Pollen image classification using the classifynder system: Algorithm comparison and a case study on New Zealand honey

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 (2,890 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.We additionally work through a real world case study where we assess the ability of the system to determine the pollen make-up of samples of New Zealand honey. 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.

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.

Classification of inventory data suit for managing Australian railway bridges

With a focus to optimising the life cycle performance of Australian Railway bridges, new bridge classification and environmental classification systems are proposed. The new bridge classification system is mainly to facilitate the implementation of novel Bridge Management System (BMS) which optimise the life cycle cost both at project level and network level while environment classification is mainly to improve accuracy of Remaining Service Potential (RSP) module of the proposed BMS. In fact, limited capacity of the existing BMS to trigger the maintenance intervention point is an indirect result of inadequacies of the existing bridge and environmental classification systems. The proposed bridge classification system permits to identify the intervention points based on percentage deterioration of individual elements and maintenance cost, while allowing performance based rating technique to implement for maintenance optimisation and prioritisation. Simultaneously, the proposed environment classification system will enhance the accuracy of prediction of deterioration of steel components.

A strain-based failure criterion for pillar stability analysis

Strain-based failure criteria have several advantages over stress-based failure criteria: they can account for elastic and inelastic strains, they utilise direct, observables effects instead of inferred effects (strain gauges vs. stress estimates), and model complete stress-strain curves including pre-peak, non-linear elasticity and post-peak strain weakening. In this study, a strain-based failure criterion derived from thermodynamic first principles utilising the concepts of continuum damage mechanics is presented. Furthermore, implementation of this failure criterion into a finite-element simulation is demonstrated and applied to the stability of underground mining coal pillars. In numerical studies, pillar strength is usually expressed in terms of critical stresses or stress-based failure criteria where scaling with pillar width and height is common. Previous publications have employed the finite-element method for pillar stability analysis using stress-based failure criterion such as Mohr-Coulomb and Hoek-Brown or stress-based scalar damage models. A novel constitutive material model, which takes into consideration anisotropy as well as elastic strain and damage as state variables has been developed and is presented in this paper. The damage threshold and its evolution are strain-controlled, and coupling of the state variables is achieved through the damage-induced degradation of the elasticity tensor. This material model is implemented into the finite-element software ABAQUS and can be applied to 3D problems. Initial results show that this new material model is capable of describing the non-linear behaviour of geomaterials commonly observed before peak strength is reached as well as post-peak strain softening. Furthermore, it is demonstrated that the model can account for directional dependency of failure behaviour (i.e. anisotropy) and has the potential to be expanded to environmental controls like temperature or moisture.

Fine-grained plant classification using convolutional neural networks for feature extraction

We present an overview of the QUT plant classification system submitted to LifeCLEF 2014. This system uses generic features extracted from a convolutional neural network previously used to perform general object classification. We examine the effectiveness of these features to perform plant classification when used in combination with an extremely randomised forest. Using this system, with minimal tuning, we obtained relatively good results with a score of 0:249 on the test set of LifeCLEF 2014.

Injury narrative text classification using factorization model

Narrative text is a useful way of identifying injury circumstances from the routine emergency department data collections. Automatically classifying narratives based on machine learning techniques is a promising technique, which can consequently reduce the tedious manual classification process. Existing works focus on using Naive Bayes which does not always offer the best performance. This paper proposes the Matrix Factorization approaches along with a learning enhancement process for this task. The results are compared with the performance of various other classification approaches. The impact on the classification results from the parameters setting during the classification of a medical text dataset is discussed. With the selection of right dimension k, Non Negative Matrix Factorization-model method achieves 10 CV accuracy of 0.93.

Decision boundary setting and classifier combination for text classification

This thesis presents a promising boundary setting method for solving challenging issues in text classification to produce an effective text classifier. A classifier must identify boundary between classes optimally. However, after the features are selected, the boundary is still unclear with regard to mixed positive and negative documents. A classifier combination method to boost effectiveness of the classification model is also presented. The experiments carried out in the study demonstrate that the proposed classifier is promising.

Classification of activities of daily living of individual with limb loss

The monitoring of the actual activities of daily living of individuals with lower limb amputation is essential for an evidence-based fitting of the prosthesis, more particularly the choice of components (e.g., knees, ankles, feet)[1-4]. The purpose of this presentation was to give an overview of the categorization of the load regime data to assess the functional output and usage of the prosthesis of lower limb amputees has presented in several publications[5, 6]. The objectives were to present a categorization of load regime and to report the results for a case.

