Search

Sustainability-focused research networks and communities of practice have emerged as a key response and strategy to build capacity and knowledge to support transformation towards more sustainable, just and equitable futures. This paper synthesises insights from the development of a community of practice on social-ecological systems (SES) research in southern Africa over the past decade, linked to the international Programme on Ecosystem Change and Society (PECS). This community consists of a network of researchers who carry out place-based SES research in the southern African region. They interact through various cross-cutting working groups and also host a variety of public colloquia and student and practitioner training events. Known as the Southern African Program on Ecosystem Change and Society (SAPECS), its core objectives are to: (1) derive new approaches and empirical insights on SES dynamics in the southern African context; (2) have a tangible impact by mainstreaming knowledge into policy and practice; and (3) grow the community of practice engaged in SES research and governance, including researchers, students and practitioners. This paper reflects on experiences in building the SAPECS community, with the aim of supporting the development of similar networks elsewhere in the world, particularly in the Global South.

This article evaluates the presence of framing mechanisms in Dutch media reporting on the Second Karabakh war. The paper is led by the following questions: To what extent, and why, does the reporting of the Dutch press favour/undermine certain actors in the conflict? What kind of framing patterns are involved in generating such partiality? And did the frames change over the course of the war? In order to evaluate the presence of framing mechanisms in Dutch media reporting on the second Karabakh war, this research conducted a qualitative data analysis of 188 articles on the topic in nine major national Dutch news media. The paper finds that Dutch newspapers created a rather stereotypical, simplified picture of the Second Karabakh war. There are instances where the reporting gave the impression of a possible bias or overemphasis on certain dimensions.

The work of artists, creatives and the cultural community that provides arts, culture and artistic education to society deserves due credit. It is not always easy to find the appropriate mechanisms to appraise and communicate in what ways this work impacts and benefits different target groups, different communities and society as whole. There is an urgent need for reliable evaluation of qualitative achievements of cultural and creative endeavours. We argue that, after years of focusing on the quantities of (economic) life, the time has arrived for considering the qualities of life. The new creative economy, based on sustainable development, calls for a different way of thinking: the Value-Based Approach (VBA). This paper will address the theoretical and methodological aspects of the VBA and suggests why it is a useful method for evaluating (social and cultural) impact of cultural production. This paper will draw on some empirical examples of the application of the VBA to the cultural sector.

Visual selective attention refers to the selection of relevant visual elements in a scene whilst ignoring irrelevant visual elements. Visual Selective Attention Dysfunctions (VSAD) are prevalent in children with Cerebral Visual Impairment (CVI), Attention Deficit Hyperactivity Disorder (ADHD), and Dyslexia. An important issue in the pediatric neuropsychological practice is how to discriminate between the task performance of these populations. We conducted a scoping review of the literature on visual search performance (VSP) in children with CVI, ADHD, and Dyslexia, aged 6-12 years. After a systematic selection process, 35 studies were included. Results suggest that all patient groups have some degree of impaired VSP compared to typically developing children. Children with CVI tend to react slower and less accurately. VSP impairments in children with ADHD are characterized by poor accuracy rather than reaction time. Children with Dyslexia tend to be slower and less accurate, depending on stimulus type. Besides VSAD, it is argued that other neurocognitive mechanisms might influence VSP, such as speed-accuracy trade-off or an executive functioning deficit in ADHD and a phonological deficit in Dyslexia. This paper further discusses the differences and similarities in visual search performance between the groups. The sparse data in children with an official diagnosis of CVI and the technical inconclusive data on children with ADHD and Dyslexia demonstrate complexity of discriminating between these populations in clinical practice based on VSP. New and more quantitative VSP parameters, such as eye tracking-based measures, may contribute to a refined classification among CVI, ADHD, and Dyslexia.

