Europe Union



World-class technology, the combined expertise of 65,000 employees and operations in 56 countries have made Thales a key player in keeping the public safe and secure, guarding vital infrastructure and protecting the national security interests of countries around the globe.


Thales products comprise many components that the company buys from a large variety of partners. The goal was to develop a platform that stores all documentation of components, suppliers of individual components and replacements. The company was looking for a partner that has experience in the development of enterprise architecture. There were 3 main goals for the project implementation:

  • R&D, which was supposed to help in the choice of technology,
  • Proof of concept activities,
  • Development of Product Lifecycle Management.


The general concept of the DPF is the following: for every business process that handles product-related data, the DPF offers an access point (interface) for a human in charge of this business process. The product-centric DPF interface enables that human user to accomplish the necessary data-handling tasks if needed, reaching across the private data structures of different companies that are part of the supply network for that product. DPF provides a separate user interface for every processes or sub-process, which allows for a separation of concerns and provides a security measure. DPF architecture distinguishes between two types of companies in the supply network for a product: the OEM company, which is the company that owns the product that is the central object of the supply network, and the Manufacturer(s) companies that are the suppliers of parts for that product.


The project has been divided into four stages.

The first phase consisted of collecting the requirements, which was the responsibility of the Thales team. For this purpose, we talked with product-owners, procurement, SCM, and change management. The set of requirements was then discussed with the DAC to make the functional requirements.

Research and architecture.

The next stage is the analysis of available technologies, research and the first proof of concepts. Architecture development and selection of technological stack.

Development and testing.

In the next stage, the time came for the development and testing of a developed solution. DAC developed an architecture to integrate cloud solutions, in which PLM partner systems were embedded. One of the assumptions was to use Arrowhead Framework, currently curated by Eclipse Foundation, Industrial IoT automation, and interoperability framework.


We are currently developing a Whitepaper in collaboration with DAC scientists and engineers to promote this innovative approach. The Whitepaper should be available in late 2019 and early 2020. We will present the solution at industry 4.0 conferences and trade fairs.

Delivered value.

The main goal has been achieved: a working prototype that demonstrates the performance of Product Lifecycle Management. The development of a functional demonstrator was crucial for the further development of the project.

The DPF in Budapest at the Productive 4.0 conference related to Industry 4.0, digital production, etc., where the domain experts had the opportunity to review and give feedback on our tool.

Used Technologies.

Arrowhead 4.1

A data-space-enabled collaborative product life cycle and supply chain management. Developed in cooperation with Thales, Digital Product Footprint integrates distributed PLM systems, operated by different parties in a multi-stakeholder ecosystem, to furnish visibility of product and component dependencies across the value chain. By encompassing all data items relevant for managing all aspects of a product, DPF supports the bidding process, product configuration, and change management.

DigiTrac is a system built on the concept of Digital Product Footprint (DPF) developed by the engineers at in collaboration with THALES, Netherlands. It is based on three core viewpoints: a product-centric, a business process-centric, and an end user-centric approach to product management, i.e., it considers business processes and the people in charge of them to be the essential parts of product management.

The DPF may be seen and explored using the system. It provides a graph description of all the pieces used to build an item (for example, a car) together with all the information such as the original manufacturer, manufacturing date, maintenance, repair history, and so on. It is already being used in the transportation industry.

DigiTrac is a functioning prototype that exhibits the effectiveness of Product Lifecycle Management and can be customised for use in various industries. DigiTrac was showcased at the Productive 4.0 Industry 4.0 conference, receiving an excellent response.

State of the art.

The concept of a Digital Product Footprint is the result of a problem-solving process in which the management of a product, as a primary business process for a product owner (who is not a customer/owner), is revisited because existing solutions in terms of process descriptions and underlying tools and methods have eroded and become less performant because of the following trends: Digital Transformation, Smart Industry, Smart Industry++, Realisation of Industrial Internet of Things.

As a result of adopting the view that the creation and use of a man-made product must be trackable and traceable, in all required detail, via data in the digital domain (or the virtual world of digital data, or however you want to describe it), we face the challenge of defining and implementing an all-inclusive set of digital data items that together and in part describe all aspects of a product over its entire lifecycle (i.e. from its conception to its decommissioning and destruction).

Thales products are made up of several components that the firm obtains from a wide range of suppliers. The purpose was to create a platform that keeps all component documentation, providers of individual components, and replacements. The organisation searched for a partner with experience in enterprise architecture development; this is where came in to expand the state-of-the-art.


Thales products comprise many components that the company buys from a large variety of partners. The goal was to develop a platform that stores all documentation of components, suppliers of individual components and replacements. The company was looking for a partner that has experience in the development of enterprise architecture. There were 3 main goals for the project implementation:

R&D, which was supposed to help in the choice of technology

Proof of concept activities

Development of Product Lifecycle Management

The Solution: How does it work?

