Development of gas sensing technology for ground and airborne applications powered by solar energy : methodology and experimental results

Monitoring gases for environmental, industrial and agricultural fields is a demanding task that requires long periods of observation, large quantity of sensors, data management, high temporal and spatial resolution, long term stability, recalibration procedures, computational resources, and energy availability. Wireless Sensor Networks (WSNs) and Unmanned Aerial Vehicles (UAVs) are currently representing the best alternative to monitor large, remote, and difficult access areas, as these technologies have the possibility of carrying specialised gas sensing systems, and offer the possibility of geo-located and time stamp samples. However, these technologies are not fully functional for scientific and commercial applications as their development and availability is limited by a number of factors: the cost of sensors required to cover large areas, their stability over long periods, their power consumption, and the weight of the system to be used on small UAVs. Energy availability is a serious challenge when WSN are deployed in remote areas with difficult access to the grid, while small UAVs are limited by the energy in their reservoir tank or batteries. Another important challenge is the management of data produced by the sensor nodes, requiring large amount of resources to be stored, analysed and displayed after long periods of operation. In response to these challenges, this research proposes the following solutions aiming to improve the availability and development of these technologies for gas sensing monitoring: first, the integration of WSNs and UAVs for environmental gas sensing in order to monitor large volumes at ground and aerial levels with a minimum of sensor nodes for an effective 3D monitoring; second, the use of solar energy as a main power source to allow continuous monitoring; and lastly, the creation of a data management platform to store, analyse and share the information with operators and external users. The principal outcomes of this research are the creation of a gas sensing system suitable for monitoring any kind of gas, which has been installed and tested on CH4 and CO2 in a sensor network (WSN) and on a UAV. The use of the same gas sensing system in a WSN and a UAV reduces significantly the complexity and cost of the application as it allows: a) the standardisation of the signal acquisition and data processing, thereby reducing the required computational resources; b) the standardisation of calibration and operational procedures, reducing systematic errors and complexity; c) the reduction of the weight and energy consumption, leading to an improved power management and weight balance in the case of UAVs; d) the simplification of the sensor node architecture, which is easily replicated in all the nodes. I evaluated two different sensor modules by laboratory, bench, and field tests: a non-dispersive infrared module (NDIR) and a metal-oxide resistive nano-sensor module (MOX nano-sensor). The tests revealed advantages and disadvantages of the two modules when used for static nodes at the ground level and mobile nodes on-board a UAV. Commercial NDIR modules for CO2 have been successfully tested and evaluated in the WSN and on board of the UAV. Their advantage is the precision and stability, but their application is limited to a few gases. The advantages of the MOX nano-sensors are the small size, low weight, low power consumption and their sensitivity to a broad range of gases. However, selectivity is still a concern that needs to be addressed with further studies. An electronic board to interface sensors in a large range of resistivity was successfully designed, created and adapted to operate on ground nodes and on-board UAV. The WSN and UAV created were powered with solar energy in order to facilitate outdoor deployment, data collection and continuous monitoring over large and remote volumes. The gas sensing, solar power, transmission and data management systems of the WSN and UAV were fully evaluated by laboratory, bench and field testing. The methodology created to design, developed, integrate and test these systems was extensively described and experimentally validated. The sampling and transmission capabilities of the WSN and UAV were successfully tested in an emulated mission involving the detection and measurement of CO2 concentrations in a field coming from a contaminant source; the data collected during the mission was transmitted in real time to a central node for data analysis and 3D mapping of the target gas. The major outcome of this research is the accomplishment of the first flight mission, never reported before in the literature, of a solar powered UAV equipped with a CO2 sensing system in conjunction with a network of ground sensor nodes for an effective 3D monitoring of the target gas. A data management platform was created using an external internet server, which manages, stores, and shares the data collected in two web pages, showing statistics and static graph images for internal and external users as requested. The system was bench tested with real data produced by the sensor nodes and the architecture of the platform was widely described and illustrated in order to provide guidance and support on how to replicate the system. In conclusion, the overall results of the project provide guidance on how to create a gas sensing system integrating WSNs and UAVs, how to power the system with solar energy and manage the data produced by the sensor nodes. This system can be used in a wide range of outdoor applications, especially in agriculture, bushfires, mining studies, zoology, and botanical studies opening the way to an ubiquitous low cost environmental monitoring, which may help to decrease our carbon footprint and to improve the health of the planet.

