Ensemble Stream Model for Data-Cleaning in Sensor Networks

Ensemble Stream Modeling and Data-cleaning are sensor information processing systems have different training and testing methods by which their goals are cross-validated. This research examines a mechanism, which seeks to extract novel patterns by generating ensembles from data. The main goal of label-less stream processing is to process the sensed events to eliminate the noises that are uncorrelated, and choose the most likely model without over fitting thus obtaining higher model confidence. Higher quality streams can be realized by combining many short streams into an ensemble which has the desired quality. The framework for the investigation is an existing data mining tool. First, to accommodate feature extraction such as a bush or natural forest-fire event we make an assumption of the burnt area (BA*), sensed ground truth as our target variable obtained from logs. Even though this is an obvious model choice the results are disappointing. The reasons for this are two: One, the histogram of fire activity is highly skewed. Two, the measured sensor parameters are highly correlated. Since using non descriptive features does not yield good results, we resort to temporal features. By doing so we carefully eliminate the averaging effects; the resulting histogram is more satisfactory and conceptual knowledge is learned from sensor streams. Second is the process of feature induction by cross-validating attributes with single or multi-target variables to minimize training error. We use F-measure score, which combines precision and accuracy to determine the false alarm rate of fire events. The multi-target data-cleaning trees use information purity of the target leaf-nodes to learn higher order features. A sensitive variance measure such as f-test is performed during each node’s split to select the best attribute. Ensemble stream model approach proved to improve when using complicated features with a simpler tree classifier. The ensemble framework for data-cleaning and the enhancements to quantify quality of fitness (30% spatial, 10% temporal, and 90% mobility reduction) of sensor led to the formation of streams for sensor-enabled applications. Which further motivates the novelty of stream quality labeling and its importance in solving vast amounts of real-time mobile streams generated today.

Ihwg-μnir: A Miniaturised Near-infrared Gas Sensor Based On Substrate-integrated Hollow Waveguides Coupled To A Micro-nir-spectrophotometer.

A miniaturised gas analyser is described and evaluated based on the use of a substrate-integrated hollow waveguide (iHWG) coupled to a microsized near-infrared spectrophotometer comprising a linear variable filter and an array of InGaAs detectors. This gas sensing system was applied to analyse surrogate samples of natural fuel gas containing methane, ethane, propane and butane, quantified by using multivariate regression models based on partial least square (PLS) algorithms and Savitzky-Golay 1(st) derivative data preprocessing. The external validation of the obtained models reveals root mean square errors of prediction of 0.37, 0.36, 0.67 and 0.37% (v/v), for methane, ethane, propane and butane, respectively. The developed sensing system provides particularly rapid response times upon composition changes of the gaseous sample (approximately 2 s) due the minute volume of the iHWG-based measurement cell. The sensing system developed in this study is fully portable with a hand-held sized analyser footprint, and thus ideally suited for field analysis. Last but not least, the obtained results corroborate the potential of NIR-iHWG analysers for monitoring the quality of natural gas and petrochemical gaseous products.

Flow Visualization in Arteriovenous Fistula and Aneurysm Using Computational Fluid Dynamics

The arteriovenous fistula (AVF) is characterized by enhanced blood flow and is the most widely used vascular access for chronic haemodialysis (Sivanesan et al., 1998). A large proportion of the AVF late failures are related to local haemodynamics (Sivanesan et al., 1999a). As in AVF, blood flow dynamics plays an important role in growth, rupture, and surgical treatment of aneurysm. Several techniques have been used to study the flow patterns in simplified models of vascular anastomose and aneurysm. In the present investigation, Computational Fluid Dynamics (CFD) is used to analyze the flow patterns in AVF and aneurysm through the velocity waveform obtained from experimental surgeries in dogs (Galego et al., 2000), as well as intra-operative blood flow recordings of patients with radiocephalic AVF ( Sivanesan et al., 1999b) and physiological pulses (Aires, 1991), respectively. The flow patterns in AVF for dog and patient surgeries data are qualitatively similar. Perturbation, recirculation and separation zones appeared during cardiac cycle, and these were intensified in the diastole phase for the AVF and aneurysm models. The values of wall shear stress presented in this investigation of AVF and aneurysm models oscillated in the range that can both cause damage to endothelial cells and develop atherosclerosis.

Equational Reasoning as a Tool for Data Analysis

A combination of deductive reasoning, clustering, and inductive learning is given as an example of a hybrid system for exploratory data analysis. Visualization is replaced by a dialogue with the data.

Visualization of learning in multilayer perceptron networks using principal component analysis

This paper is concerned with the use of scientific visualization methods for the analysis of feedforward neural networks (NNs). Inevitably, the kinds of data associated with the design and implementation of neural networks are of very high dimensionality, presenting a major challenge for visualization. A method is described using the well-known statistical technique of principal component analysis (PCA). This is found to be an effective and useful method of visualizing the learning trajectories of many learning algorithms such as back-propagation and can also be used to provide insight into the learning process and the nature of the error surface.

