2020 IEEE 24th International Conference on Intelligent Engineering Systems (INES)最新文献_第2页

Model-oriented control software development of academic autonomous test vehicle 面向模型的学术自动驾驶测试车控制软件开发

2020 IEEE 24th International Conference on Intelligent Engineering Systems (INES) Pub Date : 2020-07-01 DOI: 10.1109/ines49302.2020.9147202

Csaba Hajdu, Á. Ballagi

引用次数: 0

Measurement of outdoor gamma dose distribution with a multicopter 用多旋翼机测量室外伽马剂量分布

2020 IEEE 24th International Conference on Intelligent Engineering Systems (INES) Pub Date : 2020-07-01 DOI: 10.1109/INES49302.2020.9147190

A. Molnár, I. Lovas, Zsolt Domozi

{"title":"Measurement of outdoor gamma dose distribution with a multicopter","authors":"A. Molnár, I. Lovas, Zsolt Domozi","doi":"10.1109/INES49302.2020.9147190","DOIUrl":"https://doi.org/10.1109/INES49302.2020.9147190","url":null,"abstract":"By using geoinformatics methods it is possible to use a non-imaging detector in the conventional sense to obtain a dose distribution image from a specific area. To produce coverage of the area’s planar dose distribution, there is a need for discrete radiation measurements over the area in an even raster and to assign planar coordinates to these measured values. Assuming that the measured radiation does not show a rapid change between the measurement locations, the desired dose distribution coverage can be produced with the interpolation of the measured values. The coordinates of the measurement points can be used to calibrate the coverage. The calibrated and georeferenced coverage is capable of detecting and locating a radiation source hidden or lost in an area. The advantage of the developed method is that measurements can be conducted using a small-sized multicopter, therefore it is cost-efficient and broadly applicable. The flight time of small-sized multicopters is very limited, so increasing the efficiency of the measurement is especially important. Practical comparisons of several methods regarding the measurement procedure were made during the experiments. Similarly, based on measurement experiences, the detector system was developed and tested in three main steps. These improvements have resulted in a detector system with a total weight of 500 grams including a battery capable of operating the detector for at least 120 minutes. The device is capable of detecting an average of 30 events per minute at 0.8ms background radiation. Experiments have shown that the system can significantly detect a source of 300 μSvh with a scan flight at 10m from ground level.","PeriodicalId":175830,"journal":{"name":"2020 IEEE 24th International Conference on Intelligent Engineering Systems (INES)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131789295","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

Rule-based velocity selection for mobile robots under uncertainties 不确定条件下基于规则的移动机器人速度选择

2020 IEEE 24th International Conference on Intelligent Engineering Systems (INES) Pub Date : 2020-07-01 DOI: 10.1109/INES49302.2020.9147191

Z. Gyenes, E. Szádeczky-Kardoss

引用次数: 1

HPV and Cervical Cancer Screening Awareness: A Case-control Study in Nigeria HPV和宫颈癌筛查意识:尼日利亚的病例对照研究

2020 IEEE 24th International Conference on Intelligent Engineering Systems (INES) Pub Date : 2020-07-01 DOI: 10.1109/INES49302.2020.9147177

Ogbolu Melvin Omone, M. Kozlovszky

引用次数: 6

Concept of Energy Efficient ESP32 Chip for Industrial Wireless Sensor Network 用于工业无线传感器网络的节能ESP32芯片的概念

2020 IEEE 24th International Conference on Intelligent Engineering Systems (INES) Pub Date : 2020-07-01 DOI: 10.1109/INES49302.2020.9147189

E. Gatial, Z. Balogh, L. Hluchý

引用次数: 7

Memory Efficient Exact and Approximate Functional Dependency Extraction with ParSIT 基于ParSIT的高效内存精确近似函数依赖提取

2020 IEEE 24th International Conference on Intelligent Engineering Systems (INES) Pub Date : 2020-07-01 DOI: 10.1109/INES49302.2020.9147187

B. Tusor, A. Várkonyi-Kóczy

引用次数: 3

Rayleigh model fitting to nonnegative discrete data 非负离散数据的瑞利模型拟合

2020 IEEE 24th International Conference on Intelligent Engineering Systems (INES) Pub Date : 2020-07-01 DOI: 10.1109/INES49302.2020.9147173

Matej Petrous, Evženie Uglickich

引用次数: 1

Extracting Training Data for Machine Learning Road Segmentation from Pedestrian Perspective 基于行人视角的道路分割机器学习训练数据提取

2020 IEEE 24th International Conference on Intelligent Engineering Systems (INES) Pub Date : 2020-07-01 DOI: 10.1109/INES49302.2020.9147183

Judith Jakob, J. Tick

{"title":"Extracting Training Data for Machine Learning Road Segmentation from Pedestrian Perspective","authors":"Judith Jakob, J. Tick","doi":"10.1109/INES49302.2020.9147183","DOIUrl":"https://doi.org/10.1109/INES49302.2020.9147183","url":null,"abstract":"We introduce an algorithm that performs road background segmentation on video material from pedestrian perspective using machine learning methods. As there are no annotated data sets providing training data for machine learning, we develop a method that automatically extracts road respectively background blocks from the first frames of a sequence by analyzing weights based on mean gray value, mean saturation, and y coordinate of the block’s middle pixel. For each block labeled either road or background, several feature vectors are computed by considering smaller overlapping blocks within each block. Together with the x coordinate of a block’s middle pixel, mean gray value, mean saturation, and y coordinate form a block’s feature vector. All feature vectors and their labels are passed to a machine learning method. The resulting model is then applied to the remaining frames of the video sequence in order to separate road and background. In tests, the accuracy of the training data passed to the machine learning methods was 99.84 %. For the complete algorithm, we reached hit rates of 99.41 % when using a support vector machine and 99.87 % when using a neural network.","PeriodicalId":175830,"journal":{"name":"2020 IEEE 24th International Conference on Intelligent Engineering Systems (INES)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129079444","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

Linear Parameter-Varying Control of a Floating Piston Electro-Pneumatic Actuator 浮动活塞式电动气动执行器的线性变参数控制

2020 IEEE 24th International Conference on Intelligent Engineering Systems (INES) Pub Date : 2020-07-01 DOI: 10.1109/INES49302.2020.9147127

Ádám Szabó, Tamás Bécsi, S. Aradi

引用次数: 1

Development of Point-cloud Processing Algorithm for Self-Driving Challenges 自动驾驶挑战中点云处理算法的发展

2020 IEEE 24th International Conference on Intelligent Engineering Systems (INES) Pub Date : 2020-07-01 DOI: 10.1109/ines49302.2020.9147201

Miklós Unger, Ernő Horváth, P. Kőrös

引用次数: 0