Jung Jin Cho’s research while affiliated with Baker Hughes Incorporated and other places

Using multiple, heterogeneous sensors in surveillance systems is desirable, not only to tolerate sensor failures, but also to increase the accuracy of the event detection process and to provide complementary capability under different operating conditions. In the operation of multiple, heterogeneous sensors, we may encounter inconsistent sensor observations. Motivated by the need to make coherent decisions, we propose in this study a decision scheme to determine the right interpretations of sensor outputs when conflict arises. The proposed decision rule considers sensor heterogeneity in a surveillance system, while attempting to minimize the expected misclassification cost. Case studies of the surveillance sensor system in a major U.S. port demonstrate that the proposed decision scheme achieves a better robustness in the presence of sensor failures than the popular k -out-of- n decision fusion rule.

This paper presents a robust calibration procedure for clustered wireless sensor networks. Accurate calibration of between-node distances is one crucial step in localizing sensor nodes in an ad-hoc sensor network. The calibration problem is formulated as a parameter estimation problem using a linear calibration model. For reducing or eliminating the unwanted influence of measurement corruptions or outliers on parameter estimation, which may be caused by sensor or communication failures, a robust regression estimator such as the least-trimmed squares (LTS) estimator is a natural choice. Despite the availability of the FAST-LTS routine in several statistical packages (e.g., R, S-PLUS, SAS), applying it to the sensor network calibration is not a simple task. To use the FAST-LTS, one needs to input a trimming parameter, which is a function of the sensor redundancy in a network. Computing the redundancy degree and subsequently solving the LTS estimation both turn out to be computationally demanding. Our research aims at utilizing some cluster structure in a network configuration in order to do robust estimation more efficiently. We present two algorithms that compute the exact value and a lower bound of the redundancy degree, respectively, and an algorithm that computes the LTS estimation. Two examples are presented to illustrate how the proposed methods help alleviate the computational demands associated with robust estimation and thus facilitate robust calibration in a sensor network.

In robust statistics, the concept of breakdown point was introduced to quantify the robustness of an es-timator in a linear regression model. Computing the breakdown point is useful in tuning some robust regression estimators (e.g., the least trimmed squares estimator). Computing the breakdown point for a structured linear model (i.e., one with dependencies among some p rows of the n × p design matrix X) can be very demanding. This article presents an algorithm for calculating the maximum breakdown point for sparse linear models, which are a special type of structured linear model whose design matrix has many zero entries. The algorithm decomposes a sparse design matrix into smaller submatrixes on which the computation is performed, thereby leading to substantial savings in computation. An assembly process, along with a few numerical examples, illustrate the application of the algorithm and demonstrate its com-putational benefits.

This article studies the girth and cogirth problems for a connected matroid. The problem of finding the cogirth of a graphic matroid has been intensively studied, but studies on the equivalent problem for a vector matroid or a general matroid have been rarely reported. Based on the duality and connectivity of a matroid, we prove properties associated with the girth and cogirth of a matroid whose contraction or restriction is disconnected. Then, we devise algorithms that find the cogirth of a matroid M from the matroids associated with the direct sum components of the restriction of M. As a result, the problem of finding the (co)girth of a matroid can be decomposed into a set of smaller sub-problems, which helps alleviate the computation. Finally, we implement and demonstrate the application of our algorithms to vector matroids. © 2007 Elsevier B.V. All rights reserved.

This paper presents a robust calibration procedure for a clustered wireless sensor network. The calibration problem is often formulated as a parameter estimation problem using a linear calibration model. For reducing or eliminating unwanted influences of measurement corruptions or outliers on parameter estimation, a robust regression estimator is a natural choice. In order to solve a robust estimation problem more efficiently, we utilize cluster structure in a network configuration and decompose a large network into smaller subsystems that can be solved much faster. To this end, we present two algorithms for a robust calibration procedure. Two examples are presented to illustrate how the proposed methods enable robust calibration in a sensor network.

Recent innovations in sensor technology enable manufacturers to distribute redundant sensors in manufacturing processes for quality monitoring, defect detection, and fault diagnosis. Even if a single sensor is relatively reliable, the large number of sensors in a distributed sensor system confronts us the almost unavoidable possibility that some of the sensors may malfunction. Without isolating sensor anomalies from the underlying process changes, abnormal sensor readings can cause frequent false alarms and jeopardize productivity. Traditionally, sensor system reliability has been ensured by employing off-line gage Repeatability and Reproducibility (R&R) calibration. But this off-line approach can be time consuming and costly for in-process distributed sensor systems. This paper will present a robust estimation procedure that automatically identify the observations related to suspected sensor failures. We first identify sensor redundancy and introduce an existing algorithm to assess the redundant level. We further suggest a decomposition technique, which helps to substantially reduce the computation expense of the existing algorithms for a large sensor system. Finally, the concept and procedure is illustrated using a distributed coordinate sensor system in a multi-station manufacturing system.