Modeling crash outcome probabilities at rural intersections: Application of hierarchical binomial logistic models

It is important to examine the nature of the relationships between roadway, environmental, and traffic factors and motor vehicle crashes, with the aim to improve the collective understanding of causal mechanisms involved in crashes and to better predict their occurrence. Statistical models of motor vehicle crashes are one path of inquiry often used to gain these initial insights. Recent efforts have focused on the estimation of negative binomial and Poisson regression models (and related deviants) due to their relatively good fit to crash data. Of course analysts constantly seek methods that offer greater consistency with the data generating mechanism (motor vehicle crashes in this case), provide better statistical fit, and provide insight into data structure that was previously unavailable. One such opportunity exists with some types of crash data, in particular crash-level data that are collected across roadway segments, intersections, etc. It is argued in this paper that some crash data possess hierarchical structure that has not routinely been exploited. This paper describes the application of binomial multilevel models of crash types using 548 motor vehicle crashes collected from 91 two-lane rural intersections in the state of Georgia. Crash prediction models are estimated for angle, rear-end, and sideswipe (both same direction and opposite direction) crashes. The contributions of the paper are the realization of hierarchical data structure and the application of a theoretically appealing and suitable analysis approach for multilevel data, yielding insights into intersection-related crashes by crash type.

Multi-step ahead direct prediction for the machine condition prognosis using regression trees and neuro-fuzzy systems

This paper presents an approach to predict the operating conditions of machine based on classification and regression trees (CART) and adaptive neuro-fuzzy inference system (ANFIS) in association with direct prediction strategy for multi-step ahead prediction of time series techniques. In this study, the number of available observations and the number of predicted steps are initially determined by using false nearest neighbor method and auto mutual information technique, respectively. These values are subsequently utilized as inputs for prediction models to forecast the future values of the machines’ operating conditions. The performance of the proposed approach is then evaluated by using real trending data of low methane compressor. A comparative study of the predicted results obtained from CART and ANFIS models is also carried out to appraise the prediction capability of these models. The results show that the ANFIS prediction model can track the change in machine conditions and has the potential for using as a tool to machine fault prognosis.

Modeling random effect and excess zeros in road traffic accident prediction

Poisson distribution has often been used for count like accident data. Negative Binomial (NB) distribution has been adopted in the count data to take care of the over-dispersion problem. However, Poisson and NB distributions are incapable of taking into account some unobserved heterogeneities due to spatial and temporal effects of accident data. To overcome this problem, Random Effect models have been developed. Again another challenge with existing traffic accident prediction models is the distribution of excess zero accident observations in some accident data. Although Zero-Inflated Poisson (ZIP) model is capable of handling the dual-state system in accident data with excess zero observations, it does not accommodate the within-location correlation and between-location correlation heterogeneities which are the basic motivations for the need of the Random Effect models. This paper proposes an effective way of fitting ZIP model with location specific random effects and for model calibration and assessment the Bayesian analysis is recommended.

Freeway travel time estimation & prediction : a literature review

This report is the second deliverable of the Real Time and Predictive Traveller Information project and the first deliverable of the Freeway Travel Time Information sub-project in the Integrated Traveller Information research Domain of the Smart Transport Research Centre. The primary objective of the Freeway Travel Time Information sub-project is to develop algorithms for real-time travel time estimation and prediction models for Freeway traffic. The objective of this report is to review the literature pertaining to travel time estimation and prediction models for freeway traffic.

Arterial travel time estimation & prediction : a literature review

This report is the fourth deliverable of the Real Time and Predictive Traveller Information project and the first deliverable of the Arterial Travel Time Information sub-project in the Integrated Traveller Information research Domain of the Smart Transport Research Centre. The primary objective of the Arterial Travel Time Information sub-project is to develop algorithms for real-time travel time estimation and prediction models for arterial traffic. The objective of this report is to review the literature pertaining to travel time estimation and prediction models for arterial traffic.

