The BYOD app transforms everyday courier operations into a fully connected, data-driven workflow. From parcel validation to proof of delivery and disruption reporting, every action is securely recorded and transmitted to the central platform, ensuring logistics providers remain fully informed. 

When a courier logs in, the application automatically adapts to the configuration of the specific Living Lab deployment. The available features and workflows depend on the operational model of each environment. The BYOD app is designed to support different city deployments with tailored configurations without requiring changes to the core application. 

In the Athens Living Lab, for example, couriers can operate through either Parcels or Stops within the main menu. This flexibility allows the same application to support multiple logistics scenarios without altering the core system. 

Parcel function

In the Parcel function, couriers add parcels by scanning QR codes or by manually entering parcel IDs. For greater efficiency, multiple parcels can be selected at once by scanning code sets or entering a set ID for batch processing. 

Once validated, parcels appear in the current working list, confirming that they are correctly linked to the courier. They remain visible until delivery completion or manual removal or once the delivery is confirmed in the system. A refresh option allows the courier to retrieve the most up-to-date parcel information at any time.  

Selecting a parcel provides access to essential delivery data, including its identification number, status, delivery address, expected delivery date, weight, service type, and associated round. During the delivery process, couriers can register events and update parcel quality directly within the app. 

For proof of delivery, a single parcel is selected, and the receiver signs directly on the device. The signature is securely recorded and immediately reported, ensuring reliable confirmation of delivery and traceability. 

Stop function

Through the main menu, couriers can switch to the Stop function, which provides a structured overview of planned stops and related parcel information grouped by delivery location. Stops can be visualised on an interactive map, offering clear route visibility and improved situational awareness through real-time geolocation.  

Selecting a stop reveals the parcels assigned to that location, allowing couriers to manage grouped deliveries efficiently. If a disruption occurs, the courier can report it directly within the app by selecting the disruption type, adding comments, and automatically sharing their position. This real-time communication supports immediate operational adjustments and proactive issue management.  

BYOD impact

The Green-Log BYOD tool ensures that every action, from parcel validation to signature capture and disruption reporting, is securely transmitted to logistics operators. This continuous flow of information enhances: 

• Transparency 
• Improves coordination 
• Supports data-driven decision-making 

By combining flexibility, live operational visibility, and secure reporting, BYOD strengthens last-mile delivery efficiency while contributing to more sustainable and optimised urban logistics operations across different city environments. 

→ Check our Digital Twins solution

La entrada Bring Your Own Device overview se publicó primero en Mosaic Factor.

Within the AutoMoTIF project, this challenge is addressed through automated shunting as a service, with Mosaic Factor leading the development of the simulation framework. 

From operational bottleneck to coordinated rail operations

Shunting plays a central role in intermodal terminals, linking maritime cargo flows with inland distribution. However, traditional shunting operations are often reactive, fragmented across systems, labour-intensive, and energy-inefficient. 

Shunting as a service reimagines these operations as a digitally orchestrated service platform where autonomous locomotives, yard resources, and scheduling systems operate as an integrated ecosystem. The aim is not simply automation, but service optimisation. 

Simulation driving the transformation

Mosaic Factor’s advanced simulation environment replicates the operational complexity of rail terminals, including train movements, wagon marshalling, yard capacity constraints, container handling cycles, resource allocation, and disruption scenarios. 

Autonomous shunting locomotives are modelled as intelligent agents that dynamically respond to congestion, schedule changes, and infrastructure constraints. 

Through scenario modelling, the simulations evaluate: 

• Reduced shunting time 
• Faster wagon turnaround 
• Lower idle and waiting times 
• Optimised energy consumption 
• Increased yard throughput 
• Improved safety and lower operational costs 

This data-driven approach ensures automation concepts are validated before real-world deployment. 

