Public authorities frequently conduct surveys and analyse data from citizens, a process that is often labour-intensive when performed manually. This paper explores how Generative Artificial Intelligence (GAI) can assist in automating data analysis for public authorities. In this respect, we investigate the potential of Large Language Models (LLMs) to perform sentiment analysis and summarisation of unstructured data as smart services. Using data from the East Bristol Liveable Neighbourhood (EBLN) as a case study, we assess the accuracy and precision of these models and validate the results against ground truth data and expert evaluations. Our findings indicate that sentiment classification achieved over 90

Citizen science now relies heavily on digital platforms to engage the public in environmental data collection. Yet, many projects face declining participation over time. This study examines the effect of three elements of gamification—points, daily streaks, and real-time leaderboards—on student engagement, achievement, and immersion during a five-day campus-wide intervention utilising the GAME and a spatial crowdsourcing app. Employing a convergent mixed-methods design, we combined behavioural log analysis, validated psychometric scales (GAMEFULQUEST), and post-experiment interviews to triangulate both quantitative and qualitative dimensions of engagement. Results reveal that gamified elements enhanced students’ sense of accomplishment and early-stage motivation, which is reflected in significantly higher average scores for goal-directed engagement and recurring qualitative themes related to competence and recognition. However, deeper immersion and sustained “flow” were less robust with repetitive task design. While the intervention achieved only moderate long-term participation rates, it demonstrates that thoughtfully implemented game mechanics can meaningfully enhance engagement without undermining data quality. These findings provide actionable guidance for designing more adaptive, motivating, and inclusive citizen science solutions, underscoring the importance of mixed-methods evaluation in understanding complex engagement processes. While the sample size limits the statistical generalizability, this study serves as an exploratory field trial offering valuable design insights and methodological guidance for future large-scale, controlled citizen science interventions.

Indexing endoscopic surgical videos is vital in surgical data science, forming the basis for systematic retrospective analysis and clinical performance evaluation. Despite its significance, current video analytics rely on manual indexing, a time-consuming process. Advances in computer vision, particularly deep learning, offer automation potential, yet progress is limited by the lack of publicly available, densely annotated surgical datasets. To address this, we present TEMSET-24K, an open-source dataset comprising 24,306 trans-anal endoscopic microsurgery (TEMS) video micro-clips. Each clip is meticulously annotated by clinical experts using a novel hierarchical labeling taxonomy encompassing phase, task, and action triplets, capturing intricate surgical workflows. To validate this dataset, we benchmarked deep learning models, including transformer-based architectures. Our in silico evaluation demonstrates high accuracy (up to 0.99) and F1 scores (up to 0.99) for key phases like Setup and Suturing. The STALNet model, tested with ConvNeXt, ViT, and SWIN V2 encoders, consistently segmented well-represented phases. TEMSET-24K provides a critical benchmark, propelling state-of-the-art solutions in surgical data science.

Purpose To investigate procalcitonin (PCT) levels in full-term neonates managed for suspected early onset sepsis (EOS) due to probable maternal intrapartum sepsis. Methods Prospective longitudinal observational study at University Hospitals of Bristol NHS Foundation trust. Included were a total of 117 neonates managed for suspected EOS from June to October 2020. In addition to routine full-blood-counts and c-reactive protein (CRP) tests, serum PCT levels were also measured as part of the septic screen and follow-up blood tests. Placentas were sent for histopathology analysis. Neonatal parameters were used to categorize cases into: “high-suspicion bacterial sepsis (BS),” “equivocal BS” and “low-suspicion BS.” Statistical test Kruskal-Wallis compared categories with biomarker values and placental histopathology scores. Results A higher percentage of PCT levels showed elevation in comparison to CRP levels in the initial testing (55.3% versus 5.9%) and follow-up testing (98.9% versus 35%). There was a significant difference between the “low-suspicion BS” and “high-suspicion BS” categories for both the initial and follow-up PCT results. 71.2% of placentas showed varying degrees of chorioamnionitis. Conclusion This study provides evidence to the physiological rise in PCT during the first few days of life. The significant difference in PCT levels according to clinical severity shows that PCT could be utilized in calculating odds for EOS, but as a standalone test will have limited use.

This work presents the roadmap for the development of a research impact case study as it evolves with research carried out at the University of the West of England, in the United Kingdom (UK). The focus of the research is using Machine Learning algorithms in supporting decision making in terms of appropriate nutrition and other key factors in treating patients in Critical Care Units (CCUs) of hospitals in the UK. A first stage of the research has sought to improve the accuracy and timeliness of patient referrals to dietitians, upon arrival at the CCU. The results have shown that among various machine learning classifiers using data from various physio-logical measures of CCU patients a Support Vector Machine (SVC) classifier was the best performing model (AUC: 0.78). An electronic dashboard has been developed to support a decision maker at the CCU to process referrals efficiently and support enhanced patient care. The research has been extended to a different area of interest, this time focusing on paediatric CCU patients. The aim here it to use similar research methodologies to attempt to estimate energy expenditure for very young patients. This bears the challenge of having to use limited sized datasets, which the researchers attempt to address with explainable Artificial Intelligence.

