检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Remedios, Lucas W. Liu, Han Remedios, Samuel W. Zuo, Lianrui Saunders, Adam M. Bao, Shunxing Huo, Yuankai Powers, Alvin C. Virostko, John Landman, Bennett A. Vanderbilt University Department of Computer Science Nashville United States Vanderbilt University Department of Electrical and Computer Engineering Nashville United States Johns Hopkins University Department of Computer Science Baltimore United States National Institutes of Health Department of Radiology and Imaging Sciences Bethesda United States Vanderbilt University Department of Biomedical Engineering Nashville United States University of Texas at Austin Department of Diagnostic Medicine Dell Medical School Austin United States University of Texas at Austin Livestrong Cancer Institutes Dell Medical School Austin United States University of Texas at Austin Austin Department of Oncology Dell Medical School United States University of Texas at Austin Oden Institute for Computational Engineering and Sciences Austin United States Vanderbilt University Medical Center Department of Medicine Division of Diabetes Endocrinology and Metabolism Nashville United States VA Tennessee Valley Healthcare System Nashville United States Vanderbilt University Department of Molecular Physiology and Biophysics Nashville United States

Purpose: Combining different types of medical imaging data (multimodal fusion) promises better segmentation of anatomical structures, such as the pancreas. Strategic implementation of multimodal fusion could improve our ability to study diseases like diabetes. However, where to perform fusion in deep learning models is still an open question. It is unclear if there is a single best location to combine (fuse) information when analyzing pairs of imperfectly aligned images, or if the optimal fusion location depends on the specific model being used. Two main challenges when using multiple imaging modalities to study the pancreas are 1) the pancreas and surrounding abdominal anatomy have a deformable (changeable) structure, making it difficult to consistently align the images and 2) breathing by the individual during image collection further complicates the alignment between multimodal images. Even after using state-of-the-art deformable image registration techniques, specifically designed to align abdominal images, multimodal images of the abdomen are often not perfectly aligned. This study examines how the choice of different fusion points, ranging from early in the image processing pipeline to later stages, impacts the segmentation of the pancreas on imperfectly registered multimodal magnetic resonance (MR) images. Approach: Our dataset consists of 353 pairs of T2-weighted (T2w) and T1-weighted (T1w) abdominal MR images from 163 subjects with accompanying pancreas segmentation labels drawn mainly based on the T2w images. Because the T2w images were acquired on two breath holds (interleaved) and the T1w images on one breath hold, there were 3 different breath holds impacting the alignment of each pair of images. We used state-of-the-art deformable abdominal image registration (deeds) to align the image pairs. Then we trained a collection of basic UNets with different fusion points, spanning from early to late (early layers or late layers in the model), to assess how ea

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

An Empirical Study of Security Practices for Microservices systems

arXiv

引用

arXiv 2021年

作者： Ali, Rezaei Nasab Mojtaba, Shahin Ali, Hoseyni Raviz Seyed Peng, Liang Amir, Mashmool Valentina, Lenarduzzi School of Computer Science Wuhan University Wuhan430072 China School of Computing Technologies RMIT University Melbourne3000 Australia Department of Computer Science Bioengineering Robotics and System Engineering University of Genoa Genoa16126 Italy Faculty of Information Technology and Electrical Engineering University of Oulu OuluFI-90014 Finland

Despite the numerous benefits of microservices systems, security has been a critical issue in such systems. Several factors explain this difficulty, including a knowledge gap among microservices practitioners on properly securing a microservices system. To (partially) bridge this gap, we conducted an empirical study. We first manually analyzed 861 microservices security points, including 567 issues, 9 documents, and 3 wiki pages from 10 GitHub open-source microservices systems and 306 Stack Overflow posts concerning security in microservices systems. In this study, a microservices security point is referred to as "a GitHub issue, a Stack Overflow post, a document, or a wiki page that entails 5 or more microservices security paragraphs". Our analysis led to a catalog of 28 microservices security practices. We then ran a survey with 74 microservices practitioners to evaluate the usefulness of these 28 practices. Our findings demonstrate that the survey respondents affirmed the usefulness of the 28 practices. We believe that the catalog of microservices security practices can serve as a valuable resource for microservices practitioners to more effectively address security issues in microservices systems. It can also inform the research community of the required or less explored areas to develop microservices-specific security practices and tools. © 2021, CC BY.

