|Innovation Thinking||Kevin Turner||Climate and culture for innovative thinking|
|Integrating the physical world||Christopher Gibson||Edgware Fabric is a new open source technology developed by ETS that integrates people and devices at the very edge of the network, bringing the benefits of middleware to the Internet of Things.|
|The Bluemix Garage - IBM as a Start-up||Andy Bravery||With Bluemix IBM now has an offering that is relevant and accessible to tech start-up companies and even individual developers. The challenge is how to sell to this market segment which is unlike any of our traditional customer sets. Bluemix Garage is about meeting these new potential clients on their own turf and encouraging them to make Bluemix the platform of choice for their technology-led businesses as they position themselves for a high growth future.|
|Security - What matters most?||Saritha Arunkumar||ETS works on various interesting and unique aspects of Security, the things that matter most. Come hear about location security, Geo-spatial access control, Biometrics and modern cryptography|
|Node-RED: a year in the life of an open-source project||Nick O'Leary||Node-RED: a year in the life of an open-source project|
|Tackling Cancer with Machine Learning||Graham White||Recent ETS involvement with Cancer Research UK|
|Watson Update||Andy Naylor||ETS involvement in Watson development|
|Transatlantic research with the ITA||John Ibbotson||Innovation from ETS as leader of the International Technology Alliance research programme|
|Gaian: And you thought you had seen it all in the information management space?||Patrick Dantressangle||Introduction to the ETS Gaian asset and the part it can play in information federation|
Please contact firstname.lastname@example.org for more details on any of these talks.
Clients who maintain buildings spend many months building rules to create alarms when something goes wrong. However:
- It’s time consuming and tedious to manually enter all the rules
- Even once a large number of rules have been established, the system is still rather fragile and produces lots of false alarms. This is expensive because it wastes the engineers’ time.
- The system cannot learn over time (e.g. a new employee who likes to keep their office very cold).
The objective of this piece of work is to use IBM’s “big data” tools (both from the building and outside it) to learn the conditions that require an engineer’s attention without writing rules, and make it simpler and much cheaper when building, or extending an existing building. Instead of requiring rules to be manually entered it would sift through all the historical sensor data from the building to learn the dominant patterns and relationships. Once a model has been learnt, the system should produce an ‘anomaly’ score for any new data, and could also update its model over time. If a suitable model is used (a ‘predictive’ model as opposed to a ‘discriminative’ model) then the system could also make predictions. Our plan is to build a prototype of this system, whilst also recording a large, home-grown dataset to show off IBM’s big data tools.
The Hursley building management system has over 15,000 objects. These are connected using a protocol called BACnet (Building Automation and Control NETworks) over IP. This BACnet IP network is physically separate from IBM’s ’9′ network. We have written an application which continually polls all 15,000 objects on the network to request their present value. It takes a little under an hour to poll all 15,000 objects once. We store the data locally on the logging machine. Every midnight, the logging machine disconnects from the BACnet, connects to the IBM ’9′ network and squirts the last day’s data to the ETS instance of BigInsights and then reconnects to the BACnet to continue data collection.
Before we can build a statistical model of the data, we need to visualise it to get a feel for what’s going on.
The plot below shows 3 weeks of data for about 100 BACnet objects. The X axis represents time. X axis ticks and grid are positioned daily at midnight. Each row represents a sensor (i.e. each tick on the y-axis is a single sensor). The sensors have been ordered by how well they correlate (so sensors close together behave similarly). The output for each sensor has been linearly mapped to the range 0 to 1. Red indicates missing data.
Some objects show daily and weekly patterns (for example the ‘cooling setpoints’ and the ‘internal room temperatures’ marked on the plot below). Some objects do not appear to follow any obvious pattern. Some objects return discrete values (e.g. ‘active’ or ‘inactive’) whilst others report continuous values.
The next phase of the project will be to build statistical models for the data. The first approach will be to build models using fairly simple statistical techniques (probably little more complex than is taught on A-Level stats modules). For each continuous-valued objects which follow a regular daily pattern, we will learn a simple normal distribution for each hour of the day. For continuous-valued objects which do not follow a daily pattern, we will just use regression. For discrete-valued objects, we will try using Markov chains conditioned on the hour of the day. Once this is done, we will look at simple ways to model correlations between objects.
