Be at the forefront of innovation and work on cutting-edge research by joining the team at TSSG. We focus on a number of areas including Future Health, AR/VR, Artificial Intelligence, Smart Agri, Knowledge Defined Networks, IoT, Molecular Communications and Smart Energy.
Play a pivotal role in TSSG by joining our Business Development team where you will have the opportunity to work with leading companies who are constantly innovating to stay ahead of their competition.
Interested to know what it’s like to work in TSSG? Two of our researchers share their experiences of working directly with companies of all sizes across Ireland to help them achieve their business goals.
Christine O’Meara, Commercialisation Specialist
An Enterprise Ireland Innovation Voucher was secured by OVC to the vale is €5k. The aim of the work was to help the company find innovative ways of staying on top of a variety of key regulatory indicators including regulation changes, standards evolution, inter-jurisdictional cooperation, key areas of focus, infractions and incidents of non-compliance. The work engagement with Odyssey Validation Compliance was preceded by a problem identification and task scoping meeting which involved Oisín Curran, CEO at OVC, Eric Robson, Unit Manager of AI/ ML and Christine O’Meara who would be completing the job. Given that regulation was changing and there were several different sources and types of regulation and guidelines to be considered across a broad range of jurisdictions, it was important to adopt a pragmatic approach to what could be meaningfully achieved in the timeframe involved. Key priorities and a high-level approach was agreed. Weekly calls / status updates were delivered in order to ensure that the client was aware of progress and any blockers/ issues could be resolved in a timely manner. Frequent communication with the client helped ensure on time delivery and output matched expectations and original scope. At project completion, a workshop was held between the client and several stakeholders at TSSG including personnel from other relevant projects to discuss findings and outputs. Some follow up was required and TSSG remained available through calls to support the person at OVC tasked with managing the results thereafter.
Philip O’Brien, Senior Software Research Engineer
The SMART APPI concept evolved from discussions between TSSG and Teagasc following the publication of the food strategy document, “Food Harvest 2020” by the Department of Agriculture, Food & the Marine. This strategy paper gave the concept immediate context as part of an overall plan to promote “smart agri” solutions for Irish industries based on Irish agriculture. Through engaging heavily with two of Ireland’s leading dairy processors, Glanbia PLC and Dairygold LTD, the concept was refined to create maximum impact not only for the processors involved, but for the industry as a whole. The project was completed under the Enterprise Ireland Innovation Partnership Programme. The proposition to the dairy processors was timely as they formulated plans to address the government’s ambitious target of a 50% increase in milk output by 2020, combined with the cessation of the milk quota systems in 2015. They recognised that they needed to accurately forecast and manage the fluctuations in milk production to optimise their processing infrastructures to meet these targets. Thus, the objectives of the project were to develop a set of models that could accurately forecast milk supply. The algorithmic development research focused on two main areas: long range forecasting i.e. forecasting the entire season at the start of the year; and short-term forecasting i.e. forecasting the next 10-30 days. To maximise the results for industry the research was focused on not just the accuracy of the model (i.e. how closely it fit against the actual recorded data) in forecasting the milk curve, but also its accuracy in predicting the peaks of that curve (i.e. peak milk).
The challenge to date for long term predictions of daily milk volumes has always been accuracy of forecasting around the peak milk time period. Previous algorithms have typically underestimated the volume of milk delivered in that time period. This research prioritises that time period and achieves an accuracy of 95% Daily Milk Volume predictions ~150 days ahead of schedule for Glanbia data, and 96% Daily Milk Volume predictions ~150 days ahead of schedule for Dairygold data. The short-term predictions require a much finer grained analytical approach and as such neural networks provide the capability to deliver high accuracy over volatile data. However, before a neural network can be effectively used to predict values, a model must be fitted to the data by training the network with a significant portion of the real dataset. The neural network model produces highly accurate results – for Glanbia a consistent 94% accuracy throughout the 10-day period regardless of the time period being predicted (i.e. 10 days in Feb, vs 10 days in May/June). The challenge associated with this analysis is maintaining the accuracy the further the forecasting window is pushed out to. In this instance the research demonstrates a 99% overall accuracy for 20 days, and 98% accuracy when the forecasting window is extended to 30 days. For Dairygold a consistent 98% accuracy throughout the 10-day period regardless of the time period being predicted (i.e. 10 days in Feb, vs 10 days in May/June). In this instance the research demonstrates a 99% overall accuracy for 20 days, and 93% accuracy when the forecasting window is extended to 30 days.
A testament to the success of this project is the continued collaboration between the partners as part of the SFI Research Centre, VistaMilk
Want to learn more? Click here for more news on TSSG research and commercial engagements.
The Innovation Voucher Call opens January 9th – January 23rd. We can help your company maximise the €5k funding. Click here for more details