Application of a hybrid Entropy–McKinsey Matrix method in evaluating sustainable urbanization : a China case study

Although urbanization can promote social and economic development, it can also cause various problems. As the key decision makers of urbanization, local governments should be able to evaluate urbanization performance, summarize experiences, and find problems caused by urbanization. This paper introduces a hybrid Entropy–McKinsey Matrix method for evaluating sustainable urbanization. The McKinsey Matrix is commonly referred to as the GE Matrix. The values of a development index (DI) and coordination index (CI) are calculated by employing the Entropy method and are used as a basis for constructing a GE Matrix. The matrix can assist in assessing sustainable urbanization performance by locating the urbanization state point. A case study of the city of Jinan in China demonstrates the process of using the evaluation method. The case study reveals that the method is an effective tool in helping policy makers understand the performance of urban sustainability and therefore formulate suitable strategies for guiding urbanization toward better sustainability.

Simultaneous localization and planning on multiple map hypotheses

This paper presents a novel method to rank map hypotheses by the quality of localization they afford. The highest ranked hypothesis at any moment becomes the active representation that is used to guide the robot to its goal location. A single static representation is insufficient for navigation in dynamic environments where paths can be blocked periodically, a common scenario which poses significant challenges for typical planners. In our approach we simultaneously rank multiple map hypotheses by the influence that localization in each of them has on locally accurate odometry. This is done online for the current locally accurate window by formulating a factor graph of odometry relaxed by localization constraints. Comparison of the resulting perturbed odometry of each hypothesis with the original odometry yields a score that can be used to rank map hypotheses by their utility. We deploy the proposed approach on a real robot navigating a structurally noisy office environment. The configuration of the environment is physically altered outside the robots sensory horizon during navigation tasks to demonstrate the proposed approach of hypothesis selection.

Automated diagnosis of Age-related Macular Degeneration using greyscale features from digital fundus images

Age-related Macular Degeneration (AMD) is one of the major causes of vision loss and blindness in ageing population. Currently, there is no cure for AMD, however early detection and subsequent treatment may prevent the severe vision loss or slow the progression of the disease. AMD can be classified into two types: dry and wet AMDs. The people with macular degeneration are mostly affected by dry AMD. Early symptoms of AMD are formation of drusen and yellow pigmentation. These lesions are identified by manual inspection of fundus images by the ophthalmologists. It is a time consuming, tiresome process, and hence an automated diagnosis of AMD screening tool can aid clinicians in their diagnosis significantly. This study proposes an automated dry AMD detection system using various entropies (Shannon, Kapur, Renyi and Yager), Higher Order Spectra (HOS) bispectra features, Fractional Dimension (FD), and Gabor wavelet features extracted from greyscale fundus images. The features are ranked using t-test, Kullback–Lieber Divergence (KLD), Chernoff Bound and Bhattacharyya Distance (CBBD), Receiver Operating Characteristics (ROC) curve-based and Wilcoxon ranking methods in order to select optimum features and classified into normal and AMD classes using Naive Bayes (NB), k-Nearest Neighbour (k-NN), Probabilistic Neural Network (PNN), Decision Tree (DT) and Support Vector Machine (SVM) classifiers. The performance of the proposed system is evaluated using private (Kasturba Medical Hospital, Manipal, India), Automated Retinal Image Analysis (ARIA) and STructured Analysis of the Retina (STARE) datasets. The proposed system yielded the highest average classification accuracies of 90.19%, 95.07% and 95% with 42, 54 and 38 optimal ranked features using SVM classifier for private, ARIA and STARE datasets respectively. This automated AMD detection system can be used for mass fundus image screening and aid clinicians by making better use of their expertise on selected images that require further examination.