In parallel with this statistical modelling, we will build a pretty user interface to show to clients.
If this all works, and if there’s time left then we might try some sexier statistical techniques like recurrent neural networks (especially ‘long short term memory (LSTM)‘, which excels at modelling time series data). These models are computationally expensive to train so we might need to train on a fast GPU. Or, further into the future, maybe the code could be re-implemented on IBM’s new ‘neurosynaptic’ chips produced under the SyNAPSE project.
Jack (aka Daniel) Kelly, 16 Sep 2014
For the ETS hack day, the team of Peter J, Markus, Hamish, Yi and I experimented with the Oculus Rift (OR) which we had been lent.
We started by deciding the goal for the project – To create an interactive virtual environment that assists in controlling the real environment (including display of real-world data in the virtual world).
The aim would be to help
- Trainee engineers – they could learn how to maintain buildings to some extent without having to be in the building
- Emergency services rescue planning tool
- Engineers to peel back the building to see locations of pipes etc
- ETS – gaining experience in Virtual Reality, Augmented Reality and 3D Models
There were 5 activities that needed to be done:
- Get the 3D model showing in the OR.
- Change the socket based interface to the client centre for an MQTT one
- Publish MQTT messages from within virtual environment
- Allow highlighting of objects from within the model
- Create a control menu within the virtual environment.
By the end of the first day, the 3d model was working reasonably well in the OR, and the MQTT interface to the lab was ready to test. MQTT messages could be published from within the environment. There was a lot more work to be done to embed html within the virtual environment which did not move around with the world.
By the end of the second day, the five activities were complete – but did not all string together seamlessly.
Markus and Yi (and a bit of Peter) have since spent a couple of days ironing out the bugs and improving the performance – and this led to its first customer demonstration to a large energy company, in the context of Building Information Modelling, on Wednesday. A nice demonstration is now packaged with start-up script, and available for lab tours in the ETS lab.
Kevin Brown, 12 Jun 2014
A service bus for the physical world
The boundary between the digital and physical worlds is blurring. Sophisticated new sensors are affordable, easy to deploy and capture detailed information about the world in which we live. Mobile (and increasingly autonomous) devices are commonplace and reaching out to inaccessible and inhospitable places so that people no longer have to. Smart machine-to-machine (M2M) interaction — often driven by sensor data — is creating an ecosystem of intelligent devices that is rapidly changing the way that we live and work in the physical world.
Edgware Fabric is a lightweight, agile service bus that was developed for M2M solutions. It provides many of the features found in an enterprise service bus - discovery, routing, message transformation etc. - but built for resource constrained, dynamic and/or unreliable environments. Edgware Fabric integrates systems at the very edge of the network into a service-oriented architecture, running on (or alongside) the devices that it connects.
Edgware Fabric has been developed by IBM Emerging Technology, and released as an open-source project on GitHub, under the EPL license.
Related Focus Areas
On Monday 12th May, 15 Emerging Technology engineers gathered in the Client Centre for our inaugural Bluemix Experience Day. The objective of the day was to bring together experts from across the IBM Emerging Technology Focus Areas to take a deep dive into IBM's Codename: Bluemix platform and come up with ideas for new innovation projects which could exploit this new technology that is currently in Open Beta.
Bluemix is a platform-as-a-service (PaaS) offering, which takes open source Cloud Foundry as its base and extends it with a Dashboard for developers to manage their applications and services, a rich set of browser based development tools called IBM DevOps Services and an extensive catalog of IBM, Partner and Community created runtimes and services to support the rapid development of new Systems of Engagement.
Cloud Focus Area leads Mike Edwards and Andy Bravery hosted the day, assisted by Marc D'Arcy who already has extensive experience of using Bluemix to create mobile applications through client work eariler in the year. The other 12 participants quickly organised themselves into pairs, and selected particular areas of interest to go and explore. These included the various development tool integration options that Bluemix offers, which include Eclipse plug-ins for Cloud Foundry and integration with Rational Tooling. Individual pairs selected to develop in their preferred language, such as Java, Node.js and Ruby, exploiting the polyglot capabilities of the Bluemix environment.
