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： Alam, Intekhab Krishnamoorthy, Ramkumar Verma, Tushar K. Raghavendra, T.S. Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India Karnataka Bangalore India Department of Civil Engineering School of Engineering and Computing Dev Bhoomi Uttarakhand University Navgaon Manduwala Dehradun India School of Computer Science and Engineering Presidency University Karnataka Bengaluru India

ISBN: (纸本)9789819780426

The multiscale evaluation technique is a low-power facts aggregation method using numerous evaluation scales to mix data from several properties. The method is based on multiscale structures, in which more than one scale of facts can be leveraged to advantage notion into centered styles within an individual source or in the course of resources. Multiscale assessment allows an accurate and dependable example of facts in evaluation compared to conventional unmarried-scale techniques. It’s miles beneficial for studying structures with sparse or low-first-rate information, wherein more significance than the facts accumulated is needed to constitute the general device because it needs to be. Furthermore, this technique can detect styles in records from randomly sampled belongings or residences that might be temporally or spatially separated. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： conventional evaluation Multiscale

来源：评论

学校读者我要写书评

暂无评论

Towards Safer Digital Spaces: Automated Detection of Cyberbullying Through Multi-Modal Learning 5

Towards Safer Digital Spaces: Automated Detection of Cyberbu...

引用

5th International Conference on Sustainable Communication Networks and Application, ICSCNA 2024

作者： Karthikeyan, M. Saravana Francis Raj, J. Relin Krishnan, R. Santhana Kumari, D. Abitha Murali, S. Joshua, K. Paul Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of Computer Science and Engineering Chennai India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Electronics and Communication Engineering Chennai India SCAD College of Engineering and Technology Department of Electronics and Communication Engineering Cheranmahadevi India RMK Engineering College Department of Computer Science and Engineering Thiruvallur India Velammal College of Engineering and Technology Department of Computer Science and Engineering Madurai India SCAD College of Engineering and Technology Department of Computer Science and Engineering Cheranmahadevi India

ISBN: (纸本)9798331530013

Cyberbullying and online harassment present significant challenges to digital safety, demanding robust detection systems capable of identifying abusive content across multiple formats. This work proposes a multi-modal framework that leverages CLIP and RoBERTa embeddings to detect and categorize cyberbullying and harassment in both text and image-based posts. By utilizing two curated datasets, HarassDetect-TextImage and CyberGuard-MultiModal, the model is trained on a diverse range of offensive and non-offensive content. Text data is preprocessed through advanced techniques, while CLIP and RoBERTa generate embeddings capturing the context of both textual and visual inputs. For sequential analysis of threaded posts, a Transformer layer further enhances the model's contextual awareness, enabling it to recognize harassment patterns that unfold over multiple messages. A Support Vector Machine (SVM) classifier then categorizes content into Non-Cyberbullying, Minor, Moderate, and Severe classes, each associated with confidence levels guiding automated actions. High-confidence classifications trigger immediate responses, such as content restriction or user warnings, while moderate-confidence cases are flagged for manual review. This adaptive framework not only improves accuracy but also allows for a continuous feedback loop, updating the model to address evolving patterns of cyberbullying. Evaluation results demonstrate the efficacy of this approach in creating safer online environments through automated and contextually aware cyberbullying detection. © 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

Investigating the Role of Applied Cryptography in Digital Forensics 5th

Investigating the Role of Applied Cryptography in Digital Fo...

