Wen Gu & Shaun Smith, of Cohort 3 & 4 respectively, recently attended the 2-day Future Powertrain Conference (FPC2018). The FPC2018 invites over 500 delegates from both academia and industry to present innovative research ideas and discuss the future of the industry.

This was the first conference for the students since joining the CDT-EI and the main reasons for attending was to first potentially discover new research topics and secondly anchor their own research by considering where they could add their knowledge to the problems in the industry. In addition, the FPC2018 offered networking sessions throughout both days allowing the valuable opportunity for the students to fully immerse themselves in the sector by speaking to experts in the industry and open the door for possible collaboration.

The students highlighted several presentations that were very useful for a variety of reasons. These included, but were not limited to, talks by Prof Colin Garner of Loughborough University who challenged us to consider the most efficient sources of energy and to revisit the debate of “Battery vs Internal Combustion Engine”, Richard Burke of the University of Bath who presented a catalogue of research opportunities and Doug Cross of Leadfoot who provided a talk on the future of autonomous vehicle and if they can keep up with the expectations of the consumer. Furthermore, talks by Dr Yan Wang of Ford and Dr Mark Peckham of Cambustion provided a greater insight of the challenges that face the sector from an industry perspective

Wen Gu presented a poster at the conference to demonstrate his current research. By implementing the machine learning algorithm, he developed a model learning approach to reflect the engine behavior faster and more accurate. The adaptive model predictive control method is employed to dynamically optimise the engine fuel economy based on the developed time-varying model. This approach is promising in improving fuel economy of powertrain systems and leading the way to next generation low carbon engines. At the end of the conference, he won the third prize of poster competition section.

The future powertrain conference returns in 2019 at the National Motorcycle Museum, Solihull, where students will again be attending representing the CDT-EI.

For further information visit futurepowertrains.co.uk/

 

1.0.0.17

Deep Learning Workshop

22 February 2018

To help apply and develop their literature research on Deep Learning, Jake Rankin attended the Deep Learning Workshop. This would both provide experience with applying deep learning and an opportunity to discuss specific considerations with leading practitioners for implementing deep learning systems. The Centre for Modelling and Simulation (CFMS) Hosted a Deep Learning Workshop at the Bristol and Bath Science park, consisting of talks from Cray, Nvidia Deep Learning Institute, TSystemes and CFMS. This was then supported by a workshop that used Nvidia’s Deep Learning GPU Training System (DIGITS). The purpose of this event was to help organisations understand the challenges of implementing deep learning and the presentations were focused on business applications of deep learning and clarifying the mechanisms of deep learning.

Chris Hegarty (Cray, AI Enterprise Sector Development Lead) gave a useful presentation on the hardware and software required for the implementation of Artificial Intelligence Systems, highlighting several useful toolkits such as CNTK, TensorFlow and Caffe2 (All of which are available for use), but also highlighted a word of caution with regards to the data-processing required (Exceeding well above 25 Gflops) and the costs for algorithm training (~$25k). Adam Grzywaczewski (Nvidia, Deep Learning Solution Architect), who also led the Deep Learning Institute workshops, explained the workings behind neural networks very concisely, with focus on Convolutional Neural Networks (CNN), which would be the focus of our workshop.

The Deep Learning Institute workshop applied deep learning techniques to image processing. This was broken down into three lessons:

-          Image Classification with DIGITS

-          Object Detection with DIGITS

-          Neural Network Deployment with DIGITS and TensorFlow

The conference was a useful experience that has helped to focus literature research and consider practical constraints for the project. The networking was a useful insight of business opinions on various deep learning methods and helpful feedback was shared.

For those interested in finding out more about Nvidia DLI and future workshops, please visit www.nvidia.com/dli

We are part of the Digital Economy CDT Network, that supports and develops training activities for postgraduate research students. In early February we were delighted to attend the annual meeting, showcase and careers symposium held at the Digital Catapult, London.

Day 1 was characterised by fruitful and engaging discussions about the range of training activities and support DEN offers and could offer it student members. Attendees eagerly awaited news about the Summer School 2018, being hosted this year by the Centre for Digital Entertainment and with topics such as AI and machine learning on the agenda it was clear this year’s event was going to draw a big crowd. Day 1 concluded with a CDT showcase, allowing the member CDT’s to demonstrate the quality and quantity of research taking place at their centres and for the researchers to find out more about their peers across the UK. A particular highlight was the VR game simulation from the IGGI CDT team!

Careers was the focus of the following day and saw guest speakers, all who were alumni from CDT members of DEN. Each speaker shared their career journey, the decisions, complications and successes achieved along the way. There were speakers from academia and industry with both SME’s and large enterprises represented. The talks gave a realistic insight to what lies on the other side of the PhD thesis and each speaker shared their thoughts on what a doing a PhD in a CDT has meant to them and what they would do differently (finishing the writing process before getting a job was a reoccurring theme!).

Den Showcase

The West University of Timisoara hosted an international winter school on one of the most dynamic and important sectors of computer science, Big Data. The event covered a broad spectrum of industrial research and innovation with potential over scientific discoveries, medicine, engineering, business models and society. Attendees were master students, PhD students and industry practitioners from over 30 different countries (most participants from outside the country being from USA, Italy and German).  Among the tutors leading the specialised sessions were Jeffrey Ullman, Stanford University, and Bing Liu, University of Illinois, Chicago.

