检索结果-内蒙古大学图书馆

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Manabu Watanabe Christian Koyama Masato Hayashi Izumi Nagatani Takeo Tadono Masanobu Shimada Tokyo Denki University JAXA

ISBN: (数字)9781728163741

ISBN: (纸本)9781728163758

JJ-FAST is the SAR-satellite based early deforestation monitoring system, and deforestation information obtained by using PALSAR-2/ScanSAR data are released on the JJ-FAST web site, 3 to 4 days after the observation. ScanSAR/50m spatial resolution data is currently used for the deforestation detection, and the minimum detection size is 3ha. In this paper, ScanSAR/25m spatial resolution data is used for the deforestation detection, and the detection accuracies are compared with the one obtained with the 50m spatial resolution data for four test sites. The minimum deforestation detection size is set to be 1ha in this time. The results show that the 25m spatial resolution data always shows higher detection accuracies. The results obtained in Cambodia test site show that user's accuracies are 21.4 % higher than the case of 50m resolution, and number of correctly detected polygon is 2.3 times more than the one for the 50m resolution case. It is indicated that the 25m spatial resolution ScanSAR data improves the detection accuracies with minimum detection size of 1 ha.

关键词： Spatial resolution Forestry Speckle Remote sensing detection algorithms Standards Monitoring

来源：评论

学校读者我要写书评

暂无评论

Color Lane Line detection Using the Bhattacharyya Distance

Color Lane Line Detection Using the Bhattacharyya Distance

引用

International Conference on Information, Intelligence, Systems and Applications (IISA)

作者： J. Han C. Lee Yonsei University

ISBN: (数字)9781665422284

ISBN: (纸本)9781665422291

In this paper, we propose a color lane line detection algorithm that can be used with moving vehicles. First, to reduce false detection and processing time, we considered the geometric relationship of the camera and the vanishing point. To effectively utilize color images for color line detection, we used the edge detection method based on the Bhattacharyya distance and a morphological operation. The proposed method was tested under various conditions (highway, urban, others; sunny, cloudy, early evening) and the experimental results show promising performance.

关键词： Road transportation Image color analysis Image edge detection Clouds Color detection algorithms Morphological operations

来源：评论

学校读者我要写书评

暂无评论

Data Augmentation for Insider Threat detection with GAN

Data Augmentation for Insider Threat Detection with GAN

引用

International Conference on Tools for Artificial Intelligence (ICTAI)

作者： Fangfang Yuan Yanmin Shang Yanbing Liu Yanan Cao Jianlong Tan School of Cyber Security University of Chinese Academy of Sciences Institute of Information Engineering Chinese Academy of Sciences Beijing China

ISBN: (数字)9781728192284

ISBN: (纸本)9781728185361

In insider threat detection domain, the datasets are highly imbalanced, where the number of user's normal behavior is higher than that of insider's anomalous behavior. A direct approach to handle the class imbalance problem is using data augmentation on the minority class. Existing data augmentation methods mainly produce synthetic samples according with the linear operation based on samples of the minority class. Hence, these methods just focus on local information which leads to the unitarily of the synthetic samples, resulting in overfitting. To enrich the diversity of the synthetic samples, we propose a deep adversarial insider threat detection (DAITD) framework using the Generative Adversarial Networks (GAN) to approximate the true anomalous behavior distribution. Specifically, we first obtain anomalous user behavior representations from the anomalous behavior data (minority class), and then use the generator of the GAN to model the actual anomalous behavior distribution, use the discriminator of the GAN to distinguish whether the synthetic sample from the generator is real or not. In this way, our method is able to generate high quality synthetic samples that are close to the anomalous user behavior. Experimental results show that the DAITD framework outperforms other comparative inside threat detection algorithms.

关键词： Conferences Training data Tools Generative adversarial networks Generators Data models detection algorithms

来源：评论

学校读者我要写书评

暂无评论

Score Prediction Network and Graph-based Selection for Semantic Line detection

Score Prediction Network and Graph-based Selection for Seman...

引用

International Conference on Information and Communication Technology Convergence (ICTC)

作者： Dongkwon Jin Chang-Su Kim School of Electrical Engineering Korea University Seoul Korea

ISBN: (数字)9781728167589

ISBN: (纸本)9781728199016

In this paper, we propose a novel semantic line detection algorithm. For an input image, we first detect semantic lines using a semantic line detector by classifying candidate lines. Then, we predict scores indicating whether they are harmonized or not between the detected lines. To this end, we develop a score prediction network (SPNet). Finally, we construct a graph consisting of the detected lines and the predicted scores between them and iteratively select the reliable semantic lines. Experimental results demonstrate that the proposed algorithm detects semantic lines accurately.