The level of defence industrial innovation success has been modest in Malaysia, despite continuous investment into research and development (R&D). The authors use the Defence Research and Development Stakeholder Engagement Framework (DRDSEF) to argue that strategic collaborative engagement between stakeholders is critical for successful industrial and technological innovation. This paper has two aims: to describe the role of the stakeholders in managing defence R&D funding and to evaluate the challenges faced by these stakeholders in managing government defence R&D allocation for industrial and technological innovation. This is an exploratory case study using a combination of interpretivist and pragmatist philosophical approaches. Analysed data consists of secondary resources and primary resources included surveys in the form of open-ended semi-structured interviews and participatory observation. This paper concludes that successful defence R&D stakeholder engagement requires an open and independent platform, enhanced industry-academia cross-sector fertilisation and collaborative data analytics management tools to share information.\ud \ud

Owing to growing uncontrolled land-use change and urban expansion, farmers in urban fringes are struggling to sustain their livelihood. Farmers have been expressing their dissatisfaction at different times. This study analyzes the stakeholders' perspectives on the causes and outcomes of farmers' resistance to land-use change and urban expansion processes by zooming in on Bahir Dar, Ethiopia. The paper is based on focus group discussions with farmers in the neighboring villages, local agricultural extension experts, and, subsequently, key informant interviews of local government officials. Juxtaposing farmers' and local experts' positions reveals that inadequate compensations during land expropriation, lack of good governance in the urban expansion process, and inaccessibility of infrastructures are primary reasons for the farmers' struggle against urban expansion in the urban fringes. This study provides insights into the consequences of unplanned urban development challenges and may inform research and policymaking on sustainable urban development in the area and beyond.

In this paper, we study the influence of seasonal demands and forecasts on the performance of an Automatic Pipeline, Variable Inventory, Order-Based, Production Control System (APVIOBPCS) using linear control theory. In particular, we consider a system that uses a seasonal forecast based on a no-trend, additive-seasonality exponential-smoothing model, and compare its performance to an equivalent system using simple exponential smoothing. We find that the system with seasonal forecasting significantly outperforms the system with simple exponential smoothing under certain demand assumptions. With optimal parameter settings, the forecast error of the seasonal model can be up to 40% lower. However, we also find that the forecast superiority does not necessarily translate to the performance of the system measured through the bullwhip metrics. In addition, the seasonal forecasting model is very sensitive to the demand frequency and smoothing parameters, while the simple exponential smoothing model is very robust. This implies that the real life benefits of implementing a seasonal forecasting model are not obvious and depend on the particular situation; under a large number of settings (e.g. low seasonality, high-smoothing), the good performance of simple exponential smoothing certainly justifies its popularity in the industry and research worlds alike.

Introduction: There is a need for structured approaches to inform on pharmacotherapy in pretermneonates. With their proven track record up to regulatory acceptance, physiologically based pharmacokinetic (PBPK) modeling and simulation provide a structured approach, and hold the promise tosupport drug development in preterm neonates.Areas covered: Compared to general and pediatric use of PBPK modeling, its use to inform pharmacotherapy in preterms is limited. Using a systematic search (PBPK + preterm), we retained 25 records (20research papers, 2 letters, 3 abstracts). We subsequently collated the published information on PBPKsoftware packages (PK-Sim®, Simcyp®), and their applications and optimization efforts in pretermneonates. It is encouraging that applications cover a broad range of scenarios (pharmacokineticdynamic analyses, drug-drug interactions, developmental pharmacogenetics, lactation related exposure) and compounds (small molecules, proteins). Furthermore, specific compartments (cerebrospinalfluid, tissue) or (patho)physiologic processes (cardiac output, biliary excretion, first pass metabolism) areconsidered.Expert opinion: Knowledge gaps exist, giving rise to various levels of uncertainty in PBPK applicationsin preterm neonates. To improve this, we need cross talk between clinicians and modelers to generateand integrate knowledge (PK datasets, system knowledge, maturational physiology and pathophysiology) to further refine PBPK models.

This collective paper on radicalization and violent extremism part of the 'Philosophy of education in a new key' initiative by Educational Philosophy and Theory brings together some of the leading contemporary scholars writing on the most pressing epistemological, ethical, political and educational issues facing post-9/11 scholarship on radicalization and violent extremism. Its overall aim is to move beyond the 'conventional wisdom' associated with this area of scholarly research best represented by its many slogans, metaphors and other thought-terminating cliches. By providing conceptual lenses on issues previously compartmentalized primarily [or even exclusively] in security and intelligence studies or at the fringes of scholarly interest, radicalization and violent extremism turn out to be much more complex than 'radicalization studies' has been eager to acknowledge.

This paper proposes a new model averaging method to address model uncertainty in Poisson regressions, allowing the dimension of covariates to increase with the sample size. We derive an unbiased estimator of the Kullback–Leibler (KL) divergence to choose averaging weights. We show that when all candidate models are misspecified, the proposed estimate is asymptotically optimal by achieving the least KL divergence among all possible averaging estimators. In another situation where correct models exist in the model space, our method can produce consistent coefficient estimates. We apply the proposed techniques to study the determinants and predict corporate innovation outcomes measured by the number of patents.

