检索结果-内蒙古大学图书馆

Performance Evaluation of Biometric Authentication Using Fragment Jaya Optimizer-Based Deep CNN with Multi-kernel SVM

引用

SN computer science 2024年第4期5卷 337页

作者： Umasankari, N. Muthukumar, B. Shanmuganathan, C. Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India School of Computing Department of CSE Sathyabama Institute of Science and Technology Chennai India Rajalakshmi Engineering College Chennai India Department of Computer Science and Engineering SRM Institute of Science and Technology Ramapuram Chennai India

The earlier research clearly indicated that the bimodal authentication system has more efficiency than unimodal and multimodal. This is due to the reason for the best intact biometric traits of fingerprint and retina. There is a chance to additionally improve further performance of the proposed biometric trait combination by additional or alternate algorithms or methodologies. Therefore, in this research work, the multi-kernel support vector machine (MK-SVM), a machine learning classification approach, is proposed and is used for the implementation. In addition, a hybrid algorithm of fragment Jaya optimizer-based deep convolutional neural network (FJO-DCNN) approach is also used to improve the performance value for bimodal biometric authentication and classification. The recognition systems analyze both biometrics independently, and their conclusions are combined to determine whether to give or refuse access to the user in the end. According to the findings of the implementation, this work demonstrates more dependability than the cascaded biometric system. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd 2024.

关键词： Bimodal biometric authentication Deep convolutional neural network Fragment Jaya optimizer convolutional neural network Multi-kernel support vector machine

来源：评论

学校读者我要写书评

暂无评论

VidSum-Video Summarization using Deep Learning 2

VidSum-Video Summarization using Deep Learning

引用

2nd International Conference on Informatics, ICI 2023

作者： Anand, Nishit Koshariya, Rupesh Kumar Garg, Varsha Jaypee Institute of Information Technology Noida Department of Computer Science Engineering and Information Technology Noida India

ISBN: (纸本)9798350343830

The aim of video summarization is to create a short summary video which captures the essence of the original video and contains all the important events of the original video. This is helpful because, now we don't have to go through the entire video and are able to get a gist of it from just a short summary video. Current Supervised learning video summarization methods, use Convolutional Neural Networks and some supervised learning techniques use Recurrent Neural Networks in addition to them. We propose VidSum, an architecture for Video Summarization using Deep Learning. We combine Long Short Term Memory (LSTM) Networks with Convolutional Neural Networks to solve the problem of Video Summarization. Our deep learning model is able to find the temporal importance of video frames and is able to generate video summaries which are temporally coherent and contain the important parts of a video clip. In our testing, our model outperforms other models on the famous TVSum and SumMe datasets for the task of Video Summarization. © 2023 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Binary and Multi-Class Classification of RPL-Based Routing Attacks: An Experimental Study 4

Binary and Multi-Class Classification of RPL-Based Routing A...

引用

4th IEEE International Conference on Mobile Networks and Wireless Communications, ICMNWC 2024

作者： Sharma, Hemant Yadav, Gyan Singh Indian Institute of Information Technology Kota Department of Computer Science and Engineering Kota325003 India

ISBN: (纸本)9798350352931

The Internet of Things (IoT) envisions billions to trillions of everyday objects that can be traced, addressed, and transmitted data. Typically, Low-power and Lossy Networks (LLNs) provide a mechanism for data exchange between IoT devices with limited power, processing capability, and memory. Routing over Low Power and Lossy Network (RPL) is a distance vector proactive routing protocol for LLN-based networks defined by the Internet engineering Task Force (IETF). However, an RPL protocol is still vulnerable to a variety of routing attacks, which could disrupt the entire network architecture. As a security aspect of the RPL protocol against routing attacks, learning-based intrusion detection systems and classification have emerged as a promising research area, drawing the attention of several researchers. This paper contributes to this effort by conducting an experimental study on the classification of routing attacks using learning algorithms. A binary and multiclass dataset was created from the individual attack samples in the IoTR-DS dataset, and feature extraction via correlation enhanced the dataset with important features. To perform binary and multiclass classification, we used algorithms based on Machine Learning and Deep Learning, including Multi-layer Perceptron (MLP), Random Forest (RF), Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and Decision Tree. The performance metrics used were recall, precision, f1-score, accuracy, and root mean square error. Random Forest (RF) achieves the highest accuracy for binary (98.05%) and multiclass (99.38%), with the lowest root mean square error (0.1396). © 2024 IEEE.

