Julio Barbancho

Using artificial intelligence in routing schemes for wireless networks

For the latest 10 years, many authors have focused their investigations in wireless sensor networks. Different researching issues have been extensively developed: power consumption, MAC protocols, self-organizing network algorithms, data-aggregation schemes, routing protocols, QoS management, etc. Due to the constraints on data processing and power consumption, the use of artificial intelligence has been historically discarded. However, in some special scenarios the features of neural networks are appropriate to develop complex tasks such as path discovery. In this paper, we explore the performance of two very well-known routing paradigms, directed diffusion and Energy-Aware Routing, and our routing algorithm, named SIR, which has the novelty of being based on the introduction of neural networks in every sensor node. Extensive simulations over our wireless sensor network simulator, OLIMPO, have been carried out to study the efficiency of the introduction of neural networks. A comparison of the results obtained with every routing protocol is analyzed. This paper attempts to encourage the use of artificial intelligence techniques in wireless sensor nodes.

Energy efficient wireless sensor network communications based on computational intelligent data fusion for environmental monitoring

The study presents a novel computational intelligence algorithm designed to optimise energy consumption in an environmental monitoring process: specifically, water level measurements in flooded areas. This algorithm aims to obtain a trade-off between accuracy and power consumption. The implementation constitutes a data aggregation and fusion in itself. A harsh environment can make the direct measurement of flood levels a difficult task. This study proposes a flood level estimation, inferred through the measurement of other common environmental variables. The benefit of this algorithm is tested both with simulations and real experiments conducted in Donana, a national park in southern Spain where flood level measurements have traditionally been done manually.

Automated Meter Reading and SCADA Application for Wireless Sensor Network

Currently, there are many technologies available to automate public utilities services (water, gas and electricity). AMR, Automated Meter Reading, and SCADA, Supervisory Control and Data Acquisition, are the main functions that these technologies must support. In this paper, we propose a low cost network with a similar architecture to a static ad-hoc sensor network based on low power and unlicensed radio. Topological parameters for this network are analyzed to obtain optimal performances and to derive a pseudo-range criterion to create an application-specific spanning tree for polling optimization purposes. In application layer services, we analytically study different polling schemes.

Giving neurons to sensors. QoS management in wireless sensors networks.

Public utilities services (gas, water and electricity) have been traditionally automated with several technologies. The main functions that these technologies must support are AMR, automated meter reading, and SCADA, supervisory control and data acquisition. Most meter manufacturers provide devices with Bluetoothreg or ZigBeetrade communication features. This characteristic has allowed the inclusion of wireless sensor networks (WSN) in these systems. Once WSNs have appeared in such a scenario, real-time AMR and SCADA applications can be developed with low cost. Data must be routed from every meter to a base station. This paper describes the use of a novel QoS-driven routing algorithm, named SIR: sensor intelligence routing, over a network of meters. An artificial neural network is introduced in every node to manage the routes that data have to follow. The resulting system is named intelligent wireless sensor network (IWSN).

A new QoS routing algorithm based on self-organizing maps for wireless sensor networks

Abstract For the past ten years, many authors have focused their investigations in wireless sensor networks. Different researching issues have been extensively developed: power consumption, MAC protocols, self-organizing network algorithms, data-aggregation schemes, routing protocols, QoS management, etc. Due to the constraints on data processing and power consumption, the use of artificial intelligence has been historically discarded. However, in some special scenarios the features of neural networks are appropriate to develop complex tasks such as path discovery. In this paper, we explore and compare the performance of two very well known routing paradigms, directed diffusion and Energy-Aware Routing, with our routing algorithm, named SIR, which has the novelty of being based on the introduction of neural networks in every sensor node. Extensive simulations over our wireless sensor network simulator, OLIMPO, have been carried out to study the efficiency of the introduction of neural networks. A comparison of the results obtained with every routing protocol is analyzed. This paper attempts to encourage the use of artificial intelligence techniques in wireless sensor nodes.