The construction type of reinforcement material is a critical factor playing an essential role in the mechanical performance of composite materials. Recently, much attention has been attracted to discovering the mechanical behaviour of glass woven fabric, such as plain and different variations of twill and satin reinforced composites. In this paper, it is aimed to test the effect of a combination of unique characteristics of woven and knitted fabrics in the same matrix on the mechanical behaviour of composites. In this direction, carbon tows are fabricated into plain woven, 2/2 twill woven and interlock knitted fabrics. The effect of reinforcement construction on bending and tensile properties like strength, modulus and strain of epoxy composites manufactured in three variations as woven, knitted and woven/knitted reinforced was investigated by conducting 3-point bending and tensile tests. Experimental results indicated that hybrid composites displayed lower bending strength than woven fabric composites. However, a combination of 2/2 twill woven and knitted fabric in hybrid composites, including five fabric layers, had a higher bending modulus than 2/2 twill woven composites, including seven fabric layers. Also, it was observed that the mechanical performance of hybrid composites under tensile load was poor compared to the woven fabric composites.

Introduction: Ocular toxoplasmosis is the leading cause of posterior uveitis worldwide, affecting individuals acrossdifferent age groups. The key to reducing vision loss includes prompt diagnosis and treatment. However, despite the prevalence of ocular toxoplasmosis, there has been little consensus regarding its pathophysiology,clinical features, diagnosis, and especially management. Methods: The data sources were literature reviews, including Pub Med and Medline databases. Search terms included toxoplasmosis, retinitis, vasculitis, vitritis, uveitis alone or in combination with, serum, aqueous, vitreous eye, ocular and review. Results: In this review paper, we have sought to provide an overview of the pathophysiology, epidemiology, and clinical features of the disease, both based on current literature and our own clinical experience. We have also discussed the use of serology, ocular fluid, and ophthalmic investigations that could further facilitate the diagnosis of ocular toxoplasmosis.Different management strategies have been reported worldwide, including newer approaches such as local therapy. Conclusion: A better understanding of critical aspects of ocular toxoplasmosis will hopefully lead to reduced morbidity, including blindness associated with this condition.

This paper presents a new Cloud-deployable DEVS-based framework for optimising UAV trajectories and sensor strategies in target-search missions. DEVS provides it with a well-established, flexible, and verifiable modelling strategy to include different models for the UAV, sensor, and target dynamics; the target and sensor uncertainty; and the optimising process. Its Cloud deployability speeds up the evaluations/simulations required to optimise this NP-hard problem, which involves computationally heavy models when solving real-world missions. The framework, designed to handle different types of target-search missions, currently optimises, using a multi-objective Genetic Algorithm, free-shape trajectories of multiple UAVs,eqquiped with several static/movable sensors to detect a target within a search area. It is implemented in xDEVS and deployable over a set of containers in the Google Cloud Platform. The results show that our deployment policy speeds up the computation up to 3.35 times, letting the operator simultaneously optimise several search strategies for agiven scenario.

Background\ud Treatment success is the desired outcome in aphasia rehabilitation. However, to date, there is a lack of consensus on what defines a 'successful' result on a given aphasia outcome measurement instrument (OMI).\ud \ud Aim\ud In this methodological paper, we present strategies for how to define and measure treatment success on a given OMI at the group-level, as well as for an individual person with aphasia. The latter is particularly important when research findings from group studies are clinically implemented for individuals in rehabilitation.\ud \ud Scope\ud We start by presenting methods to calculate the average statistically significant change across several (group) studies (e.g., standardised mean difference, raw unstandardised mean difference) for a given OMI. Such metrics are useful to summarise the overall effect of the intervention of interest, particularly in meta-analyses. However, benchmarks based on group effects are not feasible for assessing an individual participant’s treatment success and thus for determining the proportion of patients who had a beneficial response to therapy (overall response rate of an intervention). We therefore recommend a distribution-based approach to determine benchmarks of a statistically significant treatment response at the individual level, i.e., the 'smallest detectable change' for a given OMI, which refers to the smallest change that can be detected by the OMI beyond measurement error. However, the statistical significance of an individual treatment effect does not necessarily correspond to its clinical impact. This requires an additional indicator. The benchmark to determine a clinically relevant improvement on a given OMI is the 'minimal important change'. The minimally important change is defined as the smallest OMI change score perceived as important by the relevant stakeholder group (i.e., people with aphasia, their relatives/caregivers, clinicians). It therefore requires relating the individual OMI change scores to 'anchors', i.e., meaningful external criteria, preferably based on patient-perceived therapy success. Currently, there is no consensus regarding the optimal 'anchors' and their respective definition of clinically important change in aphasia outcome research.\ud \ud Conclusions/Recommendations\ud Operationalising individual treatment success based on both statistically significant and (patient-reported) clinically meaningful benchmarks is a key priority in aphasia rehabilitation. Availability of such measures will (a) facilitate estimates of therapy response rate in intervention studies and thus optimise therapeutic decisions and (b) provide stakeholder groups (e.g., the society, the stroke team, people with aphasia, family, clinicians, healthcare professionals) with objective, statistically reliable and meaningful feedback on individual treatment response in the clinical setting.

