检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Li, Xiao-Yu Zhu, Qin-Sheng Hu, Yong Wu, Hao Yang, Guo-Wu Yu, Lian-Hui Chen, Geng School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu610054 China School of Physics University of Electronic Science and Technology of China Chengdu610054 China Advanced Cryptography and System Security Key Laboratory of Sichuan Province Chengdu610103 China Institute of Electronics and Information Industry Technology of Kash Kash 844000 China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu610054 China

The Hidden Quantum Markov Model (HQMM) has significant potential for analyzing time-series data and studying stochastic processes in the quantum domain as an upgrading option with potential advantages over classical Markov models. In this paper, we introduced the split HQMM (SHQMM) for implementing the hidden quantum Markov process, utilizing the conditional master equation with a fine balance condition to demonstrate the interconnections among the internal states of the quantum system. The experimental results suggest that our model outperforms previous models in terms of scope of applications and robustness. Additionally, we establish a new learning algorithm to solve parameters in HQMM by relating the quantum conditional master equation to the HQMM. Finally, our study provides clear evidence that the quantum transport system can be considered a physical representation of HQMM. The SHQMM with accompanying algorithms present a novel method to analyze quantum systems and time series grounded in physical implementation. © 2023, CC BY-NC-SA.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Method for the Diagnosis of Retinal Diseases using Convolutional Neural Network

Machine Learning Method for the Diagnosis of Retinal Disease...

引用

Data science, Agents & Artificial Intelligence (ICDSAAI), International Conference on

作者： Sumit Kushwaha Jayaram Boga Bairaboina Sai Sambasiva Rao Syed Noeman Taqui R G Vidhya J. Surendiran Department of Computer Applications University Institute of Computing Chandigarh University Punjab India Department of Computer science and Data science Marri Laxman Reddy Institute of Technology and Management Hyderabad Telangana India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram Andhra India Department of VLSI Microelectronics Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai Tamil Nadu India Department of ECE HKBK College of Engineering Bangalore India

The early diagnosis of visual problems such as diabetic retinopathy and glaucoma relies on the successful completion of medical image processing tasks such as the segmentation of retinal blood vessels. The process of isolating retinal blood vessels from images of the retinal fundus is a challenging one because of the similarities in intensity that exist between blood vessels and the surrounding tissues. In addition, there are differences in the size, shape, and intensity of the vessels. In recent times, a number of different algorithms based on deep learning have been presented for the segmentation of retinal blood vessels. These techniques have been shown to be more accurate and dependable when compared to the traditional computer vision methods that have been used. In this abstract, we present the U-Net deep learning model as well as a technique for segmenting retinal blood vessels that is based on the programming language Python. A U-Net model is trained using a series of retinal fundus images so that the features of retinal blood vessels may be comprehended. As part of the inference process, the image of the retinal fundus is loaded into a trained version of the U-Net model. This model then generates a probability map that illustrates the chance that each pixel represents an artery in the human body. The final segmentation is produced by applying a threshold to the probability map. When it comes to the process of segmenting retinal blood vessels, our python-based solution outperforms methods that are considered to be state-of-the-art in studies comparing accuracy and speed. The scientific and medical communities have unrestricted access to the software that may be used to put the suggested strategy into action since it is an open-source initiative. In conclusion, the python-based approach for retinal blood vessel segmentation that makes use of U-Net provides a potentially helpful solution for identifying retinal illnesses and has the potential to serve as a stan

关键词：

来源：评论

学校读者我要写书评

暂无评论

Next-generation machine vision systems incorporating two-dimensional materials: Progress and perspectives

引用

InfoMat 2022年第1期4卷 23-39页

作者： Peisong Wu Ting He He Zhu Yang Wang Qing Li Zhen Wang Xiao Fu Fang Wang Peng Wang Chongxin Shan Zhiyong Fan Lei Liao Peng Zhou Weida Hu State Key Laboratory of Infrared Physics Shanghai Institute of Technical PhysicsChinese Academy of SciencesShanghaiChina University of Chinese Academy of Sciences BeijingChina Hangzhou Institute for Advanced Study University of Chinese Academy of SciencesHangzhouChina State Key Laboratory of ASIC and System School of MicroelectronicsFudan UniversityShanghaiChina Henan Key Laboratory of Diamond Optoelectronic Materials and Devices School of Physics and EngineeringZhengzhou UniversityZhengzhouChina Department of Electronic and Computer Engineering The Hong Kong University of Science and TechnologyClear Water BayKowloonHong Kong SARChina School of Physics and Electronics Hunan UniversityChangshaChina

Machine vision systems(MVSs)are an important component of intelligent systems,such as autonomous vehicles and ***,with the continuous increase in data and new application scenarios,new requirements are put forward for the next generation of *** is an urgent need to find new material systems to complement the existing semiconductor technology based on thin-film materials,and new architectures must be explored to improve *** of their unique physical properties,two-dimensional(2D)materials have received extensive attention for use in MVSs,especially in biomimetic ones:the human visual system,which can process complex visual information with low power consumption,provides a model for next-generation *** review paper summarizes the progress and challenges of applying 2D material photodetectors in sense-memory-computational integration and biomimetic image sensors for machine vision.

