检索结果-内蒙古大学图书馆

5th International Conference on Data science, Machine Learning and Applications, ICDSMLA 2023

作者： Belwal, Ankit Senthilkumar, S. Alam, Intekhab Jaison, Feon Department of Civil Engineering School of Engineering and Computing Dev Bhoomi Uttarakhand University Dehradun India School of Computer Science and Engineering Presidency University Karnataka Bengaluru India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India Karnataka Bangalore India

ISBN: (纸本)9789819780426

Modern-day time series classification (TSC) in networks has emerged as famous and is presently an energetic research location. However, traditional methods in TSC in networks, including okay-nearest neighbors and help vector machines, require large training units and an extensive computational attempt as they need more capacity to extract complicated capabilities. This paper explores Multi-Layer Perceptrons (MLPs) as an alternative records-pushed approach to tackle the TSC task. We first design experiments to benchmark the performance of trendy MLPs educated on representative time series datasets from diverse domain names. We then look at the different architectures of state-of-the-art MLPs for the TSC hassle by exploring contemporary activation functions and structure variations. In addition, we speak about how distinct initialization techniques and hyperparameters may impact the schooling state-of-the-art MLP version. The outcomes reveal the higher accuracy of the MLPs in TSC networks. Eventually, we gift viable traces of the latest similar investigation for the proposed method. The technical summary explores using multi-layer perceptrons (MLP) for network time collection classification. MLP is a supervised deep mastering class set of rules used to expect time series lessons from entered data. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Flexible Global Aggregation and Dynamic Client Selection for Federated Learning in Internet of Vehicles

引用

Computers, Materials & Continua 2023年第11期77卷 1739-1757页

作者： Tariq Qayyum Zouheir Trabelsi Asadullah Tariq Muhammad Ali Kadhim Hayawi Irfan Ud Din College of Information Technology United Arab Emirates UniversityAl Ain17551UAE Department of Computing School of EECSNational University of Sciences and TechnologyIslamabad44000Pakistan College of Technological Innovation Zayed UniversityAbu Dhabi144534UAE Department of Computer Science The Superior UniversityLahore54000Pakistan

Federated Learning(FL)enables collaborative and privacy-preserving training of machine learning models within the Internet of Vehicles(IoV)*** FL effectively tackles privacy concerns,it also imposes significant resource *** traditional FL,trained models are transmitted to a central server for global aggregation,typically in the *** approach often leads to network congestion and bandwidth limitations when numerous devices communicate with the same *** need for Flexible Global Aggregation and Dynamic Client Selection in FL for the IoV arises from the inherent characteristics of IoV *** include diverse and distributed data sources,varying data quality,and limited communication *** employing dynamic client selection,we can prioritize relevant and high-quality data sources,enhancing model *** address this issue,we propose an FL framework that selects global aggregation nodes dynamically rather than a single fixed *** global aggregation ensures efficient utilization of limited network resources while accommodating the dynamic nature of IoV data *** approach optimizes both model performance and resource allocation,making FL in IoV more effective and *** selection of the global aggregation node is based on workload and communication speed ***,our framework overcomes the constraints associated with network,computational,and energy resources in the IoV environment by implementing a client selection algorithm that dynamically adjusts participants according to predefined *** approach surpasses Federated Averaging(FedAvg)and Hierarchical FL(HFL)regarding energy consumption,delay,and accuracy,yielding superior results.

关键词： IoT Federated Learning sensors IoV OMNeT++ edge computing

来源：评论

学校读者我要写书评

暂无评论

Optimizing Pneumonia Detection Model based on CNVM (CNN-SVM) 2

Optimizing Pneumonia Detection Model based on CNVM (CNN-SVM)

引用

2nd International Conference on Health Big Data and Intelligent Healthcare, ICHIH 2023

作者： Lin, Yuesheng Li, Ting Xie, Hanke Toe, Teoh Teik Lei, Lei The National University of Malaysia School of Information Science and Technology Kuala Lumpur Malaysia Harbin Institute of Technology School of Computing Weihai China Northwestern Polytechnical University School of Computing XiAn China Nanyang Technological University NTU Business AI Lab Singapore Harbin Institute of Technology School of Economics and Management Harbin China

