Tomo Popovic | University of Donja Gorica, Podgorica, Montenegro (original) (raw)

Papers by Tomo Popovic

2020 9th Mediterranean Conference on Embedded Computing (MECO), 2020

This Viticulture has always, by definition, been a "precision" production: detailed knowledge of ... more This Viticulture has always, by definition, been a "precision" production: detailed knowledge of not only individual vineyards, but also each grapevine individually, provided detailed programming of work operations and production factors adapted for each parcel individually or, better said, for each part of a single parcel. The spatial variability of a particular vineyard can be due to any difference in any element or property for each of the natural, biological, agronomic factors which influence vine performance and the expression of grape and wine characters. This research is aimed at developing methods to quantify temporal variability observed within vineyards and to use data processing tools to assist wine producers and viticulturists to control, analyse and make decisions from so-provided information. Combining the technologies and methodologies will allow wine growers to improve and optimize production systems by taking into account technical and economic aspects of management as well as environmental issues at an intra-parcel (sub-block) level

2022 26th International Conference on Information Technology (IT), 2022

The food market is changing dramatically in the last century as the world population is growing w... more The food market is changing dramatically in the last century as the world population is growing with the unprecedented pace. The wine industry is recognized as part of both agriculture and food industry, but also as a commodity. Developments in information technology and digitalization are playing a major role in the introduction of new solutions in agriculture and food production. The idea is to improve productivity of farms and vineyards, improve quality of agriculture products by optimizing irrigation, pesticide usage, and overall efficiency of the process. Furthermore, the consumer awareness about food products, its quality and origin, is on the constant rise. The information about the product throughout the whole “farm-to-fork”, or in this case “vineyard-to-glass”, value chain needs to be collected and utilized by all the participating stakeholders, in order to get a better, healthier, and more affordable product. This paper address the considerations related to implementation of a blockchain-based transparency and data provenance in the food value chain, more specifically with a focus on the wine industry.

2021 29th Telecommunications Forum (TELFOR), 2021

The use of artificial intelligence, machine learning, and deep learning is finding its purpose in... more The use of artificial intelligence, machine learning, and deep learning is finding its purpose in various fields nowadays. This paper describes a study in which Internet of Things and deep learning are used to implement human activity detection based on data collected from bracelet equipped with Bluetooth transmitter. The main focus of the study was development of a prediction model using deep learning that would help elderly people and their caretakers. Time series data about elderly people activity was collected from bracelet using a Bluetooth gateway and IoT platform, and later annotated based on the activity logs they kept in a form of diary. A neural network is trained to classify data into two groups (binary classification problem) corresponding to activity of the person wearing the bracelet. Initial study shows promising results of the presented approach for the use in human activity detection for elderly.

2019 8th Mediterranean Conference on Embedded Computing (MECO), 2019

The precision viticulture is unique in its emphasis on vineyard management according to local var... more The precision viticulture is unique in its emphasis on vineyard management according to local variation of agro biological conditions, and in its use of science and technology to accomplish this aim. To achieve a particular goal of improved yield and quality in vineyard management, it is essential to understand the impact of plant–soil–water dynamics at different phenological growth stages of the plant physiology. Irrigation system is one of the most important factors for successful agricultural production. Contemporary plant production is based on the better utilization of water per unit area, i.e. to achieve as much yield as possible, while reducing the amount of invested resources (water, fertilizers). The paper presents the results of research carried out within the company 13. Jul Plantaže and the use of irrigNET system in order to optimize irrigation of vines. At several micro localities with different vine varieties, 28 sensor devices have been installed on the Ćemovsko field to monitor moisture dew in the soil at different depths. Finally, for each micro locality, the values of the field moisture capacity were determined, all for the purpose of more precise scheduling of the irrigation and irrigation norm.

