Development and evaluation of neural network freeway incident detection models using field data

This paper discusses a multi-layer feedforward (MLF) neural network incident detection model that was developed and evaluated using field data. In contrast to published neural network incident detection models which relied on simulated or limited field data for model development and testing, the model described in this paper was trained and tested on a real-world data set of 100 incidents. The model uses speed, flow and occupancy data measured at dual stations, averaged across all lanes and only from time interval t. The off-line performance of the model is reported under both incident and non-incident conditions. The incident detection performance of the model is reported based on a validation-test data set of 40 incidents that were independent of the 60 incidents used for training. The false alarm rates of the model are evaluated based on non-incident data that were collected from a freeway section which was video-taped for a period of 33 days. A comparative evaluation between the neural network model and the incident detection model in operation on Melbourne's freeways is also presented. The results of the comparative performance evaluation clearly demonstrate the substantial improvement in incident detection performance obtained by the neural network model. The paper also presents additional results that demonstrate how improvements in model performance can be achieved using variable decision thresholds. Finally, the model's fault-tolerance under conditions of corrupt or missing data is investigated and the impact of loop detector failure/malfunction on the performance of the trained model is evaluated and discussed. The results presented in this paper provide a comprehensive evaluation of the developed model and confirm that neural network models can provide fast and reliable incident detection on freeways. (C) 1997 Elsevier Science Ltd. All rights reserved.

Capillary network models for transport in packed beds: Considerations of pore aspect ratio

The conventional analysis for the estimation of the tortuosity factor for transport in porous media is modified here to account for the effect of pore aspect ratio. Structural models of the porous medium are also constructed for calculating the aspect ratio as a function of porosity. Comparison of the model predictions with the extensive data of Currie (1960) for the effective diffusivity of hydrogen in packed beds shows good agreement with a network model of randomly oriented intersecting pores for porosities upto about 50 percent, which is the region of practical interest. The predictions based on this network model are also found to be in better agreement with the data of Currie than earlier expressions developed for unconsolidated and grainy media.

Prediction of MHC class II-binding peptides using an evolutionary algorithm and artificial neural network

Motivation: Prediction methods for identifying binding peptides could minimize the number of peptides required to be synthesized and assayed, and thereby facilitate the identification of potential T-cell epitopes. We developed a bioinformatic method for the prediction of peptide binding to MHC class II molecules. Results: Experimental binding data and expert knowledge of anchor positions and binding motifs were combined with an evolutionary algorithm (EA) and an artificial neural network (ANN): binding data extraction --> peptide alignment --> ANN training and classification. This method, termed PERUN, was implemented for the prediction of peptides that bind to HLA-DR4(B1*0401). The respective positive predictive values of PERUN predictions of high-, moderate-, low- and zero-affinity binder-a were assessed as 0.8, 0.7, 0.5 and 0.8 by cross-validation, and 1.0, 0.8, 0.3 and 0.7 by experimental binding. This illustrates the synergy between experimentation and computer modeling, and its application to the identification of potential immunotheraaeutic peptides.

Modeling the fluid-flow-induced stress and collapse in a dendritic network

An analytical approach to the stress development in the coherent dendritic network during solidification is proposed. Under the assumption that stresses are developed in the network as a result of the friction resisting shrinkage-induced interdendritic fluid flow, the model predicts the stresses in the solid. The calculations reflect the expected effects of postponed dendrite coherency, slower solidification conditions, and variations of eutectic volume fraction and shrinkage. Comparing the calculated stresses to the measured shear strength of equiaxed mushy zones shows that it is possible for the stresses to exceed the strength, thereby resulting in reorientation or collapse of the dendritic network.

