Using data mining to Do things better

– By Billiejoe Charlton, KTP Associate, Do Something Different

As part of my KTP work with Do Something Different Ltd and University of Brighton, I recently attended and presented a paper at the 7th International Digital Health Conference in London [link: http://www.acm-digitalhealth.org/ ]. Held at 30 Euston Square – the headquarters of the Royal College of General Practitioners – the conference offered the opportunity to disseminate the scientific findings from my KTP project to an interested and knowledgeable audience, and raise awareness of the vital work that Do Something Different [http://www.dsd.me/] is doing to help people change their lives for the better. It was also a wonderful chance to network with like-minded professionals from a wide variety of backgrounds, and learn about exciting new developments in the field of Digital Health.

The theme of the conference was “Global Public Health, Personalised Medicine, and Emergency Medicine in the Age of Big Data”, and it attracted experts from many fields, including medicine, disaster management, sensor technologies, data mining and social marketing. Kicking things off was Dr Oliver Morgan from the World Health Organisation, whose fascinating keynote asked, “How can we make better use of data to protect people’s health and save lives?”. Dr Morgan described the WHO’s development of a new global surveillance system for disease outbreaks, which will bring together data from national public health systems as well as from less structured sources such as news and social media reports. This set the tone for an event where the focus was firmly on using emerging technologies not for the accumulation of profit but for the benefit of all.

The research I presented is about how we have used data mining techniques to improve the behaviour change programmes delivered by Do Something Different. Each such programme consists of a series of personalised “Dos” – small recommended activities to help people practice behaving in new ways and break their habits. These behavioural prompts are delivered by a smartphone app, or by SMS or email. The approach is based on decades of psychological research, and programmes have been designed to address many personal development goals, such as smoking cessation, stress reduction, better diabetes self-management, leadership skills and so on.

A slide from my presentation: Dos are prompts for small actions, delivered by smartphone, designed to help people change their behaviour.

 

In our research we have applied data mining techniques to interaction data and psychological questionnaires from a sample of Do Something Different’s users. Our data set included information about 15,550 people who have taken part in a Do Something Different programme. Using correlation networks and regression models, we were able to construct a new, more precise model of the connections between the behaviours promoted by Do Something Different and a person’s wellbeing and happiness. This has led us to refine the contents of the programmes. The paper, titled Using Data Mining to Refine Digital Behaviour Change Interventions [link: http://dl.acm.org/citation.cfm?id=3079468 ], is co-authored with John Kingston, Miltos Petridis and Ben (C) Fletcher. Interested readers can try out Do Something Different today by going to https://dsd.me/get-started/.

My presentation was in a session on Study Metholodogies, which also featured a fantastic talk by Emily Keane from charity Save The Children, about the use of a smartphone app in the treatment of malnourished children in Africa. The app replaces paper-based child registers for recording data, and guides the health worker step-by-step through the treatment protocol, so that no steps are inadvertently missed. Video illustrations show how to correctly measure a child’s mid upper arm circumference, a key indicator in assessing nutrition, which is frequently performed incorrectly.

Away from the talks, some exciting technology was on display. I was particularly impressed by the Advies.chat system (http://www.soaaids.nl/en/advieschat), a “chatbot” advice tool that offers free and anonymous advice about sexual health and STI testing to young people, based on clinical guidelines. The developers note that “over 20 years of experience in one-on-one counseling via telephone, e-mail and direct message chat about STIs, HIV, testing and prevention were manually translated into structured responses to common questions”. This approach was thought-provoking for me, as Do Something Different is currently exploring ways to improve its user interaction experience.

I returned from the conference having made useful contacts, and more motivated than ever to work on my KTP project, where we are continually looking for new ways to use technology to help people make the changes they want in their lives, and be happier and more fulfilled. I hope to attend the conference again next year, and present further discoveries from analysing data about behaviour change.

– Billiejoe Charlton, KTP Associate, Do Something Different

Putting AI to Work – an Associate’s reflections on attending cutting edge AI Conference in New York

By Ajibola Obayemi

Data and Knowledge Systems Developer – KTP Associate

The O’Reilly AI Conference held in June in Manhattan, New York brought together industry pioneers, university experts, and thought leaders to debate, discuss and move thinking forward in one of the most cutting-edge areas in computing: Artificial Intelligence (AI). Attending this Conference and undertaking the training has deepened my knowledge, inspired my thinking and widened my network.

