检索结果-内蒙古大学图书馆

Cell quantization tool for anterior chamber OCT images

Transactions of the Korean Institute of Electrical Engineers 2020年第7期69卷 1073-1080页

作者： Lee, Yeongseop Kang, Taeseen Han, Yongseop Kim, Jinhyun Kim, Kyong Hoon Lee, Seongjin Dept. of Aerospace and Software Engineering Gyeongsang National University Korea Republic of Dept. of Informatics Gyeongsang National University Korea Republic of Dept of Ophthalmology Gyeongsang National University Changwon Hospital Changwon Korea Republic of Dept of Ophthalmology College of Medicine Gyeongsang National University Jinju Korea Republic of Dept of Information and Communication Engineering Gyeongsang University Korea Republic of School of Computer Science and Engineering Kyungpook National University Korea Republic of

In general, ophthalmologists visually grade the state of a patient by counting the cells within the anterior chamber OCT image. The manual cell counting method is highly inaccurate and spends a lot of time to determine the progress of the patient. In this work, we develop a new tool to count cells in anterior chamber OCT images to aid doctors in analyzing the state of patients. We exploit image processing to remove noises from images, segment the anterior chamber, and quantize the cells in OCT images. We also provide statistics to aid the doctors in determining the progress of the patients. © Korean Institute of Electrical Engineers

关键词： Cells

来源：评论

学校读者我要写书评

暂无评论

Accelerating an On-Line Approximation Mining for Large Closed Itemsets

Accelerating an On-Line Approximation Mining for Large Close...

引用

IEEE International Conference on Big Data

作者： Koji Iwanuma Takumi Nishina Yoshitaka Yamamoto Dept. of Computer Science & Eng. University of Yamanashi Kofu-shi Japan Dept. of Informatics Shizuoka University Hamamatsu-shi Japan

ISBN: (数字)9781728108582

ISBN: (纸本)9781728108599

In this paper, we study acceleration methods for on-line stream mining of all frequent closed itemsets under a minimal-size restriction. The algorithm LC-K-CloStream [3] can perform an 6-approximation on-line mining based on incremental intersection of transactions. We first integrate LC-K-CloStream with an extended FP-tree with skipping in order to effectively compress a huge number of mined closed itemsets. Next, we introduce novel pruning methods for rejecting a hopeless intersection computation by using look-ahead maximal-size estimation. We show, through experimental evaluations, that the proposed methods have a great performance for mining a large set of closed itemsets in dense data sets.

关键词： Itemsets Acceleration Estimation Data mining Approximation algorithms Big Data computer science

来源：评论

学校读者我要写书评

暂无评论

MRI Image Segmentation using Morphological Enhancement and Noise Removal based on Fuzzy C-means 5

MRI Image Segmentation using Morphological Enhancement and N...

引用

5th International Conference on Information Technology, computer and Electrical Engineering, ICITACEE 2018

作者： Setyawan, Robert Almahfud, Mustofa Alisahid Sari, Christy Atika Setiadi, De Rosal Ignatius Moses Rachmawanto, Eko Hari Dept. Informatics Engineering of Computer Science Faculty Dian Nuswantoro University Semarang Indonesia

ISBN: (纸本)9781538655276

Fuzzy C-means (FCM) is one of the image segmentation algorithms that has been widely used and proven to have good performance in image segmentation. This study aims to examine the effect of pre-processing stages on the FCM algorithm to segment the MRI image especially to detect brain tumors. This research proposed a pre-processing method with opening and closing morphology technique, noise removal with Weiner filter and contrast enhancement. The morphological method is used to connect the pixels adjacent. The morphological method used is opening and closing, because it can minimize the noise that is in the image by connecting the pixels are adjacent. Furthermore, noise removal and contrast enhancement are used to complete the morphological stage to produce MRI images that have less noise but are detailed. Based on the experimental results proved that the combination of pre-processing methods can improve the results of segmentation so that the tumor objects can be detected more accurately, where the accuracy is 73.585%. © 2018 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Pathogenic bacteria genus classification using support vector machine

Pathogenic bacteria genus classification using support vecto...

引用

2018 International Seminar on Research of Information Technology and Intelligent Systems, ISRITI 2018

作者： Rahmayuna, Novita Rahardwika, Dewangga Satriya Sari, Christy Atika Setiadi, De Rosal Ignatius Moses Rachmawanto, Eko Hari Dept. Informatics Engineering Faculty of Computer Science Dian Nuswantoro University Semarang Indonesia

ISBN: (纸本)9781538674222

This research was conducted to classify the pathogen bacteria at the level of the genus of the bacterial image derived from the optical sensor system. The study focused on exploring bacterial patterns and classifying four popular bacteria. The first step is to improve the image quality using the Contrast Limited Adaptive Histogram Equalization (CLAHE) method on the object image so that it can generate the object in the clearer image. The second step is to extract the value of features to be trained using the Support Vector Machine (SVM) method, which includes texture analysis and Zernike Moment Invariant (ZMI). The next stage, selected features will be trained and classified using two kinds of SVM kernels i.e. linear and Radial Basis Function (RBF). Experiments were performed on four pathogenic bacteria such as Escherichia, Listeria, Salmonella, and Staphylococcus. Based on the results of classification experiments using SVM with RBF kernel is superior to Linear kernel that is obtained 90,33% accuracy. © 2018 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Non-blind RGB image watermarking technique using 2-level discrete wavelet transform and singular value decomposition 1

Non-blind RGB image watermarking technique using 2-level dis...

