The Experts below are selected from a list of 92100 Experts worldwide ranked by ideXlab platform
Yunlong Zhang - One of the best experts on this subject based on the ideXlab platform.
-
predicting Motor Vehicle crashes using support vector machine models
Accident Analysis & Prevention, 2008Co-Authors: Xiugang Li, Dominique Lord, Yunlong ZhangAbstract:Crash prediction models have been very popular in highway safety analyses. However, in highway safety research, the prediction of outcomes is seldom, if ever, the only research objective when estimating crash prediction models. Only very few existing methods can be used to efficiently predict Motor Vehicle crashes. Thus, there is a need to examine new methods for better predicting Motor Vehicle crashes. The objective of this study is to evaluate the application of Support Vector Machine (SVM) models for predicting Motor Vehicle crashes. SVM models, which are based on the statistical learning theory, are a new class of models that can be used for predicting values. To accomplish the objective of this study, Negative Binomial (NB) regression and SVM models were developed and compared using data collected on rural frontage roads in Texas. Several models were estimated using different sample sizes. The study shows that SVM models predict crash data more effectively and accurately than traditional NB models. In addition, SVM models do not over-fit the data and offer similar, if not better, performance than Back-Propagation Neural Network (BPNN) models documented in previous research. Given this characteristic and the fact that SVM models are faster to implement than BPNN models, it is suggested to use these models if the sole purpose of the study consists of predicting Motor Vehicle crashes.
-
predicting Motor Vehicle crashes using support vector machine models
Transportation Research Board 87th Annual MeetingTransportation Research Board, 2008Co-Authors: Xiugang Li, Dominique Lord, Yunlong ZhangAbstract:Crash prediction models have been very popular in highway safety analyses. These models can be used for numerous applications, such as identifying the relationships between the dependent variable and a series of explanatory variables and for screening variables. Another important application of these models consists of estimating or predicting crashes, as its name implies, on facilities from which they were not used in the model development. However, in highway safety research, the prediction of outcomes is seldom, if ever, the only research objective when estimating crash prediction models. Only recently did researchers in highway safety focus their effort on developing models for the sole purpose of predicting Motor Vehicle crashes. Given this new line of research activity, very few methods currently exist that can be used to efficiently predict Motor Vehicle crashes and, for those available (e.g., Back-Propagation Neural Network, Bayesian Neural Network, etc.), they can sometimes be complex to implement and include important limitations, such as issues related to the over-fitting of data. Thus, there is a need to examine whether other new, simpler and innovative methods could be used for predicting Motor Vehicle crashes. The objective of this study is to evaluate the application of Support Vector Machine (SVM) models for predicting Motor Vehicle crashes. SVM models, which are based on the statistical learning theory, are a new class of models that can be used for predicting values. To accomplish the objective of this study, Negative Binomial (NB) regression and SVM models were developed and compared using data collected on rural frontage roads in Texas. Several models were estimated using different sample sizes. The study shows that SVM models predict crash data more effectively and accurately than traditional NB models. In addition, SVM models do not over-fit the data and offer similar, if not better, performance than Bayesian Neural Network (BNN) models documented in previous research. Given this characteristic and the fact that SVM models are easier to implement than BNN models, it is suggested to use these models if the sole purpose of the study consists of predicting Motor Vehicle crashes.
Stefanos N Kales - One of the best experts on this subject based on the ideXlab platform.
-
portable diagnostic devices for identifying obstructive sleep apnea among commercial Motor Vehicle drivers considerations and unanswered questions
Sleep, 2012Co-Authors: Chunbai Zhang, Mark Berger, Atul Malhotra, Stefanos N KalesAbstract:Obstructive sleep apnea (OSA), a syndrome defined by breathing abnormalities during sleep, can lead to fatigue and excessive daytime sleepiness (EDS) with an increased risk of Motor Vehicle crashes. Identifying commercial Motor Vehicle operators with unrecognized OSA is a major public health priority. Portable monitors (PMs) are being actively marketed to trucking firms as potentially lower-cost and more accessible alternatives to the reference standard of in-laboratory polysomnography (PSG) in the diagnosis of OSA among commercial Motor Vehicle operators. Several factors regarding PMs remain uncertain in this unique patient population: their sensitivity and specificity; the cost-benefit ratio of the PMs versus PSG; potential barriers from human factors; and evolving technologic advancement. Human factors that alter test accuracy are a major concern among commercial drivers motivated to gain/maintain employment. Current available data using PMs as a diagnostic tool among CMV operators indicate relatively high data loss and high loss to follow-up. Loss to follow-up has also been an issue using PSG in commercial Motor Vehicle operators. Furthermore, PM testing and PM results interpretation protocols may have no sleep specialist oversight, and sometimes minimal physician oversight and involvement. Additional studies comparing unattended and unmonitored PMs directly against full in-laboratory PSG are needed to provide evidence for their efficacy among commercial Motor Vehicle operators. CITATION: Zhang C; Berger M; Malhotra A; Kales SN. Portable diagnostic devices for identifying obstructive sleep apnea among commercial Motor Vehicle drivers: considerations and unanswered questions. SLEEP 2012;35(11):1481-1489. Language: en
Barbara Phillips - One of the best experts on this subject based on the ideXlab platform.