The DPF’s main principle is as follows: for any business process that handles product-related data, the DPF provides an access point (interface) for a human in charge of that business process. The product-centric DPF interface lets that human user do the essential data-handling operations, reaching across the proprietary data structures of multiple organisations that are part of the product’s supply network. DPF offers a different user interface for each process or sub-process, allowing for concern separation and security.

Personalised product interface for Data Analytic.

DigiTrac, facilitated by Data Space, enables a collaborative product life cycle and supply chain management. It connects distributed PLM systems run by many parties in a multi-stakeholder ecosystem to provide visibility of product and component interdependence across the value chain. DPF helps the bidding process, product configuration, and change management by incorporating all data items necessary to control all elements of a product.

DigiTrac provides access to an anonymised representation of an existing complex product involving a multi-stakeholder supply network and spanning as many lifecycle phases as possible, supplemented with other data items to cover another business process involved in DPF management, namely the Logistics process. As a result, the DPF will enable access to a wide range of data items, including design data (software, hardware, and mechanical parts), manufacturing data, supplier data, supply and logistics process and network data, and data on the product’s operating performance, maintenance, and support. This product’s change processes will comprise a variety of small and significant effect events, such as a mid-life update, ownership change, export limitations, obsolescence management, and supply network changes.

DAC Logo


The general concept of the DPF is the following: for every business process that handles product-related data, the DPF offers an access point (interface) for a human in charge of this business process. The product-centric DPF interface enables that human user to accomplish the necessary data-handling tasks if needed, reaching across the private data structures of different companies that are part of the supply network for that product. DPF provides a separate user interface for every processes or sub-process, which allows for a separation of concerns and provides a security measure. DPF architecture distinguishes between two types of companies in the supply network for a product: the OEM company, which is the company that owns the product that is the central object of the supply network, and the Manufacturer(s) companies that are the suppliers of parts for that product

Estimate your project.

Just leave your email address and we’ll be in touch soon
ornament ornament

Case Studies.

About the client

  • Name: Swiftly 
  • Line of business: Automated Recruiting and Unbiased Recruitment tools
  • Founding year: 2020
  • Country: Sweden

Problem overview

Swiftly, a Stockholm-based startup, grappled with two significant challenges within their job portal. Firstly, accurate categorization of job listings posed difficulties, leading to suboptimal user experiences and ineffective job matching. Secondly, the manual job application process was time-consuming and resource-intensive, restricting scalability.

Proposed solution

Our approach comprised two pivotal components:

  • Web Scraping Tool: We developed a sophisticated web scraping tool to extract precise keywords from job listings, enhancing categorization accuracy.
  • SOTA Presentation: We created a visionary state-of-the-art (SOTA) presentation, demonstrating automated field auto-fill capabilities to streamline the application process.

Applied technologies:

  • Python, Selenium and FastAPI were used to implement a service able to scrap form fields from a given website, and to fill automatically the forms once the data are provided
  • Neo4J and PostgreSQL were databases used for storing graph data describing relations between job offers, job seekers and other data which can be used to look for mutual associations, as well as more general and structured metadata of job offers.
  • Sklearn was used to implement a recommendation engine looking for best matches between job seekers and job offers.

Pre-existing Challenges:  

Before implementing the SOTA and POC solutions, Swiftly faced several challenges:
  • Inaccurate Categorization: Swiftly encountered difficulties in accurately categorizing job listings, causing mismatched job offers and candidates.
  • Manual Application Process: Manual application processes consumed time and resources, impeding scalability.
  • Insufficient Automation: The absence of automated keyword extraction led to imprecise job listing categorization.
  • Scaling Issues: Manual processes and categorization limitations hindered scalability.
  • Lacking Technological Strategy: Swiftly lacked a comprehensive technology-based strategy to enhance categorization accuracy and streamline processes.

Implementation Approach.

Our implementation strategy followed these steps:
Initial Talks and Kickoff

Collaborative discussions between Swiftly’s leadership and’s technical team laid the groundwork for a productive partnership, aligning expectations and goals.

Team Composition

An 8-person team, comprising ML Engineers, Embedded Systems Engineers, Data Scientists, and Fullstack Developers, came together to tackle the project.

Agile Collaboration

Daily stand-up meetings and ongoing communication facilitated iterative development and enhancements.

Results and Impact:

The project concluded with the creation of an advanced SOTA solution that effectively addressed Swiftly’s challenges. This solution improved job listing categorization precision and streamlined the application process. The SOTA also offered a proof-of-concept for refining job listing keywords and automating application field population.


Swiftly’s collaboration with resulted in the successful resolution of their job portal challenges through the implementation of innovative automation solutions. The web scraping tool and the SOTA presentation highlighted the potential of technology to enhance processes, elevate user experiences, and pave the way for future enhancements.


