22 research outputs found
Design of High Performance Multimedia Control System for UAV/UGV Based on SoC/FPGA Core
No full textAbstractThe article deals about design of low cost/small size, high performance multimedia (audio, video) control system intended for usability in mobile AGV or flying UAV. There are presented two multimedia control systems, first one based on SoC device with open source operating system (OpenWrt) for not response critical operation (OS start after reset within 30seconds, it is suitable for ground mobile or underwater devices). The second design is FPGA based without OS only with firmware for camera critical operation (start after reset within 1 second, it is suitable for aerial devices)
Path planning algorithm based on search algorithm, edge detector and GPS data/satellite image for outdoor mobile systems
No full text
Machine learning algorithms implementation into embedded systems with web application user interface
No full textData optimization for communication between wireless IoT devices and Cloud platforms in production process
No full textEmbedded vision equipment of industrial robot for inline detection of product errors by clustering–classification algorithms
No full textThe article deals with the design of embedded vision equipment of industrial robots for inline diagnosis of product error during manipulation process. The vision equipment can be attached to the end effector of robots or manipulators, and it provides an image snapshot of part surface before grasp, searches for error during manipulation, and separates products with error from the next operation of manufacturing. The new approach is a methodology based on machine teaching for the automated identification, localization, and diagnosis of systematic errors in products of high-volume production. To achieve this, we used two main data mining algorithms: clustering for accumulation of similar errors and classification methods for the prediction of any new error to proposed class. The presented methodology consists of three separate processing levels: image acquisition for fail parameterization, data clustering for categorizing errors to separate classes, and new pattern prediction with a proposed class model. We choose main representatives of clustering algorithms, for example, K-mean from quantization of vectors, fast library for approximate nearest neighbor from hierarchical clustering, and density-based spatial clustering of applications with noise from algorithm based on the density of the data. For machine learning, we selected six major algorithms of classification: support vector machines, normal Bayesian classifier, K-nearest neighbor, gradient boosted trees, random trees, and neural networks. The selected algorithms were compared for speed and reliability and tested on two platforms: desktop-based computer system and embedded system based on System on Chip (SoC) with vision equipment
Auxiliary device for accurate measurement by the smartvision system
No full textThe article deals with the design of equipment for accurate measurement or checking linear dimensions using a smart vision system. Commercial smart vision systems can not accurately measure large linear dimensions because the precision of the camera sensor decreases with distance from measured object. The main benefit of the proposed solution is the possibility of continuous measuring in production lines with high precision even for very long dimensions. © 2018, MM publishing Ltd. All rights reserved.APVV-15-0602, APVV, Agentúra na Podporu Výskumu a Vývoja; NPU I LO1303, MŠMT, Ministerstvo Školství, Mládeže a TělovýchovyAgency for Research and Development [APVV-15-0602and, NPU I LO1303]; Ministry of Education, Youth and Sports of the Czech RepublicMinistry of Education, Youth & Sports - Czech Republi
Development of a standardized measure to assess food quality: a proof of concept
No full textBackground: Food-based dietary guidelines are promoted to improve diet quality. In applying dietary recommendations, such as the MyPlate, the number of servings in a food group is the unit of measure used to make food selections. However, within each food group, different foods can vary greatly in their nutritional quality despite often having similar energy (caloric) values. This study aimed to develop a novel unit of measure that accounts for both the quantity of energy and the quality of nutrients, as defined by caloric and micronutrient density, respectively, in foods and to demonstrate its usability in identifying high quality foods within a food group. Methods: A standardized unit of measure reflecting the quality of kilocalories for nutrition (qCaln) was developed through a mathematical function dependent on the energy content (kilocalories per 100 g) and micronutrient density of foods items within a food group. Nutrition composition of 1806 food items was extracted from the USDA nutrient database. For each food item analyzed, qCaln ratios were calculated to compare qCaln to its caloric content. Finally, a case example was developed comparing two plates adapted from the MyPlate. Results: Examples of food items with highest and lowest qCaln ratios were displayed for five food groups: vegetables, fruits/fruit juices, milk/dairy products, meats/meat alternatives, and breads/cereals. Additionally, the applicability of the qCaln was presented through comparing two plates, adopted from the USDA MyPlate, to show differences in food quality. Conclusions: The newly developed qCaln measure can be used to rank foods in terms of their nutrient density while accounting for their energy content. The proposed metric can provide consumers, public health professionals, researchers, and policy makers with an easy-to-understand measure of food quality and a practical tool to assess diet quality among individuals and population groups. © 2016 The Author(s)
