V. Khryashchev, L. Ivanovsky, V. Pavlov, A. Ostrovskaya, A. Rubtsov
{"title":"Comparison of Different Convolutional Neural Network Architectures for Satellite Image Segmentation","authors":"V. Khryashchev, L. Ivanovsky, V. Pavlov, A. Ostrovskaya, A. Rubtsov","doi":"10.23919/FRUCT.2018.8588071","DOIUrl":"https://doi.org/10.23919/FRUCT.2018.8588071","url":null,"abstract":"Convolutional neural networks for detection geo-objects on the satellite images from DSTL, Landsat -8 and PlanetScope databases were analyzed. Three modification of convolutional neural network architecture for implementing the recognition algorithm was used. Images obtained from the Landsat -8 and PlanetScope satellites are used for estimation of automatic object detection quality. To analyze the accuracy of the object detection algorithm, the selected regions were compared with the areas by previously marked by experts. An important result of the study was the improvement of the detector for the class “Forest”. Segmentation of satellite images has found application at urban planning, forest management, climate modelling, etc.","PeriodicalId":183812,"journal":{"name":"2018 23rd Conference of Open Innovations Association (FRUCT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131120539","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}
{"title":"Usage Monitoring Control in Radio Access Network","authors":"E. Pencheva, I. Atanasov","doi":"10.23919/FRUCT.2018.8588098","DOIUrl":"https://doi.org/10.23919/FRUCT.2018.8588098","url":null,"abstract":"Multi-access Edge Computing is a promising research domain in 5G networks, as it is aimed at improving network efficiency by distributing cloud computing capabilities at the network edge. In this paper, we present a new mobile edge service for usage monitoring control. Usage monitoring control is defined as a part of Policy and Charging Control functionality in the core network. Moving the usage monitoring function close to the end user enables efficient control on data traffic. The proposed mobile edge service is described by typical use cases, data model and interface definition. As proof of concept, we propose resource state models as seen by mobile edge applications and platform, which are formally described and verified.","PeriodicalId":183812,"journal":{"name":"2018 23rd Conference of Open Innovations Association (FRUCT)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130692754","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}
{"title":"Expert Group Formation for Task Performing: Competence-Based Method and Implementation","authors":"M. Petrov, A. Kashevnik","doi":"10.23919/FRUCT.2018.8588099","DOIUrl":"https://doi.org/10.23919/FRUCT.2018.8588099","url":null,"abstract":"The problem of searching a group of experts to solve cross-domain problems remains an important problem in many applications. An automated expert search can make human resource management more efficient and reduce the number of problems. The paper presents a method of expert group formation for joint task performing. This method checks each available expert who can participate in task performing and sifts out the least effective of them. During this checking it forms several groups of experts and sorts them by their optimality based on their proficiency level, cost and influence of experts on each other. The method is implemented and approbated in a competence management system developed earlier.","PeriodicalId":183812,"journal":{"name":"2018 23rd Conference of Open Innovations Association (FRUCT)","volume":"112 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128096909","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}
S. Mikhel, Dmitry Popov, Shamil Mamedov, A. Klimchik
{"title":"Advancement of Robots With Double Encoders for Industrial and Collaborative Applications","authors":"S. Mikhel, Dmitry Popov, Shamil Mamedov, A. Klimchik","doi":"10.23919/FRUCT.2018.8588021","DOIUrl":"https://doi.org/10.23919/FRUCT.2018.8588021","url":null,"abstract":"The paper deals with the control strategies advancement for robots with double encoders for industrial applications and human-robot collaboration. It addresses both external force/torque detection, classification the nature of the force applied to the manipulator as well as selection of an appropriate reaction strategy for either human-robot collaboration and technological process execution. In contrast to previous works, the external force is estimated based on the stiffness model and double encoders technology. To estimate the validity of the implemented compliance error estimation and compensation techniques based on the reduces stiffness model additional analyses were done. It showed that a widely used reduced stiffness model for the compliance error compensation is able to compensate about 90% of the end-effector errors caused by the external loading. Proposed control algorithms and reaction strategies were validated by a simulation study and experimental study with a collaborative robot with torque sensors Kuka IIWA LBR 14.","PeriodicalId":183812,"journal":{"name":"2018 23rd Conference of Open Innovations Association (FRUCT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125510782","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}
