Yokie is a people-powered search & discovery engine that harnesses the social potential of millions of people on realtime social networks like Twitter, who have a habit of sharing 100s of millions of web links per day.

PreTRACT is novel image analysis system uses Diffusion Tensor Magnetic Resonance Imaging technology to generate muscle fibre representations and provide predictive metrics of early signs of injury that could lead to muscle / ligament tears.

In the always-connected 24-7 online marketplace, up-to-date knowledge is paramount for good decision making. In many timezones across the globe, content is emerging which can have an effect on the reputation of a firm, individual or product. Depending on the trust level attached to the source, a single social media message can cause significant damage to the reputation of an entity, as experienced when a tweet was sent from the hacked Associated Press Twitter account, causing the Dow Jones Index on Wall Street to drop sharply. Online monitoring of the reputation of an entity enables quick reactions to current events or market fluctuations.

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 insights will be at a considerable time interval after the original events occurred, and in many scenarios being able to analyse the live data stream and hence reduce this response delay is of critical importance. Clustering is a core data analytics technique whereby similar entities are automatically identified and grouped together. This drives many common applications of data analytics such as detecting anomalous or fraudulent activity, identifyting market segments and user behaviours, reporting spam and emerging topics and patterns. CeADAR has developed a high-throughput, scalable clustering solution for data streams that brings real-time, ‘live data’ capabilities to these advanced data analytics tasks.

Different areas of the economy require precise forecasts of future events based on knowledge collected from the past.Technology platforms which are accurate and effective in acquiring and processing such information are of great value to the market because they assist in planning and helping to prepare for what is coming. Unlike typical forecasting which can be based on informal methods, optimal forecasting methodology can be conducted based on scientific tools to assure proper outputs. As a result, appropriate feedback on a given problem can successfully warn if the process under investigation is heading towards an undesired direction. This result, in turn, can support managers with meaningful information that allows them to improve planning. An automated forecasting platform can result in trustworthy analytics which leads to better decision making processes. Successful forecasting can minimize risk which is associated with the unknown future, and if properly utilized may give rise to the profits which would not be achievable otherwise.

Finding persons of interest on social media is not a trivial task and current approaches to people search are simplistic and based on collaborative filtering. There is a growing need to find people in a particular area of expertise, location, and/or business. IdentityMatch provides near real time retrieval of results from user searches.

Object detection, especially small object detection, is a well known and studied image analysis challenge. An example of which is finding predefined brands/logos in a large number of images or a continuous image stream in real-time. Current logo detection applications are generally run in an offline way, and cannot handle a large, continuous image data stream and process it in real time or near real-time.

There is a large quantity of information communicated through speech audio streams (phone calls, broadcasts, commentary etc.) across many industries. In many instances this information is of potentially high value but is discarded for lack of efficient and accurate information retrieval strategies. Speech recognition technologies partially solve this problem but the output texts are still high volume, noisy and difficult to interpret and summarize.

With the rise of service customisation, data analytics is becoming increasingly important so as to understand the needs of a company's customers. In order for the potential of data analytics to be fully realised, analytics tools must be developed for use by the widest user-base possible. Under the CeADAR Intelligent Analytic Interfaces: Ease of Interaction theme, smart analytics tools are being developed to aid non-analytics specialist users in exploring datasets and performing analytics tasks. The first task selected for focus under this theme is customer segmentation, an especially common data analytics task and one that organisations tend to perform when they first start to use data analytics. Presenting segmentation results to the user in a way that is interpretable is the key to the success of SmartSeg. To understand customer segmentations analytics practitioners compare the distributions of features within a segment to the distributions of the same features in the underlying full population. While major existing analytics tools have enabled widespread adoption of data analytics, they remain mostly targeted at expert analytics users. At CeADAR we are developing smart analytics tools for non-analytics experts - the so called next billion users.

Providing analytics-driven insight does not guarantee that people will take note of it and change their decision-making behaviours. For example, did a customer identified as a churn risk respond to the intervention recommended; or did loan officers in a bank actually base their lending decisions on the output of risk models? Measuring the success of any analytics-driven project, therefore, requires looking beyond the insights that are produced to ways in which these insights are communicated and delivered to ensure that behavioural change takes place. This research will benefit any company that wishes to make sure that the application of analytics results produces the required or expected outcome. For example, did a customer identified by a supermarket as a user of baby products take advantage of a promotion on nappies that was on offer that week? If not, can a message be tailored for that customer to encourage them to take advantage of such a promotion the next time? Using tailored messages, our research is working on encouraging the greatest level of change in a customer/user’s behaviour .