Martin Kuehnhausen

Generalized probabilistic approximations of incomplete data

In this paper we discuss a generalization of the idea of probabilistic approximations. Probabilistic (or parameterized) approximations, studied mostly in variable precision rough set theory, were originally defined using equivalence relations. Recently, probabilistic approximations were defined for arbitrary binary relations. Such approximations have an immediate application to data mining from incomplete data because incomplete data sets are characterized by a characteristic relation which is reflexive but not necessarily symmetric or transitive. In contrast, complete data sets are described by indiscernibility which is an equivalence relation. The main objective of this paper was to compare experimentally, for the first time, two generalizations of probabilistic approximations: global and local. Additionally, we explored the problem how many distinct probabilistic approximations may be defined for a given data set.

Experiences from a Transportation Security Sensor Network Field Trial

Cargo shipments are subject to hijack, theft, or tampering. Furthermore, cargo shipments are at risk of being used to transport contraband, potentially resulting in fines to shippers. The Transportation Security Sensor Network (TSSN), which is based on open software systems and Service Oriented Architecture (SOA) principles, has been developed to mitigate these risks. Using commercial off-the-shelf (COTS) hardware, the TSSN is able to detect events and report those relevant to appropriate decision makers. Prior to deploying the TSSN it should be determined if the system can provide timely event notification. A field experiment was conducted to assess the TSSNs suitability for monitoring rail-borne cargo. Log files were collected from this experiment and postprocessed. In this paper we present empirical results on the time taken to report events using the TSSN. These results show that the TSSN can be used to monitor rail-borne cargo. Index Terms—Service oriented architecture, Mobile Rail Net- work, Trade Data Exchange, Virtual Network Operations Center

Local probabilistic approximations for incomplete data

In this paper we introduce a generalization of the local approximation called a local probabilistic approximation. Our novel idea is associated with a parameter (probability) α. If α = 1, the local probabilistic approximation becomes a local lower approximation; for small α, it becomes a local upper approximation. The main objective of this paper is to test whether proper local probabilistic approximations (different from local lower and upper approximations) are better than ordinary local lower and upper approximations. Our experimental results, based on ten-fold cross validation, show that all depends on a data set: for some data sets proper local probabilistic approximations are better than local lower and upper approximations; for some data sets there is no difference, for yet other data sets proper local probabilistic approximations are worse than local lower and upper approximations.

Application of the Java Message Service in mobile monitoring environments

Distributed systems and sensor networks in particular are in need of efficient asynchronous communication, message security and integrity, and scalability. These points are especially important in mobile environments where mobile remote sensors are connected to a control center only via intermittent communication. We present a general approach for dealing with the issues that arise in such scenarios. This approach is applied to provide flexible and efficient cargo monitoring on trains. The Java Message Service (JMS) presents a flexible transport layer for asynchronous communication that enables transparent store-and-forward queuing for entities that need to be connected to each other. Previously JMS was primarily used in always-connected high-bandwidth enterprise communication systems. We present the advantages of using JMS in a mobile, bandwidth-limited, and intermittently connected monitoring environment and provide a working implementation called the Transportation Security SensorNet (TSSN) that makes use of an implementation of JMS called ActiveMQ. This solution is employed here to enable monitoring of cargo in motion along trusted corridors. Results obtained from experiments and a field trial show that using JMS provides not just a practical alternative to often custom binary communication layers, but a better and more flexible approach, by providing transparency. Applications on both communication ends only need to implement JMS connectors while the remaining functionality is provided by the JMS implementation. Another benefit arises from the exchangeability of JMS implementations. In utilizing JMS we demonstrate a new, flexible and scalable approach to cope with challenges inherent in intermittent and low-bandwidth communication in mobile monitoring environments.

An Open-System Transportation Security Sensor Network: Field-Trial Experiences

Cargo shipments are subject to hijack, theft, or tampering. Furthermore, cargo shipments are at risk of being used to transport contraband, potentially resulting in fines to shippers. The Transportation Security Sensor Network (TSSN), which is based on open software systems and service-oriented architecture principles, has been developed to mitigate these risks. Using commercial off-the-shelf hardware, the TSSN can detect and report events that are relevant to appropriate decision makers. However, field testing is required to validate the system architecture and to determine if the system can provide timely event notification. Field experiments were conducted to assess the TSSNs suitability to monitor rail-borne cargo. Log files were collected from these experiments and were postprocessed. We present the TSSN architecture and results of field experiments, including the time taken to report events using the TSSN and the interaction between various components of the TSSN. These results show that the TSSN architecture can be used to monitor rail-borne cargo.

Anomaly Detection with Sensor Data for Distributed Security

There has been increasing interest in incorporating sensing systems into objects or the environment for monitoring purposes. In this work we compare approaches to performing fully-distributed anomaly detection as a means of detecting secu- rity threats for objects equipped with sensing and communication abilities. With the desirability of increased visibility into the cargo in the transport chain and the goal of improving security, we consider the approach of equipping cargo with sensing and communication capabilities as a means of ensuring the security of the cargo as a key application. We have gathered real sensor test data from a rail trial and used the collected data to test the feasibility of the anomaly detection approach. The results demonstrate the effectiveness of our approach. I. INTRODUCTION

Transportation Security SensorNet: a service‐oriented architecture for cargo monitoring

Purpose – Security and accountability within the transportation industry are vital because cargo theft could amount to as much as

Trusting smartphone Apps? To install or not to install, that is the question

60 billion per year. Since goods are often handled by many different parties, it must be possible to tightly monitor the location of cargo and handovers. Tracking trade is difficult to manage in different formats and legacy applications Web services and open standards overcome these problems with uniform interfaces and common data formats. This allows consistent reporting, monitoring and analysis at each step. The purpose of this paper is to examine Transportation Security SensorNet (TSSN), the goal being to promote the use of open standards and specifications in combination with web services to provide cargo monitoring capabilities.Design/methodology/approach – This paper describes a system architecture for the TSSN targeted for cargo monitoring. The paper discusses cargo security and reviews related literature and approaches. The paper then describes the proposed solution of...