Josef Bajada

Dr. Josef Bajada

orcid

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 October 2013
Verified
Conference Paper
Closed access
JBJosef Bajada
Josef Bajada
MFMaria Fox
Maria Fox
DLDerek Long
Derek Long
In order to evaluate the effectiveness of demand-side management techniques, mechanisms to simulate electricity consumption activities at a granular level are required. A bottom-up approach that uses a non-homogeneous Markov chain to model each appliance within each household is proposed. This model is time-aware and captures the variability of the transition probabilities as they change throughout the day. A simulator was developed based on this model and it was configured with data obtained from a household electricity survey conducted in the UK. The resultant load curves from a simulation of a thousand households are compared with the average hourly load reported in the survey, with significant similarities observed between the two. The same model can be parametrised to simulate hypothetical scenarios, such as a future where electric vehicles are more popular. The simulation framework also supports a plug-in mechanism through which demand control policies can be integrated into the system such that the effects and performance of demand-side management strategies can be evaluated.


1 February 2025 in Bioengineering
Verified
Journal Article
Open access
PDF file
MBMark Borg
Mark Borg
SMStpehen Mizzi
Stpehen Mizzi
RFRobert Farrugia
Robert Farrugia
TMTiziana Mifsud
Tiziana Mifsud
AMAnabelle Mizzi
Anabelle Mizzi
OFOwen Falzon
Owen Falzon
Monitoring plantar foot temperatures is essential for assessing foot health, particularly in individuals with diabetes at increased risk of complications. Traditional thermographic imaging measures foot temperatures in unshod individuals lying down, which may not reflect thermal characteristics of feet in shod, active, real-world conditions. These controlled settings limit understanding of dynamic foot temperatures during daily activities. Recent advancements in wearable technology, such as insole-based sensors, overcome these limitations by enabling continuous temperature monitoring. This study leverages a data-driven clustering approach, independent of pre-selected foot regions or models like the angiosome concept, to explore normative thermal patterns in shod feet with insole-based sensors. Data were collected from 27 healthy participants using insoles embedded with 21 temperature sensors. The data were analysed using clustering algorithms, including k-means, fuzzy c-means, OPTICS, and hierarchical clustering. The clustering algorithms showed a high degree of similarity, with variations primarily influenced by clustering granularity. Six primary thermal patterns were identified, with the “butterfly pattern” (elevated medial arch temperatures) predominant, representing 51.5% of the dataset, aligning with findings in thermographic studies. Other patterns, like the “medial arch + metatarsal area” pattern, were also observed, highlighting diverse yet consistent thermal distributions. This study shows that while normative thermal patterns observed in thermographic imaging are reflected in insole data, the temperature distribution within the shoe may better represent foot behaviour during everyday activities, particularly when enclosed in a shoe. Unlike thermal imaging, the proposed in-shoe system offers the potential to capture dynamic thermal variations during ambulatory activities, enabling richer insights into foot health in real-world conditions.

7 December 2023
Verified
Conference Paper
Closed access
MBMark Borg
Mark Borg
SMStpehen Mizzi
Stpehen Mizzi
TMTiziana Mifsud
Tiziana Mifsud
CMChiara Modestini
Chiara Modestini
AMAnabelle Mizzi
Anabelle Mizzi
OFOwen Falzon
Owen Falzon
In this work, we describe the use of time series features extracted from foot temperature data obtained from a wearable in-shoe system to discriminate between feet from individuals affected by diabetes, and feet from healthy individuals. We identify a set of features that are statistically significant in discriminating between the two classes and that thus can serve as input to machine learning classifiers.

12 November 2021 in arXiv
Verified
Preprint
Open access
PDF file
JBJosef Bajada
Josef Bajada
FBFrancesco Borg Bonello
Francesco Borg Bonello
Real-time EEG-based Emotion Recognition (EEG-ER) with consumer-grade EEG devices involves classification of emotions using a reduced number of channels. These devices typically provide only four or five channels, unlike the high number of channels (32 or more) typically used in most current state-of-the-art research. In this work we propose to use Discrete Wavelet Transforms (DWT) to extract time-frequency domain features, and we use time-windows of a few seconds to perform EEG-ER classification. This technique can be used in real-time, as opposed to post-hoc on the full session data. We also apply baseline removal preprocessing, developed in prior research, to our proposed DWT Entropy and Energy features, which improves classification accuracy significantly. We consider two different classifier architectures, a 3D Convolutional Neural Network (3D CNN) and a Support Vector Machine (SVM). We evaluate both models on subject-independent and subject dependent setups to classify the Valence and Arousal dimensions of an individual's emotional state. We test them on both the full 32-channel data provided by the DEAP dataset, and also a reduced 5-channel extract of the same dataset. The SVM model performs best on all the presented scenarios, achieving an accuracy of 95.32% on Valence and 95.68% on Arousal for the full 32-channel subject-dependent case, beating prior real-time EEG-ER subject-dependent benchmarks. On the subject-independent case an accuracy of 80.70% on Valence and 81.41% on Arousal was also obtained. Reducing the input data to 5 channels only degrades the accuracy by an average of 3.54% across all scenarios, making this model appropriate for use with more accessible low-end EEG devices.

27 January 2022 in IEEE Transactions on Artificial Intelligence
Verified
Journal Article
Closed access
JBJosef Bajada
Josef Bajada
MFMaria Fox
Maria Fox
DLDerek Long
Derek Long
Temporal planning often involves numeric effects that are directly proportional to their action’s duration. These include continuous effects, where a numeric variable is subjected to a rate of change while the action is being executed, and discrete duration-dependent effects, where the variable is updated instantaneously but the magnitude of such change is computed from the action’s duration. When these effects are linear, state-of-the-art temporal planners often make use of linear programming to ensure that these numeric updates are consistent with the chosen start times and durations of the plan’s actions. This is typically done for each evaluated state as a part of the search process. This exhaustive approach is not scalable to solve real-world problems that require long plans, because the size of the linear program becomes larger and slower to solve. In this article, we propose techniques that minimize this overhead by computing these checks more selectively and formulating linear programs that have a smaller footprint. The effectiveness of these techniques is demonstrated on domains that use a mix of discrete and continuous effects, which is typical of real-world planning problems. The resultant planner also outperforms most state-of-the-art temporal–numeric and hybrid planners, in terms of both coverage and scalability.