSI) has emerged as a promising tool for brain tumor detection, as it can capture detailed spectral information that can be leveraged for classification. This paper proposes a novel modified deep learning architecture named 3D InceptionNet to classify hyperspectral brain images. 3D InceptionNet combines the advantages of 3D convolutional layers and the InceptionNet module to extract and learn discriminative features from the 3D hyperspectral data. To demonstrate the efficacy of our proposed approach, we evaluated its performance on an in-vivo hyperspectral brain image dataset using various performance measures. © 2024 IEEE.

关键词： Hyperspectral imaging

来源：评论

学校读者我要写书评

暂无评论

Early Detection of Alzheimer's Disease based on the State-Of-The-Art Deep Learning Approach 7

Early Detection of Alzheimer's Disease based on the State-Of...

引用

7th IEEE Pune Section International Conference, PuneCon 2024

作者： Bagade, Virendra Godse, S.P. Vishwakarma Institute of Information Technology Department of Computer Engineering Maharashtra Pune India

ISBN: (纸本)9798331527822

In this paper, we introduce a deep convolutional neural network architecture, code-named Inception, which sets a new benchmark for classification and detection tasks. Early detection of Alzheimer's disease (AD) is critical, as the brain is the primary organ affected, and early intervention can help slow disease progression. Traditionally, AD diagnosis relies heavily on MRI scans, a process that is both time-consuming and resource-intensive. However, recent advancements in artificial intelligence (AI) present promising solutions for more efficient detection. This study examines the application of various Convolutional Neural Network (CNN) models for detecting AD in MRI images. A comprehensive comparison was performed on four distinct CNN architectures - Inception-V3, ResNet-152, VGG16, and VGG19 - using MRI data from the Alzheimer's Disease Neuroimaging Initiative (ADNI). The images were categorized into four classes: Non-Demented, Very Mild Demented, Mild Demented, and Moderate *** convolutional neural networks (CNNs) excel at identifying advanced dementia stages (Stages 5-7), accurately classifying the earliest, most elusive stages (Stages 2-4) remains a significant challenge. This paper tackles this crucial gap by systematically comparing various CNN models to achieve promising classification accuracy for these crucial early stages of dementia. Through rigorous analysis, we aim to advance the field of dementia detection by enabling earlier diagnosis and intervention, ultimately improving patient outcomes. Therefore, the application of machine learning technology can assist healthcare professionals in enhancing their efforts to combat Alzheimer's, a serious medical condition. © 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

Lung Cancer Detection Using Machine Learning and Deep Learning Models 21

Lung Cancer Detection Using Machine Learning and Deep Learni...

引用

21st International Multi-Conference on Systems, Signals and Devices, SSD 2024

作者： Alheeti, Khattab M. Ali Al-Shouka, Tabreer T. Majeed, Saleem Hamad Ahmed, Amjed Abbas College of Computer and Information Technology University of Anbar Computer Networking Systems Department Anbar Iraq College of Computer and Information Technology University of Anbar Computer Sciences Department Anbar Iraq Department of Computer Techniques Engineering Baghdad Iraq

ISBN: (纸本)9798350374131

technology and artificial intelligence play a significant role in improving healthcare and enable tasks to be automated. In addition, the diseases can be better understood and diagnosed faster, saving time and reducing costs. This study examines the impact of transfer learning models on the effectiveness of deep learning models in classifying lung cancer through the analysis of CT scan images. Additionally, it investigates the relative performance of various machine learning and deep learning models, encompassing Support Vector Machine (SVM) and convolutional neural net-works (CNN) such as InceptionV3, VGG16, Xception, ResNet50, and MobileNetV2, in the early detection of lung cancer based on CT scan images. The SVM model achieved an overall accuracy of 89% after preprocessing, the proposed approach was applied to five pre-trained models (ResNet50, In-ceptionV3, VGG16, Xception, MobileNetV2) using the dataset: Chest CT-Scan;Among the pre-trained CNN models, the Mo-bileNetV2 model achieved the highest accuracy of 98% and the lowest test loss, indicating it performed the best. The Xception model achieved the second-highest accuracy of 97%. The image pre-processing phase plays a significant role in im-proving system performance in terms of improving image contrast and increasing processing speed. © 2024 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Function Scheduling with Data Security in Serverless Computing Systems 17

Function Scheduling with Data Security in Serverless Computi...