引用

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

作者： Mishra, Awakash Nachappa, M.N. Negi, Bichitra Singh Dakhole, Dipali Khushalrao Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India Karnataka Bangalore India Department of Civil Engineering School of Engineering and Computing Dev Bhoomi Uttarakhand University Navgaon Manduwala Dehradun India School of Computer Science and Engineering Presidency University Karnataka Bengaluru India

ISBN: (纸本)9789819780426

This paper examines the position of cryptography in virtual forensic evaluation. It aims to discover the one-of-a-kind sorts of cryptographic techniques available to investigators and to talk about how they may be applied to beautify the accuracy of digital forensic work. It also considers the character of cryptographic algorithms and their relative strengths and weaknesses, as well as the numerous applications of cryptographic software and devices in digital forensics. The paper then argues that using cryptography in digital forensic analysis can toughen virtual forensic effects by introducing additional safety features, allowing encrypted facts to be reliably recovered and investigated, and presenting a further degree of warranty while proof is given. It additionally addresses the ethical concerns that must be taken into consideration by virtual forensic investigators during the usage of cryptography in their work. Eventually, it identifies numerous avenues for future studies into using cryptography and its ability applications in virtual forensics. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Digital forensics

来源：评论

学校读者我要写书评

暂无评论

Enhancing Human Action Recognition with Adaptive Hybrid Deep Attentive Networks and Archerfish Optimization

引用

computers, Materials & Continua 2024年第9期80卷 4791-4812页

作者： Ahmad Yahiya Ahmad Bani Ahmad Jafar Alzubi Sophers James Vincent Omollo Nyangaresi Chanthirasekaran Kutralakani Anguraju Krishnan Department of Accounting and Finance Faculty of BusinessMiddle East UniversityAmman11831Jordan Faculty of Engineering Al-Balqa Applied UniversitySalt19117Jordan Department of Mathematics Kongunadu College of Engineering and Technology(Autonomous)TholurpattiTrichy621215India Department of Computer Science and Software Engineering Jaramogi Oginga Odinga University of Science and TechnologyBondo210-40601Kenya Department of Electronics and Communication Engineering Saveetha School of EngineeringSaveetha Institute of Medical and Technical SciencesChennai602105India Department of Electronics and Communication Engineering Saveetha Engineering College(Autonomous)Chennai602105India Department of Computer Science and Engineering Kongunadu College of Engineering and Technology(Autonomous)TholurpattiTrichy621215India

In recent years,wearable devices-based Human Activity Recognition(HAR)models have received significant *** developed HAR models use hand-crafted features to recognize human activities,leading to the extraction of basic *** images captured by wearable sensors contain advanced features,allowing them to be analyzed by deep learning algorithms to enhance the detection and recognition of human *** lighting and limited sensor capabilities can impact data quality,making the recognition of human actions a challenging *** unimodal-based HAR approaches are not suitable in a real-time ***,an updated HAR model is developed using multiple types of data and an advanced deep-learning ***,the required signals and sensor data are accumulated from the standard *** these signals,the wave features are *** the extracted wave features and sensor data are given as the input to recognize the human *** Adaptive Hybrid Deep Attentive Network(AHDAN)is developed by incorporating a“1D Convolutional Neural Network(1DCNN)”with a“Gated Recurrent Unit(GRU)”for the human activity recognition ***,the Enhanced Archerfish Hunting Optimizer(EAHO)is suggested to fine-tune the network parameters for enhancing the recognition *** experimental evaluation is performed on various deep learning networks and heuristic algorithms to confirm the effectiveness of the proposed HAR *** EAHO-based HAR model outperforms traditional deep learning networks with an accuracy of 95.36,95.25 for recall,95.48 for specificity,and 95.47 for precision,*** result proved that the developed model is effective in recognizing human action by taking less ***,it reduces the computation complexity and overfitting issue through using an optimization approach.

关键词： Human action recognition multi-modal sensor data and signals adaptive hybrid deep attentive network enhanced archerfish hunting optimizer 1D convolutional neural network gated recurrent units

来源：评论

学校读者我要写书评

暂无评论

Variational Bayesian Adaptive Learning of Deep Latent Variables for Acoustic Knowledge Transfer

引用

IEEE/ACM Transactions on Audio Speech and Language Processing 2025年 33卷 719-730页

作者： Hu, Hu Siniscalchi, Sabato Marco Yang, Chao-Han Huck Lee, Chin-Hui School of Electrical and Computer Engineering Georgia Institute of Technology AtlantaGA30332 United States Georgia Institute of Technology University of Palermo Palermo90133 Italy Norwegian University of Science and Technology Trondheim7034 Norway Nvidia Santa ClaraCA95051 United States

