检索结果-内蒙古大学图书馆

2022 IEEE International Conference on Unmanned Systems, ICUS 2022

作者： Fu, Wei Shen, Xingfa Zhou, Wenhui Zhdanov, Andrei D. Geng, Chuntong Itmo Joint Institute Hangzhou Dianzi University Department of Computer Science Hangzhou China School of Computer Science and Technology Hangzhou Dianzi University Hangzhou China Itmo University Faculty of Software Engineering and Computer Systems St.Petersburg Russia

ISBN: (数字)9781665484565

ISBN: (纸本)9781665484565

Light field imaging is an important achievement in visual information exploration in recent years, which can capture more abundant visual information from the real world. However, most existing light field image quality assessment (LF-IQA) indicators rely heavily on feature extraction based on high complexity statistics in quality evaluation tasks, which is not comprehensive in future modern applications or power-limited devices. To solve this problem, the research puts forward a light field image quality evaluation method based on stereo vision. By introducing a brand-new light field image coding method and training the neural network, the purpose of image quality evaluation is finally achieved. Some experiments show that our model achieves good results in open source data sets. © 2022 IEEE.

关键词： Stereo vision

来源：评论

学校读者我要写书评

暂无评论

An Improved Boolean Load Matrix-Based Frequent Pattern Mining

An Improved Boolean Load Matrix-Based Frequent Pattern Minin...

引用

3rd International Conference on Intelligent Computing and Optimization, ICO 2020

作者： Roy, Shaishab Akhtar, Mohammad Nasim Rahman, Mostafijur Department of Computer Science and Engineering Dhaka University of Engineering and Technology Gazipur Dhaka Bangladesh Department of Software Engineering Daffodil International University Dhaka Bangladesh

ISBN: (纸本)9783030681531

Frequent Pattern Mining (FPM) has been playing an essential role in data mining research. In literature, many algorithms have proposed to discover interesting association patterns. However, frequent pattern mining in a large-scale dataset is a complex task because of a prohibitively large number of the smaller pattern need to be generated first to identify the extended pattern. The complexity in terms of computational time is a big concern. In this paper, we have proposed an updated novel FPM algorithm that uses a boolean matrix and then decomposed the matrix vertically. Here we have reduced the computational time by reducing a few steps and added itemset if and only if satisfy the condition instead of pruning after added into the candidate itemset. Our proposed algorithm has reduced the computational time at least two times on the generation of the boolean matrix (i.e. Q), frequent-1 matrix (i.e., F1) and frequent-1 itemset (i.e., L1), which has improved the efficiency of the algorithm. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Cardinality and Representation of Stone Relation Algebras

arXiv

引用

arXiv 2023年

作者： Furusawa, Hitoshi Guttmann, Walter Department of Science Kagoshima University Kagoshima Japan Department of Computer Science and Software Engineering University of Canterbury Christchurch New Zealand

Previous work has axiomatised the cardinality operation in relation algebras, which counts the number of edges of an unweighted graph. We generalise the cardinality axioms to Stone relation algebras, which model weighted graphs, and study the relationships between various axioms for cardinality. This results in simpler cardinality axioms also for relation algebras. We give sufficient conditions for the representability of Stone relation algebras and for Stone relation algebras to be relation algebras. Copyright © 2023, The Authors. All rights reserved.

关键词： Algebra

来源：评论

学校读者我要写书评

暂无评论

Enhancing Nurse Scheduling with User Preferences: Hybrid Genetic Algorithm and Variable Neighbourhood Search Approach

Enhancing Nurse Scheduling with User Preferences: Hybrid Gen...

引用

IEEE International Conference on Emerging & Sustainable Technologies for Power & ICT in a Developing Society (NIGERCON)

作者： Kehinde Segun Atoyebi Adebayo Abayomi-Alli Dauda Wisdom Daniel Morolake Oladayo Lawrence Orobosade Adewunmi Alabi Bayo Olushola Omoyiola Department of Software Engineering University of Bolton Bolton United Kingdom Department of Computer Science Federal University of Agriculture Abeokuta Nigeria Department of Computer Science Baze University Abuja Nigeria Department of Computer Science University of the People California United States

ISBN: (数字)9798331542559

ISBN: (纸本)9798331542566

The Nurse Scheduling Problem (NSP) assigns nurses to shifts while meeting constraints, making it an NP-hard problem. This study proposes GAV_NS 2 , a hybrid Genetic Algorithm (GA) and Variable Neighbourhood Search (VNS) model, to optimize scheduling while considering nurse preferences. Implemented in Java, GAV_NS 2 was evaluated using simulations and a dataset of 151 nurses from a Federal Medical Centre in Nigeria. Results showed allocation, duplication, clash, and multiple shift rates of 98.6%, 0.11%, 0.39%, and 0.2%, respectively. Simulations achieved 99.02%, 0%, 1.15%, and 0%, with computation times of 50.13ms−85.91ms. GAV_NS 2 outperforms manual and traditional GA-based scheduling. While it optimally distributes obligatory shifts, non-obligatory preferences like 3-day weekends were not fully met. The adoption of this system will enhance hospital efficiency, and nurse satisfaction, and provide historical data for future decision-making.

