Cluster Correspondence Analysis

Generation of nighttime pedestrian fatal precrash scenarios at junctions in Tamil Nadu, India, using cluster correspondence analysis

OBJECTIVE

Modern transportation amenities and lifestyles have changed people's behavioral patterns while using the road, specifically at nighttime. Pedestrian and driver maneuver behaviors change based on their exposure to the environment. Pedestrians are more vulnerable to fatal injuries at junctions due to increased conflict points with vehicles. Generation of precrash scenarios allows drivers and pedestrians to understand errors on the road during driver maneuvering and pedestrian walking/crossing. This study aims to generate precrash scenarios using comprehensive nighttime fatal pedestrian crashes at junctions in Tamil Nadu, India.

METHODS

Though numerous studies were available on identifying pedestrian crash patterns, only some focused on identifying crash patterns at junctions at night. We used cluster correspondence analysis (CCA) to address this research gap to identify the patterns in nighttime pedestrian fatal crashes at junctions. Further, high-risk precrash scenarios were generated based on the positive residual means available in each cluster. This study used crash data from the Road Accident Database Management System of Tamil Nadu State in India from 2009 to 2018. Characteristics of pedestrians, drivers, vehicles, crashes, light, and roads were input to the CCA to find optimal clusters using the average silhouette width, Calinski-Harabasz measure, and objective values.

RESULTS

CCA found 4 clusters with 2 dimensions as optimal clusters, with an objective value of 3.3618 and a valence criteria ratio of 80.03%. Results from the analysis distinctly clustered the pedestrian precrash behaviors: Clusters 1 and 2 on pedestrian walking behaviors and clusters 3 and 4 on crossing behaviors. Moreover, a hidden pattern was observed in cluster 4, such as transgender drivers involved in fatal pedestrian crashes at junctions at night.

CONCLUSION

The generated precrash scenarios may be used to train drivers (novice and inexperienced for nighttime driving), test scenario creation for developing advanced driver/rider assistance systems, hypothesis creation for researchers, and planning of effective strategic interventions for engineers and policymakers to change pedestrian and driver behaviors toward sustainable safety on Indian roads.

Visual hazardous models: A hybrid approach to investigate road hazardous events

Road users (drivers, passengers, pedestrians, and Animals) are exposed to hazardous events during their commute. With 23 % of global fatalities among pedestrians, their safety continues to be a principal interest for policymakers worldwide. Owing to limited budgets available, there is a growing emphasis on data-driven stochastic models to decide on policies. However, statistical models have limitations due to crash data having redundant features, inherent heterogeneity, and unobserved characteristics. The random parameter model framework addresses the unobserved heterogeneity, but redundant features and inherent heterogeneity among the data's characteristics still compute the biased estimates. This is further complicated if the data has spatiotemporal attributes. To address this, we developed two visual hazardous (VH) models: (i) addresses the unobserved heterogeneity in the data, and (ii) addresses the dimensionality, inherent heterogeneity among the characteristics and unobserved heterogeneity in the collected data after spatiotemporal pattern identification. The feature selection model reduces the dimensionality, whereas latent class clustering classifies the data into maximum heterogeneity between classes. This integration reduces bias in the estimates. As a use-case, pedestrian crosswalk crashes for a decade (2009-2018) in the Indian state of Tamil Nadu extracted from the Road Accident Database Management System (RADMS) was used to understand model performance. This data comprises the crash location, road, vehicle, driver, pedestrian, and environment details. Results show that visual hazardous model 2 allows for generating crash scenarios with five homogeneous sub-classes and the magnitude with marginal effects of contributing factors impacting it. For example, pedestrians during their crosswalks are likely to sustain 82% more chance of fatal/grievous injuries on expressways (posted speed limit: 100 km per hour) in annual hazardous zone locations. Working pedestrian age group (25-64 years), an older pedestrian (>64 years), the pedestrian position on a pedestrian crossing and not in the centre of the road, pedestrian action: walking along the edge of the road, multiple lanes, two lanes, paved shoulder, straight and flat road, motorcycle, bus, truck, medium-duty vehicle, illegal driver (<=17 years), going ahead/ overtaking, high speed, expressways, and rural region were statistically significant (positively) contributing to the fatal/grievous injury pedestrian crashes during their crosswalk. This technique serves as a structure for engineers, researchers, and policymakers to formulate effective countermeasures that enhance road safety.