关键词： in-sensor computing machine vision systems photodetectors two-dimensional materials

来源：评论

学校读者我要写书评

暂无评论

Advancing HRM with AI Powered Recruitment Performance Management and Employee Engagement Using One Class SVMs 3

Advancing HRM with AI Powered Recruitment Performance Manage...

引用

3rd International Conference on Integrated Circuits and Communication Systems, ICICACS 2025

作者： Banu, Rafiya Tripathi, Ruchi Sharma, Saumya Chenniappan, Loganathan Chandrasekaran, K. Umanesan, R. B. S. Abdur Rahman Crescent Institute of Science and Technology Department of Commerce Chennai India SRM-IST Faculty of Management Studies Ghaziabad India The Northcap University Department of Management & Commerce Gurugram India Business Administration IBRI Oman K.S.R College of Engineering Department of Mechanical Engineering Tiruchengode India School of Computing Vel Tech Rangarajan Dr Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798331508456

AI is making labour-intensive HRM operations like hiring, performance review, and employee engagement more efficient and effective. The incorporation of AI technology in HRM could change several sectors. Through efficient applicant sourcing, screening, and selection, AI-driven solutions simplify hiring processes and ensure fair and accurate picks. Performance management using AI-powered solutions provides data-driven feedback and customized development plans to align individual progress with organizational goals. Predictive analytics improve employee engagement by personalizing experiences and meeting needs. The method focuses on preprocessing and model training. Data are cleansed, ordinal and categorical variables encoded, scaling characteristics and engineering features applied, and dimensional homogeneity assured before processing. For model training, the simple and robust one-class SVM technique is used. One-class SVM model outperformed others with 95.28%. This method worked best compared to GAN and GRU models. AI could improve HRM by improving decision-making and offering data-driven solutions. The findings show that the proposed model outperforms current options, providing the framework for HRM AI applications. © 2025 IEEE.

关键词： Human resource management

来源：评论

学校读者我要写书评

暂无评论

Medical Image Registration and Its Application in Retinal Images: A Review

arXiv

引用

arXiv 2024年

作者： Nie, Qiushi Zhang, Xiaoqing Hu, Yan Gong, Mingdao Liu, Jiang Research Institute of Trustworthy Autonomous Systems Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China Center for High Performance Computing Shenzhen Key Laboratory of Intelligent Bioinformatics Shenzhen institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China Singapore Eye Research Institute 169856 Singapore State Key Laboratory of Ophthalmology Optometry and Visual Science Eye Hospital Wenzhou Medical University Wenzhou325027 China

Medical image registration is vital for disease diagnosis and treatment with its ability to merge diverse information of images, which may be captured under different times, angles, or modalities. Although several surveys have reviewed the development of medical image registration, these surveys have not systematically summarized methodologies of existing medical image registration methods. To this end, we provide a comprehensive review of these methods from traditional and deep learning-based directions, aiming to help audiences understand the development of medical image registration quickly. In particular, we review recent advances in retinal image registration at the end of each section, which has not attracted much attention. Additionally, we also discuss the current challenges of retinal image registration and provide insights and prospects for future research. © 2024, CC BY-NC-SA.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Facial Emotion Recognition Using a Local Binary Pattern based Deep Learning

Facial Emotion Recognition Using a Local Binary Pattern base...

引用

computer, Communication and Control (IC4), International Conference on

作者： Iftikhar Aslam Tayubi Dilip N. Pawar Ajmeera Kiran Pundru Chandra Shaker Reddy Nipun Sharma D Chitra Faculty of Computing and Information Technology Rabigh King Abdulaziz University Jeddah Saudi Arabia Instrumentation Engineering Bharati Vidyapeeth College of Engineering Navi Mumbai Maharashrra India Department of Computer Science and Engineering MLR Institute of Technology Dundigal Hyderabad Telangana India School of Computer Science and Artificial Intelligence SR University Warangal Telangana India Electronics and Communication Engineering Presidency University Bangalore Karnataka India Master of Business Administration Panimalar Engineering College Chennai Tamil Nadu India

