No abstract

Designing backbone network architecture (position of routers) of a distributed wireless sensor network for smart buildings can be a difficult task without the use of computer-aided tools. These tools should provide a robust and efficient solution to the problem with quick response time. However, available synthesis tools for designing wireless sensor networks are very limited, and in most cases, do not have the capability to perform an automatic synthesis of the backbone network. Puggelli et al. proposed an interactive design tool based on Dijkstras algorithm, which can assist the rapid design of sensor networks. However, it has a very high execution time when the network size is relatively large (e.g., more than 50 nodes). In addition, it can produce suboptimal solutions, by placing a large number of router nodes in the network. In this paper, we present efficient and robust synthesis algorithms that improve the run time with respect to Puggelli et al. for large networks by as much as 13× (4× on average). In comparison with Puggelli et al., the number of routers in these networks was also reduced by as much as 60% (41% on average). Index Terms-Wireless sensor network; router placement; synthesis algorithm.1530-437X . His novel ideas of model-based design for sensor networks made profound impact on engineering and industrial communities, and have been published in book chapters, renowned journals, conference proceedings, major scientific magazines, and also translated in several different languages. His research interests include methodologies and tools for embedded system design, in particular, the domain of sensor networks, energy-efficient building management and control system design, cloud computing, cyber physical system, and methodology for the design of distributed embedded systems subject to high real-time, safety, and reliability constraints.

In this paper, we propose an in-node microprocessor-based vehicle classification approach to analyze and determine the types of vehicles passing over a 3-axis magnetometer sensor. Our approach for vehicle classification utilizes J48 classification algorithm implemented in Weka (a machine learning software suite). J48 is a Quinlan's C4.5 algorithm, an extension of decision tree machine learning based on ID3 algorithm. The decision tree model is generated from a set of features extracted from vehicles passing over the 3-axis sensor. The features are attributes provided with correct classifications to the J48 training algorithm to generate a decision tree model with varying degrees of classification rates based on crossvalidation. Ideally, using fewer attributes to generate the model allows for the highest computational efficiency due to fewer features needed to be calculated while minimalizing the tree with fewer branches. The generated tree model can then be easily implemented using nested if-loops in any language on a multitude of microprocessors. In addition, setting an adaptive baseline to negate the effects of the background magnetic field allows reuse of the same tree model in multiple environments. The result of our experiment shows that the vehicle classification system is effective and efficient with the accuracy at nearly 100%.

Living in an era characterized by the rapid growth of Internet of Things (IoT), people can now easily access information about anything at anytime and anywhere. Still today, what is missing is that people cannot get relatively basic information of their own health without visiting a physician. Moreover, there is no generally acceptable system to provide vital health information such as heart rate, skin/core body temperature, respiratory rate, blood pressure, etc. In BioMeSensi, we propose an implementation of a wearable system which will be connected with the cloud infrastructure to collect valuable health related data to fill the current technological void.

Reliability is one of the most critical design features in Aircraft Electric Power Distribution system (EPDS). In an EPDS, the power is distributed from generators to loads, sensors and actuators through AC and DC distribution buses using control switches. Because of the increasing demands of loads and their power requirements, EPDS design must be optimized in order to have maximum efficiency. In this paper, we propose a synthesis tool based on a need-based design method to obtain the optimal topology of EPDS considering maximum reliability, continuous connectivity, power requirements, and minimum cost. We treat the EPDS as an optimization problem by using Integer Linear Programming (ILP) to achieve minimum cost and maximum reliability while satisfying a set of constraints.