Regional and total body bone mineral density in elite collegiate male swimmers

Back,ground To examine the role of long-term swimming exercise on regional and total body bone mineral density (BMD) in men. Methods. Experimental design: Cross-sectional. Setting: Musculoskeletal research laboratory at a medical center, Participants:We compared elite collegiate swimmers (n=11) to age-, weight-, and height-matched non-athletic controls (n=11), Measures: BMD (g/cm(2)) of the lumbar spine L2-4, proximal femur (femoral neck, trochanter, Ward's triangle), total body and various subregions of the total body, as well as regional and total body fat and bone mineral-free lean mass (LM) was assessed by dual-energy X-ray absorptiometry (DXA, Hologic QDR 1000/W). Results. Swimmers, who commenced training at 10.7+/-3.7 yrs (mean+/-SD) and trained for 24.7+/-4.2 hrs per week, had a greater amount of LM (p<0.05), lower fat mass (p<0.001) and percent body fat (9.5 vs 16.2 %, p<0.001) than controls. There was no significant difference between groups for regional or total body BRID, In stepwise multiple regression analysis, body weight was a consistent independent predictor of regional and total body BMD, Conclusions. These results suggest that long-term swimming is not an osteogenic mode of training in college-aged males. This supports our previous findings in young female swimmers who displayed no bone mass benefits despite long-standing athletic training.

Life tables of the processionary caterpillar Ochrogaster lunifer Herrich-Schaffer (Lepidoptera : Thaumetopoeidae) at local and regional scales

A major ongoing debate in population ecology has surrounded the causative factors underlying the abundance of phytophagous insects and whether or not these factors limit or regulate herbivore populations. However, it is often difficult to identify mortality agents in census data, and their distribution and relative importance across large spatial scales are rarely understood. Were, we present life tables for egg batches and larval cohorts of the processionary caterpillar Ochrogaster lunifer Herrich-Schaffer, using intensive local sampling combined with extensive regional monitoring to ascertain the relative importance of different mortality factors at different localities. Extinction of entire cohorts (representing the entire reproductive output of one female) at natural localities was high, with 82% of the initial 492 cohorts going extinct. Mortality was highest in the egg and early instar stages due to predation from dermestid beetles, and while different mortality factors (e.g. hatching failure, egg parasitism and failure to establish on the host) were present at many localities, dermestid predation, either directly observed or inferred from indirect evidence, was the dominant mortality factor at 89% of localities surveyed. Predation was significantly higher in plantations than in natural habitats. The second most important mortality factor was resource depletion, with 14 cohorts defoliating their hosts. Egg and larval parasitism were not major mortality agents. A combination of predation and resource depletion consistently accounted for the majority of mortality across localities, suggesting that both factors are important in limiting population abundance. This evidence shows that O. lunifer is not regulated by natural enemies alone, but that resource patches (Acacia trees) ultimately, and frequently, act together to limit population growth.

Regional-scale investigation of the spatial distribution and origin of soluble salts in central north Queensland

A method for regional assessment of the distribution of saline outbreaks is demonstrated for a large area (68 000 km(2)) in north Queensland, Australia. Soil samples were used in conjunction with a digital elevation model and a map of potentially saline discharge zones to examine the landscape distribution of soluble salts in the region. The hypothesis of atmospheric accession of salt was tested for the topographically defined catchment regions feeding into each potentially saline discharge area. Most catchments showed a salt distribution consistent with this hypothesis, i.e. %TSS was large near the discharge areas and decreased rapidly with distance uphill from the discharge areas. In some catchments, however, local saline outbreaks were apparent at significant distances uphill from discharge areas. The possibility of geological sources of this salt was examined by comparing random point distributions with the location of saline points with distance downhill from geological units (excluding points near discharge zones). The distribution of some saline outbreaks was consistent with the occurrence of Cambro-Ordovician metasediments, Devonian limestone, Upper Devonian-Lower Carboniferous volcanics, and Triassic sediments. Copyright (C) 2000 John Wiley & Sons, Ltd.

Identifying regional dust transport pathways: Application of kinematic trajectory modelling to a trans-Tasman case

PI kinematic trajectory model is used to investigate potential pathways of dust transport from Australia to New Zealand. Historically, these have been assumed to follow rather direct west-east trajectories spanning 2 to 3 days, often resulting in red snow events in the Southern Alps of New Zealand. However, results from the present study which examined the route taken by air parcels originating in southern Australia during dust storms on 24 and 25 May 1994, indicate that trans-Tasman dust transport trajectories are more diverse than previously thought, and display considerable variation during single events. These mon divergent pathways tie in more closely with aeolian dust sedimentation patterns identified by ocean coring in the Tasman Sea, and may account for the deposition of Australian dust on sub-Antarctic islands located well south of the Australian continent. Copyright 2000 John Wiley Sons, Ltd.