Shunting as a Service Platform

Shunting as a service introduces a shift in how rail yard operations are structured. Instead of a fixed internal activity, shunting is modelled as a service-oriented platform where capacity is dynamically allocated, operations are digitally coordinated, and performance is continuously monitored. 

This approach supports greater interoperability between terminal operators, rail infrastructure managers, logistics providers, and port authorities, while enabling integration with other automated processes within AutoMoTIF. 

Supporting Smarter Rail Terminals 

To ensure realistic outcomes, Mosaic Factor calibrates simulations using historical operational data, planning inputs, and stress-test scenarios that reflect peak demand and future growth. 

The resulting models provide decision-support tools for infrastructure investment, automation strategies, business models, and regulatory alignment, helping reduce risk and accelerate deployment. 

Strengthening Europe’s Rail Freight Network 

By improving rail efficiency, automated shunting supports broader logistics goals, including: 

• Modal shift from road to rail 
• Reduced terminal congestion 
• Lower emissions 
• Safer working conditions 
• More reliable logistics operations 

Through simulation-driven validation, Mosaic Factor demonstrates how automated shunting can increase throughput, reduce delays, optimise energy use, and enhance safety. 

Automated shunting as a service-oriented platform represents more than a technological upgrade. It introduces a new operational model that strengthens the role of rail in Europe’s transport system while supporting a more efficient and sustainable logistics network. 

→ Check our Digital Twins solution

La entrada Automated Shunting as a Service Platform se publicó primero en Mosaic Factor.

Tackling urban blind spots

In busy city environments, parked cars, buildings, and vegetation often obstruct vehicle sensors, creating blind spots that pose serious risks, especially for vulnerable road users (VRUs) like children, cyclists, and road workers. Current detection systems struggle in these scenarios, with recognition rates dropping below 65% when individuals are fully occluded.

HIDDEN aims to overcome this challenge by enhancing Collective Awareness through Vehicle-to-Everything (V2X) communication and Artificial Intelligence. By sharing sensor data between vehicles, infrastructure, and road users, the project enables a more complete and dynamic understanding of the urban environment.

Hybrid Intelligence: a human-machine fusion

What sets HIDDEN apart is its use of Hybrid Intelligence (HI): a fusion of human and machine intelligence. This approach allows automated systems to make decisions that are not only technically sound but also ethically and legally grounded, reflecting human judgment and behavior.

“HIDDEN goes beyond conventional AI,” said Dr. Angelos Amditis, HIDDEN Coordinator and R&D Director at ICCS. “We’re bringing human judgement into the loop -so automated systems can act not just accurately, but wisely.”

Real-world testing

The project will test its approach in four high-risk urban scenarios:

• A child running from behind a parked car
• A cyclist navigating mixed-traffic zones
• A road worker obscured by vegetation
• A vehicle hidden at an unsignalised intersection

These cases reflect complex, real-world challenges where improved perception and ethically grounded decision-making could be life-saving.

A pan-European collaboration toward safer, smarter cities

Funded by Horizon Europe’s Cluster 5 with a grant of approximately €5 million, HIDDEN is supported by the Connected, Cooperative and Automated Mobility (CCAM) Partnership. The consortium includes 14 partners and 2 affiliated entities across 7 EU countries, bringing together expertise from research institutes, universities, SMEs, automotive leaders, regulatory bodies, and social science researchers.

HIDDEN isn’t just about smarter vehicles—it’s about building trust, aligning technology with human values, and paving the way for safer streets across Europe. Through field tests and virtual simulations, the project will validate its technologies and work closely with EU type approval bodies and UNECE working groups to shape future standards and policies.

Mosaic Factor’s contribution

Mosaic Factor leads the development of Explainable AI (XAI) and Human-Feedback Reinforcement Learning (RLHF) methods within the project. Their work focuses on creating a transparency-first explanatory toolkit that fosters trust, user acceptance, and ethical integration of AI in connected and automated vehicles.