Travel time prediction on signalised urban arterials by applying SARIMA modelling on Bluetooth data

Travel time prediction has long been the topic of transportation research. But most relevant prediction models in the literature are limited to motorways. Travel time prediction on arterial networks is challenging due to involving traffic signals and significant variability of individual vehicle travel time. The limited availability of traffic data from arterial networks makes travel time prediction even more challenging. Recently, there has been significant interest of exploiting Bluetooth data for travel time estimation. This research analysed the real travel time data collected by the Brisbane City Council using the Bluetooth technology on arterials. Databases, including experienced average daily travel time are created and classified for approximately 8 months. Thereafter, based on data characteristics, Seasonal Auto Regressive Integrated Moving Average (SARIMA) modelling is applied on the database for short-term travel time prediction. The SARMIA model not only takes the previous continuous lags into account, but also uses the values from the same time of previous days for travel time prediction. This is carried out by defining a seasonality coefficient which improves the accuracy of travel time prediction in linear models. The accuracy, robustness and transferability of the model are evaluated through comparing the real and predicted values on three sites within Brisbane network. The results contain the detailed validation for different prediction horizons (5 min to 90 minutes). The model performance is evaluated mainly on congested periods and compared to the naive technique of considering the historical average.

Development and validation of anthropometric prediction equations for estimation of lean body mass and appendicular lean soft tissue in Indian men and women

Lean body mass (LBM) and muscle mass remains difficult to quantify in large epidemiological studies due to non-availability of inexpensive methods. We therefore developed anthropometric prediction equations to estimate the LBM and appendicular lean soft tissue (ALST) using dual energy X-ray absorptiometry (DXA) as a reference method. Healthy volunteers (n= 2220; 36% females; age 18-79 y) representing a wide range of body mass index (14-44 kg/m2) participated in this study. Their LBM including ALST was assessed by DXA along with anthropometric measurements. The sample was divided into prediction (60%) and validation (40%) sets. In the prediction set, a number of prediction models were constructed using DXA measured LBM and ALST estimates as dependent variables and a combination of anthropometric indices as independent variables. These equations were cross-validated in the validation set. Simple equations using age, height and weight explained > 90% variation in the LBM and ALST in both men and women. Additional variables (hip and limb circumferences and sum of SFTs) increased the explained variation by 5-8% in the fully adjusted models predicting LBM and ALST. More complex equations using all the above anthropometric variables could predict the DXA measured LBM and ALST accurately as indicated by low standard error of the estimate (LBM: 1.47 kg and 1.63 kg for men and women, respectively) as well as good agreement by Bland Altman analyses. These equations could be a valuable tool in large epidemiological studies assessing these body compartments in Indians and other population groups with similar body composition.

Effects of seasonal variability on FT-NIR prediction of dry matter content for whole Hass avocado fruit

Fourier Transform (FT)-near infra-red spectroscopy (NIRS) was investigated as a non-invasive technique for estimating percentage (%) dry matter of whole intact 'Hass' avocado fruit. Partial least squares (PLS) calibration models were developed from the diffuse reflectance spectra to predict % dry matter, taking into account effects of seasonal variation. It is found that seasonal variability has a significant effect on model predictive performance for dry matter in avocados. The robustness of the calibration model, which in general limits the application for the technique, was found to increase across years (seasons) when more seasonal variability was included in the calibration set. The R-v(2) and RMSEP for the single season prediction models predicting on an independent season ranged from 0.09 to 0.61 and 2.63 to 5.00, respectively, while for the two season models predicting on the third independent season, they ranged from 0.34 to 0.79 and 2.18 to 2.50, respectively. The bias for single season models predicting an independent season was as high as 4.429 but <= 1.417 for the two season combined models. The calibration model encompassing fruit from three consecutive years yielded predictive statistics of R-v(2) = 0.89, RMSEP = 1.43% dry matter with a bias of -0.021 in the range 16.1-39.7% dry matter for the validation population encompassing independent fruit from the three consecutive years. Relevant spectral information for all calibration models was obtained primarily from oil, carbohydrate and water absorbance bands clustered in the 890-980, 1005-1050, 1330-1380 and 1700-1790 nm regions. These results indicate the potential of FT-NIRS, in diffuse reflectance mode, to non-invasively predict the % dry matter of whole 'Hass' avocado fruit and the importance of the development of a calibration model that incorporates seasonal variation. Crown Copyright (c) 2012 Published by Elsevier B.V. All rights reserved.