As the day progressed, there was lively discussion around how other emerging technologies such as the Gaian database and various security technologies could add value to developers working with Bluemix, and the rapid development lifecycle capabilities of a PaaS environment meant that these discussions could quickly move on into prototyping of ideas, without having to spend time provisioning new machines and installing software stacks. Bluemix even allows the developer to specify the web address they want their application to have, and makes it available at the click of a button eliminating the need to involve IT network management in the deployment of new applications.
By the end of the day, a long list of follow-on project ideas had been drawn up, which will hopefully soon start to bring valuable new capabilities to the Bluemix platform and our clients who want to exploit it. Why not sign up for your free Bluemix Open Beta account today, and see why the Emerging Technology team are making this one of their key enablement tools going forward.
Dr Dave Watson, Director, Emerging Technology has been elected as a Fellow to the Royal Academy of Engineering. The Academy honours the UK's most distinguished engineers. It aims to take advantage of the enormous wealth of engineering knowledge they possess and, through the interdisciplinary character of its membership, it provides a unique breadth of engineering experience to further the art and practice of engineering in all its forms.
This significant accolade recognises Dave's leadership of IBM’s Emerging Technology Team, and the extent of his involvement with national research bodies.
Raising awareness, influencing change
The Royal Academy of Engineering is the principal national body for engineering, bringing together outstanding engineers from across a wide range of industry sectors. The Academy works to improve public awareness of engineering, and to influence change in government policy on behalf of the engineering profession. It is very vocal in its support of Science, Technology, Engineering and Mathematics (STEM) subjects in schools.
The Academy comprises around 1,500 Fellows, with up to 60 new Fellows being elected each year from nominations submitted by existing Fellows. Three other UK IBMers are already Fellows of the Academy: Ian Nussey (University Relations), Mandy Chessell (Information Management) and Pieter Lindeque (Global Business Services).
Dave, who is also a Fellow of the Institution of Engineering and Technology and a chartered engineer, received significant backing for his appointment from existing Fellows in both academia and industry.
Dave began his IBM career in the UK Scientific Centre in Winchester, and progressed via senior management positions in Websphere MQ and CICS product development at Hursley, to become the Director of ETS around 12 years ago. He is also the joint leader of a major US/UK defence research project - the International Technology Alliance in Network Science - which involves more than 20 partners in industry and academia.
Dave has also been actively involved with the Engineering and Physical Sciences Research Council (EPSRC) since 2004, and has chaired a number of EPSRC and Research Councils UK advisory boards. In 2009, Dave was appointed to the governing body of the EPSRC, which allocates research funding across UK universities.
He describes his election as a Fellow of the Royal Academy of Engineering as ‘a fantastic networking opportunity which will enable me to engage with the top echelons of the engineering profession in the UK’.
“Also, as a representative of one of the newer engineering disciplines, I will aim to encourage the development of professional recognition for engineers who are working in the IT industry.”
Node-RED is the visual tool for wiring the Internet of Things that Nick O’Leary and Dave Conway-Jones have been working on. What started as an educational exercise to get to grips with technologies such as Node.js and d3, soon turned into a tool that provided real value in client engagements.
One of the goals all along was to open-source the tool; to build a community of users and contributors. All the approvals needed are in place and at the start of September Node-RED has been released as an Apache v2 licensed open source project on github.
You can find out more here: nodered.org.
Congratulations to Emerging Technologies Saritha Arunkumar. Saritha, an expert in Security, was shortlisted for the Technology & Digital category of the 2013 Women of the Future awards. Saritha has built a reputation for knowledge & presentations in the field, and is also currently working for a PhD in mobile security.
This Category is brand new to the awards and has been introduced due to the strength of the candidates.
The Women of the Future Awards is the largest national search for exceptionally talented women. The hunt unearths the next generation of high-flying women across nine industries, including technology, media, business, arts and science.
This is the second year that members of ETS have been recognised in these awards, last year Helen McAllister (nee Bowyer) was selected for the Science and Technology Shortlist.