检索结果-内蒙古大学图书馆

3rd IEEE International Conference on Distributed Computing and Electrical Circuits and Electronics, ICDCECE 2024

作者： Edara, Venkata Sandeep Kulkarni, R.N. Sasi Institute Of Technology And Engineering Affiliated To Vtu Belagavi Department Of Computer Science And Engineering Andhra Pradesh Tadepalligudem India Ballari Institute Of Technology And Management Department Of Computer Science And Engineering Karnataka Ballari India

ISBN: (纸本)9798350318609

During the last three decades, the importance of the application software is tremendously increased. Every organization has automated all their day-to-day activities. For automation purpose they used the procedural or object-oriented programming languages. During the 1990's to 2010 many organizations used C++ programming language for the development of application software. Today because of the changes in Hardware and Software technology the C++ programming is not much widely used. But these applications require trained experts to maintain the system otherwise it becomes legacy system. These Legacy systems are at the heart of many outstanding companies. Although they are still essential to the general operation of the business, their solutions are out-of-date and, in certain circumstances, no longer even supported by the original software developer or vendor. Abstracting any reusable components from these systems is difficult. These systems can be modernized as to stay competitive by adding current sustainable features. In this paper, a methodology is proposed to abstract the design information which is a reusable component from the given input legacy C++ program in form of Control Flow and Data Flow Tables. © 2024 IEEE.

关键词： Application programs

来源：评论

学校读者我要写书评

暂无评论

Systematic Selection of a Suitable Data Imputation Technique Based on Data Characteristics

引用

SN computer science 2025年第5期6卷 1-19页

作者： Sebastian, Anu Maria Peter, David Artificial Intelligence Lab Department of Computer Science Cochin University of Science and Technology Kerala Cochin India Department of Computer Science and Engineering Indian Institute of Information Technology Kottayam India

Analyzing incomplete data is one of the prime concerns in data analysis. Discarding the missing records or values might result in inaccurate analysis outcomes or loss of helpful information, especially when the size of the data is small. A preferable alternative is to substitute the missing values using imputation such that the substituted values are very close to the actual missing values and this is a challenging task. In spite of the existence of many imputation algorithms, there is no universal imputation algorithm that can yield the best values for imputing all types of datasets. This is mainly because of the dependence of the imputation algorithm on the inherent properties of the data. These properties include type of data distribution, data size, dimensionality, presence of outliers, data dependency among the attributes, and so on. In the literature, there exists no straightforward method for determining a suitable imputation algorithm based on the data characteristics. The existing practice is to conduct exhaustive experimentation using the available imputation techniques with every dataset and this requires a lot of time and effort. Moreover, the current approaches for checking the suitability of imputations cannot be done when the ground truth data is not available. In this paper, we propose a new method for the systematic selection of a suitable imputation algorithm based on the inherent properties of the dataset which eliminates the need for exhaustive experimentation. Our method determines the imputation technique which consistently gives lower errors while imputing datasets with specific properties. Also, our method is particularly useful when the real-world data do not have the ground truth for missing data to check the imputation performance and suitability. Once the suitability of a DI technique is established based on the data properties, this selection will remain valid for another dataset with similar properties. Thus, our method can save time an

关键词： Data analysis Data distribution Data imputation Data preprocessing Imputation performance Machine learning Missing value handling

来源：评论

学校读者我要写书评

暂无评论

GRA: Graph Representation Alignment for Semi-Supervised Action Recognition

引用

IEEE Transactions on Neural Networks and Learning Systems 2024年第9期35卷 11896-11905页

作者： Huang, Kuan-Hung Huang, Yao-Bang Lin, Yong-Xiang Hua, Kai-Lung Tanveer, M. Lu, Xuequan Razzak, Imran National Taiwan University of Science and Technology Department of Computer Science and Information Engineering Taipei10607 Taiwan Indian Institute of Technology Indore Department of Mathematics Indore Simrol453552 India La Trobe University Department of Computer Science and IT MelbourneVIC3086 Australia University of New South Wales School of Computer Science and Engineering SydneyNSW2052 Australia

Graph convolutional networks (GCNs) have emerged as a powerful tool for action recognition, leveraging skeletal graphs to encapsulate human motion. Despite their efficacy, a significant challenge remains the dependency on huge labeled datasets. Acquiring such datasets is often prohibitive, and the frequent occurrence of incomplete skeleton data, typified by absent joints and frames, complicates the testing phase. To tackle these issues, we present graph representation alignment (GRA), a novel approach with two main contributions: 1) a self-training (ST) paradigm that substantially reduces the need for labeled data by generating high-quality pseudo-labels, ensuring model stability even with minimal labeled inputs and 2) a representation alignment (RA) technique that utilizes consistency regularization to effectively reduce the impact of missing data components. Our extensive evaluations on the NTU RGB+D and Northwestern-UCLA (N-UCLA) benchmarks demonstrate that GRA not only improves GCN performance in data-constrained environments but also retains impressive performance in the face of data incompleteness. © 2012 IEEE.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