Key numbers

  • Project Duration: Successfully completed within 16 days!

Estimate your project!

Let’s revolutionize your customer experience together. Get in touch today!
ornament ornament

Check other case studies:

Our Client

  • Name: MuuMap
  • Line of business: Software for the dairying industry
  • Country: Poland




The client noticed that the dairy industry was heavily reliant on traditional practices, leading to inefficiencies. Recognizing the opportunity for improvement, the client aimed to create a digital system that could streamline milk delivery management and procurement processes.

Solution’s team collaborated closely with the client to create a comprehensive end-to-end product. We decided together on the features and improved the concept collaboratively.

Which technologies have we applied:

The team and our approach to the project.  

The team comprised a Product Owner, 3 backend developers, 2 frontend developers, a UI/UX designer, and 1 tester. As the project required, the team size was adjusted accordingly, growing when new functionalities were needed and scaling down during lower business demand. 

To accommodate the complex and evolving nature of the system, we opted to work in a Time and Materials model. This approach provided the necessary flexibility and responsiveness to adapt to the project’s changing needs over time.

The begin of the journey

  • It all started with a navigation tool for the drivers. The client noticed that new drivers faced challenges navigating through the 3000 dairy farms. They needed details about accessing area premises, locating milk tanks, and gate openings. Typically, new drivers spent two months riding along with experienced drivers to learn the routes, and even then, they would call dispatchers or other drivers for directions to specific farms.
  • To address this, we collaborated with the client and developed a solution. We placed location pins on the map for each farm’s milk cooling station and, if needed, “drew” a new road. This helped drivers get precise route plans, accurate directions, and essential information about the yards they visited.
  • The success of this application reduced driver training time from two months to just 2-3 days.
  • Later, the Manager module was created, serving as a massive CRM system. It holds vast amounts of information about farmers, their milk deliveries, drivers, license expiration dates, available fleet, subcontractors, destination points, and daily production demand. This comprehensive tool provides an all-encompassing overview of the entire dairy operation.
Review Quote
We’ve been collaborating with for many years, and truth be told, we co-created MuuMap together. The success we’ve achieved is undoubtedly a result of this partnership. is a trusted partner and our number one choice.
Adam Strużyński
Product Manager of MuuMap

MuuBox – an answer to how to optimize a delivery process


As we continued to enhance the system, the client recognized the need to optimize the milk delivery process further. To achieve this, our team introduced automatic route planning algorithms, which revolutionized how routes were planned for the drivers. Instead of relying on manual decision-making, the system could generate the most efficient routes based on various factors like delivery locations, vehicle capacity, and traffic conditions. This saved time, reduced fuel consumption, and improved overall operational efficiency.


Additionally, we sought to digitize and simplify the process of documenting milk quantities at each farm. To accomplish this, we developed electronic devices called MuuBox. These devices were installed in milk tankers and are responsible for uploading data in real time to the MuuMap system.


Previously, the milk collection process involved a lot of manual work for the drivers. They either had to use handwritten protocols to record the quantity of milk collected at each farm or print bulk receipts from their route, which had to be manually entered into the computer. This manual data entry was a time-consuming and labor-intensive task. For instance, entering 3000 positions manually required significant effort.

However, with the implementation of our solution, this manual process was digitized and streamlined. The collected pick ups data is now automatically aggregated in our system and allows integration with others. This automation significantly reduced the need for manual data entry, resulting in fewer errors than the previous approach.


By automating the data entry process, MuuBox significantly reduced the administrative burden on both drivers and the milk collection department. Instead of being the source of mistakes, the department can now focus on correcting errors.

See how we adapted IoT in the MuuMap system.

Visit the website

We are aware of different customer needs

For those MuuMap clients who preferred not to use the MuuBox devices, we introduced a manual entry functionality directly on their tablets. With this option, they could input the milk quantities manually. The advantage of this approach was that it eliminated the need for paperwork while ensuring accurate data recording. Just like with the MuuBox integration, the collected data from the manual entries were uploaded in real-time to the MuuMap system, streamlining the process and ensuring seamless data management.

Review Quote
The product quality is phenomenal, and all of my expectations have been met.
Adam Strużyński
Product Manager of MuuMap

From manual to autonomous milk reception

  • The latest module created is for milk reception at the plant. During inspections, officials present a purchased product with a QR code, requesting documentation for that product. That’s when a manual paperwork process begins.
  • The quality control department employee needs to search for the delivery from that day and then look for the specific delivery to that particular tank. Only then can they find the precise time the milk from different routes was collected in that tank. This process can be time-consuming and prone to errors due to the manual nature of the documentation.
  • Now, with the newest module, MuuMap continues to be involved in the process beyond milk delivery to the gate. The customer supports weighing the truck upon entry, documenting laboratory tests, and recording the destination tank where the milk is pumped or stored.
  • After the truck leaves the plant, it is weighed again, providing valuable information on the actual milk quantity received compared to the declared amount. Based on this data, MuuMap’s application generates a digitized route report, allowing easy traceability of the milk’s journey, including the specific day, routes, and suppliers contributing to each tank.