2022 IEEE International Conference on Omni-layer Intelligent Systems (COINS)

Tehnicki Vjesnik-technical Gazette, Dec 14, 2015

Subject review This article presents a case study of adopting the Scrum process for Java developm... more Subject review This article presents a case study of adopting the Scrum process for Java development using tools coming from the open source software world. The approach is focused on small to medium sized software enterprises, which can sometimes be intimidated by the introduction of formal processes and quality management systems. The paper describes agile practices, Scrum process, and tools selection aimed at software development using Java. Each selected tool is described and put into the context of the Scrum process and implementation of a quality management system. The paper introduces ISO 9001:2008 standard and discusses benefits of the implementation of a quality management system. Finally, the case study illustrates how the selected tools and Scrum artefacts can be used for the adoption of a quality management system, which leads to a successful ISO 9001:2008 certification.

This paper presents the evaluation of a fungal disease forecast model in vineyards for qualitativ... more This paper presents the evaluation of a fungal disease forecast model in vineyards for qualitative parameter analysis using the data from off the shelf sensors, i.e. temperature and air relative humidity, rain precipitation, and leaf wetness. The rules for the fungal disease models are digitalized as a decision support tool that serve as an indicator to farmers for the need of spraying of the chemical substances to ensure the best growing condition and suppress the level of parasites. The temperature and humidity contexts are used interchangeably in practice to detect the risk of the disease occurrence. By taking into account a number of influences on these parameters collected from the shelf sensors, new topics for research in the multidimensional field of precision agriculture emerge. In this study, the impact of the humidity is evaluated by assessing how different humidity parameters correlate with the accuracy of the Botrytis cinerea fungi forecast. Each humidity parameter has i...

2021 11th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS), 2021

The spot price prediction for the electric energy markets is a widely approached problem, used by... more The spot price prediction for the electric energy markets is a widely approached problem, used by many participants in the market. The ever-shifting rules and regulations, rising percentage of the electricity on the market being produced by solar and wind plants and many stochastic factors influencing it make the market price of electricity very volatile and hard to forecast. Many methods are used to tackle this problem, and their efficiency varies from dataset to dataset. In this work, we use the dataset of hourly day-ahead spot prices from the Hungarian HUPX market, and couple it with weather data for Hungary. We test various types of Dense, Recurrent and Convolutional neural network architectures and report on the results.

The paper discusses collection and utilization of IED-recorded substation data in an automatic wa... more The paper discusses collection and utilization of IED-recorded substation data in an automatic way. It focuses on adding new automated functions built on the top of the substation IED database. There are several types of modern IEDs used in today’s substations. Different file formats and data collection strategies are provided by different vendors. The paper addresses the issue of integrating IED data collected by different IED types and then focuses on how to use the integrated substation data. Several new analysis functions can be performed on the collected IED data and the results of the analysis can serve different groups of users. The paper introduces four newly created and implemented analysis functions. The new functions include automated analysis of digital fault recorder data, digital protective relay data, and circuit breaker monitor data. In addition, a high-level analysis function that performs system-wide fault analysis and fault location is described. This high-level f...

Electric Power Systems Research, 2015

ABSTRACT In this paper, a real-time tool to detect transmission line relay mis-operation is imple... more ABSTRACT In this paper, a real-time tool to detect transmission line relay mis-operation is implemented. The tool uses time-synchronized measurements obtained from both ends of the line during disturbances. The proposed fault analysis tool comes into the picture only after the protective device has operated and tripped the line. The proposed methodology is able not only to detect, classify, and locate transmission line faults, but also to accurately confirm whether the line was tripped due to a mis-operation of protective relays. The analysis report includes either detailed description of the fault type and location or detection of relay mis-operation. As such, it can be a source of very useful information to support the system restoration. The focus of the paper is on the implementation requirements that allow practical application of the methodology, which is illustrated using the field data obtained the real power system. Testing and validation is done using the field data recorded by digital fault recorders and protective relays. The test data included several hundreds of event records corresponding to both relay mis-operations and actual faults. The discussion of results addresses various challenges encountered during the implementation and validation of the presented methodology.