ISBN: (纸本)9798350309324

To improve the precision of the diagnosis of pneumonia, this study presents a unique method that combines Convolutional Neural Networks (CNN) with Support Vector Machines (SVM). Using sophisticated convolution and pooling techniques, the CNN is used to extract complex features from X-ray images, turning the image data into high-dimensional feature vectors. This makes it possible to analyze structural details precisely. These feature vectors are then fed into an SVM classifier, which uses its robust classification abilities to differentiate between cases of pneumonia and non-pneumonia. The SVM builds a solid classification limit after extensive training on a variety of datasets, producing extremely precise diagnoses. In comparison to traditional methods, experimental results show a considerable improvement in pneumonia detection. The combined CNN-SVM technique demonstrates improved sensitivity and specificity, which significantly lowers the rate of misdiagnosis. The model also performs exceptionally well across diverse pneumonia types and severity levels, highlighting its adaptability and dependability. In conclusion, this study offers a novel method for diagnosing pneumonia by combining CNN and SVM. It delivers a considerable improvement in diagnostic precision and has enormous potential to assist clinical judgment in instances of pneumonia. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Forecasting of Groundwater Quality Utilizing an Efficient K-Means with Principal Component Analysis Approach 2

Forecasting of Groundwater Quality Utilizing an Efficient K-...

引用

2nd IEEE International Conference on Integrated Intelligence and Communication Systems, ICIICS 2024

作者： Adnan, Myasar Mundher Manjula, B.M. Mishra, Antim Dev Ganti, Swathi Bala Dhandayuthapani, V. The Islamic University of Babylon Babylon Iraq Department of Electronics and Communication Engineering Nitte Meenakshi Institute of Technology Bengaluru India Department of Computer Science and Engineering School of Engineering and Technology Sushant College Gurgaon India Department of Nano Technology Andhra University Visakhapatnam India Department of Information Technology College of Computing and Information Sciences University of Technology and Applied Sciences Shinas Oman

ISBN: (纸本)9798331504960

Groundwater stands as a pivotal freshwater resource in numerous regions worldwide, but the burgeoning population and diverse economic activities have adversely impacted its quality. However, the K-means algorithm is sensitive to the initial placement of centroids, where outliers can significantly influence the position of centroids resulting in suboptimal clusters. To address this, it is recommended to remove or clip outliers before applying K-means scales well to large datasets making it suitable for handling substantial amounts of data. In this proposed method, attributes are first calculated using Principal Component Analysis (PCA) determines the weight of each attribute based on eigenvalues. The PCA, by determining attribute weights and Rapid Centroid Estimation (RCE), by establishing the initial cluster centre, contribute to the overall effectiveness of the method. The classification step utilizes a Linear Support Vector Machine (SVM), suitable for linear hyper line data when the dataset can be classified into two classes using a single straight line. The results obtained showcase the superiority of the proposed method, achieving a Root Mean Squared Error (RMSE) of 1.23, R-squared (R2) of 0.90, Mean Absolute Deviation (MAD) of 0.28 and E of 0.97 on the Indian groundwater dataset. These outcomes affirm better detection and classification performance compared to other existing methods, such as Random Forest (RF), Decision Tree (DT) and K-Nearest Neighbour (KNN). © 2024 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

A Study of Word Embedding Models for Machine Translation of North Eastern Languages 5th

A Study of Word Embedding Models for Machine Translation o...

引用

5th International Conference on Computational Intelligence in Communications and Business Analytics, CICBA 2023

作者： Nath, Basab Sarkar, Sunita C. Debnath, Narayan Department of Computer Science and Engineering Assam University Silchar India School of Computing and Information Technology Eastern International University Binh Duong Thu Dau Mot Viet Nam