This review aimed, as part of a larger FIFA project aiming to steer women's football research, to scope literature on any level of competitive football for women, to understand the current quantity of research on women's football injuries. The study reviewed all injury-related papers scoped by a recent scoping review mapping all published women's football research with an updated search performed on 23 February 2021. Eligibility criteria assessment followed the recent scoping review with injury-specific research focus. A total of 497 studies were scoped. Most studies contained an epidemiological (N = 226; 45%) or risk factors assessment (N = 105; 21%). Less assessed areas included financial burden (N = 1

This work is motivated by recent researches in particles and their bienergy in different types of geometric structures and applied physical spacetime phases. In this paper, we define a new approach of bienergy and biangle with Sasaki metric in Minkowski spacetime. Moreover, we use the ED-frame method for bienergy and biangle of first and second kind fields. We study the bienergy and biangle for the extended Darboux frame (ED-frame) fields of first and second kind on some hypersurfaces in Minkowski spacetime. Also, we obtain main results as a new relationship for biangle and bienergy of the particle on the hypersurface in Minkowski spacetime. We get new geometric properties of some graphics with the bienergy and biangle. Finally, we determine a new relationship for biangle and bienergy of the particle on the hypersurface in Minkowski spacetime.

The phenomenon of contemporary tourism, overtourism, known mainly from destinations such as Barcelona, Venice, Amsterdam or Prague, does not avoid even small destinations with a rather regional character. Karstejn (Czech Republic), known for its iconic Gothic castle, is visited by up to 250,000 visitors every year. The township Karlstejn is thus daily exposed to the streams of tourists who influence the local environment, inhabitants and the quality of their lives. While the negative influences and impacts of overtourism on the locals in the destination are already well mapped, despite the importance of the influence and the vital role that visitors play in a destination, little academic attention has been directed toward understanding their point of view (Moyle et s., 2013). Therefore, this paper aims to fill this research gap and to examine the visitors’ perception of overtourism impacts in the peak season in the destination Karlstejn. 174 questionnaires were obtained during August 2019 and evaluated using statistical methods of principal component analysis (PCA), linear regression and non-parametric analysis of variance (ANOVA). The results show contradiction to a general definition of overtourism (UNWTO, 2018; Responsible Tourism Partnership, 2019) that implies a deterioration in the quality of life of both local and negative impact on the visitors' experience.

Geohazard risk is high in Arab countries due to ineffective disaster preparedness measures, mismanagement, lack of public awareness, inadequate funding and lack of stakeholder support. One such country is Egypt, which is hit by floods every year that cost lives and bring the economy to a standstill. Moreover, not much has been done to map flood-prone areas. In this paper, flood susceptibility modelling was evaluated in the Ras Gharib region of Egypt using two effective techniques machine learning technique-MLT (Support Vector Machine (SVM)) and deep learning method-DL (Convolutional Neural Networks (CNN)). Thirteen flood related factors and flood inventory layer were prepared to construct these models. Validation was performed with 30% of the flood locations where receiver operating characteristic (ROC) curves showed that the deep learning technique (CNN) gave a prediction accuracy of 86.5% (high performance), while the MLTs (SVM) gave 71.6% (medium performance). The results show that CNN provides 17% better than SVM which indicates a powerful and accurate model in flood susceptibility mapping. Results were confirmed using the Astro Digital images shortly after the 2016 flood, in which the CNN model provides a good agreement.

