Exploratory Data Analysis Methods Research Articles

Implementation of Business Intelligence for Analysis Data of Drug Sales Using Exploratory Data Analysis (EDA) and Visualization Data Using Looker Studio

This study aims to analyze pharmaceutical sales performance by leveraging big data and advanced information technology tools, providing insights for improved business strategies. Using the Exploratory Data Analysis (EDA) method, the study processes raw sales data through spreadsheet applications to identify key patterns and trends. The findings are then visualized with Looker Studio on an intelligent dashboard tailored to the needs of the marketing team. The dashboard enables quick, data-driven decision-making by displaying performance metrics and trends relevant to sales and marketing strategies. The results reveal critical insights into sales behavior, including high-performing products, regional sales variations, and temporal sales trends. The analysis equips the marketing team with actionable data to refine their strategies, prioritize product focus, and adjust marketing efforts in response to identified patterns. In conclusion, the use of EDA and data visualization provides a structured approach to big data interpretation, allowing the company to optimize business and marketing performance. The study underscores the potential of data-driven dashboards to enhance strategic planning, suggesting broader applications in various data-intensive business environments.

Identification of organic contaminants in water and related matrices using untargeted liquid chromatography high-resolution mass spectrometry screening with MS/MS libraries

Nontargeted and suspect screening with liquid chromatography-high resolution mass spectrometry (LC-HRMS) has become an indispensable tool for quality assessment in the aquatic environment – complementary to targeted analysis of organic (micro)contaminants. An LC-HRMS method is presented, suitable for the analysis of a wide variety of water related matrices: surface water, groundwater, wastewater, sediment and sludge, including extracts from passive samplers and on-site solid phase enrichment, while focusing on the data processing aspect of the method. A field study is included to demonstrate the practical application and versatility of the whole process. HRMS/MS data were recorded following LC separation in both (ESI) positive and negative ionization modes using data dependent as well as data independent acquisition. Two vendor (Agilent's Personal Compound Database and Library and from National Institute of Standards and Technology) and one open (MassBank/EU) tandem mass spectral libraries were utilized for the identification of compounds via mass spectral match. The development of a novel software tool for parsing, grouping and reduction of MS/MS features in data files converted to mascot generic format (MGF) helped to substantially decrease the amount of time and effort needed for MS library search. While applying the method, in the course of the entire field study, 18771 detections (from 870 individual compounds) in total were recorded in 275 samples, resulting in 68.3 identified compounds per sample, on average. Among the top ten most frequently detected contaminants across all samples and sample types were pharmaceutical compounds carbamazepine, 4-acetamidoantipyrine, 4-formylaminoantipyrine, tramadol, lamotrigine and phenazone and industrial contaminants toluene-2-sulfonamide, tolytriazole, tris(2-butoxyethyl) phosphate and benzotriazole. Exploratory data analysis methods and tools enabled us to discover organic pollutant occurrence patterns within the comprehensive sets of qualitative data collected from various projects between the years 2018–2023. The results may be used as valuable inputs for future water quality monitoring programs.

Characterizing Temporal Patterns of Intra-Urban Human Mobility in Bike-Sharing through Trip Analysis: A Case Study of Shanghai, China

Human mobility, encompassing the movement of individuals and/or groups across space and time, significantly impacts various aspects of society, with intra-urban mobility being a major research focus of scholars in diverse disciplines. Bike-sharing systems have become an alternatives in cities for achieving more sustainable transportation. Hence, bike-sharing-related data are considered an important data source to study intra-urban human mobility. To better understand human mobility in cities, it is essential to characterize the typical patterns involved in intra-urban human mobility. This paper mainly focuses on characterizing the temporal patterns of intra-urban human mobility on bike-sharing based on the trip information of the acquired bike-sharing data. To achieve this, on the one hand, we adopted an exploratory data analysis (EDA) method to describe the temporal patterns by performing exploratory analyses of bike-sharing trips. On the other hand, we used the continuous triangular model (CTM) to conduct multi-temporal-scale analysis of bike-sharing trips for further explorations of the temporal patterns where necessary. The data of bike-sharing trips in Shanghai, China, were adopted as the dataset for the case study. Generally, the study was conducted at two different levels: the trip level and the bike level. Specifically, at each level, the explorations were conducted from varying perspectives. According to the analyses, numerous meaningful temporal patterns were discovered, and several distinctive findings were acquired. The results of this study show the effectiveness of the EDA and CTM methods in characterizing temporal patterns of intra-urban human mobility, based on which potentially insightful information and suggestions can be provided to assist related actions.

