AIMHiGH as an FF4EuroHPC success story
The AIMHiGH project is an experiment that was conducted under the FF4EuroHPC initiative to improve the efficiency and performance of high-performance computing in Europe. The main goal of the engagement was to understand their business challenges and to present an IoT-based poultry farm management solution, supported by a set of sensors for environmental monitoring. The use of HPC and deep learning AI were used to create prediction models that can be deployed on edge devices equipped with camera sensors for use in IoT/AI solutions in the poultry sector.
Several organizations collaborated on the AIMHiGH project. The end-users were the Radinović Company and Meso-Promet Franca, while the University of Donja Gorica, which is part of the NCC Montenegro, provided domain expertise. The ISV for the project was DunavNET, and DigitalSmart provided HPC and AI expertise.
The AIMHiGH project resulted in a new digital farming solution that combines cameras, edge computing, and an IoT platform. The system helped to reduce manual labor costs and chicken mortality rates by 10% and detect disease or abnormalities quicker than before. The technology developed in this project has become a part of the poultryNET platform offering, and there is an opportunity to sell such components to third-party vendors active in the market of smart agriculture solutions.
Overall, the AIMHiGH project demonstrated the potential of artificial intelligence, machine learning, and high-performance computing to develop innovative solutions for the agriculture industry. The project also showcased the benefits of collaboration among different organizations with expertise in various fields.
We invite you to view the video presentation highlighting the AIMHiGH project as one of the success stories of FF4EuroHPC.
Read More
New publication on Botrytis cinerea forecast model
A new paper on Botrytis cinerea forecast modelling has been published in the Journal of Networking and Network Applications (2022). The paper is titled, “Qualitative parameter analysis for Botrytis cinerea forecast modelling using IoT sensor networks’. Botrytis cinerea is a fungus that affects many plant species but attacks wine grapes frequently. The research leading to these results received funding from the European Union’s Horizon 2020 — The EU Framework Programme for Research and Innovation 2014–2020, under DEMETER.
The authors of the publication are Spasenija Gajinov, Tomo Popović, Dejan Drajić, Nenad Gligorić and Srđan Krčo.
Abstract: This paper provides results of an evaluation of a fungal disease Botrytis cinerea forecast model (Model for Botrytis cinerea appearing) in vineyards for qualitative analysis of parameters that affect the development of the disease by using data from a network of connected sensors (air temperature and relative humidity, rain precipitation, and leaf wetness). The fungal disease model used by agronomists was digitalized and integrated into agroNET, a decision support tool, helping farmers to decide when to apply chemical treatments and which chemicals to use, to ensure the best growing conditions and suppress the growth of Botrytis cinerea. The temperature and humidity contexts are used to detect the risk of the disease occurrence. In this study, the impact of the humidity conditions (relative humidity, rain precipitation, and leaf wetness) is evaluated by assessing how different humidity parameters correlate with the accuracy of the Botrytis cinerea fungi forecast. Each observed parameter has its own threshold that triggers the second step of the disease modelling-risk index based on the temperature. The research showed that for relative humidity, rain precipitation, and leaf wetness measurements, a low-cost relative humidity sensor can detect, on average, 14.61% of cases, a leaf wetness sensor an additional 3.99% of risk cases, and finally, a precipitation sensor can detect an additional 0.59% of risk cases (in the observed period the risk was detected in 19.19% (14.61%+3.99%0.59%) of the time), which gives a guide to farmers how to consider cost effective implementation of sensors to achieve good performance. The use of the proposed model reduced the use of pesticides up to 20%
The full paper is available DOI:10.33969/J-NaNA.2022.020305
Read MorepoultryNET case study video presentation
poultryNET is a cloud-based solution for the digital transformation of poultry farms. It provides real-time observations of the parameters of interest and digitized domain expertise enabling farmers to manage all steps in the broiler production while reducing negative environmental impact and respecting animal wellbeing.
The main features provide complete 24/7 insight into poultry barns from monitoring environmental parameters, daily weight and consumed feed and water, to a biosafety guide, costs/revenue calculator and digital assistant in problem solving. Using the poultryNET the environmental conditions, as well as food and water consumption and prepared feed mixture, could be tailored to specific animal needs and production goals. Increased of energy, optimized food and water consumption and better meat quality are the main benefits.