The results of the dairy revolution

Thanks to the application, the client became a pioneer in the market by offering a tool specifically designed for the traditional dairy industry. The unique and efficient solution attracted the first customers, who loved it and spread positive reviews. As a result, the client’s reputation grew, and more and more people started using the application. Eventually, it captured a significant portion of the Polish dairy market, securing a dominant position with a 30% market share.


27600 Farmers

677 Road Tankers

30 Dairy Plants

1175 Drivers

650 Devices

Over 5 billion liters

34,30% in Poland
3,48 % in Europe

Estimate your project!

Let’s revolutionize your customer experience together. Get in touch today!
ornament ornament


Enelion is a manufacturer of electric car chargers and ecosystem management software for electromobility. The company has been designing electronics and manufacturing equipment in Poland since 2016 and has delivered several thousand chargers to customers at home and abroad. Enelion is also developing charger network management software to provide operator and charging service providers. In addition to foreign customers, Enelion cooperates in the Polish market with PGE, Tauron, Energa, Polenergia, and Greenway.
Experience we shared
Efficient Systems Data management
Software integration

Customers’ business goals

The simple provision of chargers to tenants and billing of energy consumed in the administration system.

Optimal use of available power in the building.

Protection against network overload in an office building or parking lot.


A search for users optimization

Here we have used PostgreSQL algorithms (ltree) for representing labels of data stored in a hierarchical tree-like structure.

Closest stations search optimization

We have employed a PostGIS, a spatial database extender for PostgreSQL object-relational database. It supports geographic objects allowing location queries to be run in SQL.

Communication between applications and queuing

We have deployed an open-source message broker, RabbitMQ, which can be deployed in distributed and federated configurations to meet high-scale, high-availability requirements.

Hardware management integration between apps

The goal was to provide remote access to the status of the charger but also to allow users and end-users to control the charger, e.g., switch it on/off remotely. Both groups are using different apps to perform these activities. Our team accessed the chargers software backend and conducted the integration from that level.

Process software development team has been working together with the client’s team. The work has been aligned with the scrum methodology.

Delivered value:

  • A search of charging stations,
  • Chargers booking,
  • Payments monitoring,
  • Integration of the platform with end users’ mobile app,
  • Remote control over the charger stations (start/end, status),
  • Users division (Operators & Charging Service Providers) and access level control.

The system allows dividing the network into smaller operators, who will only have access to their devices. Charging Service Providers can check the status of the charging station. Thanks to the connection with the Enelink system, most of the maintenance activities will be performed remotely. Another feature was setting up a charging plan that will limit the station’s power at the right time if the Service provider chooses several Operators. All charging stations can be labeled. This makes it easier for Service Provider to manage the stations from a given label. Then, information about the stations’ availability can be easily shared with end-users in a few clicks.

Dynamic Tariff solution gives an attractive offer for each end-user, encourages them to charge in specific places, and introduces discount coupons and VIP programs. Entering tariffs helps Service Providers optimize earnings at charging stations.

Used Technologies:

rabbit mq
Flask Framework

Are you interested in solutions for electromobility?

Just leave your email address and we’ll be in touch soon
ornament ornament


Sports Computing
Sports Computing combines the best of both worlds – a high-tech app based on AI with motion tracking and football. Changing the way we train, stay active and share our love of the sport, Sports Computing lets you share your love of football no matter where in the world you are. KickerAce – All you need is your phone and a ball.
Sports Computing
Experience we shared.
Computer vision processing Computer vision processing
Artificial Intelligence & Machine Learning
Mobile application development Mobile application development


  • Need to promptly deliver a revamped version of the app based on a new UI design.
  • The software was expected to facilitate a large number of concurrent users, which required full scalability.
  • Lack of internal tech resources on the client’s end.
  • Looking for a team with competencies across a broad spectrum of skills – including mobile development, backend, video and image processing, AI/ML, and the ability to package all these skills together.
  • Previously choosing a partner that failed to deliver expected results and caused a go-to-market delay. 
  • Unmaintainable, messy code with no versioning scheme.