ISBN: (纸本)9783031488788

Neural Machine Translation (NMT) has experienced significant growth in recent years and is now a well-established field. Despite being the most popular machine translation solution, NMT’s performance on low-resource language pairs is inferior to that of high-resource language pairs because of the lack of large parallel corpora for these *** paper explores how pre-trained word embedding models, specifically FastText and Word2Vec, can enhance the translation performance of NMT (neural machine translation) systems for low resource English-Assamese, English-Manipuri, and English-Nepali language pairs. We have compared the performance of NMT systems trained with the use of these pre-trained word embedding models and evaluated the results on test sets of English-Assamese, English-Manipuri, and English-Nepali translations. The resukts indicate that the use of FastText significantly improves the translation performance of NMT systems for both language pairs, with an average increase in BLEU score of 5.6, 7.3, and 4.4 points for English-Assamese, English-Manipuri, and English-Nepali, respectively. We have also discussed the potential challenges and limitations of using pre-trained word embedding models for NMT in low-resource languages and suggested directions for future work in this area. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Idecomp: imbalance-aware decomposition for class-decomposed classification using conditional GANs

引用

Discover Artificial Intelligence 2023年第1期3卷 31页

作者： Buczek, Patryk Zidan, Usama Gaber, Mohamed Medhat Abdelsamea, Mohammed M. School of Computing and Digital Technology Birmingham City University Birmingham100190 United Kingdom Faculty of Computer Science and Engineering Galala University Suez435611 Egypt Department of Computer Science Faculty of Computers and Information Assiut University Assiut71515 Egypt

Medical image classification tasks frequently encounter challenges associated with class imbalance, resulting in biased model training and suboptimal classification performance. To address this issue, the combination of class decomposition and transfer learning has proven to be effective in classifying imbalanced medical imaging datasets. Nevertheless, in order to further augment the performance gains achieved through the utilisation of class decomposition within deep learning frameworks, we propose a novel model coined imbalance-Aware Decomposition for Class-Decomposed Classification (iDeComp) model. By incorporating a conditional Generative Adversarial Network (GAN) model, iDeComp is capable of generating additional samples specifically tailored to underrepresented decomposed subclasses. This paper investigates the application of iDeComp using two different medical imaging datasets. iDeComp selects underrepresented samples from the training set of the sublevel classes within each dataset, which are then employed to train separate conditional Deep Convolutional GAN (DCGAN) models and verification models. The conditional DCGAN model is responsible for generating additional samples, while the verification model critically evaluates the appropriateness of the synthesised images. Subsequently, the resulting augmented samples are utilized to train the classification model. To assess the effectiveness of iDeComp, we employ various evaluation metrics including accuracy, precision, recall, and F1 score. The results obtained from our experiments clearly indicate that iDeComp outperforms existing approaches in terms of classifying both imbalanced datasets. © The Author(s) 2023.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Efficiency in 6G Radio Resource Allocation Using Machine Learning Algorithms 5th

Enhancing Efficiency in 6G Radio Resource Allocation Using M...

引用

5th International Conference on Data science, Machine Learning and Applications, ICDSMLA 2023

作者： Kamalraj, R. Nautiyal, Kshitij Taranum, Ayesha Savita Karnataka Bangalore India Department of Electrical Engineering School of Engineering and Computing Dev Bhoomi Uttarakhand University Dehradun India School of Computer Science and Engineering Presidency University Karnataka Bengaluru India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India

ISBN: (纸本)9789819780426

Using machine gaining knowledge of algorithms with 6G radio resource allocation can assist to enhance network performance by using automating the selection making technique on a cease-to-stop foundation. This paper proposes a more suitable implementation of 6G radio aid allocation the usage of device getting to know algorithms to expand a framework for optimized useful resource utilization. The consequences of the experiments conducted in a real-world testbed validate the effectiveness of the proposed structure in achieving the desired goals consisting of improved community performance and decreased strength consumption. Moreover, the proposed improved implementation might be relevant in a huge range of other resource allocation eventualities. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

The Detection of Mirai Botnet Attack on the Internet of Things (IoT) Device Using Support Vector Machine (SVM) Model 10

The Detection of Mirai Botnet Attack on the Internet of Thin...

