检索结果-内蒙古大学图书馆

Big Data, Artificial Intelligence and Internet of Things Engineering (ICBAIE), International Conference on

作者： Yihan Wang Bailin Li Ying Xiong Mechanical Engineering Southwest Jiaotong University Chengdu Sichuan China

ISBN: (数字)9781665415408

ISBN: (纸本)9781665447065

The goal of this paper is to accomplishing the automatic detection for railway cable fixtures. Since Yolov4-tiny achieves relatively lower recall and precision on the fixture dataset, we modify its Cross Stage Partial (CSP) architecture to reduce the repeated gradient information, so that the modified architecture achieves a better performance on the communication cable fixtures dataset. Meanwhile, our algorithm modifies the classification loss function by introducing a heuristic penalty factor to pay more attention on the minor classes in the imbalanced dataset. Experimental results show that the proposed algorithm has increased recall and precision by 3.3% and 2.4% compared with the baseline algorithm, respectively.

关键词： Railway communication Fixtures Communication cables Classification algorithms Internet of Things detection algorithms Task analysis

来源：评论

学校读者我要写书评

暂无评论

An ensemble-of-classifiers approach for corn leaf based diseases detection

An ensemble-of-classifiers approach for corn leaf based dise...

引用

Information Technology International Seminar (ITIS)

作者： Wahyudi Agustiono Engineering Faculty University of Trunojoyo Madura Bangkalan Indonesia

ISBN: (纸本)9781665408080

This study at hand proposes an ensemble-of-classifiers approach for corn leaf based diseases detection. Instead of using a single classical machine learning method, it developed a detection model by employing two classification methods: Voting Classifier with Majority Voting and 5 Classification and Regression Tree (CART) with max depth 2, 4, 6, 8, and 10 to obtain higher accuracy in results. In particular, it benefited from PlantVillage, a public repository that provided over 8,000 corn leaf images as the dataset for the training and testing. All these images were extracted using the Global Color Histogram (GCH), Color Coherence Vector (CCV). Test results of segmented image against Red pixel using the Color Processing detection Algorithm (CPDA) showed the best accuracy with a Precision of 82.92%, Recall 82.55%, and an f1-Score of 82.6%.

关键词： Image segmentation Histograms Image color analysis Crops Coherence Feature extraction detection algorithms

来源：评论

学校读者我要写书评

暂无评论

Signal-to-noise Ratio Analysis of Infrared Small Target detection Based on Energy Accumulation For High-dimensional Motion Parameters

Signal-to-noise Ratio Analysis of Infrared Small Target Dete...

引用

Chinese Automation Congress (CAC)

作者： Tianlei Ma Jiaqi Wang Zhen Yang Yanan Ku Chengshuo Zhang Xiangyang Ren College of Electrical Engineering Zhengzhou University Zhengzhou China School of Information Science and Engineering Shenyang University of Technology Shenyang China

ISBN: (纸本)9781665426480

Infrared (IR) small target detection in heavy noise has always been a challenging research task. detection methods based on energy accumulation can effectively suppress noise and improve the signal-to-noise ratio (SNR). Unfortunately, the detection performance of such dim and small target detection methods is limited due to the lack of accurate target motion modeling. In this paper, considering that the target motion is complex and diverse, a high-dimensional motion parameter (HMP) target motion model is studied. The HMP target motion model can cover various target motion forms, including constant velocity (CV) linear motion, constant acceleration (CA) linear motion and constant velocity curvilinear motion (CVC). Then, the SNR gain based on the energy accumulation detection algorithm under HMP is analyzed in detail. Experimental results show that when the target motion is non-linear, the energy accumulation method based on the HMP motion model can more effectively improve the SNR compare to the energy accumulation method based on CA motion model.

关键词： Analytical models Automation Object detection detection algorithms Task analysis Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Image based tiny fire detection in a grid environment using human geometric constrains

Image based tiny fire detection in a grid environment using ...

