Manuel Toledano-Ayala

Revisiting Gaussian Process Regression Modeling for Localization in Wireless Sensor Networks

Signal strength-based positioning in wireless sensor networks is a key technology for seamless, ubiquitous localization, especially in areas where Global Navigation Satellite System (GNSS) signals propagate poorly. To enable wireless local area network (WLAN) location fingerprinting in larger areas while maintaining accuracy, methods to reduce the effort of radio map creation must be consolidated and automatized. Gaussian process regression has been applied to overcome this issue, also with auspicious results, but the fit of the model was never thoroughly assessed. Instead, most studies trained a readily available model, relying on the zero mean and squared exponential covariance function, without further scrutinization. This paper studies the Gaussian process regression model selection for WLAN fingerprinting in indoor and outdoor environments. We train several models for indoor/outdoor- and combined areas; we evaluate them quantitatively and compare them by means of adequate model measures, hence assessing the fit of these models directly. To illuminate the quality of the model fit, the residuals of the proposed model are investigated, as well. Comparative experiments on the positioning performance verify and conclude the model selection. In this way, we show that the standard model is not the most appropriate, discuss alternatives and present our best candidate.

A survey of hybridisation methods of GNSS and wireless LAN based positioning system

Self-localisation has become a matter of course in our daily life. The emerging market of mobile devices still boosts the demand for seamless, ubiquitous positioning. The repertoire of sensors serviceable for localisation provided by current mobile devices is large; however the main positioning systems used today are based on wireless local area networks (WLAN), cellular networks and certainly global navigation satellite systems (GNSS). Because of the accuracy, the vast deployment and the channel characteristics, researchers have been focused on WLAN based positioning systems (WPS) in particular, to achieve seamless positioning. This paper reviews the latest data fusion approaches to seamless positioning by GNSS and WPS. In accordance to the level of data fusion, several approaches are categorised and briefly presented, differences in performance of these approaches are highlighted and future challenges identified.

A rigorous evaluation of Gaussian process models for WLAN fingerprinting

Location based services require accurate and seamless positioning in large urban areas. In contrast to GNSS, WLAN fingerprinting positioning offers seamless localization in these areas. Though, it requires a huge effort to create the radio maps. Interpolating radio maps is a viable solution; in particular Gaussian process (GP) regression is very effective for this task. Based on a thorough evaluation of different Gaussian process models we appoint the best suited model for spatial signal strength interpolation. We pursue the model evaluation by establishing GP maximum likelihood (ML) estimators and assess their effects on the positioning accuracy in a realistic WLAN indoor/outdoor localization scenario. Insights on the spatial density of fingerprints are included in our study. We found that the commonly used GP model, with zero mean and squared exponential covariance function, is not the best suited model and propose a better and more robust alternative. Moreover, this study demonstrates that a low amount of fingerprints not necessarily impairs, but potentially improves the accuracy of the ML estimators.

Long-Range Wireless Mesh Network for Weather Monitoring in Unfriendly Geographic Conditions

In this paper a long-range wireless mesh network system is presented. It consists of three main parts: Remote Terminal Units (RTUs), Base Terminal Units (BTUs) and a Central Server (CS). The RTUs share a wireless network transmitting in the industrial, scientific and medical applications ISM band, which reaches up to 64 Km in a single point-to-point communication. A BTU controls the traffic within the network and has as its main task interconnecting it to a Ku-band satellite link using an embedded microcontroller-based gateway. Collected data is stored in a CS and presented to the final user in a numerical and a graphical form in a web portal.

Dedicated feature descriptor for outdoor augmented reality detection

Stable augmented reality applications consist of an accurate registration supported by a robust tracking module. In outdoor locations, the changing environmental and light conditions compromise this tracking. Reliable descriptors under unsettled conditions are essential for this process. The most used descriptors have this distinctive capacity, but computers and mobile devices process them in a long time frame. This paper investigates a new lightweight environment dedicated descriptor (EDD) trained with a machine-learning algorithm. The descriptor analyzes the scene characteristics with elements that can be computed fast and that have distinctive information about the selected area. The complete descriptor is used for semantic feature extraction with the aid of a trained random forest classifier. The descriptor is compared with the most popular descriptors—with respect to speed, accuracy, and invariance to illumination changes, scale, affine transformation, and rotation—and the results show that it is faster and in most cases equally reliable .

