检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Hirano, Manabu Kobayashi, Ryotaro Department of Information and Computer Engineering National Institute of Technology Toyota College Toyota Japan Faculty of Informatics Kogakuin University Tokyo Japan

Since modern anti-virus software mainly depends on a signature-based static analysis, they are not suitable for coping with the rapid increase in malware variants. Moreover, even worse, many vulnerabilities of operating systems enable attackers to evade such protection mechanisms. We, therefore, developed a thin and lightweight live-forensic hypervisor to create an additional protection layer under a conventional protection layer of operating systems with supporting ransomware detection using dynamic behavioral features. The developed live-forensic hypervisor collects low-level memory access patterns instead of high-level information such as process IDs and API calls that modern Virtual Machine Introspection techniques have employed. We then created the low-level memory access patterns dataset of three ransomware samples, one wiper malware sample, and four benign applications. We confirmed that our best machine learning classifier using only low-level memory access patterns achieved an F1 score of 0.95 in detecting ransomware and wiper malware. © 2022, CC BY-NC-ND.

关键词： Malware

来源：评论

学校读者我要写书评

暂无评论

Development of Visual Dashboard for River Monitoring System 8

Development of Visual Dashboard for River Monitoring System

引用

8th IEEE International Conference on Smart Instrumentation, Measurement and Applications, ICSIMA 2022

作者： Ahmad, Yasser Asrul Gunawan, Teddy Surya Munir, Muhd Hisyamuddin Mohd Rasidi Al Yusoff, Nelidya Md. Kartiwi, Mira Mansor, Hasmah International Islamic University Malaysia Electrical and Computer Engineering Dept Kuala Lumpur53100 Malaysia Razak Faculty of Tech. and Informatics Universiti Teknologi Malaysia Kuala Lumpur54100 Malaysia Information Systems Department International Islamic University Malaysia Kuala Lumpur53100 Malaysia

ISBN: (数字)9781665488006

ISBN: (纸本)9781665488006

Monitoring a tributary's water depth and velocity can provide a wealth of information for ecological systems. Typically, tributaries are located deep within the jungle, and manual measurement is the norm. The research aims to develop a real-time remote monitoring system for measuring water depth and velocity. The system uses ultrasonic and water flow sensors to measure velocity and river depth. The data will be transmitted to the back-end software, including Arduino IDE and Node-RED, for data collection. The data is then stored in the cloud database InfluxDB for future use. The data can be set to be automatically deleted every 1 hour, 1 day, 1 month, or at other time intervals. The Grafana platform can produce an interactive Graphical User Interface (GUI), and the administrator can modify the visual dashboard using either their program code or existing features. It can then be made available to the general public as an observer for the online visual dashboard via the Uniform Resource Locator (URL). © 2022 IEEE.

关键词： Remote control

来源：评论

学校读者我要写书评

暂无评论

Generalizable deep clustering based on Bi-LSTM with applications to sepsis and acute kidney disease populations

Generalizable deep clustering based on Bi-LSTM with applicat...

引用

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Tan, Yongsen Huang, Jiahui Zhuang, Jinhu Liu, Yong Huang, Haofan Yu, Xiaxia Wang, Fusheng Shenzhen University School of Biomedical Engineering Health Science Center Shenzhen China Shenzhen Hospital Southern Medical University Department of Intensive Care Unit Shenzhen China Stony Brook University Department of Biomedical Informatics Department of Computer Science Stony BrookNY United States

