Periodic Reporting for period 1 - optiSLATER (optiSLATER: Automated Classification System for the categorization of slate slabs.)
Reporting period: 2019-08-01 to 2019-11-30
Slate manufacturing heavily relies on subjective and costly manual work for the quality control and categorization of its products, during which the price of the final product is defined. Due to the subjectivity of this manual process as well as the labour shortage (i.e. due to hard and harmful working conditions – carcinogenic components), this industry is urgently requiring accurate, efficient, unbiased and automated classification systems, able to reduce production costs, increase productivity, competitiveness and traceability but also improving the working conditions of the employees.
The objective of the Feasibility Study project was to deepen on market analysis, commercial strategy and business model, as well as accurately estimate the remaining tasks to reach OPTISLATER up to a TRL9 together with the required funding needs. In addition, we identified the associated risks and prevented them through the deployment of contingency measures.
The objective of the Feasibility Study project was to deepen on market analysis, commercial strategy and business model, as well as accurately estimate the remaining tasks to reach OPTISLATER up to a TRL9 together with the required funding needs. In addition, we identified the associated risks and prevented them through the deployment of contingency measures.
We have established a work plan to finalise OptiSLATER that includes, tasks, timing and resources allocate for such purposes.
We have identified the risks involved on launching our product to the targeted market and prepared contingency measures for it.
We have deepen into the market analysis, figures, projections, drivers, competitors, etc.
We have established an exploitation strategy that includes dissemination activities for longer term commercial purposes.
We have analysed and quantified our revenue model to deploy a sustainable and profitable economic activity.
We have identified the key partners involved and extended alternative partners in case we are in need to consider other options within the value chain.
Further and accurate analysis of regulatory and IPR requirements and strategy has been determined.
Financial projections emerged from previous activities have been updated.
We have identified the risks involved on launching our product to the targeted market and prepared contingency measures for it.
We have deepen into the market analysis, figures, projections, drivers, competitors, etc.
We have established an exploitation strategy that includes dissemination activities for longer term commercial purposes.
We have analysed and quantified our revenue model to deploy a sustainable and profitable economic activity.
We have identified the key partners involved and extended alternative partners in case we are in need to consider other options within the value chain.
Further and accurate analysis of regulatory and IPR requirements and strategy has been determined.
Financial projections emerged from previous activities have been updated.
Up to date as per our prototype we can only foresee the impact that may have in the future as we have not implemented these planned actions yet.
However, we have already reached an accuracy rate that revolves around 85% that we aim to extend up to 95% in the near future together with and enlargement of the slate slabs samples to widen and accelerate the learning process of the deep learning algorithms supporting our Computer Vision based solution.
Impact will be quantified once it has been implemented. However, we already foresee the following:
• Optislater will support differentiation of European natural slate slabs that accounts with higher quality, to those imported from other regions, particularly China.
• Will support an industry that struggles due to skilled workers shortage for that specific qualification in such remote rural areas.
• It will increase competitiveness of Slate processors by means of more efficient performance respect to manual activity.
However, we have already reached an accuracy rate that revolves around 85% that we aim to extend up to 95% in the near future together with and enlargement of the slate slabs samples to widen and accelerate the learning process of the deep learning algorithms supporting our Computer Vision based solution.
Impact will be quantified once it has been implemented. However, we already foresee the following:
• Optislater will support differentiation of European natural slate slabs that accounts with higher quality, to those imported from other regions, particularly China.
• Will support an industry that struggles due to skilled workers shortage for that specific qualification in such remote rural areas.
• It will increase competitiveness of Slate processors by means of more efficient performance respect to manual activity.