Smart city digital twins can provide useful insights by making effective use of multidisciplinary urban data from diverse sources. Whilst these insights provide new information that helps cities in decision making, verifying the authenticity, integrity, traceability and data ownership across various functional units have become critical characteristics to ensure the data is from an authentic and trustworthy source. However, these characteristics are rarely considered in a digital twin ecosystem. In this research we introduce a novel framework, namely, ‘SIGNED: Smart cIty diGital twiN vErifiable Data framework’ that is designed on the basis of data ownership, selective disclosure and verifiability principles. Using Verifiable Credentials, SIGNED ensures digital twin data are verifiably authentic i.e., it covers provenance, transparency, and reliability through verifiable presentation. A proof of concept is designed and evaluated based on a smart water management use case to demonstrate the effectiveness of SIGNED in securing verifiable exchange of digital twin data across multiple functional units. The proof-of-concept demonstrates that SIGNED successfully allows the exchange of data in a trusted and verifiable manner at negligible performance cost, thus enhancing security and alleviating privacy issues when sharing data between various functional units in a smart city.

Critical Care Unit (CCU) patients often benefit from being referred to dietitians for various reasons. This can help improve recovery time, resulting in more effective utilisation of valuable resources within the NHS (National Health Service) in the United Kingdom. However, said resources are often in high demand with scarce availability. Therefore, in this paper we propose an AI-based dashboard that can help clinicians automatically identify such patients, thereby reducing workload as well as cognitive load on clinical staff. We have trained various machine learning classifiers using various physiological measures of CCU patients and have identified a Support Vector Machine (SVC) classifier as the best performing model (AUC: 0.78). Our investigation shows promise results that significantly improve quality of patient care within the NHS. In future we intend to undertake more extensive evaluation of the dashboard developed as well as extend this work to paediatric patients.

BACKGROUND:Procalcitonin is an established biomarker for bacterial sepsis in the nonpregnant population with better diagnostic and prognostic value for bacterial infections.OBJECTIVE:This study aimed to evaluate whether procalcitonin levels could be used in the diagnosis and management of intrapartum sepsis in women and their neonates suspected of intrapartum bacterial sepsis.STUDY DESIGN:A prospective observational cohort study was conducted at the University Hospitals of Bristol and Weston NHS Foundation Trust. Overall, 117 women and their neonates managed for suspected intrapartum sepsis from June 2020 to October 2020 were included. Procalcitonin levels were measured in addition to routine biomarkers white cell count and C-reactive protein in women and their neonates during the initial septic screen and follow-up blood samples. The placentas underwent detailed histopathology. Maternal and neonatal parameters were used to categorize cases into "high-suspicion bacterial sepsis," "equivocal bacterial sepsis," and "low-suspicion bacterial sepsis." The Kruskal-Wallis test was used to compare categories with biomarker values and placental histology scores.RESULTS:Procalcitonin level was increased in 6 women in the initial septic screen sample, compared with 100 women with an increased C-reactive protein level. There was a significant difference in maternal postnatal procalcitonin results between "high-suspicion bacterial sepsis" and "low-suspicion bacterial sepsis" categories (P=.004). Moreover, 71.2% of placentas showed varying degrees of chorioamnionitis.CONCLUSION:In our cohort of women, 94.6% had normal procalcitonin levels while in labor at the time of the septic screen, consistent with the low number of confirmed bacteremia. The result provided a basis that procalcitonin may complement clinical judgment and interpretation of already used prognostic and diagnostic tests, improving patient care in the management of intrapartum sepsis.

•We have undertaken a retrospective observational study describing the dynamics of PCT and CRP, including the response to antibiotic treatment, in adults with severe COVID-19 infection requiring ICU admission.•Results were compared to two better-understood groups of patients from historical data, adult ICU patients with either bacteraemia or influenza.•Elevated PCT in the first 48 h of admission was rare in COVID-19 patients. Where PCT was recorded it was <1.0 ng/L in 68.9% of COVID compared to 38% influenza patients.•PCT was low throughout the study, or responded rapidly to antibiotics 65.4% and 82.6% of COVID-19 and influenza patients respectively.•The dynamics of PCT in COVID-19 patients are consistent with a response to secondary bacterial infection and are not consistent with an inflammatory response to COVID-19 alone, and in contrast to CRP, PCT appears to be a useful biomarker in identifying COVID-19 patients with super-added bacterial.

Critical Care Units (CCU) in a hospital treat the severely sick patients that need constant monitoring and close medical attention. Feeding patients, enteral feeding in particular, is a critical and continuous process. Monitoring patients, managing their feeding and referring to a dietician is a key factor in CCUs. Screening patients for referral to a dietician in a CCU is an error-prone and complicated task. One of the main challenges in this regard is that the data needed to screen patients is scattered among many different variables and textual forms. The number of patients being treated in the CCU is also a significant problem since it becomes difficult for the staff to keep track of the needs of all patients. Therefore, an automated screening tool can support effectively the feeding process and contribute considerably towards improving the quality and consistency of patient care. In this paper we present early stages of a project that aims at using machine learning techniques to help CCU consultants to automatically screen patients for dietician referral.