SIR: a new wireless sensor network routing protocol based on artificial intelligence

Currently, Wireless Sensor Networks (WSNs) are formed by hundreds of low energy and low cost micro-electro-mechanical systems. Routing and low power consumption have become important research issues to interconnect this kind of networks. However, conventional Quality of Service routing models, are not suitable for ad hoc sensor networks, due to the dynamic nature of such systems. This paper introduces a new QoS-driven routing algorithm, named SIR: Sensor Intelligence Routing. We have designed an artificial neural network based on Kohonen self organizing features map. Every node implements this artificial neural network forming a distributed intelligence and ubiquitous computing system.

mTOSSIM: A simulator that estimates battery lifetime in wireless sensor networks

Abstract Knowledge of the battery lifetime of the wireless sensor network is important for many situations, such as in evaluation of the location of nodes or the estimation of the connectivity, along time, between devices. However, experimental evaluation is a very time-consuming task. It depends on many factors, such as the use of the radio transceiver or the distance between nodes. Simulations reduce considerably this time. They allow the evaluation of the network behavior before its deployment. This article presents a simulation tool which helps developers to obtain information about battery state. This simulator extends the well-known TOSSIM simulator. Therefore it is possible to evaluate TinyOS applications using an accurate model of the battery consumption and its relation to the radio power transmission. Although an specific indoor scenario is used in testing of simulation, the simulator is not limited to this environment. It is possible to work in outdoor scenarios too. Experimental results validate the proposed model.

Five years of designing wireless sensor networks in the Doñana Biological Reserve (Spain): an applications approach.

Wireless Sensor Networks (WSNs) are a technology that is becoming very popular for many applications, and environmental monitoring is one of its most important application areas. This technology solves the lack of flexibility of wired sensor installations and, at the same time, reduces the deployment costs. To demonstrate the advantages of WSN technology, for the last five years we have been deploying some prototypes in the Doñana Biological Reserve, which is an important protected area in Southern Spain. These prototypes not only evaluate the technology, but also solve some of the monitoring problems that have been raised by biologists working in Doñana. This paper presents a review of the work that has been developed during these five years. Here, we demonstrate the enormous potential of using machine learning in wireless sensor networks for environmental and animal monitoring because this approach increases the amount of useful information and reduces the effort that is required by biologists in an environmental monitoring task.

Applying case based reasoning for prioritizing areas of business management

Determining the importance of different management areas in a company provides guidance about the needs of increasing the analysis and actions focuses in particular topic. To do it, it is necessary to decompose the management in a coherent set of specific management areas and provide a way that allows the company to determine the importance of these areas for them. This paper presents a novel system that guides companies to obtain a classification of important management areas for them. It is focused on the use of a case based reasoning system because the variability and the evolution of companies as time passes requires using techniques with learning capabilities. The proposed system provides an automatic self-assessment system that provides companies an ordered list of their most important management areas. This system was implemented a year ago for the evaluation of Spanish companies. Currently, it is in production providing relevant information about the management areas of these companies.

Evaluation of MPEG-7-Based Audio Descriptors for Animal Voice Recognition over Wireless Acoustic Sensor Networks

Environmental audio monitoring is a huge area of interest for biologists all over the world. This is why some audio monitoring system have been proposed in the literature, which can be classified into two different approaches: acquirement and compression of all audio patterns in order to send them as raw data to a main server; or specific recognition systems based on audio patterns. The first approach presents the drawback of a high amount of information to be stored in a main server. Moreover, this information requires a considerable amount of effort to be analyzed. The second approach has the drawback of its lack of scalability when new patterns need to be detected. To overcome these limitations, this paper proposes an environmental Wireless Acoustic Sensor Network architecture focused on use of generic descriptors based on an MPEG-7 standard. These descriptors demonstrate it to be suitable to be used in the recognition of different patterns, allowing a high scalability. The proposed parameters have been tested to recognize different behaviors of two anuran species that live in Spanish natural parks; the Epidalea calamita and the Alytes obstetricans toads, demonstrating to have a high classification performance.