检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Automation and Computation, AUTOCOM 2024

作者： Singh, Kamred Udham Varshney, Neeraj Kumar, Pushpendra Sharma, Pradeep Kumar Mishra, Umang Deep Singh, Teekam Graphic Era Hill University School of Computing Dehradun India Gla University Department of Computer Engineering & Applications UP Mathura India Scanno System Greater Noida India Hcl Technology UP India Unique Institute of Management & Technology Muradnagar India Graphic Era Deemed to Be University Department of Computer Science and Engineering Dehradun India

ISBN: (纸本)9798350382723

Data security in conventional applications was only available at the application layer. Within the scope of the intended research, the safety of the merchandise is ensured. The deficiencies that are present in the security systems that are already in place have led to the realisation that a new security system is required. Considering that authentication is not present, the likelihood of decryption should be reduced. Establishing a decentralised security system is essential in order to protect against threats coming from a variety of digital networks. The new encryption standard is said to improve multilayer security, according to the claims. The material is split into two halves using this method, which also provides a reliable transmission mechanism. Because of the technology, hackers are unable to create vulnerabilities in the security system. There was a need for security in both the cloud and the edge environment in order to prevent intruders. Increasing the reliability and security of data transmission over a variety of networks was the motivation for the development of the two fish approach. Because of its security mechanism, it has been able to survive assaults from crackers and hackers. The paper that is being presented advises doing research on the safety of edge transmissions that are based on slicing. In order to prevent attackers from launching attacks from several networks, it is necessary to establish decentralised security. Layered security will help increase encryption standards, which is a significant benefit. Over the course of various investigations, computer security edge generators have been the focus of attention. Quite a few of them have already been extensively discussed. For the purpose of developing a reliable method of transmission, the proposed research splits the data into two parts, each of which is further encrypted at a different level. As a result of the development of multilayer encryption, the reliability and safety of data transm

关键词： Fish

来源：评论

学校读者我要写书评

暂无评论

Hyperparameter Tuned Deep Learning Enabled Cyberbullying Classification in Social Media

引用

computers, Materials & Continua 2022年第12期73卷 5011-5024页

作者： Mesfer Al Duhayyim Heba G.Mohamed Saud S.Alotaibi Hany Mahgoub Abdullah Mohamed Abdelwahed Motwakel Abu Sarwar Zamani Mohamed I.Eldesouki Department of Computer Science College of Sciences and Humanities-AflajPrince Sattam bin Abdulaziz UniversitySaudi Arabia Department of Electrical Engineering College of EngineeringPrincess Nourah Bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Information Systems College of Computing and Information SystemUmm Al-Qura UniversitySaudi Arabia Department of Computer Science College of Science&Art at MahayilKing Khalid UniversityMuhayel AseerSaudi Arabia Faculty of Computers and Information Computer Science DepartmentMenoufia UniversityEgypt Research Centre Future University in EgyptNew Cairo11845Egypt Department of Computer and Self Development Preparatory Year DeanshipPrince Sattam bin Abdulaziz UniversityAl-KharjSaudi Arabia Department of Information System College of Computer Engineering and SciencesPrince Sattam bin Abdulaziz UniversityAl KharjSaudi Arabia

Cyberbullying(CB)is a challenging issue in social media and it becomes important to effectively identify the occurrence of *** recently developed deep learning(DL)models pave the way to design CB classifier models with maximum *** the same time,optimal hyperparameter tuning process plays a vital role to enhance overall *** study introduces a Teacher Learning Genetic Optimization with Deep Learning Enabled Cyberbullying Classification(TLGODL-CBC)model in Social *** proposed TLGODL-CBC model intends to identify the existence and non-existence of CB in social media ***,the input data is cleaned and pre-processed to make it compatible for further *** by,independent recurrent autoencoder(IRAE)model is utilized for the recognition and classification of ***,the TLGO algorithm is used to optimally adjust the parameters related to the IRAE model and shows the novelty of the *** assuring the improved outcomes of the TLGODLCBC approach,a wide range of simulations are executed and the outcomes are investigated under several *** simulation outcomes make sure the improvements of the TLGODL-CBC model over recent approaches.

关键词： Social media deep learning cyberbullying cybersecurity hyperparameter optimization

来源：评论

学校读者我要写书评

暂无评论

ML-Driven HR system: Candidate Assessment for Enhanced Recruitment Outcomes 3

ML-Driven HR System: Candidate Assessment for Enhanced Recru...

