Rameez Raja Kureshi

Generative AI, such as Large Language Models (LLMs), has achieved impressive progress but still produces hallucinations and unverifiable claims, limiting reliability in sensitive domains. Retrieval-Augmented Generation (RAG) improves accuracy by grounding outputs in external knowledge, especially in domains like healthcare, where precision is vital. However, RAG remains opaque and essentially a black box, heavily dependent on data quality. We developed a method-agnostic, perturbation-based framework that provides token and component-level interoperability for Graph RAG using SMILE and named it as Knowledge-Graph (KG)-SMILE. By applying controlled perturbations, computing similarities, and training weighted linear surrogates, KG-SMILE identifies the graph entities and relations most influential to generated outputs, thereby making RAG more transparent. We evaluate KG-SMILE using comprehensive attribution metrics, including fidelity, faithfulness, consistency, stability, and accuracy. Our findings show that KG-SMILE produces stable, human-aligned explanations, demonstrating its capacity to balance model effectiveness with interpretability and thereby fostering greater transparency and trust in machine learning technologies.

The detrimental effects of air pollutants on human health have prompted increasing concerns regarding indoor air quality (IAQ). The emergence of digital health interventions and citizen science initiatives has provided new avenues for raising awareness, improving IAQ, and promoting behavioural changes. The Technology Acceptance Model (TAM) offers a theoretical framework to understand user acceptance and adoption of IAQ technology. This paper presents a case study using the COM-B model and Internet of Things (IoT) technology to design a human-centred digital visualisation platform, leading to behavioural changes and improved IAQ. The study also investigates users' acceptance and adoption of the technology, focusing on their experiences, expectations, and the impact on IAQ. Integrating IAQ sensing, digital health-related interventions, citizen science, and the TAM model offers opportunities to address IAQ challenges, enhance public health, and foster sustainable indoor environments. The analytical results show that factors such as human behaviour, indoor activities, and awareness play crucial roles in shaping IAQ.

The topic of indoor air pollution has yet to receive the same level of attention as ambient pollution. We spend considerable time indoors, and poorer indoor air quality affects most of us, particularly people with respiratory and other health conditions. There is a pressing need for methodological case studies focusing on informing households about the causes and harms of indoor air pollution and supporting changes in behaviour around different indoor activities that cause it. The use of indoor air quality (IAQ) sensor data to support behaviour change is the focus of our research in this paper. We have conducted two studies—first, to evaluate the effectiveness of the IAQ data visualisation as a trigger for the natural reflection capability of human beings to raise awareness. This study was performed without the scaffolding of a formal behaviour change model. In the second study, we showcase how a behaviour psychology model, COM-B (Capability, Opportunity, and Motivation-Behaviour), can be operationalised as a means of digital intervention to support behaviour change. We have developed four digital interventions manifested through a digital platform. We have demonstrated that it is possible to change behaviour concerning indoor activities using the COM-B model. We have also observed a measurable change in indoor air quality. In addition, qualitative analysis has shown that the awareness level among occupants has improved due to our approach of utilising IoT sensor data with COM-B-based digital interventions.

Atmospheric microplastics (MPs) are a ubiquitous environmental contaminant of emerging concern. Sampling methods provide information relating to surface area concentration and MP characteristics, without direct comparison with routinely measured standard air quality parameters. This study analysed 6 active air samples generated by a local authority as part of their routine air quality monitoring activities. Continuous sampling totalled 10 months, within the city centre of Kingston-upon-Hull. By using μFTIR analysis, levels of total particles detected using the NOx inlet filters ranged from 5139 ± 2843 particles m⁻² day⁻¹, comprising 1029 ± 594 MPs m⁻² day⁻¹. The controls displayed a mean level of 2.00 ± 3.49 MPs. The polymers nylon (32%) and polypropylene, PP (22%) were the most abundant. Small fragments of 47.42 ± 48.57 μm (length) and 21.75 ± 13.62 μm (width) were most common. An increase in MP levels during April 2020 coincided with an increase in PM₁₀ levels. This study used robust procedures to measure MPs in the air by exploiting existing air quality monitoring equipment. Knowing the levels, types, and characteristics of MPs can inform toxicity studies to provide more environmentally relevant exposures, which is urgent now that MPs have been reported in human lung tissue.