引用

10th International Conference on information and Communication technology, ICoICT 2022

作者： Azhari, Revaldi Gilang Suryani, Vera Pahlevi, Rizka Reza Wardana, Aulia Arif School of Computing Telkom University Bandung Indonesia Doctoral School Information and Communication Technology Wroclaw University of Science and Technology Wroclaw Poland

ISBN: (数字)9781665481656

ISBN: (纸本)9781665481656

There are various types of attacks on IoT devices, one of which is Mirai botnet that attacks a number of IoT devices such as web cameras, security cameras, and routers. Even it has caused internet downtime for the users in Europe and North America. Hence, it is deemed necessary to have a system to detect Mirai botnet attack using the Support Vector Machine (SVM) model. This model becomes a solution to detect Mirai botnet attacks for having good generalization performance when the parameter is properly configured in modeling the training set (training dataset) and getting good classification results without a lot of training data. The results of the analysis from the use of the SVM model showed the accuracy of 92.91% with a linear kernel and max_iter 10000. Also, the performance of the Support Vector Machine (SVM) model based on the precision parameter obtained a value of 94.13% with max_iter 10000 and the recall parameter resulted in a value of 91.10% with max_iter 10000. © 2022 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Performance Assessment of Multi-Controller in Software Defined Network 4

Performance Assessment of Multi-Controller in Software Defin...

引用

4th IEEE International Conference on computing, Communication, and Intelligent Systems, ICCCIS 2023

作者： Jaiswal, Ankita Patra, Sudhansu Shekhar Dash, Bibhuti Bhusan Barik, Lalbihari Pandey, Trilok Nath Mishra, Manoj Ranjan School of Computer Engineering KIlT Deemed to Be University Bhubaneswar India King Abdulaziz University Faculty of Computing and Information Technology in Rabigh Department of Information Systems Saudi Arabia School of Computer Science and Engineering Vellore Institute of Technology Chennai India

ISBN: (纸本)9798350306118

In a network design, the control plane and the data plane are separated by the architectural concept of software defined networking (SDN). A centralised controller that serves as the only point of control for the whole network is introduced by the SDN architecture. The controller serves as a logically centralized entity in charge of communicating the appropriate rules to a switch's flow table. Using a single controller to handle a lot of flows becomes insufficient. A lot of large-scale networks have employed multi-controller SDN to meet their objectives. In this research, we use a multi-controller infinite buffer waiting queue model to analyze the system performance metrics. Both numerical and simulated assessments are used to illustrate the proposed model. © 2023 IEEE.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Multi-attribute wearable pressure sensor based on multilayered modulation with high constant sensitivity over a wide range

引用

Nano Research 2023年第5期16卷 7583-7592页

作者： Ning Li Song Gao Yang Li Jianwen Liu Wenhao Song Guozhen Shen School of Information Science and Engineering University of JinanJinan 250022China Shandong Provincial Key Laboratory of Network Based Intelligent Computing University of JinanJinan 250022China School of Integrated Circuits and Electronics Beijing Institute of TechnologyBeijing 100081China School of Aeronautical and Astronautical Engineering Purdue University West LafayetteIN 47907USA

Flexible pressure sensors capable of monitoring diverse physiological signals and body movements have garnered tremendous attention in wearable electronic ***,high constant sensitivity over a wide pressure range combined with breathability,biocompatibility,biodegradability is pivotal for manufacturing of reliable pressure sensors in practical sensing *** this work,inspired by the multilayered structure of skin epidermis,we propose and demonstrate a multi-attribute wearable piezoresistive pressure sensor consisting of multilayered gradient conductive poly(ε-caprolactone)nanofiber membranes *** response to externally applied pressure,a layer-by-layer current path is activated inside the multilayered membranes composites,leading to the most salient sensing performance of high constant sensitivity of 33.955 kPa^(−1) within the pressure range of 0–80 *** proposed pressure sensor also exhibits a fast response–relaxation time,a low detection limit,excellent stability,which can be successfully used to measure human physiological ***,an integrated sensor array system that can locate objects’positions is constructed and applied to simulate sitting posture *** results indicate that the proposed pressure sensor holds great potential in health monitoring and wearable electronic devices.

关键词： wearable pressure sensors multilayer structure high constant sensitivity multi-attribute physiological signals monitoring

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：