关键词： Open systems

来源：评论

学校读者我要写书评

暂无评论

Using chaotic stream cipher to enhance data hiding in digital images

arXiv

引用

arXiv 2021年

作者： Haimour, Sana AL-Mousa, Mohammad Rasmi Marie, Rashiq R. Department of Computer Science Zarqa University Zarqa13132 Jordan Department of Software Engineering Zarqa University Zarqa13132 Jordan Information System Department Taibah University Madinah Saudi Arabia

The growing potential of modern communications needs the use of secure means to protect information from unauthorized access and use during transmission. In general, encryption a message using cryptography techniques and then hidden a message with a steganography methods provides an additional layer of protection. Furthermore, using these combination reduces the chance of finding the hidden message. This paper proposed a system which combines schemes of cryptography with steganography for hiding secret messages and to add more complexity for steganography. The proposed system secret message encoded with chaotic stream cipher and afterwards the encoded data is hidden behind an RGB or Gray cover image by modifying the kth least significant bits (k-LSB) of cover image pixels. The resultant stego-image less distorters. After which can be used by the recipient to extract that bit-plane of the image. In fact, the schemes of encryption/decryption and embedding/ extracting in the proposed system depends upon two shred secret keys between the sender and the receiver. An experiment shows that using an unauthorized secret keys between the sender and the receiver have totally different messages from the original ones which improve the confidentiality of the images. © 2021, CC BY.

关键词： Steganography

来源：评论

学校读者我要写书评

暂无评论

Amfmer: A Multimodal Full Transformer for Unifying Aesthetic Assessment Tasks ⋆

SSRN

引用

SSRN 2023年

作者： Qi, Jin Su, Can Hu, Xiao-Xuan Chen, Meng-Wei Sun, Yan-Fei Dong, Zhen-Jiang Cao, Yue Liu, Tian-Liang Luo, Jie-Bo College of Internet of Things Nanjing University of Posts and Telecommunications Nanjing210003 China College of Computer Science Nanjing University of Posts and Telecommunications Nanjing210046 China Jiangsu ToYou Research Institute of Information Intelligence and Technology Nanjing210012 China College of Telecommunications and Information Nanjing University of Posts and Telecommunications Nanjing210003 China Department of Computer Science University of Rochester RochesterNY14627 United States Institute of System Security and Trusted Computing School of Cyber science and Engineering Wuhan University Wuhan430072 China

Computational aesthetics aims to simulate the human visual perception process via the computers to automatically evaluate aesthetic quality with automatic methods. This topic has been widely studied by numerous researchers. However, existing research mostly focuses on image content while disregarding high-level semantics in the related image comments. In addition, most major assessment methods are based on convolutional neural networks (CNNs) for learning the distinctive features, which lack representational power and modeling capabilities for multimodal assessment requirement. Furthermore, many transformer-based model approaches suffer from limited information ffow between different parts of the assumed model, and aesthetic prior knowledge may, to some extent, limit the ability of the given model to perceive image style and atmosphere. Inspired by the above questions, in this paper, A novel Multimodal Full transforMER (AMFMER) evaluation model without prior knowledge is proposed, consisting of three components: visual stream, textual stream and multimodal fusion layer. Firstly, the visual stream exploits the improved Swin transformer to extract the distinctive layer features of the input image. Secondly, the textual stream is based on the robustly optimized bidirectional encoder representations from transformers (RoBERTa) text encoder to extract semantic information from the corresponding comments. Thirdly, the multimodal fusion layer fuses visual features, textual features and low-layer salient features in a cross-attention manner to extract the multimodal distinctive features. Experimental results show that the proposed AMFMER approach in this paper outperforms current mainstream methods in a uniffed aesthetic prediction task, especially in terms of the correlation between the objective model evaluation and subjective human evaluation. © 2023, The Authors. 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

RSSI Data Preparation for Machine Learning 2

RSSI Data Preparation for Machine Learning

引用

2nd International Conference on Informatics, Multimedia, Cyber, and Information system, ICIMCIS 2020

作者： Abidin, Dodo Zaenal Nurmaini, Siti Firsandava Malik, Reza Erwin Rasywir, Errissya Pratama, Yovi Universitas Sriwijaya Palembang Lecturer of Computer Faculty of Universitas Dinamika Bangsa Jambi Indonesia Leader of Intelligence System Research Group Universitas Sriwijaya Palembang Indonesia Leader Team of Communication Networks Research Universitas Sriwijaya Palembang Indonesia Informatics Engineering Departement of Sriwijaya University Jambi Indonesia Informatics Engineering Computer Departement of Dinamika Bangsa University Jambi Indonesia