引用

3rd International Conference on Automation, Computing and Renewable systems, ICACRS 2024

作者： Dixon, G.C. Srithanujan, S. Ranaweera, H.D.T.N. Ariyarathne, R.M.P.M. Weerasinghe, K.L. Gamage, N. Department of Information Technology SriLanka Institure of Information Technology New Kandy Rd Malabe Sri Lanka Department of Computer System engineering SriLanka Institure of Information Technology New Kandy Rd Malabe Sri Lanka Department of Computer Science and Software Engineering SriLanka Institure of Information Technology New Kandy Rd Malabe Sri Lanka

ISBN: (纸本)9798331532420

This study developed and implemented a machine learning-driven HR system designed to enhance recruitment outcomes, particularly in online interviews. Challenges such as candidate impersonation, interview question memorization, and deepfake manipulations were addressed. The system incorporated several critical processes utilizing advanced algorithms: pre-interview shortlisting employed Support Vector Machines (SVM) achieving 92% accuracy;cognitive skills assessment utilized adaptive testing methods powered by fine-tuned Large Language Models (LLMs) with 88% accuracy;emotional intelligence evaluation was conducted using deep learning-based emotion detection algorithms attaining 85% accuracy;face verification leveraged Convolutional Neural Networks (CNNs) for identity and deepfake detection with 90% accuracy;online video interviews were analyzed through integrated audio-visual processing techniques;language proficiency testing employed Natural Language Processing (NLP) models reaching 87% accuracy;analysis of thinking patterns was performed using sentiment analysis algorithms with 83% accuracy;and candidate grading was facilitated by ensemble learning methods ensuring consistent and reliable evaluations. The results demonstrated the system’s effectiveness in verifying candidate authenticity and assessing competence, providing a robust solution for modern recruitment challenges. © 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

Absolute longitudinal distance measurement verification of a standard polystyrene nanoparticle near a surface in water by means of multi-wavelength evanescent field 22

Absolute longitudinal distance measurement verification of a...

引用

22nd International Conference of the European Society for Precision engineering and Nanotechnology, EUSPEN 2022

作者： Blattler, Aran Khajornrungruang, Panart Suzuki, Keisuke Baba, Akiyoshi Goto, Daiki Graduate School of Computer Science and System Engineering Mechanical Information Science and Technology Course Kyushu Institute of Technology Fukuoka Japan Department of Intelligent and Control Systems Advanced Mechanical Division Kyushu Institute of Technology Fukuoka Japan Center of Microelectronic System Kyushu Institute of Technology Fukuoka Japan School of Computer Science and System Engineering Advanced Mechanical Course Kyushu Institute of Technology Fukuoka Japan

ISBN: (纸本)9781998999118

In the wet semiconductor process, abrasive nanoparticles are widely used in the chemical mechanical polishing (CMP) process to polish wafer surfaces for high planarization. During polishing, nanoparticles move with a high-speed three-dimensional (3D) position in the solution. In the 3D particles's moving positions, Z is a perpendicular longitudinal distance between the surface to the nanoparticle that plays a significant role in polishing, which could not be measured by general microscopy without longitudinal scanning. To understand nanoparticle phenomena near-surface, we have proposed and developed the apparatus with real-time fastmotion tracking on optical multi-wavelength evanescent fields microscopy to measure the 3D motion of the nanoparticle in water without scanning. In euspen's 2020, we could verify the relative distance ?Z of nanoparticles in water, but the absolute distance Z is unknown yet. In this manuscript, we have therefore developed an invisible nano-step height in water to verify the absolute height Z of an individual nanoparticle. The invisible nano-step height in water is made from an optical resin with a refractive index of 1.35 that is close to a refractive index of water to avoid unnecessary light during experimental verification. The nano-step height was less than 100 nm on a glass surface, fabricated using nanoimprint lithography. Polystyrene f100 nm standard particles in water were used to verify the height Z. The results of height Z of nanoparticles could be measured less than 100 nm with the measurement uncertainty ±10 nm (2s), which is related to the interferometer result of the nano-step height. © European Society for Precision engineering and Nanotechnology, Conference Proceedings - 22nd International Conference and Exhibition, EUSPEN 2022. All rights reserved.