A study of vertical cloud structure of the Indian summer monsoon using CloudSat data

Precise specification of the vertical distribution of cloud optical properties is important to reduce the uncertainty in quantifying the radiative impacts of clouds. The new global observations of vertical profiles of clouds from the CloudSat mission provide opportunities to describe cloud structures and to improve parameterization of clouds in the weather and climate prediction models. In this study, four years (2007-2010) of observations of vertical structure of clouds from the CloudSat cloud profiling radar have been used to document the mean vertical structure of clouds associated with the Indian summer monsoon (ISM) and its intra-seasonal variability. Active and break monsoon spells associated with the intra-seasonal variability of ISM have been identified by an objective criterion. For the present analysis, we considered CloudSat derived column integrated cloud liquid and ice water, and vertically profiles of cloud liquid and ice water content. Over the South Asian monsoon region, deep convective clouds with large vertical extent (up to 14 km) and large values of cloud water and ice content are observed over the north Bay of Bengal. Deep clouds with large ice water content are also observed over north Arabian Sea and adjoining northwest India, along the west coast of India and the south equatorial Indian Ocean. The active monsoon spells are characterized by enhanced deep convection over the Bay of Bengal, west coast of India and northeast Arabian Sea and suppressed convection over the equatorial Indian Ocean. Over the Bay of Bengal, cloud liquid water content and ice water content is enhanced by similar to 90 and similar to 200 % respectively during the active spells. An interesting feature associated with the active spell is the vertical tilting structure of positive CLWC and CIWC anomalies over the Arabian Sea and the Bay of Bengal, which suggests a pre-conditioning process for the northward propagation of the boreal summer intra-seasonal variability. It is also observed that during the break spells, clouds are not completely suppressed over central India. Instead, clouds with smaller vertical extent (3-5 km) are observed due to the presence of a heat low type of circulation. The present results will be useful for validating the vertical structure of clouds in weather and climate prediction models.

Robot navigation in dense crowds : statistical models and experimental studies of human robot cooperation

This thesis explores the problem of mobile robot navigation in dense human crowds. We begin by considering a fundamental impediment to classical motion planning algorithms called the freezing robot problem: once the environment surpasses a certain level of complexity, the planner decides that all forward paths are unsafe, and the robot freezes in place (or performs unnecessary maneuvers) to avoid collisions. Since a feasible path typically exists, this behavior is suboptimal. Existing approaches have focused on reducing predictive uncertainty by employing higher fidelity individual dynamics models or heuristically limiting the individual predictive covariance to prevent overcautious navigation. We demonstrate that both the individual prediction and the individual predictive uncertainty have little to do with this undesirable navigation behavior. Additionally, we provide evidence that dynamic agents are able to navigate in dense crowds by engaging in joint collision avoidance, cooperatively making room to create feasible trajectories. We accordingly develop interacting Gaussian processes, a prediction density that captures cooperative collision avoidance, and a "multiple goal" extension that models the goal driven nature of human decision making. Navigation naturally emerges as a statistic of this distribution.

Most importantly, we empirically validate our models in the Chandler dining hall at Caltech during peak hours, and in the process, carry out the first extensive quantitative study of robot navigation in dense human crowds (collecting data on 488 runs). The multiple goal interacting Gaussian processes algorithm performs comparably with human teleoperators in crowd densities nearing 1 person/m², while a state of the art noncooperative planner exhibits unsafe behavior more than 3 times as often as the multiple goal extension, and twice as often as the basic interacting Gaussian process approach. Furthermore, a reactive planner based on the widely used dynamic window approach proves insufficient for crowd densities above 0.55 people/m². We also show that our noncooperative planner or our reactive planner capture the salient characteristics of nearly any dynamic navigation algorithm. For inclusive validation purposes, we show that either our non-interacting planner or our reactive planner captures the salient characteristics of nearly any existing dynamic navigation algorithm. Based on these experimental results and theoretical observations, we conclude that a cooperation model is critical for safe and efficient robot navigation in dense human crowds.