引用

1st International Conference on Information and Communications Technology, ICOIACT 2018

作者： Mekarsari, Yudit Arum Setiadi, De Rosal Ignatius Moses Sari, Christy Atika Rachmawanto, Eko Hari Muljono Dept. of Informatics Engineering Faculty of Computer Science Dian Nuswantoro University Semarang Indonesia

ISBN: (纸本)9781538609545

The main problem in using various watermarking methods to secure digital images is how to optimize the trade-off between robustness watermarked image against the effect of distortion and imperceptibility on watermark insertion. This research proposes a watermark insertion method to protect copyright in true color (RGB) images by combining Discrete Wavelet Transform (DWT) and Singular Value Decomposition (SVD) algorithms. DWT process will be done as much as 2 levels then selected subband LL2 to inserted watermark by Singular Value Decomposition (SVD) method. Measuring tool in this research using MSE, PSNR, SSI M for imperceptibility and NC quality measurement for robustness measurement. The results show that the proposed scheme can optimize the trade-off between imperceptibility and robustness. Some attacks are used such as Gaussian noise, salt & pepper noise, crop, blur and rotate for watermarked image resilience. The PSNR and SSIM values produced from this method are fairly stable values above 40 dB for PSNR and above 0.99 for SSIM. While the average value of NC resulting from this method is 1. © 2018 IEEE.

关键词： Image watermarking

来源：评论

学校读者我要写书评

暂无评论

Simple and secure image steganography using LSB and triple XOR operation on MSB 1

Simple and secure image steganography using LSB and triple X...

引用

1st International Conference on Information and Communications Technology, ICOIACT 2018

作者： Astuti, Yani Parti Setiadi, De Rosal Ignatius Moses Rachmawanto, Eko Hari Sari, Christy Atika Dept. of Informatics Engineering Faculty of Computer Science Dian Nuswantoro University Semarang Indonesia

ISBN: (纸本)9781538609545

Least Significant Bit (LSB) is a very popular method in the spatial domain of steganographic images. This method is widely used and continues to be developed to date, because of its advantages in steganographic image quality. However, the traditional LSB method is very simple and predictable. It needs a way to improve the security of hidden messages in this way. This research proposes a simple and safe way to hide messages in LSB techniques. Three times the XOR operation is done to encrypt the message before it is embedded on the LSB. To facilitate the process of encryption and decryption of messages, three MSB bits are used as keys in XOR operations. The results of this study prove that this method provides security to messages with very simple operation. The imperceptibility quality of the stego image is also excellent with a PSNR value above 50 dB. © 2018 IEEE.

关键词： Steganography

来源：评论

学校读者我要写书评

暂无评论

Goal-Aware RSS for Complex Scenarios via Program Logic

arXiv

引用

arXiv 2022年

作者： Hasuo, Ichiro Eberhart, Clovis Haydon, James Dubut, Jérémy Bohrer, Rose Kobayashi, Tsutomu Pruekprasert, Sasinee Zhang, Xiao-Yi Pallas, Erik André Yamada, Akihisa Suenaga, Kohei Ishikawa, Fuyuki Kamijo, Kenji Shinya, Yoshiyuki Suetomi, Takamasa Tokyo101-8430 Japan Dept. Computer Science Worcester Polytechnic Institute 100 Institute Road WorcesterMA01609-2280 United States Inst. Software & Systems Engineering University of Augsburg Universitätstraße 6a AugsburgD-86135 Germany Cyber Physical Security Research Center AIST Aomi 2-4-7 Tokyo135-0064 Japan Graduate School of Informatics Kyoto University Kyoto606-8501 Japan Mazda Motor Corporation Fuchu730-8670 Japan SOKENDAI The Graduate University for Advanced Studies Japan Tokyo Japan

We introduce a goal-aware extension of responsibility-sensitive safety (RSS), a recent methodology for rule-based safety guarantee for automated driving systems (ADS). Making RSS rules guarantee goal achievement—in addition to collision avoidance as in the original RSS—requires complex planning over long sequences of manoeuvres. To deal with the complexity, we introduce a compositional reasoning framework based on program logic, in which one can systematically develop RSS rules for smaller subscenarios and combine them to obtain RSS rules for bigger scenarios. As the basis of the framework, we introduce a program logic dFHL that accommodates continuous dynamics and safety conditions. Our framework presents a dFHL-based workflow for deriving goal-aware RSS rules;we discuss its software support, too. We conducted experimental evaluation using RSS rules in a safety architecture. Its results show that goal-aware RSS is indeed effective in realising both collision avoidance and goal achievement. © 2022, CC BY-NC-ND.

