检索结果-内蒙古大学图书馆

1st International Conference on Intelligent Systems and Computational Networks, ICISCN 2025

作者： Singh, Prabhdeep Singh, Pawan Agarwal, Abhay Kumar Kumar, Anil Amity School of Engineering and Technology Department of Computer Science and Engineering Lucknow India Kamla Nehru Institute of Technology Department of Computer Science and Engineering Sultanpur India Amity University Amity School of Engineering and Technology Lucknow India

ISBN: (纸本)9798331529246

Cloud Computing (CC) offers a diverse range of services along with huge data storage across a network. CC has collaborated with varied emerging technologies like IoT because of its numerous advantages. Despite CC's benefits, cloud-based servers are not always trustworthy in real-world scenarios. Users' privacy will be compromised if they send their data straight to cloud platforms since crucial information will be exposed to cloud servers. Thereby, this work develops a data security model in the cloud with two stages, proposed secured data storage and proxy re-encryption. Initially, the data is stored securely in the cloud based on improved AES-based encryption as well as obfuscation-based encryption. Based on the request from the data user, proxy re-encryption is done using Kronecker product-based encryption. The enhanced AES achieved the lowest value of 0.025 for the CCA attack with a key size of 128 bits. Thus, the final encoded key is obtained. © 2025 IEEE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Modeling and Evaluating Stock Market and Commodity Price Fluctuation Using Time Series Sequence Learning

引用

SN computer Science 2025年第5期6卷 1-18页

作者： Veningston, K. Ronalda, M. Shaikh, Tawseef Ayoub Gazi, Farhaan Bhagat, Sanket Department of Computer Science and Engineering National Institute of Technology Srinagar Jammu and Kashmir Srinagar 190006 India

Algorithmic trading using neural network models has gained significant attention in predicting stock and commodity price fluctuations and understanding their dynamics. Deep learning techniques have shown significant results in predicting stock market prices in recent years. Modelling stock market price dynamics using sequence learning techniques leverages the historical trends and dependencies in price data to predict future price movements. This paper presents a comprehensive analysis of Autoregressive Integrated Moving Average (ARIMA), standard neural network, Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU) for forecasting stock movements in various industry stocks. The main objective is to assess the performance of each model in predicting stock price fluctuations. Each model undergoes systematic validation and evaluation based on key performance indicators such as accuracy, normalised root mean squared error (NRMSE), and Weighted Mean Absolute Percentage Error (WMAPE). The forecast made by each model is compared to the actual stock prices to measure the effectiveness of the forecasting methods. This paper presents a time series sequence learning approach for modelling and evaluating stock market price fluctuation. The proposed approach uses an LSTM network to learn the sequential patterns in stock price data. The LSTM network is trained on a historical dataset of stock prices, and it is then used to predict future stock prices. The proposed approach is evaluated on a dataset of stock prices from seven different industry domains, including Investment, Infrastructure, Information technology, Pharma, Fast Moving Consumer Goods and agri-business (FMCG), Vehicles, and Banking, which enables a comprehensive evaluation of various models. The results show that the proposed LSTM approach can achieve notable accuracy in predicting future stock prices. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Lt

关键词： Algorithmic trading Sequence learning Share price dynamics Stock market price forecast Time-series analysis

来源：评论

学校读者我要写书评

暂无评论

Classifying distinct emotions from parents of ASD child using EEG source data by combining Bernoulli–Laplace Prior and graph neural networks

引用

Neural Computing and Applications 2025年第12期37卷 7877-7895页

作者： ArulDass, Stephen Dass Jayagopal, Prabhu School of Computer Science Engineering and Information Systems Vellore Institute of Technology Tamil Nadu Vellore632014 India