  • Initially, performing detective work to find the most recent version of the app, fixed all burning issues, and deployed the app again to the testers to create a baseline.
  • Cleaning up the code and redesigning the application based on the new designs.
  • Bringing the backend in order based on established good practices – decoupling environment, creating a separate development and production infrastructure, setting up proper DevOps infrastructure in Azure context as well as setting up the CI/CD pipelines for mobile app
  • Setting up a dedicated team tackling the image analysis aspects of the app.
  • Developing the product in line with the Sport’s Computing Product Owner cooperation


The services are performed by developers chosen to form an interdisciplinary, independent team. The core areas of support were based on Data Science with Python and Image Analysis knowledge and experience and DevOps support and were aligned during the so-called “Block Planning Sessions” or prioritized and assigned to our team via email. The initial collaboration began with KickerAce mobile app development and further collaboration on Shot Analyzer software.

Delivered value.

The customer has been provided with fully scalable and functional software, meeting the deadlines, requirements, and specifications presented towards the beginning of the project. The collaboration between and customers’ teams has been based on transparency, openness, and honesty resulting in solid trust. Our problem-solving approach and excellent understanding of both technology and business allowed the Sports Computing team to feel comfortable and confident in the results of our work.


Review Quote
Most important is that you cover our professional needs, which are pretty extensive and different from traditional projects. We couldn’t get a more ideal partner with extraordinary skills both within AI and application development. Professional and transparent project management is vital. PM and interactions are working exceptionally well. Your ability to work independently and come up with constructive alternative solutions, understandable for a layperson, has reduced the stress and concerns. We appreciate the good chemistry. We see as more than just another developer. We see you as an extension of Sports Computing.
Kjell Heen
CEO of Sports Computing

Used Technologies.

React Native

Are you interested in video processing and mobile app development?

Just leave your email address and we’ll be in touch soon
ornament ornament



AFarCloud is an EU project with a budget of EUR 16.6 million and 59 participants from 14 countries. AFarCloud will provide a distributed platform for autonomous farming that will allow the integration and cooperation of agriculture Cyber Physical Systems in real-time in order to increase efficiency, productivity, animal health, food quality and reduce farm labour costs.


The main goal of the PEF-DST is to support the end-user in monitoring the PEF of two Diary Supply Chain (DSC) stages: milk production and milk transportation. The DSC data is analyzed in order to assess the quality of the supply chain operation in terms of sustainability.


PEF-DST presents the following information:
  • aggregated PEF of the factory the number is the indicator for the user on the overall PEF performance along the supply chain,
  • a graphical presentation of aggregated PEF of the factory and its components (in this case: Aggregated Transport PEF, Farm PEF and Average PEF per route)
  • the graphical presentation of Aggregated Factory PEFliter should allow for simplified overview and extended view with detailed data and components of analyzed Factory PEF,
  • historical data – the user needs to be allowed to review historical data to improve future inference and business decisions. PEF reductions will be the goal.
  • transport PEF for each hauler and Farm PEF for each milk supplier – environmental issues should be one of the components of decision making when choosing business partners. Each party in the supply chain should aim to minimize PEF of its own activities.
  • input data edit option for each transport provider – possibility to edit input data to show what changes in Aggregated PEF occur when CO2 emission norm changes or the provider modifies routes and limits the number of kilometers daily.
  • input form – some of the data needs to be entered manually for the players that do not have own PEF monitoring tools. PEF of each farm may be calculated from the chosen parameters provided once by each supplier. Data sets may be updated.
  • archiving of data sets – modification of data sets (manual or real) influence the performance on PEF. It is useful to have a possibility to leave a comment if a data set modification results from a known event or external factors (e.g. weather conditions, new investments, road failures, etc.)
  • emission norms – the following versions of PEF Mode may be connected to databases that will update automatically the standardized data as they are modified by the authorities. Now, however, those values should be updated manually.

The goal is to give the user a bigger picture – PEF is not just a number. The possibility to modify the data manually and see the prediction of expected PEF values is essential from the perspective of the sense of agency. First attempts of PEF implementation into business routine require to relate to users’ sentiments and the image of a cycle where each party along the supply chain plays a significant role. The user should feel the change is possible.



PEF is based on Life Cycle Assessment methodology, defined by the European Commission’s Joint Research Center. Its purpose is to provide a standard for entities within the EU to measure environmental performance. Every product category can be defined by a distinctive set of rules that are to be applied.

PEF-DST monitors the footprint as a multi-factor measure of the impact of dairy farms or transportation on the environment. It is calculated using a set of factors that impact the milk production and transport ecosystem. Monitoring PEF in PEF-DST allows us to identify trade-offs and make better strategic decisions.

The EU commission has provided Product Environmental Footprint Category Rules (PEFCRs) as specific guidance for PEF studies, at the level of a specific product category, for calculating and reporting products’ life cycle environmental impacts. PEFCRs shift the focus of the PEF study towards these aspects and parameters that matter the most and hence contribute to increased relevance, reproducibility, and consistency of the results by reducing costs.

Delivered value.

