Advanced Analytics

Project Description   MARKET NEED ML4GE explores machine learning techniques to analyse smart-meter data. The idea is to use deep learning based clustering approaches to find similar energy consumption patterns and to put these similar patterns in the same group or cluster and then use these patterns to forecast total demand for each cluster. Recently smart meters have been widely deployed in many countries. These devices replace conventional electrical meters and are able to provide measurements for time intervals of typically less than one hour and can send these to the utility. This technology provides utilities a large amount of data

Project Description MARKET NEED EdgeAI explores the whole pipeline of an edge AI project from creating and training a neural network to pruning and quantizing it. Also, it creates embedded code to deploy the network on an edge device. Edge AI is predicted to be used in billions of electronic devices to add more advanced AI capabilities to those devices. Certain additional steps are needed to run these memory and computationally intensive algorithms on edge devices. Hence, we created  a complete pipeline right from model creation and training,  to pruning and quantizing it and finally automatic embedded code generation. We explored various

Project Description MARKET NEED AI for Bill Reduction investigates the use of AI for the task of optimising energy usage in both commercial and domestic settings. The idea is to use reinforcement learning (RL), given the potential it has shown in solving complex optimisation problems. Businesses have several incentives to reduce energy consumption. Lower consumption means lower energy bills and saved money. This is especially relevant to high consumption sectors such as manufacturing and heavy industry, and given the fact that most of the world’s energy is still produced from fossil fuel sources, reduced consumption also helps to combat climate change

Project Description MARKET NEED Natural language Processing (NLP) combined with machine learning has been used for many applications such as sentiment analysis, topic modelling, document categorisation, spam detection, fake news identification, and chatbots. Explaining why a machine learning model made a particular decision is key to trusting AI based systems as well as complying with legislation such as the GDPR. Although a number of different explainable machine learning libraries and tools have been developed, it is often unclear as to which to use in different scenarios, and how these work specifically in the context of text data. TECHNOLOGY SOLUTION The

Project Description MARKET NEED Earth Observation (EO) is a booming industry with many wide ranging applications. The sheer volume and complexity of EO data requires the application of novel AI algorithms. AI-based computer vision models have been emerging as effective and efficient tools to analyse and extract essential insights from EO imagery data. However, applying such models to EO imagery requires access to large training datasets, as well as relevant machine learning and satellite imagery skills, making it difficult for researchers, scientists, and companies to develop or test their use-cases. TECHNOLOGY SOLUTION We developed a flexible pipeline that integrates and

Project Description MARKET NEED As we are moving towards a digital society, our world has become more and more connected. This seamless connectivity has transformed and accelerated the way business is conducted, but it also increases exposure to cyber threats. The main problem when dealing with modern cyber attacks is the sheer amount of data which passes through a computer system, the complexity of automatic attacks, as well as the high frequency of attacks. This project explores applying Machine Learning to the problem of malware detection – the most prevalent cyberthreat. TECHNOLOGY SOLUTION We developed a machine learning library to

Project Description MARKET NEED Information contained in text documents is central to the legal profession e.g. contracts, end user agreements, industrial regulations etc. Text Analytics and Natural Language Processing (NLP) allow for the automatic extraction and processing of information from text documents. These techniques are increasingly being applied to legal tasks such as contract drafting, automatic compliance checks and extraction of contract elements e.g. contract start and end dates. TECHNOLOGY SOLUTION CeADAR’s Text Analytics for Contract Understanding demonstrator application shows how these techniques can be applied to the real world task of mobile app privacy policy analysis. The demonstrator allows

MARKET NEED There is an information overload from unstructured text used as business leads (knowledge on customers, markets  or technologies) from which users need to find the Facts:  the relevant Entities, the Links between Entities and their evolution. Extracting practical information from text is a complex task requiring human understanding of semantics. The Knowledge Graph (KG) technologies bring a competitive edge as part of the Semantic Web. KGs can capture the network of Relationships between Entities in a graph structure, while also building a Knowledge Base (KB), designed to enable automated reasoning. Existing open-access industrial knowledge graphs have mapped billions of entities from large scale web

