scholarly journals Dilemma Zone: Modeling Drivers’ Decision at Signalized Intersections against Aggressiveness and Other Factors Using UAV Technology

Safety ◽  
2021 ◽  
Vol 7 (1) ◽  
pp. 11
Author(s):  
Panagiotis Papaioannou ◽  
Efthymis Papadopoulos ◽  
Anastasia Nikolaidou ◽  
Ioannis Politis ◽  
Socrates Basbas ◽  
...  
Keyword(s):  
Relative Position ◽  
Latent Class ◽  
Latent Class Model ◽  
Explanatory Power ◽  
Dilemma Zone ◽  
Factors Affecting ◽  
Intersection Safety ◽  
Binary Choice Models ◽  
Aerial Vehicle ◽  
Zone Modeling

Intersection safety and drivers’ behavior are strongly interrelated, especially when the latter are located in dilemma zone. This paper explores, among others, the main factors affecting driver behavior, such as distance to stop line, approaching speed and acceleration/deceleration, and two additional factors, namely, driver’s aggressiveness and driver’s relative position at the onset of the yellow signal. Field data were collected using unmanned aerial vehicle (UAV) technology. Two binary choice models were developed, the first relying on observed data and the latter enriched by the latent factor drivers’ aggressiveness and the vehicles’ relative position. Drivers were classified to aggressive and non-aggressive ones using a latent class model that combined approaching speed and acceleration/deceleration data. Drivers were further grouped according to their expected reaction/decision to stop or cross the intersection in relation to their relative position. Both models equally explain drivers’ decisions adequately, but the second one offers additional explanatory power attributed to aggressiveness. Being able to identify the level of aggressiveness among the drivers enables the calculation of the probability that drivers will cross the intersection even if caught in a dilemma zone or in a zone in which the obvious decision is to stop. Such findings can be valuable when designing a signalized intersection and the traffic time settings, as well as the posted speed limit.

scholarly journals Exploring factors associated with red-light running: a case study of Hanoi city

2021 ◽  
Vol 72 (7) ◽  
pp. 800-810
Author(s):  
Dung Chu Tien
Keyword(s):  
Latent Class ◽  
Latent Class Model ◽  
Red Light ◽  
Probit Model ◽  
Red Light Running ◽  
Factors Affecting ◽  
Factors Associated ◽  
The Road ◽  
Road Users ◽  
The People

Red-light running (RLR) is the most significant factor involved in traffic crashes and injuries at signalized intersections. In Vietnam, little knowledge of factors affecting RLR has been found. This paper applied an ordered probit model to investigate factors associated with RLR using questionnaire data collected in Hanoi. Generally, this paper found that males and motorcyclists have a higher likelihood of RLR than females and car drivers. In addition, the younger and lower-income road users and the ones who are businessmen and who have a commuting trip in off-peak hours are more likely to run the red light. By contrast, the road users who go to school and the people who understand traffic law are less likely to violate the red light. In the future, it is necessary to collect data in different cities to generalize the results. In addition, may need to apply a more powerful method such as the latent class model, which can discover hidden facts among respondents. In the new model, other factors such as weather, waiting time, and countdown signal will be considered to investigate their effects on RLR.

scholarly journals Consumer Preferences for Private Label Brand vs. National Brand Organic Juice and Eggs: A Latent Class Approach

2021 ◽  
Vol 13 (13) ◽  
pp. 7028
Author(s):  
Ellen J. Van Loo ◽  
Fien Minnens ◽  
Wim Verbeke
Keyword(s):  
Orange Juice ◽  
Latent Class ◽  
Consumer Preferences ◽  
Latent Class Model ◽  
Organic Food ◽  
Food Products ◽  
Organic Production ◽  
Private Label ◽  
National Brand ◽  
Major Barrier