Spatiotemporal evolution and influencing factors of urban resilience in the Yellow River Basin, China

The Yellow River Basin of China is a key region that contains myriad interactions between human activities and natural environment. Industrialization and urbanization promote social-economic development, but they also have generated a series of environmental and ecological issues in this basin. Previous researches have evaluated urban resilience at the national, regional, urban agglomeration, city, and prefecture levels, but not at the watershed level. To address this research gap and elevate the Yellow River Basin’s urban resilience level, we constructed an urban resilience evaluation index system from five dimensions: industrial resilience, social resilience, environmental resilience, technological resilience, and organizational resilience. The entropy weight method was used to comprehensively evaluate urban resilience in the Yellow River Basin. The exploratory spatial data analysis method was employed to study the spatiotemporal differences in urban resilience in the Yellow River Basin in 2010, 2015, and 2020. Furthermore, the grey correlation analysis method was utilized to explore the influencing factors of these differences. The results of this study are as follows: (1) the overall level of urban resilience in the Yellow River Basin was relatively low but showed an increasing trend during 2010–2015, and significant spatial distribution differences were observed, with a higher resilience level in the eastern region and a low-medium resilience level in the western region; (2) the differences in urban resilience were noticeable, with industrial resilience and social resilience being relatively highly developed, whereas organizational resilience and environmental resilience were relatively weak; and (3) the correlation ranking of resilience influencing factors was as follows: science and technology level>administrative power>openness>market forces. This research can provide a basis for improving the resilience level of cities in the Yellow River Basin and contribute to the high-quality development of the region.

An integrated urban flooding risk analysis framework leveraging machine learning models: A case study of Xi'an, China

As global climate change intensifies and urbanization progresses, the frequency and extent of urban flooding have been increasing. This trend poses a significant threat to the safety and property of urban residents and severely impedes the advancement of sustainable development goals (SDGs). This study proposed an integrated urban flooding risk analysis framework to provide an essential basis for developing effective adaptation and mitigation measures. The kernel density estimation was adopted to analyze the distribution characteristics of urban flooding hotspots. The maximum entropy (MaxEnt) model was adopted for urban flooding risk probability assessment based on multi-source data. This study conducted an in-depth analysis from three perspectives including spatial analysis, risk planning and model comparison. The MaxEnt model and multiple exploratory spatial data analysis methods were combined to reveal spatial distribution patterns at grid cell scale. The MaxEnt and Zonation models were coupled to generate an urban flooding risk map. Further, six traditional machine learning models were compared with the MaxEnt model. The results indicate that rapid urbanization and intense human activities have significantly increased the number of buildings, leading to loss of previously existing blue and green spaces. These urban characteristics increase the vulnerability of cities to extreme rainfall. Compared to traditional machine learning models, the MaxEnt model has significant advantages. In the field of urban flooding risk, the MaxEnt model demonstrates significant potential for practical application. In summary, the framework empowers urban managers to comprehensively evaluate flooding risk in planning, supporting urban design and risk prevention.

RETRACTED: A semi-arid climate's use of exploratory data analysis (EDA) as a reliable non-parametric method for geochemical mapping