The aim of the PEF-DST is to present the PEF results for farmers and milk transportation. The PEF-DST provides an end-user interface with clean, consistent and personalized dashboards. The tool also provides customized enterprise reporting capabilities for the DSC participants.

Used Technologies.

rabbit mq

System Prototype Demonstrated in Operational Environment.

PEF-CaS is a business intelligence tool for industry sectors where the collection of raw materials is involved in milk production. It is a solution based on the methodology of assessing Product Environmental Footprint (PEF), a metric developed by the European Council to measure the environmental impact of different production industries.

Apart from the PEF calculation, a system enabling real-time data collection was implemented and consisted of a cloud-based application. The system has been tested and deployed for milk haulers to show how to calculate it for the milk production industry and how particular parts of this process contribute to PEF (milk transport, milking, cow feeding, etc.).

PEF-CaS is mature and has diverse capabilities. It is implementable to other software solutions. PEF is a highly complex indicator, and each enterprise has specific, controllable factors influencing its aggregated PEF. The DAC’s goal was to design an interface flexible enough to be suitable for the presentation of various data sets. PEF-CaS was designed as an additional component of the MilkMap system. MilkMap is a tailored solution for managing the milk supply chain that was developed by DAC.Digital in cooperation with their clients (both milk and dairy producers).

The system has the potential to be adapted for other industries and sectors for the calculation of PEF based on European Commission guidelines.

State of the art.

The environmental effect of the Dairy Supply Chain (DSC) has been and is a major factor in the direction of sustainable growth. However, this is not the only one, other factors that align with the sustainable development approach also exist.

For example, improving food waste recycling, strengthening facility sharing, and sustainable logistics, which are understood as a balance between logistics, the environment, and the economy. There is a need to define sustainability measures that indicate/estimate the impact of human activities within the dairy industry on the environment to achieve sustainable development goals, such as ensuring sustainable consumption and production patterns and taking urgent action to combat climate change and its impacts.


In order to give explicit guidelines at the level of a single product category for calculating and reporting goods’ life cycle environmental impacts, the European Commission created Product Environmental Footprint Category Rules (PEFCRs). By lowering expenditures compared to research based on the exhaustive criteria of the PEF guide, PEFCRs aid in shifting the emphasis of the PEF study toward those features and characteristics that matter the most, increasing the relevance, repeatability, and consistency of the results. These PEFCRs are industry specific.

The whole life cycle of dairy products supplied in the European and EFTA markets is covered by PEFCR for Dairy Products (PEFCR-DP). Liquid milk, dry whey products, cheeses, fermented milk products, and butterfat products are considered subcategories. This PEFCR-DP makes it possible to evaluate several dairy products in the same subcategory side by side. In order to get comparable results, it uses a structured and systematic methodology to assess the environmental effects of dairy products supplied in Europe.

This raises the need for ensuring all stages of DSC are visible to facilitate its sustainability orientation. Visibility of all DSC phases would also guarantee the DSC’s long-term growth, which produces dairy products of the highest quality. DSC visibility is shown in Figure 1 and is defined as the ability of the supply chain to view the life cycle of a dairy product, including the production of feed and milk, transportation of milk, processing of milk, distribution of dairy products to end users, and end-of-life activities and processes.

Figure 1. Dairy Supply Chain with corresponding data sources.

Figure 1. Dairy Supply Chain with corresponding data sources.

Currently, visibility is enabled across much of the DSC, from milk production to dairy product consumption, making the DSC manageable. Traceability is another desirable feature in modern DSC, which is defined in the food industry as the ability to trace and follow a food, feed, food-producing animal, or substance intended to be, or expected to be, incorporated into a food or feed through all stages of production, processing, and distribution as per the Regulation (EC) No 178/2002 of the European Parliament and of the Council of 28 January 2002. The Internet of Things (IoT) is the core notion that offers visibility and interoperability amongst dispersed systems in complicated DSCs depicted in Figure 1. As a result, today’s administration of integrated DSC is shifting toward IoT-based cloud-distributed solutions, blockchain-based transactions, and big data analysis of tracked data.

The visibility and traceability afforded by IoT, among other things, help in monitoring the two most important environmental variables impacting DSC, water consumption and GHG emissions. When milk production and transportation are included, the impact of DSC on world GHG emissions is estimated to be 2.7%. As a result, the dairy industry is an important actor/suspect in the EU’s climate change policy, with the European Union Emission Trading System (EU ETS) functioning as a critical tool for cost-effectively cutting greenhouse gas emissions. Here a Product Environmental Footprint Decision Support Tool would come in very handy.

The Solution: How does it work?

PEF-CaS is based on the European Commission’s Joint Research Center’s Life Cycle Assessment approach. Its goal is to offer a standard for measuring environmental performance among EU institutions. Every product category can be defined by a unique set of criteria that must be followed.

