No abstract

Because energy efficiency is gaining more importance these days and Bluetooth Low Energy (BLE) could be used to make use of potential everyday objects into Internet of Things (IOT) - a software, platform and vendor independent common service interface that can be used in such low resource devices has high potential. OPC UA is an emerging middleware solution that addresses the above points but is bulky due to its abundant features. Further optimization is necessary to bring the OPC UA into such resource-limited devices. We have scaled down the OPC UA protocol stack footprint down to the chip level [16]. In this paper, we propose an optimization approach to minimize the OPC UA network footprint

Typically, cognitive radio systems either sense the channel just before transmission or perform this task periodically in order to remain aware about the operational environment. However, a channel sensed as 'free' can become busy during the transmission of the cognitive system resulting in harmful collisions and unnecessary interruptions in the secondary user data transmission. As a solution, predictive based approaches has been proposed and has shown promising results in simulated environments. However, modeling real-time, dynamic, coexisting environments demand investigation with real-time demonstrators. This paper investigates industrial coexisting environments and illustrates the prediction model selection and its parameter estimation criteria. Based on the investigation a real-time testbed is implemented using a CC2500 TRX and MSP430 μC based platform.

Cognitive radios (CR) can sense and detect temporarily available spectral holes for an opportunistic operation to improve the spectral efficiency and coexistence of industrial radio systems. It will be of particular interest for a CR system to apply predictive modeling in order to forecast the behavior of the coexisting environment. A secondary cognitive user shall use preemptive tuning of its operating parameters following the predictive model. However, a considerable challenge is to generate an accurate model and predict efficiently in order to meet strict time related requirements of industrial applications. Such predictive modeling has already gained some attention but real-time results are never reported. In this contribution we investigate real-time aspects of predictive modeling for its application in industrial CR systems.

Probabilistic machine learning approaches has been successfully applied in various applications and is gaining more and more popularity. But the success of such approaches are based on the quality of the data. Getting quality data is the biggest challenge for most of the real-life applications and our application domain, i.e. industrial cleaning process, is no exception. In our application domain, the data collection is mostly performed manually without using any standards and is highly influenced by the expertise and interpretation of individual cleaning personnel. We have developed a Bayesain predictive assistance system (BPAS) that uses a real-life cleaning data to provide decision support to the cleaning personnel. In this paper, we extend our BPAS and propose a hybrid approach to develop an assistance system for resource optimization in industrial cleaning processes. The proposed approach, which combines Bayesian network and rule-based system, aims at increasing the robustness and the stability of the assistance system