Performance dispersion for evidence-based classification of stationary throwers

Background There is a need for better understanding of the dispersion of classification-related variable to develop an evidence-based classification of athletes with a disability participating in stationary throwing events. Objectives The purposes of this study are (A) to describe tools designed to comprehend and represent the dispersion of the performance between successive classes, and (B) to present this dispersion for the elite male and female stationary shot-putters who participated in Beijing 2008 Paralympic Games. Study design Retrospective study Methods This study analysed a total of 479 attempts performed by 114 male and female stationary shot-putters in three F30s (F32-F34) and six F50s (F52-F58) classes during the course of eight events during Beijing 2008 Paralympic Games. Results The average differences of best performance were 1.46±0.46 m for males between F54 and F58 classes as well as 1.06±1.18 m for females between F55 and F58 classes. The results demonstrated a linear relationship between best performance and classification while revealing two male Gold Medallists in F33 and F52 classes were outliers. Conclusions This study confirms the benefits of the comparative matrices, performance continuum and dispersion plots to comprehend classification-related variables. The work presented here represents a stepping stone into biomechanical analyses of stationary throwers, particularly on the eve of the London 2012 Paralympic Games where new evidences could be gathered.

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.

An application of fuzzy DL-Based semantic perception to soil container classification

Semantic perception and object labeling are key requirements for robots interacting with objects on a higher level. Symbolic annotation of objects allows the usage of planning algorithms for object interaction, for instance in a typical fetchand-carry scenario. In current research, perception is usually based on 3D scene reconstruction and geometric model matching, where trained features are matched with a 3D sample point cloud. In this work we propose a semantic perception method which is based on spatio-semantic features. These features are defined in a natural, symbolic way, such as geometry and spatial relation. In contrast to point-based model matching methods, a spatial ontology is used where objects are rather described how they "look like", similar to how a human would described unknown objects to another person. A fuzzy based reasoning approach matches perceivable features with a spatial ontology of the objects. The approach provides a method which is able to deal with senor noise and occlusions. Another advantage is that no training phase is needed in order to learn object features. The use-case of the proposed method is the detection of soil sample containers in an outdoor environment which have to be collected by a mobile robot. The approach is verified using real world experiments.

Towards robust automatic affective classification of images using facial expressions for practical applications

Affect is an important feature of multimedia content and conveys valuable information for multimedia indexing and retrieval. Most existing studies for affective content analysis are limited to low-level features or mid-level representations, and are generally criticized for their incapacity to address the gap between low-level features and high-level human affective perception. The facial expressions of subjects in images carry important semantic information that can substantially influence human affective perception, but have been seldom investigated for affective classification of facial images towards practical applications. This paper presents an automatic image emotion detector (IED) for affective classification of practical (or non-laboratory) data using facial expressions, where a lot of “real-world” challenges are present, including pose, illumination, and size variations etc. The proposed method is novel, with its framework designed specifically to overcome these challenges using multi-view versions of face and fiducial point detectors, and a combination of point-based texture and geometry. Performance comparisons of several key parameters of relevant algorithms are conducted to explore the optimum parameters for high accuracy and fast computation speed. A comprehensive set of experiments with existing and new datasets, shows that the method is effective despite pose variations, fast, and appropriate for large-scale data, and as accurate as the method with state-of-the-art performance on laboratory-based data. The proposed method was also applied to affective classification of images from the British Broadcast Corporation (BBC) in a task typical for a practical application providing some valuable insights.

Reliability and criterion-related validity with a smartphone used in timed-up-and-go test

Background The capacity to diagnosys, quantify and evaluate movement beyond the general confines of a clinical environment under effectiveness conditions may alleviate rampant strain on limited, expensive and highly specialized medical resources. An iPhone 4® mounted a three dimensional accelerometer subsystem with highly robust software applications. The present study aimed to evaluate the reliability and concurrent criterion-related validity of the accelerations with an iPhone 4® in an Extended Timed Get Up and Go test. Extended Timed Get Up and Go is a clinical test with that the patient get up from the chair and walking ten meters, turn and coming back to the chair. Methods A repeated measure, cross-sectional, analytical study. Test-retest reliability of the kinematic measurements of the iPhone 4® compared with a standard validated laboratory device. We calculated the Coefficient of Multiple Correlation between the two sensors acceleration signal of each subject, in each sub-stage, in each of the three Extended Timed Get Up and Go test trials. To investigate statistical agreement between the two sensors we used the Bland-Altman method. Results With respect to the analysis of the correlation data in the present work, the Coefficient of Multiple Correlation of the five subjects in their triplicated trials were as follows: in sub-phase Sit to Stand the ranged between r = 0.991 to 0.842; in Gait Go, r = 0.967 to 0.852; in Turn, 0.979 to 0.798; in Gait Come, 0.964 to 0.887; and in Turn to Stand to Sit, 0.992 to 0.877. All the correlations between the sensors were significant (p < 0.001). The Bland-Altman plots obtained showed a solid tendency to stay at close to zero, especially on the y and x-axes, during the five phases of the Extended Timed Get Up and Go test. Conclusions The inertial sensor mounted in the iPhone 4® is sufficiently reliable and accurate to evaluate and identify the kinematic patterns in an Extended Timed Get and Go test. While analysis and interpretation of 3D kinematics data continue to be dauntingly complex, the iPhone 4® makes the task of acquiring the data relatively inexpensive and easy to use.