2022 21st International Symposium INFOTEH-JAHORINA (INFOTEH)

Introduction Topological characterizati... more Introduction Topological characterization of the Retinal microvascular nEtwork visualized by portable fuNDus camera (TREND) is a database of digital color eye fundus images created by medical professionals of the Faculty of Medicine of the University of Montenegro in 2020. Purpose 1) to provide a standard that defines normal retinal anatomy and microvascular geometry as it appears when visualized by the portable fundus camera 2) to help the development of new methods for stratification of the risk for the development of various eye diseases, as well as systemic diseases that affect microvasculature 3) to aid the development of biomarkers of accelerated aging 4) to provide a standard that can be used to develop software for segmentation of retinal microvasculature, grading the quality of retinal digital images, and computer-aided diagnosis of systemic and chronic diseases. All color digital images were acquired with a hand-held portable, non-mydriatic MiiS HORUS Scope DEC 200 with 45º FOV and 2560 X 1920 pixel resolution. Data The TREND public database contains 72 color fundus images of healthy young subjects. Each image is associated with a corresponding binarized image of the manually segmented microvascular network. A set of poor quality images is also included. For comparison of the microvascular geometry, an additional set of 10 digital color fundus images of older healthy subjects is included. Each of these images has its corresponding segmented image. In addition, and a set of low quality images captured on healthy older subjects is also included. Files: 1_HEALTHY YOUNG RAW_GOOD QUALITY (72 images in tif format) 2_HEALTHY YOUNG SEGMENTED (72 images in png format) 3_HEALTHY YOUNG RAW _BAD QUALITY (14 images in tif format) 4_HEALTHY OLD RAW_GOOD QUALITY (10 images in tif format) 5_HEALTHY OLD SEGMENTED (10 images in png format) 6_HEALTHY OLD RAW_BAD QUALITY (8 images in tif f [...]

2018 23rd International Scientific-Professional Conference on Information Technology (IT), 2018

Counterfeit wine presents a significant issue for winemakers since it affects producer's repu... more Counterfeit wine presents a significant issue for winemakers since it affects producer's reputation, profit and most importantly it can be harmful for the consumers. This paper describes a brand protection and anti-counterfeiting solution for wine industry based on smart tags and Cloud enabled technologies. The main idea behind smart tags is to utilize quick response codes and functional inks supported by the Cloud system and two-way communication between the winemaker and end-user. The proposed system is expected to make wine counterfeiting hard and unprofitable.

2020 24th International Conference on Information Technology (IT), 2020

One of the most interesting enabling technologies for digital transformation is computer vision. ... more One of the most interesting enabling technologies for digital transformation is computer vision. Object and character recognition has already become very popular and it is used in everyday life. This research focuses on the use of computer vision to read serial numbers from wine labels in order to enable applications based on tracking and tracing of each individual wine bottle. After experimenting with several OCR tools, an open source software called Tesseract OCR engine was selected for the pilot solution. The paper discusses the implementation and image processioning that improved detection accuracy. The coding was done in the Python programming language. The solution code was tested using real-life like images of wine serial numbers. In addition, a custom built web-based evaluation tool was created and used for the interactive evaluation of the system.

2016 24th Telecommunications Forum (TELFOR), 2016

pyPMU is an open source Python package library that implements the IEEE C37.118 standard protocol... more pyPMU is an open source Python package library that implements the IEEE C37.118 standard protocol for synchrophasor data transfer. Synchrophasor measurements provide a precise and time-synchronized phasor measurements collected throughout power grid. The pyPMU library offers various functions for supporting synchrophasor applications and it enables rapid synchrophasor test bed implementations. The paper provides detailed overview of the pyPMU package, its installation, and usage examples. The most interesting use scenarios include PMU simulator and PMU data stream splitter, which have been described in the paper. The discussion illustrates initial benchmarking results and current issues. Finally, the paper outlines future work on the improvements and practical applications. The pyPMU project is published under 3-clause BSD license and made available at GitHub.

IEEE/PES Transmission and Distribution Conference and Exhibition