For more details, you can read and download the full press release here:

HIDDEN Press Release _EN_final

→ Review our Data Enhanced Product solutions

La entrada HIDDEN project launch se publicó primero en Mosaic Factor.

Key Challenges for Automotive AI teams

The main challenges when developing AI models for SDVs are:

• High-Risk Classification: AI systems in SDVs often fall under the “high-risk” category, triggering mandatory conformity assessments, documentation, and audit readiness.
• Complex Compliance Landscape: with over 450 pages of legal text, translating regulation into engineering tasks is a daunting challenge. Manual reviews and fragmented documentation slow innovation and increase costs.
• Audit Pressure: teams must prepare for both scheduled and surprise inspections. Non-compliance can result in fines up to €7.5 million or 3% of global turnover.

AI Trust & Compliance frameworks

To address these hurdles, it is key to develop modular, automated compliance frameworks tailored for SDVs to enable:

• End-to-End System Assessments: rapid, audit-ready evaluations aligned with the EU AI Act.
• Configurable Reports: targeted assessments for specific AI components, such as dataset balance or model transparency.
• Audit Phase Interface: tools for third-party assessors, streamlining feedback and reducing evaluation time.

Who should worry about this?

• OEMs: responsible for system-level compliance, they must ensure every AI component meets regulatory standards before vehicle launch.
• Tier 1 Suppliers: developers of critical AI modules must demonstrate component-level compliance to OEMs, enhancing collaboration and market competitiveness.

Industry-wide implications

The EU AI Act is not just a legal hurdle, but a strategic opportunity. By embedding compliance into the development lifecycle, automakers can build more resilient, transparent, and future-proof AI systems.

The Act encourages:

• Cross-functional collaboration: AI, cybersecurity, safety, and regulatory teams must work in tandem.
• Lifecycle accountability: from design to post-market monitoring, traceability becomes a core requirement.
• Innovation through structure: automated tools and frameworks transform compliance from a bottleneck into a catalyst for better engineering practices.

As SDVs become the norm, the EU AI Act will shape how automotive AI is built, validated, and deployed. Forward-thinking developers and suppliers who embrace structured compliance will not only avoid penalties but will lead the next wave of intelligent mobility.

GPAI & GenAI Under the EU AI Act: what developers must know

The GPAI Code of Practice, finalised in May 2025, provides critical guidance for providers of General-Purpose AI (GPAI) models, including Generative AI (GenAI) systems. The EU AI Act distinguishes between complex GenAI models -those with systemic risk– and simpler GenAI models, each facing different compliance burdens:

• Complex GenAI (systemic risk models): These models exceed thresholds like 10²⁵ FLOPs in training compute or demonstrate high-impact capabilities across domains. Providers must conduct adversarial testing, risk assessments, and incident reporting, and ensure cybersecurity protections. They must also notify the European Commission for public database inclusion and maintain detailed documentation of model architecture and evaluation strategies.
• Simple GenAI Models: These are not classified as systemic risk and face lighter obligations. Providers must publish a summary of training data, ensure copyright compliance, and maintain technical documentation for downstream users. Transparency is key: outputs must be labeled, and users informed when interacting with AI systems.

The Code of Practice serves as a blueprint for demonstrating compliance, helping developers navigate the AI Act’s layered requirements while fostering innovation and trust in GenAI technologies.

La entrada Navigating the EU AI Act: what it means for SDV developers and Automotive innovators se publicó primero en Mosaic Factor.

Here are the key trends and developments that stood out.

Digital Twin Innovations

The fair featured numerous Digital Twin solutions, emphasizing virtual commissioning and real-time manufacturing services:

• Delta Electronics presented a Digital Twin for virtual commissioning of robotic gluing cells, enhancing automation efficiency.
• An open-source initiative by IDTA (Eclipse Foundation) garnered attention for advancing accessibility in Digital Twin technology.
• Circularity emerged as a critical theme, with contributions from Fraunhofer or Schneider promoting sustainable manufacturing practices. These projects spanned sectors such as food production and automotive component recycling.
• Siemens showcased a wind tunnel simulation using Digital Twin and AI technologies, it demonstrates the potential for advanced testing methods.

