Category: Uncategorized

Post by Siyang Song (2016 Cohort)

Venue: FG 2018, Xi’an, China https://fg2018.cse.sc.edu/

Paper Title: Human Behaviour-based Automatic Depression Analysis using Hand-crafted Statistics and Deep Learned Spectral Features

The work presented in this paper is the extension of my CDT PLP module. During the PLP, we found that current clinical standards for depression assessment are subjective, and requires extensive participation from experienced psychologists. Therefore, my supervisor (Dr. Michel Valstar) and I explored a video-based automatic depression analysis approach, and find our approach beat state of the art systems in a dataset. As a result, we decided to write a paper about this approach.

This bulk of the paper was written by me. Since I didn’t have much experience about writing paper at that point, my supervisor helped and taught me about how to organize a paper, as well as how to implement ablation studies to show the strengths of the proposed approach. In addition, my external partner (Prof. Linlin Shen) also helped me to check the typos and languages. After, several rounds improvement, we eventually submitted the paper to FG conference which focus on the automatic face and gesture analysis.

Three months after the submission, we received the reviewers comments, where two of them gave ‘weak accept’ and two of them gave ‘borderline’. In the rebuttal, we addressed issues one by one. For some real drawbacks, we made some changes. Also, some comments were gave due to the misunderstanding of the paper. To deal with them, we detailed explained in the rebuttal.

Posters:

This study is the basis of my PhD study. Based on this work, while we continuously developing a better model for practical use, we also looking to other temporal modeling methods.

Building several models for not only depression analysis, but also personality traits and anxiety analysis.

https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8373825

–originally posted on Siyang’s blog

Post by Roza Vasileva (2016 Cohort)

On January 26, 2019 I had an excellent opportunity to present my PhD research project. More specifically, I spoke about the findings emerging from my research interviews in Dar es Salaam with various stakeholders of the Tanzanian data ecosystem: government, donor institutions, local community organisers, start-ups, international experts and academia. This study aimed to understand what processes take place on the ground when people try to take advantage of data and technology to transform Dar es Salaam into a ‘smarter city’, and what the challenges are.

This was a public event as part of the ODI Fridays – free lunchtime lectures for everyone. Below is the video recording of the presentation.

–originally posted on Roza’s blog

Post by Roza Vasileva (2016 Cohort)

On October 1-3, 2018, I had the pleasure to participate in the first National Open Data Symposium in Omanas a speaker on principles and benefits of Open Data. The presentation covered various definitions of open data, including examples in some key sectors such as health, education, transport, etc.

I was pleased to see representatives from five different sectors across government and private sector together, having a discussion, raising challenging questions. There are many agencies within the government, which have started publishing open data, and these efforts are a bit uneven. I think the most important thing about the symposium was that these agencies came together to start moving towards a collaborative approach to open data. This event sent a powerful message to the public, government and even international open data community that Oman strives to advance their open data agenda and has desire to bring best international practices in this process.

Being one of the international speakers in the event and having worked with the World Bank on open data in many countries, it means to me that Oman is really keen to learn from other international experiences and adopt best global practices in their approach to do open data and moving towards smarter future. We need to remember that we’re increasingly living in cities, and Open Data is key to creating a platform for smart cities. Citizen-focused smart cities increasingly use data analytics to improve service delivery to its citizens making them more accessible, engage with the communities, find joint solutions to most pressing urban issues, making our cities more livable and sustainable. As my own area of academic research lies in looking how open data can support smart cities, I want to see Oman open data use it for open urban innovations and delivering better services to its people.

Conversations evolved around how to make data more usable for the data users. Engagement with the consumers of the data was one of the key points that was raised throughout the symposium. I echo one of the participants comments that value of releasing open data comes from data use. One of the key elements to open data is adopting open license that explicitly gives permission to use and re-use data for any purpose, including commercial purposes. If the license does not exist on the portal and does not articulate those rights for data re-use, the users cannot be sure that they can use the data. This is one of the challenges Oman will need to address to enable the open data benefits, especially for economic growth that were extensively discussed at the Symposium.

-originally posted on Roza’s blog

Post by Richard Ramchurn (2015 Cohort)

In October 2017 I set out to direct my second brain controlled film. For the previous two years I have been doing a PhD in brain controlled cinema, which has consisted of taught courses, ‘performance led research in the wild’ studies, a bit of my own practice and a lot of reading. The PhD has given me the time and resources to study and analyse how people came to interact with my first film The Disadvantages of Time Travel, and to read up on passive theories of control amongst other topics relevant to my field. All this has informed my practice and when it came to returning to the director’s chair it was with the foundation of that work. The process of making my second film The MOMENT required me to dedicate all of my time and resources to it, and being able to officially pause my PhD during that time was invaluable. The production was gruelling. For at least a month I worked 7 days a week on no more than 4 hours sleep a night. After the shoot a lot of the crew, the producer and myself went into a kind of freefall and took a few days to return to a semblance of our previous selves. The MOMENT is the largest project where I have been at  the helm, it had a crew of 28, and 9 professional actors and we worked to a budget of £54k.

I kept detailed notes as I went along, throughout all of production, which will be helpful when it comes to writing up the practice side of the thesis. Screenings of The MOMENT have been used to collect ‘in the wild’ data form the public focusing on their interaction with the brain controlled film. However the film itself has its own touring life and a sustainable tour is currently being planned throughout 2019.

Making of the MOMENT on Vimeo

A project of this scale needs a team behind it. It is worth mentioning that I have the privilege of having an excellent and engaged supervision team who have supported the process, and my producer and partner who have made the practicalities of this project possible. I also found additional partnerships in industry with Live Cinema UK who helped with exhibition and engagement with widespread cultural organisations.

Lessons learnt summary –

• Make sure you have adequate budget and time.
• Time spent planning is never wasted.
• Pool your resources, work with people you trust and if possible have history.
• An army marches on its stomach, keep your crew fed and watered.
• Find all the support you can from within and outside the PhD structure.
• Continue to make friends with organisations.
• Engage with the press.
• Talk about your work whenever you can.

It brings me great pleasure to announce that I am now the Social Media Specialist for Horizon CDT at the University of Nottingham.

I will be managing social media platforms and the blog for the unit, bringing it a fresh feel. We will be working towards showcasing students’ and staff members’ research as well as increasing engagement with our audiences. It feels very exciting to become part of the Horizon team and I can’t wait to get stuck in!

Written by Kate Green