检索结果-内蒙古大学图书馆

Advance Computing and Innovative technologies in Engineering (ICACITE), International Conference on

作者： A. Sangeetha Devi Deepanshu Bhatt Saloni Bansal A Keerthika T. Mohanraj S. Santhosh Department of Science and Humanities (Mathematics) Nehru Institute of Engineering and Technology T.M.Palayam Tamil Nadu India Department of Mechanical Engineering IES Institute of Technology and Management IES University Bhopal M.P India Department of Computer Engineering and Applications GLA University Mathura Department of Computer Science and Engineering Prince Shri Venkateshwara Padmavathy Engineering College TN Department of Computer Science Engineering (CSE) Karpagam Academy of Higher Education TN Department of Electronic and Communication Engineering Einstein College of Engineering Tamil nadu

ISBN: (数字)9798350360165

ISBN: (纸本)9798350360172

The scientific community and industry have been working together in recent years to shift computational resources off centralized cloud systems to decentralized computing, or ‘edge’ computing. This change is a result of the cloud system’s inability to keep up with the growing demands of emerging relationships, which are marked by the spread of time-sensitive applications like sophisticated robotics, augmented reality/virtual the truth technologies, self-driving cars, and vital remote control of Internet of Things applications. Decentralized computing at the border is still in its infancy and lacks a full platform, despite the critical role that it will play in future distributed systems. This article presents OMNIBUS, a novel decentralized edge architecture. This approach uses moving vehicles as resources for processing and storage, enabling the continuous delivery of computational capability to end-devices across many locations. Scalability and flexibility are two characteristics that set OMNIBUS distinct from other edge computing solutions. The suggested method, which is based on mathematical models of prediction, determines computational capacity for particular locations by learning the direction and time of vehicle movements. It also presents a theoretical foundation for learning, improvement, and caching amid dynamic conditions caused by moving vehicles, specifically for sequential concurrent conversion. OMNIBUS’s scalability allows for almost infinite growth, which might result in a significant increase in network speed.

关键词： Cloud computing Scalability Transportation computer architecture Traffic control Nonlinear dynamical systems Smart grids

来源：评论

学校读者我要写书评

暂无评论

Efficient Novel Method for EEG Signal Classification in Epileptic Seizure Identification using Metaheuristic Deep Learning

Efficient Novel Method for EEG Signal Classification in Epil...

引用

Recent Advances in science and Engineering Technology (ICRASET), International Conference on

作者： Kiran Sree Pokkuluri Nishesh Nigam Avita Fuskele C. Raja Prashant Kumar Shukla Chhaya Department of Computer Science and Engineering Shri Vishnu Engineering College for Women Bhimavaram India Department of Computer Science and Engineering IES Institute of Technology and Management IES University Bhopal MP India Information Technology Department Jabalpur Engineering College Jabalpur India ECE Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram Guntur India Mangalayatan University Jabalpur India

ISBN: (数字)9798350388602

ISBN: (纸本)9798350388619

Using a metaheuristic deep learning strategy, the research focuses on the challenge of epileptic seizure detection. A diagnostic tool known as an electroencephalogram (EEG) may detect improperly functioning brain cells, the underlying cause of seizures. To enhance the precision of seizure detection, the offered approach merges deep learning with a metaheuristic optimization technique. This method involves preprocessing raw EEG data in order to extract fundamental characteristics. A classifier that is part of a deep learning system is subsequently fed these characteristics in stages. When it comes to finding a decent solution with high accuracy dimensions, the metaheuristic component finds the optimal values for the deep learning model. Due to the sluggish convergence and trapping of local minima in standard clustering methods, this approach seeks to improve detection performance. Using industry standard EEG datasets, we evaluate our hybrid technique’s performance to that of other relevant models. These findings demonstrate that the system is a dependable tool for real-time seizure detection, with sensitivity, specificity, and accuracy all surpassing the current standards. This method stands head and shoulders above its predecessors, proving its viability for clinical usage in epilepsy monitoring and diagnosis.

