Implementing statistical learning methods through Bayesian networks. Part 1: a guide to Bayesian parameter estimation using forensic science data

As a thorough aggregation of probability and graph theory, Bayesian networks currently enjoy widespread interest as a means for studying factors that affect the coherent evaluation of scientific evidence in forensic science. Paper I of this series of papers intends to contribute to the discussion of Bayesian networks as a framework that is helpful for both illustrating and implementing statistical procedures that are commonly employed for the study of uncertainties (e.g. the estimation of unknown quantities). While the respective statistical procedures are widely described in literature, the primary aim of this paper is to offer an essentially non-technical introduction on how interested readers may use these analytical approaches - with the help of Bayesian networks - for processing their own forensic science data. Attention is mainly drawn to the structure and underlying rationale of a series of basic and context-independent network fragments that users may incorporate as building blocs while constructing larger inference models. As an example of how this may be done, the proposed concepts will be used in a second paper (Part II) for specifying graphical probability networks whose purpose is to assist forensic scientists in the evaluation of scientific evidence encountered in the context of forensic document examination (i.e. results of the analysis of black toners present on printed or copied documents).

Estimation of the noisy component of anatomical backgrounds.

The knowledge of the relationship that links radiation dose and image quality is a prerequisite to any optimization of medical diagnostic radiology. Image quality depends, on the one hand, on the physical parameters such as contrast, resolution, and noise, and on the other hand, on characteristics of the observer that assesses the image. While the role of contrast and resolution is precisely defined and recognized, the influence of image noise is not yet fully understood. Its measurement is often based on imaging uniform test objects, even though real images contain anatomical backgrounds whose statistical nature is much different from test objects used to assess system noise. The goal of this study was to demonstrate the importance of variations in background anatomy by quantifying its effect on a series of detection tasks. Several types of mammographic backgrounds and signals were examined by psychophysical experiments in a two-alternative forced-choice detection task. According to hypotheses concerning the strategy used by the human observers, their signal to noise ratio was determined. This variable was also computed for a mathematical model based on the statistical decision theory. By comparing theoretical model and experimental results, the way that anatomical structure is perceived has been analyzed. Experiments showed that the observer's behavior was highly dependent upon both system noise and the anatomical background. The anatomy partly acts as a signal recognizable as such and partly as a pure noise that disturbs the detection process. This dual nature of the anatomy is quantified. It is shown that its effect varies according to its amplitude and the profile of the object being detected. The importance of the noisy part of the anatomy is, in some situations, much greater than the system noise. Hence, reducing the system noise by increasing the dose will not improve task performance. This observation indicates that the tradeoff between dose and image quality might be optimized by accepting a higher system noise. This could lead to a better resolution, more contrast, or less dose.

Lag-one autocorrelation in short series: Estimation and hypothesis testing

In the first part of the study, nine estimators of the first-order autoregressive parameter are reviewed and a new estimator is proposed. The relationships and discrepancies between the estimators are discussed in order to achieve a clear differentiation. In the second part of the study, the precision in the estimation of autocorrelation is studied. The performance of the ten lag-one autocorrelation estimators is compared in terms of Mean Square Error (combining bias and variance) using data series generated by Monte Carlo simulation. The results show that there is not a single optimal estimator for all conditions, suggesting that the estimator ought to be chosen according to sample size and to the information available of the possible direction of the serial dependence. Additionally, the probability of labelling an actually existing autocorrelation as statistically significant is explored using Monte Carlo sampling. The power estimates obtained are quite similar among the tests associated with the different estimators. These estimates evidence the small probability of detecting autocorrelation in series with less than 20 measurement times.

Comparison of methods for estimation of needle losses in Scots pine following defoliation by Bupalus piniaria

Abstract

Visibility and Speed Estimation of Iowa State Highway Commission Snowplows, HR-174, 1975

Many accidents involving Iowa snowplows have happened in recent years. This study investigated the influence of time of day, sex of subject, type of snowplow sign and snowplow speed on the criteria of oncoming driver reaction time and his estimate of snowplow speed. Film strips were made of a car passing a snow-Plow under various experimental conditions. These experimental movie strips were viewed in the laboratory by college student drivers who were asked to indicate their reaction time to slow down and to estimate the speed of the snowplow being passed. The generally best sign condition for the snowplow was to have a striped rear sign and a speed-proportional flashing light in addition to the standard rotating beacon on top of the truck. Several recommendations were made.

New reference tables and user-friendly Internet application for predicted heart weights.