Machine Learning for Data Fusion:A Fuzzy AHP Approach for Open Issues

引用

computers, Materials & Continua 2023年第12期77卷 2899-2914页

作者： Vinay Kukreja Asha Abraham K.Kalaiselvi K.Deepa Thilak Shanmugasundaram Hariharan Shih-Yu Chen Chitkara University Institute of Engineering and Technology Chitkara UniversityPunjab140401India Department of Networking and Communications SRM Institute of Science and TechnologyKattankulathurChengalpattuTamil Nadu603203India Department of Networking and Communications Faculty of Engineering and TechnologySRM Institute of Science and TechnologyKattankulathurChengalpattuTamil Nadu603203India Department of Computer Science and Engineering Vardhaman College of EngineeringHyderabad501218India Department of Computer Science and Information Engineering National Yunlin University of Science and TechnologyYunlin64002Taiwan Intelligence Recognition Industry Service Research Center National Yunlin University of Science and TechnologyYunlin64002Taiwan

Data fusion generates fused data by combining multiple sources,resulting in information that is more consistent,accurate,and useful than any individual source and more reliable and consistent than the raw original data,which are often imperfect,inconsistent,complex,and *** data fusion methods like probabilistic fusion,set-based fusion,and evidential belief reasoning fusion methods are computationally complex and require accurate classification and proper handling of raw *** fusion is the process of integrating multiple data *** filtering means examining a dataset to exclude,rearrange,or apportion data according to the *** sensors generate a large amount of data,requiring the development of machine learning(ML)algorithms to overcome the challenges of traditional *** advancement in hardware acceleration and the abundance of data from various sensors have led to the development of machine learning(ML)algorithms,expected to address the limitations of traditional ***,many open issues still exist as machine learning algorithms are used for data *** the literature,nine issues have been identified irrespective of any *** decision-makers should pay attention to these issues as data fusion becomes more applicable and successful.A fuzzy analytical hierarchical process(FAHP)enables us to handle these *** helps to get the weights for each corresponding issue and rank issues based on these calculated *** most significant issue identified is the lack of deep learning models used for data fusion that improve accuracy and learning quality weighted *** least significant one is the cross-domain multimodal data fusion weighted 0.076 because the whole semantic knowledge for multimodal data cannot be captured.

关键词： Signal level fusion feature level fusion decision level fusion fuzzy hierarchical process machine learning

来源：评论

学校读者我要写书评

暂无评论

DICNet: A Novel CNN Model based on DenseNet with Interleaved Convolutional Block Attention Module for the Classification of Breast Cancer Histopathology Images

DICNet: A Novel CNN Model based on DenseNet with Interleaved...

引用

2024 International Conference on Smart Systems for Applications in Electrical sciences, ICSSES 2024

作者： Kumar, Arvind Singh, Chandan Sachan, Manoj Kumar Sant longowal Institute of Engineering and Technology Department of Computer Science and Engineering Sangrur India Punjabi University Department of Computer Science Patiala India

ISBN: (纸本)9798350364040

Histopathology image analysis is crucial for the accurate diagnosis of breast cancer (BC), which is the most prevalent cancer among women. The prompt secondary opinions based on automated analysis can assist pathologists, reduce workload, and minimize interobserver variability. This paper introduces the DICNet, a novel convolutional neural network (CNN) architecture based on DenseNet with interleaved convolutional block attention module (CBAM) to classify the BC histopathology images. Specifically, the interleaved attention mechanism utilizes inter-channel and inter-spatial relationships among convolutional features to accentuate more informative and discriminative features. Furthermore, the pooled responses from multiple convolutional layers with varying spatial resolutions are concatenated to obtain a multi-scale representation. The classification performance of the proposed model is evaluated on the publicly available benchmark BreaKHis dataset with four magnification levels. The proposed DICNet model achieves an overall best classification accuracy of 94.02 % at the 40× magnification level. Additionally, DICNet demonstrates enhanced classification performance at every magnification level, and significantly outperforms existing state-of-the-art approaches. © 2024 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

QMCS-IAS: Quantum mechanism and compression sensing-based image authentication and security technique