关键词： Deep learning Training Accuracy Sensitivity Convolution Metaheuristics Epilepsy Brain modeling Electroencephalography Standards

来源：评论

学校读者我要写书评

暂无评论

Reply with Sticker: New Dataset and Model for Sticker Retrieval

arXiv

引用

arXiv 2024年

作者： Liang, Bin Wang, Bingbing Bai, Zhixin Lang, Qiwei Sun, Mingwei Hou, Kaiheng Zhou, Lanjun Xu, Ruifeng Wong, Kam-Fai Department of Systems Engineering and Engineering Management The Chinese University of Hong Kong Hong Kong Shenzhen China Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies Shenzhen China School of Computer Science and Technology Harbin Institute of Technology Harbin China School of Computer Science and Artificial Intelligence Foshan University Foshan China

Using stickers in online chatting is very prevalent on social media platforms, where the stickers used in the conversation can express someone’s intention/emotion/attitude in a vivid, tactful, and intuitive way. Existing sticker retrieval research typically retrieves stickers based on context and the current utterance delivered by the user. That is, the stickers serve as a supplement to the current utterance. However, in the real-world scenario, using stickers to express what we want to say rather than as a supplement to our words only is also important. Therefore, in this paper, we create a new dataset for sticker retrieval in conversation, called StickerInt, where stickers are used to reply to previous conversations or supplement our words1. Based on the created dataset, we present a simple yet effective framework for sticker retrieval in conversation based on the learning of intention and the cross-modal relationships between conversation context and stickers, coined as Int-RA. Specifically, we first devise a knowledge-enhanced intention predictor to introduce the intention information into the conversation representations. Subsequently, a relation-aware sticker selector is devised to retrieve the response sticker via cross-modal relationships. Extensive experiments on the created dataset show that the proposed model achieves state-of-the-art performance in sticker retrieval2 © 2024, CC BY-NC-ND.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Robust Secure Access Entrance Method Based on Multi Model Biometric Credentials Iris and Finger Print 3rd

A Robust Secure Access Entrance Method Based on Multi Model ...

引用

3rd International Conference on Machine Learning, Image Processing, Network Security and Data sciences, MIND 2021

作者： Yadav, Pranay Chaurasia, Nishant Gola, Kamal Kumar Semwan, Vijay Bhasker Gomasta, Rakesh Dubey, Shivendra Madhya Pradesh Bhopal462023 India Department of Computer Science and Engineering S V Polytechnic College Madhya Pradesh Bhopal462002 India Uttarakhand Roorkee247667 India Department of CSE MANIT Madhya Pradesh Bhopal India Department of Research and Development Navigator Technologies Madhya Pradesh Bhopal India Senior IT Faculty iNurture Education Solution Pvt. Ltd Karnataka Bangalore560052 India

ISBN: (纸本)9789811958670

In the last decade secure access entrance system is a critical problem in between researchers. Single model-based biometric credentials entrance system face many lack of access failures. There failures are over come in multi model secure access system in which use more than one biometric system such as finger print as well as iris or finger print as well as face recognition. In this proposed work presented a secure access entrance multi model that is based on two biometric credentials iris as well as finger print. For the simulation of proposed method use matrix laboratory (R2018b). Simulations indicate proposed multi model biometric internee system perform better as compare to single model entrance system. The proposed method compare the performance in terms of accuracy. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Talent Acquisition in Human Resources with Advanced Deep Learning-Based Resume Screening and Candidate Matching Algorithms 3

Revolutionizing Talent Acquisition in Human Resources with A...

引用

3rd IEEE International Conference on Automation and Computation, AUTOCOM 2025

作者： Dilli Ganesh, V. Erkinjon, Tulovov Alzubaidi, Laith H. Vijayakumar, K. Singh, K. Ranjith Rahuman, A. Kaleel Department of Mechanical Engineering Chennai India Tashkent State University of Economics Department of Audit Tashkent Uzbekistan College of technical engineering The Islamic University Department of Computer Techniques Engineering Najaf Iraq Flextronics Technologies India Pvt.Ltd. India Karpagam Academy of Higher Education Department of Computer Science Coimbatore India Psna College of Engineering and Technology Department of Electronics and Communication Engineering India

ISBN: (纸本)9798331542375

In general, this paper outlines a research agenda to transform the approach to talent management in HR using deep learning strategies for enhanced resume analysis and candidate matching. The above work proposed and developed a system that exploits the most advanced tools of natural language processing, and recent advances in neural networks to correctly parse resumes and the candidates to jobs descriptions. The system deals with the issues of unstructured resume data, the efficient extraction of the required data, and assessment of the candidate on his/her fitness in the given company in terms of his/her technical competencies and compatibility with the company's work culture. Substantial real life data analysis presented in the paper proves high efficiency and equity of the applications. This research also incorporates the ethical questions as well as the ways of dealing with data privacy regulations and the biases in the historical data by applying the explainable AI methods. A questionnaire to the users of the system, which are the HR professionals further verifies the real-world application and usability of the system based on concepts such as ease of use, precision and time economy. In conclusion, the study adds knowledge to the process of establishing ethical and optimal AI implementations in the field of HRM and results in the improvement of talent recruitment strategies and practices promoting fair hiring decisions. © 2025 IEEE.