关键词： Random forests

来源：评论

学校读者我要写书评

暂无评论

Secondary electron emission and photoemission from a negative electron affinity semiconductor with large mean escape depth of excited electrons

引用

Chinese Physics B 2023年第4期32卷 677-690页

作者：谢爱根董红杰刘亦凡 School of Physics and Optoelectronic Engineering Nanjing University of Information Science and TechnologyNanjing 210044China Jiangsu Key Laboratory for Optoelectronic Detection of Atmosphere and Ocean Nanjing University of Information Science&TechnologyNanjing 210044China Jiangsu international Joint Laboratory on Meteorological Photonics and Optoelectronic Detection Nanjing University of Information Science&TechnologyNanjing 210044China

The formulae for parameters of a negative electron affinity semiconductor(NEAS)with large mean escape depth of secondary electrons A(NEASLD)are *** methods for obtaining parameters such asλ,B,E_(pom)and the maximumδandδat 100.0 keV≥E_(po)≥1.0 keV of a NEASLD with the deduced formulae are presented(B is the probability that an internal secondary electron escapes into the vacuum upon reaching the emission surface of the emitter,δis the secondary electron yield,E_(po)is the incident energy of primary electrons and E_(pom)is the E_(po)corresponding to the maximumδ).The parameters obtained here are analyzed,and it can be concluded that several parameters of NEASLDs obtained by the methods presented here agree with those obtained by other *** relation between the secondary electron emission and photoemission from a NEAS with large mean escape depth of excited electrons is investigated,and it is concluded that the presented method of obtaining A is more accurate than that of obtaining the corresponding parameter for a NEAS with largeλ_(ph)(λ_(ph)being the mean escape depth of photoelectrons),and that the presented method of calculating B at E_(po)>10.0 keV is more widely applicable for obtaining the corresponding parameters for a NEAS with largeλ_(ph).

关键词： negative electron affinity semiconductor secondary electron emission photoemission the probability secondary electron yield large mean escape depth of excited electrons

来源：评论

学校读者我要写书评

暂无评论

Convolution Neural Network Regression Model to Predict Personality Scores

引用

Journal of engineering science and technology Review 2022年第4期15卷 25-32页

作者： Bhamare, Mamta Ashokkumar, K. Department of Computer Science and Engineering Sathyabama Institute of Science & Technology Chennai India School of Computer Engineering and Technology MITWPU Pune India

The world has witnessed tremendous increase in the use of social media platforms in the last decade. Posting and updating on such platforms have become a way for people to express their opinions, experiences, feelings, views etc. Along with all these, they tend to post and share their personal information. This information can be used in advantageous way to understand their needs and requirements The approach, known as personality prediction, entails sepΑarating digital input into attributes and mapping it according to a personality model. In this paper, we are interested to predict the personality of such users. Researchers have shown based on the social behavior towards friends, number of friends, groups joined etc. can help in predicting the personality trait from Facebook and Twitter. The text posts for the user are converted to be suitable representation using GloVe algorithm. And then feeding it to Convolution Neural Net, a popular Deep Learning architecture on the text posts that was implemented for the traits present in the Big Five trait theory. This method helped to achieve comparable outputs with other recent models © 2022 school of science, IHU. All rights reserved

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Job Resumes Recommendation using Integration of Fuzzy Discernibility Matrix Feature Selection and Convolutional Neural Network Multi-label Text Classification

Informatica (Slovenia)

引用

Informatica (Slovenia) 2025年第13期49卷 49-58页

作者： Hayami, Regiolina Yusoff, Nooraini Daud, Kauthar Mohd Fatma, Yulia Department of Informatics Engineering Faculty Computer Science Universitas Muhammadiyah Riau Indonesia Faculty of Data Science and Computing Universiti Malaysia Kelantan 16100 Malaysia Center for Artificial Intelligence Technology Faculty of Information Science and Technology Universiti Kebangsaan Malaysia 43600 Malaysia