引用

Multimedia Tools and Applications 2024年 1-27页

作者： Singh, Ranjeet Kumar Tripathi, Kuldeep Narayan Kaur, Gagandeep Agrawal, Rohit Department of Computer Science and Engineering Madhav Institute of Technology & ampScience Race Course Road MP Gwalior474005 India

Ensuring the security and protection of digital content transmitted over a network is a critical challenge, as data can take various forms, such as text, images, audio, and videos, all of which can be easily manipulated by hackers. Watermarking is one of the practical approaches to address data authentication, copyright protection, and document ownership issues. The primary objective of this research is to develop hybrid watermark encryption and as well as compression of watermark embedding mechanism that ensures secure and efficient watermarking of images using quantum chaos maps and discrete wavelet transformation. This study also introduces a novel dual watermarking approach combining quantum chaos-based encryption and discrete wavelet transformation to achieve robust watermark embedding, also its maintain the capacity of watermarked images. The method involves encrypting watermark components using measurement matrices derived from quantum chaos maps, followed by pixel exchange procedures and embedding into specific frequency sub-bands of the host image, thereby enhancing both the security and quality of watermarking. The objective of this work is to maintain the capacity of watermarked images during the dual embedding process using a compression mechanism. Experimental results show the proposed approach consistently outperforms the existing approach in terms of watermark image quality and robustness. The correlation coefficient (CC) coefficients for the proposed algorithm generally range between 0.95 and 0.99, indicating superior watermark preservation and retrieval capabilities. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Model to Detect Fake News about COVID-19

引用

Recent Advances in computer science and Communications 2023年第9期16卷 58-66页

作者： Shanmugavel, Selva Birunda Rangaswamy, Kanniga Devi Muthukannan, Muthiah Department of Computer Science and Engineering Kalasalingam Academy of Research and Education Tamil Nadu India School of Computer Science and Engineering Vellore Institute of Technology Chennai Tamil Nadu Chennai India Department of Civil Engineering KCG College of Technology Chennai India

Aims/Background: Twitter has rapidly become a go-to source for current events coverage. The more people rely on it, the more important it is to provide accurate data. Twitter makes it easy to spread misinformation, which can have a significant impact on how people feel, especially if false information spreads around COVID-19. Methodology: Unfortunately, twitter was also used to spread myths and misinformation about the illness and its preventative immunization. So, it is crucial to identify false information before its spread gets out of hand. In this research, we look into the efficacy of several different types of deep neural networks in automatically classifying and identifying fake news content posted on social media platforms in relation to the COVID-19 pandemic. These networks include long short-term memory (LSTM), bi-directional LSTM, convolutional-neural-networks (CNN), and a hybrid of CNN-LSTM networks. Results: The "COVID-19 Fake News" dataset includes 42,280, actual and fake news cases for the COVID-19 pandemic and associated vaccines and has been used to train and test these deep neural networks. Conclusion: The proposed models are executed and compared to other deep neural networks, the CNN model was found to have the highest accuracy at 95.6%. © 2023 Bentham science Publishers.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

IWF-ECTIC: Improved Wiener filtering and ensemble of classification model for tourism image classification

引用

Multimedia Tools and Applications 2024年 1-38页

作者： Bhosale, Tejaswini A. Pushkar, S. Department of Computer Science and Engineering Birla Institute of Technology Jharkhand Mesra835215 India Birla Institute of Technology Ranchi Mesra835215 India

Social media is so widely used;travelers frequently post texts, photos, and videos about their experiences online. These user-generated content (UGCs) significantly affect how travelers perceive Tourist Destination Image (TDI) and directly influence their decision-making. UGC photos represent passengers' visual preferences for a certain place. Considering the significance of photographs, a lot of researchers have tried to analyze them using machine learning methods. Nevertheless, a limitation of research efforts employing these techniques for tourism image analysis is that they cannot precisely categorize the unique photos found in specific tourist destinations using predetermined images. In order to get rid of these challenges, this work proposes a Tourism image classification model termed as Improved Weiner Filtering and Ensemble of Classification model for Tourism Image Classification (IWF-ECTIC) model which includes steps like preprocessing, segmentation, feature extraction, and classification. The preprocessing is done via improved wiener filtering which provides a more robust assessment of image quality. The segmentation is done by the Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN) model which can effectively handle outliers and noisy points. Subsequent to the segmentation, MLGBPHS (Modified Local Gabor Binary Pattern Histogram Sequence), MBP (Median Binary Pattern), color, shape and Improved Entropy-based features are extracted in the feature extraction stage to reduce the dimensionality of the data. Finally, ensemble classification is done by combining the Multihead Convolutional Neural Network with Attention Mechanism (MHCNN-AM), Bidirectional Long Short-Term Memory (Bi-LSTM), and Recurrent Neural Network (RNN) classifiers to classify the images. To improve the classification accuracy, optimal training will be done in MHCNN-AM, Bi-LSTM, and RNN classifier using the proposed Cuckoo Updated Chimp Optimization (CUCO) algorit