关键词： Mergers and acquisitions

来源：评论

学校读者我要写书评

暂无评论

A Novel Recurrent Neural Net based Dimension Reduction Technique for Effectual Data Visualization

A Novel Recurrent Neural Net based Dimension Reduction Techn...

引用

Communications and Information technologies (GCCIT), Global Conference on

作者： Monoo John Y. K. Sharma N. V. Balaji Sahil Suri Nishanthi R Samaksh Goyal School of Mangement - PG Management JAIN (Deemed to be University) Bangalore Karnataka Computer Engineering Vishwakarma Institute of Technology Pune Department of Computer Science Karpagam Academy of Higher Education Coimbatore Centre of Research Impact and Outcome Chitkara University Rajpura Punjab India Department of Computer Science and Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai Quantum University Research Center Quantum University Roorkee Uttarakhand India

ISBN: (数字)9798350388916

ISBN: (纸本)9798350388923

t-SNE, UMAP, & Tramp have shown excellent visualization performance on various real-world datasets. These approaches may preserve global structure but not local structure, a trade-off that has always plagued them. computer science RNN machine learning is evolving. RNN models can reliably forecast numeric values or nominal classifications, but a general-purpose mechanism for RNN architecture construction has yet to be devised. computer scientists must use trial-and-error to create accurate RNN models. Models often need multiple input parameters. When there are many input factors, it might be hard to determine which ones affect model prediction the most. science calls this the "curse of dimensionality." Problems may be reduced to two dimensions, however. Humans can plan and understand two-dimensional problems. Visualizing a multi-dimensional dataset may reveal which input factors most affect a nominal or numeric outcome. Identifying these factors may help train RNN models faster by utilizing only input variables that impact the result variable. This study explores RNN training methods and uses dimensional reduction to see and interpret complicated data.

关键词： Training Recurrent neural networks Accuracy Computational modeling Data visualization Predictive models Mathematical models Numerical models Reliability Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Leveraging Neural Networks with BiLSTM and CNN Models for Enhanced HR management Practices

Leveraging Neural Networks with BiLSTM and CNN Models for En...

引用

Integrated Circuits and Communication Systems (ICICACS), IEEE International Conference on

作者： Yamini Kalva Anuradha Parasar Rajlaxmi Pramod Pujar K. Balasubramanian Zameer Pasha S. Ramya Department of Computer Science and Engineering Sri Ramachandra Institute of Higher Education and Research Chennai India School of Liberal Education Galgotias University Dankaur India Department of Marketing Indira School of Business Studies PGDM Pune India Department of Computer Applications Kalasalingam Academy of Research and Education- Deemed to be University Krishnankoil India Department of Management St. Claret College (Autonomous) Bengaluru India Department of Artificial Intelligence and Machine Learning M.Kumarasamy College of Engineering Karur India

ISBN: (数字)9798331508456

ISBN: (纸本)9798331508463

The most valuable asset of any business is its employees. Even with technological advances, organizations rely heavily on human resources for system administration. An increasingly competitive sector makes managing and retaining talented workers difficult. An organization's ability to develop, survive, and compete depends on its employees' skills. These challenges can be overcome using preprocessing, feature extraction, and model training. Data preparation for machine learning is necessary yet time-consuming. Features selection is critical since it enhances accuracy and reduces overfitting. CNN-BiLSTM trained the model. The CNN- BiLSTM model outperformed BiLSTM and CNN. The model's 90.62 percent accuracy showed it could handle HR tasks. For effective human resource management, this study recommends sophisticated machine learning models. Today's businesses need reliable tools for managing and keeping people, and the CNN-BiLSTM model helps.

关键词： Training Accuracy Bidirectional long short term memory Machine learning Aging Feature extraction Convolutional neural networks Integrated circuit modeling Retirement Overfitting

来源：评论

学校读者我要写书评

暂无评论

A Colored Petri Net Tool for the Design of Robotic Palletizing Cells

A Colored Petri Net Tool for the Design of Robotic Palletizi...

引用

International Conference on Control, Decision and Information technologies (CoDIT)

作者： Graziana Cavone Silvia Stella Paolo Scarabaggio Raffaele Carli Stefano Lisi Achille Claudio Garavelli Mariagrazia Dotoli Department of Civil Computer Science and Aeronautical Technologies Engineering University Roma Tre Italy Department of Mechanics Mathematics and Management Polytechnic of Bari Italy Department of Electrical and Information Engineering Polytechnic of Bari Italy

