检索结果-内蒙古大学图书馆

Intelligent Control, Computing and Communications (IC3), International Conference on

作者： Soummya Chowdhury Hardeo Kumar Thakur Jagendra Singh Ashish Kumar Mathur Nilesh Kumar Sen Isha Gupta School of Business GITAM (Deemed to be) University Hyderabad India School of Computer Science Engineering & Technology Bennett University Greater Noida India Department of CSE-AIML ABES Engineering College Ghaziabad India Department of Computer Science Raj Kumar Goel Institute of Technology Ghaziabad India

ISBN: (数字)9798331527495

ISBN: (纸本)9798331527501

With the increasing reliance of Human Resource (HR) management on digital systems, protection of sensitive employee data is critical to prevent unauthorised access. This research addresses the necessity of an advanced security system in detecting and mitigating potential security threats in HR operations. A machine learning (ML)-based system was thus designed and implemented, using the models support vector machines, recurrent neural networks, autoencoders, and random forests. The training was thus conducted utilising a mix of real-world and synthetic data, specifically including HR system logs as well as user activities and various security events, including login attempts and unauthorised access to some files. After feature engineering and preprocessing, all the models were evaluated with respect to the metrics of accuracy, precision, recall, and F1 score. Results indicated that Support Vector Machine (SVM) outperformed all models in terms of 98.54% accuracy with low latency, 15 ms, a throughput of 150 predictions per second, and 1.2 seconds for the detection time. These results point out that the SVM model is suitable for real-time applications, showing that it is efficient in detecting security breaches and scalable in large HR systems. Findings indicate that machine learning models, especially SVM, can be used to increase IT security in HR management, allowing for timely detection and mitigation of security threats.

关键词： Support vector machines Accuracy Recurrent neural networks Autoencoders Throughput Real-time systems Security Human resource management Low latency communication Synthetic data

来源：评论

学校读者我要写书评

暂无评论

Ageing Characteristics of Ceramifiable Silicone Rubber Nanocomposites Exposed To Electrolytic Solution

引用

IEEE Transactions on Dielectrics and Electrical Insulation 2025年

作者： Varun, Jatoth Mishra, Palash Dharanish, Addala El Hag, Ayman Sarathi, R. Mondal, Mithun Electrical Engineering Department National Institute of Technology Warangal Telangana Hanamkonda506004 India Electrical and Computer Engineering Department University of Waterloo Waterloo Canada Department of Electrical Engineering Indian Institute of Technology Tamil Nadu Chennai600036 India Department of Electrical and Electronics Engineering Birla Institute of Technology and Science Pilani Hyderabad Campus Telangana Hyderabad500078 India

The capability to transform into a flame-retardant ceramic body when encountering high temperatures makes low melting glass (LMG) powder an effective additive for room temperature vulcanized (RTV) silicone rubber composites, which are used as coating materials for outdoor high-voltage insulators operating in harsh environments. In this context, the present study, examines the impact of nano LMG powder on the aging characteristics of 5 wt.% boron nitride (BN) doped silicone rubber nanocomposites exposed to a strong electrolytic aqueous ammonium chloride (NH4Cl) solution. LMG nanofiller was added in varying weight percentages of 3 wt.% and 7 wt.%. Except for the 7 wt.% LMG doped composite, a distinct dip in weight gain, indicating higher degradation and detachment of filler particles, was noted in all the composites during diffusion test. Ageing-induced deterioration of surface morphology is well evident in 3D microscopy, contact angle and FTIR spectroscopic test results, which clearly demonstrate increased surface roughness and scissioning of side chains (Si-CH3) and backbone chains (Si-O-Si) in silicone rubber matrix of all the composites post-ageing. Further, antipollution performance and thermal properties of all the test specimens were evaluated through inclined plane tracking and erosion test, thermogravimetric analysis and IR thermography. The test results demonstrated that LMG doped composites showed better tracking and erosion resistance, higher thermal stability and lower surface temperature distribution during IPT compared to the only BN specimen before and after aging. The experimental results revealed the 7 wt.% LMG composite exhibited better resistance to degradation caused by the NH4Cl solution. © 2025 IEEE.