AI driving innovation

AI applications in manufacturing were prominently displayed, extending beyond traditional machine learning:

• The importance of Explainable AI (XAI) and Certified AI was highlighted, reflecting the industry’s commitment to transparency and reliability.
• Schneider utilised AI in plant-based milk production to optimise processes, ensuring consistent sugar content—an example of machine learning automating complex tasks.
• DFKI‘s AI solutions included temperature configuration analysis for heating systems and quality assurance for car body construction, combining image analysis, sensors, and Digital Twin technology.
• Robotics-integrated AI applications also introduced explainability for tasks such as detecting assembly errors and automating quality checks.

Robotics and AI convergence

The robotics exhibits presented diverse applications:

• Project ROX demonstrated process automation.
• Siemens unveiled projects combining robots with virtual PLCs, powered by AI and large language models (LLMs). One application involved assembling toys based on customer instructions via a digital interface.

Hannover Messe proved that the synergy of Digital Twins, AI, and Robotics is transforming manufacturing. These technologies not only enhance efficiency but also pave the way for sustainable and innovative production solutions.

La entrada Hannover Messe: Exploring the Future of Manufacturing se publicó primero en Mosaic Factor.

The EV Charging Location Planning Tool includes socio-demographic data, mobility flows, and charging session data from existing charging stations to predict future needs for charging points, both slow and fast, according to scenarios that include the anticipated adoption of electric vehicles. The tool was presented to target group users, mainly public authorities interested in the effective and efficient placement of charging points. Their feedback has been positive, especially as they seek to determine which sites to prioritise first and where to deploy additional chargers.

On another hand, users have seen different benefits from the tool’s demos.

1. It facilitates informed decision-making by allowing users to make data-backed decisions when planning charging infrastructure, which is a clear improvement over the traditional, intuition-based methods.
2. The tool also ensures efficiency in resource allocation by focusing on the most promising locations for new charging points and estimating usage rates and profitability.
3. It also enhances EV driver satisfaction by increasing the availability of charging points in the most needed areas.
4. Finally, the tool supports long-term planning by simulating scenarios for three to five years, providing confidence for future developments.

Nevertheless, conclusions during the final project meeting highlighted recommendations for policymakers and investors to guide future charging efforts and investments. Project partner experiences and a European survey of public authorities and operators pointed out:

• the need for tailored design guidance,
• improved grid connections,
• streamlined planning processes
• the importance of interoperability,
• user-friendly interfaces,
• and political support to maximise the impact and accessibility of innovative EV solutions.

Moving forward, following the end of the project we expect to reuse and possibly scale the product concept. Our scalability and exploitation efforts for this tool will focus on:

1. Business and Market analysis to assess fit to other locations and organisations in Europe in the EV ecosystem.
2. Contact and implementation plans to reuse the Location Planning Tool concept at R+D level in the identified locations and organisations, in collaboration with partners of the model development.
3. Result gathering to assess validation of the European rollout plan in the pre-identified locations and organisations and planning any future scaling to other locations outside the EU.
4. Assessment of different use cases where the product could be scaled in markets outside the EV environment where the applicability is strong (for instance, hydrogen vehicles).

The simulation platform

During the project, we first performed an analysis of EV drivers’ needs related to vehicle charging which resulted in the solution we designed and integrated: the Location Planning Tool.

This tool has been used and validated in three types of areas while running the project:

1. A small village in a rural environment without EVs (Val Trompia, in northern Italy). Public authorities validated the tool.
2. A city, Barcelona. A company has validated the tool: B:SM (Barcelona de Serveis Municipals).
3. One country, Luxembourg where CPOs have validated it.

