We have worked with many clients and we always like to hear they come out from the cooperation happy and satisfied.

• Our research for Digital Catapult focused on two specific areas of Natural Language Processing: abstractive text summarisation and extractive text generalisation. Following extensive research and testing, we discovered algorithms that would be most efficient at providing an insight into the contents of a passage, whilst also adapting existing methodologies that aim to automatically remove sensitive information about individuals and companies. BLEU (BiLingual Evaluation Understudy), METEOR (Metric for Evaluation of Translation with Explicit ORdering), SpaCY and numerous other metrics were utilised in the process of developing an algorithm that would be most effective at imitating human speech and limiting access to confidential information without distorting original meaning.

  

  Digital Catapult

  NLP

• During our collaboration with Envitia Ltd on a mutual project for the UK Environment Agency, we were responsible for creating a system that would automatically recognise the altering water levels across the UK and warn the population of potential floods up to two weeks in advance. Through the power of Machine Learning, AI and Big Data analysis, a model was created to recognise the base water level via CCTV footage to subsequently estimate the probability and likely severity of a flood.

  

  Envitia

  Flood prevention

• Furthermore, we closely worked with the UK Ministry of Defence through Envitia to complete a project based around the recognition of foreign military vessels from satellite images. Initially, a simple model was developed to examine high-resolution images of vessels in the Red Sea during the blockage of the Suez Canal by an ‘Evergreen’ freighter in 2021; this allowed for all vessels to be automatically identified and classified. Over time, this model evolved to track the movement patterns of vessels, providing a well-structured foundation for distinguishing between military and civil vessels. Ultimately, a working product was created within one month that was capable of independently identifying different categories of military vessels, such as frigates, warships and destroyers. An API-based approach was employed in order to respond to user requests and make the necessary data available through a web interface.

  

  Envitia

  Satellite image processing

• Through a comprehensive analysis of nuclear unit performance data, we were able to identify the most valued indicators and redesign the IAEA power reactor information system (PRIS) website to improve navigation and ease of use. New information was gathered from open sources and proof-checked with industry experts, prior to its inclusion on the PRIS website. Moreover, data and performance indicators were provided by over 30 national bodies for future analysis, cleaning and processing. The final product is available on the IAEA PRIS website.

  

  IAEA

  PRIS

• Whilst working with Methods Analytics, our primary role was to ensure that quality is embedded into the production process, and that the final product satisfies all key requirements. Therefore, process maps were integrated into the QA system, to enhance productivity and minimise losses. Furthermore, training was provided for all members of staff involved in the production cycle on how to manage projects and write code in the most efficient manner to prevent a duplication of efforts. Consequently, the long-run supportability and versatility of the code improved, with a library of standard functions created to increase the speed of development.

  

  Methods Analytics

  QA

• Similarly, we were also involved in transforming business requirements into a tangible set of technical tasks which would subsequently be used to define the project’s architecture. By following the Agile and Scrum methodologies, communication between clients, stakeholders and suppliers was significantly improved, thus helping to avoid the common principle-agent problem.

  

  Methods Analytics

  QA

• Similarly, an analysis of all the available information sources related to COVID-19 was undertaken in 2021 to limit the spread of COVID-19 and predict its future economic impact. By managing the project through MS Azure, and constructing a data pipeline using MS Synapse, we were able to efficiently process the data through a cluster approach; with calculations and analyses completed in parallel, the speed of execution tripled in comparison to conventional methodologies.

  

  Unided Nations

  COVID-19 Analysis

• One of the most significant projects completed for the United Nations involved the assessment of energy availability for developing countries on regional and settlement levels through geospatial analysis. Utilising advanced Machine Learning methodologies had allowed us to extract, combine and discover dependencies between the population and illumination layers. As a result, a baseline was created to determine the specific criteria under which electricity access levels could be classified and recognised accurately.

  

  Unided Nations

  Energy Access Assessment