Mr Jon Baker

Graduate Teaching Assistant

About

Jon Baker is a Graduate Teaching Assistant in the School of Engineering and Digital Arts.

Research interests

Next2Me: Capturing Social Interactions through Smartphone Devices using WiFi and Audio signals

Today, there is an increasing interest in using technologies that can capture, record and analyse the daily activities of people. From the perspective of self-improvement, the quantified-self movement is aiming to offer ways for individuals to record and understand their own behaviour. In a societal scale, tracking the activities of people can allow the analysis of the behaviour of whole communities, and enable large-scale analytics. These visions are primarily motivated by the proliferation of life-logging technologies that can capture events, experiences, and raw data, while keeping them in a chronological timeline. The “life data” that is involved in life logging, is acquired using devices such as sensors and actuators, where it is then stored and examined. Recent technologies can be used to develop self-monitoring and self-sensing devices for life logging, which would deliver information of behavioural changes, environmental accountability, quantified-self and much more.​

In a technological world where smartphones devices and wireless connectivity are becoming more common, there is significant scope to develop methodologies for the gathering of hard data about behavioural activities of users within social environments, for the purpose of life-logging, memory augmentation and social sensing. “Next2Me” describes an Android mobile app specifically designed to track the social interactions between a set of users within various scenarios and environments. The system samples the signals from nearby Wi-Fi access points in the form of Wi-Fi fingerprints, which are then analysed as a method of single modality. The key idea is to branch away from energy-consuming GPS methodologies and instead use a technique which can passively track social interactions continuously using smartphone devices, using less power, with the objective of implementing further modalities to improve accuracy.

This project won the IEEE UKRI Telecommunications Prize for the best Student Project in the Telecommunications Field in October 2015. Since then, research surrounding the app continueed as part of my PhD.

Teaching

2017 - 2018

  • Digital Portfolio BSc: Web design and development
  • Mobile Application Design BSc: Android app development and design
  • Mobile Application Design MSc: Android app development and design

2016 - 2017

  • Digital Portfolio BSc: Web design and development
  • Software Development BSc: PHP and MySQL development
  • Internet Programming with Java BSc: Web applet development using Java 7 and BlueJ
  • Mobile Application Design BSc: Android app development and design
  • Mobile Application Design MSc: Android app development and design

2015 - 2016

  • Digital Portfolio BSc: Web design and development
  • Mobile Application Design BSc: Android app development and design
  • Mobile Application Design MSc: Android app development and design

2014 - 2015

  • Digital Portfolio BSc: Web design and development
  • Mobile Application Design BSc: Android app development and design
  • Internet Programming with Java BSc: Web applet development using Java 7 and BlueJ
  • Software Development BSc: PHP and MySQL development

Publications

Conference or workshop item

  • Lunerti, C. et al. (2017). Environmental Effects on Face Recognition in Smartphones. in: 51st IEEE International Carnahan Conference on Security Technology. Institute of Electrical and Electronics Engineers.
    Face recognition is convenient for user authentication on smartphones as it offers several advantages suitable for mobile environments. There is no need to remember a numeric code or password or carry tokens. Face verification allows the unlocking of the smartphone, pay bills or check emails through looking at the smartphone. However, devices mobility also introduces a lot of factors that may influence the biometric performance mainly regarding interaction and environment. Scenarios can vary significantly as there is no control of the surroundings. Noise can be caused by other people appearing on the background, by different illumination conditions, by different users’ poses and through many other reasons. User-interaction with biometric systems is fundamental: bad experiences may derive to unwillingness to use the technology. But how does the environment influence the quality of facial images? And does it influence the user experience with face recognition? In order to answer these questions, our research investigates the user-biometric system interaction from a non-traditional point of view: we recreate reallife scenarios to test which factors influence the image quality in face recognition and, quantifiably, to what extent. Results indicate the variability in face recognition performance when varying environmental conditions using smartphones.
  • Baker, J. and Efstratiou, C. (2017). Next2Me: Capturing Social Interactions through Smartphone Devices using WiFi and Audio signals. in: EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services (MobiQuitous 2017). ACM, pp. 412-421. Available at: http://dx.doi.org/10.1145/3144457.3144500.
    Typical approaches in detecting social interactions consider the use of co-location as a proxy for real-world interactions. Such approaches can underperform in challenging situations where multiple social interactions can occur in close proximity to each other. In this paper, we present a novel approach to detect co-located social interactions using smartphones. Next2Me relies on the use of WiFi signals and audio signals to accurately distinguish social groups interacting within a few meters from each other. Through a range of real-world experiments, we demonstrate a technique that utilises WiFi fingerprinting, along with sound fingerprinting to identify social groups. Experimental results show that Next2Me can achieve a precision of 88% within noisy environments, including smartphones that are placed in users’ pockets, whilst maintaining a very low energy footprint (<3% of battery capacity per day).