In this work, we propose a novel variational Bayesian adaptive learning approach for cross-domain knowledge transfer to address acoustic mismatches between training and testing conditions, such as recording devices and environmental noise. Different from the traditional Bayesian approaches that impose uncertainties on model parameters risking the curse of dimensionality due to the huge number of parameters, we focus on estimating a manageable number of latent variables in deep neural models. Knowledge learned from a source domain is thus encoded in prior distributions of deep latent variables and optimally combined, in a Bayesian sense, with a small set of adaptation data from a target domain to approximate the corresponding posterior distributions. Two different strategies are proposed and investigated to estimate the posterior distributions: Gaussian mean-field variational inference, and empirical Bayes. These strategies address the presence or absence of parallel data in the source and target domains. Furthermore, structural relationship modeling is investigated to enhance the approximation. We evaluated our proposed approaches on two acoustic adaptation tasks: 1) device adaptation for acoustic scene classification, and 2) noise adaptation for spoken command recognition. Experimental results show that the proposed variational Bayesian adaptive learning approach can obtain good improvements on target domain data, and consistently outperforms state-of-the-art knowledge transfer methods. © 2025 IEEE. All rights reserved

关键词： Background noise

来源：评论

学校读者我要写书评

暂无评论

Interference Management for IRS-NOMA Networks via Constructive Interference 16

Interference Management for IRS-NOMA Networks via Constructi...

引用

16th International Conference on Wireless Communications and Signal Processing, WCSP 2024

作者： Cui, Ke Wang, Wei Dong, Chao Zhao, Nan Wu, Qihui Niyato, Dusit School of Information and Communication Engineering Dalian University of Technology Dalian China School of Electronic and Information Engineering Nanjing University of Aeronautics and Astronautics Nanjing China School of Computer Science and Engineering Nanyang Technological University Singapore

ISBN: (纸本)9798350390643

Owing to the ability of reconfiguring wireless channels, intelligent reflecting surface (IRS) can help non-orthogonal multiple access (NOMA) to release its tremendous potential. However, the inter-user interference becomes the bottleneck of IRS-NOMA networks. To tackle this challenge, we propose two constructive interference precoding (CIP) based countermeasures for interference exploitation in IRS-NOMA networks. Specifically, the first scheme makes the interference from higher-order users (HUs) be constructive to lower-order users (LUs), so that the interference-free decoding can be achieved. While the second scheme utilizes the interference from LUs for the signal reception of HUs to avoid successive interference cancellation (SIC). The transmit power is mini-mized by jointly optimizing the BS active and the IRS passive beamformings for the two schemes. To solve each scheme, we apply successive convex approximation (SCA) and alternating optimization (AO) algorithm. Simulation results are presented to show the superiority and applicability of the proposed schemes compared to benchmarks. © 2024 IEEE.

关键词： Multiple access interference

来源：评论

学校读者我要写书评

暂无评论

Attention-Based Recurrent Neural Networks for Medical Image Classification 5th

Attention-Based Recurrent Neural Networks for Medical Image ...

引用

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

作者： Manjunath, K.V. Alam, Intekhab Nidhya, M.S. Verma, Tushar K. 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 Bengaluru India Department of Civil Engineering School of Engineering and Computing Dev Bhoomi Uttarakhand University Navgaon Manduwala Dehradun India

ISBN: (纸本)9789819780426

Attention-primarily based Recurrent Neural Networks (RNNs) are a technique for medical image classification. RNNs can robotically extract temporal and spatial facts from scientific imaging statistics and make sensible decisions. RNNs are especially nicely-perfect for clinical photograph category obligations, cutting-edge their potential to perceive lengthy-term temporal styles, recognize the relationships between distinct medical picture datasets, and enable In this paper, we overview the existing tries to use interest-based RNNs for medical image classification, discuss the contemporary demanding situations and suggest some ability future guidelines for studies. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Evolving ATM Networks for High Volume Transactions 5th