ISBN: (纸本)9781665468190

Despite the abundance of subphenotype clustering studies on sepsis and acute kidney injury (AKI), few models consider the real-time information of clinical features. The lack of supervision may lead to patient subgroups being derived as clusters without the stratification of patients based on the outcome of interests. The sensitivity of the dimension in clustering methods is generally ignored, so clusters lack robustness. In this study, we propose an ensembled outcome-driven bidirectional long short-term memory autoencoder (BiLSTM-AE) architecture with high robustness and transferability to identify subphenotypes. BiLSTM-AE learns the advanced representation of the time-series clinical features by co-training the encoder and a weak predictor to achieve the risk-stratified clustering of patients. Clusters of a variety of dimensions are ensembled to combine global and local information. Four different datasets from three public datasets, MIMIC-III-AKI, MIMIC-IV-sepsis, eICU-AKI, and eICU-sepsis, were used to assess the method's effectiveness in clustering and prediction. Compared to baseline approaches including latent class analysis (LCA), subgroups generated by BiLSTMAE exhibited the highest mortality risk ratios between subgroups: the mortality for subphenotypes 1, 2, and 3 of BiLSTM and LCA was 6.91%, 17.53%, and 75.56% vs. 13.2%, 14.4%, and 19.7% for MIMIC-III-AKI. The prediction metric area under the receiver operating characteristic curve was 0.86 for MIMIC-IIIAKI, 0.91 for eICU-AKI, 0. SS for MIMIC-IV-sepsis, and 0. S9 for eICU-sepsis. Additionally, clinical evaluation of BiLSTM-AE generated subgroups revealed more meaningful distributions of member characteristics across subgroups. Thus, the method is an effective means to consider the real-time information of clinical features. © 2022 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

Evaluating shallow capsule networks on complex images

引用

International Journal of Information Technology (Singapore) 2021年第3期13卷 1047-1057页

作者： Mensah, Patrick Kwabena Weyori, Benjamin Asubam Ayidzoe, Mighty Abra Department of Computer Science and Informatics University of Energy and Natural Resources P.O. Box 214 Sunyani Ghana School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China

Useful real-life images meant for computer vision applications appear in complex forms with varied backgrounds. Convolutional neural networks with their invariance outperforms capsule networks (CapsNets) on such images. Recent research to improve the accuracy of CapsNets on complex images such as CIFAR10 involves the increase in depth of the networks. However, smaller architectures with efficient feature extractors can perform comparatively well with additional advantages of having less computational cost, reduced risk of overfitting, increased suitability for deployment on devices with smaller memories, and enhanced feasibility to perform distributed training across servers and in the cloud. This paper, therefore, proposes a shallow CapsNet based on dynamic routing with a custom squashing function and normalizer to gain all of these advantages. The model is evaluated on three publicly available datasets;fashion-MNIST, CIFAR-10, and tomato datasets. Experimental results show that the proposed model outperforms the original CapsNet by generating fewer parameters and performing comparably well in terms of accuracy with some state-of-the-art multi-lane and ensemble capsule network models. © 2021, Bharati Vidyapeeth's Institute of computer Applications and Management.

关键词： Capsule network Complex images Convolutional neural networks Dynamic routing Local binary pattern Plant diseases

来源：评论

学校读者我要写书评

暂无评论

Observing Generator Performance by Finite Element Analysis Considering Coil Numbers

Observing Generator Performance by Finite Element Analysis C...

引用

Technology and Policy in Energy and Electric Power (ICT-PEP), International Conference on

作者： Muhammad Afnan Habibi Mochamad Farhan Ali Irfani Langlang Gumilar Arya Kusumawardana Aripriharta Angger Baskoro Study Program of Power Plant Engineering Technology Universitas Negeri Malang Malang Indonesia Department of Electrical Engineering and Informatics Universitas Negeri Malang Malang Indonesia Dept. Electrical Engineering and Computer Sciences National Yang Ming Chiao Tung University Hsinchu Taiwan

