A comparison of classification algorithms within the Classifynder pollen imaging system

We describe an investigation into how Massey University's Pollen Classifynder can accelerate the understanding of pollen and its role in nature. The Classifynder is an imaging microscopy system that can locate, image and classify slide based pollen samples. Given the laboriousness of purely manual image acquisition and identification it is vital to exploit assistive technologies like the Classifynder to enable acquisition and analysis of pollen samples. It is also vital that we understand the strengths and limitations of automated systems so that they can be used (and improved) to compliment the strengths and weaknesses of human analysts to the greatest extent possible. This article reviews some of our experiences with the Classifynder system and our exploration of alternative classifier models to enhance both accuracy and interpretability. Our experiments in the pollen analysis problem domain have been based on samples from the Australian National University's pollen reference collection (2890 grains, 15 species) and images bundled with the Classifynder system (400 grains, 4 species). These samples have been represented using the Classifynder image feature set. In addition to the Classifynder's native neural network classifier, we have evaluated linear discriminant, support vector machine, decision tree and random forest classifiers on these data with encouraging results. Our hope is that our findings will help enhance the performance of future releases of the Classifynder and other systems for accelerating the acquisition and analysis of pollen samples. © 2013 AIP Publishing LLC.

An evaluation of the neocognitron

We describe a sequence of experiments investigating the strengths and limitations of Fukushima's neocognitron as a handwritten digit classifier. Using the results of these experiments as a foundation, we propose and evaluate improvements to Fukushima's original network in an effort to obtain higher recognition performance. The neocognitron's performance is shown to be strongly dependent on the choice of selectivity parameters and we present two methods to adjust these variables. Performance of the network under the more effective of the two new selectivity adjustment techniques suggests that the network fails to exploit the features that distinguish different classes of input data. To avoid this shortcoming, the network's final layer cells were replaced by a nonlinear classifier (a multilayer perceptron) to create a hybrid architecture. Tests of Fukushima's original system and the novel systems proposed in this paper suggest that it may be difficult for the neocognitron to achieve the performance of existing digit classifiers due to its reliance upon the supervisor's choice of selectivity parameters and training data. These findings pertain to Fukushima's implementation of the system and should not be seen as diminishing the practical significance of the concept of hierarchical feature extraction embodied in the neocognitron. © 1997 IEEE.

Degradation of hydroxycinnamic acid mixtures in aqueous sucrose solutions by the Fenton process

The degradation efficiencies and behaviors of caffeic acid (CaA), p-coumaric acid (pCoA) and ferulic acid (FeA) in aqueous sucrose solutions containing the mixture of these hydroxycinnamic acids (HCAs) mixtures were studied by the Fenton oxidation process. Central composite design and multi-response surface methodology were used to evaluate and optimize the interactive effects of process parameters. Four quadratic polynomial models were developed for the degradation of each individual acid in the mixture and the total HCAs degraded. Sucrose was the most influential parameter that significantly affected the total amount of HCA degraded. Under the conditions studied there was < 0.01% loss of sucrose in all reactions. The optimal values of the process parameters for a 200 mg/L HCA mixture in water (pH 4.73, 25.15 °C) and sucrose solution (13 mass%, pH 5.39, 35.98 °C) were 77% and 57% respectively. Regression analysis showed goodness of fit between the experimental results and the predicted values. The degradation behavior of CaA differed from those of pCoA and FeA, where further CaA degradation is observed at increasing sucrose and decreasing solution pH. The differences (established using UV/Vis and ATR-FTIR spectroscopy) were because, unlike the other acids, CaA formed a complex with Fe(III) or with Fe(III) hydrogen-bonded to sucrose, and coprecipitated with lepidocrocite, an iron oxyhydroxide.

