Aruneema Das

Big data integration shows Australian bush-fire frequency is increasing significantly.

Increasing Australian bush-fire frequencies over the last decade has indicated a major climatic change in coming future. Understanding such climatic change for Australian bush-fire is limited and there is an urgent need of scientific research, which is capable enough to contribute to Australian society. Frequency of bush-fire carries information on spatial, temporal and climatic aspects of bush-fire events and provides contextual information to model various climate data for accurately predicting future bush-fire hot spots. In this study, we develop an ensemble method based on a two-layered machine learning model to establish relationship between fire incidence and climatic data. In a 336 week data trial, we demonstrate that the model provides highly accurate bush-fire incidence hot-spot estimation (91% global accuracy) from the weekly climatic surfaces. Our analysis also indicates that Australian weekly bush-fire frequencies increased by 40% over the last 5 years, particularly during summer months, implicating a serious climatic shift.

Deep cognitive imaging systems enable estimation of continental-scale fire incidence from climate data

Unplanned fire is a major control on the nature of terrestrial ecosystems and causes substantial losses of life and property. Given the substantial influence of climatic conditions on fire incidence, climate change is expected to substantially change fire regimes in many parts of the world. We wished to determine whether it was possible to develop a deep neural network process for accurately estimating continental fire incidence from publicly available climate data. We show that deep recurrent Elman neural network was the best performed out of ten artificial neural networks (ANN) based cognitive imaging systems for determining the relationship between fire incidence and climate. In a decennium data experiment using this ANN we show that it is possible to develop highly accurate estimations of fire incidence from monthly climatic data surfaces. Our estimations for the continent of Australia had over 90% global accuracy and a very low level of false negatives. The technique is thus appropriate for use in estimating the spatial consequences of climate scenarios on the monthly incidence of wildfire at the landscape scale.

Mobile application based sustainable irrigation water usage decision support system: An intelligent sensor CLOUD approach

In this paper a novel data integration approach based on three environmental Sensors - Model Networks (including the Bureau of Meteorology-SILO database, Australian Cosmic Ray Sensor Network database (CosmOz), and Australian Water Availability Project (AWAP) database) has been proposed to estimate ground water balance and average water availability. An unsupervised machine learning based clustering technique (Dynamic Linear Discriminant Analysis (D-LDA)) has been applied for extracting knowledge from the large integrated database. The Commonwealth Scientific and Industrial Research Organisation (CSIRO) Sensor CLOUD computing infrastructure has been used extensively to process big data integration and the machine learning based decision support system. An analytical outcome from the Sensor CLOUD is presented as dynamic web based knowledge recommendation service using JSON file format. An intelligent ANDROID based mobile application has been developed, capable of automatically communicating with the Sensor CLOUD to get the most recent daily irrigation, water requirement for a chosen location and display the status in a user friendly traffic light system. This recommendation could be used directly by the farmers to make the final decision whether to buy extra water for irrigation or not on a particular day.

Detection of oil pollution in seawater: Biosecurity prevention using electronic nose technology

In this paper-conducting polymer gas sensor based AutoNose electronic nose (E-Nose) technology has been used for detection of oil contamination in seawater samples. AutoNose E-nose is a headspace analyzer based on six conducting polymer sensors. Seawater samples with known (or induced) oil contamination were tested and classified against the unpolluted seawater samples using machine learning based ensemble classifiers with very high accuracy. We show that a simple headspace sensing E-Nose could be used to rapidly detect oil pollution in seawater for early biosecurity prevention.

Estimation of physiological body parameters from smart garment data

A wearable smart garment containing embedded sensors produces live data stream like electrocardiograph, respiratory rate, tidal volume and body temperature. Additional vital body parameters are necessary to assess the physiological state of a person especially for athletes, firefighters, combat personnel etc. This work shows the development of a graphical user interface software application for estimation of parameters like metabolic rate, heart rate, heat stress index, core body temperature, sweat rate and heat strain following standard physiological equations. The smart garment and the software application can be used for remotely monitoring the health status of a person and taking necessary actions when required.