This paper conducts a comprehensive analysis of electrical generator performance using Finite Element Analysis (FEA), with a specific emphasis on the role of coil numbers in influencing generator efficiency and functionality. In the context of modern energy systems, where efficient power generation is paramount, this research aims to elucidate the relationship between the number of coils within a generator and its overall performance, including power output and electromagnetic behavior. Through systematic FEA simulations that vary coil numbers while keeping other parameters constant, this study provides valuable insights into the trade-offs associated with increased coil numbers and enhanced efficiency. These findings have significant implications for optimizing generator designs across various applications, from renewable energy systems to industrial power generation, ultimately advancing our understanding of generator dynamics and contributing to more sustainable and efficient power generation technologies.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Construction of Influenza Early Warning Model Based on Combinatorial Judgment Classifier:A Case Study of Seasonal Influenza in Hong Kong

引用

Current Medical Science 2022年第1期42卷 226-236页

作者： Zi-xiao WANG James NTAMBARA Yan LU Wei DAI Rui-jun MENG Dan-min QIAN Department of Medical Informatics School of MedicineNantong UniversityNantong 226001China Department of Computer Science College of Engineering and Computing SciencesNew York Institute of TechnologyNew York 10023USA Department of Computer Science College of Overseas EducationNanjing University of Posts and TelecommunicationsNanjing 210023China Department of Epidemiology School of Public HealthNantong UniversityNantong 226019China Artificial Intelligence Laboratory Center De Montfort University of LeicesterLeicester LE1 9BHUnited Kingdom

Objective:The annual influenza epidemic is a heavy burden on the health care system,and has increasingly become a major public health problem in some areas,such as Hong Kong(China).Therefore,based on a variety of machine learning methods,and considering the seasonal influenza in Hong Kong,the study aims to establish a Combinatorial Judgment Classifier(CJC)model to classify the epidemic trend and improve the accuracy of influenza epidemic early warning.

关键词： influenza prediction data-driven Support Vector Machine Discriminant Analysis Ensemble Classifier

来源：评论

学校读者我要写书评

暂无评论

Classification of Gastric Lesions Using Gabor Block Local Binary Patterns

引用

computer Systems Science & engineering 2023年第9期46卷 4007-4022页

作者： Muhammad Tahir Farhan Riaz Imran Usman Mohamed Ibrahim Habib College of Computing and Informatics Saudi Electronic UniversityRiyadh11673Saudi Arabia College of Electrical and Mechanical Engineering National University of Sciences and TechnologyIslamabadPakistan Department of Computer Science National University of Sciences and TechnologyBalochistan CampusQuettaPakistan

The identification of cancer tissues in Gastroenterology imaging poses novel challenges to the computer vision community in designing generic decision support *** generic nature demands the image descriptors to be invariant to illumination gradients,scaling,homogeneous illumination,and *** this article,we devise a novel feature extraction methodology,which explores the effectiveness of Gabor filters coupled with Block Local Binary Patterns in designing such *** effectively exploit the illumination invariance properties of Block Local Binary Patterns and the inherent capability of convolutional neural networks to construct novel rotation,scale and illumination invariant *** invariance characteristics of the proposed Gabor Block Local Binary Patterns(GBLBP)are demonstrated using a publicly available texture *** use the proposed feature extraction methodology to extract texture features from Chromoendoscopy(CH)images for the classification of cancer *** proposed feature set is later used in conjuncture with convolutional neural networks to classify the CH *** proposed convolutional neural network is a shallow network comprising of fewer parameters in contrast to other state-of-the-art networks exhibiting millions of parameters required for effective *** obtained results reveal that the proposed GBLBP performs favorably to several other state-of-the-art methods including both hand crafted and convolutional neural networks-based features.

关键词： Texture analysis Gabor filters gastroenterology imaging convolutional neural networks block local binary patterns

来源：评论

学校读者我要写书评

暂无评论

Triple-band Modified Printed Inverted-F Antenna Design for WI-FI-7 Applications

Triple-band Modified Printed Inverted-F Antenna Design for W...