Cohort 3 research, Orange Gao, attended the BigDat winter school to update herself about the most recent advances in the area of big data and to know current research and industrial innovation in different fields. Her major is computer science, specifically on computer vision, and there are many common algorithms with big data, so she hoped the course would help her to broaden her knowledge and understand real applications in commercial world to prepare the future career choices. She chose 3 courses, which was running in parallel during the whole event. Semantic Technologies for Open Data Publishing, which was a fantastic introduction to ontology-based data management (OBDM), Network Science Fundamentals, in which she deep-dived into recent advances in stochastic flow clustering of networks and Lifelong Learning and its Applications in NLP, which is an advanced machine learning paradigm. Since attending the winter school, her future plans are to, firstly, sort out the notes which she kept during the courses! The biggest gain she sees from BigDat was the change from thinking towards to the knowledge. She explains that researchers should not only digest necessary domain knowledge but also understand knowledge’s dynamics and constantly provide technical vision.

Several CDT-EI researchers from Heriot-Watt University are undertaking a 6-month training programme in applied data science. The course, which is being run by Cambridge Spark Ltd will take place over 20 weekends from February 2018 to July 2018. The programme will be project-based learning over 9 modules covering topic areas such as cloud computing and databases, neural networks and deep learning. The researchers will also undertake an industry sponsored project as well as attend a final showcase weekend. Lucas Kirschbaum, CDT-EI, Cohort 4 says

The data science course I will attend is an elaborate training in the most recent data processing techniques. Therefore, this course will not only build up fundamental knowledge but also support me understanding the practical aspects of managing the data I collect within the scope of my PhD. I am hoping to gain valuable insights of how to set up customized algorithms for different testing scenarios, validating the data and in general how to approach big datasets.

Dr Will Whittow has been listed as a finalist for the 2018 FDM Everywoman in Technology awards.

Dr Whittow, senior lecturer at The Wolfson School of Mechanical, Electrical and Manufacturing Engineering, and one of our PhD supervisors, has been named as one of three finalists for ‘The Male Agent of Change’ award.

This brand new award will be presented to a male recipient who has shown a commitment to encourage and champion women to progress in the world of technology.

Maxine Benson MBE, co-founder of everywoman comments: “At everywoman, we recognise the role that men also play in ensuring a strong pipeline of female talent, which is why this year we have introduced the Male Agent of Change Award.”

The awards are in their eighth year and celebrate some of the most inspiring individuals that have changed the world of technology both in the UK and internationally.

This year’s theme was Improving Tomorrow’s World, which aims to highlight the significance of supporting girls and women into studying STEM subjects, despite the dominance of men in the sector.

The winners will be announced on Thursday 8 February at the awards evening which will take place in London.

Dr Whittow has previously won the Women’s Engineering Society ‘Men as Allies’ award for his efforts to support female colleagues and students in the field of engineering.  

Good Luck Will!

Cohort 3 researcher, Darius Roman, visited the Center for Advanced Life Cycle Engineering (CALCE) to attend the Failure Analysis short course, present his research to CALCE students and faculty, and to discuss his research challenges with the CALCE team.

Darius’ PhD research project involves a fusion prognostics approach that incorporates failure analysis, modelling, condition monitoring, machine learning and prognostics techniques to predict the remaining useful life in bottom hole assembly electronics for oil and gas companies, including Baker Hughes a GE Company—his current project sponsor. Following the presentation, Prof. Michael Pecht met individually with Darius to discuss best methods and ideas to contribute to the success of the research and the project. Darius is a member of the Smart Systems Group (SSG) at Heriot-Watt University, where he acts as an ambassador. The group is led by director, Dr. David Flynn, an Associate Professor at Heriot-Watt University and Co-Director of the CDT-EI. The SSG’s view is that global society is placing increasing demands on its critical infrastructure, systems that deliver vital services such as energy, transportation, telecommunications, food and water, the built environment and healthcare. The systems within these sectors are increasingly complex and interdependent, interacting at a global scale. This complexity is required for efficient operation, but also makes them more susceptible to cascading failure under stress. The Group believe we must transform data into actionable information and utilise this insight to create innovative, data informed, Smart Systems that can assess, adapt and respond to dynamic conditions.

The collaboration between CALCE and SSG began with the seminar titled “The Era of Embedded Intelligence” where Prof. Pecht acted as a key note speaker on PHM. The seminar brought together global leaders and innovators in Embedded Intelligence from industry and academia on how this field of research is influencing future product development, business models, resilience of critical infrastructure and exploration within extreme environments. The seminar aimed to promote the importance and impact this area is making to society, and to engage the audience on how we innovate and train the next generation of engineers, scientists and business people – to prosper in this data driven age. CALCE and SSG are currently looking for future collaboration where students and academics alike could visit, exchange research ideas and discuss research challenges. Prof. Pecht will be visiting HWU periodically in an advising and educating capacity to further straighten the collaboration.

To read more about the collaboration visit here

To learn more about SSG visit here

On 7th December 2017, the Doctoral College hosted the annual Loughborough University Research Conference (#LboroResConf17) for doctoral researchers, research staff, academic staff and professional service staff. The event provided attendees with an excellent opportunity to network with one another whilst learning more about the vast range of research conducted at Loughborough University and Loughborough University London.

The theme of this year’s University Research Conference was ‘Building Research Excellence'. In total, there were 19 oral presentations, including Cohort 1 researcher Joe Holt, and 41 poster presentations, inlcuding Cohort 2's Gaj Sivayogan and Cohort 3's Marcus Pollard.

Joe Holt has said “I enjoyed the opportunity to present my work to a wide and varied audience. Trying to tailor my presentation to a general audience helped me to distil down the more important points of my research and really focus on the parts that matter.”

follow us
@cdt_ei


General Enquiries Contacts:

Loughborough University

Loughborough, Leicestershire
LE11 3TU
United Kingdom
Tel: +44 (0)1509 227 518
CDT Office
cdt-ei@lboro.ac.uk