In this study, exploratory data analysis (EDA) methods, specifically boxplots, were employed to examine the composition of stream sediments in the Collo area of Northeast Algeria. The region's diverse lithological formations, interactions between permanent and temporary watercourses, intermittent flash floods, rugged topography, and fluctuating climatic conditions contribute significantly to data variability. Utilizing the boxplot's capabilities, our analytical approach successfully identified outliers, recorded the actual distribution of data, and determined skewness without the need for prior data processing, often required in conventional statistical studies. The boxplot proved to be an effective tool, offering insights into the geographical distribution of elemental concentrations, including iron (Fe), zinc (Zn), copper (Cu), arsenic (As), chromium (Cr), and lead (Pb). Geochemical mapping, driven by a robust class selection mechanism developed from the boxplot, revealed strong geographical correlations. A notable northeastern anomaly, characterized by elevated concentrations of Pb, Zn, Cu, and As, aligned with known base-metal sulfide and arsenopyrite mineralization sites. Additionally, outlier data for Cr indicated proximity to a plagioclase-lherzolite intrusion and known chromite deposits. The geographical distribution of iron, corresponding with known magnetite and hematite resources, was effectively highlighted using robust class selection based on boxplot analysis. This comprehensive investigation underscores the value of EDA methods in identifying mineralization trends amid the complex variability of the Collo area.

Caritas’s Work for the Goals of Agenda 2030: A Study on the Services Provided in Campania

The United Nations’ Agenda 2030 has established a series of Sustainable Development Goals to address global challenges, including poverty, food insecurity, access to education, and social inequality. In this context, charitable organizations such as Caritas play a crucial role in mitigating the negative effects of these challenges and promoting fair and sustainable development. This study aims to analyze prevalent needs among individuals seeking assistance from Caritas in Campania and examine how the organization contributes to achieving the Agenda 2030 Goals in the region. The statistical investigation techniques considered include tandem analysis a dimension-reduction technique, such as multiple factor analysis, and then a cluster analysis to identify similar groups of individuals. These exploratory data analysis methods have allowed for the identification of common needs, including food assistance, support for education, employment, and housing assistance. Subsequently, Caritas programs and initiatives aimed at meeting these needs and promoting sustainable development are explored. The results indicate that Caritas plays a significant role in addressing the urgent needs of the vulnerable population in Campania and contributes to the goals of Agenda 2030, particularly those related to poverty alleviation, immigration, health promotion, education, employment, and the reduction of social inequalities. This study provides an important perspective on the relevance and effectiveness of Caritas’s work in the context of Agenda 2030.

Deforestation drivers in northern Morocco: an exploratory spatial data analysis

Formulating effective policies to address or mitigate deforestation requires a comprehensive understanding of the contributing factors. This study examines the drivers of deforestation from 2001 to 2020 in the Tangier-Tetouan-Al Hoceima (TTA) region, a northern Moroccan area distinguished by the country’s highest deforestation rate. Through an extensive review of existing literature and employing Geist and Lambin’s deforestation framework, we identified five key causes: infrastructure extension, agricultural expansion, logging, wildfires as direct causes, and demographic factors as an indirect cause. Data on deforestation and its contributing factors were sourced from diverse databases, including Global Forest Change (GFC), Global Land Analysis and Discovery (GLAD), Burned Area Product (MODIS Fire_CCI51), World Population, Forest Proximate People (FPP), and National Forest Inventory (NFI) datasets. Pixel-level analysis of GFC data indicated that wildfires are the primary driver of deforestation in the region, accounting for 35.2%, followed by agricultural expansion (30.6%), logging (13.2%), and infrastructure extension (10.1%). The remaining 10.9% of losses were attributed to other disturbances, such as illegal extraction, pests, and dieback. Spatial patterns were further analyzed through Exploratory Spatial Data Analysis (ESDA) methods at a 1 km2 gridded scale, revealing strong clustering for all studied factors. Spatial relationships were explored using the bivariate local Moran’s index, which highlighted the highest spatial dependence between deforestation and fires (I = 0.21). Correlations between deforestation and other factors, including agricultural expansion, logging, infrastructure extension, and demographic pressure, were assessed at 0.18, 0.17, 0.08, and 0.05, respectively. Landscape pressures (LSP), encompassing deforestation, agricultural expansion, fires, infrastructure extension, and demographic pressure, were analyzed using the local Geary index, revealing a positive correlation in approximately 59% of spatial units. Last, a composite map of LSP clusters and an explanatory diagram illustrating dominant patterns in the TTA region were generated based on the results from local Geary’s multivariate and local Moran’s univariate tests.