The conference covered two days of training and tutorials and two days of talks, workshops and seminars about applied AI in businesses and the use cases in different industries. As a Data and Knowledge Systems developer with BCMY Ltd and the University of Brighton, I have been tasked with building intelligent systems, optimizing work flow and using technology to facilitate business growth. This conference and the training provided just the right mix of learning, networking and understanding what other businesses are doing, what they are using to do it and how this is positively or negatively affecting their businesses.

The training

There were four different training sessions: Deep learning with TensorFlow, NVIDIA Deep Learning Institute bootcamp, Natural Language processing with Deep Learning and Neural Networks for time series analysis using DeepLearning4j.

The training was hands-on and we worked with a few deep learning frameworks (Caffe2, TensorFlow, Theano, and NVIDIA Digits) and library (Keras). For the most part, we used Convolutional Neural Networks (CNN) to solve Image Classification, Image Segmentation and Object Detection problems and used Recurrent Neural Networks (RNN) for modelling timeseries. Using transfer learning we made a model solve a similar problem on a new dataset which the model was not trained for. This is interesting as it means by making some changes and removing the output layer we can use pre-trained models on a new dataset, saving a significant amount of time and resources.

One of the cogent points for me is the clear distinction between training, validation and test datasets. Usually, validation and test datasets are used interchangeably in books and papers but each of these datasets have their uses and should be treated differently. Hyperparameter optimization was key as well, as it affects your learning rate, loss function, momentum and basically your training iterations.

 

The Conference

After two days of training, the full Conference got underway with some great keynotes from industry pioneers and experts leading significant projects and research in companies such as Google (Google Brain), IBM (IBM Watson), Facebook, NVIDIA, Intel (Intel Nervana), Salesforce and universities such as MIT, UC Berkeley, John Hopkins University, Carnegie Mellon University. The O’Reilly AI Conference is definitely a key place to network with industry experts. There was also a speed networking event which set the basis for introduction and other non-formal events held after the day was over for attendees to bond outside of the conference.

Several sessions were held with experts showing how they have applied AI and Machine Learning to varying problems. Some of the sessions highlighted the use cases for using AI and Machine Learning in discovering new drugs; discovering cancerous cells; solving eye care issues; predicting faults in machines before they happen, thereby facilitating cost effective preventive maintenance for industries that cannot afford any sort of downtime; cognitive mobile healthcare for patients and physicians; solving financial fraud with Machine Learning; and solving child pornography and human trafficking with AI. Seeing first-hand the diversity of AI applications across such a range of sectors and their impact was inspiring.

Some of the more technical sessions included Deploying AI systems in Edge and Cloud environments; Running TensorFlow at scale in the cloud; Software architectures for building enterprise AI; integrating deep learning libraries with Apache Spark; Recommending products for 1.91 billion people on Facebook; and the AI-powered newsroom.

Certainly, there was a lot to take away from the conference and the blend of these experiences from the training sessions and seminars/ workshops has for me ignited a new way of thinking about problems which can be solved using these Artificial Intelligence and Machine Learning techniques.

My project

For my project, the team and I have worked on a model for dynamic product pricing based on historical prices and product performance and I am currently rounding up work on a classifier algorithm for customer classification. With the new skillset, I will be optimizing the product pricing model, predicting demand and using this to generate a demand curve which can be clustered and the effective pricing for each cluster can be applied to products that have not been sold before. I will also be using sentiment analysis to reduce sales cycle and increasing the average negotiation turnaround period. Specifically, deep learning will help facilitate operational efficiency at BCMY Ltd by solving some computer vision tasks and ultimately remove certain constraints experienced at the moment. It is certainly an exciting time for BCMY Ltd as technology continues to play important roles in the service delivery pipeline.

I have the support of an effective team at BCMY Ltd and the University of Brighton and undoubtedly look forward to the coming months and how these implementations will deliver value to both BCMY Ltd and the University of Brighton.

Lastly, a word to take home, “as an Engineer, your focus should be in building your network, increasing the inference accuracy and ensuring your model does not mimic human bias”.

Ajibola Obayemi

Data and Knowledge Systems Developer – KTP Associate

BCMY Ltd and University of Brighton