Automatic UAV forced landing site detection using machine learning

The commercialization of aerial image processing is highly dependent on the platforms such as UAVs (Unmanned Aerial Vehicles). However, the lack of an automated UAV forced landing site detection system has been identified as one of the main impediments to allow UAV flight over populated areas in civilian airspace. This article proposes a UAV forced landing site detection system that is based on machine learning approaches including the Gaussian Mixture Model and the Support Vector Machine. A range of learning parameters are analysed including the number of Guassian mixtures, support vector kernels including linear, radial basis function Kernel (RBF) and polynormial kernel (poly), and the order of RBF kernel and polynormial kernel. Moreover, a modified footprint operator is employed during feature extraction to better describe the geometric characteristics of the local area surrounding a pixel. The performance of the presented system is compared to a baseline UAV forced landing site detection system which uses edge features and an Artificial Neural Network (ANN) region type classifier. Experiments conducted on aerial image datasets captured over typical urban environments reveal improved landing site detection can be achieved with an SVM classifier with an RBF kernel using a combination of colour and texture features. Compared to the baseline system, the proposed system provides significant improvement in term of the chance to detect a safe landing area, and the performance is more stable than the baseline in the presence of changes to the UAV altitude.

Real-time assessment of GNSS observation noise with single receivers

Stochastic modelling is critical in GNSS data processing. Currently, GNSS data processing commonly relies on the empirical stochastic model which may not reflect the actual data quality or noise characteristics. This paper examines the real-time GNSS observation noise estimation methods enabling to determine the observation variance from single receiver data stream. The methods involve three steps: forming linear combination, handling the ionosphere and ambiguity bias and variance estimation. Two distinguished ways are applied to overcome the ionosphere and ambiguity biases, known as the time differenced method and polynomial prediction method respectively. The real time variance estimation methods are compared with the zero-baseline and short-baseline methods. The proposed method only requires single receiver observation, thus applicable to both differenced and un-differenced data processing modes. However, the methods may be subject to the normal ionosphere conditions and low autocorrelation GNSS receivers. Experimental results also indicate the proposed method can result on more realistic parameter precision.

Numerical algorithms for time-fractional subdiffusion equation with second-order accuracy

This article aims to fill in the gap of the second-order accurate schemes for the time-fractional subdiffusion equation with unconditional stability. Two fully discrete schemes are first proposed for the time-fractional subdiffusion equation with space discretized by finite element and time discretized by the fractional linear multistep methods. These two methods are unconditionally stable with maximum global convergence order of $O(\tau+h^{r+1})$ in the $L^2$ norm, where $\tau$ and $h$ are the step sizes in time and space, respectively, and $r$ is the degree of the piecewise polynomial space. The average convergence rates for the two methods in time are also investigated, which shows that the average convergence rates of the two methods are $O(\tau^{1.5}+h^{r+1})$. Furthermore, two improved algorithms are constrcted, they are also unconditionally stable and convergent of order $O(\tau^2+h^{r+1})$. Numerical examples are provided to verify the theoretical analysis. The comparisons between the present algorithms and the existing ones are included, which show that our numerical algorithms exhibit better performances than the known ones.

Text mining for screening efficiency? Testing within a Cochrane public health review

Background The requirement for dual screening of titles and abstracts to select papers to examine in full text can create a huge workload, not least when the topic is complex and a broad search strategy is required, resulting in a large number of results. An automated system to reduce this burden, while still assuring high accuracy, has the potential to provide huge efficiency savings within the review process. Objectives To undertake a direct comparison of manual screening with a semi‐automated process (priority screening) using a machine classifier. The research is being carried out as part of the current update of a population‐level public health review. Methods Authors have hand selected studies for the review update, in duplicate, using the standard Cochrane Handbook methodology. A retrospective analysis, simulating a quasi‐‘active learning’ process (whereby a classifier is repeatedly trained based on ‘manually’ labelled data) will be completed, using different starting parameters. Tests will be carried out to see how far different training sets, and the size of the training set, affect the classification performance; i.e. what percentage of papers would need to be manually screened to locate 100% of those papers included as a result of the traditional manual method. Results From a search retrieval set of 9555 papers, authors excluded 9494 papers at title/abstract and 52 at full text, leaving 9 papers for inclusion in the review update. The ability of the machine classifier to reduce the percentage of papers that need to be manually screened to identify all the included studies, under different training conditions, will be reported. Conclusions The findings of this study will be presented along with an estimate of any efficiency gains for the author team if the screening process can be semi‐automated using text mining methodology, along with a discussion of the implications for text mining in screening papers within complex health reviews.