关键词： Boron nitride

来源：评论

学校读者我要写书评

暂无评论

A dynamic probabilistic graphical model for mapping tasks to virtual machines in data centers

引用

engineering Applications of Artificial Intelligence 2025年 155卷

作者： Sindhu, Korrapati Seshadri, Karthick Department of Computer Science and Engineering National Institute of Technology Andhra Pradesh Tadepalligudem534101 India

Efficient mapping of tasks to Virtual Machines is significant in optimizing resource utilization and performance in Virtual Data Centers. In this work, a novel approach for mapping tasks to Virtual Machines by leveraging a bespoke probabilistic graphical model is proposed. The proposed framework maps tasks to Virtual Machines in two phases: constructing a Dynamic Bayesian Network to model scheduling factors and solving the mapping as an inference problem using the Junction Tree algorithm. The model updates the states of Virtual and Physical Machines during mapping, allowing for optimal mapping decisions based on evolving conditions. Experimental findings demonstrate that the proposed model outperforms the state-of-the-art models across various counts, achieving a makespan of 18.87 s, a degree of load imbalance of 0.22, a task guarantee ratio of 83%, an average Service Level Agreement violation rate of 0.32, and an energy consumption of 67 Kilo Joules. Compared to the strongest meta-heuristic baseline, the proposed model reduces makespan by 6.89%, decreases load imbalance by 11.08%, lowers Service Level Agreement violations by 12.44%, reduces energy consumption by 2.50%, and improves the task guarantee ratio by 4.28%. © 2025 Elsevier Ltd

关键词： Photomapping

来源：评论

学校读者我要写书评

暂无评论

A Binary PSO Based Ensemble Under-Sampling Model for Rebalancing Imbalanced Training Data

arXiv

引用

arXiv 2025年

作者： Li, Jinyan Wu, Yaoyang Fong, Simon Tallón-Ballesteros, Antonio J. Yang, Xin-She Mohammed, Sabah Department of Computer and Information Science University of Macau Taipa China Department of Languages and Computer Systems University of Seville Seville Spain Design Engineering and Math School of Science & Technology Middlesex University London United Kingdom Department of Computer Science Lakehead University Thunder Bay Canada

Ensemble technique and Under-sampling technique are both effective tools for resolvig imbalanced dataset classification problems, which commonly denotes the quantitative imbalance of a binary class dataset where minority class is the target class. In this paper, a novel ensemble method absorbing the advantages of both ensemble learning for biasing classifiers and a new evolutional under-sampling method is proposed. The under-sampling method is named Binary PSO instance selection, it gathers with ensemble classifiers to find the most suitable length and combination of majority class samples to build a new dataset with minority class samples. The proposed method adopts multi-objective strategy, objectives of this method is to improve the performances of imbalanced classification and to guarantee the maximum integrity of the original dataset. We examined our proposed method, the Binary PSO instance selection by comparing its performance of processing imbalanced dataset with several other conventional basic ensemble methods. Experiments are also conducted with Binary PSO instance selection wrapping with ensemble classifiers for further improvement of imbalanced classification. Based on comaprison experiments, our proposed methods outperform single ensemble methods, state-of-the-art under-sampling methods as well as their combinations with traditional PSO instance selection algorithm. Copyright © 2025, The Authors. All rights reserved.

关键词： Data assimilation

来源：评论

学校读者我要写书评

暂无评论

A Complete Axiomatization of Branching Bisimilarity for a Simple Process Language with Probabilistic Choice

arXiv

引用

arXiv 2025年

作者： van Glabbeek, Rob J. J.F., Groote E.P., de Vink Data61 CSIRO Sydney Australia Computer Science and Engineering University of New South Wales Australia Department of Mathematics and Computer Science Eindhoven University of Technology Eindhoven Netherlands

This paper proposes a notion of branching bisimilarity for non-deterministic probabilistic processes. In order to characterize the corresponding notion of rooted branching probabilistic bisimilarity, an equational theory is proposed for a basic, recursion-free process language with non-deterministic as well as probabilistic choice. The proof of completeness of the axiomatization builds on the completeness of strong probabilistic bisimilarity on the one hand and on the notion of a concrete process, i.e. a process that does not display (partially) inert τ-moves, on the other hand. The approach is first presented for the non-deterministic fragment of the calculus and next generalized to incorporate probabilistic choice, too. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Social Media Sentiment Analysis for Airline Customer Satisfaction

Social Media Sentiment Analysis for Airline Customer Satisfa...