Using multidimensional projection techniques for reaching a high distinguishing ability in biosensing

Recent advances in the control of molecular engineering architectures have allowed unprecedented ability of molecular recognition in biosensing, with a promising impact for clinical diagnosis and environment control. The availability of large amounts of data from electrical, optical, or electrochemical measurements requires, however, sophisticated data treatment in order to optimize sensing performance. In this study, we show how an information visualization system based on projections, referred to as Projection Explorer (PEx), can be used to achieve high performance for biosensors made with nanostructured films containing immobilized antigens. As a proof of concept, various visualizations were obtained with impedance spectroscopy data from an array of sensors whose electrical response could be specific toward a given antibody (analyte) owing to molecular recognition processes. In addition to discussing the distinct methods for projection and normalization of the data, we demonstrate that an excellent distinction can be made between real samples tested positive for Chagas disease and Leishmaniasis, which could not be achieved with conventional statistical methods. Such high performance probably arose from the possibility of treating the data in the whole frequency range. Through a systematic analysis, it was inferred that Sammon`s mapping with standardization to normalize the data gives the best results, where distinction could be made of blood serum samples containing 10(-7) mg/mL of the antibody. The method inherent in PEx and the procedures for analyzing the impedance data are entirely generic and can be extended to optimize any type of sensor or biosensor.

Integrating high and moderate spatial resolution image data to estimate forest age structure

The collection of spatial information to quantify changes to the state and condition of the environment is a fundamental component of conservation or sustainable utilization of tropical and subtropical forests, Age is an important structural attribute of old-growth forests influencing biological diversity in Australia eucalypt forests. Aerial photograph interpretation has traditionally been used for mapping the age and structure of forest stands. However this method is subjective and is not able to accurately capture fine to landscape scale variation necessary for ecological studies. Identification and mapping of fine to landscape scale vegetative structural attributes will allow the compilation of information associated with Montreal Process indicators lb and ld, which seek to determine linkages between age structure and the diversity and abundance of forest fauna populations. This project integrated measurements of structural attributes derived from a canopy-height elevation model with results from a geometrical-optical/spectral mixture analysis model to map forest age structure at a landscape scale. The availability of multiple-scale data allows the transfer of high-resolution attributes to landscape scale monitoring. Multispectral image data were obtained from a DMSV (Digital Multi-Spectral Video) sensor over St Mary's State Forest in Southeast Queensland, Australia. Local scene variance levels for different forest tapes calculated from the DMSV data were used to optimize the tree density and canopy size output in a geometric-optical model applied to a Landsat Thematic Mapper (TU) data set. Airborne laser scanner data obtained over the project area were used to calibrate a digital filter to extract tree heights from a digital elevation model that was derived from scanned colour stereopairs. The modelled estimates of tree height, crown size, and tree density were used to produce a decision-tree classification of forest successional stage at a landscape scale. The results obtained (72% accuracy), were limited in validation, but demonstrate potential for using the multi-scale methodology to provide spatial information for forestry policy objectives (ie., monitoring forest age structure).

A titrimetric respirometer measuring the nitrifiable nitrogen in wastewater using in-sensor-experiment

Measurement of nitrifiable nitrogen contained in wastewater by combining the existing respirometric and titrimetric principles is reported. During an in-sensor-experiment using nitrifying activated sludge. both the dissolved oxygen (DO) and pH in the mixed liquor were measured, and the FH was controlled at a set-point through titration of base or acid. A combination of the oxygen uptake rate (OUR), which was obtained from the measured DO signal, and the titration data allowed calculation of the nitrifiable nitrogen and the short-term biological oxygen demand (BOD) of the wastewater sample that was initially added to the sludge. The calculation was based solely on stoichiometric relationships. The approach was preliminarily tested with two types of wastewaters using a prototype sensor. Good correlation was obtained. (C) 2000 Elsevier Science Ltd. All rights reserved.

Development of a novel titration and off-gas analysis (TOGA) sensor for study of biological processes in wastewater treatment systems