{"title":"On-Board Dynamic Tour Support System: The Concept and Technological Infrastructure","authors":"N. Shilov, A. Smirnov, M. Petrov, V. Parfenov","doi":"10.23919/FRUCT.2018.8588093","DOIUrl":"https://doi.org/10.23919/FRUCT.2018.8588093","url":null,"abstract":"Modern technologies do not only enable new solutions improving humans life but also change the way of doing business. Together these two factors lead to the appearance of a new, previously unavailable, class of systems called product-service systems. The paper describes the concept and technological framework of a system aimed at context-dependent planning and dynamic adaptation of guided tourist rides in a car based on the usage of car connectivity technologies and cloud-based services. The system is based on the integration of the previously developed by the authors tourist support system TAIS with Ford SYNC Applink.","PeriodicalId":183812,"journal":{"name":"2018 23rd Conference of Open Innovations Association (FRUCT)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128998023","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}
K. Zimenko, M. Afanasev, A. Krylova, S. Shorokhov, Yuri V. Fedosov
{"title":"Motion Profile Control Algorithm and Corner Smoothing Technique for Trajectory Optimization of High-Precision Processing","authors":"K. Zimenko, M. Afanasev, A. Krylova, S. Shorokhov, Yuri V. Fedosov","doi":"10.23919/FRUCT.2018.8588025","DOIUrl":"https://doi.org/10.23919/FRUCT.2018.8588025","url":null,"abstract":"Processing accuracy in instrumental technology has always been of great importance. Producers of Computer Numeric Control (CNC) systems are constantly looking for novel solutions to achieve higher velocities and precision. However, most of the produced software algorithms are inaccessible to the general public. Hence the task to develop sufficient open source software arises. This paper aims to create a trajectory optimization algorithm, including feed rate control and a corner smoothing technique, which will allow effective high-speed and high-precision processing. It is intended to standardize the algorithm for application with both stepper and servo motor driven machines. The developed motion planning method is based on a cosine function to attain a smooth change of velocity that allows for vibration reduction. To achieve smooth corner processing, spline curves are applied to adjust the size and shape of a fillet and thus satisfy the required tolerance and maintain high velocities. The resulting algorithm is programmed and simulation tests are carried out. The final algorithm shows a smooth transition of velocities, which leads to vibration reduction and consequently to minimization of machining error. In corner smoothing the use of parametric curves demonstrates the ability to vary tolerance. As a result, a sufficient motion control algorithm is developed and can be used in CNC software.","PeriodicalId":183812,"journal":{"name":"2018 23rd Conference of Open Innovations Association (FRUCT)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123488029","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}
Ivan D. Zyrianoff, Alexandre Heideker, Dener Silva, C. Kamienski
{"title":"Scalability of an Internet of Things Platform for Smart Water Management for Agriculture","authors":"Ivan D. Zyrianoff, Alexandre Heideker, Dener Silva, C. Kamienski","doi":"10.23919/FRUCT.2018.8588086","DOIUrl":"https://doi.org/10.23919/FRUCT.2018.8588086","url":null,"abstract":"The emergence of a new breed of smart applications requires middleware platforms that enable the rapid development of IoT-based solutions, which can be hosted partially in fog nodes, as well as in a traditional cloud datacenter. Currently, there is no scalable de facto open IoT platform but the European Commission is pushing FIWARE to fill this gap. We analyzed the performance of FIWARE under different platform configurations comparing fog/cloud and cloud-only scenarios for precision irrigation in smart farming. Our results reveal interesting and non-intuitive findings, such as that fog computing does not always improve the overall system performance and in some cases it even makes it worse. Also, the network between the farm and the cloud datacenter causes some unexpected differences between different scenarios.","PeriodicalId":183812,"journal":{"name":"2018 23rd Conference of Open Innovations Association (FRUCT)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123728100","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}