Emotion recognition using biological brain signals needs to be reliable to attain effective signal processing and feature extraction techniques. The impact of emotions in interpretations, conversations, and decision-making, has made automatic emotion recognition and examination of a significant feature in the field of psychiatric disease treatment and cure. The problem arises from the limited spatial resolution of EEG recorders. Predetermined quantities of electroencephalography (EEG) channels are used by existing algorithms, which combine several methods to extract significant data. The major intention of this study was to focus on enhancing the efficiency of recognizing emotions using signals from the brain through an experimental, adaptive selective channel selection approach that recognizes that brain function shows distinctive behaviors that vary from one individual to another individual and from one state of emotions to another. We apply a Bernoulli–Laplace-based Bayesian model to map each emotion from the scalp senses to brain sources to resolve this issue of emotion mapping. The standard low-resolution electromagnetic tomography (sLORETA) technique is employed to instantiate the source signals. We employed a progressive graph convolutional neural network (PG-CNN) to identify the sources of the suggested localization model and the emotional EEG as the main graph nodes. In this study, the proposed framework uses a PG-CNN adjacency matrix to express the connectivity between the EEG source signals and the matrix. Research on an EEG dataset of parents of an ASD (autism spectrum disorder) child has been utilized to investigate the ways of parenting of the child's mother and father. We engage with identifying the personality of parental behaviors when regulating the child and supervising his or her daily activities. These recorded datasets incorporated by the proposed method identify five emotions from brain source modeling, which significantly improves the accurac

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

A novel framework for improving class imbalance learning using feature space identification and fast informative resampling techniques

引用

International Journal of Information technology (Singapore) 2025年 1-14页

作者： Kadiyala, V. S. NageswaraRao Nayak, Sabuzima Patgiri, Ripon Department of Computer Science & Engineering National Institute of Technology Silchar Assam Cachar 788010 India Department of Computer Science and Engineering Institute of Technical Education and Research Siksha ‘O’ Anusandhan Odisha Bhubaneswar 751020 India

This study presents a new data stream learning framework for class imbalance data sources that can improve classification. This framework uses a genetic algorithm to select the best features and perform fast resampling using intelligent techniques to identify clusters with unique inheriting structures. The proposed approach learns one chunk at a time without requiring access to previous data and emphasizes updating misclassified examples in the model building. The experiments demonstrated that the suggested framework improves performance for classifying the imblance data stream. Moreover, the proposed approach exhibited the best performance on compared models with different evaluation metrics. © Bharati Vidyapeeth's institute of computer Applications and Management 2025.

关键词： Class imbalance Data mining Data stream Decision Tree Genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

Identification of products for campaigning with budget constraint

引用

International Journal of Information technology (Singapore) 2025年第2期17卷 727-748页

作者： Kumar, Abhishek Bishnu, Partha Sarathi Department of Computer Science Birla Institute of Technology Mesra India

technology helps producers to collect enormous amounts of customer-product interaction (CPI) data. From the collected CPI data, the importance of the customers and the products can be measured. This study focuses on finding the best number of products for the business for campaign selection based on customers’ liking and disliking of products and their frequency of purchases. Campaign selection is an essential process for marketing, and when the total budget of the campaign is fixed, identifying the optimal products for campaigning is challenging. This paper aims to identify the important existing customers and products and identify the optimal product combinations for campaign selection. We propose two algorithms to identify highly valuable customers and products and solve the complex optimization problem of identifying the optimal product combinations for campaign selection that maximize the business’s profits. We compare our proposed algorithms on real and synthetic datasets, and the results are presented. © Bharati Vidyapeeth's institute of computer Applications and Management 2024.

关键词： Algorithm Business intelligence Data science Machine learning Marketing

来源：评论

学校读者我要写书评

暂无评论

Efficacy of image based deep learning CNN models for bolt loosening detection in steel structures

引用

Asian Journal of Civil engineering 2025年第6期26卷 2409.0-2417页

作者： Alapati, Mallika Ramesh Chandra, G. Abboju, Shivani Department of Civil Engineering VNR Vignana Jyothi Institute of Engineering and Technology Telangana Hyderabad India Department of Computer Science and Engineering VNR Vignana Jyothi Institute of Engineering and Technology Telangana Hyderabad India