Finally, we produce a large database of ground truth pedestrian crowd data. We make this ground truth database publicly available for further scientific study of crowd prediction models, learning from demonstration algorithms, and human robot interaction models in general.

Vibration from railways: Can we achieve better than +/-10dB prediction accuracy?

This paper examines the sources of uncertainly in models used to predict vibration from underground railways. It will become clear from this presentation that by varying parameters by a small amount, consistent with uncertainties in measured data, the predicted vibration levels vary significantly, often by more than 10dB. This error cannot be forecast. Small changes made to soil parameters (Compressive and Shear Wave velocities and density), to slab bending stiffness and mass and to the measurement position give rise to changes in vibration levels of more than lOdB. So if 10dB prediction error results from small uncertainties in soil parameters and measurement position it cannot be sensible to rely on prediction models for accuracy better than 10dB. The presentation will demonstrate in real time the use of the new - and freely-available - PiP software for calculating vibration from railway tunnels in real time.

Discussion on the basic mathematical models of neurons - Double synaptic weight neuron in general-purpose neurocomputer, theory and application

Based on the introduction of the traditional mathematical models of neurons in general-purpose neurocomputer, a novel all-purpose mathematical model-Double synaptic weight neuron (DSWN) is presented, which can simulate all kinds of neuron architectures, including Radial-Basis-Function (RBF) and Back-propagation (BP) models, etc. At the same time, this new model is realized using hardware and implemented in the new CASSANN-II neurocomputer that can be used to form various types of neural networks with multiple mathematical models of neurons. In this paper, the flexibility of the new model has also been described in constructing neural networks and based on the theory of Biomimetic pattern recognition (BPR) and high-dimensional space covering, a recognition system of omni directionally oriented rigid objects on the horizontal surface and a face recognition system had been implemented on CASSANN-H neurocomputer. The result showed DSWN neural network has great potential in pattern recognition.

Performance models of storage contention in cloud environments

We propose simple models to predict the performance degradation of disk requests due to storage device contention in consolidated virtualized environments. Model parameters can be deduced from measurements obtained inside Virtual Machines (VMs) from a system where a single VM accesses a remote storage server. The parameterized model can then be used to predict the effect of storage contention when multiple VMs are consolidated on the same server. We first propose a trace-driven approach that evaluates a queueing network with fair share scheduling using simulation. The model parameters consider Virtual Machine Monitor level disk access optimizations and rely on a calibration technique. We further present a measurement-based approach that allows a distinct characterization of read/write performance attributes. In particular, we define simple linear prediction models for I/O request mean response times, throughputs and read/write mixes, as well as a simulation model for predicting response time distributions. We found our models to be effective in predicting such quantities across a range of synthetic and emulated application workloads. 

Hybrid image/ray-shooting UHF radio propagation predictor for populated indoor environments

A novel model for indoor wireless communication, based on a dual image and ray-shooting approach, is presented. The model, capable of improved site-specific indoor propagation prediction, considers multiple human bodies moving within the environment. In a modern office at 2.45GHz, the combined effect of pedestrian traffic and a moving receiver causes rapid temporal fading of up to 30dB.

Inferring and Exploiting Categories for Next Location Prediction

Predicting the next location of a user based on their previous visiting pattern is one of the primary tasks over data from location based social networks (LBSNs) such as Foursquare. Many different aspects of these so-called “check-in” profiles of a user have been made use of in this task, including spatial and temporal information of check-ins as well as the social network information of the user. Building more sophisticated prediction models by enriching these check-in data by combining them with information from other sources is challenging due to the limited data that these LBSNs expose due to privacy concerns. In this paper, we propose a framework to use the location data from LBSNs, combine it with the data from maps for associating a set of venue categories with these locations. For example, if the user is found to be checking in at a mall that has cafes, cinemas and restaurants according to the map, all these information is associated. This category information is then leveraged to predict the next checkin location by the user. Our experiments with publicly available check-in dataset show that this approach improves on the state-of-the-art methods for location prediction.