-
obstructive sleep apnea and risk of Motor Vehicle crash systematic review and meta analysis
Journal of Clinical Sleep Medicine, 2009Co-Authors: Stephen J Tregear, James Reston, Karen M Schoelles, Barbara PhillipsAbstract:STUDY OBJECTIVES: We performed a systematic review of the OSA-related risk of crash in commercial Motor Vehicle (CMV) drivers. The primary objective involved determining whether individuals with obstructive sleep apnea (OSA) are at an increased risk for a Motor Vehicle crash when compared to comparable individuals who do not have the disorder. A secondary objective involved determining what factors are associated with an increased Motor Vehicle crash risk among individuals with OSA. DESIGN/SETTING: Seven electronic databases (MEDLINE, PubMed (PreMEDLINE), EMBASE, PsycINFO, CINAHL, TRIS, and the Cochrane library) were searched (through May 27, 2009), as well as the reference lists of all obtained articles. We included controlled studies (case-control or cohort) that evaluated crash risk in individuals with OSA. We evaluated the quality of each study and the interplay between the quality, quantity, robustness, and consistency of the body of evidence, and tested for publication bias. Data were extracted by 2 independent analysts. When appropriate, data from different studies were combined in a fixed- or random-effects meta-analysis. RESULTS: Individuals with OSA are clearly at increased risk for crash. The mean crash-rate ratio associated with OSA is likely to fall within the range of 1.21 to 4.89. Characteristics that may predict crash in drivers with OSA include BMI, apnea plus hypopnea index, oxygen saturation, and possibly daytime sleepiness. CONCLUSIONS: Untreated sleep apnea is a significant contributor to Motor Vehicle crashes. Language: en
-
Adolescent sleep, school start times, and teen Motor Vehicle crashes.
Journal of clinical sleep medicine : JCSM : official publication of the American Academy of Sleep Medicine, 2008Co-Authors: Fred Danner, Barbara PhillipsAbstract:To assess the effects of delayed high school start times on sleep and Motor Vehicle crashes, a survey of the sleep habits of the students from an entire county-wide school district was administered before and after a change in school start times. There was only 1 school district in this county, and students from the entire district participated. State-collected measures of collision statistics by age and residence of driver were used to compute crash rates per 1000 licensed drivers for teen driv- ers before and after the change in school start times in both the county in which the start times changed and in the rest of the state, where start times remained unchanged. Methods study objectives : To assess the effects of delayed high-school start times on sleep and Motor Vehicle crashes. Methods : The sleep habits and Motor Vehicle crash rates of adoles- cents from a single, large, county-wide, school district were assessed by questionnaire before and after a 1-hour delay in school start times. Results : Average hours of nightly sleep increased and catch-up sleep on weekends decreased. Average crash rates for teen drivers in the study county in the 2 years after the change in school start time dropped 16.5%, compared with the 2 years prior to the change, whereas teen crash rates for the rest of the state increased 7.8% over the same time period. conclusions : Later school start times may both increase the sleep of adolescents and decrease their risk of Motor Vehicle crashes. Keywords: Adolescents, sleep deprivation, crash, public policy, school
Xiugang Li - One of the best experts on this subject based on the ideXlab platform.