The poultryNET solution is applicable for broiler farms, parental flocks and laying hens.
Case study
Four years ago, we started cooperation with Agroprodukt Šinković company by implementing our digital farming platform for poultry production on their farm. The collaboration continued within the DEMETER project by expanding solutions and setting a basis for a transparent supply chain.
The Agroprodukt Šinković is a Serbian company focused on raising laying hens, parental flocks and day-old chicks for over 20 years. Their annual production is more than 10 million day-old chickens.
The video briefly presents the poultryNET case study – with case study customer Agroproduct Šinković Farm.
Read More
Veštačka inteligencija u srpskom agraru?
Digitalizacija je postala jedan od pojmova koji se najčešće provlači kroz javni sektor. Od kulture, preko školstva, pa do javne uprave, neophodno je da i poljoprivreda postane jedan od stubova digitalizacije Srbije.
Kao rezultat zajedničke saradnje sa kompanijom Telekom Srbija, na jednom mestu se našli Telekomova infrastruktura i DunavNET – ova ekspertiza u oblasti IoT/ML/AI tehnologija, te je stvorena odlična polazna osnova za unapređenje poljoprivredne proizvodnje digitalizacijom.
Pročitajte više u mts blogu posvećenom temi upotrebe novih tehnologija i digitalizacije u poljoprivredi.
Read MoreDEMETER Open Call 2
The Horizon 2020 project, DEMETER, has announced the launch of its 2nd Open Call, DEPLOY, with a total budget of €740,000 available. DEMETER aims to lead the digital transformation of Europe’s agri-food sector through the rapid adoption of advanced Internet of Things (IoT) technologies, data science and smart farming ensuring the industry’s long-term viability and sustainability.
DEPLOY, the second Open Call in DEMETER, aims to increase the outreach of the DEMETER value proposition by funding small consortia of 2-3 partners for the deployment of new, high-value pilots in the agri-food sector. These pilots will focus on employing DEMETER methodologies and technologies, addressing clear farmers’ needs, with a particular focus on EU geographic regions not represented within DEMETER pilots. This will expand the technological and/or business coverage of the project, towards digitalising and boosting the European agrobusiness sector. European countries not covered by DEMETER pilots are Austria, Bulgaria, Croatia, Cyprus, Denmark, Estonia, France, Hungary, Lithuania, Luxembourg, Malta, Netherlands, Slovakia and Sweden.
Twenty pilot projects are currently running in DEMETER to demonstrate and evaluate how innovations and extended capabilities benefit from the interoperability mechanisms. A wide spectrum of sub-sectors: arable crops, irrigated crops, fruit production and livestock (poultry, dairy, animal welfare) are covered. These pilots can be used as an example for potential applicants to develop similar or different pilots to be funded under DEPLOY.
The new pilots to be funded under the DEMETER Open Call #2 – DEPLOY must address specific farmers’ needs and fit into one or more DEMETER challenges and objectives.
Open Call #2 – DEPLOY will fund consortia composed of two or three:
- micro, small, and medium-sized enterprises (SMEs),
- secondary and higher education establishments, research institutes and other not-for profit research entities.
The Open Call closes on the 16th February 2022 at (17.00 CET).
More information on DEPLOY and how to apply is available at www.h2020-demeter.eu/open-call-deploy.
Applications can be made via the F6S platform at www.f6s.com/demeter-open-call-2-deploy/apply
Read MorePigstEYE solution
Within the first ATLAS Demo Day, our product manager Senka Gajinov, presented the PigstEYE, our solution for livestock farm management, exploring the topic of Behavioral Analysis and Management of Livestock.
The first ATLAS Demo Day brought together speakers from the agricultural sector. They explored the benefits of data-driven agriculture using the ATLAS Interoperability Network within a multitude of pilot studies. The event cast light on agricultural challenges and opportunities to overcome these through digital agriculture. It Is organized under the title: “Business Opportunities for Innovative Digital Data-Driven Agriculture”.