Evolving ATM Networks for High Volume Transactions

引用

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

作者： Impa, B.H. Alam, Intekhab Kavitha, R. Prajapati, Sandhya 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 Department of Civil Engineering School of Engineering and Computing Dev Bhoomi Uttarakhand University Manduwala Dehradun Navgaon India

ISBN: (纸本)9789819780426

ATM networks are evolving to guide excessive extent transactions and offer new features which includes increased safety, scalability, and cost performance. To lessen value, Banks are utilizing personal cloud environments to host their ATMs, whilst banks are looking for to deploy new offerings that assist their customers provide a higher enjoy. To enhance protection, banks are searching at encrypting data, and leveraging biometric authentication methods. Banks also are seeking to extend their offerings utilization of analytics to better goal purchaser advertising campaigns. Sooner or later, banks are adopting the use of micro services and disbursed architectures to enable building an extra scalable infrastructure that can scale horizontally with minimal effort. A majority of these advances are main to ATM networks which are efficient, comfy and dependable. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

PBRL-TChain: A performance-enhanced permissioned blockchain for time-critical applications based on reinforcement learning

引用

Future Generation computer Systems 2024年 154卷 301-313页

作者： Zhang, Yiguang Lin, Junxiong Lu, Zhihui Duan, Qiang Huang, Shih-Chia School of Computer Science Fudan University Shanghai200433 China Information Sciences & Technology Department Pennsylvania State University AbingtonPA United States Shanghai Blockchain Engineering Research Center Shanghai China Department of Electronic Engineering National Taipei University of Technology Taiwan

Permissioned blockchains can provide high security and reliability for various Internet of Things (IoT) systems, such as smart healthcare and vehicular networks. However, the performance issues of permissioned blockchains have been a constraint for fully supporting time-critical tasks with tight requirements of low latency and high throughput. This paper proposes PBRL-TChain, a performance-enhanced permissioned blockchain for time-critical applications based on deep reinforcement learning (DRL). First, we propose a priority ordering mechanism to minimize latency and maximize reliability. Then, we design a fast retransmission mechanism to alleviate the impact of transaction conflicts on the latency performance. Finally, we propose a DRL-based dynamic adjustment method in PBRL-TChain to achieve better performance and reliability. Experiments show that our method outperforms existing methods. Compared with Fabric++ and Athena, it can reduce the latency of time-critical transactions by 10 times, achieving a level of 10 ms, significantly improving the system's performance and reliability. © 2023 Elsevier B.V.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Optimizing Fabric Welding Using Image Processed Laser Inspection 5th

Optimizing Fabric Welding Using Image Processed Laser Inspec...

引用

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

作者： Ansari, Tabish Sekhar, Malepati Chandra Alam, Intekhab Bargavi, Manju Department of Civil Engineering School of Engineering and Computing Dev Bhoomi Uttarakhand University Navgaon Manduwala 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 Bengaluru India

ISBN: (纸本)9789819780426

Material welding is used in expanding industrial and industrial applications and depends on accuracy and precision to ensure satisfaction and protection. Laser inspection technology has been developed to help enhance the procedure's accuracy and performance by presenting rapid, reliable imaging that may be processed to decide where changes are wished. Through photograph processing, particular modifications to cloth welding can be recognized quickly and effectively. Additionally, photograph-processed laser inspection can hit upon any irregularities or defects in the welding method that can cause premature failure or decreased functionality. With this generation, designers and manufacturers can also develop higher control structures for his or her tasks, making more accurate and price-effective use of their assets. Sooner or later, the laser inspection era can offer actual-time remarks for automatic tactics, allowing changes to be made quickly with minimal disruption. Using this image processing technology, fabric welding groups can improve exceptional accuracy and value across merchandise. Optimizing material welding through image-processed laser inspection is a valuable method for controlling the pleasantness of welds. This technique uses a laser scanner, mild source, and a digital camera to seize detailed photos of the welds before and after welding. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Inspection

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：