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.

The novel genome organization of the insect picorna-like virus Drosophila C virus suggests this virus belongs to a previously undescribed virus family

The complete nucleotide sequence of the genomic RNA from the insect picorna-like virus Drosophila C virus (DCV) was determined. The DCV sequence predicts a genome organization different to that of other RNA virus families whose sequences are known. The single-stranded positive-sense genomic RNA is 9264 nucleotides in length and contains two large open reading frames (ORFs) which are separated by 191 nucleotides. The 5' ORF contains regions of similarities with the RNA-dependent RNA polymerase, helicase and protease domains of viruses from the picornavirus, comovirus and sequivirus families. The 3' ORF encodes the capsid proteins as confirmed by N-terminal sequence analysis of these proteins. The capsid protein coding region is unusual in two ways: firstly the cistron appears to lack an initiating methionine and secondly no subgenomic RNA is produced, suggesting that the proteins may be translated through internal initiation of translation from the genomic length RNA. The finding of this novel genome organization for DCV shows that this virus is not a member of the Picornaviridae as previously thought, but belongs to a distinct and hitherto unrecognized virus family.

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.

Linking client and employee perceptions of the organization: A study of client satisfaction with health care services

Client satisfaction with health care sen ices has usually been researched in terms of socio-demographic and predispositional characteristics associated with the client. The present study included organizational characteristics as predictors of client satisfaction with health care services. Participants in the research were clients and employees of an Australian public-sector health care organization who responded to separate client and employee questionnaires. Hierarchical regression analyses indicated that, after controlling for a number of client characteristics, organizational characteristics, as perceived by employees, accounted for a significant proportion of additional variance in client satisfaction with health care services. Results of the present study provided some support for the proposition that employee perceptions of the working environment should be considered in a more comprehensive understanding of client satisfaction with health care services. Limitations of the study highlight practical difficulties in the assessment of client outcomes and methodological complexities in linking individual and organizational processes.

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.

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.

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.

The human organization of time: Temporal realities and experience (Book)

Reviews the book "The Human Organization of Time: Temporal Realities and Experience," by Allen C. Bluedorn.

Effects of restricted cochlear lesions in adult cats on the frequency organization of the inferior colliculus

Restricted cochlear lesions in adult animals result in plastic changes in the representation of the lesioned cochlea, and thus in the frequency map, in the contralateral auditory cortex and thalamus. To examine the contribution of subthalamic changes to this reorganization, the effects of unilateral mechanical cochlear lesions on the frequency organization of the central nucleus of the inferior colliculus (ICC) were examined in adult cats. Lesions typically resulted in a broad high-frequency hearing loss extending from a frequency in the range 15-22 kHz. After recovery periods of 2.5-18 months, the frequency organization of ICC contralateral to the lesioned cochlea was determined separately for the onset and late components of multiunit responses to tone-burst stimuli. For the late response component in all but one penetration through the ICC, and for the onset response component in more than half of the penetrations, changes in frequency organization in the lesion projection zone were explicable as the residue of prelesion responses. In half of the penetrations exhibiting nonresidue type changes in onset-response frequency organization, the changes appeared to reflect the unmasking of normally inhibited inputs. In the other half it was unclear whether the changes reflected unmasking or a dynamic process of reorganization. Thus, most of the observed changes were explicable as passive consequences of the lesion, and there was limited evidence for plasticity in the ICC. The implications of the data with respect to the primary locus of the changes and to the manner in which they contribute to thalamocortical reorganization are considered. (C) 2003 Wiley-Liss, Inc.

Sequence analysis, chromosomal distribution and long-range organization show that rapid turnover of new and old pBuM satellite DNA repeats leads to different patterns of variation in seven species of the Drosophila buzzatii cluster

We aimed to study patterns of variation and factors influencing the evolutionary dynamics of a satellite DNA, pBuM, in all seven Drosophila species from the buzzatii cluster (repleta group). We analyzed 117 alpha pBuM-1 (monomer length 190 bp) and 119 composite alpha/beta (370 bp) pBuM-2 repeats and determined the chromosome location and long-range organization on DNA fibers of major sequence variants. Such combined methodologies in the study of satDNAs have been used in very few organisms. In most species, concerted evolution is linked to high copy number of pBuM repeats. Species presenting low-abundance and scattered distributed pBuM repeats did not undergo concerted evolution and maintained part of the ancestral inter-repeat variability. The alpha and alpha/beta repeats colocalized in heterochromatic regions and were distributed on multiple chromosomes, with notable differences between species. High-resolution FISH revealed array sizes of a few kilobases to over 0.7 Mb and mutual arrangements of alpha and alpha/beta repeats along the same DNA fibers, but with considerable changes in the amount of each variant across species. From sequence, chromosomal and phylogenetic data, we could infer that homogenization and amplification events involved both new and ancestral pBuM variants. Altogether, the data on the structure and organization of the pBuM satDNA give insights into genome evolution including mechanisms that contribute to concerted evolution and diversification.

Organization, evolution and transcriptional profile of hexamerin genes of the parasitic wasp Nasonia vitripennis (Hymenoptera: Pteromalidae)

Hexamerins and prophenoloxidases (PPOs) proteins are members of the arthropod-haemocyanin superfamily. In contrast to haemocyanin and PPO, hexamerins do not bind oxygen, but mainly play a role as storage proteins that supply amino acids for insect metamorphosis. We identified seven genes encoding hexamerins, three encoding PPOs, and one hexamerin pseudogene in the genome of the parasitoid wasp Nasonia vitripennis. A phylogenetic analysis of hexamerins and PPOs from this wasp and related proteins from other insect orders suggests an essentially order-specific radiation of hexamerins. Temporal and spatial transcriptional profiles of N. vitripennis hexamerins suggest that they have physiological functions other than metamorphosis, which are arguably coupled with its lifestyle.

The alpha-galactosyl derivatives of ganglioside GD(1b) are essential for the organization of lipid rafts in RBL-2H3 mast cells

Gangliosides are complex glycosphingolipids that are important in many biological processes. The present study investigated the role of gangliosides in the organization of lipid rafts in RBL-2H3 mast cells and in the modulation of mast cell degranulation via Fc epsilon RI. The role of gangliosides was examined using two ganglioside deficient cell lines (B6A4A2III-E5 and B6A4C1III-D1) as well as the parent cell line (RBL-2H3). All three cell lines examined express Fc epsilon RI, Lyn, Syk and LAT. However, only in RBL-2H3 cells were Fc epsilon RI, LAT and alpha-galactosyl derivatives of ganglioside GD(1b) mobilized to lipid raft domains following Fc epsilon RI stimulation. The inhibition of glycosphingolipid synthesis in RBL-2H3 cells also resulted in a decrease in the release of beta-hexosaminidase activity after Fc epsilon RI activation. The two mutant cell lines have a reduced release of beta-hexosaminidase activity after Fc epsilon RI stimulation, but not after exposure to calcium ionophore. These results indicate that the alpha-galactosyl derivatives of ganglioside GD(1b) are important in the initial events of Fc epsilon RI signaling upstream of Ca(2+) influx. Since the initial signaling events occur in lipid rafts and in the mutant cell lines the rafts are disorganized, these results also suggest that these gangliosides contribute to the correct assembly of lipid rafts and are essential for mast cell activation via Fc epsilon RI. (c) 2008 Published by Elsevier Inc.