Decision support system for age-related macular degeneration using discrete wavelet transform

Age-related macular degeneration (AMD) affects the central vision and subsequently may lead to visual loss in people over 60 years of age. There is no permanent cure for AMD, but early detection and successive treatment may improve the visual acuity. AMD is mainly classified into dry and wet type; however, dry AMD is more common in aging population. AMD is characterized by drusen, yellow pigmentation, and neovascularization. These lesions are examined through visual inspection of retinal fundus images by ophthalmologists. It is laborious, time-consuming, and resource-intensive. Hence, in this study, we have proposed an automated AMD detection system using discrete wavelet transform (DWT) and feature ranking strategies. The first four-order statistical moments (mean, variance, skewness, and kurtosis), energy, entropy, and Gini index-based features are extracted from DWT coefficients. We have used five (t test, Kullback–Lieber Divergence (KLD), Chernoff Bound and Bhattacharyya Distance, receiver operating characteristics curve-based, and Wilcoxon) feature ranking strategies to identify optimal feature set. A set of supervised classifiers namely support vector machine (SVM), decision tree, k -nearest neighbor ( k -NN), Naive Bayes, and probabilistic neural network were used to evaluate the highest performance measure using minimum number of features in classifying normal and dry AMD classes. The proposed framework obtained an average accuracy of 93.70 %, sensitivity of 91.11 %, and specificity of 96.30 % using KLD ranking and SVM classifier. We have also formulated an AMD Risk Index using selected features to classify the normal and dry AMD classes using one number. The proposed system can be used to assist the clinicians and also for mass AMD screening programs.

The use of penumbrae to define and analyse non-standard fields

Aim A new method of penumbral analysis is implemented which allows an unambiguous determination of field size and penumbra size and quality for small fields and other non-standard fields. Both source occlusion and lateral electronic disequilibrium will affect the size and shape of cross-axis profile penumbrae; each is examined in detail. Method A new method of penumbral analysis is implemented where the square of the derivative of the cross-axis profile is plotted. The resultant graph displays two peaks in the place of the two penumbrae. This allows a strong visualisation of the quality of a field penumbra, as well as a mathematically consistent method of determining field size (distance between the two peak’s maxima), and penumbra (full-widthtenth-maximum of peak). Cross-axis profiles were simulated in a water phantom at a depth of 5 cm using Monte Carlo modelling, for field sizes between 5 and 30 mm. The field size and penumbra size of each field was calculated using the method above, as well as traditional definitions set out in IEC976. The effect of source occlusion and lateral electronic disequilibrium on the penumbrae was isolated by repeating the simulations removing electron transport and using an electron spot size of 0 mm, respectively. Results All field sizes calculated using the traditional and proposed methods agreed within 0.2 mm. The penumbra size measured using the proposed method was systematically 1.8 mm larger than the traditional method at all field sizes. The size of the source had a larger effect on the size of the penumbra than did lateral electronic disequilibrium, particularly at very small field sizes. Conclusion Traditional methods of calculating field size and penumbra are proved to be mathematically adequate for small fields. However, the field size definition proposed in this study would be more robust amongst other nonstandard fields, such as flattening filter free. Source occlusion plays a bigger role than lateral electronic disequilibrium in small field penumbra size.

Detection of rain in acoustic recordings of the environment

Environmental monitoring has become increasingly important due to the significant impact of human activities and climate change on biodiversity. Environmental sound sources such as rain and insect vocalizations are a rich and underexploited source of information in environmental audio recordings. This paper is concerned with the classification of rain within acoustic sensor re-cordings. We present the novel application of a set of features for classifying environmental acoustics: acoustic entropy, the acoustic complexity index, spectral cover, and background noise. In order to improve the performance of the rain classification system we automatically classify segments of environmental recordings into the classes of heavy rain or non-rain. A decision tree classifier is experientially compared with other classifiers. The experimental results show that our system is effective in classifying segments of environmental audio recordings with an accuracy of 93% for the binary classification of heavy rain/non-rain.

A convolutional neural network for automatic analysis of aerial imagery

This paper introduces a new method to automate the detection of marine species in aerial imagery using a Machine Learning approach. Our proposed system has at its core, a convolutional neural network. We compare this trainable classifier to a handcrafted classifier based on color features, entropy and shape analysis. Experiments demonstrate that the convolutional neural network outperforms the handcrafted solution. We also introduce a negative training example-selection method for situations where the original training set consists of a collection of labeled images in which the objects of interest (positive examples) have been marked by a bounding box. We show that picking random rectangles from the background is not necessarily the best way to generate useful negative examples with respect to learning.