Autonomous Framework for Sensor Network Quality Annotation: Maximum Probability Clustering Approach

Abstract In this paper an autonomous feature clustering framework has been proposed for performance and reliability evaluation of an environmental sensor network. Environmental time series were statistically preprocessed to extract multiple semantic features. A novel hybrid clustering framework was designed based on Principal Component Analysis (PCA), Guided Self-Organizing Map (G-SOM), and Fuzzy-C-Means (FCM) to cluster the historical multi-feature space into probabilistic state classes. Finally a dynamic performance annotation mechanism was developed based on Maximum (Bayesian) Probability Rule (MPR) to quantify the performance of an individual sensor node and network. Based on the results from this framework, a “data quality knowledge map” was visualized to demonstrate the effectiveness of this framework.

Improved spirometric detection of small airway narrowing: concavity in the expiratory flow–volume curve in people aged over 40 years

Background and objective We have explored whether assessing the degree of concavity in the descending limb of the maximum expiratory flow–volume curve enhanced spirometric detection of early small airway disease. Methods We used spirometry records from 890 individuals aged ≥40 years (mean 59 years), recruited for the Burden of Obstructive Lung Disease Australia study. Central and peripheral concavity indices were developed from forced expired flows at 50% and 75% of the forced vital capacity, respectively, using an ideal line joining peak flow to zero flow. Results From the 268 subjects classified as normal never smokers, mean values for post-bronchodilator central concavity were 18.6% in males and 9.1% in females and those for peripheral concavity were 50.5% in males and 52.4% in females. There were moderately strong correlations between concavity and forced expired ratio (forced expiratory volume in 1 second/forced vital capacity) and mid-flow rate (forced expiratory flow between 25% and 75% of the FVC [FEF25%–75%]; r=−0.70 to −0.79). The additional number of individuals detected as abnormal using the concavity indices was substantial, especially compared with FEF25%–75%, where it was approximately doubled. Concavity was more specific for symptoms. Conclusion The inclusion of these concavity measures in the routine reports of spirometry would add information on small airway obstruction at no extra cost, time, or effort.

Farm biosecurity hot spots prediction using big data analytics

In this paper a novel application of salad leaf disease detection has been developed using a combination of big data analytics and on field multi-dimensional sensing. Heterogeneous knowledge integration from publicly available various big data sources, calibrated with in-situ ground truth information, has the merit to be a very efficient way to tackle large area wise farm biosecurity related issues and early disease or pest infestation prevention. We propose a cloud computing based intelligent big data analysis platform to predict farm hot spots with high probability of potential biosecurity threats and early monitoring system aiming to save the farm from significant economic damage.

Automated Estimation and Analysis of Lung Function Test Parameters from Spirometric Data for Respiratory Disease Diagnostics

Abstract A spirometer is used for basic lung function test for preliminary diagnosis of respiratory diseases. There are significant amount of calculations and graphical analysis required to transform the raw spirometric data into meaningful parameters. This parameters and graphs help the physicians in preliminary patient diagnosis for respiratory disorders like asthma, chronic obstructive pulmonary disease, etc. This study was undertaken for the development of a software system which can be used with any spirometric instrument to automate the calculations of pulmonary dead space volumes and analysis of raw data. The clinician can feed the raw data from patient testing into the easy to use graphical user interface of the software which will be analyzed instantly and all the parameters, regression slopes, shape analysis plots and the results will be displayed graphically. The estimation of the vital parameters and regression slopes are based on standard protocols and equations. This system will eliminate presently practiced time consuming manual calculations and graphical analysis; will have increased precision, be considerably faster and more versatile.

Notice of Removal Upper arm rehabilitation for stroke patients using computer controlled functional electrical stimulation and motion sensors - Withdrawn

Withdrawn.