Browsing by Author "Cherkassky, Vladimir"

Now showing 1 - 7 of 7
  • Thumbnail Image
    Item
    Effect of Compliance Reviews on Out-of-Service Rates of Region 5 Carriers: A Study
    (Minnesota Department of Transportation, 1999-07) Khosa, Vikram; Cherkassky, Vladimir
    This Phase II study involved studying the short-term and long-term effects of the Compliance Review (CR) programs conducted in the Region 5 states of Wisconsin, Indiana, Michigan, Minnesota, Ohio, and Illinois on the Out-of-Service (OOS) rates of interstate freight-carriers based in those states. A preliminary analysis of the inspections data revealed low OSS rates based on inspection records--across all level of inspection--for the years 1993-94, indicating defective collection/interpretation of data and thereby invalidating any OOS rate analysis for this time period. Also, it was found that Level 1 and 2 inspections together constitute nearly 80 percent of all inspections records, thus marginalizing the effect of the other levels of inspection on the final results of this analysis. The results of both the short-term and long-term effects of OOS rate analysis suggest an overall positive effect of the Compliance Review program on the reduction of OOS (Event and Violation) rates of the carriers. These results are consistent over the rest of the time period (1995-97) and across three levels of inspection (Levels 1, 2, and 3). The conclusions drawn about the nature of the effects of a Compliance Review could be much better validated if the currently spurious inspections data for the years 1993-94 were restored, or a fresh analysis using later available data (1997-99) were carried out based on the same algorithms.
  • Thumbnail Image
    Item
    Image Compression for Storage and Transmission of Digital Images
    (2000-08-01) Cherkassky, Vladimir; He, Xuhao; Shao, Jie
    This project researched image compression methods for storage and transmission of digital images at the Minnesota Department of Transportation (Mn/DOT). Researchers compared the performance of several commercial and research methods for image compression based on the "typical" image provided by the Mn/DOT Office of Land Management. They also surveyed some new image compression methods based on wavelet thresholding. The report details the analyses and comparisons and includes recommendations. Researchers choose MrSID, a commercial software package for image compression, as a suitable method for the needs of Mn/DOT's Office of Land Management. MrSID uses a wavelet transform-based algorithm to achieve both the efficient storage and retrieval of large digital images. Its main practical advantages include improved utilization of storage and transmission resources and a multi-resolution browsing capability. MrSID can selectively decompress a portion of an image by zooming at different levels of detail. Researchers implemented a demo website, which can be browsed easily and implements the zooming function. The web site address is http://rocky.dot.state.mn.us/research.
  • Thumbnail Image
    Item
    Implementation of Quality of Service (QoS) with Dynamic Resource Allocation
    (2004-03-01) Cherkassky, Vladimir; Rostovtsev, Harry
    As the need to monitor traffic conditions on highway systems increases, the ability to get a clear video picture decreases due to network congestion. There are many Quality of Service (QoS) implementations available on the market for high traffic networks but none implement dynamic priority assignment changes to different network traffic. This is very useful for highway video surveillance using camera systems attached to a limited bandwidth network. This project uses freely available software and low cost hardware to provide such a system. A working prototype of the system has been developed and a detailed performance analysis has been performed.
  • Thumbnail Image
    Item
    Motor Carrier Compliance Reviews: Measuring Their Impact on Improved Safety Performance Among Interstate Freight Motor Carriers Based in Minnesota
    (Minnesota Department of Transportation, 1997-05) Pagel, David; Cherkassky, Vladimir
    This study seeks to measure the safety performance of compliance reviews (CRs) conducted in Minnesota under the Motor Carrier Safety Assistance Program (MCSAP). This study employs data gathered by the Federal Highway Administration surrounding two MCSAP activities: compliance reviews and roadside inspections. It specifically investigates the change in a carrier's annual out-of-service violation rate (OOS) in response to receiving a review or a higher number of inspections. A measurable reduction in a carrier's OOS rate occurs in the year after a CR, according to the data. The annual OOS rate appears to be a viable measure of the impact of a compliance review, given that a carrier's vehicles and drivers are adequately inspected in the year following a CR.
  • Thumbnail Image
    Item
    Real-Time Prediction of Freeway Occupancy for Congestion Control
    (Center for Transportation Studies, University of Minnesota, 1997-09) Cherkassky, Vladimir; Yi, Sangkug
    Accurate traffic prediction is critical for effective control of on-ramp traffic (ramp metering). During congestion, traffic shock waves propagate back and forth between the detectors, and traffic becomes inherently non-stationary and difficult to predict. Recently, several adaptive non-linear time series prediction methods have been developed in statistics and in artificial neural networks. We applied these methods to develop real-time prediction of freeway occupancy during congestion periods, from current and time-lagged observations of occupancy at several (neighboring) detector stations. This study used the following function estimation methodologies for real-time occupancy prediction: two statistical techniques, multivariate adaptive regression splines (MARS) and projection pursuit regression; two neural network methods, multi-layer perceptrons (MLP) and constrained topological mapping (CTM). All these methods were applied to freeway occupancy data collected on I-35W during morning rush hours. Data collected on one day was used for training (model estimation), whereas the data collected on a different day was used for testing, i.e., estimating the quality of prediction (generalization). Results for this study indicate that the proposed methodology provides 10-15% more accurate prediction of traffic during congestion periods than the approach currently used by Minnesota DOT.
  • Thumbnail Image
    Item
    Statistical Analysis of the Soil Chemical Survey Data
    (Minnesota Department of Transportation Research Services Section, 2010-06) Dhar, Sauptik; Cherkassky, Vladimir
    This report describes data-analytic modeling of the Minnesota soil chemical data produced by the 2001 metro soil survey and by the 2003 state-wide survey. The chemical composition of the soil is characterized by the concentration of many metal and non-metal constituents, resulting in high-dimensional data. This high dimensionality and possible unknown (nonlinear) correlations in the data make it difficult to analyze and interpret using standard statistical techniques. This project applies a machine learning technique, called Self Organizing Map (SOM), to present the high-dimensional soil data in a 2D format suitable for human understanding and interpretation. This SOM representation enables analysis of the soil chemical concentration trends within the metro area and in the state of Minnesota. These trends are important for various Minnesota regulatory agencies concerned with the concentration of polluting chemical elements due to both (a) human activities, i.e., different industrial land usage, and (b) natural geological factors, such as the geomorphic codes and provenance of glacial sediments.
  • Thumbnail Image
    Item
    Wireless Transmission of Image and Video Data
    (2002-04-01) Cherkassky, Vladimir; He, Xuhao; Balasubramanian, Prakash
    This project focuses on the issues involved in wireless transmission of video data and addresses two main issues: video compression and quality of service. The report describes the research experiment, analysis, and results. Researchers compared several compression techniques that are commercially available and recommended wavelet-based compression technique for video compression and network prioritization for issues related to quality of service.