Spatial modeling of the occurrences of geogenic fluoride in groundwater systems in Tanzania: Implications for the provision of safe drinking water

Inadequate data and spatial dependence in the observations during geochemical studies are among the disturbing conditions when estimating environmental factors contributing to the local variability in the pollutants of interest. Usually, spatial dependence occurs due to the researcher's imperfection on the natural scale of occurrence which affects the sampling strategy. As a consequence, observations on the study variable are significantly correlated in space. In this study, the machine learning approach was developed and used to study the environmental factors controlling the local variability in fluoride concentrations in drinking water sources of northern Tanzania within the East African Rift Valley. The approach constituted the use of geographical information systems (GIS) technology, exploratory spatial data analysis (ESDA) methods, and spatial regression modeling at a local level. The environmental variables used to study the local variation in fluoride concentration include topography, tectonic processes, water exchanges between hydrogeological layers during lateral movement, mineralization processes (EC), and water pH. The study was based on 20 local spatial regimes determined using GIS based on water sources density in the four hydrogeological environments. Specifically, the non-parametric (one-way Kruskal-Wallis sum ranks test and Multiple Comparisons Dunn Test), spatial statistics (Global Moran's I statistic), ordinary least squares (OLS) regression, and spatial lag models were used to quantify the effects of topography, tectonic processes, water exchange between hydrogeological environments and water physiochemical parameters (pH and EC) on the spatial variability of fluoride concentrations in drinking water sources at a local scale. In order of significance, the local spatial variation in fluoride concentration is influenced by the EC, topography, tectonic processes, pH, and water exchange between hydrogeological layers during water movement. The results presented in this paper are crucial for safe water access planning in naturally contaminated aquifer systems.

Spatio-temporal heterogeneity of urban ecological resilience in the middle reaches of the Yangtze River in China

Urban ecology is continuously suffering from risky impacts, and the enhancement of urban ecological resilience has become the basis of practice for addressing environmental challenges and responding to green development. The entropy weight method was used to measure the ecological resilience level of 28 cities in the middle reaches of the Yangtze River in China from 2008 to 2018, the Theil index decomposition method was used to measure the differences in resilience, the exploratory spatial data analysis method revealed its evolution law, and the obstacle model was used for the identification of influencing factors. The findings suggest that: (1) The level of ecological resilience of Chinese cities is generally on a fluctuating upward trend, and the gap between different provinces is gradually decreasing. (2) The spatial distribution of urban ecological resilience is characterized by a “central” feature, with provincial capitals generally higher than other regions, Hubei as a whole being characterized by “high in the east and low in the west” and “eccentricity”, while Hunan and Jiangxi have a “diffusion effect”. The spatial evolution stage can be divided into the period of ecological resilience impact and the overall enhancement period. (3) The area of green space in parks, the level of greening in built-up areas and the level of comprehensive utilization of industrial solid waste in general have always been the most important barriers to the level of ecological resilience of cities. In addition, factors such as the sound treatment of domestic waste, the treatment of respirable fine particulate matter, sewage treatment and the control of industrial smoke and dust in the city should not be overlooked. Based on this, policy recommendations such as promoting regional collaboration to reduce inter-provincial differences and implementing precise policies to address the main obstacles are proposed.

Exploratory Data Analysis (EDA) of Social Aid Recipients in Murung Raya District Central Kalimantan Province with Machine Learning Approach

Various kinds of problems often occur in programs implemented by the government, one of which is the problem that often arises is the uneven distribution of social assistance carried out to people with low economic levels, poverty is the main problem being faced by all countries in the world, including Indonesia. The purpose of implementing the dataset of social assistance recipients using EDA. To find the correlation of 4 variables, namely Number of Population, Number of Recipients, Occupation, and Age in the dataset of social assistance recipients in Murung Raya District, Central Kalimantan Province, with a machine learning approach. Then the research method used here is quantitative methods and experiments with machine learning approaches. So by using the EDA method on data on social assistance recipients in Murung Raya Regency, Central Kalimantan Province, it can be seen that the variable Number of population has.

