CEChristos Efstratiou

Christos Efstratiou

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Christos Efstratiou has a total of 81 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A Machine Learning Framework for Optimising Indoor Thermal Comfort and Air Quality through Sensor Data Streams

    by Chun Wai Chiu, Christos Efstratiou, Marialena Nikolopoulou, Matthew Barker, Andrew Baldwin, Malcolm Clarke

    Optimising thermal comfort and air quality in indoor environments presents a complex, dynamic challenge that traditional static systems struggle to address effectively. We propose a novel real-time framework that tackles this multifaceted problem by leveraging stream clustering and time-series forecasting techniques. Our system continuously analyses sensor data to summarise comfort conditions and predict future indoor states. Simulations based on the stream clustering model indicate potential for significant improvements in indoor comfort, increasing comfort duration from 6% to 74%. Furthermore, the time-series forecasting model demonstrated strong performance, achieving mean absolute errors of 0.026 and 0.034 on test and demonstration datasets, respectively. This resource-efficient approach demonstrates promise for real-time indoor environment management, effectively balancing thermal comfort and air quality considerations.


  • Open Access

    Data-Driven Optimisation Based Machine Learning for Thermal Comfort in Building Environment

    by Ismail Alarab, Christos Efstratiou, Simant Prakoonwit, Fernando Otero, Marialena Nikolopoulou, Matthew Barker, Andrew Baldwin, Malcolm Clarke

    Achieving thermal comfort under minimum energy considerations has become a hot topic in the field of energy building management. The existing studies have suggested several methods to predict thermal comfort and accordingly adjust the temperature setpoints to reduce the energy. The two drawbacks of the existing studies involve the increased complexity in optimisation methods using multiple models and the lack of these methods in the optimisation approach. Our novel work proposes a data-driven optimisation solution based on machine learning (ML) to maintain thermal comfort under energy efficiency considerations. We simply infer the input from a desired output using supervised learning models as an optimisation solution. We discuss the efficiency and cost-effectiveness of the proposed solution using a public UK-schools dataset from the ASHRAE database.

  • Open Access

    Spatial Knowledge Acquisition for Pedestrian Navigation: A Comparative Study between Smartphones and AR Glasses

    by Aymen Lakehal, Sophie Lepreux, Christos Efstratiou, Christophe Kolski, Pavlos Nicolaou

    Smartphone map-based pedestrian navigation is known to have a negative effect on the long-term acquisition of spatial knowledge and memorisation of landmarks. Landmark-based navigation has been proposed as an approach that can overcome such limitations. In this work, we investigate how different interaction technologies, namely smartphones and augmented reality (AR) glasses, can affect the acquisition of spatial knowledge when used to support landmark-based pedestrian navigation. We conducted a study involving 20 participants, using smartphones or augmented reality glasses for pedestrian navigation. We studied the effects of these systems on landmark memorisation and spatial knowledge acquisition over a period of time. Our results show statistically significant differences in spatial knowledge acquisition between the two technologies, with the augmented reality glasses enabling better memorisation of landmarks and paths.


  • Open Access

    Mirror Placement Matters in Remote Collaboration

    by Boyd Branch, Piotr Mirowski, Sophia Ppali, Rocio Von Jungenfeld, Paul Allain, Christos Efstratiou


  • Quantitative Shape Measurement of an Inflatable Rubber Dam Using an Array of Inertial Measurement Units