关键词： computer circuits

来源：评论

学校读者我要写书评

暂无评论

Heaps don’t lie: Countering unsoundness with heap snapshots

arXiv

引用

arXiv 2019年

作者： Grech, Neville Fourtounis, George Francalanza, Adrian Smaragdakis, Yannis Dept. of Informatics University of Athens Ilisia Athens15784 Greece University of Malta Malta Dept. of Computer Science University of Malta Msida Malta

Static analyses aspire to explore all possible executions in order to achieve soundness. Yet, in practice, they fail to capture common dynamic behavior. Enhancing static analyses with dynamic information is a common pattern, with tools such as Tamiflex. Past approaches, however, miss significant portions of dynamic behavior, due to native code, unsupported features (e.g., invokedynamic or lambdas in Java), and more. We present techniques that substantially counteract the unsoundness of a static analysis, with virtually no intrusion to the analysis logic. Our approach is reified in the HeapDL toolchain and consists in taking whole-heap snapshots during program execution, that are further enriched to capture significant aspects of dynamic behavior, regardless of the causes of such behavior. The snapshots are then used as extra inputs to the static analysis. The approach exhibits both portability and significantly increased coverage. Heap information under one set of dynamic inputs allows a static analysis to cover many more behaviors under other inputs. A HeapDL-enhanced static analysis of the DaCapo benchmarks computes 99.5% (median) of the call-graph edges of unseen dynamic executions (vs. 76.9% for the Tamiflex tool). Copyright © 2019, The Authors. All rights reserved.

关键词： Static analysis

来源：评论

学校读者我要写书评

暂无评论

Fault location technique of 154 kV substation using neural network

引用

Transactions of the Korean Institute of Electrical Engineers 2018年第9期67卷 1146-1151页

作者： Ahn, Jong-Bok Kang, Tae-Won Park, Chul-Won Dept. of Electrical Engineering Gangneung-Wonju National University Korea Republic of Dept. of Biomedical Convergence Engineering Gangneung-Wonju National University Korea Republic of Dept. of Computer Science and Engineering Gangneung-Wonju National University Korea Republic of

Recently, researches on the intelligence of electric power facilities have been trying to apply artificial intelligence techniques as computer platforms have improved. In particular, faults occurring in substation should be able to quickly identify possible faults and minimize power fault recovery time. This paper presents fault location technique for 154kV substation using neural network. We constructed a training matrix based on the operating conditions of the circuit breaker and IED to identify the fault location of each component of the target 154kV substation, such as line, bus, and transformer. After performing the training to identify the fault location by the neural network using Weka software, the performance of fault location discrimination of the designed neural network was confirmed. Copyright © The Korean Institute of Electrical Engineers.

关键词： Location

来源：评论

学校读者我要写书评

暂无评论

Evaluation of a Dual Convolutional Neural Network Architecture for Object-wise Anomaly Detection in Cluttered X-ray Security Imagery

Evaluation of a Dual Convolutional Neural Network Architectu...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Yona Falinie A. Gaus Neelanjan Bhowmik Samet Akçay Paolo M. Guillén-Garcia Jack W. Barker Toby P. Breckon Dept. of Computer Science Durham University Durham UK Dept. of Biomedical Eng. Universidad Politécnica de Chiapas Chiapas Mexico

X-ray baggage security screening is widely used to maintain aviation and transport secure. Of particular interest is the focus on automated security X-ray analysis for particular classes of object such as electronics, electrical items and liquids. However, manual inspection of such items is challenging when dealing with potentially anomalous items. Here we present a dual convolutional neural network (CNN) architecture for automatic anomaly detection within complex security X-ray imagery. We leverage recent advances in region-based (R-CNN), mask-based CNN (Mask R-CNN) and detection architectures such as RetinaNet to provide object localisation variants for specific object classes of interest. Subsequently, leveraging a range of established CNN object and fine-grained category classification approaches we formulate within object anomaly detection as a two-class problem (anomalous or benign). Whilst the best performing object localisation method is able to perform with 97.9% mean average precision (mAP) over a six-class X-ray object detection problem, subsequent two-class anomaly/benign classification is able to achieve 66% performance for within object anomaly detection. Overall, this performance illustrates both the challenge and promise of object-wise anomaly detection within the context of cluttered X-ray security imagery.

关键词： X-ray imaging Security Anomaly detection Object detection computer architecture Feature extraction Convolutional neural networks

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：