Road Type Identification Ahead of the Tire Using D-CNN and Reflected Ultrasonic Signals

Volunteered Geographic Information (VGI) is often collected by non-expert users. This raises concerns about the quality and veracity of such data. There has been much effort to understand and quantify the quality of VGI. Extrinsic measures which compare VGI to authoritative data sources such as National Mapping Agencies are common but the cost and slow update frequency of such data hinder the task. On the other hand, intrinsic measures which compare the data to heuristics or models built from the VGI data are becoming increasingly popular. Supervised machine learning techniques are particularly suitable for intrinsic measures of quality where they can infer and predict the properties of spatial data. In this article we are interested in assessing the quality of semantic information, such as the road type, associated with data in OpenStreetMap (OSM). We have developed a machine learning approach which utilises new intrinsic input features collected from the VGI dataset. Specifically, using our proposed novel approach we obtained an average classification accuracy of 84.12%. This result outperforms existing techniques on the same semantic inference task. The trustworthiness of the data used for developing and training machine learning models is important. To address this issue we have also developed a new measure for this using direct and indirect characteristics of OSM data such as its edit history along with an assessment of the users who contributed the data. An evaluation of the impact of data determined to be trustworthy within the machine learning model shows that the trusted data collected with the new approach improves the prediction accuracy of our machine learning technique. Specifically, our results demonstrate that the classification accuracy of our developed model is 87.75% when applied to a trusted dataset and 57.98% when applied to an untrusted dataset. Consequently, such results can be used to assess the quality of OSM and suggest improvements to the data set.

Download Full-text

Measurement of flow velocity profiles in tank structures using the prototype device OCM Pro LR

Water Science & Technology ◽

10.2166/wst.2011.173 ◽

2011 ◽

Vol 64 (1) ◽

pp. 263-270 ◽

Cited By ~ 2

Author(s):

K. Klepiszewski ◽

M. Teufel ◽

S. Seiffert ◽

E. Henry

Keyword(s):

Flow Velocity ◽

Large Scale ◽

Fluid Dynamic ◽

Waste Water Treatment ◽

Transport Processes ◽

Treatment Efficiency ◽

Cleaning Efficiency ◽

Cfd Modelling ◽

Ultrasonic Signals ◽

Cfd Models

Generally, studies investigating the treatment efficiency of tank structures for storm water or waste water treatment observe pollutant flows in connection with conditions of hydraulic loading. Further investigations evaluate internal processes in tank structures using computational fluid dynamic (CFD) modelling or lab scale tests. As flow paths inside of tank structures have a considerable influence on the treatment efficiency, flow velocity profile (FVP) measurements can provide a possibility to calibrate CFD models and contribute to a better understanding of pollutant transport processes in these structures. This study focuses on tests carried out with the prototype FVP measurement device OCM Pro LR by NIVUS in a sedimentation tank with combined sewer overflow (CSO) situated in Petange, Luxembourg. The OCM Pro LR measurement system analyses the echo of ultrasonic signals of different flow depths to get a detailed FVP. A comparison of flow velocity measured by OCM Pro LR with a vane measurement showed good conformity. The FVPs measured by OCM Pro LR point out shortcut flows within the tank structure during CSO events, which could cause a reduction of the cleaning efficiency of the structure. The results prove the applicability of FVP measurements in large-scale structures.

Download Full-text

Prediction of Ultrasonic Signals Captured from a Side-Drilled Hole Using a Rectangular Transducer

Key Engineering Materials ◽

10.4028/www.scientific.net/kem.321-323.497 ◽

2006 ◽

Vol 321-323 ◽

pp. 497-500

Author(s):

Hak Joon Kim ◽

Sung Jin Song ◽

Lester W. Schmerr

Keyword(s):

Reference Model ◽

Measurement Model ◽

Ultrasonic Measurement ◽

Beam Model ◽

System Efficiency ◽

Ultrasonic Beam ◽

Ultrasonic Signals ◽

Measurement Results ◽

Complete Measurement ◽

Proper Interpretation

For the proper interpretation of ultrasonic measurement results from a side-drilled hole (SDH) using a rectangular transducer, it is very helpful to have a complete ultrasonic measurement model. A highly efficient ultrasonic beam model of a rectangular transducer and an accurate scattering model of a SDH are currently available. However, to develop such a complete measurement model, a reference model for the system efficiency factor is also needed. In this study a reference model suitable for a rectangular transducer is given and combined with existing models to develop a complete ultrasonic measurement model that can the predict ultrasonic signals from a SDH. Based on this model, we have calculated the ultrasonic signals from a SDH at different transducer orientations and compared the model-based predictions with experiments.

Download Full-text

Application of a Max-Min algorithm on ultrasonic signals for tissue texture analysis

Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society ◽

10.1109/iembs.1992.5762188 ◽

1992 ◽

Author(s):

P. Giat ◽

G. Berger ◽

P. Laugier ◽

S. Abouelkaram

Keyword(s):

Texture Analysis ◽

Ultrasonic Signals

Download Full-text

Road Parameter-Based Driver Assistance System for Safe Driving

SAE International Journal of Connected and Automated Vehicles ◽

10.4271/12-02-04-0019 ◽

2019 ◽

Vol 2 (4) ◽

pp. 253-262

Author(s):

Sai Charan Addanki ◽

Keyword(s):

Driver Assistance System ◽

Assistance System ◽

Driver Assistance ◽

Driver Assistance Systems ◽

Safe Driving ◽

The Road ◽

Lane Tracking ◽

Road Type ◽

Key Aspects ◽

Type Classification

One of the key aspects of Advanced Driver Assistance Systems (ADAS) is ensuring the safety of the driver by maintaining a safe drivable speed. Overspeeding is one of the critical factors for accidents and vehicle rollovers, especially at road turns. This article aims to propose a driver assistance system for safe driving on Indian roads. In this regard, a camera-based classification of the road type combined with the road curvature estimation helps the driver to maintain a safe drivable speed primarily at road curves. Three Deep Convolutional Neural Network (CNN) models viz. Inception-v3, ResNet-50, and VGG-16 are being used for the task of road type classification. In this regard, the models are validated using a self-created dataset of Indian roads and an optimal performance of 83.2% correct classification is observed. For the calculation of road curvature, a lane tracking algorithm is used to estimate the curve radius of a structured road. The road type classification and the estimated road curvature values are given as inputs to a simulation-based model, CARSIM (vehicle road simulator to estimate the drivable speed). The recommended speed is then compared and analyzed with the actual speeds obtained from subjective tests.

Download Full-text