Ubiquitous and Seamless Localization: Fusing GNSS Pseudoranges and WLAN Signal Strengths

Ubiquitous global positioning is not feasible by GNSS alone, as it lacks accurate position fixes in dense urban centres and indoors. Hybrid positioning methods have been developed to aid GNSS in those environments. Fingerprinting localization in wireless local area networks (WLANs) is a promising aiding system because of its availability, accuracy, and error mechanisms opposed to that of GNSS. This article presents a low-cost approach to ubiquitous, seamless positioning based on a particle filter integrating GNSS pseudoranges and WLAN received signal strength indicators (RSSIs). To achieve accurate location estimates indoors/outdoors and in the transition zones, appropriate likelihood functions are essential as they determine the influence of each sensor information on the position estimate. We model the spatial RSSI distributions with Gaussian processes and use these models to predict RSSIs at the particle’s positions to obtain point estimates of the RSSI likelihood function. The particle filter’s performance is assessed with real data of two test trajectories in an environment challenging for GNSS and WLAN fingerprinting localization. Outcomes of an extended Kalman filter using pseudoranges and a WLAN position as observation is included as benchmark. The proposed algorithm achieves accurate and robust seamless localization with a median accuracy of five meters.

Aquatic Biosystems: Applications in Aquacultural Engineering as a Sustainable Technology

Aquaculture has been supporting human demands for fish products for centuries and is an important industry worldwide. Global production from aquaculture has been increasing steadily, having more than doubled in the last decade; aquaculture now supplies one-third of seafood consumed worldwide. However, the expansion of aquaculture has been accompanied by degradation of the natural environment, especially on marine aquaculture. Direct impacts of fisheries and aquaculture are habitat modification, collection of wild seedstock, changes of food webs, introduction of nonnative fish species, and diseases that harm wild fish populations, and nutrient pollution. According to the FAO, major issues that need to be addressed are problems with access to proper technology and financial resources, together with environmental impacts and diseases. Some others argue that further increases in aquaculture production will come mainly from further investment in biotechnology or nanotechnology ranging from protein expression and DNA vaccines, water filtration and remediation, nanoparticles, gene delivery (and chips) to transgenic technologies. The purpose of this chapter is to present the progress in the research about to get a sustainable aquaculture.

Thermal behavior in different roof coverings on classrooms

2 . Three classrooms were covered with asphaltic bitumen of three different colors (red tile, matte white and ebony black) the last one was covered with typical clay of the region. Two temperature sensors were installed in each classroom. The first one was fixed outside of the calssrooom at 0.40 m above the roof surface and the second one was installed 0.15 m below the ceiling. The temperature data were stored over ten minutes with a set of remote terminal units which form a wireless sensor network. The results showed significant differences in temperature between the four classrooms with a grade of significance of 0.05, and it showed that the color of the roof deck significantly influences the thermal behavior inside the classrooms. The influence of external temperature over the internal temperature was quantified with the r-Person coefficient, which was found at a mean value of 0.98.

Water, gas and electric power monitoring system for residential developments: A technological approach

Savings in energy and water consumption represents one of the most important challenges for governments around the world today. Residential developments in Mexico offer a feasible way for low-income families in populated cities to acquire a house. This paper presents a novel technological approach to achieve substantial savings in energy and water in residential developments; as well it can be used as a tool for billing, and consumption planning. The system was tested in the municipality of Tecamac during the warmest months of the year in Mexico. The following results were recorded: 13.43% of savings in power consumption, 10.18% related to the conservation of water and 9.13% less gas was used. Practical applications: Significant savings related to energy used and water conserved, are possible when networked technological systems such as the one proposed herein are installed either when the house is being built or can also be implemented in existing houses. Indirect benefits are present as well as tax reductions for constructors who build using eco-friendly and best housing practices. These savings and benefits can further be extended to services suppliers, reduce internal traffic in residential developments, among others.