关键词： Nanoparticles

来源：评论

学校读者我要写书评

暂无评论

Robust Method for Embedding an Image Inside Cover Image Based on Least Significant Bit Steganography

引用

Informatica (Slovenia) 2022年第9期46卷 53-60页

作者： Almola, Sahera A.S. Qasim, Najat H. Ali Abed Alasadi, Hamid Department of Information System College of Computer Sciences and Information Technology University of Basrah Iraq Department of Computer Science College of Education for Pure Sciences University of Basrah Iraq Communications Engineering Department Iraq University College Istqlal Street Basra61004 Iraq

According to the enormous evolution of the internet and communications, the security of private or sensitive information has become the important issue. The private information can be passed between a sender and a receiver with high security using Cryptography and Steganography. By the cryptography, as the information can be secured with the cipher key for encryption. By the Steganography, the secret information can hide within usual data such as images, videos, audios. In this paper we proposed the robust method that includes two phases. The first phase consists of two stages. In the first stage we encrypt a secret image using encryption algorithm in order of increasing security of information. In the second stage, we complete the first stage for embedding the most significant bits (MSB) of the encrypted image into the least significant bits (LSB) of the cover image for instituting the stego image. The second phase is the obverse of the first phase, where, the encrypted image is retrieved from the stego image and then, decrypted process construct the secret image. The proposed method is efficient in terms of security compare with the other methods. Where, both encryption and embedding algorithms have an efficient role for embedding the secret image and preserving the good visual quality of stego images. Furthermore, extraction algorithms obtained better and faster results to a restoration of the secret image. © 2022 Slovene Society Informatika. All rights reserved.

关键词： Steganography

来源：评论

学校读者我要写书评

暂无评论

TRNet: Two-Tier Recursion Network for Co-Salient Object Detection

引用

IEEE Transactions on Circuits and systems for Video Technology 2025年第6期35卷 5844-5857页

作者： Cong, Runmin Yang, Ning Liu, Hongyu Zhang, Dingwen Huang, Qingming Kwong, Sam Zhang, Wei Shandong University School of Control Science and Engineering Jinan250061 China Ministry of Education Key Laboratory of Machine Intelligence and System Control Jinan250061 China Beijing Jiaotong University Institute of Information Science Beijing100044 China Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing100044 China Northwestern Polytechnical University Brain and Artificial Intelligence Laboratory School of Automation Xi'an710129 China University of Chinese Academy of Sciences School of Computer Science and Technology Beijing101408 China Lingnan University Hong Kong

Co-salient object detection (CoSOD) is to find the salient and recurring objects from a series of relevant images, where modeling inter-image relationships plays a crucial role. Different from the commonly used direct learning structure that inputs all the intra-image features into some well-designed modules to represent the inter-image relationship, we resort to adopting a recursive structure for inter-image modeling, and propose a two-tier recursion network (TRNet) to achieve CoSOD in this paper. The two-tier recursive structure of the proposed TRNet is embodied in two stages of inter-image extraction and distribution. On the one hand, considering the task adaptability and inter-image correlation, we design an inter-image exploration with recursive reinforcement module to learn the local and global inter-image correspondences, guaranteeing the validity and discriminativeness of the information in the step-by-step propagation. On the other hand, we design a dynamic recursion distribution module to fully exploit the role of inter-image correspondences in a recursive structure, adaptively assigning common attributes to each individual image through an improved semi-dynamic convolution. Experimental results on five prevailing CoSOD benchmarks demonstrate that our TRNet outperforms other competitors in terms of various evaluation metrics. The code and results of our method are available at https://***/rmcong/TRNetTCSVT2025. © 1991-2012 IEEE.

关键词： HTTP

来源：评论

学校读者我要写书评

暂无评论

Identifying Inaccurate Stories: Leveraging High Knowledge and Big Data 15

Identifying Inaccurate Stories: Leveraging High Knowledge an...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Khan, Mohammad Ahmar Verma, Pushpendra Kumar Ghaldiyal, Shivangi Balaji, N.V. Francis, G. Arun Patil, Swati Bula Department of Management Information System College of Commerce & Business Administration Dhofar University Country Sultanate of Oman Oman School of Computer Science and Applications IIMT University Meerut India Department of Computer Applications Invertis University Uttar Pradesh Bareilly India Department of Computer Science Karpagam Academy of Higher Education Tamil Nadu Coimbatore India Department of Electronics and Communication Engineering Karpagam College of Engineering Tamil Nadu Coimbatore India IT Vishwakarma Institute of Technology Pune India

ISBN: (纸本)9798350370249

Research on fake news has gained significant traction in a number of fields, We describe how the issue is tackled from a natural language processing standpoint in this research with the aim of developing identify false material in news. Collecting high-quality data, such as examples of false and actual news stories on a diverse range of subjects, is the key obstacle in this field of study. We examine the available before introducing the site as our lab's gift to the . We provide the whole text of the news that have already been applied based on human evaluation of the articles' authenticity. In order to clarify the gaps and causes of imbalance in the datasets that are now accessible and to direct ongoing attempts, we also conduct an appearance-based experiment. We urge the public to gather more information and make it accessible for study. ©2024 IEEE.