The manual analysis of job resumes poses specific challenges, including the time-intensive process and the high likelihood of human error, emphasizing the need for automation in content-based recommendations. Recent advancements in deep learning, particularly Convolutional Neural Networks (CNN) for Multi-label Text Classification (MLTC), offer a promising solution for addressing these challenges through artificial intelligence. While CNN is renowned for its robust feature extraction capabilities, it faces specific challenges such as managing high-dimensional data and poor data interpretability. To address these limitations, this study employs the Fuzzy Discernibility Matrix (FDM) feature selection technique to determine the relevance of skills for each job vacancy. FDM assigns weights to the features of each job category and ranks their relevance based on the highest scores, which are then utilized in the MLTC CNN model. The integration of FDM and MLTC CNN serves as the foundation for generating content-based recommendations derived from key features in job resumes. This study produces a content-based job recommendation system that displays the top three job categories, accompanied by explanations of the skills supporting each selected category. These recommendations also consider cosine similarity values between analyzed items and the integrated results of FDM and MLTC CNN. The application of FDM for feature weighting has been proven to enhance multi-label text classification outcomes by providing better insights during the feature selection process. With a recall of 97.26%, precision of 94.81%, and accuracy of 98.58%, the MLTC model integrating FDM feature selection and CNN demonstrates robust performance characteristics in content-based job recommendation tasks. © 2025 Slovene Society Informatika. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

LLDif: Diffusion Models for Low-Light Facial Expression Recognition 27th

LLDif: Diffusion Models for Low-Light Facial Expression Rec...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Wang, Zhifeng Zhang, Kaihao Sankaranarayana, Ramesh College of Engineering and Computer Science Australian National University CanberraACT Australia School of Computer Science and Technology Harbin Institute of Technology Shenzhen China

ISBN: (纸本)9783031782008

This paper introduces LLDif, a novel diffusion-based facial expression recognition (FER) framework tailored for extremely low-light (LL) environments. Images captured under such conditions often suffer from low brightness and significantly reduced contrast, presenting challenges to conventional methods. These challenges include poor image quality that can significantly reduce the accuracy of emotion recognition. LLDif addresses these issues with a novel two-stage training process that combines a Label-aware CLIP (LA-CLIP), an embedding prior network (PNET), and a transformer-based network adept at handling the noise of low-light images. The first stage involves LA-CLIP generating a joint embedding prior distribution (EPD) to guide the LLformer in label recovery. In the second stage, the diffusion model (DM) refines the EPD inference, ultilising the compactness of EPD for precise predictions. Experimental evaluations on various LL-FER datasets have shown that LLDif achieves competitive performance, underscoring its potential to enhance FER applications in challenging lighting conditions. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Analyze the impact of feature selection techniques in the early prediction of CKD

引用

International Journal of Cognitive Computing in engineering 2024年第1期5卷 66-77页

作者： Hema, K. Meena, K. Pandian, Ramaraj Department of Computer Science and Engineering GITAM School of Technology GITAM University Bangalore India Netapp San JoseCA United States

Background: Chronic renal disease, often known as Chronic Kidney Disease (CKD), is an illness that causes a steady decline in kidney function. As per the World Health Organization survey, the incidence of CKD may increase from 10% to 13% by 2030. Because of the lack of symptoms in the initial phase, diagnosing CKD early on may be difficult. The key objective of this study is to develop a forecasting model for the early detection of chronic renal disease. Methods: In medical science, Machine Learning (ML) Techniques play a significant role in disease prediction despite numerous studies conducted to categorize CKD in patients using machine learning tools. Most researchers need to analyze the impact of feature selection techniques, yielding high-quality and reliable results. The efficiency of any Techniques/Algorithms depends on feature selection, feature extraction, and classifiers. In this work, the impact of feature selection is experimented with using the Exhaustive Feature Selection (EFS) method. For the early prediction of CKD, a comparative examination of machine learning classifiers, including Gradient Boost (GB), XGBoost, Decision Tree (DT), Random Forest (RF), and KNN (k-nearest neighbors), are utilized. Results: Two types of datasets, standard (New Model) & real-time data sets collected from the dialysis unit of a reputed hospital in Chennai, are used to carry out extensive experiment analysis. Various metrics, including Accuracy, Precision, Recall, and F1-score, are used to tabulate the results of experiments conducted to measure the performance of the proposed approach for various combinations of test and training data. Conclusion: CKD is an irreversible and silent disease;it might have a high impact on many people and begin to manifest themselves at an early age in life. This research paper analyses the effect of feature selection techniques on early CKD prediction. © 2023 The Authors

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

UAV-Assisted Dynamic Avatar Task Migration for Vehicular Metaverse Services: A Multi-Agent Deep Reinforcement Learning Approach