Critical risk factors associated with fatal/severe crash outcomes in personal mobility device rider at-fault crashes: A two-step inter-cluster rule mining technique

Personal Mobility Devices (PMDs) have witnessed an extraordinary surge in popularity, emerging as a favored mode of urban transportation. This has sparked significant safety concerns, paralleled by a stark increase in PMD-involved crashes. Research indicates that PMD user behavior, especially in urban areas, is crucial in these crashes, underscoring the need for an extensive investigation into key factors, particularly those causing fatal/severe outcomes. Remarkably, there exists a noticeable gap in the research concerning the analysis of determinants behind fatal/severe PMD crashes, specifically in PMD rider-at-fault collisions. This study addresses this gap by identifying uniform groups of PMD rider-at-fault crashes and investigating cluster-specific key factor associations and determinants of fatal/severe crash outcomes using Seoul's PMD rider-at-fault crash data from 2017 to 2021. A comprehensive two-step framework, integrating Cluster Correspondence Analysis (CCA) and Association Rules Mining (ARM) techniques is employed to segment PMD rider-at-fault crash data into homogeneous groups, revealing unique risk factor patterns within each cluster and further exploring the combination of factors associated with fatal/severe PMD rider-at-fault crash outcomes. CCA revealed three distinct groups: PMD-vehicle, PMD-pedestrian, and single-PMD crashes. From the ARM, it was found that fatal/severe crashes were linked to dry road conditions, male PMD users, and weekdays, irrespective of the cluster. Whereas speeding violations and side collisions were associated with fatal/severe PMD-vehicle rider-at-fault crashes, traffic control violations were related to fatal/severe PMD-pedestrian rider-at-fault crashes at pedestrian crossings. Unsafe riding practices predominantly caused single-PMD crashes during daytime hours. From the findings, engineering improvements, awareness campaigns, education, and law enforcement actions are recommended. The new insights gleaned from this research provide a foundation for informed decision-making and the implementation of policies designed to enhance PMD safety.

Qluster: An easy-to-implement generic workflow for robust clustering of health data

The exploration of heath data by clustering algorithms allows to better describe the populations of interest by seeking the sub-profiles that compose it. This therefore reinforces medical knowledge, whether it is about a disease or a targeted population in real life. Nevertheless, contrary to the so-called conventional biostatistical methods where numerous guidelines exist, the standardization of data science approaches in clinical research remains a little discussed subject. This results in a significant variability in the execution of data science projects, whether in terms of algorithms used, reliability and credibility of the designed approach. Taking the path of parsimonious and judicious choice of both algorithms and implementations at each stage, this article proposes Qluster, a practical workflow for performing clustering tasks. Indeed, this workflow makes a compromise between (1) genericity of applications (e.g. usable on small or big data, on continuous, categorical or mixed variables, on database of high-dimensionality or not), (2) ease of implementation (need for few packages, few algorithms, few parameters, ...), and (3) robustness (e.g. use of proven algorithms and robust packages, evaluation of the stability of clusters, management of noise and multicollinearity). This workflow can be easily automated and/or routinely applied on a wide range of clustering projects. It can be useful both for data scientists with little experience in the field to make data clustering easier and more robust, and for more experienced data scientists who are looking for a straightforward and reliable solution to routinely perform preliminary data mining. A synthesis of the literature on data clustering as well as the scientific rationale supporting the proposed workflow is also provided. Finally, a detailed application of the workflow on a concrete use case is provided, along with a practical discussion for data scientists. An implementation on the Dataiku platform is available upon request to the authors.

Benchmarking distance-based partitioning methods for mixed-type data

Clustering mixed-type data, that is, observation by variable data that consist of both continuous and categorical variables poses novel challenges. Foremost among these challenges is the choice of the most appropriate clustering method for the data. This paper presents a benchmarking study comparing eight distance-based partitioning methods for mixed-type data in terms of cluster recovery performance. A series of simulations carried out by a full factorial design are presented that examined the effect of a variety of factors on cluster recovery. The amount of cluster overlap, the percentage of categorical variables in the data set, the number of clusters and the number of observations had the largest effects on cluster recovery and in most of the tested scenarios. KAMILA, K-Prototypes and sequential Factor Analysis and K-Means clustering typically performed better than other methods. The study can be a useful reference for practitioners in the choice of the most appropriate method.

A hybrid approach for the analysis of complex categorical data structures: assessment of latent distance learning perception in higher education

A long tradition of analysing ordinal response data deals with parametric models, which started with the seminal approach of cumulative models. When data are collected by means of Likert scale survey questions in which several scored items measure one or more latent traits, one of the sore topics is how to deal with the ordered categories. A stacked ensemble (or hybrid) model is introduced in the proposal to tackle the limitations of summing up the items. In particular, multiple items responses are synthesised into a single meta-item, defined via a joint data reduction approach; the meta-item is then modelled according to regression approaches for ordered polytomous variables accounting for potential scaling effects. Finally, a recursive partitioning method yielding trees provides automatic variable selection. The performance of the method is evaluated empirically by using a survey on Distance Learning perception.