Bolted connections are integral components in steel structures and often are vulnerable to loosening due to cyclic loading and fatigue. Detecting bolt loosening in early stages is critical to prevent sudden catastrophic failures. Recent advancements in image capturing and processing, combined with machine learning techniques have significantly improved the accuracy of detecting bolt loosening. Deep learning techniques, in specific those based on image analysis, have proven to be effective tool for damage detection in structural members. In this study, initially captured dataset of 120 images from a laboratory model is augmented to 576 images using the Roboflow platform. Investigations in this work are tied to one image data set and the metrics are analysed for how well a model performs. Usually, it depends on each use case as to which model would be best suited. In the present work, dataset featured two states of bolt loosening: tight and loose. Convolution Neural Network architectures AlexNet and ResNet are applied individually to the augmented dataset to predict the bolt loosening states as binary classification problem. The results demonstrated an accuracy of 87.931%, indicating that the AlexNet model effectively distinguished between loose and tight conditions. Whereas the ResNet algorithm exhibited relatively better accuracy of 90.8%. Further, an integrated hybrid model (CNN model with LSTM) is also applied on the same image data to further enhance the efficiency of the deep learning frame work. The performance of the trained CNN algorithms was further validated with image responses from various real time scenarios of various lighting conditions and found to be fairly good. This study highlights the potential of using deep learning techniques, specifically AlexNet, ResNet and CNN with LSTM for accurately detecting bolt loosening, thereby contributing to the safety and reliability of steel structures. © The Author(s), under exclusive licence to Springer Nature S

关键词： AlexNet Bolt loosening Bolted connections Convolution neural network architectures Image based deep learning ResNet architecture

来源：评论

学校读者我要写书评

暂无评论

Ranking-based Diversified Influence Maximization for Dynamic Social Networks 17

Ranking-based Diversified Influence Maximization for Dynamic...

引用

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

作者： Meena, Sunil Kumar Singh, Shashank Sheshar Singh, Kuldeep University of Delhi New Delhi Department of Computer Science New Delhi India Thapar Institute of Engineering and Technology Department of Computer Science and Engineering Patiala India

ISBN: (纸本)9798331531195

Influence maximization (IM) is the task of selecting the most influential nodes in the network. IM achieves the goal of spreading information, influencing behaviour, or promoting sales of products. Existing studies in IM focus on maximizing the activated nodes in the static network and neglecting the communities. In this paper, we give a novel ranking-based algorithm that ranks the nodes based on their reachability and diversity. This paper proposes an objective function that considers both diversity and activated nodes to determine the diversity capability of the nodes. The proposed algorithm utilizes previous computation and integrates reachability centrality with the objective function to rank the nodes at a timestamp in a dynamic network. We execute the proposed and benchmark algorithms on five datasets. The experiments show that the suggested algorithm produces superior and competitive outcomes in comparison to the benchmark algorithms. © 2025 IEEE.

关键词： Diversified Influence Maximization Dynamic Networks Influence Maximization Local Reaching Centrality Social Network Analysis

来源：评论

学校读者我要写书评

暂无评论

An Experimental Study on Dynamic Lifelong Learning with GPT for Mitigating Catastrophic Forgetting in Aspect-Based Sentiment Analysis

引用

IEEE Access 2025年 13卷 90316-90332页

作者： Huang, Huang Asemi, Adeleh Universiti Malaya Faculty of Computer Science Information Technology Department of Software Engineering Kuala Lumpur Malaysia

