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.

Book review of: 'Textual traffic: Colonialism, modernity and the economy of text' by S. Shankar

No abstract

Traffic and residue cover effects on infiltration

Wheel traffic can lead to compaction and degradation of soil physical properties. This study, as part of a study of controlled traffic farming, assessed the impact of compaction from wheel traffic on soil that had not been trafficked for 5 years. A tractor of 40 kN rear axle weight was used to apply traffic at varying wheelslip on a clay soil with varying residue cover to simulate effects of traffic typical of grain production operations in the northern Australian grain belt. A rainfall simulator was used to determine infiltration characteristics. Wheel traffic significantly reduced time to ponding, steady infiltration rate, and total infiltration compared with non-wheeled soil, with or without residue cover. Non-wheeled soil had 4-5 times greater steady infiltration rate than wheeled soil, irrespective of residue cover. Wheelslip greater than 10% further reduced steady infiltration rate and total infiltration compared with that measured for self-propulsion wheeling (3% wheelslip) under residue-protected conditions. Where there was no compaction from wheel traffic, residue cover had a greater effect on infiltration capacity, with steady infiltration rate increasing proportionally with residue cover (R-2 = 0.98). Residue cover, however, had much less effect on infiltration when wheeling was imposed. These results demonstrated that the infiltration rate for the non-wheeled soil under a controlled traffic zero-till system was similar to that of virgin soil. However, when the soil was wheeled by a medium tractor wheel, infiltration rate was reduced to that of long-term cropped soil. These results suggest that wheel traffic, rather than tillage and cropping, might be the major factor governing infiltration. The exclusion of wheel traffic under a controlled traffic farming system, combined with conservation tillage, provides a way to enhance the sustainability of cropping this soil for improved infiltration, increased plant-available water, and reduced runoff-driven soil erosion.

Tillage and traffic effects on runoff

Traffic and tillage effects on runoff and crop performance on a heavy clay soil were investigated over a period of 4 years. Tillage treatments and the cropping program were representative of broadacre grain production practice in northern Australia, and a split-plot design used to isolate traffic effects. Treatments subject to zero, minimum, and stubble mulch tillage each comprised pairs of 90-m 2 plots, from which runoff was recorded. A 3-m-wide controlled traffic system allowed one of each pair to be maintained as a non-wheeled plot, while the total surface area of the other received a single annual wheeling treatment from a working 100-kW tractor. Rainfall/runoff hydrographs demonstrate that wheeling produced a large and consistent increase in runoff, whereas tillage produced a smaller increase. Treatment effects were greater on dry soil, but were still maintained in large and intense rainfall events on wet soil. Mean annual runoff from wheeled plots was 63 mm (44%) greater than that from controlled traffic plots, whereas runoff from stubble mulch tillage plots was 38 mm (24%) greater than that from zero tillage plots. Traffic and tillage effects appeared to be cumulative, so the mean annual runoff from wheeled stubble mulch tilled plots, representing conventional cropping practice, was more than 100 mm greater than that from controlled traffic zero tilled plots, representing best practice. This increased infiltration was reflected in an increased yield of 16% compared with wheeled stubble mulch. Minimum tilled plots demonstrated a characteristic midway between that of zero and stubble mulch tillage. The results confirm that unnecessary energy dissipation in the soil during the traction process that normally accompanies tillage has a major negative effect on infiltration and crop productivity. Controlled traffic farming systems appear to be the only practicable solution to this problem.

The t-SNARE syntaxin 4 is regulated during macrophage activation to function in membrane traffic and cytokine secretion

Activation of macrophages with lipopolysaccharide (LPS) induces the rapid synthesis and secretion of proinflammatory cytokines, such as tumor necrosis factor (TNFalpha), for priming the immune response [1, 2]. TNFalpha plays a key role in inflammatory disease [3]; yet, little is known of the intracellular trafficking events leading to its secretion. In order to identify molecules involved in this secretory pathway, we asked whether any of the known trafficking proteins are regulated by LPS. We found that the levels of SNARE proteins were rapidly and significantly up- or downregulated during macrophage activation. A subset of t-SNAREs (Syntaxin 4/SNAP23/Munc18c) known to control regulated exocytosis in other cell types [4, 5] was substantially increased by LPS in a temporal pattern coinciding with peak TNFalpha secretion. Syntaxin 4 formed a complex with Munc18c at the cell surface of macrophages. Functional studies involving the introduction of Syntaxin 4 cDNA or peptides into macrophages implicate this t-SNARE in a rate-limiting step of TNFalpha secretion and in membrane ruffling during macrophage activation. We conclude that in macrophages, SNAREs are regulated in order to accommodate the rapid onset of cytokine secretion and for membrane traffic associated with the phenotypic changes of immune activation. This represents a novel regulatory role for SNAREs in regulated secretion and in macrophage-mediated host defense.