This three-fold validation of the tool has proven valuable to illustrate the potential and capabilities of our approach of combining Big data analytics using real-time usage to enable public administrations and private companies to plan future charging infrastructure deployment in the right locations.

→ Check our Predictive Models solution

La entrada Charging Point Location Planning Tool se publicó primero en Mosaic Factor.

• Expanding functionalities and ensuring compatibility across components.
• Version 3 of the platform will introduce interactive features, allowing users to adjust optimization parameters directly within the application.
• Version 4 will extend all functionalities to include all Living Labs, ensuring adaptability to diverse urban contexts.

The final version will incorporate the enhanced optimisation module, integrating simulation workflows to create a fully operational platform capable of addressing complex logistical needs. Through continued iteration, stakeholder collaboration, and meticulous testing, the AIMP is on course to deliver a robust and adaptable solution for urban logistics, addressing the needs of Living Labs and showcasing its potential in real-world applications.

The simulation platform

Here you can have a sneak peak on how the AIMP looks like:

→ Check our Digital Twins solution

La entrada Augmented Intelligence Modelling Platform se publicó primero en Mosaic Factor.

To provide an idea, the top-5 algorithms we use more often for predictive models are:

1. Statistical Models: sophisticated statistical models and approaches such as generalised modeling, regularisation, Bayesian Inference, and time series analysis and forecasting which are used to capture intricate dependencies, model uncertainty, and make robust predictions with generalised models based on complex data distributions and latent structures.
2. Machine Learning Algorithms: powerful models to capture complex data relationships with tree-based, kernel-based, ensemble techniques (bagging, boosting, stacking and blending, and voting ensembles). The advanced supervised ML approaches are enhanced with techniques to improve generalisation and interpretability. Reinforcement learning through environment interactions by applying optimisation of policies, value-based learning, and actor-critic methods are designed for (sequential) decision-making.Advanced and tailored unsupervised learning techniques to focus on discovering hidden patterns, creation of segments and groups are developed and used. These techniques include:
   1. clustering,
   2. dimensionality reduction,
   3. and representation learning.
3. Deep Learning techniques: Deep Learning is based on deep neural networks to learn hierarchical representations of data, being key in applications such as natural language processing and image recognition.
4. Neural Networks are advanced models and approaches from deep learning. Representation learning, and attention-based architectures that enable state-of-the-art and also beyond-state-of-the-art with innovation in areas like computer vision, natural language processing, and sequential modelling. The motivation stands for:
   1. improving generalisation,
   2. scalability,
   3. and interpretability through advanced techniques by pushing the boundaries of what a machine can learn.
5. Explainable Artificial Intelligence (XAI techniques): methods aiming to uncover how models with complex dataset and structure make the predictions, providing transparency in decision-making pipelines and processes. Techniques include both model-agnostic and model-specific approaches; they are crucial to understand the rationale behind a model output and a decision.

→ Check our Predictive Model solutions as well as our Trustworthy AI solutions.

La entrada Our top algorithms for predictive modeling se publicó primero en Mosaic Factor.

What are LLMs?

LLMs (Large Language Models), are advanced AI systems capable of understanding and generating various forms of content, including text, code, images, video, and audio. These models are trained on at least one billion parameters (data points), which allow them to grasp language patterns and respond appropriately.

LLMs find applications in natural language processing tasks such as text generation, translation, sentiment analysis, data analysis, question answering, and text summarisation.

Evolution of LLMs

Key milestones include:

• 1966 ELIZA: The first chatbot simulating a psychotherapist.
• 2013 word2vec: Efficient methods for learning word embeddings from raw text.
• 2018 GPT and BERT: Groundbreaking models.
• 2020 GPT-3: A significant leap.
• Late 2021 and 2022: GPT-4 and other advancements.
• Statistical models: Developed to learn patterns from text data.

LLMs vs. NLP

While NLP (Natural Language Processing) models interpret or transform existing text, LLMs excel at generating new, coherent text from scratch.