关键词： Wiener filtering

来源：评论

学校读者我要写书评

暂无评论

Proactive Memory Efficient DDOS Attack Detection at IoT Gateways Through Microneural Networks with Jellyfish Optimizer

引用

SN computer science 2025年第5期6卷 1-16页

作者： Manjula, L. Raju, G.T. Pallavi, N. Department of Artificial Intelligence and Machine Learning BGS College of Engineering and Technology Visvesvaraya Technological University Belagavi India Department of Computer science and Engineering SJC Institute of Technology Visvesvaraya Technological University Belagavi India Department of Computer science and Engineering Ramaiah Institute of Technology Visvesvaraya Technological University Belagavi India

The modernization of IoT technology has introduced new cybersecurity challenges, with Distributed Denial of Service (DDoS) attacks posing significant risks to the availability of IoT services. These attacks disrupt targeted services by overwhelming them with traffic from multiple sources, emphasizing the need for robust detection and mitigation mechanisms. In an IoT context, identifying and mitigating these attacks across diverse network components such as gateways, fully connected nodes, and edge devices is critical to ensuring uninterrupted service delivery. Given the heterogeneity of IoT networks, which include constrained and non-constrained devices like IPv6 over Low-Power Wireless Personal Area Networks (6LoWPAN) and Long Range Wide Area Network (LoRaWAN), mitigation techniques must balance early attack detection with low resource consumption in terms of memory and inference time. To address these challenges, this study introduces a novel Distributed Denial of Service (DDoS) attack detection model that utilizes the Jellyfish (JF) Jaro optimizer for feature selection and a lightweight Micro Neural Network with String Interning (MNNSI) designed specifically for IoT platforms. The Micro Neural Network with String Interning - Jellyfish Jaro Optimizer (MNNSI-JF) approach focuses on automated and efficient attack detection with minimal memory usage. Simulation results on benchmark datasets demonstrate significant performance improvements over prior models, particularly in terms of reduced memory consumption and inference time, which are key performance metrics for evaluating IoT attack detection systems. This highlights the method’s effectiveness in addressing the unique constraints of Internet of Things (IoT) networks. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Bio inspired algorithms DDOS attack detection Internt of things gateways Microneural Networks with jellyfish optimizer Proactive memory efficient

来源：评论

学校读者我要写书评

暂无评论

Incipient motion of sediment by turbulent kinetic energy in the presence of emergent vegetation in the outer sidewall of a bend

引用

ISH Journal of Hydraulic engineering 2025年第2期31卷 139-147页

作者： Rismani, Nasim Afzalimehr, Hossein Asghari-Pari, Seyed-Amin Nazari-Sharabian, Mohammad Karakouzian, Moses Department of Civil Engineering Iran University of Science and Technology Tehran Iran Department of Civil Engineering Behbahan Khatam Alanbia University of Technology Behbahan Iran Department of Mathematics Engineering and Computer Science West Virginia State University Institute WV United States Department of Civil and Environmental Engineering and Construction University of Nevada Las Vegas NV United States

This study examines the influence of vegetation on sediment movement in a 180° river bend with rigid emergent vegetation on the outer side. Using an Acoustic Doppler Velocimeter, researchers collected 504 velocity profiles under conditions with and without vegetation, across four different vegetation densities. The findings indicate that vegetation reduces the critical velocity needed for sediment movement by 59%. Additionally, the presence of vegetation increases turbulent kinetic energy, with the highest levels observed at the lowest vegetation density, and decreasing as vegetation density increases. This pattern suggests that vegetation not only modifies flow dynamics but also affects the threshold conditions for sediment transport, especially on the outer side of the bend. For example, turbulent kinetic energy is amplified 18 times at a 150-degree angle. In contrast, the bare bed exhibited minimal turbulent kinetic energy, underscoring the significant role of vegetation in altering flow structures. This study highlights the critical importance of emergent vegetation in river management and sediment control, demonstrating a more pronounced effect on the outer bend than the inner side, thus contributing to the sustainability and management of natural streams. © 2024 Indian Society for Hydraulics.

关键词： Kinetic energy

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：