引用

Electrical Engineering and Control Technologies (CEECT), Conference on

作者： Lei Chen Weili Xue Beijing Institute of tracking and telcommunication technology Beijing China Shanghai Jiao Tong University Shanghai China

Smoking detection is critical for fire safety in the grid facility environment. The vision-based smoking detection algorithm plays a key role to prevent a fire in grid facility environment. However, traditional methods based on target detection remain challenging in the realistic scenario, such as that it can not correctly distinguish whether a tiny object is a cigarette. In this paper, based on human geometric constraints(HGC), we propose a method which combines action recognition and target detection. First, in order to remove irrelevant action frames, we extract human skeletal key points from relevant frames using HGC algorithm, and build a smoking action dataset. Second, we train a neural network with the dataset of smoking action and then combine the deep learning-based target detection method to refine the judgment of smoking action with the bounding box extracted by skeletal points. Comprehensive experimental results demonstrate that our proposed method removes about 90% interfering action frames, improves average precision of the network from 77% to 82% in our dataset.

关键词： Electrical engineering Target recognition Neural networks Object detection Task analysis detection algorithms Fire safety

来源：评论

学校读者我要写书评

暂无评论

Contextual Information Based Community detection in Attributed Heterogeneous Networks

引用

IEEE LATIN AMERICA TRANSACTIONS 2019年第2期17卷 236-244页

作者： Dias, Marcio Braz, Paulo Bezerra, Eduardo Goldschmidt, Ronaldo IME CEFET/RJ

Community detection is an important network analysis task that has been studied by academy and industry for the last years. Community detection algorithms try to maximize the number of connections in each community and minimize the number of connections between different communities. Some of them consider not only the topological aspects of the networks but also try to explore existing information about the context of the application available in attributes of nodes and/or connections in order to find cohesive content communities. Those algorithmswere designed to run exclusively over homogeneous networks and cannot deal with heterogeneous structures. Nevertheless, typical real-world networks are heterogeneous. Thus, this article proposes ComDet, a community detection approach that fills this gap by taking into account topological and contextual information to detect communities in heterogeneous networks. The proposed approach uses data clustering as a pre-processing step for the community detection process in order to identify similar nodes that are directly or indirectly linked and organize them in cohesive and possibly overlapping communities. Experiments in three attributed heterogeneous networks show that ComDet leads to interesting partitions with cohesive content communities.

关键词： Heterogeneous networks Laser radar IEEE transactions Task analysis Industries detection algorithms Indexes Community detection Data Clustering Heterogeneous Networks Attributed

来源：评论

学校读者我要写书评

暂无评论

Floating Small Target detection Algorithm based on Features Fusion of Full Polarization Information in Sea Clutter

Floating Small Target Detection Algorithm based on Features ...

引用

IEEE Advanced Information Technology, Electronic and Automation Control Conference (IAEAC)

作者： Jianjun Tang Hao Liang Zhangqin Zhu Lin Jin Nanjing Institute of electronic technology Nanjing China

ISBN: (数字)9781728180281

ISBN: (纸本)9781728180298

The detection of floating small targets in strong sea clutter is a difficult problem for radar detection. Traditional algorithms have poor detection performance in a single domain (time domain, Doppler domain, and time-frequency domain). Feature-based detection algorithms are an effective method for detecting floating small targets on the sea surface. This paper proposes a feature fusion detection algorithm based on full polarization information. This paper selects six features in the time domain and Doppler domain, and extracts six features based on full polarization information. This paper analyzes the separability of these features, and finally uses the PCA-based anomaly detector to detect target. It is verified on the IPIX radar data set. Compared with the existing six-feature PCA-based anomaly detector algorithm, the experimental results prove that the proposed algorithm has excellent detection performance.

关键词： Radar clutter Radar detection Object detection Feature extraction Doppler effect Time-domain analysis detection algorithms

来源：评论

学校读者我要写书评

暂无评论

Infrared Image Pedestrian detection via YOLO-V3

Infrared Image Pedestrian Detection via YOLO-V3

引用

IEEE Advanced Information Technology, Electronic and Automation Control Conference (IAEAC)

作者： Wei Li School of Artificial Intelligence and Automation Huazhong University of Science and Technology

ISBN: (数字)9781728180281

ISBN: (纸本)9781728180298

Thermal imaging is often used for pedestrian detection at night to make up for the inability of traditional cameras to be used in harsh lighting conditions. However, the pedestrian detection technology based on thermal imaging is difficult to overcome the interference of high-heat objects around the human body, and it is easy to cause misidentification. This paper proposes to detect pedestrians in infrared images at night through the YOLO-V3 detection framework. Experimental results show that the proposed method can not only accurately locate pedestrians at night, but also maintain high detection accuracy when pedestrians overlap.