关键词： Semantics Detectors Prediction algorithms Classification algorithms Information and communication technology Reliability detection algorithms

来源：评论

学校读者我要写书评

暂无评论

Feature Maps Channel Augmentation for Object detection

Feature Maps Channel Augmentation for Object Detection

引用

Computer Vision, Image and Deep Learning (CVIDL), International Conference on

作者： Yuqi BAI Zhaohui MENG Hohai University NanJing City JiangSu Province China

ISBN: (数字)9781728194813

ISBN: (纸本)9781728194820

Taking advantage of feature maps channels is one of the key challenges in object detection. In this study, we propose an optimization solution to further utilize the inter-channel relationship of feature maps. According to the exploration experiments, we have proposed a new Feature Maps Channel Augmentation module (FMCA) that can be inserted into mainstream structures to better establish the strong and weak dependency relationship between channels. We used comparison and ablation experiments and found that the FMCA module achieved a certain improvement under the circumstances that the detection speed was less affected. On the COCO dataset, our FMCA with ResNet-50 backbone has achieved relatively better results.

关键词： Feature extraction Object detection Convolution Context modeling Semantics detection algorithms Task analysis

来源：评论

学校读者我要写书评

暂无评论

Effect of Airbag Deployment Phases on Tactile Occupant detection Sensor

Effect of Airbag Deployment Phases on Tactile Occupant Detec...

引用

International Science-Technical Conference Automotive Safety

作者： Naveen Shirur Christian Birkner Roman Henze Thomas M. Deserno Darshankumar Dudhat CARISSMA Technische Hochschule Ingolstadt Ingolstadt Germany Institute of Automotive Engineering Technische Universitát Braunschweig Braunschweig Germany Peter L. Reichertz Institute for Medical Informatics Technische Universitát Braunschweig Braunschweig Germany

An airbag is a crucial passive safety system that protects an occupant in the event of severe vehicle collisions. Its restraint effect can be controlled only when the occupant's contact data with the airbag is available. A new capacitive tactile sensor is developed and installed on the airbag surface to provide the occupant's first contact time, contact area and position on the airbag. Based on this feedback, the airbag pressure can be controlled. An airbag deployment is associated with different phases from trigger to full deployment. Before detecting the occupant, it is important to know the effect of these phases on the sensor. In this paper, the phase effects of dynamic airbag deployment on the contact sensor during the simplified static deployment tests are analyzed and discussed. Time-to-first-gas, unfolding of the textile, inflation, and cable capacitance effects are the key points brought to discussion. The results reveal, no effects of time-to-first-gas and inflation on the contact sensor. While the unfolding and cable capacitance have significant effects on the sensor which should be accounted for the occupant detection algorithm.

关键词： Tactile sensors Vehicle crash testing Capacitance Safety Vehicle dynamics detection algorithms Textiles

来源：评论

学校读者我要写书评

暂无评论

detection of Temporal Communities in Mobile Social Networks

Detection of Temporal Communities in Mobile Social Networks

引用

IEEE Conference on Computer Communications Workshops, INFOCOM Wksps

作者： Mengni Ruan Huan Zhou Dawei Li Xuxun Liu Qingyong Deng College of Computer and Information Technology China Three Gorges University Yichang China Montclair State University Montclair NJ USA College of Electronic and Information Engineering South China University of Technology Guangzhou China College of Information Engineering Xiangtan University Xiangtan China

ISBN: (数字)9781728186955

ISBN: (纸本)9781728186962

In recent years, community detection in Mobile Social Networks (MSNs) has attracted a lot of attentions from both academia and industry areas. The existing methods of community detection usually focus on static networks. However, MSNs in essence are dynamically intermittently connected networks with a time-varying topology. Therefore, this paper proposes a novel temporal community detection method based on nodes' temporal closeness. In order to evaluate the performance of the proposed method and study the evolution law of the temporal community, we conduct extensive simulations using two real mobility traces, the MIT Reality trace and the Infocom 06 trace. The results show that many temporal communities share similar members and appear at different times. Furthermore, we find the periodic appearance of temporal community.

关键词： Social network services Measurement detection algorithms Bluetooth Network topology Indexes Wireless fidelity

来源：评论

学校读者我要写书评

暂无评论

DC Series Arc Fault detection Using Machine Learning in Photovoltaic Systems: Recent Developments and Challenges

DC Series Arc Fault Detection Using Machine Learning in Phot...