BACKGROUND: Knowledge of normal heart weight ranges is important information for pathologists. Comparing the measured heart weight to reference values is one of the key elements used to determine if the heart is pathological, as heart weight increases in many cardiac pathologies. The current reference tables are old and in need of an update. AIMS: The purposes of this study are to establish new reference tables for normal heart weights in the local population and to determine the best predictive factor for normal heart weight. We also aim to provide technical support to calculate the predictive normal heart weight. METHODS: The reference values are based on retrospective analysis of adult Caucasian autopsy cases without any obvious pathology that were collected at the University Centre of Legal Medicine in Lausanne from 2007 to 2011. We selected 288 cases. The mean age was 39.2 years. There were 118 men and 170 women. Regression analyses were performed to assess the relationship of heart weight to body weight, body height, body mass index (BMI) and body surface area (BSA). RESULTS: The heart weight increased along with an increase in all the parameters studied. The mean heart weight was greater in men than in women at a similar body weight. BSA was determined to be the best predictor for normal heart weight. New reference tables for predicted heart weights are presented as a web application that enable the comparison of heart weights observed at autopsy with the reference values. CONCLUSIONS: The reference tables for heart weight and other organs should be systematically updated and adapted for the local population. Web access and smartphone applications for the predicted heart weight represent important investigational tools.

Estimation du degré de couverture d'un registre pour les cancers notifiés au décès [Evaluation of the comprehensiveness of a cancer register from death certificates].

The comparison of cancer prevalence with cancer mortality can lead under some hypotheses to an estimate of registration rate. A method is proposed, where the cases with cancer as a cause of death are divided into 3 categories: (1) cases already known by the registry (2) unknown cases having occured before the registry creation date (3) unknown cases occuring during the registry operates. The estimate is then the number of cases in the first category divided by the total of those in categories 1 and 3 (these only are to be registered). An application is performed on the data of the Canton de Vaud. Survival rates of the Norvegian Cancer Registry are used for computing the number of unknown cases to be included in second and third category, respectively. The discussion focusses on the possible determinants of the obtained comprehensiveness rates for various cancer sites.

The estimation of PMP and PMF on alpine basins in Switzerland

This paper presents a very fine grid hydrological model based on the spatiotemporal repartition of precipitation and on the topography. The goal is to estimate the flood on a catchment area, using a Probable Maximum Precipitation (PMP) leading to a Probable Maximum Flood (PMF). The spatiotemporal distribution of the precipitation was realized using six clouds modeled by the advection-diffusion equation. The equation shows the movement of the clouds over the terrain and also gives the evolution of the rain intensity in time. This hydrological modeling is followed by a hydraulic modeling of the surface and subterranean flows, done considering the factors that contribute to the hydrological cycle, such as the infiltration, the exfiltration and the snowmelt. This model was applied to several Swiss basins using measured rain, with results showing a good correlation between the simulated and observed flows. This good correlation proves that the model is valid and gives us the confidence that the results can be extrapolated to phenomena of extreme rainfall of PMP type. In this article we present some results obtained using a PMP rainfall and the developed model.

Limitations and information needs for engineered nanomaterial-specific exposure estimation and scenarios: recommendations for improved reporting practices

The aim of this paper is to describe the process and challenges in building exposure scenarios for engineered nanomaterials (ENM), using an exposure scenario format similar to that used for the European Chemicals regulation (REACH). Over 60 exposure scenarios were developed based on information from publicly available sources (literature, books, and reports), publicly available exposure estimation models, occupational sampling campaign data from partnering institutions, and industrial partners regarding their own facilities. The primary focus was on carbon-based nanomaterials, nano-silver (nano-Ag) and nano-titanium dioxide (nano-TiO2), and included occupational and consumer uses of these materials with consideration of the associated environmental release. The process of building exposure scenarios illustrated the availability and limitations of existing information and exposure assessment tools for characterizing exposure to ENM, particularly as it relates to risk assessment. This article describes the gaps in the information reviewed, recommends future areas of ENM exposure research, and proposes types of information that should, at a minimum, be included when reporting the results of such research, so that the information is useful in a wider context.

Reciprocal Translocations in Cattle: frequency estimation

Chromosomal anomalies, like Robertsonian and reciprocal translocations represent a big problem in cattle breeding as their presence induces, in the carrier subjects, a well documented fertility reduction. In cattle reciprocal translocations (RCPs, a chromosome abnormality caused by an exchange of material between nonhomologous chromosomes) are considered rare as to date only 19 reciprocal translocations have been described. In cattle it is common knowledge that the Robertsonian translocations represent the most common cytogenetic anomalies, and this is probably due to the existence of the endemic 1;29 Robertsonian translocation. However, these considerations are based on data obtained using techniques that are unable to identify all reciprocal translocations and thus their frequency is clearly underestimated. The purpose of this work is to provide a first realistic estimate of the impact of RCPs in the cattle population studied, trying to eliminate the factors which have caused an underestimation of their frequency so far. We performed this work using a mathematical as well as a simulation approach and, as biological data, we considered the cytogenetic results obtained in the last 15 years. The results obtained show that only 16% of reciprocal translocations can be detected using simple Giemsa techniques and consequently they could be present in no less than 0,14% of cattle subjects, a frequency five times higher than that shown by de novo Robertsonian translocations. This data is useful to open a debate about the need to introduce a more efficient method to identify RCP in cattle.

