2021 International Symposium on Computer Science and Intelligent Controls (ISCSIC)最新文献_第5页

Autonomous Obstacle Detection and Avoidance of Lunar Landing Based on Active and Passive Sensors 基于主动和被动传感器的月球自主障碍物检测与避障

2021 International Symposium on Computer Science and Intelligent Controls (ISCSIC) Pub Date : 2021-11-01 DOI: 10.1109/ISCSIC54682.2021.00076

T. Hu, Liang He, Tao Cao, Hanmo Zhang, Yangxiu Hu, Zhouyuan Qian

{"title":"Autonomous Obstacle Detection and Avoidance of Lunar Landing Based on Active and Passive Sensors","authors":"T. Hu, Liang He, Tao Cao, Hanmo Zhang, Yangxiu Hu, Zhouyuan Qian","doi":"10.1109/ISCSIC54682.2021.00076","DOIUrl":"https://doi.org/10.1109/ISCSIC54682.2021.00076","url":null,"abstract":"lunar landing and exploration in the future require precise landing near the living cabin, as well as some complex scientific target environments such as moon craters and caves, requiring high positioning and navigation accuracy, and these complex areas is rugged, there is no prior environmental information. In view of the characteristics of the lunar surface, an obstacle detection and site selection method based on illumination gradient and 3D point cloud is proposed. When the distance from the lunar surface is relatively far, the illumination direction of image acquisition is determined; the region of interest (ROI) is selected to improve detection efficiency; then detect the rocks and craters in each ROI, and output them as fitted ellipses with geometric and position information, construct a mask to remove obstacles, and generate a safe landing zone. When the distance from the lunar surface is relatively close. Perform motion compensation on the point cloud data detected by the lidar, correct it according to the local gravity direction, and perform voxel grid down-sampling, using morphological progressive filtering and random sampling consistency for plane fitting and external point obstacle collection, extract obstacles in safe flat areas. In the simulated lunar landing test site, the UAV platform equipped with active and passive sensors was used. Based on the principles of physical kinematics and dynamics, the reduction simulation of the obstacle avoidance landing process of lunar descent was carried out to verify the algorithm. The method presented in this paper is able to detect and landing accurately in a safe area in real time, which is shown in the test results.","PeriodicalId":431036,"journal":{"name":"2021 International Symposium on Computer Science and Intelligent Controls (ISCSIC)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123194331","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Active Learning for Text Classification and Fake News Detection 基于主动学习的文本分类与假新闻检测

2021 International Symposium on Computer Science and Intelligent Controls (ISCSIC) Pub Date : 2021-11-01 DOI: 10.1109/ISCSIC54682.2021.00027

Marko Sahan, V. Šmídl, R. Marik

{"title":"Active Learning for Text Classification and Fake News Detection","authors":"Marko Sahan, V. Šmídl, R. Marik","doi":"10.1109/ISCSIC54682.2021.00027","DOIUrl":"https://doi.org/10.1109/ISCSIC54682.2021.00027","url":null,"abstract":"Supervised classification of texts relies on the availability of reliable class labels for the training data. However, the process of collecting data labels can be complex and costly. A standard procedure is to add labels sequentially by querying an annotator until reaching satisfactory performance. Active learning is a process of selecting unlabeled data records for which the knowledge of the label would bring the highest discriminability of the dataset. In this paper, we provide a comparative study of various active learning strategies for different embeddings of the text on various datasets. We focus on Bayesian active learning methods that are used due to their ability to represent the uncertainty of the classification procedure. We compare three types of uncertainty representation: i) SGLD, ii) Dropout, and iii) deep ensembles. The latter two methods in cold- and warm-start versions. The texts were embedded using Fast Text, LASER, and RoBERTa encoding techniques. The methods are tested on two types of datasets, text categorization (Kaggle News Category and Twitter Sentiment140 dataset) and fake news detection (Kaggle Fake News and Fake News Detection datasets). We show that the conventional dropout Monte Carlo approach provides good results for the majority of the tasks. The ensemble methods provide more accurate representation of uncertainty that allows to keep the pace of learning of a complicated problem for the growing number of requests, outperforming the dropout in the long run. However, for the majority of the datasets the active strategy using Dropout MC and Deep Ensembles achieved almost perfect performance even for a very low number of requests. The best results were obtained for the most recent embeddings RoBERTa","PeriodicalId":431036,"journal":{"name":"2021 International Symposium on Computer Science and Intelligent Controls (ISCSIC)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127783230","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 8