Glucocorticoid receptors in human preadipocytes: regional and gender differences

Glucocorticoid excess causes visceral obesity and its accompanying insulin resistance, dyslipidemia and hypertension. Glucocorticoids enhance preadipocyte (PA) differentiation and increase their aromatase activity (oestrogen production) and there is regional variability in these PA processes. Therefore, we studied human PAs for the presence of, and any regional or gender differences in, glucocorticoid receptors (GRs). Confluent subcultured human subcutaneous (Sc) and visceral (Vis) PAs from both genders contained GRs as assessed by GR gene expression and specific glucocorticoid (dexamethasone) binding. The dissociation constant was similar to that of other human cells and there was no difference between Sc and Vis sites or between males and females. There was significantly less GR mRNA in Vis PAs compared with Sc PAs in females (P=0.008) but not in males. There was less glucocorticoid binding in Vis compared with Sc PAs in females, measured by maximal binding capacity (P=0.035) or single saturating dose glucocorticoid binding (Bssd) (P=0.019). There was no regional difference in specific glucocorticoid binding in males. There was a gender difference with fewer GRs in Vis PAs in females compared with males measured by Bssd (P=0.006). In summary, GRs are present in human PAs. There is a lower GR density in Vis compared with Sc PAs in females, and females have fewer GRs in Vis PAs compared with males. These differences are likely to affect regional aromatase activity and to contribute to the smaller visceral fat mass in females compared with males.

An object-oriented neural network approach to short-term traffic forecasting

This paper discusses an object-oriented neural network model that was developed for predicting short-term traffic conditions on a section of the Pacific Highway between Brisbane and the Gold Coast in Queensland, Australia. The feasibility of this approach is demonstrated through a time-lag recurrent network (TLRN) which was developed for predicting speed data up to 15 minutes into the future. The results obtained indicate that the TLRN is capable of predicting speed up to 5 minutes into the future with a high degree of accuracy (90-94%). Similar models, which were developed for predicting freeway travel times on the same facility, were successful in predicting travel times up to 15 minutes into the future with a similar degree of accuracy (93-95%). These results represent substantial improvements on conventional model performance and clearly demonstrate the feasibility of using the object-oriented approach for short-term traffic prediction. (C) 2001 Elsevier Science B.V. All rights reserved.

Identifying rate-limiting nodes in large-scale cortical networks for visuospatial processing: an illustration using fMRI

With the advent of functional neuroimaging techniques, in particular functional magnetic resonance imaging (fMRI), we have gained greater insight into the neural correlates of visuospatial function. However, it may not always be easy to identify the cerebral regions most specifically associated with performance on a given task. One approach is to examine the quantitative relationships between regional activation and behavioral performance measures. In the present study, we investigated the functional neuroanatomy of two different visuospatial processing tasks, judgement of line orientation and mental rotation. Twenty-four normal participants were scanned with fMRI using blocked periodic designs for experimental task presentation. Accuracy and reaction time (RT) to each trial of both activation and baseline conditions in each experiment was recorded. Both experiments activated dorsal and ventral visual cortical areas as well as dorsolateral prefrontal cortex. More regionally specific associations with task performance were identified by estimating the association between (sinusoidal) power of functional response and mean RT to the activation condition; a permutation test based on spatial statistics was used for inference. There was significant behavioral-physiological association in right ventral extrastriate cortex for the line orientation task and in bilateral (predominantly right) superior parietal lobule for the mental rotation task. Comparable associations were not found between power of response and RT to the baseline conditions of the tasks. These data suggest that one region in a neurocognitive network may be most strongly associated with behavioral performance and this may be regarded as the computationally least efficient or rate-limiting node of the network.

Inter-subband redundancy prediction using neural network for video coding

High performance video codec is mandatory for multimedia applications such as video-on-demand and video conferencing. Recent research has proposed numerous video coding techniques to meet the requirement in bandwidth, delay, loss and Quality-of-Service (QoS). In this paper, we present our investigations on inter-subband self-similarity within the wavelet-decomposed video frames using neural networks, and study the performance of applying the spatial network model to all video frames over time. The goal of our proposed method is to restore the highest perceptual quality for video transmitted over a highly congested network. Our contributions in this paper are: (1) A new coding model with neural network based, inter-subband redundancy (ISR) prediction for video coding using wavelet (2) The performance of 1D and 2D ISR prediction, including multiple levels of wavelet decompositions. Our result shows a short-term quality enhancement may be obtained using both 1D and 2D ISR prediction.