PigstEYE is the turnkey IoT/AI solution designed to improve animal welfare on pig farms and improve the overall farm performance. The solution provides pigs’ recognition, calculation of their size, and tracking of their movement. The work done in the PigstEye project will be used as the basis for the creation of a line of animal wellbeing features and features enabling optimization of another process in the value chain. PigstEYE is supported by H2020 ATLAS Project.
The Demo Day was held on November 24, as a virtual event. In case you missed it, you can watch the presentation and learn more about the PigstEYE solution and our involvement in the ATLAS H2020 project here.
Read MoreagroNET in poultry barns
Three years ago, we started cooperation with Agroprodukt Šinković company by implementing our agroNET platform for poultry production on their farm. The cooperation continued within the DEMETER project by expanding solution and setting a basis for a transparent supply chain.
agroNET platform modules for optimizing poultry breeding, both parental flocks and laying hens have been deployed in Agroprodukt’s poultry barns in order to provide real-time insight into environmental conditions and enable animal welfare.
The Agroprodukt Šinković is a Serbian company that has been focused on raising laying hens, parental flocks and day-old chicks for more than 20 years. Their annual production is more than 10 million day-old chickens.
Laslo Šinković, the owner of the company, said: “We are using the agroNET platform for poultry production as a tool for optimization of raising laying hens and parental flocks. The platform brings us 24/7 insight into poultry barns without the need for on-site inspection a few times per day. This allows us to react on time and provide optimal environmental conditions for raising poultry. Additionally, the possibility of comparing our results with technology parameters is very helpful in feed management.”
Future steps will lead to wider cooperation: “We are planning to expand digitization on other parts of our production to be able to optimize inputs and provide transparency of all relevant parameters for our partners, different stakeholders” – explains Laslo.
Watch the interview with Laslo and learn more about their involvement in the DEMETER project.
Read MorePanel Discussion – IoT in Agriculture
Last month, we participated in the 30th Industry 4.0 conference panel. This edition was held as an online event, hosted by FEFA Faculty, Belgrade.
The main theme of the panel was Industry 4.0 and its significance for Serbia, and it was held through four sessions. One session was referred to the application of IoT technology in agriculture. Dr. Srđan Krčo was the moderator.
The panelists were David Blaževski – Fresh AgTech, Dr Vladimir Polaček – Scientific Institute for Veterinary Science, Novi Sad, Gordan Bašić – Association of Grape and Wine Producers Srem – Fruška gora, Spasenija Gajinov – DunavNET, and Dr Milan Dobrota – Agremo.
The whole session on the application of new technologies in agriculture is available on the FEFA YouTube channel.

When wine bottles can tell a story
Counterfeit products and brands are a global problem with tremendous economic and health consequences. Counterfeit in the wine industry is no exception, and wine fraud is a real problem both for wine producers and wine consumers. Recently, our CEO Srdjan Krco, as one of the authors, has published a paper in the Elsevier journal “Internet of Things” on a novel solution for wine counterfeit prevention that can allow consumers to have instant and in-depth access to key product characteristics.
A novel solution for counterfeit prevention in the wine industry based on IoT, smart tags, and crowd-sourced information
Authors: Tomo Popović, Srdjan Krčo, Vesna Maraš, Liisa Hakola, Sanja Radonjić, Rob van Kranenburg, Stevan Šandi
This paper describes a novel solution for counterfeit prevention and brand protection in the wine industry. The presented approach combines Internet of Things, Cloud, and Mobile technologies with the use of custom designed smart tags applied to each bottle of wine in order to provide food track and trace capabilities. The smart tags combine QR code with additional information printed with an invisible photochromatic ink. The tags are activated by flashlight on mobile devices during the scanning. Before scanning, users are prompted to select the context of the wine bottle (in store, sold, consumed) in order to provide additional information about each bottle as it moves through the supply chain. This information is used by the custom-made heuristic to help users and wine makers detect issues with individual instances of the product. The system was implemented as a pilot project that was executed during a period of 6 months. End users showed a great interest in the possibility to implement such a system, consumers liked the interaction with the product using the mobile app and smart tags, while wine makers expressed their interest in the solution. Besides counterfeit that affects profit, the benefits of such systems include improved brand protection and reduced risk of health hazards.