Work from home in the post-COVID world

The working standard of shared office spaces has evolved in recent years. Due to the ongoing COVID-19 pandemic, many companies have instituted work from home (WFH) policies in accordance with public health guidelines in order to increase social distancing and decrease the spread of COVID-19. As the pandemic and WFH-related policies have continued for more than a year, there has been a rise in people becoming accustomed to the remote environments; however, others are more enthusiastic about returning to in-person work environments, reflecting the desire to restore pre-pandemic environments. As working from home is related to transportation issues such as changing commuting patterns and decreased congestion, motorized trips, and emission, there is a need to explore the extent of public attitudes on this important issue. This study used unique open-source survey data that provides substantial information on this topic. Using an advanced categorical data analysis method known as cluster correspondence analysis, this study identified several key findings. Not having prior WFH experiences, being eager to interact with colleagues, difficulties with adapting to virtual meeting technologies, and challenges with self-discipline while WFH were strongly associated with individuals who refused to continuously WFH at all after the pandemic. Individuals holding a strong view against the seriousness of the COVID-19 pandemic were also largely associated with never choosing WFH during and after the pandemic. For individuals with some prior WFH experiences, the transition to WFH every day in response to the outbreak was much easier, compared to those without prior experiences. Moreover, being forced to WFH during the COVID-19 pandemic positively influences the choice of WFH after the pandemic. The findings of this study will be beneficial to help policymakers and sustainable city planners understand public opinions about WFH.

Phenotypic clusters and survival analyses in interstitial pneumonia with myositis-specific autoantibodies

Background:

Idiopathic inflammatory myopathy (IIM) is highly combined with interstitial pneumonia (IP), often as the initial or solo presentation with positive myositis-specific autoantibodies (MSAs) but does not fulfill the diagnostic criteria.

Objectives:

We aimed to explore the phenotypic clusters and prognosis of the patients with IP and positive MSA, which is called MSA-IP in the present study.

Methods:

A total of 178 patients with MSA-IP were prospectively enrolled for analysis. Serum MSAs were detected using Western blotting. Radiological patterns of IP were determined according to the classification of idiopathic IPs. Clusters of patients with MSA-IP were identified using cluster analysis. Predictors for acute/subacute onset, therapeutic response, IP progression and survival were also analyzed.

Results:

Patients with MSA-IP were classified into four distinct clusters. Cluster 1 were the elderly with chronic onset, nearly normal oxygenation and good survival. Cluster 2 had dyspnea on exertion and nonspecific IP pattern, with moderate survival. Patients in cluster 3 had chronic onset and were prone to IP progression (OR 2.885). Cluster 4 had multi-systemic involvements, positive anti-melanoma differentiation associated gene 5 antibody, and were prone to acute/subacute onset (OR 3.538) and IP progression (OR 5.472), with poor survival. Corticosteroids combined immunosuppressants showed therapeutic response in MSA-IP (OR 4.303) and had a protective effect on IP progression (OR 0.136).

Conclusions:

Four clusters of the patients with MSA-IP suggested the distinct clinical, radiological and prognostic features.

Subclustering in Skeletal Class III Phenotypes of Different Ethnic Origins: A Systematic Review

OBJECTIVE

We aimed to systematically review articles investigating the efficiency of the clustering of skeletal class III malocclusion phenotypic subtypes of different ethnic origins as a diagnostic tool.

METHODS

The review protocol was structured in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses statement and registered in Prospero (CRD42016053865). A survey of articles published up to March 2018 investigating the identification of different subgroups of skeletal class III malocclusion via cluster analysis was performed using 11 electronic databases. Any type of study design that addressed the classification of subclusters of class III malocclusion was considered. The Newcastle-Ottawa scale for cohort and cross-sectional (modified) studies was used for quality assessment.

RESULTS

The final selection included 7 studies that met all the criteria for eligibility (% overall agreement 0.889, free marginal kappa 0.778). All studies identified at least 3 different types of class III clusters (ranging from 3 to 14 clusters; the total variation of the prevalence of each cluster ranged from 0.2% to 36.0%). The main shared variables used to describe the more prevalent clusters in the studies included were vertical measurements (Ar-Go-Me: 117.51°-135.8°); sagittal measurements: maxilla (SNA: 75.3°-82.95°), mandible (SNB: 77.03°-85.0°). With regard to ethnicity, a mean number of 8.5 and 3.5 clusters of class III were retrieved for Asian and Caucasian population, respectively.

CONCLUSIONS

The total number of clusters identified varied from 3 to 14 to explain all the variability in the phenotype class III malocclusions. Although each extreme may be too simple or complex to facilitate an exhaustive but useful classification for clinical use, a classification system including 4 to 7 clusters may prove to be efficient for clinical use in conjunction with complete and meticulous subgrouping.

CLINICAL SIGNIFICANCE

The identification and description of a subclustering classification system may constitute an additional step toward more precise orthodontic/orthopedic diagnosis and treatment of skeletal class III malocclusion.