引用

Disruptive Technologies (ICDT), International Conference on

作者： Shivani Chaudhary Khushi Garg Purnima Gupta Anshu Kumar Dwivedi Department of Computer Science Institute of Management Studies Ghaziabad (University Courses Campus) Adhyatmik Nagar India School of Computer Science Engineering and Technology Bennett University Greater Noida India

ISBN: (数字)9798331519582

ISBN: (纸本)9798331519599

Among the most important subfields in natural language processing, one of the fields is sentiment analysis. Sentiment analysis focuses on recognizing and estimating emotions in text. It has gained more importance in aviation in the sense that it can present insights into customer satisfaction and brand reputation as well as operational efficiency. This work investigates the topic of the sentiment analysis of the Twitter US Airline Sentiment Dataset: more than 14,000 tweets regarding the major US airlines labelled as positive, neutral, or negative. By such approaches documented in the literature, challenges consisting of the noise and subtlety of sentiment in the given data largely remain unsolved. To address these deficiencies, this research will use the machine learning techniques in the form of Naive Bayes and Random Forest models, classifying sentiments by methods like class imbalances through SMOTE, and using TF-IDF vectorization in extracting features. Results for the experiment showed that the Random Forest model outperforms Naive Bayes as the former can classify more neutral and positive sentiments correctly. It is, therefore, concluded that sentiment analysis may be useful to airlines for enhancement in customer experience and future research should emphasize on advanced deep learning models with rich data sets for further potential enhancement.

关键词： Sentiment analysis Analytical models Social networking (online) Atmospheric modeling Customer satisfaction Blogs Feature extraction Bayes methods Random forests Airline industry

来源：评论

学校读者我要写书评

暂无评论

Modelling radiological features fusion and explainable AI in pneumonia detection: A graph- based deep learning and transformer approach

引用

Results in engineering 2025年 26卷

作者： Kaushik, Pratham Jain, Eshika Kukreja, Vinay Hariharan, Shanmugasundaram Krishnamoorthy, Murugaperumal Ahuja, Vandana Bhattacherjee, Abhishek Kaushal, Rajesh Kumar Chen, Shih-Yu Centre for Research Impact and Outcome Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Department of Artificial Intelligence and Data Science Vardhaman College of Engineering India Department of Electrical and Electronics Engineering Vardhaman College of Engineering India Department of Computer Science & Engineering Swami Vivekanand Institute of Engineering and Technology Punjab Ramnagar India Department of Computer Science Engineering Lovely Professional University Punjab India Department of Computer Applications Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Department of Computer Science and Information Engineering National Yunlin University of Science and Technology Yunlin64002 Taiwan Intelligence Recognition Industry Service Research Center National Yunlin University of Science and Technology Yunlin64002 Taiwan

Objectives: This study aims to develop a deep learning-based methodology for pneumonia detection using lung CT scans. The research focuses on integrating U-Net for lung segmentation, graph-based feature representations, and transformer-based models to improve interpretability and diagnostic accuracy. Methodology: We utilized 500 annotated lung CT scans, split into 70 % training (350 images), 15 % validation (75 images), and 15 % testing (75 images). U-Net was employed for lung segmentation, with segmentation performance evaluated using Dice Similarity Coefficient (DSC) and Intersection over Union (IoU). The classification model incorporated feature fusion, combining handcrafted radiological features with transformer-based feature extraction. The model's noise sensitivity and interpretability were assessed using Grad-CAM and attention maps. Results: The segmentation model achieved a DSC of 0.943 on the training set, 0.928 on the validation set, and 0.910 on the test set. The IoU values were 0.890, 0.872, and 0.850, respectively. The model's inference time was 25 milliseconds per image. The classification model achieved an overall accuracy of 94 %, with pneumonia cases showing precision, recall, and F1-scores of 0.95, 0.94, and 0.94, respectively. For normal cases, precision, recall, and F1-scores were 0.92, 0.94, and 0.93. The model's performance improved over 20 epochs, with training accuracy reaching 0.94 and validation accuracy reaching 0.88. The feature fusion method achieved an attention score of 0.88, with node intensity scores of 0.85. Noise sensitivity analysis revealed a performance drop beyond a noise level of 0.3. Conclusions: This study demonstrates the potential of AI-driven solutions for pneumonia detection, achieving high accuracy, robustness, and interpretability. While the model performs well, further optimization is needed to address noise sensitivity and enhance model generalization for real-world applications. © 2025

关键词： Image annotation

来源：评论

学校读者我要写书评

暂无评论

MNCL: Empirical Development of Human Action Recognition Based on Postures Using Modified Neural Classification Logic

MNCL: Empirical Development of Human Action Recognition Base...