Analytical study of implementation issues of NTRU

Nth-Dimensional Truncated Polynomial Ring (NTRU) is a lattice-based public-key cryptosystem that offers encryption and digital signature solutions. It was designed by Silverman, Hoffstein and Pipher. The NTRU cryptosystem was patented by NTRU Cryptosystems Inc. (which was later acquired by Security Innovations) and available as IEEE 1363.1 and X9.98 standards. NTRU is resistant to attacks based on Quantum computing, to which the standard RSA and ECC public-key cryptosystems are vulnerable to. In addition, NTRU has higher performance advantages over these cryptosystems. Considering this importance of NTRU, it is highly recommended to adopt NTRU as part of a cipher suite along with widely used cryptosystems for internet security protocols and applications. In this paper, we present our analytical study on the implementation of NTRU encryption scheme which serves as a guideline for security practitioners who are novice to lattice-based cryptography or even cryptography. In particular, we show some non-trivial issues that should be considered towards a secure and efficient NTRU implementation.

Centroid training to achieve effective text classification

Traditional text classification technology based on machine learning and data mining techniques has made a big progress. However, it is still a big problem on how to draw an exact decision boundary between relevant and irrelevant objects in binary classification due to much uncertainty produced in the process of the traditional algorithms. The proposed model CTTC (Centroid Training for Text Classification) aims to build an uncertainty boundary to absorb as many indeterminate objects as possible so as to elevate the certainty of the relevant and irrelevant groups through the centroid clustering and training process. The clustering starts from the two training subsets labelled as relevant or irrelevant respectively to create two principal centroid vectors by which all the training samples are further separated into three groups: POS, NEG and BND, with all the indeterminate objects absorbed into the uncertain decision boundary BND. Two pairs of centroid vectors are proposed to be trained and optimized through the subsequent iterative multi-learning process, all of which are proposed to collaboratively help predict the polarities of the incoming objects thereafter. For the assessment of the proposed model, F1 and Accuracy have been chosen as the key evaluation measures. We stress the F1 measure because it can display the overall performance improvement of the final classifier better than Accuracy. A large number of experiments have been completed using the proposed model on the Reuters Corpus Volume 1 (RCV1) which is important standard dataset in the field. The experiment results show that the proposed model has significantly improved the binary text classification performance in both F1 and Accuracy compared with three other influential baseline models.

From ImageNet to mining: Adapting visual object detection with minimal supervision

This paper presents visual detection and classification of light vehicles and personnel on a mine site.We capitalise on the rapid advances of ConvNet based object recognition but highlight that a naive black box approach results in a significant number of false positives. In particular, the lack of domain specific training data and the unique landscape in a mine site causes a high rate of errors. We exploit the abundance of background-only images to train a k-means classifier to complement the ConvNet. Furthermore, localisation of objects of interest and a reduction in computation is enabled through region proposals. Our system is tested on over 10km of real mine site data and we were able to detect both light vehicles and personnel. We show that the introduction of our background model can reduce the false positive rate by an order of magnitude.

Customer agility, smart shopping apps and their implications: Customer relationship management systems in the digital age

This thesis examines the complementarities and vulnerabilities of customer connectivity that contemporary firms achieved through ubiquitous digital technologies. Taking the example of deployment of smart shopping apps to connect with consumers in the context of Australian retail, the study examines how such customer connectivity positively influences firm performances through firm's customer agility whilst creating implications for firms' digital business strategy through altered customer cognitions. Employing Oliver's (1977) Expectation Confirmation Theory, this study empirically tests a conceptual model involving digital connectivity, digital expectations, experiences and satisfaction of the customers who uses smart shopping apps in Australian consumer retail.