PEF-CaS measures the footprint as a multi-factor assessment of the environmental effect of dairy farms or transportation. It is estimated by taking into account a number of elements that influence the milk production and transportation environment. We may detect trade-offs and make better strategic decisions by monitoring PEF in PEF-CaS.

Required Inputs to PEF-CaS.

The AFarCloud Semantic Middleware has a data streaming component (see Figure 2) that can quickly ingest and analyze high-velocity data from remote data sources. The data in question comes from various phases of milk production and transportation and is required to calculate the PEF factor.

Figure 2 Streaming Engine architecture

Input data depends on the PEF factory accuracy and the product category. Some of the global normalization factors which have been recommended by European Commission are: 

Acidification, Climate change, Eutrophication – freshwater, Eutrophication – marine, Eutrophication – terrestrial, Ionizing radiation – human health, Land use, Ozone depletion, Particulate matter, Photochemical ozone formation – human health, Resource use – fossils, Resource use – minerals and metals, and Water use.

OnPuts from PEF-CaS.

The output received from the PEF-CaS are the PEF results for farmers and milk transportation. It offers an end-user experience that is clean, consistent, and customized. The technology also gives DSC members customizable corporate reporting options.

To summarize PEF-CaS can carry out the following functions:


estimation of the environmental footprint of milk production (results calculated per cow)

graphical presentation of farm-scale environmental footprint (results calculated for the entire herd)

PEF-calculation implements the EU recommended Environmental Impact Assessment methodology

Example Applications.

Use Case.

Calculating the Product Environmental Footprint


Product Environmental Footprint (PEF) can be calculated for the farm or a specific type of farm production (e.g. cows breeding or milk transportation).


SPE saves data from sensors that monitor the whole production (plants or animals), such as corrals, stables, greenhouses, vehicles, agricultural gadgets, and types of machinery. As a result, SPE collects all of the information required to compute PEF through a specific application of third-party software, DSS algorithm, or Stream Processor.

Use Case.

Monitoring of global PEF production


Required analysis of PEF by concerned agencies / associations


The aggregated data includes the amount of milk collected from each farm and information on how the milk was delivered (e.g. average speed, the distance between collection points). Every day, data for each milk transportation route is pooled.

Use Case.

PEF Administration


PEF profile management


The PEF indications and levels can be customized by the user. It will be able to update the reference indicators in the event of a change (by European or national guidelines).

The so-called PEF component is generated by every milk producer and every vehicle providing transportation services. PEF production from the dairy production and transport phases is totaled up at the conclusion of the trip for a certain vehicle. With such information available in monitoring mode, the analyst can investigate what PEF production looked like throughout the supply chain, such as PEF in dairy production or PEF in transportation.


Review Quote
It is important to take into consideration all the environmental impacts of products in a balanced way. In the case of some product groups, GHG emissions are not the most significant environmental aspect, therefore other environmental impacts need to be taken into account as well to provide balanced information for consumers on the environmental performance of products.
European Commission

Estimate your project.

Just leave your email address and we’ll be in touch soon
ornament ornament

Case Studies.

We are a team of engineers & problem solvers who deliver value across areas of IoT, hardware, embedded systems, big data, machine learning, DLT, DevOps, and software engineering.

System Prototype Demonstrated in Operational Environment.

N-SAAW is a one-of-a-kind Deep Neural Network (DNN)-based system for monitoring farm animal health and wellbeing. This method was created specifically to examine the milk protein to fat ratio, encompassing extremes associated with malnutrition. This type of detection aids in lowering the danger of ketosis or acidosis induced by starvation. N-SAAW has already been deployed and evaluated in real-world agricultural settings, where it has been shown to identify malnutrition about 3.5 times sooner than current analytical approaches. Furthermore, because of the pre-processing, there was no possibility of the DNN missing starvation.

N-SAAW may be effortlessly linked with farm sensors and provides a way for autonomous monitoring to collect data that is then analyzed to provide insights to farmers. It also includes a visualization and reporting tool, allowing the provenance to be disclosed farther down the supply chain.

The Solution: How does it work?

The solution developed and demonstrated was a tool to support the monitoring and analysis of milk cows’ bio parameters (temperature, pH). The data on temperature and pH are gathered from a ruminal probe.

The tool’s core functionality is based on a Recurrent Neural Network trained to predict the possible health deterioration of a specimen. In case of a predicted threat, an alert is triggered to inform the farm manager about the malnutrition of an animal. The triggering value has been set to a pH = 5.8, sustaining over a period of a few hours. Figure 1 presents the tool’s user interface, showing measurements and predictions tables, alerts, and pH values over time.