关键词： Schedules Processor scheduling Hospitals NP-hard problem Computational modeling Manuals Scheduling Resource management Standards Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Geometric Spanning Trees Minimizing the Wiener Index

arXiv

引用

arXiv 2023年

作者： Abu-Affash, A. Karim Carmi, Paz Luwisch, Ori Mitchell, Joseph S.B. Department of Software Engineering Shamoon College of Engineering Israel Computer Science Department Ben-Gurion University Israel Department of Applied Mathematics and Statistics Stony Brook University United States

The Wiener index of a network, introduced by the chemist Harry Wiener [30], is the sum of distances between all pairs of nodes in the network. This index, originally used in chemical graph representations of the non-hydrogen atoms of a molecule, is considered to be a fundamental and useful network descriptor. We study the problem of constructing geometric networks on point sets in Euclidean space that minimize the Wiener index: given a set P of n points in d, the goal is to construct a network, spanning P and satisfying certain constraints, that minimizes the Wiener index among the allowable class of spanning networks. In this work, we focus mainly on spanning networks that are trees and we focus on problems in the plane (d = 2). We show that any spanning tree that minimizes the Wiener index has non-crossing edges in the plane. Then, we use this fact to devise an O(n4)-time algorithm that constructs a spanning tree of minimum Wiener index for points in convex position. We also prove that the problem of computing a spanning tree on P whose Wiener index is at most W, while having total (Euclidean) weight at most B, is NP-hard. Computing a tree that minimizes the Wiener index has been studied in the area of communication networks, where it is known as the optimum communication spanning tree problem. © 2023, CC0.

关键词： Atoms

来源：评论

学校读者我要写书评

暂无评论

Anomaly-based network intrusion detection using Transfer learning

Anomaly-based network intrusion detection using Transfer lea...

引用

Multidisciplinary engineering and Applied Science (ICMEAS), International Conference on

作者： Similoluwa Ola-Obaado Muhammad Aliyu Suleiman Computer Science Department Nile University of Nigeria Abuja Nigeria Software Engineering Department Nile University of Nigeria Abuja Nigeria

The rapid development of computer networks and network applications, along with the present global increase in hacking and computer network attacks, has increased the demand for stronger intrusion detection and prevention solutions. The intrusion detection system (IDS) is crucial in detecting irregularities and attacks on the network, which has expanded in size and pervasiveness. In this paper, we develop an intrusion detection system based on deep learning and leverage a recent security dataset, CSE-CIC-IDS2018, to implement a more realistic IDS. We proposed an approach for network intrusion detection using Transfer learning to address both the binary and multiclass classification of network attacks. Network features from the dataset are transformed into grayscale images, the images are used as input to the ResNet50 deep learning model. The dataset is imbalanced, therefore, to increase the generalization of model, the imbalance ratio is reduced by using a synthetic data generation model called Synthetic Minority Oversampling Technique (SMOTE). Experimental results show that our model achieves good performance for both binary and multiclass classification with accuracy of 92 percent for each case. The proposed approach provides a new method for intrusion detection using transfer learning and SMOTE for correcting data imbalance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

STEIN LATENT OPTIMIZATION FOR GENERATIVE ADVERSARIAL NETWORKS 10

STEIN LATENT OPTIMIZATION FOR GENERATIVE ADVERSARIAL NETWORK...

引用

10th International Conference on Learning Representations, ICLR 2022

作者： Hwang, Uiwon Kim, Heeseung Jung, Dahuin Jang, Hyemi Lee, Hyungyu Yoon, Sungroh Department of Electrical and Computer Engineering AIIS ASRI INMC ISRC NSI and Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul08826 Korea Republic of

Generative adversarial networks (GANs) with clustered latent spaces can perform conditional generation in a completely unsupervised manner. In the real world, the salient attributes of unlabeled data can be imbalanced. However, most of existing unsupervised conditional GANs cannot cluster attributes of these data in their latent spaces properly because they assume uniform distributions of the attributes. To address this problem, we theoretically derive Stein latent optimization that provides reparameterizable gradient estimations of the latent distribution parameters assuming a Gaussian mixture prior in a continuous latent space. Structurally, we introduce an encoder network and novel unsupervised conditional contrastive loss to ensure that data generated from a single mixture component represent a single attribute. We confirm that the proposed method, named Stein Latent Optimization for GANs (SLOGAN), successfully learns balanced or imbalanced attributes and achieves state-of-the-art unsupervised conditional generation performance even in the absence of attribute information (e.g., the imbalance ratio). Moreover, we demonstrate that the attributes to be learned can be manipulated using a small amount of probe data. © 2022 ICLR 2022 - 10th International Conference on Learning Representationss. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Digital Technology in Health Education Trend Mapping through Bibliometrics Analysis 4

Digital Technology in Health Education Trend Mapping through...