ISBN: (纸本)9781728191676

In this study, we prepared unstructured raw RSSI (Received Signal Strength Indication) data to prepare it for use in machine learning predictive modeling. RSSI data preparation is very important in predictive modeling machine learning projects, such as classification and regression, so that the algorithm can model it based on the right conditions, because the data has a more specific part but does not necessarily affect the algorithm performance. RSSI data were collected from the Dinamika Bangsa University Campus building, namely 225 reference points. The two main processes involved in data compilation, namely construction data and data cleaning. From the process of identifying a column containing a single RSSI value, several unique values were found in each column in the RSSI data table. Since no column has a Single Value, no columns are deleted. Then in the process of deleting columns that have low RSSI variance, the input is 5969 rows and 18 columns. The output is 5969 rows and 3 columns. However, the number of columns that passed the Low Variance selection was 5969 rows and 18 columns, meaning that all columns in the dataset have high variance. Additionally, no duplicate RSSI data were found. It can be said that the result of the overall preparation of this data set is the RSSI data used in good condition and can be used for machine learning needs. © 2020 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Power silicon carbide schottky diodes as current mode ?-radiation detectors 32

Power silicon carbide schottky diodes as current mode ?-radi...

引用

32nd IEEE International Conference on Microelectronics, MIEL 2021

作者： Ilic, S.D. Andjelkovic, M.S. Carvajal, M.A. Lallena, A.M. Krstic, M. Stankovic, S. Ristic, G.S. University of Belgrade Center of Microelectronic Technologies Technology and Metallurgy Serbia IHP-Leibniz-Institut für Innovative Mikroelektronik System Architectures Department Frankfurt Germany University of Granada Department of Electronics and Computer Technology Granada Spain Vincca Institute of Nuclear Sciences Department of Radiation and Environmental Belgrade Serbia University of Niš Faculty of Electronic Engineering Department of Microelectronics Niš Serbia

ISBN: (纸本)9781665445283

In this paper, the feasibility of using commercial power Silicon Carbide (SiC) Schottky diodes as a current mode ?-radiation detector have been examined. Diodes with almost identical electric characteristics are purchased from two different manufacturers, On Semiconductor and RoHM. They have been tested under gamma radiation exposure from a Co-60 source. The current response during irradiation has been measured for various dose rates with reversed diode bias. Investigated range of dose rates was from 0.258 Gy/h to 26.312 Gy/h, and reverse diode bias values were 10 V, 20 V, 50 V, 100 V and 200 V. Tested Schottky diodes produce stable current response for the investigated dose rates. Although the manufacturers are different, the results show that the dosimetric characteristics of these diodes have an excellent match. Sensitivity was proportional to the applied reverse bias voltage. A simple power-law can very well describe the dependence of measured radiation-induced current on dose rate. © 2021 IEEE.

关键词： Silicon carbide

来源：评论

学校读者我要写书评

暂无评论

A non-parametric modelling of concrete mixtures for optimum productivity 2

A non-parametric modelling of concrete mixtures for optimum ...

引用

2nd International Conference on Advances in Big Data, Computing and Data Communication systems, icABCD 2019

作者： Machele, Ipeleng Labius Owolawi, Pius Adewale Tu, Chunling Dept. Computer System Engineering Tshwane University of Technology TUT Tshwane South Africa

ISBN: (纸本)9781538692363

The absence of the distribution assumption in the modeling of any physical quantity enhance the quality of modeling. The complexity in concrete mixture modeling becomes critical in optimum design and control of concrete mixture. In this paper, a nonparametric modeling technique is adopted to avoid the guessing assumption noted with parametric. In order to address this condition, Kernel estimator techniques is considered as a result of its efficiency to model such a task as concrete mixture distribution. A thousand and thirty (1030) portion mixes for each of the two segments was considered, particularly the water to bond proportion (w/c) with a range (0.27-1.88), and the fine concrete quantities with a scope of (140-540), estimated in kilograms(Kg) were embraced. The performance of the kernel estimator is measured by using the Integrated Square Errors (ISE) for the various smoothing techniques. The paper considered seven kernel estimators and the most performed estimator is evaluated based on the ISE testing technique. By means of observation, the Epanechnikov kernel estimator was considered the most appropriate with ISE of about 7.33%, thus allowing the water to bond proportion to have a major effect on the concrete mixture. © 2019 IEEE.

关键词： Concrete mixtures

来源：评论

学校读者我要写书评

暂无评论

Object-oriented Map Exploration and Construction Based on Auxiliary Task Aided DRL

Object-oriented Map Exploration and Construction Based on Au...