关键词： Data collection

来源：评论

学校读者我要写书评

暂无评论

What Improves the Generalization of Graph Transformers? A Theoretical Dive into the Self-attention and Positional Encoding 41

What Improves the Generalization of Graph Transformers? A Th...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Li, Hongkang Wang, Meng Ma, Tengfei Liu, Sijia Zhang, Zaixi Chen, Pin-Yu Department of Electrical Computer and System Engineering Rensselaer Polytechnic Institute TroyNY United States Department of Biomedical Informatics Stony Brook University Stony BrookNY United States Department of Computer Science and Engineering Michigan State University East LansingMI United States MIT-IBM Watson AI Lab IBM Research MA United States Department of Computer Science and Engineering University of Science and Technology of China Anhui Hefei China IBM Thomas J. Watson Research Center Yorktown HeightsNY United States

Graph Transformers, which incorporate self-attention and positional encoding, have recently emerged as a powerful architecture for various graph learning tasks. Despite their impressive performance, the complex non-convex interactions across layers and the recursive graph structure have made it challenging to establish a theoretical foundation for learning and generalization. This study introduces the first theoretical investigation of a shallow Graph Transformer for semi-supervised node classification, comprising a self-attention layer with relative positional encoding and a two-layer perceptron. Focusing on a graph data model with discriminative nodes that determine node labels and non-discriminative nodes that are class-irrelevant, we characterize the sample complexity required to achieve a desirable generalization error by training with stochastic gradient descent (SGD). This paper provides the quantitative characterization of the sample complexity and number of iterations for convergence dependent on the fraction of discriminative nodes, the dominant patterns, and the initial model errors. Furthermore, we demonstrate that self-attention and positional encoding enhance generalization by making the attention map sparse and promoting the core neighborhood during training, which explains the superior feature representation of Graph Transformers. Our theoretical results are supported by empirical experiments on synthetic and real-world benchmarks. Copyright 2024 by the author(s)

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Reference Tracking for Constrained Uncertain Linear systems by Stochastic MPC

引用

IFAC-PapersOnLine 2023年第2期56卷 10421-10427页

作者： Jannik Hahn Olaf Stursberg Control and System Theory Dept. of Electrical Engineering and Computer Science University of Kassel 34121 Kassel Germany

This paper addresses model predictive control of a class of linear systems subject to additive stochastic disturbances and constraints. The underlying stochastic optimal control problem combines inverse cumulative distribution functions with ellipsoid-in-polyhedron formulations to reduce the conservatism induced by constraint satisfaction. By use of terminal constraints and time-varying weights within the cost functional, the presented control scheme satisfies criteria for mean-square stability and can be adapted to reference-tracking problems for arbitrary reference signals.

关键词： Probabilistic Constraints Mean-Square Stability Predictive Control Stochastic Control Uncertain systems

来源：评论

学校读者我要写书评

暂无评论

Leveraging the Pre-Trained Whisper Model and Levenshtein Distance for Audio Buginesse Transcription

Leveraging the Pre-Trained Whisper Model and Levenshtein Dis...

引用

2024 Beyond Technology Summit on Informatics International Conference, BTS-I2C 2024

作者： Mukmin, Amirul Adnan Jalil, Abdul Pallawabonang, Mahabintang Prakasa, Esa Yuyun Handayani University of Makassar Dept. of informatics engineering Makassar Indonesia Handayani University of Makassar Dept. of computer system Makassar Indonesia Research center for data and information science National Research and Innovation Agency Bandung Indonesia

ISBN: (纸本)9798331508579

This research aims to transcribe audio into text using the pre-trained Whisper model, focusing on Bugis, a low-resource language. A key challenge in transcribing local languages like Bugis is the limited availability of language model. To address this, we implemented an algorithmic correction approach that does not require extensive datasets or computationally demanding customizations. The Whisper model provides an initial transcription, serving as a foundation;however, the output often lacks accuracy due to the absence of specific adjustments for Bugis. To enhance accuracy, we applied the Levenshtein distance algorithm to correct word errors by comparing transcription results with entries in a Bugis language dataset based on similarity. Although this method is not fully precise and depends on the completeness of the reference dataset, evaluation results indicate that it effectively lowers the word error rate (WER) and improves transcription accuracy. This research produces SRT files containing transcripts that have been corrected using the Levenhstein distance algorithm, which not only improves accessibility but also contributes to the preservation of Bugis language through digital media. This approach is expected to provide a practical solution to improve transcription accuracy and support more accurate documentation in Bugis language preservation efforts. © 2024 IEEE.

关键词： Speech recognition

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：