    by Yonghui Hu, Yong Yan, Christos Efstratiou, David Vela-Orte

    Shape measurement plays an important role in the condition monitoring and operation control of inflatable rubber dams. This article presents a method to measure the cross-sectional shape of a rubber dam using an array of inertial measurement units (IMUs) placed on the circumference of the dam. Accelerometer and gyroscope measurements are combined using an adaptive complementary filter to determine the tangent angles of the dam circumference. The adaptive complementary filter adjusts the weights of the accelerometer and gyroscope measurements dynamically in order to reduce the uncertainty in orientation estimation due to external acceleration under dynamic conditions. A natural cubic spline that interpolates the measured tangent angles at discrete locations is used to represent the tangent angles along the dam circumference as a continuous function of the arc length. Finally, the cross-sectional shape is reconstructed by integrating the continuous tangent angle function along the circumference of the dam. Experimental assessment of the measurement system was performed on a purpose-built test rig using a digital camera as a reference measuring device. Results under a typical static condition show that the measured and reference shapes agree well with each other, with a similarity index being 3.74%, a mismatch distance of the last IMU node being 12.3 mm, and a relative error of height measurement being −2.44%. Under dynamic conditions, the measurement results deteriorate due to external acceleration, but considerable improvement is achieved in comparison with an accelerometer-only approach. In addition, the elimination of faulty nodes from shape reconstruction has negligible influence on the results, suggesting that the measurement system enjoys a high degree of fault tolerance.


  • Swallowing detection for game control: Using skin-like electronics to support people with dysphagia

    by Benjamin Nicholls, Chee Siang Ang, Christos Efstratiou, Yongkuk Lee, Woon-Hong Yeo

    In this paper, we explore the feasibility of developing a sensor-driven rehabilitation game for people suffering from dysphagia. This study utilizes the skin-like electronics for unobtrusive, comfortable, continuous recording of surface electromyograms (EMG) during swallowing and use them for driving game-based, user-controlled feedback. The experimental study includes the development and evaluation of a real-time swallow detection algorithm using skin-like sensors and a game-based human-computer interaction. The user evaluations support the ease of use of the skin-like electronics as a motivational tool for people with dysphagia.


  • Open Access

    OSN mood tracking

    by James Alexander Lee, Christos Efstratiou, Lu Bai

    Online social networks (OSNs) have become an integral part of our everyday lives, where we share our thoughts and feelings. This study analyses the extent to which the changes of an individual's real-world psychological mood can be inferred by tracking their online activity on Facebook and Twitter. By capturing activities from the OSNs and ground truth data via experience sampling, it was found that mood changes can be detected within a window of 7 days for 61% of the participants by using specific, combined online activity signals. The participants fall into three distinct groups: those whose mood correlates positively with their online activity, those who correlate negatively and those who display a weak correlation. We trained two classifiers to identify these groups using features from their online activity, which achieved precision of 95.2% and 84.4% respectively. Our results suggest that real-world mood changes can be passively tracked through online activity on OSNs.


  • weSport: Utilising wrist-band sensing to detect player activities in basketball games

    by Lu Bai, Christos Efstratiou, Chee Siang Ang

    Wristbands have been traditionally designed to track the activities of a single person. However there is an opportunity to utilize the sensing capabilities of wristbands to offer activity tracking services within the domain of team-based sports games. In this paper we demonstrate the design of an activity tracking system capable of detecting the players' activities within a one-to-one basketball game. Relying on the inertial sensors of wristbands and smartphones, the system can capture the shooting attempts of each player and provide statistics about their performance. The system is based on a two-level classification architecture, combining data from both players in the game. We employ a technique for semi-automatic labeling of the ground truth that requires minimum manual input during a training game. Using a single game as a training dataset, and applying the classifier on future games we demonstrate that the system can achieve a good level of accuracy detecting the shooting attempts of both players in the game (precision 91.34%, recall 94.31%).


  • Smart Sensing Systems for the Daily Drive

    by Sarfraz Nawaz, Christos Efstratiou, Cecilia Mascolo

    When driving, you might sometimes wonder, "Are there any disruptions on my regular route that might delay me, and will I be able to find a parking space when I arrive?" Two smartphone-based prototype systems can help answer these questions. The first is ParkSense, which can be used to sense on-street parking-space occupancy when coupled with electronic parking payment systems. The second system can sense and recognize a user's repeated car journeys, which can be used to provide personalized alerts to the user. Both systems aim to minimize the impact of sensing tasks on the device's lifetime so that the user can continue to use the device for its primary purpose. This department is part of a special issue on smart vehicle spaces.


  • Smartphone sensing offloading for efficiently supporting social sensing applications

    by Kiran K. Rachuri, Christos Efstratiou, Ilias Leontiadis, Cecilia Mascolo, Peter J. Rentfrow