Exploratory data analysis for electric vehicle driving range prediction: insights and evaluation

One of the biggest challenges of electric vehicle (EV) users has been predicting the amount of driving time their vehicles will have on one battery charge. Planning a trip and reducing range anxiety depends on an accurate range estimate. This study aims to anticipate the EV driving range using machine learning methods. In this research, several regression models for predicting EV driving range will be developed and compared. A real-world dataset comprising various factors affecting EV range, such as power, trip distance, energy consumption, driving style, and environmental factors, is used for analysis. The dataset is preprocessed using exploratory data analysis methods to manage missing values, outliers, and categorical variables. The findings of this study contribute to the expanding area of EV range prediction and provide EV buyers, producers, and regulators with insightful information. The user experience can be improved, EV adoption can be boosted, and effective charging infrastructure design is made possible with accurate range prediction. The study also highlights the importance of model selection and data pretreatment in making accurate predictions.

Identification of Geochemical Anomalies Based on RPCA and Multifractal Theory: A Case Study of the Sidaowanzi Area, Chifeng, Inner Mongolia.

The focus of exploration geochemistry is an accurate interpretation of geochemical data and the precise extraction of anomaly information related to mineralization from complex geological information. However, geochemical data are component data and exhibit a closure effect. Thus, traditional statistical methods cannot adequately reveal and identify the distribution of deep-seated anomaly information. This paper focuses on the Sidaowanzi area in Inner Mongolia and uses multivariate component data analysis methods to process 1:50 000 soil geochemical data. Using the Exploratory Data Analysis (EDA) method, the spatial distribution and internal structure characteristics of raw, logarithmic, and isometric logarithmic ratio (ILR) transformed data were compared and, coupled with robust principal component analysis (RPCA) and elemental component biplots, the association between element combinations and mineralization indicated by these three types of data was revealed. The S-A method was used to decompose composite anomalies of the ILR transformed RPCA score data to extract the characteristics of elemental combination anomalies and background distribution, and the Fry analysis method was utilized to analyze the dominant mineralization direction within the area. The results show that (1) data transformed using the ILR eliminated the influence of the closure effect, making the data more uniform on a spatial scale and exhibiting characteristics of an approximately normal distribution. (2) The S-A method was further used to decompose the composite anomaly of the PC1 and PC2 principal component combinations. The screened-out anomaly and background fields can essentially reflect the ore-causing anomalies dominated by Au and Cu-Mo mineralization. Moreover, the extracted anomalies and background information closely align with known mineral deposits (prospects) and can effectively identify weakly retarded geochemical anomaly information. (3) Fry analysis based on geochemical anomalies indicates that the dominant mineralization directions, by an assemblage dominated by Au and Cu-Mo, predominantly occur in the NE, NW, and proximate EW orientations. The combined application of the aforementioned three methods for the quantitative analysis of geochemical data aims to explore a transferable methodological system, providing new insights and approaches for further prediction of mineralization potential.

Lifting the veil off treatment effect heterogeneity

Clinicians often suspect that a treatment effect can vary across individuals. However, they usually lack “evidence-based” guidance regarding potential heterogeneity of treatment effects (HTE). Potentially actionable HTE is rarely discovered in clinical trials and is widely believed (or rationalized) by researchers to be rare. Conventional statistical methods to test for possible HTE are extremely conservative and tend to reinforce this belief. In truth, though, there is no realistic way to know whether a common, or average, effect estimated from a clinical trial is relevant for all, or even most, patients. This absence of evidence, misinterpreted as evidence of absence, may be resulting in sub-optimal treatment for many individuals. We first summarize the historical context in which current statistical methods for randomized controlled trials (RCTs) were developed, focusing on the conceptual and technical limitations that shaped, and restricted, these methods. In particular, we explain how the common-effect assumption came to be virtually unchallenged. Second, we propose a simple graphical method for exploratory data analysis that can provide useful visual evidence of possible HTE. The basic approach is to display the complete distribution of outcome data rather than relying uncritically on simple summary statistics. Modern graphical methods, unavailable when statistical methods were initially formulated a century ago, now render fine-grained interrogation of the data feasible. We propose comparing observed treatment-group data to “pseudo data” engineered to mimic that which would be expected under a particular HTE model, such as the common-effect model. A clear discrepancy between the distributions of the common-effect pseudo data and the actual treatment-effect data provides prima facie evidence of HTE to motivate additional confirmatory investigation. Artificial data are used to illustrate implications of ignoring heterogeneity in practice and how the graphical method can be useful.