Boundary-based Real-time Text Detection on Container Code 基于边界的容器代码实时文本检测

2021 International Symposium on Computer Science and Intelligent Controls (ISCSIC) Pub Date : 2021-11-01 DOI: 10.1109/ISCSIC54682.2021.00025

Kuikun Liu, Cai Sun, Haoyuan Chi

引用次数: 1

An Improved Firefly Algorithm Based on An Attraction Switch 基于吸引开关的改进萤火虫算法

2021 International Symposium on Computer Science and Intelligent Controls (ISCSIC) Pub Date : 2021-11-01 DOI: 10.1109/ISCSIC54682.2021.00070

Jianxun Liu, Jinfei Shi, Fei Hao

引用次数: 1

A Personalized Learning Framework for Software Vulnerability Detection and Education 软件漏洞检测与教育的个性化学习框架

2021 International Symposium on Computer Science and Intelligent Controls (ISCSIC) Pub Date : 2021-11-01 DOI: 10.1109/ISCSIC54682.2021.00032

Maryam Taeb, H. Chi

{"title":"A Personalized Learning Framework for Software Vulnerability Detection and Education","authors":"Maryam Taeb, H. Chi","doi":"10.1109/ISCSIC54682.2021.00032","DOIUrl":"https://doi.org/10.1109/ISCSIC54682.2021.00032","url":null,"abstract":"The software has become a necessity for many different societal industries including, technology, health care, public safety, education, energy, and transportation. Therefore, training our future software developers to write secure source code is in high demand. With the advent of data-driven techniques, there is now a growing interest in leveraging machine learning and natural language processing (NLP) as a source code assurance method to build trustworthy systems. In this work, we propose a framework including learning modules and hands-on labs to guide future IT professionals towards developing secure programming habits and mitigating source code vulnerabilities at the early stages of the software development lifecycle following the concept of Secure Software Development Life Cycle (SSDLC). In this research, our goal is to prepare a set of hands-on labs that will introduce students to secure programming habits using source code and log file analysis tools to predict, identify, and mitigate vulnerabilities. In summary, we develop a framework which will (1) improve students' skills and awareness on source code vulnerabilities, detection tools and mitigation techniques (2) integrate concepts of source code vulnerabilities from Function, API and library level to bad programming habits and practices, (3) leverage deep learning, NLP and static analysis tools for log file analysis to introduce the root cause of source code vulnerabilities.","PeriodicalId":431036,"journal":{"name":"2021 International Symposium on Computer Science and Intelligent Controls (ISCSIC)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129493636","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Research on Method of Fixed Load Aerodynamic Center in the Flight Test for Civil Aircraft 民机飞行试验中固定载荷气动中心方法研究

2021 International Symposium on Computer Science and Intelligent Controls (ISCSIC) Pub Date : 2021-11-01 DOI: 10.1109/ISCSIC54682.2021.00017

Zhi Qiu, Xueliang Wang

引用次数: 0

People-Centric Smart Campus 以人为本的智慧校园

2021 International Symposium on Computer Science and Intelligent Controls (ISCSIC) Pub Date : 2021-11-01 DOI: 10.1109/ISCSIC54682.2021.00055

Ebrahim Alharbi

引用次数: 1

Scaling Time-Dependent Origin-Destination Matrix Using Growth Factor Model 使用生长因子模型缩放时变起点-目的地矩阵

2021 International Symposium on Computer Science and Intelligent Controls (ISCSIC) Pub Date : 2021-11-01 DOI: 10.1109/ISCSIC54682.2021.00021

Fereshteh Asgari, A. Amrani, M. Khouadjia

{"title":"Scaling Time-Dependent Origin-Destination Matrix Using Growth Factor Model","authors":"Fereshteh Asgari, A. Amrani, M. Khouadjia","doi":"10.1109/ISCSIC54682.2021.00021","DOIUrl":"https://doi.org/10.1109/ISCSIC54682.2021.00021","url":null,"abstract":"Demand estimation in public transport is critical for transport stakeholders. Thanks to the emerging technologies in recent years, many sources of mobility data are available to model passengers flow in public transport network. One of the most added-value mobility data is smart card Origin-Destination (OD) data. These data could inform us on when, where and how flows transit within the network. The OD matrix used in this work is obtained from smart card data collected by Automated Fare Collection (AFC) system in the Greater Paris Area which is called Navigo Pass. Despite its immense value, this matrix doesn't cover the entire passenger flow. This is due to fraud, other types of tickets (e.g. the standard paper ticket) and uncertainties in destination estimates. In this paper we propose a two-step approach for correcting and scaling smart card OD matrix based on adapted Growth Factor model considering the complexity caused by temporal variation of the OD matrix. In the first step we map all the OD pairs in the OD matrix over our area of study to infer their departure and arrival stations and time. In the second step we exploit passengers' counting data and use growth factor model to scale the OD matrix to obtain a new corrected matrix which can present the real flow in the transit network. We apply our proposed methodology to scale an OD matrix constructed only from smart card validation data which presents between 40% to 65% of the overall flow. For this purpose, passengers' counting data are exploited.","PeriodicalId":431036,"journal":{"name":"2021 International Symposium on Computer Science and Intelligent Controls (ISCSIC)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124975855","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