With the increasing role of ICT in enabling and supporting smart cities, the demand for big data analytics solutions is increasing. Various artificial intelligence, data mining, machine learning and statistical analysis-based solutions have been successfully applied in thematic domains like climate science, energy management, transport, air quality management and weather pattern analysis. In this paper, we present a systematic review of the literature on smart city big data analytics. We have searched a number of different repositories using specific keywords and followed a structured data mining methodology for selecting material for the review. We have also performed a technological and thematic analysis of the shortlisted literature, identified various data mining/machine learning techniques and presented the results. Based on this analysis we also present a classification model that studies four aspects of research in this domain. These include data models, computing models, security and privacy aspects and major market drivers in the smart cities domain. Moreover, we present a gap analysis and identify future directions for research. For the thematic analysis we identified the themes smart city governance, economy, environment, transport and energy. We present the major challenges in these themes, the major research work done in the field of data analytics to address these challenges and future research directions. This article is categorized under: Application Areas > Government and Public Sector Fundamental Concepts of Data and Knowledge > Big Data Mining

Intelligence delivered by earth observation (EO) satellites performs a vital role in supporting ICT enabled urban governance, and the creation of decision making tools delivering integrated urban planning. This paper reviews the DECUMANUS project experience, detailing the development of the EO derived tools, and evaluating the service products that facilitate the deployment of top-down expertise in land use planning. The central purpose of the paper is to assess the potential for use of these DECUMANUS high resolution EO images and data, also to support bottom-up participatory planning, promoting co-design. It is concluded: 1) EO derived images and associated data offer great opportunity to deliver top-down decision making tools, which combined with auxiliary data, including participatory sensing data, effectively support integrated urban planning; 2) EO derived images also offer substantial potential as communication tools, enabling citizens to make more informed and responsible choices and participate in co-designed urban planning.

Effective communication with citizens is an important goal of smart cities. To this end the digital age offers many mechanisms to not only enable timely communication, but also bilateral communication. Mechanisms such as blog posts and online press releases allow cities and organisations to leverage these benefits. However, to assess the efficacy of these communication mechanisms, cities need to track the virality of the news they publish. To this end we propose a novel architecture that uses natural language processing techniques to track not only the resharing of the original articles, but also other articles and posts about that article. We have developed a prototype implementation of this article and present the interface as well as the results of performance tests.

Citizen participation for social innovation and co-creating urban regeneration proposals can be greatly facilitated by innovative IT systems. Such systems can use Open Government Data, visualise urban proposals in 3D models and provide automated feedback on the feasibility of the proposals. Using such a system as a communication platform between citizens and city administrations provides an integrated top-down and bottom-up urban planning and decision-making approach to smart cities. However, generating automated feedback on citizens' proposals requires modelling domain-specific knowledge i.e., vocabulary and rules, which can be applied on spatial and temporal 3D models. This paper presents the European Commission funded H2020 smarticipate project that aims to achieve the above challenge by applying it on three smart cities: Hamburg, Rome and RBKC-London. Whilst the proposed system architecture indicates various innovative features, a proof of concept of the automated feedback feature for the Hamburg use case 'planting trees' is demonstrated. Early results and lessons learned show that it is feasible to provide automated feedback on citizen-initiated proposals on specific topics. However, it is not straightforward to generalise this feature to cover more complex concepts and conditions which require specifying comprehensive domain languages, rules and appropriate tools to process them. This paper also highlights the strengths of the smarticipate platform, discusses challenges to realise its different features and suggests potential solutions.

This paper presents some results from an EU FP7 RTD project urbanAPI, in which three ICT applications target different aspects of participatory urban governance. The 3D Scenario Creator allows urban planners to visualise urban development proposals in three dimensions, share them with different stakeholders and obtain their feedback. The Mobility Explorer allows urban land use and transport planners to visualise and analyse population distribution and mobility patterns in the city. Finally, the Urban Development Simulator simulates socio-economic activity in response to alternative planning scenarios. These urbanAPI ICT applications are implemented in four pilot cities; Vienna (Austria), Vitoria-Gasteiz (Spain), Bologna (Italy) and Ruse (Bulgaria), and evaluated with respect to their various requirements. Results show that the applications are useful tools, enhancing spatial planning assessements, and enabling public participation, communicating proposed plans to different stakeholders and identifying key development issues which can provide crucial inputs in planning and decision making processes.

ICT is becoming an enabler for smart city applications by making effective use of various data resources generated daily in an urban environment. Mostly this data is utilised by city authorities for city planning purposes and often citizens become indirect beneficiaries of such applications. In this paper we present an algorithm for real-time processing of streaming data from multiple sources. We also present the design and proof of concept of an application that performs mining and analysis of open data available through city portals and social networks and generates an information service in real time for use by city administrations. The prototype utilises streaming data from Twitter and open data from Bristol to demonstrate a hypothetical scenario using Apache Storm. The output is presented in the form of visual maps using OpenStreetMaps as a backend and the prototype highlights various challenges which are discussed in detail.