引用

International Conference on Pattern Recognition

作者： Junzhe Xu Jianhua Zhang Shengyong Chen Honghai Liu College of Computer Science and Technology Zhejiang University of Technology Hangzhou China College of Computer Science and Technology Tianjin University of Technology Tianjin China State Key Laboratory of Robotics and System School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen China

Environment exploration by autonomous robots through deep reinforcement learning (DRL) based methods has attracted more and more attention. However, existing methods usually focus on robot navigation to single or multiple fixed goals, while ignoring the perception and construction of external environments. In this paper, we propose a novel environment exploration task based on DRL, which requires a robot fast and completely perceives all objects of interest, and reconstructs their poses in a global environment map, as much as the robot can do. To this end, we design an auxiliary task aided DRL model, which is integrated with the auxiliary object detection and 6-DoF pose estimation components. The outcome of auxiliary tasks can improve the learning speed and robustness of DRL, as well as the accuracy of object pose estimation. Comprehensive experimental results on the indoor simulation platform AI2-THOR have shown the effectiveness and robustness of our method.

关键词： Navigation Object oriented modeling Pose estimation Semantics Object detection Reinforcement learning Robustness

来源：评论

学校读者我要写书评

暂无评论

A Multilevel Non-interference Vulnerability Analysis Method for Information Leakage Problem

A Multilevel Non-interference Vulnerability Analysis Method ...

引用

IEEE International Conference on Data Science in Cyberspace (DSC)

作者： Wenjing Zhong Jinjing Zhao Hesuan Hu National Key Laboratory of Science and Technology on Information System Security Beijing China School of Electro-Mechanical Engineering Xidian University Xi&#x0027 an Shaanxi China National Key Laboratory of Science and Technology on Information System Security BeijingChina100101 State Key Laboratory for Manufacturing Systems Engineering School of Electro-Mechanical Engineering Xidian University Xi&#x0027 an Jiaotong University Xi&#x0027 School of Computer Science and Engineering College of Engineering Nanyang Technological University Singapore

ISBN: (纸本)9781665418164

Security vulnerabilities caused by information leakage are a critical aspect of the security for information systems. Such vulnerabilities can be identified by non-interference analysis. Strong nondeterministic non-interference (SNNI) and bisimulation SNNI (BSNNI) are the typical properties of non-interference. Existing works related to non-interference analysis are mainly based on the setting with only two security levels. Such setting is coarse-grained compared to the real system. In this paper, we analyze the non-interference with multiple security levels by integer linear programming. Obviously, the non-interference with multiple security levels is more fine-grained but more complex than that with only two security levels. On the perspective of complexity, we provide the general and simplified non-interference analyses in turn for multilevel SNNI and BSNNI which are defined on the concepts of upper sets. The general analysis is derived from the definitions of multilevel SNNI and BSNNI, and solve the identification problem of multilevel SNNI and BSNNI directly. By analyzing and removing the impact of upper sets' coverability, the simplified analysis reduces the redundancy and improves the efficiency in the analysis process.

关键词： Graphics Conferences Redundancy Cyberspace Integer linear programming Data science Mathematics

来源：评论

学校读者我要写书评

暂无评论

Video-Based 3D Human Pose Estimation Research

Video-Based 3D Human Pose Estimation Research

引用

IEEE Conference on Industrial Electronics and Applications (ICIEA)

作者： Siting Tao Zhi Zhang College of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan China China Big Data Science and Engineering Research Institute Wuhan University of Science and Technology Wuhan China China

ISBN: (纸本)9781665409858

At present, most of the video-based 3D human pose estimation methods process the video frame by frame, ignoring the timing information of the upper and lower frames of the video. When there is a single-frame estimation error caused by self-occlusion, the occlusion part will be Some strange movements appear due to information loss, and the estimated results make it difficult to produce accurate motion sequences. Therefore, considering the continuity of the upper and lower frames of the video, this paper adopts the HMR algorithm and introduces a bidirectional long-term memory network (BI-LSTM) in the encoding part to process the video sequence, and then outputs the parameters of the human body model through the SMPL parameters and inputs them into the discriminator for confrontation, train. In order for the discriminator to also take into account the semantic information of the temporal context, the discriminator in this paper also introduces a BI-LSTM network to improve the authenticity of the generated poses. Experimental results show that the accuracy of the model is improved when self-occlusion occurs.

关键词： Training Industrial electronics Solid modeling Estimation error Three-dimensional displays Biological system modeling Pose estimation

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：