Facial-emotion-recognition(FER) is being conducted with the goals of analyzing the psychological characteristics of juvenile offenders and promoting the use of deep learning to the extraction of psychological features. Initially, we talk about how certain personality traits are linked to being good at reading facial expressions. To build a facial emotion identification model from this data, we add more convolutional layers to a CNN and combine it with other neural networks like VGGNet, AlexNet, and LeNet-5. Next, a Central-Local-Binary-Pattern(CLBP) method, which is optimized, is incorporated into the CNN to build a CNN-CLBP framework for FER. After face photos have been preprocessed and key parameters have been optimized, the algorithm is subjected to a validity study. The average detection rate for the CNN-CLBP is 88.16%, which is greater than the recognition rate for other approaches. In addition, image preparation and parameter tuning boost the recognition accuracy of this approach without resorting to poor-tting. In addition, the CNN-CLBP system accurately identifies 97% of pleased and startled expressions, but 22.54% of sad ones. The study's findings can be used as a starting point for further investigations into the mental health of teen offenders.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Phase Shift Signaling Reduction for IRS-Aided Internet of Things Networks by Exploiting Global Attention

Phase Shift Signaling Reduction for IRS-Aided Internet of Th...

引用

International Conference on Communication technology (ICCT)

作者： Xianhua Yu Dong Li Haotong Cao Zhi Lin Kang An Jiangzhou Wang Naofal AI-Dhahir School of Computer Science and Engineering Macau University of Science and Technology Macau China Department of Computing Hong Kong Polytechnic University Hong Kong SAR China College of Electronic Engineering National University of Defense Technology Hefei China Sixty-third Research Institute National University of Defense Technology Nanjing China School of Engineering University of Kent Canterbury U.K. Department of Electrical and Computer Engineering The University of Texas at Dallas Richardson USA

The Internet of Things (IoT) has recently received considerable attention due to its ability to enhance high-data rate multiple access for massive IoT devices. However, these devices sometimes suffer from coverage and performance degradation when they are geographically far from each other. Moreover, as IoT devices often operate in power-saving mode, they require energy-efficient transmissions. In response to these challenges, the Intelligent Reflecting Surface (IRS) has been proposed and attracted increasing attention in recent years. Most existing researches on IRS-aided IoT networks assume that the IRS possesses full knowledge of the quantized phase shift (QPS). However, in practice, obtaining the optimized QPS poses significant challenges for the IRS, mainly due to constraints on signaling storm. To address the issue of QPS signaling overhead, we propose a novel deep learning (DL) model known as the global attention phase shift compression network (GAPSCN). Further-more, we introduce a global attention mechanism within the GAPSCN to enhance reconstruction accuracy. This mechanism exploits the correlation between the channel and spatial dimensions, emphasizing a larger number of meaningful features than in existing attention-based works. Simulation results demonstrate the effectiveness of the global attention mechanism compared to conventional attention mechanisms, as well as the proposed GAPSCN, which achieves reliable reconstruction performance relative to existing state-of-the-art compression models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

scIAC: clustering scATAC-seq data based on Student’s t-distribution similarity imputation and denoising autoencoder

scIAC: clustering scATAC-seq data based on Student’s t-dist...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Wei Lan Jin Ye Xun Sun Xiaoshu Zhu Qingfeng Chen Yi Pan School of computer electronic and information and Guangxi Key Laboratory of Multimedia Communications and Network Technology Guangxi University Nanning China School of computer electronic and information Guangxi University Nanning China School of Computer Science and Engineering Yulin Normal University Yulin China School of Computer Science and Control Engineering Shenzhen Institute of Advanced Technology Shenzhen China

ISBN: (数字)9781665468190

ISBN: (纸本)9781665468206

Assay of single cell transposase-accessible chromatin with high-throughput sequencing (scATAC-seq) have enabled massively profiling of the chromatin accessibility landscape at the single-cell level. The essential step in analyzing scATAC-seq data is to cluster the cells into different clusters and utilize the clustering information in the subsequent downstream analysis. However, there are some challenges in the clustering analysis of scATAC-seq data. For example, scATAC-seq data are often high-dimensional and extremely sparse, as well as featuring high loss rate or noise. In this study, we proposed the scIAC to address these challenges of scATACseq data. In particular, scIAC combines the Student’s t-distribution similarity imputation and the denoising autoencoder based on the Zero-inflated Negative Binomial (ZINB) distribution. The Student’s t-distribution similarity imputation is used to solve the problem of high sparsity and high loss rate. The denoising autoencoder is employ to extract features which are useful for clustering and to reduce data noises. In addition, the self-training soft K-means and pairwise constraints are utilized in the clustering phase to enhance clustering performance. The experimental validation on several datasets shows that the proposed method performed better than other state-of-the-art methods. In conclusion, scIAC is an effective method to accurately cluster and identify cell types in scATAC-seq data.