Read more about the paper in the “Internet of Things”, the Elsevier journal.
Read More
SmartTags-enabled for monitoring of the supply chain
Recently, Nenad Gligoric, our senior researcher, together with Suparna De from the University of Winchester has published an article on SmartTags for supply chain monitoring.
Smart Tags are new types of sensors that are printable and can collect, sense, and read environmental parameters of relevance to the product. Their use was developed in one of our previous projects H2020 TagItSmart. For fast-moving consumer goods (FMCG) this represents the basis for the creation of a new generation of supply chains which, in combination with GS1 Digital Link global specifications standard, makes it possible to identify each product item, track it and monitor it on an item level. These capabilities offer opportunities for informed management of assets and innovative consumer engagement by transforming consumer goods into digital assets.
About H2020 TagItSmart project
H2020 TagItSmart project has researched and piloted the use of QR-codes printed with functional inks and printed NFC (Near Field Communication) tags with sensing capabilities to create ‘SmartTags’. The project made solid ground on the research topic and development of the SmartTag technology, which is, because of its simplicity and standardized approach, adopted and used by many industry players.
Environment-reactive SmartTags with Functional Inks
With NFC and RFID (Radio Frequency Identification) solutions proving expensive for consumer-packaged goods, TagItSmart has pioneered the use of dynamic QR-codes that are printed on consumer goods using environmentally reactive inks that change appearance according to selected conditions, e.g. temperature, humidity, light intensity. The growing use of smartphones equipped with cameras facilitates an off-the-shelf solution for scanning the dynamic QR-code information as well as lifecycle tracking of the item through seamless observation measurements of the generated smart tag data. This visual change on the product packaging, as well as individual product identification using the GS1 Digital Link Standard allows not only tracking of every individual item from the factory to recycling, but also enables additional information about the item to be communicated to consumers. This includes visual clues to consumers that a product is at its optimum consumption temperature, monitoring of condition-sensitive goods during transport (e.g. vaccines, meat, and dairy goods), alerts to retailers that an item is close to its best-before date, and also if an item has been properly recycled.
In a nutshell, smart tags open up exciting possibilities for consumer engagement, supply chain tracking, and product recycling.
Use case: SmartTags-enabled Ice cream
The TagItSmart technology can be showcased in numerous scenarios, with an ice cream scenario being noteworthy, due to the possibility to showcase most of the SmartTag’s technology benefits. An irreversible functional ink is used to create the SmartTag, capturing temperatures larger than −10 °C with a timestamp set to 30 minutes. The sensing capability of the SmartTag, supported by the ink, is specifically designed for the ice cream scenario to satisfy specific requirements, as shown in Fig. 1:

The SmartTags are encoded with a QR code to identify and encode the temperature-sensitive property and an image to show the user that the ice cream is good to be consumed. Next, a mobile phone with a web browser is selected as the scanner for the SmartTag. The identifiers for the designed SmartTags are created and the resulting tags are printed.
The next step is to model the objects that will be labeled with the SmartTags, i.e. the ice cream virtual entity, which is achieved through a VE-front end in the platform (Fig. 2). The front end is driven by the VE semantic model.

The user experience with the SmartTags is also an important part of the application development process. It will typically involve how the user is going to scan the SmartTag and how the information generated is going to be used and presented. This is developed as a Web application and integrates the mobile phone scanner and application workflow through the correspondent SDKs and libraries, as shown in Fig. 3.

To ensure the smooth creation of the tags, the TagItSmart project created a semantic model for describing the environment-reactive properties of the QR codes and NFC electronic tags. The model incorporates the materials’ composition of the physical products, the characteristics of the functional ink, such as what environmental conditions it reacts to (e.g. temperature, humidity, time-lapse, etc.), the accompanying relevant state changes (e.g. color and visibility changes), as well as observation measurements together with their spatial description.
Nenad Gligoric is one of the pioneers of the IoT scene in Serbia, working as a software engineer in Ericsson and as a project manager in DunavNET on more than 10 EU, FP7 and H2020 projects. He was one of the technical managers of the H2020 TagItSmart project.
Read More