关键词： Neural networks Lighting Interference Security Information technology detection algorithms Monitoring

来源：评论

学校读者我要写书评

暂无评论

Pedestrian detection Algorithm based on Improved Faster RCNN

Pedestrian Detection Algorithm based on Improved Faster RCNN

引用

IEEE Advanced Information Technology, Electronic and Automation Control Conference (IAEAC)

作者： Xiaoqiang Shao Jinyang Wei Defeng Guo Runyang Zheng Xinchao Nie Guowei Wang Yu Zhao College of Electric and Control Engineering Xi’an University of Science and Technology Xi’an China

ISBN: (数字)9781728180281

ISBN: (纸本)9781728180298

To solve the problem of poor detection effect of small-scale pedestrian in the image, based on the existing deep convolutional neural network(CNN)model. We propose an improved pedestrian detection algorithm based on Faster RCNN. First, the image features are extracted by CNN, and the areas that may contain pedestrians are extracted by clustering and regional Recommendation Network (RPN), Secondly, a multi-layer feature fusion strategy based on cascade is proposed. The semantic information of the network can be enhanced by combining the features of the high level with those of the low level. Finally, the Online Hard Example Mining(OHEM) method is used to train the high loss samples to deal with the imbalance between the positive and negative samples, so as to significantly improve the detection performance of the algorithm. Experimental results show that this method greatly improves the accuracy of small target pedestrian detection. In PASCAL VOC 2007 and INRIA pedestrian data sets, the average accuracy was improved by 6.3% and 13.93% respectively.

关键词： Conferences Semantics Clustering algorithms Feature extraction Convolutional neural networks detection algorithms Information technology

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Learning Approaches for Construction of Malware Families

Unsupervised Learning Approaches for Construction of Malware...

引用

IEEE International Conference on Big Data

作者： Alexis J. Jackson Krishnendu Ghosh Department of Computer Science College of Charleston South Carolina US

ISBN: (纸本)9781665480468

Construction of malware families from behavioral properties of malware in wild is challenging. The understanding of behavioral properties of malware families is key in detection of malware attacks. In this work, a methodology is described for unsupervised construction of malware families using two phase approach. The first phase includes natural language processing techniques such as term-frequency and inverse document frequency are applied on trace data to compute similarities. A graph of textual similarities of trace sequences is constructed. The second phase, consists of application of minimum spanning tree and community detection algorithms for construction of malware families. Experiments employing the proposed methodology are conducted on a published dataset and the results are reported. Machine learning algorithms are evaluated on the constructed malware families. The results are promising in automated detection of variants of malware from malware families.

关键词： Machine learning algorithms Big Data Malware Natural language processing Behavioral sciences detection algorithms Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Developing Self-evolving Deepfake Detectors Against AI Attacks

Developing Self-evolving Deepfake Detectors Against AI Attac...

引用

IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA)

作者： Ian Miller Dan Lin Department of Computer Science Vanderbilt University Nashville TN USA

As deep-learning based image and video manipulation technology advances, the future of truth and information looks bleak. In particular, Deepfakes, wherein a person’s face can be transferred onto the face of someone else, pose a serious threat for potential spread of convincing misinformation that is drastic and ubiquitous enough to have catastrophic real-world consequences. To prevent this, an effective detection tool for manipulated media is needed. However, the detector cannot just be good, it has to evolve with the technology to keep pace with or even outpace the enemy. At the same time, it must defend against different attack types to which deep learning systems are vulnerable. To that end, in this paper, we review various methods of both attack and defense on AI systems, as well as modes of evolution for such a system. Then, we put forward a potential system that combines the latest technologies in multiple areas as well as several novel ideas to create a detection algorithm that is robust against many attacks and can learn over time with unprecedented effectiveness and efficiency.

关键词： Deep learning Deepfakes Privacy Detectors Security Intelligent systems 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：