With the emergence of Low-Cost Sensor (LCS) devices, measuring real-time data on a large scale has become a feasible alternative approach to more costly devices. Over the years, sensor technologies have evolved which has provided the opportunity to have diversity in LCS selection for the same task. However, this diversity in sensor types adds complexity to appropriate sensor selection for monitoring tasks. In addition, LCS devices are often associated with low confidence in terms of sensing accuracy because of the complexities in sensing principles and the interpretation of monitored data. From the data analytics point of view, data quality is a major concern as low-quality data more often leads to low confidence in the monitoring systems. Therefore, any applications on building monitoring systems using LCS devices need to focus on two main techniques: sensor selection and calibration to improve data quality. In this paper, data-driven techniques were presented for sensor calibration techniques. To validate our methodology and techniques, an air quality monitoring case study from the Bradford district, UK, as part of two European Union (EU) funded projects was used. For this case study, the candidate sensors were selected based on the literature and market availability. The candidate sensors were narrowed down into the selected sensors after analysing their consistency. To address data quality issues, four different calibration methods were compared to derive the best-suited calibration method for the LCS devices in our use case system. In the calibration, meteorological parameters temperature and humidity were used in addition to the observed readings. Moreover, we uniquely considered Absolute Humidity (AH) and Relative Humidity (RH) as part of the calibration process. To validate the result of experimentation, the Coefficient of Determination (R²), Root Mean Square Error (RMSE), and Mean Absolute Error (MAE) were compared for both AH and RH. The experimental results showed that calibration with AH has better performance as compared with RH. The experimental results showed the selection and calibration techniques that can be used in designing similar LCS based monitoring systems.

In this demonstration, we propose an AQ-SCIENCE (Air Quality - Smart Cities with IoT-ENabled Citizen Engagement) framework to enhance citizen engagement with an IoT-enabled LCS (low-cost sensors) monitoring kit and platform. Our LCS kits and user study platform empower citizens with indoor air quality data with referential values and allow them to learn about ways to improve the air quality in their homes. It also provides scientists to collect qualitative data to link the air quality with indoor daily activities. The kits and platform is utilized in a user study linking Air quality and activities in the Bradford region in the UK as part of two European Union projects.

Monitoring indoor air quality is becoming crucial as people spend most of their time indoors. In recent years, respiratory problems such as chronic obstructive pulmonary disease and asthma appear as among the common diseases that are the reasons for hospitalization among people. Monitoring the indoor pollutant, using the low-cost sensor-based IoT system, can play an important role in the management of these chronic conditions. In this paper, we set out the design of a trial involving an unobtrusive IoT-based monitoring system to observe indoor environment passively in the house of people suffering from Asthma. The system monitors Particulate Matter (PM2.5 & PM10) and Carbon dioxide (CO2) in the indoor environment together with householder's indoor activities such as type of cooking, smoking, ventilation hour, cleaning, and so on.

On average, we spend around 90% of the time in indoor environments. Indoor Air Quality (IAQ) has been receiving increased attention from the environmental bodies, local authorities and citizens as it is becoming clearer that poor IAQ has public health implications. Therefore, monitoring of indoor environment and involving citizens becomes crucial to enhance IAQ and managing their indoor environments by raising awareness – a goal of many Citizen Science (CS) projects. In this work, we present a use case of IAQ monitoring in a European project with a focus on Smart Cities with citizen engagement and involvement. It is well known that the cost of Air Quality (AQ) monitoring stations, which are often stationary, and generally produce reliable, and high-quality data is a non-starter for CS projects as cost prohibits the scaling of deployment and citizen involvement. On the other hand, it is widely assumed that low-cost devices for AQ, although available in abundance, often produce low-quality data, putting the credibility of basing any analysis on low-cost sensors. There is an increasing number of research efforts that look at how to ascertain the data quality of such sensors so that they could still be used reliably, often to provide indicative readings, and for analytics. In this work, we present data science-based techniques that have been utilised for selecting low-cost sensors based on their data quality indicators, and an integrated visualisation system that utilises structure data for IAQ to support multi-city trials in a CS project. The sensors are selected after analysing their consistency over a period by applying different approaches such as statistical analysis and graphical plots.