Driven by the digital transformation required by Logistics 4.0, the use of automation in warehouses is constantly growing. In particular, robotic palletizers offer significant potential for optimizing warehouse operations, thanks to higher flexibility and throughput than traditional palletizing systems. Despite the availability of several solutions in the market, the optimal deployment of a robotic palletizer in warehouses is not straightforward: a design phase is needed to determine the most convenient configuration that ensures automatic palletizing is fully integrated into the warehouse processes. In this paper, we propose a simulation-based versatile tool for modeling and analysis purposes, aimed at supporting the design of a robotic palletizing cell in a bottom-up fashion. As a core methodology, we employ timed colored Petri nets, which allow - once the analysis on packing requirements and constraints is conducted - to rapidly model the system as a composition of basic subsystems, and implement alternative simulations to evaluate the corresponding performance and effectively benchmark the alternative configurations. The proposed approach is applied to a real case study, showing its effectiveness in identifying the solution that achieves a good compromise between the use of resources and the performance of warehouse operations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SBA: A Swift and Stealthy Backdoor Attack Framework for Federated Learning

SBA: A Swift and Stealthy Backdoor Attack Framework for Fede...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Junhan Wang Zhangming Wu Zhuoyue Wang Lu Dong School of Cyber Science and Engineering Southeast University Nanjing China Engineering Research Center of Blockchain Application Supervision and Management Southeast University Ministry of Education Department of Electrical Engineering and Computer Sciences University of California Berkeley USA

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Federated Learning (FL) enables collaborative model training while protecting the privacy of individual participants. However, this decentralized framework is vulnerable to certain risks, particularly backdoor attacks. In such attacks, malicious actors embed triggers into the global model, causing incorrect classifications for inputs with specific features. Traditional backdoor attacks typically use uniform triggers, which makes them more likely to be detected. Furthermore, These methods tend to overlook the fact that poisoned samples may cause abnormal confidence levels in non-target classes. These methods also require an extended attack window to achieve the desired success rate, which reduces their efficiency and increases the chances of detection. This paper introduces a novel backdoor attack method called Swift Backdoor Attack (SBA), designed to overcome these challenges. SBA improves both the stealth and success rate of backdoor attacks by generating adaptive triggers tailored to specific inputs. It also incorporates Non-Target Class Suppression (NTCS) loss and an entropy gain mechanism to enhance the attack’s effectiveness. Our approach suppresses unnecessary activations in the neural network when encountering poisoned samples, making the attack harder to be detected. Experimental results demonstrate that this method significantly increases the success rate of backdoor attacks within a shorter attack window, while evading existing detection mechanisms. This provides a more efficient and covert strategy for executing backdoor attacks in FL. Our code is available at https://***/bigcheeses/SBA.

关键词： Training Privacy Codes Federated learning Neural networks Collaboration Signal processing Entropy Robustness Speech processing

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Feature-Selection Method Based on mRMR and Binary Peacock Optimization Algorithm

A Hybrid Feature-Selection Method Based on mRMR and Binary P...

引用

International Conference on Computational and Characterization Techniques in Engineering & sciences (CCTES)

作者： Bibhuprasad Sahu Amrutanshu Panigrahi Abhilash Pati Rajalaxmi Mishra Sudhir Kumar Senapati Kashyapa Kanti Sahu Department of Information Technology Vardhaman College of Engineering (Autonomous) Hyderabad India Department of CSE Siksha 'O' Anusandhan (Deemed to be University) Bhubaneswar Odisha India Department of CSA College of IT and Management Education Bhubaneswar Odisha India Department of Computer Science Pj College of Management and Technology Bhubaneswar Odisha India

ISBN: (数字)9798350364699

ISBN: (纸本)9798350364705

An essential aspect of developing effective biomarkers that facilitate disease diagnosis and drug discovery is identifying the most critical characteristics from microarray data. Since it is expensive to validate biomarkers, the number of biomarkers must be reduced while retaining their effectiveness. A common challenge with microarray data is that it results in a large number of properties, known as the curse of dimensionality. Almost all the feature selection (FS) techniques developed up-to-date do not possess the ability to result in lower dimensionality, ensure sound classification, easy algorithms and exhaustive search of the parameter space. This study describes a hybrid FS approach by combining the mRMR and binary variant of the peacock algorithm (Binary POA) algorithm. It introduces mRMR by modifying its quantization functions to the continuous nature of the microarray data attribute and uses mRMR as a first step to normalize both datasets and select an initial feature subset. In the following step, a binary POA algorithm is deployed to optimize the selected feature subset. The performance of the proposed mRMR-BPOA ML model is evaluated using benchmark classifier Support Vector Machine. The Result analysis proves that the performance of mRMR-BPOA is superior to the existing counterparts.

关键词： Support vector machines Quantization (signal) Biomarkers Filtering algorithms Feature extraction Classification algorithms Drug discovery Medical diagnosis Optimization Cancer

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：