引用

4th International Conference on Informatics, Multimedia, Cyber and Information System, ICIMCIS 2022

作者： Maulana, Fairuz Iqbal Lestari, Dian Widartha, Vandha Pradwiyasma Haidar, Nirwana Dirgantara, Wahyu School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia Airlangga University Faculty of Medicine Surabaya60132 Indonesia Telkom University Information System of Industrial Engineering Faculty Bandung Indonesia University of Madura Informatics Engineering Study Program Pamekasan Indonesia University of Merdeka Malang Department of Electrical Engineering Malang Indonesia

ISBN: (纸本)9781665473279

This study examines the mapping of research data on digital technology in the field of health education using bibliometric analysis method. Data was collected by identifying keywords in the Scopus database and sorting them out to sort the studies from the last 10 years (2012-2021). Through this step, a total of 1482 documents were obtained (articles, journals, proceedings, books, and others). The data is then processed using the VOSViewer instrument to obtain a visualization of the mapping analysis. This study also analyzes the network types of authors and co-authors through the VOSViewer instrument. The result of this study indicates that the most document types published within ten years are Articles (66.5%), Review (22.9%), Conference Paper (4.2%), and others. The most studied subjects are Medicine (55.7%), Nursing (9.0%), Health Professions (8.2%), Social Sciences (7.8%), engineering (3.9%), computer Science (2.6%), Environmental Science (2.6%), Biochemistry-Genetics and Molecular Biology (2.2%), Psychology (1.6%), and Dentistry (1.3%). This study offers a written communication process and the nature and direction of developing descriptive means of counting and analyzing the various phases of communication as well as recognizing the authorship and direction of its symptoms in documents on the subject of digital technology in the health sector. © 2022 IEEE.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Saccadic Detection in Virtual Gaming for Dyslexia Classification

Saccadic Detection in Virtual Gaming for Dyslexia Classifica...

引用

IEEE International Symposium on Biomedical Imaging

作者： Yih-Choung Yu Haki Shyntassov Padmanabh Kaushik Lisa Gabel Department of Electrical and Computer Engineering Lafayette College Easton PA USA Department of Psychology and the Neuroscience Program Lafayette College Easton PA USA

ISBN: (数字)9798350313338

ISBN: (纸本)9798350313345

Dyslexia (aka reading disability) is the most common cause of learning disabilities. It affects children across language orthographies, despite adequate intelligence and educational opportunity. Studies have shown that identifying children with dyslexia at young age is crucial to provide effective intervention to improve learning outcomes. Recently we demonstrated that children with reading disability exhibit impaired performance on a virtual maze learning task across language orthographies. Using a machine learning algorithm, we have achieved a classification accuracy up to 80%. This paper presents an algorithm, including image segmentation, synchronization of image and text data, saccade detection, and event alignment, using the eye-gazing data recorded from an eye tracker during maze-solving tasks. The saccadic events detected by this algorithm showed good correlation with the incorrect decisions participants made during maze-solving, which could be an additional variable to be used in the machine learning algorithm to enhance the accuracy for dyslexia classification.

关键词： Image segmentation Machine learning algorithms Correlation Accuracy Signal processing algorithms Predictive models Dyslexia

来源：评论

学校读者我要写书评

暂无评论

Improving Traffic Surveillance: Deep Learning Approach for Road Anomaly Detection in Videos

Improving Traffic Surveillance: Deep Learning Approach for R...

引用

Computing and Machine Intelligence (ICMI), International Conference on

作者： Sarfaraz Natha Muhammad Arif Syed Shahryar Jamil Fareed Ahmed Jokhio Muslim Jameel Syed Department of Software Engineering Sir Syed University of Engineering and Technology Karachi Pakistan Instituto Politécnico Nacional (IPN) Mexico MAJU Karachi Pakistan Department of Computer Systems Engineering Quaid-e-Awam University of Engineering and Technology Nawabshah Pakistan Department of Enterprise and Technology Atlantic Technological University Galway Ireland

ISBN: (数字)9798350372977

ISBN: (纸本)9798350372984

In recent years, Closed-circuit Television (CCTV) cameras have been playing a vital role in the surveillance of both public and private areas. The primary objective of surveillance is to monitor human behavior and road conditions. In the real-world situation, detecting, and recognizing abnormal activities poses significant challenges due to the densely crowded environment and the complex nature of transportation systems. These factors make it difficult to automatically identify various anomalies that occur while traveling, leading to emergencies, and endangering human life and property. This study introduces an automatic detection framework for recognizing road anomalies such as accidents, fighting, car fires, and armed snatching (gunpoint) in road surveillance videos. After reviewing the literature, the review directs that convolutional neural networks (CNNs) are a specialized deep learning approach well suited for image and video analysis. The proposed methodology combines the pretrained CNN models with Data Augmentation (DA) techniques to fine-tune hyperparameters such as learning rate and momentum that enhance the model learning accuracy and performance for recognizing road anomalies. Furthermore, it introduced a rolling prediction algorithm to solve the flickering problem during testing and created a new road anomaly dataset (RAD) as a benchmark consisting of road surveillance videos and images. Our proposed model combined with the InceptionV3 pre-trained model achieved a best accuracy is $98.81\%$ for detection and classification as compared to other deep learning models.

关键词： Deep learning Accuracy Roads Surveillance Computational modeling Prediction algorithms Data augmentation

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：