Large-scale analysis of soccer matches using spatiotemporal tracking data

Although the collection of player and ball tracking data is fast becoming the norm in professional sports, large-scale mining of such spatiotemporal data has yet to surface. In this paper, given an entire season's worth of player and ball tracking data from a professional soccer league (approx 400,000,000 data points), we present a method which can conduct both individual player and team analysis. Due to the dynamic, continuous and multi-player nature of team sports like soccer, a major issue is aligning player positions over time. We present a "role-based" representation that dynamically updates each player's relative role at each frame and demonstrate how this captures the short-term context to enable both individual player and team analysis. We discover role directly from data by utilizing a minimum entropy data partitioning method and show how this can be used to accurately detect and visualize formations, as well as analyze individual player behavior.

Identifying team style in soccer using formations learned from spatiotemporal tracking data

To the trained-eye, experts can often identify a team based on their unique style of play due to their movement, passing and interactions. In this paper, we present a method which can accurately determine the identity of a team from spatiotemporal player tracking data. We do this by utilizing a formation descriptor which is found by minimizing the entropy of role-specific occupancy maps. We show how our approach is significantly better at identifying different teams compared to standard measures (i.e., shots, passes etc.). We demonstrate the utility of our approach using an entire season of Prozone player tracking data from a top-tier professional soccer league.

On-line estimation of Allan variance parameters

A new online method is presented for estimation of the angular random walk and rate random walk coefficients of IMU (inertial measurement unit) gyros and accelerometers. The online method proposes a state space model and proposes parameter estimators for quantities previously measured from off-line data techniques such as the Allan variance graph. Allan variance graphs have large off-line computational effort and data storage requirements. The technique proposed here requires no data storage and computational effort of O(100) calculations per data sample.

Anomaly detection in online social networks : using data-mining techniques and fuzzy logic

This research is a step forward in improving the accuracy of detecting anomaly in a data graph representing connectivity between people in an online social network. The proposed hybrid methods are based on fuzzy machine learning techniques utilising different types of structural input features. The methods are presented within a multi-layered framework which provides the full requirements needed for finding anomalies in data graphs generated from online social networks, including data modelling and analysis, labelling, and evaluation.

Dispatch strategy of PHEVs to mitigate selected patterns of seasonally varying outputs from renewable generation

Rapid development of plug-in hybrid electric vehicles (PHEVs) brings new challenges and opportunities to the power industry. A large number of idle PHEVs can potentially be employed to form a distributed energy storage system for supporting renewable generation. To reduce the negative effects of unsteady renewable generation outputs, a stochastic optimization-based dispatch model capable of handling uncertain outputs of PHEVs and renewable generation is formulated in this paper. The mathematical expectations, second-order original moments, and variances of wind and photovoltaic (PV) generation outputs are derived analytically. Incorporated all the derived uncertainties, a novel generation shifting objective is proposed. The cross-entropy (CE) method is employed to solve this optimal dispatch model. Multiple patterns of renewable generation depending on seasons and renewable market shares are investigated. The feasibility and efficiency of the developed optimal dispatch model, as well as the CE method, are demonstrated with a 33-node distribution system.

Comparative studies made simple in GPFlow

This work describes recent extensions to the GPFlow scientific workflow system in development at MQUTeR (www.mquter.qut.edu.au), which facilitate interactive experimentation, automatic lifting of computations from single-case to collection-oriented computation and automatic correlation and synthesis of collections. A GPFlow workflow presents as an acyclic data flow graph, yet provides powerful iteration and collection formation capabilities.

Short-data recursive HMM parameter estimation for rapid vision-based aircraft heading estimation

Rapid recursive estimation of hidden Markov Model (HMM) parameters is important in applications that place an emphasis on the early availability of reasonable estimates (e.g. for change detection) rather than the provision of longer-term asymptotic properties (such as convergence, convergence rate, and consistency). In the context of vision- based aircraft (image-plane) heading estimation, this paper suggests and evaluates the short-data estimation properties of 3 recursive HMM parameter estimation techniques (a recursive maximum likelihood estimator, an online EM HMM estimator, and a relative entropy based estimator). On both simulated and real data, our studies illustrate the feasibility of rapid recursive heading estimation, but also demonstrate the need for careful step-size design of HMM recursive estimation techniques when these techniques are intended for use in applications where short-data behaviour is paramount.