-
predicting Motor Vehicle crashes using support vector machine models
Accident Analysis & Prevention, 2008Co-Authors: Xiugang Li, Dominique Lord, Yunlong ZhangAbstract:Crash prediction models have been very popular in highway safety analyses. However, in highway safety research, the prediction of outcomes is seldom, if ever, the only research objective when estimating crash prediction models. Only very few existing methods can be used to efficiently predict Motor Vehicle crashes. Thus, there is a need to examine new methods for better predicting Motor Vehicle crashes. The objective of this study is to evaluate the application of Support Vector Machine (SVM) models for predicting Motor Vehicle crashes. SVM models, which are based on the statistical learning theory, are a new class of models that can be used for predicting values. To accomplish the objective of this study, Negative Binomial (NB) regression and SVM models were developed and compared using data collected on rural frontage roads in Texas. Several models were estimated using different sample sizes. The study shows that SVM models predict crash data more effectively and accurately than traditional NB models. In addition, SVM models do not over-fit the data and offer similar, if not better, performance than Back-Propagation Neural Network (BPNN) models documented in previous research. Given this characteristic and the fact that SVM models are faster to implement than BPNN models, it is suggested to use these models if the sole purpose of the study consists of predicting Motor Vehicle crashes.
-
predicting Motor Vehicle crashes using support vector machine models
Transportation Research Board 87th Annual MeetingTransportation Research Board, 2008Co-Authors: Xiugang Li, Dominique Lord, Yunlong ZhangAbstract:Crash prediction models have been very popular in highway safety analyses. These models can be used for numerous applications, such as identifying the relationships between the dependent variable and a series of explanatory variables and for screening variables. Another important application of these models consists of estimating or predicting crashes, as its name implies, on facilities from which they were not used in the model development. However, in highway safety research, the prediction of outcomes is seldom, if ever, the only research objective when estimating crash prediction models. Only recently did researchers in highway safety focus their effort on developing models for the sole purpose of predicting Motor Vehicle crashes. Given this new line of research activity, very few methods currently exist that can be used to efficiently predict Motor Vehicle crashes and, for those available (e.g., Back-Propagation Neural Network, Bayesian Neural Network, etc.), they can sometimes be complex to implement and include important limitations, such as issues related to the over-fitting of data. Thus, there is a need to examine whether other new, simpler and innovative methods could be used for predicting Motor Vehicle crashes. The objective of this study is to evaluate the application of Support Vector Machine (SVM) models for predicting Motor Vehicle crashes. SVM models, which are based on the statistical learning theory, are a new class of models that can be used for predicting values. To accomplish the objective of this study, Negative Binomial (NB) regression and SVM models were developed and compared using data collected on rural frontage roads in Texas. Several models were estimated using different sample sizes. The study shows that SVM models predict crash data more effectively and accurately than traditional NB models. In addition, SVM models do not over-fit the data and offer similar, if not better, performance than Bayesian Neural Network (BNN) models documented in previous research. Given this characteristic and the fact that SVM models are easier to implement than BNN models, it is suggested to use these models if the sole purpose of the study consists of predicting Motor Vehicle crashes.
Chunbai Zhang - One of the best experts on this subject based on the ideXlab platform.
-
portable diagnostic devices for identifying obstructive sleep apnea among commercial Motor Vehicle drivers considerations and unanswered questions
Sleep, 2012Co-Authors: Chunbai Zhang, Mark Berger, Atul Malhotra, Stefanos N KalesAbstract:Obstructive sleep apnea (OSA), a syndrome defined by breathing abnormalities during sleep, can lead to fatigue and excessive daytime sleepiness (EDS) with an increased risk of Motor Vehicle crashes. Identifying commercial Motor Vehicle operators with unrecognized OSA is a major public health priority. Portable monitors (PMs) are being actively marketed to trucking firms as potentially lower-cost and more accessible alternatives to the reference standard of in-laboratory polysomnography (PSG) in the diagnosis of OSA among commercial Motor Vehicle operators. Several factors regarding PMs remain uncertain in this unique patient population: their sensitivity and specificity; the cost-benefit ratio of the PMs versus PSG; potential barriers from human factors; and evolving technologic advancement. Human factors that alter test accuracy are a major concern among commercial drivers motivated to gain/maintain employment. Current available data using PMs as a diagnostic tool among CMV operators indicate relatively high data loss and high loss to follow-up. Loss to follow-up has also been an issue using PSG in commercial Motor Vehicle operators. Furthermore, PM testing and PM results interpretation protocols may have no sleep specialist oversight, and sometimes minimal physician oversight and involvement. Additional studies comparing unattended and unmonitored PMs directly against full in-laboratory PSG are needed to provide evidence for their efficacy among commercial Motor Vehicle operators. CITATION: Zhang C; Berger M; Malhotra A; Kales SN. Portable diagnostic devices for identifying obstructive sleep apnea among commercial Motor Vehicle drivers: considerations and unanswered questions. SLEEP 2012;35(11):1481-1489. Language: en