Regional features of the manifestation of demographic threats in terms of characteristics of marriage, motherhood and childhood

The subject of the research is the regional characteristics of demographic indicators of marriage, motherhood and childhood, their relationship with the indicator of natural growth. At the same time, the natural decline of the population is considered as one of the key threats to the demographic and, consequently, national security of the population of the Russian Federation, since it entails a number of economic and geopolitical risks. The variability of indicators of marriage, motherhood and childhood is considered in the study as a possible source of variability in natural growth. Therefore, the regional peculiarities of the numerical characteristics of each of these features are analyzed in detail. Special attention is paid to regions showing abnormal values. In addition, the nature of the influence of individual indicators of marriage, motherhood and childhood on the natural growth rate has been studied in order to identify key factors determining the variability of the latter. The paper uses methods of exploratory data analysis: elements of descriptive statistics and diagrams to demonstrate trends . The closeness of the relationship between the indicators of the natural growth coefficient and the indicators of marriage, motherhood and childhood is also determined and a model of linear regression of the natural growth coefficient on the total fertility rate is constructed. The authors' contribution to the development of the topic is that, despite the simplicity of the stated methods, the study allowed us to identify regions with specific features in one or more indicators of marriage, motherhood, childhood, as well as natural growth. Further study of the features of regional demographic policy, the state of health, and cultural characteristics of the selected regions will allow us to borrow positive experience and correct negative trends, which should lead to a decrease in the factors determining the depopulation of the Russian population in terms of marriage, motherhood and childhood. The regression model allowed us to conclude that measures are needed to increase the total fertility rate, since, among the factors considered, the natural growth rate turned out to be the most sensitive to this trait, which simultaneously characterizes the propensity of women to motherhood and the intensity of fertility

Development of sensor system and data analytic framework for non-invasive blood glucose prediction

AbstractPeriodic quantification of blood glucose levels is performed using painful, invasive methods. The proposed work presents the development of a noninvasive glucose-monitoring device with two sensors, i.e., finger and wrist bands. The sensor system was designed with a near-infrared (NIR) wavelength of 940 nm emitter and a 900–1700 nm detector. This study included 101 diabetic and non-diabetic volunteers. The obtained dataset was subjected to pre-processing, exploratory data analysis (EDA), data visualization, and integration methods. Ambiguities such as the effects of skin color, ambient light, and finger pressure on the sensor were overcome in the proposed ‘niGLUC-2.0v’. niGLUC-2.0v was validated with performance metrics where accuracy of 99.02%, mean absolute error (MAE) of 0.15, mean square error (MSE) of 0.22 for finger, and accuracy of 99.96%, MAE of 0.06, MSE of 0.006 for wrist prototype with ridge regression (RR) were achieved. Bland–Altman analysis was performed, where 98% of the data points were within ± 1.96 standard deviation (SD), 100% were under zone A of the Clarke Error Grid (CEG), and statistical analysis showed p < 0.05 on evaluated accuracy. Thus, niGLUC-2.0v is suitable in the medical and personal care fields for continuous real-time blood glucose monitoring.

Tailored Mass Spectral Data Exploration Using the SpecXplore Interactive Dashboard.

Untargeted metabolomics promises comprehensive characterization of small molecules in biological samples. However, the field is hampered by low annotation rates and abstract spectral data. Despite recent advances in computational metabolomics, manual annotations and manual confirmation of in-silico annotations remain important in the field. Here, exploratory data analysis methods for mass spectral data provide overviews, prioritization, and structural hypothesis starting points to researchers facing large quantities of spectral data. In this research, we propose a fluid means of dealing with mass spectral data using specXplore, an interactive Python dashboard providing interactive and complementary visualizations facilitating mass spectral similarity matrix exploration. Specifically, specXplore provides a two-dimensional t-distributed stochastic neighbor embedding embedding as a jumping board for local connectivity exploration using complementary interactive visualizations in the form of partial network drawings, similarity heatmaps, and fragmentation overview maps. SpecXplore makes use of state-of-the-art ms2deepscore pairwise spectral similarities as a quantitative backbone while allowing fast changes of threshold and connectivity limitation settings, providing flexibility in adjusting settings to suit the localized node environment being explored. We believe that specXplore can become an integral part of mass spectral data exploration efforts and assist users in the generation of structural hypotheses for compounds of interest.