Many retailers have expanded and diversified their private label food product assortment by offering premium-quality private label food products such as organic products. With price being identified as the major barrier for organic food purchases, private label organic food products could be a suitable and more affordable alternative for many consumers. While numerous studies have examined consumer preferences for organic food, very few organic food studies have incorporated the concept of private labels. This study addresses this research gap by studying consumer preferences and willingness to pay for national brand and private label organic food using a latent class model. Specifically, this study analyzes consumer preferences for organic eggs and orange juice and the effect of national branding versus private label. Findings show heterogeneity in consumer preferences for production method and brand, with three consumer segments being identified based on their preferences for both juice and eggs. For eggs, about half of the consumers prefer private label and organic production, whereas one-quarter clearly prefers organic, and another quarter is indifferent about the brand and the organic production. For orange juice, the majority (75%) prefer the national brand. In addition, one-quarter of the consumers prefers organic juice, and about one-third values both organic and the national brand.

scholarly journals Head-to-head comparison of clustering methods for heterogeneous data: a simulation-driven benchmark

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Gregoire Preud’homme ◽  
Kevin Duarte ◽  
Kevin Dalleau ◽  
Claire Lacomblez ◽  
Emmanuel Bresso ◽  
...  
Keyword(s):  
Hierarchical Clustering ◽  
Latent Class ◽  
Latent Class Model ◽  
Real Life ◽  
Heterogeneous Data ◽  
Mixed Data ◽  
Categorical Variables ◽  
Clustering Methods ◽  
Model Based ◽  
Partitioning Around Medoids

AbstractThe choice of the most appropriate unsupervised machine-learning method for “heterogeneous” or “mixed” data, i.e. with both continuous and categorical variables, can be challenging. Our aim was to examine the performance of various clustering strategies for mixed data using both simulated and real-life data. We conducted a benchmark analysis of “ready-to-use” tools in R comparing 4 model-based (Kamila algorithm, Latent Class Analysis, Latent Class Model [LCM] and Clustering by Mixture Modeling) and 5 distance/dissimilarity-based (Gower distance or Unsupervised Extra Trees dissimilarity followed by hierarchical clustering or Partitioning Around Medoids, K-prototypes) clustering methods. Clustering performances were assessed by Adjusted Rand Index (ARI) on 1000 generated virtual populations consisting of mixed variables using 7 scenarios with varying population sizes, number of clusters, number of continuous and categorical variables, proportions of relevant (non-noisy) variables and degree of variable relevance (low, mild, high). Clustering methods were then applied on the EPHESUS randomized clinical trial data (a heart failure trial evaluating the effect of eplerenone) allowing to illustrate the differences between different clustering techniques. The simulations revealed the dominance of K-prototypes, Kamila and LCM models over all other methods. Overall, methods using dissimilarity matrices in classical algorithms such as Partitioning Around Medoids and Hierarchical Clustering had a lower ARI compared to model-based methods in all scenarios. When applying clustering methods to a real-life clinical dataset, LCM showed promising results with regard to differences in (1) clinical profiles across clusters, (2) prognostic performance (highest C-index) and (3) identification of patient subgroups with substantial treatment benefit. The present findings suggest key differences in clustering performance between the tested algorithms (limited to tools readily available in R). In most of the tested scenarios, model-based methods (in particular the Kamila and LCM packages) and K-prototypes typically performed best in the setting of heterogeneous data.

scholarly journals Multimorbidity patterns in old adults and their associated multi-layered factors: a cross-sectional study

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Jiao Lu ◽  
Yuan Wang ◽  
Lihong Hou ◽  
Zhenxing Zuo ◽  
Na Zhang ◽  
...  
Keyword(s):  
Latent Class ◽  
Metabolic Diseases ◽  
Ecological Model ◽  
Explanatory Power ◽  
Cross Sectional Study ◽  
Shanxi Province ◽  
Cluster Sampling ◽  
Cross Sectional ◽  
Old Patients ◽  
Old Adults