Maxim Sharagin, S. Popov, V. Glazunov, V. Zaborovsky
{"title":"The Method of Modelling Wireless Network Using Telematics Maps","authors":"Maxim Sharagin, S. Popov, V. Glazunov, V. Zaborovsky","doi":"10.23919/FRUCT.2018.8588103","DOIUrl":"https://doi.org/10.23919/FRUCT.2018.8588103","url":null,"abstract":"The paper describes development of the methods and algorithm for predicting telematics on the vehicle’s route. Described data management technology on global and local wireless networks, provides methods for managing data on the telematics environment, implemented a prototype of the data management subsystem. The time dependencies of the execution of queries are analyzed depending on the amount of data for the data warehouse on board the vehicle and for the cloud service. The result of the work is recommendations for developing connection management methods in wireless multiprotocol networks on vehicle devices. The paper describes the result of the development and research methods for predicting the telematics environment, for obtaining and analyzing the temporal characteristics of their functioning from global and local telematic maps.","PeriodicalId":183812,"journal":{"name":"2018 23rd Conference of Open Innovations Association (FRUCT)","volume":"104 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127961996","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}
{"title":"On the Data Freshness for IoT Traffic Modelling in Real-Time Emergency Observation Systems","authors":"Kemal Cagri Serdaroglu, S. Baydere","doi":"10.23919/FRUCT.2018.8588029","DOIUrl":"https://doi.org/10.23919/FRUCT.2018.8588029","url":null,"abstract":"Internet of things (IoT) and fog computing based observation systems are gaining more importance as Internet becomes the main infrastructure to augment the pervasiveness in remote monitoring of the physical world. Considering the explosion in the number of connected “things”, the increase of data traffic density on interconnection devices (i.e., IoT gateways) becomes an important problem for scalable real-time emergency detection and monitoring. Thus, data traffic analysis and modeling of fog services become an important research area to get more insights into real-time behavior of such systems. The outcomes of such analysis are important for prediction of IoT system behavior in a given network topology. In this paper, we elaborate on an architectural solution for periodic data acquisition from a wireless sensor network(WSN). To this end, we propose a publish/subscribe (P/S) based observation scheme which simultaneously interconnects clients to different kind of sensor devices over a fog layer service. Then, we examine the data freshness which is a critical traffic modeling parameter for real-time emergency observation. With using such scheme, we devise an analysis for understanding the behavior of the overall system in the context of data freshness. The results obtained from our experimental setup illustrate the appropriateness of freshness time calculation methods for obtaining the required service quality.","PeriodicalId":183812,"journal":{"name":"2018 23rd Conference of Open Innovations Association (FRUCT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114814299","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}
{"title":"Decision Support System for Drivers & Passengers: Smartphone-Based Reference Model and Evaluation","authors":"A. Kashevnik, I. Lashkov","doi":"10.23919/FRUCT.2018.8588072","DOIUrl":"https://doi.org/10.23919/FRUCT.2018.8588072","url":null,"abstract":"Last years, decision support systems brought a lot of new possibilities for the people. Developing such technologies as context-aware recommendations, personification, cloud computing allows to support vehicle drivers and passengers in their trips. Decision support systems for vehicle drivers and passengers allows one to provide context-based personalized recommendations based on determined situation in the vehicle cabin and location region as well as driver preferences. For example, during the trip the driver can be notified about the interesting places. If the system determines the dangerous state it generates recommendations for the driver to predict the emergency situation. The paper presents a reference model of the decision support system, describe the dangerous state identification scheme, and discuss evaluation.","PeriodicalId":183812,"journal":{"name":"2018 23rd Conference of Open Innovations Association (FRUCT)","volume":"220 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124254732","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}