Figure 1: The user interface of an analytical application for pH monitoring and prediction of the bio parameters related to the functioning of the digestive system
Figure 1: The user interface of an analytical application for pH monitoring and prediction of the bio parameters related to the functioning of the digestive system

DAC conducted an initial validation of the health deterioration (malnutrition) prediction model. The results of the validation are considered satisfactory. As shown in the confusion matrix below (Figure N), the accuracy of “bad” and “good” predictions is reliable, producing an insignificant number of false positives. The mismatch between “warning” and “good” can be reduced with an auxiliary analytical algorithm.

Figure 2: Confusion matrix of the Recurrent Neural Network (RNN) trained to predict possible health deterioration resulting from malnutrition.


  • health control based on pH and temperature from a ruminal sensor
  • fat-to-protein ratio control, based on milk parameters analysis, in order to detect improper nutrition

Estimate your project.

Just leave your email address and we’ll be in touch soon
ornament ornament

Case Studies.

Advantages of IREENE system.

IREENE adds significant capability to product knowledge management in modern manufacturing enterprises.

Topic modelling and semantic representation of existing documents’ knowledge graphs might minimise the time necessary for the manual processing of essential documentation by individuals involved in product management across several organisational verticals.

It has already achieved great success in offering insights for product management, including but not limited to operations, compliance, R&D, and intellectual property rights.

Stack of papers

State of the art.

Every manufacturing organisation must deal with a substantial volume of external documents. Intellectual property and fundamental standard compliance must be studied and analysed before development. Every day, patents (including Standard Essential Patents), technological standards, and scientific papers are searched across all sectors.

However, the amount of relevant textual materials available is huge. Over 3.4 million patent applications were filed globally in 2021, with the number growing by 5-9% each year since 2011. In addition, the average word count in patent applications has increased throughout the 1990s, surpassing 7,000 in 2007. An average reader would need 200 years to read (nonstop) 3.4 million patent applications without titles, abstracts, or references.

Mobile app development process

A quick glance at the most prominent standards bodies demonstrates the breadth of accessible sources. There are 22,538 ISO standards, for example, and over 1,300 IEEE standards. With the rising digitisation of the sector and current technical advancement, we anticipate that numbers will rise. Over 50 million scientific articles have been published by 2010, and the overall quantity of scholarly papers is doubling every nine years.

Patent information is used in a variety of contemporary organisations, including strategic management as a foundation for competitive environment monitoring, technology assessment, or even R&I portfolio management, design and engineering, to name state-of-the-art research, and legal when functionality, design, and implementation technique are studied in the context of the so-called “Freedom to Operate” analysis to determine whether the development and marketing of a product is permissible.

Man writing an article

IREENE (Information Retrieval Engine) is a solution to this need of providing methods of processing unstructured text documents in order to create a knowledge graph representing the contents of available sources.

The Solution: How does it work?

In the case of the digital industry, data-driven engineering and manufacturing refer not only to machine-generated data fed through IIoT but also to the vast accumulation of unstructured data, including textual content written in natural languages. The volume of available data is even bigger as virtual organisations build on the free flow of information and knowledge between direct partners and third parties.

Design, engineering, manufacturing, and other processes of industrial enterprises are deeply embedded in textual data, usually human-generated content such as patent files, scientific publications or industrial standards like IEEE or IEC. In order to embrace both the volume and potential of pertinent but heterogeneous data, it is necessary to make it machine-readable first. This is where IREENE comes in.

Input files to IREENE could include a wide range of inputs such as patents, user requirements sheets, customer feedback, troubleshooting descriptions, failure, and fault reports, insights from previous projects, regulatory considerations, engineering standards such as those defined by ISO, IEEE, or IEC, not to mention product-relevant scientific publications.

IREENE processes input files of different formats (e.g. text documents, spreadsheets, presentations) in order to create a knowledge graph representing the contents of processed sources. The data sets used in the development have been subjected to topic modeling, which as an unsupervised machine-learning technique to detect similarities between documents and cluster expressions that statistically define the contents of a document in the most accurate manner.

IREENE uses a topical model to enable functionalities of (a) smart semantic search and (b) visual knowledge-graph browsers. Smart semantic search and visual knowledge-graph browser are the enablers to apply the Business Platform for Distributed and Decentralized Data Exchange Ecosystems not only to the traceability use case but for Electronics and ICT as an enabler for the digital industry and optimised supply chain management covering the entire product lifecycle in large ecosystems.

The ambition is to analyse documents and find similarities in a way that search engines like Google are possible in a B2B environment and, by that enabling a Product Life Cycle Management.

Case Studies.

We are a team of engineers & problem solvers who deliver value across areas of IoT, hardware, embedded systems, big data, machine learning, DLT, DevOps, and software engineering.

Estimate your project.

Just leave your email address and we’ll be in touch soon
ornament ornament