引用

European Conference on Antennas and Propagation, EuCAP

作者： Lazaros A. Iliadis Vasileios P. Rekkas Achilles D. Boursianis Panagiotis Sarigiannidis George K. Karagiannidis Christos Christodoulou Sotirios K. Goudos ELEDIA@AUTH School of Physics Aristotle University of Thessaloniki Thessaloniki Greece Department of Informatics and Telecommunications Engineering University of Western Macedonia Kozani Greece Department of Electrical and Computer Engineering Aristotle University of Thessaloniki Thessaloniki Greece Department of Engineering and Computing The University of New Mexico USA

WI-FI-6/6E is now commercialized and the WI-FI community is currently developing the IEEE 802.11be standard, namely WI-FI-7, which will offer enhanced throughput and higher data rate than its predecessors. In this article, a compact triple-band printed inverted-F (IF) antenna operating at 2.4 GHz, 5 GHz, and 6 GHz frequency bands is designed for WI-FI-7 applications. We design a novel antenna structure that is well-suited for triple-band operation. The core idea is to use a stripline as a feeder that also couples two modified IF designs. A nature-inspired optimization method, namely the artificial hummingbird algorithm (AHA), is used to achieve an optimal design solution for the triple-band IF antenna. Computed results demonstrate that the proposed antenna achieves satisfactory results regarding the reflection coefficient and the realized gain in all the frequency bands of interest.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Latent Multi-Relation Reasoning for GAN-Prior based Image Super-Resolution

arXiv

引用

arXiv 2022年

作者： Zhang, Jiahui Zhan, Fangneng Yu, Yingchen Wu, Rongliang Zhang, Xiaoqin Lu, Shijian The School of Computer Science and Engineering Nanyang Technological University Singapore Singapore Max Planck Institute for Informatics Germany The Wenzhou University China

Recently, single image super-resolution (SR) under large scaling factors has witnessed impressive progress by introducing pre-trained generative adversarial networks (GANs) as priors. However, most GAN-Priors based SR methods are constrained by an attribute disentanglement problem in inverted latent codes which directly leads to mismatches of visual attributes in the generator layers and further degraded reconstruction. In addition, stochastic noises fed to the generator are employed for unconditional detail generation, which tends to produce unfaithful details that compromise the fidelity of the generated SR image. We design LAREN, a LAtent multiRelation rEasoNing technique that achieves superb large-factor SR through graph-based multi-relation reasoning in latent space. LAREN consists of two innovative designs. The first is graph-based disentanglement that constructs a superior disentangled latent space via hierarchical multi-relation reasoning. The second is graph-based code generation that produces image-specific codes progressively via recursive relation reasoning which enables prior GANs to generate desirable image details. Extensive experiments show that LAREN achieves superior large-factor image SR and outperforms the state-of-the-art consistently across multiple benchmarks. Copyright © 2022, The Authors. 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

Comparison of Model in Predicting Customer Churn Based on Users' habits on E-Commerce

Comparison of Model in Predicting Customer Churn Based on Us...

引用

International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)

作者： Arif Ridho Lubis Santi Prayudani Julham Okvi Nugroho Yuyun Yusnida Lase Muharman Lubis Department of Computer Engineering and Informatics Politeknik Negeri Medan Medan Indonesia SMA Muhammadiyah 2 Medan Indonesia School of Industrial Engineering Telkom University Bandung Indonesia

Customer churn is a situation that receives extensive analysis using a variety of techniques from data mining or machine learning. Data mining techniques may be used to anticipate customer churn. A data mining algorithm was used in this study to forecast client turnover. Logistic Regression and gradient boosting models were employed as one of the data mining techniques for implementing customer churn forecasts. The gradient boosting model could be said to perform better in predicting customer churn when compared to the logistic regression model, which produced accuracy training 87% and testing 88%. The results showed that the gradient boosting model was able to carry out the training and testing process with a training accuracy of 93% and a testing accuracy of 91%.

关键词： Training Seminars Machine learning algorithms Predictive models Boosting Prediction algorithms Data mining

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：