The paper is devoted to the integral functionals $\int_0^\infty f(X_t)\,{\mathrm{d}t}$ of Markov processes in $\X$ in the case $d\ge 3$. It is established that such functionals can be presented as the integrals $\int_{\X} f(y) \G(x, \mathrm{d}y, \omega)$ with vector valued random measure $\G(x, \mathrm{d}y, \omega)$. Some examples such as compound Poisson processes, Brownian motion and diffusions are considered., Comment: 12 pages. arXiv admin note: text overlap with arXiv:2006.07514

We consider the problem of deriving from experimental data an approximation of an unknown function, whose derivatives also approximate the unknown function derivatives. Solving this problem is useful, for instance, in the context of nonlinear system identification for obtaining models that are more accurate and reliable than the traditional ones, based on plain function approximation. Indeed, models identified by accounting for the derivatives can provide a better performance in several tasks, such as multi-step prediction, simulation, Nonlinear Model Predictive Control, and control design in general. In this paper, we propose a novel approach based on convex optimization, allowing us to solve the aforementioned identification problem. We develop an optimality analysis, showing that models derived using this approach enjoy suitable optimality properties in Sobolev spaces. The optimality analysis also leads to the derivation of tight uncertainty bounds on the unknown function and its derivatives. We demonstrate the effectiveness of the approach with two numerical examples. The first one is concerned with approximation of an univariate function, the second one with multi-step prediction of the Chua chaotic circuit.

Complex product and production systems often result in high variability in the production flow, prohibiting the sustainable implementation of lean practices. In this paper the authors introduce a PDCA cycle to analyse and reduce variability in value streams. The value stream is divided into zones, which are then qualified as stable or unstable. Lean practices can be applied in stable zones, unstable zones remain expert-driven. Measures are introduced to reduce variability in unstable zones with the ultimate target, to turn them into stable zones, extending sustainable lean activities in the value stream, step by step. An IT system is developed to acquire, process and visualise the vast amount of data to provide structured information for experts and management for the reduction of variability in production.

The characterization of firearm discharge residue (FDR) as a piece of evidence plays an essential role in interpreting the forensic cases involving the use of firearms, such as robberies, murders, suicides, and serious attacks. In the last decade, modern or non-toxic primers have emerged due to environmental issues. Forensic examination of gunshot residue (GSR) has become challenging as primer compositions now vary greatly. The goal of this paper is to provide the elemental profiling of both toxic and lead-free cartridge primers available in the Turkish ammunition market. Inductively coupled plasma-mass spectrometry (ICP-MS), scanning electron microscopy coupled with energy-dispersive X-ray analysis (SEM-EDS), and X-ray photoelectron spectroscopy (XPS) were used in this investigation. Multivariate statistical methodologies such as principal component analysis (PCA) and Pearson's correlation coefficient (PCC) analysis were used to interpret the elemental profile data determined in the residue generated after ignition of the cartridge primers. Three components were observed: Ba-Sb-Pb-Cu-Gd, Ti-Sr-Zn, and Al-Ca-Ga, which is also consistent with the PCC analysis. SEM-EDS was employed to confirm the existence of GSR particles. The binding energies, determined using XPS, indicated the chemical state assignments in samples such as Pb(NO3)(2), Sb2S3, Ba(NO3)(2), CuO, ZnO and MoS2. This research will improve the robustness of the interpretation of GSR-related evidence., Giresun University Scientific Research Unit [FEN-BAP-A-270220-40], This study was financially supported by Giresun University Scientific Research Unit [Fund Number: FEN-BAP-A-270220-40].

Assessing the extent and level of building damages is crucial to support post-earthquake rescue and relief activities. There is a large body of literature proposing novel frameworks for automating earthquake-induced building damage mapping using high-resolution remote sensing images. Yet, its deployment in real-world scenarios is largely limited to the manual interpretation of images. Although manual interpretation is costly and labor-intensive, it is preferred over automatic and semi-automatic building damage mapping frameworks such as machine learning and deep learning because of its reliability. Therefore, this review paper explores various automatic and semi-automatic building damage mapping techniques with a quest to understand the pros and cons of different methodologies to narrow the gap between research and practice. Further, the research gaps and opportunities are identified for the future development of real-world scenarios earthquake-induced building damage mapping. This review can serve as a guideline for researchers, decision-makers, and practitioners in the emergency management service domain.