Spine curvature analysis between participants with obesity and normal weight participants: A biplanar electromagnetic device measurement

To analyse and compare standing thoracolumbar curves in normal weight participants and participants with obesity, using an electromagnetic device, and to analyse the measurement reliability. Material and Methods. Cross-sectional study was carried out. 36 individuals were divided into two groups (normal-weight and participants with obesity) according to their waist circumference. The reference points (T1–T8–L1–L5 and both posterior superior iliac spines) were used to perform a description of thoracolumbar curvature in the sagittal and coronal planes. A transformation from the global coordinate system was performed and thoracolumbar curves were adjusted by fifth-order polynomial equations. The tangents of the first and fifth lumbar vertebrae and the first thoracic vertebra were determined from their derivatives. The reliability of the measurement was assessed according to the internal consistency of the measure and the thoracolumbar curvature angles were compared between groups. Results. Cronbach’s alpha values ranged between 0.824 (95% CI: 0.776–0.847) and 0.918 (95% CI: 0.903–0.949). In the coronal plane, no significant differences were found between groups; however, in sagittal plane, significant differences were observed for thoracic kyphosis. Conclusion. There were significant differences in thoracic kyphosis in the sagittal plane between two groups of young adults grouped according to their waist circumference.

Stochastic analysis of a radial-inflow turbine in the presence of parametric uncertainties

This paper presents an uncertainty quantification study of the performance analysis of the high pressure ratio single stage radial-inflow turbine used in the Sundstrand Power Systems T-100 Multi-purpose Small Power Unit. A deterministic 3D volume-averaged Computational Fluid Dynamics (CFD) solver is coupled with a non-statistical generalized Polynomial Chaos (gPC) representation based on a pseudo-spectral projection method. One of the advantages of this approach is that it does not require any modification of the CFD code for the propagation of random disturbances in the aerodynamic and geometric fields. The stochastic results highlight the importance of the blade thickness and trailing edge tip radius on the total-to-static efficiency of the turbine compared to the angular velocity and trailing edge tip length. From a theoretical point of view, the use of the gPC representation on an arbitrary grid also allows the investigation of the sensitivity of the blade thickness profiles on the turbine efficiency. The gPC approach is also applied to coupled random parameters. The results show that the most influential coupled random variables are trailing edge tip radius coupled with the angular velocity.

Robotic detection and tracking of Crown-Of-Thorns starfish

This paper presents a novel vision-based underwater robotic system for the identification and control of Crown-Of-Thorns starfish (COTS) in coral reef environments. COTS have been identified as one of the most significant threats to Australia's Great Barrier Reef. These starfish literally eat coral, impacting large areas of reef and the marine ecosystem that depends on it. Evidence has suggested that land-based nutrient runoff has accelerated recent outbreaks of COTS requiring extensive use of divers to manually inject biological agents into the starfish in an attempt to control population numbers. Facilitating this control program using robotics is the goal of our research. In this paper we introduce a vision-based COTS detection and tracking system based on a Random Forest Classifier (RFC) trained on images from underwater footage. To track COTS with a moving camera, we embed the RFC in a particle filter detector and tracker where the predicted class probability of the RFC is used as an observation probability to weight the particles, and we use a sparse optical flow estimation for the prediction step of the filter. The system is experimentally evaluated in a realistic laboratory setup using a robotic arm that moves a camera at different speeds and heights over a range of real-size images of COTS in a reef environment.

Similarity-based birdcall retrieval from environmental audio

Automated digital recordings are useful for large-scale temporal and spatial environmental monitoring. An important research effort has been the automated classification of calling bird species. In this paper we examine a related task, retrieval of birdcalls from a database of audio recordings, similar to a user supplied query call. Such a retrieval task can sometimes be more useful than an automated classifier. We compare three approaches to similarity-based birdcall retrieval using spectral ridge features and two kinds of gradient features, structure tensor and the histogram of oriented gradients. The retrieval accuracy of our spectral ridge method is 94% compared to 82% for the structure tensor method and 90% for the histogram of gradients method. Additionally, this approach potentially offers a more compact representation and is more computationally efficient.