引用

17th International Conference on COMmunication Systems and NETworkS, COMSNETS 2025

作者： Saha, Srestha Pandey, Arvind Addya, Sourav Kanti Brata Nath, Shubha Indian Institute of Information Technology Department of Computer Science and Engineering Guwahati India SRM Institute of Science and Technology Department of Computer Science and Engineering Tamil Nadu India National Institute of Technology Karnataka Department of Computer Science and Engineering Surathkal India

ISBN: (纸本)9798331531195

In serverless computing, the service provider takes full responsibility for function management. However, serverless computing has many challenges regarding data security and function scheduling. To address these challenges, we have proposed a system to secure the data of an end-user. We also aim to meet the quality of service (QoS) for the end-user requests. This work presents a Simulated Annealing-based optimization algorithm for function placement. Also, we have Hyperledger Fabric, a blockchain framework in the system architecture for securing the data of an end-user. We have conducted experiments in Amazon Elastic Compute Cloud (EC2) taking virtual machine instances. The experiments in Amazon EC2 indicate that the proposed system secures the data and enhances the end-user's QoS. © 2025 IEEE.

关键词： Simulated annealing

来源：评论

学校读者我要写书评

暂无评论

Smart IoT System for Cardiopulmonary Resuscitation Training: Embedded Sensor Integration and Android Application 2

Smart IoT System for Cardiopulmonary Resuscitation Training:...

引用

2nd International Symposium on information technology and Digital Innovation, ISITDI 2024

作者： Aisuwarya, Ratna Erlina, Tati Mitzi, Richo Attir Universitas Andalas Faculty of Information Technology Computer Engineering Department Padang Indonesia

ISBN: (纸本)9798350389241

Lack of awareness and experience in CPR often discourages individuals from initiating rescue actions of Out-of-hospital cardiac arrest (OHCA). This research presents a new approach to CPR training using embedded system-based devices. This system, which resembles the human body's torso and head sections, monitors and calculates key parameters critical to successful CPR, including compression, airway management, and breathing techniques. Sensor nodes are placed to measure pressure during compression and monitor airway and respiratory processes. The collected data is transmitted and processed using Internet of Things (IoT) technology with a multi-user Android application, facilitating collaborative training sessions. Experimental testing validated the system's functional capabilities with successful network connection, real-time data transmission, and effective execution of CPR procedures. Hardware implementations use microcontrollers and sensors, with Arduino and NodeMcu ESP8266 enabling data processing and transmission. Software components developed within the Arduino IDE and Android Studio ensure efficient data handling and visualization. The results highlight the system's effectiveness in improving the accessibility and affordability of CPR training, potentially improving intervention by witnesses, and improving OHCA survival rates. © 2024 IEEE.

关键词： Resuscitation

来源：评论

学校读者我要写书评

暂无评论

Parametrized Optimization Based on an Investigation of Musical Similarities Using SPARK and Hadoop

引用

SN computer Science 2024年第1期5卷 78页

作者： Chaudhary, Savita Karthik, V. Shankar, R. Taranum, Ayesha Naresh, E. Department of Computer Science and Engineering Sir M Visvesvaraya Institute of Technology Bengaluru Bengaluru India Department of Information Science and Engineering Ramaiah Institute of Tech B’lore India Department of Computer Science and Engineering BMS Institute of Technology and Engineering Bengaluru India Department of Computer Science and Engineering Vidyavardhaka College of Engineering Mysuru India Department of Information Technology Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India

The big data processing framework Spark is used to power a parameterizable recommender system that can make recommendations for music based on a user’s individual tastes and take into account a variety of musical tonal qualities. The system as it is presently built is completely scalable, which means that additional songs can be contributed to the data, the cluster size could be increased, and new types of audio information, in addition to more cutting-edge similarity evaluations, may be included. Another issue discussed in this research paper is the parallel collection of required audio characteristics on a computer cluster. Song recommendations for a dataset including more than 114,000 songs may be created on a Spark cluster with 16 nodes in under 12 s by integrating eight distinct audio feature types and similarity assessments. After the features have been retrieved, they are sent to the Spark-based recommender system to be processed. The calculated distance was displayed, examined, and graphically depicted. By computing the distance depending on the melody, rhythmic, and timbral components of the music, the final software controls song suggestion. © 2023, The Author(s).

关键词： Big data Hadoop Music information retrieval Optimization Spark

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：