The development of the new TOGA (titration and off-gas analysis) sensor for the detailed study of biological processes in wastewater treatment systems is outlined. The main innovation of the sensor is the amalgamation of titrimetric and off-gas measurement techniques. The resulting measured signals are: hydrogen ion production rate (HPR), oxygen transfer rate (OTR), nitrogen transfer rate (NTR), and carbon dioxide transfer rate (CTR). While OTR and NTR are applicable to aerobic and anoxic conditions, respectively, HPR and CTR are useful signals under all of the conditions found in biological wastewater treatment systems, namely, aerobic, anoxic and anaerobic. The sensor is therefore a powerful tool for studying the key biological processes under all these conditions. A major benefit from the integration of the titrimetric and off-gas analysis methods is that the acid/base buffering systems, in particular the bicarbonate system, are properly accounted for. Experimental data resulting from the TOGA sensor in aerobic, anoxic, and anaerobic conditions demonstrates the strength of the new sensor. In the aerobic environment, carbon oxidation (using acetate as an example carbon source) and nitrification are studied. Both the carbon and ammonia removal rates measured by the sensor compare very well with those obtained from off-line chemical analysis. Further, the aerobic acetate removal process is examined at a fundamental level using the metabolic pathway and stoichiometry established in the literature, whereby the rate of formation of storage products is identified. Under anoxic conditions, the denitrification process is monitored and, again, the measured rate of nitrogen gas transfer (NTR) matches well with the removal of the oxidised nitrogen compounds (measured chemically). In the anaerobic environment, the enhanced biological phosphorus process was investigated. In this case, the measured sensor signals (HPR and CTR) resulting from acetate uptake were used to determine the ratio of the rates of carbon dioxide production by competing groups of microorganisms, which consequently is a measure of the activity of these organisms. The sensor involves the use of expensive equipment such as a mass spectrometer and requires special gases to operate, thus incurring significant capital and operational costs. This makes the sensor more an advanced laboratory tool than an on-line sensor. (C) 2003 Wiley Periodicals, Inc.

Sensor-driven agenda for intelligent home care of the elderly

The exponential increase of home-bound persons who live alone and are in need of continuous monitoring requires new solutions to current problems. Most of these cases present illnesses such as motor or psychological disabilities that deprive of a normal living. Common events such as forgetfulness or falls are quite common and have to be prevented or dealt with. This paper introduces a platform to guide and assist these persons (mostly elderly people) by providing multisensory monitoring and intelligent assistance. The platform operates at three levels. The lower level, denominated ‘‘Data acquisition and processing’’performs the usual tasks of a monitoring system, collecting and processing data from the sensors for the purpose of detecting and tracking humans. The aim is to identify their activities in an intermediate level called ‘‘activity detection’’. The upper level, ‘‘Scheduling and decision-making’’, consists of a scheduler which provides warnings, schedules events in an intelligent manner and serves as an interface to the rest of the platform. The idea is to use mobile and static sensors performing constant monitoring of the user and his/her environment, providing a safe environment and an immediate response to severe problems. A case study on elderly fall detection in a nursery home bedroom demonstrates the usefulness of the proposal.

A brief survey on online analysis of movement data

The increasing availability of mobility data and the awareness of its importance and value have been motivating many researchers to the development of models and tools for analyzing movement data. This paper presents a brief survey of significant research works about modeling, processing and visualization of data about moving objects. We identified some key research fields that will provide better features for online analysis of movement data. As result of the literature review, we suggest a generic multi-layer architecture for the development of an online analysis processing software tool, which will be used for the definition of the future work of our team.

Histogram-based DNA analysis for the visualization of chromosome, genome and species information

We describe a novel approach to explore DNA nucleotide sequence data, aiming to produce high-level categorical and structural information about the underlying chromosomes, genomes and species. The article starts by analyzing chromosomal data through histograms using fixed length DNA sequences. After creating the DNA-related histograms, a correlation between pairs of histograms is computed, producing a global correlation matrix. These data are then used as input to several data processing methods for information extraction and tabular/graphical output generation. A set of 18 species is processed and the extensive results reveal that the proposed method is able to generate significant and diversified outputs, in good accordance with current scientific knowledge in domains such as genomics and phylogenetics.

Does Independent Component Analysis Play a Role in Unmixing Hyperspectral Data?

Chapter in Book Proceedings with Peer Review First Iberian Conference, IbPRIA 2003, Puerto de Andratx, Mallorca, Spain, JUne 4-6, 2003. Proceedings

Fractional dynamics and MDS visualization of earthquake phenomena

This paper analyses earthquake data in the perspective of dynamical systems and fractional calculus (FC). This new standpoint uses Multidimensional Scaling (MDS) as a powerful clustering and visualization tool. FC extends the concepts of integrals and derivatives to non-integer and complex orders. MDS is a technique that produces spatial or geometric representations of complex objects, such that those objects that are perceived to be similar in some sense are placed on the MDS maps forming clusters. In this study, over three million seismic occurrences, covering the period from January 1, 1904 up to March 14, 2012 are analysed. The events are characterized by their magnitude and spatiotemporal distributions and are divided into fifty groups, according to the Flinn–Engdahl (F–E) seismic regions of Earth. Several correlation indices are proposed to quantify the similarities among regions. MDS maps are proven as an intuitive and useful visual representation of the complex relationships that are present among seismic events, which may not be perceived on traditional geographic maps. Therefore, MDS constitutes a valid alternative to classic visualization tools for understanding the global behaviour of earthquakes.

Disseminating data using broadcast when topology is unknown

Consider the problem of disseminating data from an arbitrary source node to all other nodes in a distributed computer system, like Wireless Sensor Networks (WSNs). We assume that wireless broadcast is used and nodes do not know the topology. We propose new protocols which disseminate data faster and use fewer broadcasts than the simple broadcast protocol.