In this paper we provide two significant extensions to the recently developed parameter estimation-based observer design technique for state-affine systems. First, we consider the case when the full state of the system is reconstructed in spite of the presence of unknown, time-varying parameters entering into the system dynamics. Second, we address the problem of reduced order observers with finite convergence time. For the first problem, we propose a simple gradient-based adaptive observer that converges asymptotically under the assumption of generalised persistent excitation. For the reduced order observer we invoke the advanced dynamic regressor extension and mixing parameter estimator technique to show that we can achieve finite convergence time under the weak interval excitation assumption. Simulation results that illustrate the performance of the proposed adaptive observers are given. This include, an unobservable system, an example reported in the literature and the widely popular, and difficult to control, single-ended primary inductor converter.

This paper presents the results of field and laboratory studies of slurry tracks along the South Coast rail line in NSW, Australia. Site investigations on fouled tracks were followed by a series of laboratory tests to determine the properties of mud fines, and how they can reduce track performance. This study reveals two distinctly different ways of forming slurry tracks, i.e., non-subgrade and subgrade mud pumping, resulting in different characteristics of degraded tracks. More cohesive the fouling materials are, the greater the reduction in hydraulic conductivity (kb) and shear strength (Sb) of the contaminated ballast. When the fouling index FI > 30%, kb drops severely, causing insufficient drainage capacity of the track while the loss of Sb can exceed 22%. Different types of fouling index are also discussed with reference to the field and laboratory data, followed by proposed empirical equations to estimate the values of kb and Sb.

The mounting evidence of unintended harmful social consequences of automated algorithmic decision-making (AADM), powered by AI and big data, in transformative services (e.g., welfare services), is startling. The algorithmic harm experienced by individuals, communities and society-at-large involves new injustice claims and disputes that go beyond issues of social justice. Drawing from the theory of “abnormal justice” in this paper we articulate a new theory of algorithmic justice that addresses the questions: WHAT is the matter of algorithmic justice? WHO counts as a subject of algorithmic justice? HOW are algorithmic justices performed? and How to address and resolve disputes about the WHAT, WHO and HOW of algorithmic justice? We illustrate the theory of algorithmic justice by drawing from a case of AADM in social welfare services, widely adopted by governments around the world. Our research points to datafication, technological inscribing and the systemic nature of injustices as important IS-specific aspects of algorithmic justice. Our main practical contribution comes from the articulation of algorithmic justice as a framework that (1) makes visible the injustices related to the “what”, “who”, and “how” of AADM in transformative services, and (2) provides further insights into how we might address and resolve these algorithmic injustices.

Dengue Fever (DF) is a common vector-borne disease with catastrophic health implications. DF prediction modelling is a challenging task, although technologies such as Geographical Information Systems (GIS) and spatial statistics have improved our understanding of dengue dynamics. In this paper, we create a robust data analysis model to (i) provide a better understanding of confirmed dengue fever cases despite missing data, (ii) obtain better insights into risk factors associated with confirmed cases, and (iii) by means of machine learning, create clusters of patients with comparable characteristics. The last was accomplished with a self-organizing feature map (SOFM) and the density-based spatial clustering of applications with noise (DBSCAN). The approaches used to classify confirmed cases were: Decision Tree, k-nearest neighbours, Random Forest, AdaBoost, Support Vector Classification (SVC), CatBoost, and Naive Bayes. The CatBoost classifier achieved the best accuracy for the analysis of confirmed cases. Spatial analysis was conducted using the ordinary least square (OLS) and geographically weighted regression (GWR) models to identify high-risk areas. SOM can group patients with similar features into clusters, then DBSCAN detects and retrieves six clusters from this data. The clustering of confirmed cases increases CatBoost’s modelling prediction accuracy and reveals complex factors that influence prediction accuracy. Because confirmed cases in each cluster have different features, CatBoost is applied to each cluster individually to improve the prediction accuracy. Variable values in each cluster are analysed to clarify the confirmed cases of a specific subset of DF incidents. Overall, OLS outperforms GWR when identifying hotspot areas. The proposed novel, data-driven and machine-learning-based strategy facilitates the understanding and identification of patterns associated with confirmed DF cases. The study's findings can be utilized to cluster historical patient data into groups or subgroups sharing similar variables. Using identifiable patient clusters rather than raw history data improves the model accuracy provided by CatBoost.