Incorporating demand-side aspects into regional policy: variations in the importance of private investment decision factors across regions

Most regional programs focus on the supply side of regions, emphasizing the attraction conditions offered, such as infrastructure, labor skills, tax incentives, etc. This study analyzes one aspect of the demand side, that is, how investment decisions of private firms are made by asking the question: ""Do corporations decide the same way on investments in different parts of the territory?"" The paper analyzes the investments of 373 large Brazilian firms during 1996-2004. Based on the investment decisions of these firms, the role of sales, cash-flow, external financing, and working capital is investigated through regression analysis. The regional influence is captured by explanatory variables representing regional and firm characteristics, and by interaction dummies between the region and the main investment determinants. The results indicate significant differences across regions in the importance of investment determinants. This information is important for regional development policy, because different mechanisms should be used in different regions to foster private investments.

Transport-Regional Equity Issue Revisited

Almeida E. S. de, Haddad E. A. and Hewings G. J. D. Transport-regional equity issue revisited, Regional Studies. The objective of this paper is to analyse the relationship between transport and regional equity in Minas Gerais, Brazil. Furthermore, the existence of a trade-off between economic performance and regional equity is investigated as well. To do so, the paper develops a spatial computable general equilibrium model based on Brocker and Schneider`s approach of 2002 to implement comparative static analysis, explicitly incorporating iceberg transportation costs. Four activities are modelled, namely production, final demand, transportation and exports. Two production factors are assumed: labour and other factors. The model has 12 domestic regions and three external regions. Four counterfactual experiments are developed based on decreases in transportation costs due to a `distance shortening`. The main findings indicate that if the transport infrastructure improvement is focused only among poor regions, the promotion of regional equity is insignificant. If the transport infrastructure improvement links are concentrated among rich regions, there is an increase in regional income inequalities. However, if the improvements are targeted to the roads linking poor regions and rich ones, there is greater promotion of regional equity. The same result will occur when improvements are made to all road links of the state. [image omitted] Almeida E. S. de, Haddad E. A. et Hewings G. J. D. La question du rapport entre le transport et l`equilibre regional vue sous un jour nouveau, Regional Studies. Cet article cherche a analyser le rapport entre le transport et l`equilibre regional en Minas Gerais au Bresil. En outre, on examine la presence d`un echange entre la performance economoique et l`equilibre regional. Pour le faire, on construit un modele geographique de l`equilibre general a utiliser sur ordinateur fonde sur l`approche de Brockner et Schneider en 2002 afin de mettre en oeuvre une analyse statique comparative qui comprend explicitement les frais de transport iceberg. On modelise quatre activites, a savoir, la production, la demande finale, le transport et l`exportation. On fait deux suppositions quant aux facteurs de production: la main-d`oevre et d`autres facteurs. Le modele embrasse douze regions internes et trois regions externes. On fait quatre experiences paradoxales fondees sur la baisse des frais de transport due a une `reduction des distances`. Les principaux resultats indiquent que si l`amelioration de l`equipement de transport ne porte que sur les regions defavorisees, la promotion de l`equilibre regional s`avere negligeable. Si l`amelioration de l`equipement de transport focalise les regions riches, il s`avere un creusement des ecarts des revenus regionaux. Cependant, si les ameliorations ciblent les routes qui relient les regions defavorisees aux regions riches, il s`avere une plus grande promotion de l`equilibre regional. Il en va de meme pour la situation ou on a apporte des amenagements a toutes les liaisons routieres de l`etat. Modele geographique de l`equilibre general a utiliser sur ordinateur Equilibre regional Peformance economique Frais de transport Almeida E. S. de, Haddad E. A. und Hewings G. J. D. Die