Abstract Background Influenced by various factors such as socio-demographic characteristics, behavioral lifestyles and socio-cultural environment, the multimorbidity patterns in old adults remain complex. This study aims to identify their characteristics and associated multi-layered factors based on health ecological model. Methods In 2019, we surveyed a total of 7480 participants aged 60+ by using a multi-stage random cluster sampling method in Shanxi province, China. Latent class analysis was used to discriminate the multimorbidity patterns in old adults, and hierarchical regression was performed to determine the multi-layered factors associated with their various multimorbidity patterns. Results The prevalence of multimorbidity was 34.70% among the old patients with chronic disease. Over half (60.59%) of the patients with multimorbidity had two co-existing chronic diseases. “Degenerative/digestive diseases”, “metabolic diseases” and “cardiovascular diseases” were three specific multimorbidity patterns. Behavioral lifestyles-layered factors had the most explanatory power for the three patterns, whose proportions of explanatory power were 54.00, 43.90 and 48.15% individually. But the contributions of other multi-layered factors were different in different patterns; balanced diet, medication adherence, the size of family and friendship network, and different types of basic medical insurance might have the opposite effect on the three multimorbidity patterns (p < 0.05). Conclusions In management of old patients with multimorbidity, we should prioritize both the “lifestyle change”-centered systematic management strategy and group-customized intervention programs.

Extreme price moves: an INGARCH approach to model coexceedances in commodity markets

2020 ◽  
Author(s):  
Bernardina Algieri ◽  
Arturo Leccadito
Keyword(s):  
Goodness Of Fit ◽  
Emerging Market ◽  
Explanatory Power ◽  
Commodity Markets ◽  
Credit Spread ◽  
Market Demand ◽  
Factors Affecting ◽  
Monday Effect ◽  
Tail Events ◽  
Weather Anomalies

Abstract This study presents a set of integer-valued generalised autoregressive conditional heteroskedastic models to identify possible transmission channels of joint extreme price moves (coexceedances) across a group of agricultural commodities. These models are very useful to identify factors affecting joint tail events and they are superior in terms of goodness of fit to models without autoregressive components. Emerging market demand, crude oil, exchange rate, stock market conditions and credit spread explain extreme joint returns. Psychological factors and the Monday effect play a role in affecting extreme events, while weather anomalies (El Niño and La Niña episodes) do not have explanatory power.

scholarly journals An ecological latent class model of adolescent risk and protective factors: Implications for substance use and depression prevention

2021 ◽  
pp. 016502542110055
Author(s):  
Benjamin L. Bayly ◽  
Sara A. Vasilenko
Keyword(s):  
Substance Use ◽  
Native American ◽  
Latent Class ◽  
Latent Class Model ◽  
Single Parent ◽  
Low Risk ◽  
Heavy Episodic Drinking ◽  
Health Study ◽  
Adolescent Risk ◽  
Parent Relationship

To provide a comprehensive view of the unique contexts shaping adolescent development in the U.S., we utilized latent class analysis (LCA) with indicators of risk and protection across multiple domains (family, peers, school, neighborhood) and examined how latent class membership predicted heavy episodic drinking, illicit substance use, and depression in adolescence and 6 years later when participants were young adults. Data came from Wave 1 (W1) and Wave 3 (W3) of the nationally representative U.S.-based Add Health study ( N = 6,649; Mage W1 = 14.06; Mage W3 = 20.38; 53.8% female; 56.1% White/European American, 22.8% Black/African American, 9.5% Hispanic, 6.7% Biracial, Asian or Pacific Islander 4.2%, American Indian/Native American 0.7%). A six-class solution was selected with classes named: Two Parent: Low Risk, Two Parent: Relationship Risks, Two Parent: Neighborhood Risks, Single Parent: Low Risk, Single Parent: Relationship Risks, and Single Parent: Multidimensional Risk. Subsequent analyses suggested that adolescent social relationships are particularly important for prevention interventions as the classes marked by substance using peers and a lack of closeness to parents and teachers in adolescence (Two Parent: Relationship Risks and Single Parent: Relationship Risks) had consistently poorer outcomes in adolescence and young adulthood.

Sign in / Sign up

Export Citation Format

Share Document