A5057663485- Music and Audio Processing
- Phonocardiography and Auscultation Techniques
- Chronic Obstructive Pulmonary Disease (COPD) Research
- Data Management and Algorithms
- Semantic Web and Ontologies
- Time Series Analysis and Forecasting
- Advanced Chemical Sensor Technologies
- COVID-19 diagnosis using AI
- Anomaly Detection Techniques and Applications
- Advanced Text Analysis Techniques
- Traffic Prediction and Management Techniques
- Music Technology and Sound Studies
- Radiation Effects in Electronics
- Data Visualization and Analytics
- VLSI and Analog Circuit Testing
- Diverse Musicological Studies
- Natural Language Processing Techniques
- Respiratory and Cough-Related Research
- Advancements in Semiconductor Devices and Circuit Design
- Chronic Disease Management Strategies
- Respiratory Support and Mechanisms
- Data Stream Mining Techniques
- Digital Mental Health Interventions
- Human Mobility and Location-Based Analysis
- Asthma and respiratory diseases
University of Essex
2018-2024
King's College London
2017-2018
MRC Centre for Environment and Health
2018
University of Surrey
2016
Queen Mary University of London
2009-2013
Our world and our lives are changing in many ways. Communication, networking, computing technologies among the most influential enablers that shape today. Digital data connected worlds of physical objects, people, devices rapidly way we work, travel, socialize, interact with surroundings, they have a profound impact on different domains, such as healthcare, environmental monitoring, urban systems, control management applications, several other areas. Cities currently face an increasing...
An increasing number of cities are confronted with challenges resulting from the rapid urbanization and new demands that a rapidly growing digital economy imposes on current applications information systems. Smart city enable authorities to monitor, manage, provide plans for public resources infrastructures in environments, while offering citizens businesses develop use intelligent services cities. However, providing such smart gives rise several issues, as semantic heterogeneity...
This study aims to explore the potential of Internet Things (IoT) devices and explainable Artificial Intelligence (AI) techniques in predicting biomarker values associated with GDM when measured 13–16 weeks prior diagnosis. We developed a system that forecasts biomarkers such as LDL, HDL, triglycerides, cholesterol, HbA1c, results from Oral Glucose Tolerance Test (OGTT) including fasting glucose, 1-hour, 2-hour post-load glucose values. These are predicted based on sensory measurements...
Data owners are creating an ever richer set of information resources online, and these being used for more applications. Spatial data on the Web is becoming ubiquitous voluminous with rapid growth location-based services, spatial technologies, dynamic services published by different organizations. However, heterogeneity peculiarities data, such as use coordinate reference systems, make it difficult users, applications, to discover, interpret in large distributed system that Web. To...
In this paper we present a novel hybrid system that involves formal method of automatic ontology generation for web-based audio signal processing applications. An is seen as knowledge management structure represents domain in machine interpretable format. It describes concepts and relationships within particular domain, our case, the musical instruments. However, different tasks engineering including manual annotation, hierarchical structuring organization data can be laborious challenging....
Abstract Databases of electronic health records (EHR) are not only a valuable source data for research but have also recently been used as medium through which potential study participants can be screened, located and approached to take part in research. The aim was assess whether it is feasible practical screen, locate approach patients the Clinical Practice Research Datalink (CPRD). This cohort primary care. CPRD anonymised EHR database searched screen with Chronic Obstructive Pulmonary...
The emergence of new nanoscale technologies has imposed significant challenges to designing reliable electronic systems in radiation environments. A few types like Total Ionizing Dose (TID) can cause permanent damages on such devices, and current state-of-the-art tackle TID make use expensive radiation-hardened devices. This paper focuses a novel different approach: using machine learning algorithms consumer level Field Programmable Gate Arrays (FPGAs) effects monitor them replace before...
Cities have been a thriving place for citizens over the centuries due to their complex infrastructure. The emergence of Cyber-Physical-Social Systems (CPSS) and context-aware technologies boost growing interest in analysing, extracting eventually understanding city events which subsequently can be utilised leverage citizen observations cities. In this paper, we investigate feasibility using Twitter textual streams events. We propose hierarchical multi-view deep learning approach...
This paper presents a deep learning system applied for detecting anomalies from respiratory sound recordings. Initially, our begins with audio feature extraction using Gammatone and Continuous Wavelet transformation. step aims to transform the input into two-dimensional spectrogram where both spectral temporal features are presented. Then, proposed integrates Inception-residual-based backbone models combined multi-head attention multi-objective loss classify anomalies. Instead of applying...
We describe the process of collecting, organising and publishing a large set music similarity features produced by SoundBite [10] playlist generator tool. These data can be valuable asset in development evaluation of new Music Information Retrieval algorithms. They also used Web-based search retrieval applications. For this reason, we make database available on Semantic Web via SPARQL end-point, which Linked Data services. provide examples using research tool, as well simple web...
Background: Continuous monitoring of glucose (CGM) via subcutaneous patch is an accurate self-monitoring tool blood glucose, but also introduces a range additional benefits such as real-time feedback. While its value among pregnant women with gestational diabetes mellitus (GDM) established in high-income countries, little known about the feasibility and acceptability without GDM low-resource settings low- middle-income countries.Objectives: This study aims to assess CGM mothers South Africa...
This paper evaluates a wide range of audio-based deep learning frameworks applied to the breathing, cough, and speech sounds for detecting COVID-19. In general, audio recording inputs are transformed into low-level spectrogram features, then they fed pre-trained models extract high-level embedding features. Next, dimension these features reduced before fine-tuning using Light Gradient Boosting Machine (LightGBM) as back-end classification. Our experiments on Second DiCOVA Challenge achieved...
In this study, we present a cohort study involving 106 COPD patients using portable environmental sensor nodes with attached air pollution sensors and activity-related sensors, as well daily symptom records peak flow measurements to monitor patients' activity personal exposure pollution. This is the first which attempts predict symptoms based on exposure. We developed system that can detect one day in advance of appearing. proposed Probabilistic Latent Component Analysis (PLCA) model...
<b>Background:</b> Environmental exposures play a role in COPD exacerbations. Developments portable environmental sensors mean that patients can now carry personal monitor (PAM) as they go about their lives to capture direct link between individual activities, and health. We developed method of predicting exacerbations utilising long-term deployment PAMs improve disease management patients. <b>Methods:</b> 102 participants have been recruited. are given PAM for up six months, while keeping...
Background Chronic Obstructive Airway Disease (COPD) is marked by often severely debilitating exacerbations. Efficient patient-centric research approaches are needed to better inform health management primary-care. Aim The ‘COPE study’ aims develop a method of predicting COPD exacerbations utilising personal air quality sensors, environmental exposure modelling and electronic records through the recruitment patients from consenting GPs contributing Clinical Practice Research Datalink (CPRD)....
This paper presents a deep learning system applied for detecting anomalies from respiratory sound recordings. Initially, our begins with audio feature extraction using Gammatone and Continuous Wavelet transformation. step aims to transform the input into two-dimensional spectrogram where both spectral temporal features are presented. Then, proposed integrates Inception-residual-based backbone models combined multi-head attention multi-objective loss classify anomalies. Instead of applying...
This paper evaluates a wide range of audio-based deep learning frameworks applied to the breathing, cough, and speech sounds for detecting COVID-19. In general, audio recording inputs are transformed into low-level spectrogram features, then they fed pre-trained models extract high-level embedding features. Next, dimension these features reduced before fine-tuning using Light Gradient Boosting Machine (LightGBM) as back-end classification. Our experiments on Second DiCOVA Challenge achieved...