GPT is widely recognized as one of the most versatile and powerful large language models, excelling across diverse domains. However, its significant computational demands often render it economically unfeasible for individuals and small businesses, underscoring the need for efficient, domainspecific alternatives. In Aspect-Based Sentiment Analysis (ABSA), existing models are typically optimized for single domains, facing challenges in performing effectively across multiple domains. A key issue, known as "catastrophic forgetting," arises when models trained on one domain lose previously learned knowledge upon exposure to new domain data. This leads to two significant problems: limited cross-domain generalization and difficulty in retaining prior knowledge while learning domain-specific information. To address these challenges, we introduce the Dynamic Lifelong Learning Aspect-Based Sentiment Analysis GPT (DllaGPT), a model designed to handle multiple domains while mitigating catastrophic forgetting. Leveraging datasets from four ABSA domains—Laptops, Restaurants, Tweets, and Finance—this study fine-tunes a pretrained GPT model from HuggingFace sequentially across domains. DllaGPT employs a mechanism to retain real data from earlier domains during new domain training, effectively preserving prior knowledge. Experimental results highlight that DllaGPT achieves an average accuracy of 0.85 and a Backward Transfer (BWT) score of -0.09 across the four domains, showcasing its high accuracy and robust lifelong learning capabilities. © 2025 institute of Electrical and Electronics Engineers Inc.. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Fusion of IoT and Blockchain (BIoT): A Novel Architecture for Smart Agriculture 8th

Fusion of IoT and Blockchain (BIoT): A Novel Architecture...

引用

8th International Conference on Internet of Things and Connected Technologies, ICIoTCT 2023

作者： Das, Priyanka Ray, Sangram Dasgupta, Mou Govil, Mahesh Chandra Department of Computer Science and Engineering National Institute of Technology Sikkim Sikkim Ravangla737139 India Department of Computer Application National Institute of Technology Raipur Chhattisgarh Raipur492010 India

ISBN: (纸本)9789819757855

Internet of Things (IoT) plays a crucial role in automating systems, offering effectual and reliable services with minimal human intervention. To be precise, IoT-enabled smart agriculture is a vital factor in the modern digital world which ensures to provide various functionalities such as—water level monitoring, temperature monitoring, moisture sensing, and plant growth tracking. These functionalities of smart agriculture significantly simplify the work of farmers. But on the contrary, several security and privacy-related concerns were identified such as critical agriculture field data storage and management. Therefore, the evolution of integration of the IoT and blockchain (BIoT) came into the limelight. BIoT-based smart agriculture can enhance efficiency, sustainability, etc., leading to increased productivity, improved resource management, and secure data storing management in a decentralized manner. In this paper, we propose an architecture for a smart agriculture ecosystem based on the fusion of both IoT and blockchain. Primarily, our proposed architecture consists of three stages, PEGASIS-based chain construction phase, mutual authentication and key agreement phase, and blockchain-based data storage in base-station phase. Finally, this paper highlights on security analysis of our proposed architecture and found that it is well-secured against broadly known security attacks. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

Impact of Different Integration Times on Distributions of Rain Rates for Predictions of Rain Attenuation

引用

Progress in Electromagnetics Research C 2025年 154卷 229-238页

作者： Hassan, Mohammad Rofiqul Rafiqul, Islam Md. Habaebi, Mohamed Hadi Suriza, Ahmad Zabidi Badron, Khairayu Budalal, Asma Ali Mahfuz, Md. Mahmudul Hasan Department of Electrical and Computer Engineering Faculty of Engineering International Islamic University Malaysia Jalan Gombak Kuala Lumpur53100 Malaysia College of Electrical and Electronics Technology Benghazi Libya Department of Electrical and Computer Engineering Concordia University Canada

All wireless communication systems are moving towards higher and higher frequencies day by day which are severely attenuated by rains in outdoor environment. To design a reliable RF system, an accurate prediction method of rain attenuation is established and used globally based on local rain intensity measurement. Required rain intensity used for attenuation prediction is generally measured at a point with 1-min integration time or converted from higher integration time to 1-min. Recent measurements of rain intensity with a 10-second integration time indicate that intensity is not uniform over a 1-minute duration. Consequently, the statistics of rain intensity distribution and attenuation predictions are influenced by measurements with integration times shorter than 1 minute. It has been established that an integration time of 0.01% provides the optimal fit for actual rain rate data. This paper presents the rain intensity distributions from data measured with 2-min, 1-min, 30-sec, 20-sec, and 10-sec integration times, and it has impact on rain rate distributions as well as rain attenuation predictions. © 2025, Electromagnetics Academy. All rights reserved.

关键词：

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：