Project Description MARKET NEED All industries are now collecting large volumes of data from diverse sources. However, when developing a predictive analytics application it is challenging to know how best to utilize these different data modalities. Deep Learning has become the mainstream machine learning method due to its impressive performance in many applications. However, multimodal deep learning research currently focuses on only very specific settings. The project explores the use of deep learning to integrate heterogeneous data sources in a single predictive model for better performance. TECHNOLOGY SOLUTION We implemented a multimodal deep learning library: That allows users to create

Project Description Market Need Although a research area since at least the 1980s, RL has recently attracted interest due to breakthroughs such as Deepstack, a recent algorithm able to defeat professional poker players or an algorithm from DeepMind which is claimed to reduce the energy bill of Google data centres by 40%. However, RL can be complex and challenging to understand. The application we created is aimed at making RL technology more accessible to industry. Our application explains in a friendly and understandable way how DQN and its main parameters work. Since the benefits of RL are potentially enormous, the

Project Description DataFIX poster MARKET NEED Novel business applications use raw, real-life or online data that contains various types of errors. Existing data cleaning platforms lack automation and require high-levels of expert interaction. Hence, identifying and correcting erroneous data is expensive, requiring analysts’ expertise and ad-hoc solutions. There is a real need for solutions that help to automate data quality investigation and where appropriate automated correction of data. TECHNOLOGY SOLUTION Our solution automates the data correction process with an easy to use interface that sits over state of the art algorithms for: Data cleaning Anomaly detection for time-series data, and

Project Description MARKET NEED Graph data plays an important role in big data analysis, and there are an increasing number of companies showing particular interest in being able to derive insights from this type of data. Graph data contains information about relationships among data points. Thus, useful insights can be mined in certain use cases where relationships matter. One major limitation of existing graph data analysis tools is that they require an understanding of many complex concepts and terms such as centrality, modularity, motif finding etc. which are not readily familiar even for data analysts. The EXPERTS project provides a use-case

Project Description MARKET NEED From  object recognition to machine translation, deep learning is being used to automate many complex tasks due to its impressive performance. However, training a deep learning model for a new dataset is challenging. The number of potential deep learning models to fit a dataset is large due to the required complexity to learn the direct mapping from raw input to output, hence expertise is needed to find a suitable deep learning model among many candidates. TECHNOLOGY SOLUTION We  created a demonstrator to allow industry partners to apply deep learning on new labeled datasets in an intuitive manner; it has a simple user interface to

Project Description Market Need Blockchain may be one of the most revolutionary technologies to arise in the last decade, with the potential to transform many industries. Blockchain a pplications centre around the management of value through the use of programs called smart contracts. Value on a blockchain can take many forms including currency, real world assets, identity and credentials. Smart contracts are used to enforce contractual agreements, often using triggers from outside the blockchain to transfer value. A commonly used smart contract in the context of cryptocurrencies is the transfer of money between accounts. The aim of this project was

 MARKET NEED                   One of the most important components of blockchain technology is its ability to transfer monetary value and do so in untrusted environments. Blockchain has garnered much attention recently, primarily as it can be a secure, fault tolerant, highly available, transparent technology which can provide different levels of access to data. These aspects of the technology make it well suited to improve the efficiency of certain financial and legal processes, and also serves as a new way of solving logistics management problems.Comparison of different network topologies. Centralised and decentralised networks both

Market Need High volume, high throughput data streams are common in many industries including financial services (transaction streams), communications (instant messaging, SMS, micro – blogging), web and gaming (action and event streams) and production line environments (machine generated data). The ability to analyse and gain insights from this type of data as events happen, in real – time, can be hugely beneficial . Traditionally data analytics is performed as an off – line, batch process where the results are available hours or even days after the data was produced . This means that any actions taken based on these