引用

IEEE/CAA Journal of Automatica Sinica 2024年第2期11卷 430-445页

作者： Jiawen Kang Junlong Chen Minrui Xu Zehui Xiong Yutao Jiao Luchao Han Dusit Niyato Yongju Tong Shengli Xie IEEE School of Automation Guangdong University of TechnologyGuangzhou 510006China 111 Center for Intelligent Batch Manufacturing based on IoT Technology Guangzhou 510006China Key Laboratory of Intelligent Information Processing and System Integration of IoT Ministry of EducationGuangzhou 510006China School of Computer Science and Engineering Nanyang Technological UniversitySingaporeSingapore Pillar of Information Systems Technology and Design Singapore University of Technology and DesignSingaporeSingapore College of Communication Engineering Army Engineering University of PLANanjing 210007China National Natural Science Foundation of China Beijing 100085China Key Laboratory of Intelligent Detection and IoT in Manufacturing Ministry of EducationGuangzhou 510006China Guangdong Key Laboratory of IoT Information Technology Guangzhou 510006China

Avatars, as promising digital representations and service assistants of users in Metaverses, can enable drivers and passengers to immerse themselves in 3D virtual services and spaces of UAV-assisted vehicular Metaverses. However, avatar tasks include a multitude of human-to-avatar and avatar-to-avatar interactive applications, e.g., augmented reality navigation,which consumes intensive computing resources. It is inefficient and impractical for vehicles to process avatar tasks locally. Fortunately, migrating avatar tasks to the nearest roadside units(RSU)or unmanned aerial vehicles(UAV) for execution is a promising solution to decrease computation overhead and reduce task processing latency, while the high mobility of vehicles brings challenges for vehicles to independently perform avatar migration decisions depending on current and future vehicle status. To address these challenges, in this paper, we propose a novel avatar task migration system based on multi-agent deep reinforcement learning(MADRL) to execute immersive vehicular avatar tasks dynamically. Specifically, we first formulate the problem of avatar task migration from vehicles to RSUs/UAVs as a partially observable Markov decision process that can be solved by MADRL algorithms. We then design the multi-agent proximal policy optimization(MAPPO) approach as the MADRL algorithm for the avatar task migration problem. To overcome slow convergence resulting from the curse of dimensionality and non-stationary issues caused by shared parameters in MAPPO, we further propose a transformer-based MAPPO approach via sequential decision-making models for the efficient representation of relationships among agents. Finally, to motivate terrestrial or non-terrestrial edge servers(e.g., RSUs or UAVs) to share computation resources and ensure traceability of the sharing records, we apply smart contracts and blockchain technologies to achieve secure sharing management. Numerical results demonstrate that the proposed approach

关键词： Avatar blockchain metaverses multi-agent deep reinforcement learning transformer UAVs

来源：评论

学校读者我要写书评

暂无评论

Real-Time Lightweight Convolutional Neural Network for Polyp Detection in Endoscope Images

引用

Journal of Shanghai Jiaotong University (science) 2025年第3期30卷 521-534页

作者： Si, Bingqi Pang, Chenxi Wang, Zhiwu Jiang, Pingping Yan, Guozheng School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai200240 China Shanghai Engineering Research Center of Intelligent Drug Detoxification and Rehabilitation Shanghai200240 China College of Computer Science and Technology Jilin University Changchun130012 China

Colorectal cancer is the most common cancer with a second mortality rate. Polyp lesion is a precursor symptom of colorectal cancer. Detection and removal of polyps can effectively reduce the mortality of patients in the early period. However, mass images will be generated during an endoscopy, which will greatly increase the workload of doctors, and long-term mechanical screening of endoscopy images will also lead to a high misdiagnosis rate. Aiming at the problem that computer-aided diagnosis models deeply depend on the computational power in the polyp detection task, we propose a lightweight model, coordinate attention-YOLOv5-Lite-Prune, based on the YOLOv5 algorithm, which is different from state-of-the-art methods proposed by the existing research that applied object detection models or their variants directly to prediction task without any lightweight processing, such as faster region-based convolutional neural networks, YOLOv3, YOLOv4, and single shot multibox detector. The innovations of our model are as follows: First, the lightweight EfficientNetLite network is introduced as the new feature extraction network. Second, the depthwise separable convolution and its improved modules with different attention mechanisms are used to replace the standard convolution in the detection head structure. Then, the α-intersection over union loss function is applied to improve the precision and convergence speed of the model. Finally, the model size is compressed with a pruning algorithm. Our model effectively reduces parameter amount and computational complexity without significant accuracy loss. Therefore, the model can be successfully deployed on the embedded deep learning platform, and detect polyps with a speed above 30 frames per second, which means the model gets rid of the limitation that deep learning models must rely on high-performance servers. © Shanghai Jiao Tong University 2023.

关键词： Object detection

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：