关键词： Sequential analysis Runtime Clustering methods Noise reduction Neural networks Feature extraction Data models

来源：评论

学校读者我要写书评

暂无评论

Genetic Privacy Shields: A DNA Steganography Approach for Multi-Level Text Encryption : Unveiling the Future of Genetic Data Protection

Genetic Privacy Shields: A DNA Steganography Approach for Mu...

引用

Advances in Electrical, Electronics and Computational Intelligence (ICAEECI), International Conference on

作者： S Harshita C M Jayanth Adhitya P Geethika Naidu T Bashpika V S S S R Manikumar I R Oviya Divya S Rajender Kumar Department of Computer Science and Engineering (Artificial Intelligence) Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India Department of Chemistry School of Engineering Sciences in Chemistry Biotechnology and Health Division of Glycoscience KTH Royal Institute of Technology Alba Nova University Center Stockholm Sweden

In the current era genetic sequencing has emerged as an indispensable methodology for examining diverse DNA profiles across domains encompassing healthcare, agriculture, and forensic science. To enhance precision, a range of techniques, including high-throughput shotgun sequencing, have evolved over time. Recent strides in next-generation sequencing methodologies have facilitated the embedding of data within DNA using synthesized oligonucleotides. Notably, significant efforts have been dedicated to embedding extensive volumes of information within living organisms to safeguard intellectual property. When it comes to DNA steganography, traditional detection methods, exemplified by frequency analysis-based approaches, often overlook crucial signals and are susceptible to newly emerging steganography techniques. This study undertakes a comprehensive analysis of inherent allocations, distribution variance computation, and the classification of sequences as coding or non-coding. Our research endeavors to devise an advanced security strategy employing DNA steganography. Central to our proposition is the utilization of DNA steganography to forge a robust security framework. In this study, we introduce the DNA-Genetic Encryption (D-GET) mechanism to augment security. The D-GET technique involves the binarization of digital data followed by its conversion into DNA sequences. Subsequently, a sequence of operations, including reshaping, encryption, crossover, and mutation, is performed iteratively to heighten the robustness and unpredictability of the technique. The core processes of D-GET are iterated at least three times. Encrypted data is transmitted in either text or image file formats. Upon reception, the D-GET approach is employed to decode and restore the acquired data to its original form. A distinguishing aspect of our approach is the transformation of textual content into visual representations and vice versa, augmenting security measures. Multiple key sequences are

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Feature Selection Method Based on Rankability

SSRN

引用

SSRN 2024年

作者： Kong, Lingping Velasquez, Juan D. Perfilieva, Irina Pant, Millie Pan, Jeng-Shyang Snášel, Václav Department of Computer Science VSB-Technical University of Ostrava Ostrava Czech Republic Department of Industrial Engineering University of Chile Santiago Chile Santiago Chile Institute for Research and Applications of Fuzzy Modeling Centre of Excellence IT4Innovations division of The University of Ostrava Ostrava Czech Republic Department of Applied Mathematics and Scientific Computing Indian Institute of Technology Uttarakhand Roorkee247667 India School of Artificial Intelligence Nanjing University of Information Science and Technology China Instituto Sistemas Complejos de Ingeniería Santiago Chile Santiago Chile Faculty of Computer Science and Telecommunications Cracow University of Technology Kraków Poland Mehta Family School of Data Science and Artificial Intelligence Indian Institute of Technology Uttarakhand Roorkee247667 India College of Computer Science and Engineering Shandong University of Science and Technology China

Within the realm of data mining and machine learning, feature selection stands out as an essential technique for dimensionality reduction, presenting both popularity and complexity. Feature selection involves a nuanced trade-off that results in information loss. This distinction underscores the necessity for the development of lightweight, efficient, and practical methods capable of minimizing information loss while executing dimensional reduction. In this paper, we introduce a rankability-based feature selection method. The concept of rankability, proposed in 2019 and similar to the entropy concept, remains relatively unexplored. Our proposed method distinguishes itself by its lightweight complexity, eliminating the need for iterative *** evaluate the effectiveness of our approach, we conducted experiments on forty-one datasets and compared the results with four other algorithms using refined data with 10\%, 30\%, and 50\% feature dimension reduction. The findings reveal that our rankability-based feature selection method consistently outperforms the other four methods across a majority of datasets in terms of accuracy, precision, recall, and F1-macro performance. Specifically, the classification score exceeds 0.9 on accuracy for 50\% feature dimension reduction in twelve datasets, with nine datasets achieving scores over 0.9 in recall, F1-macro, and precision. Overall, our proposed feature selection method demonstrates promising performance. © 2024, The Authors. All rights reserved.

关键词： Feature Selection

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：