引用

International Conference on Condition Monitoring and Diagnosis, CMD

作者： Shibo Lu Animesh Sahoo Rui Ma B. T. Phung School of Electrical Engineering and Telecommunications University of New South Wales Sydney Australia University of Miami Coral Gables Florida USA

ISBN: (数字)9781728159317

ISBN: (纸本)9781728159324

DC arc faults, especially series arc faults, are becoming more common in photovoltaic (PV) systems. Without timely detection and interruption, such dangerous events can cause catastrophic fires, posing severe threat to human safety and properties. This paper presents a review on DC series arc fault detection using machine learning (ML) in PV systems. Technical details of applied ML methods, including conventional ML and deep learning (DL), in recent published paper are summarized and discussed. In addition, several popular ML methods are evaluated and compared using the same experimental datasets collected in laboratory to examine their effectiveness in DC series arc fault detection. Finally, practical challenges are identified, potential solutions are provided, and future research directions are recommended.

关键词： Photovoltaic systems Deep learning Condition monitoring Machine learning algorithms Fault detection Safety detection algorithms

来源：评论

学校读者我要写书评

暂无评论

Poor Man's Virtual Camera: Real-Time Simultaneous Matting and Camera Pose Estimation

引用

IEEE COMPUTER GRAPHICS AND APPLICATIONS 2019年第6期39卷 108-119页

作者： Szentandrasi, Istvan Dubska, Marketa Zacharias, Michal Herout, Adam Brno Univ Technol Brno Czech Republic

Today's film and advertisement production heavily uses computer graphics combined with living actors by chroma keying. The matchmoving process typically takes a considerable manual effort. Semiautomatic matchmoving tools exist as well, but they still work offline and require manual check-up and correction. In this paper, we propose an instant matchmoving solution for green screen. It uses a recent technique of planar uniform marker fields. Our technique can be used in indie and professional filmmaking as a cheap and ultramobile virtual camera, and for shot prototyping and storyboard creation. The matchmoving technique based on marker fields of shades of green is very computationally efficient: we developed and present in this paper a mobile application running at 33 FPS. Our technique is thus available to anyone with a smartphone at low cost and with an easy setup, opening space for new levels of filmmakers' creative expression.

关键词： Augmented Reality Cameras Mobile Computing Pose Estimation Real Time Systems Camera Pose Estimation Matchmoving Technique Storyboard Creation Shot Prototyping Ultramobile Virtual Camera Professional Filmmaking Planar Uniform Marker Fields Green Screen Semiautomatic Matchmoving Tools Chroma Keying Living Actors Computer Graphics Advertisement Production Cameras Image Edge detection Production Image Color Analysis Real Time Systems detection algorithms

来源：评论

学校读者我要写书评

暂无评论

Whole genome comparative analysis of CpG islands in camelid and other mammalian genomes

引用

MAMMALIAN BIOLOGY 2019年第1期98卷 73-79页

作者： Barazandeh, Arsalan Mohammadabadi, Mohammadreza Ghaderi-Zefrehei, Mostafa Rafeie, Farjad Imumorin, Ikhide G. Shahid Bahonar Univ Kerman Dept Anim Sci 22 Bahman Blvd Kerman *** Iran Univ Jiroft Dept Anim Sci Jiroft Iran Univ Yasuj Dept Anim Sci Anim Genet & Breeding Yasuj Iran Univ Guilan Fac Agr Sci Dept Agr Biotechnol Rasht Iran Georgia Inst Technol Sch Biol Sci Atlanta GA 30332 USA

Camels bear unique genotypes and phenotypes for adaptation in their environment, and as such could be very useful in the weather extremes accelerated by global climate change. Published sequences of Camelidae genomes provide an opportunity to elucidate the genomic architecture of these animals. CpG islands (CGIs) sequence patterns in complex genomes play important roles in gene regulation via epigenetic change. Comparative large-scale genome analysis of CGIs in Camelidae was carried out using five different CGI detection algorithms, evaluating numbers of CGIs, CGI density and CGI length distribution in Camelidae. All algorithms identified the alpaca genome as having the largest number of CGIs, CGI density and average length of CGIs, though, the CGI length distribution and their number could be implicitly attributed to the characteristics of an algorithm for CGI identification rather than that of the species. In addition, high algorithm-to-algorithm variability of the observed CGI properties was shown. It was well expected, since there is no clear definition of a CGI and different algorithms could identify different genome regions as CGIs. Comparison with other mammalian genomes (human, mouse, dog, horse and cow) shows that CGIs features in cow were most similar to camelid genomes. Further analysis of camelid genomes may shed more light on molecular origins and mechanisms of adaptation in these extreme heat-adapted animals. (C) 2019 Published by Elsevier GmbH on behalf of Deutsche Gesellschaft fur Saugetierkunde.

关键词： Adaptation Camelid genomes CGIs detection algorithms

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：