Research on the spatial allocation of national fitness resources at the street scale—taking Fuzhou city as an example

To explore the spatial allocation of national fitness resources at different spatial scales in Fuzhou city to provide useful references for optimizing and enhancing the spatial allocation of national fitness resources and urban planning. The equity, spatial distribution characteristics, accessibility and supply-demand balance of national fitness resources in Fuzhou city are analysed in depth by using the two-step mobile search method of multiple travel modes, the Gini coefficient, and exploratory spatial data analysis methods. The results show that the overall spatial allocation of national fitness resources is in a balanced state, but there are serious inequities and spatial mismatches in each district (county); the spatial distribution of national fitness resources is characterized by centralized agglomeration and surface dispersion, being dense in the south and sparse in the north. Areas with insufficient resources per capita have an agglomeration-type scattering distribution; areas with sufficient resources per capita have a dispersed patch distribution. Access to national fitness resources and the relationship between their supply and demand are characterized by positive spatial concentration; however, the layout of the national fitness resources planned for the old urban areas urgently needs to be optimized, with the Chating and Antai streets serving as centres, to increase the effective supply. Finally,we suggestions that Top-level design should be strengthened, the communalization of sports public services should be promoted, the service capacity and utilization efficiency of national fitness resources should be enhanced, and the construction of national fitness resources in new urban areas and new industrial agglomerations should be accelerated.

Data engineering for predictive machine learning of stormwater infrastructure conditions

Culverts are stormwater structures that require ongoing condition assessment and proactive maintenance for optimal performance to reduce flooding, especially in urban areas. Managing these structures can be complex and costly regarding time, money, and personnel resources. Machine learning (ML) tools are a powerful means of predicting culvert conditions via learning from their existing data records. However, the data available on such subjects are usually low in quantity and of various qualities; thus, they need significant data processing for ML. Existing stormwater infrastructure condition prediction studies rarely detail their data processing methods. Hence, this work uses a comprehensive case study to illustrate essential data preparation techniques to address common data issues and enhance the performance of commonly used ML algorithms. The study shows methods for exploratory data analysis to understand the dataset, data wrangling methods for preprocessing data of various quality, and data engineering procedures for addressing insufficient data issues. After the data processing procedures are applied, F-1 scores are used to evaluate the ML models' performance. The random forest classifier model, one of the four ML models, performed best after applying the data wrangling and data engineering methods. Overall, this work provides transparency of methods and applications to encourage ML use in the water resources engineering field.

Mathematical Modeling of Dengue Cases in Region XI Philippines

Dengue was recognized by the World Health Organization (WHO) in 2023 as a prominent arthropod-borne viral illness and poses a significant global health threat. This study focuses on Region XI in the Philippines, where dengue is alarmingly prevalent, and in forecasting dengue cases, it employs the ARIMA model. The study, spanning from January 2019 to August 2023, integrates univariate exploratory data analysis and statistical methods to understand the patterns and trends of dengue cases. The ARIMA model, specifically (0,0,1) with a nonzero mean, the candidate model, was identified and utilized from RStudio through coefficient tests of AIC values. The forecasting results predict a decline in dengue cases over the next 16 months. The normality test of residuals and Q-Q plot affirm the model’s reliability. A significant test using the two-sample t-test demonstrates a substantial difference between actual and forecasted values. In conclusion, this study provides crucial insights for public health planning, community intervention, and future research. The ARIMA model’s successful application emphasizes the need for refined dengue control and mitigation strategies in Region XI. The results underscore the urgency of collective efforts to minimize dengue transmission and address the challenges posed by this prevalent and impactful disease.