Maximum likelihood Linear Programming Data Fusion for Speaker Recognition

Biometric system performance can be improved by means of data fusion. Several kinds of information can be fused in order to obtain a more accurate classification (identification or verification) of an input sample. In this paper we present a method for computing the weights in a weighted sum fusion for score combinations, by means of a likelihood model. The maximum likelihood estimation is set as a linear programming problem. The scores are derived from a GMM classifier working on a different feature extractor. Our experimental results assesed the robustness of the system in front a changes on time (different sessions) and robustness in front a change of microphone. The improvements obtained were significantly better (error bars of two standard deviations) than a uniform weighted sum or a uniform weighted product or the best single classifier. The proposed method scales computationaly with the number of scores to be fussioned as the simplex method for linear programming.

Estimation of a maximum Lu diffusion rate in a natural eclogite garnet

Lutetium zoning in garnet within eclogites from the Zermatt-Saas Fee zone, Western Alps, reveal sharp, exponentially decreasing central peaks. They can be used to constrain maximum Lu volume diffusion in garnets. A prograde garnet growth temperature interval of 450-600 A degrees C has been estimated based on pseudosection calculations and garnet-clinopyroxene thermometry. The maximum pre-exponential diffusion coefficient which fits the measured central peak is in the order of D-0= 5.7*10(-6) m(2)/s, taking an estimated activation energy of 270 kJ/mol based on diffusion experiments for other rare earth elements in garnet. This corresponds to a maximum diffusion rate of D (600 A degrees C) = 4.0*10(-22) m(2)/s. The diffusion estimate of Lu can be used to estimate the minimum closure temperature, T-c, for Sm-Nd and Lu-Hf age data that have been obtained in eclogites of the Western Alps, postulating, based on a literature review, that D (Hf) < D (Nd) < D (Sm) a parts per thousand currency sign D (Lu). T-c calculations, using the Dodson equation, yielded minimum closure temperatures of about 630 A degrees C, assuming a rapid initial exhumation rate of 50A degrees/m.y., and an average crystal size of garnets (r = 1 mm). This suggests that Sm/Nd and Lu/Hf isochron age differences in eclogites from the Western Alps, where peak temperatures did rarely exceed 600 A degrees C must be interpreted in terms of prograde metamorphism.

Muscle moment-arms: a key element in muscle-force estimation.

A clear and rigorous definition of muscle moment-arms in the context of musculoskeletal systems modelling is presented, using classical mechanics and screw theory. The definition provides an alternative to the tendon excursion method, which can lead to incorrect moment-arms if used inappropriately due to its dependency on the choice of joint coordinates. The definition of moment-arms, and the presented construction method, apply to musculoskeletal models in which the bones are modelled as rigid bodies, the joints are modelled as ideal mechanical joints and the muscles are modelled as massless, frictionless cables wrapping over the bony protrusions, approximated using geometric surfaces. In this context, the definition is independent of any coordinate choice. It is then used to solve a muscle-force estimation problem for a simple 2D conceptual model and compared with an incorrect application of the tendon excursion method. The relative errors between the two solutions vary between 0% and 100%.

Highway Work Zone Capacity Estimation Using Field Data from Kansas, TPF-5(081), 2015

Although extensive research has been conducted on urban freeway capacity estimation methods, minimal research has been carried out for rural highway sections, especially sections within work zones. This study attempted to fill that void for rural highways in Kansas, by estimating capacity of rural highway work zones in Kansas. Six work zone locations were selected for data collection and further analysis. An average of six days’ worth of field data was collected, from mid-October 2013 to late November 2013, at each of these work zone sites. Two capacity estimation methods were utilized, including the Maximum Observed 15-minute Flow Rate Method and the Platooning Method divided into 15-minute intervals. The Maximum Observed 15-minute Flow Rate Method provided an average capacity of 1469 passenger cars per hour per lane (pcphpl) with a standard deviation of 141 pcphpl, while the Platooning Method provided a maximum average capacity of 1195 pcphpl and a standard deviation of 28 pcphpl. Based on observed data and analysis carried out in this study, the suggested maximum capacity can be considered as 1500 pcphpl when designing work zones for rural highways in Kansas. This proposed standard value of rural highway work zone capacity could be utilized by engineers and planners so that they can effectively mitigate congestion at or near work zones that would have otherwise occurred due to construction/maintenance.