ULeaf-Net: Leaf Segmentation Network Based on U-shaped Symmetric Encoder-Decoder Architecture ULeaf-Net:基于u形对称编码器-解码器架构的叶子分割网络

2021 International Symposium on Computer Science and Intelligent Controls (ISCSIC) Pub Date : 2021-11-01 DOI: 10.1109/ISCSIC54682.2021.00030

Jiaqi Sun, Jianyu Zhao, Z. Ding

{"title":"ULeaf-Net: Leaf Segmentation Network Based on U-shaped Symmetric Encoder-Decoder Architecture","authors":"Jiaqi Sun, Jianyu Zhao, Z. Ding","doi":"10.1109/ISCSIC54682.2021.00030","DOIUrl":"https://doi.org/10.1109/ISCSIC54682.2021.00030","url":null,"abstract":"The study of plant phenotypes can help improve crop yields in response to the planet's food resources scarcity. Traditional approaches to plant phenotyping are destructive and require the empirical judgment of experts. To improve efficiency and accuracy, researchers begin to explore the feasibility of the determination of plant phenotypic parameters automatically, which is achieved by precisely segmenting the plant leaf profile. Some deep-learning-based leaf segmentation methods proposed in recent years did not ideally work because they are limited by the quality and size of the dataset and the reasonableness of the network architecture itself. Therefore, a leaf segmentation network based on U-shaped symmetric encoder-decoder architecture called ULeaf-Net is proposed. It replaces the traditional same-layer feature fusion with cross-layer feature fusion and introduces a robust feature extraction structure BasicBlock, and it also uses a patch learning method to expand the dataset size in the training stage for better training of the network. Finally, we compare the leaf segmentation results of ULeaf-Net with UNet. ULeaf-Net has an excellent leaf segmentation capability both in terms of evaluation metrics and intuitively.","PeriodicalId":431036,"journal":{"name":"2021 International Symposium on Computer Science and Intelligent Controls (ISCSIC)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114414208","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Active Scanning in the Industrial Control Systems 工业控制系统中的主动扫描

2021 International Symposium on Computer Science and Intelligent Controls (ISCSIC) Pub Date : 2021-11-01 DOI: 10.1109/ISCSIC54682.2021.00049

Ondrej Pospisil, Petr Blazek, R. Fujdiak, J. Misurec

{"title":"Active Scanning in the Industrial Control Systems","authors":"Ondrej Pospisil, Petr Blazek, R. Fujdiak, J. Misurec","doi":"10.1109/ISCSIC54682.2021.00049","DOIUrl":"https://doi.org/10.1109/ISCSIC54682.2021.00049","url":null,"abstract":"Industrial control systems (ICS) networks have faced challenges in incident detection over the last few years. One of the issues harming ICS networks is the active scanning of such structures. Active scanning can be used in two different key scenarios: either by an attacker causing network damage or by the network owner to explore network hosts and visualize network architecture; in both cases, it can affect ICS network traffic. This paper aims to demonstrate active scanning using two tools (Nmap, Zmap) from the penetration tester's perspective. The penetration tester operation was described in the context of the impact on the failure or the delay of communication in the network. As a part of this work, an industrial testbed was created to analyse the impact of the scanning. While scanning with the Zmap tool, there was a complete loss of communication between the device and the testbed network. On the other hand, the Nmap tool displayed a delay and an occasional network outage. The article then described and visualized the delay and outage data. These results clearly show that it is not appropriate to use active scanners in industrial networks, as they can have a fatal impact on the entire network's communication.","PeriodicalId":431036,"journal":{"name":"2021 International Symposium on Computer Science and Intelligent Controls (ISCSIC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129884066","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4