引用

2025 International Conference on Visual Analytics and Data Visualization, ICVADV 2025

作者： Krishna, S.Rama Pavithra, M. Arul Prasath, A. Thatipudi, Jayendra Gopal Gopinath, D. Rajkumar, K. Department of Computer Science & Engineering GSoT Hyderabad502329 India Chennai Institute of Technology Dept. of Electronics and Communication Engineering Chennai India Dr. Sagunthala R&d Institute of Science and Technology Department of Cse Vel Tech Rangarajan Chennai India University of North Dept. of Computer Science TX United States Department of Computer Science Karnataka Bengaluru India School of Engineering Sr University Department of Ece Telangana India

ISBN: (纸本)9798331521394

In this research, we introduce an innovative method for the recognition of human actions based on skeletal joint data, which offers greater privacy compared to color photos. The methodology includes defining an activity using a sequence of instructive fundamental postures, and combining machine learning methods for activity recognition. Based on normalized skeletal data points, posture features such as absolute joint positions, relative joint positions, and joint angle quaternions are proposed to derive. Feature dimensionality and system complexity are reduced through posture selection, followed by temporal modeling to minimize the effects of rate variation, temporal misalignment and noise. A Modified Neural Classification Logic (MNCL) model is proposed, based on certain principles, to identify actions. Position- and angle-based kinematics are suggested, with angle based features that are naturally normalized and are independent of an individual's physique. To reduce posture similarity and make the method more general, a posture selection method based on the K-means clustering algorithm is implemented. The proposed MNCL model links weights of the MNCL model between the previous layer and the current layer using a linear function instead of the non-linearity provided in the original MNCL model. An innovative inference engine for logical connections based decision making is used to improve the output layer recognition rate. In this work, we propose a system for human action recognition based on skeletal joint properties, intended to provide an efficient and privacy preserving solution. © 2025 IEEE.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Optimizing Neural Machine Translation Workflows Using Queuing Theory

Optimizing Neural Machine Translation Workflows Using Queuin...

引用

2025 International Conference on Visual Analytics and Data Visualization, ICVADV 2025

作者： Kavitha, K. Maragathasundari, S. Karthikeyan, K. Swedheetha, C. Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Mathematics Chennai India Velammal Institute of Technology Department of Mathematics Chennai India Velammal College of Engineering and Technology Department of Computer Science and Engineering Madurai India

ISBN: (纸本)9798331521394

In the Neural Machine Translation (NMT) process, each translation task is processed by a model designed to generate accurate, context-sensitive translations. This involves analyzing the input to select the appropriate language pair, dataset, and translation model before producing the final output. The process ensures that translations are both precise and relevant by relying on advanced machine learning techniques. However, to optimize this process further, queuing theory can be applied to model the flow of translation tasks, treating each as a job entering a queue awaiting processing. By applying queuing theory, inefficiencies can be identified, resource allocation can be optimized, and delays can be minimized, ensuring faster and more accurate translations. Additionally, periodic server downtimes for maintenance and reinitialization are better managed, leading to improved system stability and a smooth, real-time translation service for users. © 2025 IEEE.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

A Hybrid CNN-LSTM-PSO Framework for Enhanced Cybersecurity Threat Detection and Classification

A Hybrid CNN-LSTM-PSO Framework for Enhanced Cybersecurity T...

引用

Multi-Agent Systems for Collaborative Intelligence (ICMSCI), International Conference on

作者： S. Akilandeswari Soumya T R S. Sumathi Mishmala Sushith V. Brinda S. Rajan Department of Artificial Intelligence & Data Science E.G.S. Pillay Engineering College Nagapattinam Department of Computer Science Engineering Prathyusha Engineering College Tiruvallur Department of Electronics and Communication Engineering Velammal Engineering College Chennai Department of Information Technology Adithya institute of Technology Kurumbapalayam Department of Electronics and Communication Engineering K.Ramakrishnan College Of Engineering Samayapuram Department of Electronics and Communication Engineering Velalar College of Engineering and Technology Erode

ISBN: (数字)9798331509828

ISBN: (纸本)9798331509835

With the advancement of digital era comes an increased value for cybersecurity, and these need to be dealt with using advanced techniques. Deep learning — metaheuristic optimization hybrid model for advanced threat detection and mitigation is presented in this paper. With a Convolutional Neural Network (CNN) for feature extraction and Long Short-Term Memory (LSTM) for sequence analysis, the proposed framework integrates all the modules in order to provide robust cyber-attack detection. In order to optimize the parameters of the model, a Particle Swarm Optimization (PSO) algorithm is used in order to achieve better classification accuracy and faster computation. Benchmark datasets are used for extensive experiments, where existing methods outperformed in terms of precision, recall, and Fl-score. The results demonstrate that with detected flagged FPs and the hybrid model, the increased detection rates are achieved without the reduction in true negatives, rendering it a practical solution for real world applications. This research adds to the field by providing a solution to cybersecurity problems that is scalable and adaptable to the present and beyond.

关键词： Adaptation models Analytical models Accuracy Computational modeling Benchmark testing Feature extraction Threat assessment Convolutional neural networks Particle swarm optimization Long short term memory

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：