Wiederaufnahme der Frage von Verkehrswesen im Verhaltnis zu regionaler Fairness, Regional Studies. Dieser Aufsatz beabsichtigt, die Beziehung zwischen Verkehrswesen und regionaler Fairness in Minas Gerais (Brasilien) zu analysieren und zugleich auch das Vorkommen von Einbussen entweder bei wirtschaftlicher Leistung der regionaler Fairness zu untersuchen. Zu diesem Zwecke wird ein auf dem Ansatz von Brocker und Schneider (2002) aufbauendes raumliches komputables allgemeines Gleichgewichtsmodell entwickelt, um vergleichende statistische Analysen durchzufuhren, wobei verborgene `Eisberg`-Transportkosten ausdrucklich berucksichtigt werden. Es werden vier Unternehmenstatigk eiten aufgefuhrt: Herstellung, Nachfrage, Transportwesen und Exporte, und zwei Produktionsfaktoren vorausgesetzt: Arbeitskrafte und andere Faktoren. Das Modell umfasst zwolf Inlandsregionen und drei externe Regionen. Es werden vier gegensatzliche Experimente entwickelt, die auf einer Abnahme der Transportkosten infolge einer `Verkurzung der Entfernungen` beruhen. Die Hauptbefunde weisen darauf hin, dass die Forderung regionaler Fairness unbedeutend bleibt, wenn die Verbesserungen der Transportinfrastruktur sich nur auf minderbemittelte Regionen konzentrieren; werden die Verbesserungen der Verbindungen der Transportinfrastruktur in wohlhabenden Regionen durchgefuhrt, so nehmen regionale Einkommensunterschiede zu. Wenn die Verbesserungen jedoch auf Strassen abzielen, die wohlhabende Regionen mit weniger bemittelten verbinden, wird regionale Fairness starker gefordert. Das gleiche Ergebnis wird sich einstellen, wenn Verbesserungen an allen Strassenverbindungen des Staates vorgenommen werden. Raumliches, komputables, allgemeines Gleichgewichtsmodell Regionale Fairness Wirtschaftsleistung Transportkosten Almeida E. S. de, Haddad E. A. y Hewings G. J. D. Revisando el tema de la igualdad del transporte en las regiones, Regional Studies. El objetivo de este documento es analizar la relacion entre el transporte y la igualdad regional en Minas Gerais, Brasil. Asimismo investigamos la existencia de una compensacion entre el rendimiento economico y la igualdad regional. Para ello desarrollamos un modelo de equilibrio general computable y espacial basado en el enfoque de Brocker y Schneider en 2002 para hacer un analisis estatico y comparativo, explicitamente incorporando los costes ocultos de transporte. Se modelan cuatro actividades: la produccion, la demanda final, el transporte y las exportaciones. Suponemos que existen dos factores de produccion: mano de obra y otros factores. En este modelo, existen doce regiones internas y tres regiones externas. Desarrollamos cuatro experimentos contrafactuales basados en la disminucion de los costes de transporte debido a una `acortamiento de las distancias`. Los principales resultados indican que si la mejora de la infraestructura del transporte se centra solo entre las regiones mas pobres, el fomento de la igualdad regional es insignificante. Si los enlaces de la mejora de la infraestructura del transporte se concentran en las regiones ricas, aumentan las desigualdades de ingresos regionales. Sin embargo, si se mejoran los enlaces de carreteras entre las regiones pobres y ricas, se fomenta mejor la igualdad regional. El mismo resultado ocurre cuando se mejoran los enlaces de todas las carreteras del estado. Modelo de equilibrio general computable y espacial Igualdad regional Rendimiento economico Costes de transporte.

Petroleum royalties and regional development in Brazil: The economic growth of recipient towns

In 1997, Brazil approved law n(cr) 9478, establishing new rules for sharing petroleum royalties with Brazilian municipalities. The goal of this paper is to evaluate whether royalties distributed under the new law have contributed for the development of benefited municipalities. For that the difference-indifferences estimator (diff-in-diff) is used, which compares the evolution of the economic product into the municipality affected by the new law with the unaffected ones, by exploring the new legislation as an exogenous change. The data refer to the municipal gross domestic product (GDP) growth rate before and after the event. Results are surprising, showing that royalty receivers grew less than municipalities that did not receive such resources. The difference is small but statistically significant. In general, an increase of one real in royalties per capita reduces the growth rate of the municipal product in 0.002 percentile points. (C) 2009 Elsevier Ltd. All rights reserved.