They can create essays, stories, and even computer code that mimics human writing styles.

Light LLMs

Nowadays, though, there is an increasing importance of smaller models (light LLMs) for specific domain applications.

While the largest models would all be “general purpose”, light LLMs are developed with a specific sector use in mind.

That is:

• Large models use a huge number of parameters, without tuning to a specific use, use a lot of energy, sometimes with questionable reliability, and that provide answers even when they don’t know them.
• Smaller models consider the use that is going to be given to it, refining its responses (fine-tuning) the specific model for a specific use.

Light LLMs benefits

1. Efficiency: Light LLMs require fewer computational resources, making them faster and more cost-effective.
2. Scalability: Companies can deploy light LLMs across various applications without straining infrastructure.
3. Customisation: Light models allow fine-tuning for specific tasks, tailoring them to company needs.
4. Privacy: Smaller models reduce the risk of inadvertently leaking sensitive information.
5. Easier Maintenance: Light LLMs are simpler to manage and update.

To conclude, while both open-source and closed LLMs have their merits, light LLMs offer practical advantages for companies seeking efficient, adaptable solutions. Therefore, you should consider your specific requirements when choosing the right LLM for your organisation.

→ Check our LLMs solution

La entrada What are light LLMs? se publicó primero en Mosaic Factor.

Our team visited Kyutech in Japan to collaborate in the creation of AI-enhanced healthcare products

During the conference, we were able to connect with top HealthTech researchers, developers, and institutions. Following the conference, our team met with Professor Sozo Inoue, Director of “Care XDX Center Kyutech”, Kyushu Institute of Technology, focused on the application of ML and IoT on activity recognition aimed at Healthcare & Nursing Tech. These technologies can significantly improve patient care and monitoring.

It was also relevant the discussion with Doctor Colley from Hokkaido University (Noriyo Colley, Ed.D., MNS, BE, BN, RN in Japan and Australia) whose team developed an interactive simulator to train nurses and improve nursing care quality. Training nurses effectively is essential for maintaining high-quality healthcare services.

Innovation in Big Data and AI

These meetings will facilitate the collaboration between the institutions both in the field of innovation in big data and AI projects, and in the promotion of new data-based products in the international market to improve health care systems (HealthTech).

Clearly, collaborations like these foster innovation: integrating big data and AI can lead to breakthroughs in healthcare, from predictive analytics to personalised treatments.

It’s exciting to see how these partnerships will promote new data-based products globally, enhancing health systems.

Seminar on Trustworthy AI

During her visit, our CMO, as per her role as Associate Professor at UAB as well as her professional career as digital business and strategy expert, held the seminar entitled “Trustworthy AI: Solving problems with data while making a positive impact in society” at the Kyushu Institute of Technology.

The talk was about the importance of working not only on the use of data to solve real problems of companies and society but also the relevance of thinking and establishing how to work with data at a strategic level: paying attention both to market aspects and to what is referred as Trustworthy AI. This includes elements such as accessibility, security, equity, accountability, transparency, fairness, reliability, and robustness of the artificial intelligence algorithms that are integrated as well as the ability to explain how they reach to their conclusions.

Ensuring ethical and transparent AI development is crucial. The above factors are essential for building AI systems that benefit society. This means working with AI algorithms with a white-box perspective, including explainable-by-design and fairness-by-design approaches; so, making AI trustworthy by also having the capacity to explain the reasoning behind the algorithm and making this explanation accessible to different stakeholders so that they can take strategic and business decisions based on this information instead of working with black-box AI tools.

Finally, the talk included different use cases that we are working at Mosaic Factor on the application of AI algorithms in different sectors, including Trustworthy AI and explainability of AI algorithms.

→ Check our Trustworthy AI solution

La entrada AI-enhanced products to improve healthcare se publicó primero en Mosaic Factor.