Competitive Learning Research Articles

Ostrakinda: A Game-Based Learning Toolkit for Ancient Mediterranean Cities

The study develops the 'Ostrakinda' toolkit for teaching morphologies of ancient Mediterranean cities. The methodology consists of a triple structure involving design, play, and analysis phases. In the design phase, the level of interest and actual demands of students regarding game-based learning (GBL) and ancient cities were explored through pre-experiments. The play phase involved experimental studies conducted in courses and workshops, where both physical and digital toolkits were tested by a total of 331 students. The analysis phase aimed to evaluate the impact of the game by systematically addressing five research questions. The results of the paired t-test confirm a significant difference in scores before and after playing the game, thus validating the effectiveness of the proposed strategy. Additionally, Chi-square (X2) tests revealed significant relationships between the form of play and the level of abstraction in the game outputs. Individual and group experiences during gameplay were associated with various interactions, and group experiences particularly fostered competitive and collaborative learning. The extensive analysis using the GBL Design Scale, comprising ten critical factors (GBL-Fn), showed that the challenge factor (F8) had the weakest values, while fantasy (F5) and narrative (F6) had the highest values in the correlation matrix. Overall, the study contributes methodologically and contextually to the existing literature, offering valuable findings for the future development of similar strategies in architectural education. However, it is important to acknowledge the limitations of this interdisciplinary study, particularly with regards to technical, cognitive, and archaeological aspects. Nevertheless, the clear and effective structure of the game holds promise as a valuable tool for learning.

MLBRSA: Multi-Learning-Based Reptile Search Algorithm for Global Optimization and Software Requirement Prioritization Problems.

In the realm of computational problem-solving, the search for efficient algorithms tailored for real-world engineering challenges and software requirement prioritization is relentless. This paper introduces the Multi-Learning-Based Reptile Search Algorithm (MLBRSA), a novel approach that synergistically integrates Q-learning, competitive learning, and adaptive learning techniques. The essence of multi-learning lies in harnessing the strengths of these individual learning paradigms to foster a more robust and versatile search mechanism. Q-learning brings the advantage of reinforcement learning, enabling the algorithm to make informed decisions based on past experiences. On the other hand, competitive learning introduces an element of competition, ensuring that the best solutions are continually evolving and adapting. Lastly, adaptive learning ensures the algorithm remains flexible, adjusting the traditional Reptile Search Algorithm (RSA) parameters. The application of the MLBRSA to numerical benchmarks and a few real-world engineering problems demonstrates its ability to find optimal solutions in complex problem spaces. Furthermore, when applied to the complicated task of software requirement prioritization, MLBRSA showcases its capability to rank requirements effectively, ensuring that critical software functionalities are addressed promptly. Based on the results obtained, the MLBRSA stands as evidence of the potential of multi-learning, offering a promising solution to engineering and software-centric challenges. Its adaptability, competitiveness, and experience-driven approach make it a valuable tool for researchers and practitioners.

SOINN Intrusion Detection Model Based on Three-Way Attribute Reduction

With a large number of intrusion detection datasets and high feature dimensionality, the emergent nature of new attack types makes it impossible to collect network traffic data all at once. The modified three-way attribute reduction method is combined with a Self-Organizing Incremental learning Neural Network (SOINN) algorithm to propose a self-organizing incremental neural network intrusion detection model based on three-way attribute reduction. Attribute importance is used to perform attribute reduction, and the data after attribute reduction are fed into a self-organized incremental learning neural network algorithm, which generalizes the topology of the original data through self-organized competitive learning. When the streaming data are transferred into the model, the inter-class insertion or node fusion operation is performed by comparing the inter-node distance and similarity threshold to achieve incremental learning of the model streaming data. The inter-node distance value is introduced into the weight update formulation to replace the traditional learning rate and to optimize the topological structure adjustment operation. The experimental results show that T-SOINN achieves high precision and recall when processing intrusion detection data.

Optimization of number of wireless temperature sensors using clustering algorithm for deep learning algorithm-based Kimchi quality prediction

The production and storage of kimchi in a factory require monitoring temperature and humidity to maintain optimal quality. Recently, smart packaging devices such as wireless sensors have been used, but their installation and maintenance are costly and require additional resources. In this study, kimchi is packaged in polyethylene packages and placed in plastic baskets. Thirty baskets are stacked in the middle of the storage room. Wireless sensors placed inside the baskets collect temperature data alongside the kimchi for 60 days. The data is sent to a server through communication unit using 4G network. Two clustering algorithms, Competitive Learning Neural Network (CLNN) and k-means, are used to determine the optimal number and location of sensors. Deep learning algorithms, specifically Long Short-Term Memory (LSTM), predict the acidity and ripeness grade of the kimchi. The study found that the optimal number of temperature sensor groups for CLNN was 6 for acidity and 4 for ripeness grade classification. Increasing the number of sensors improved the kimchi acidity prediction, and the accuracy of ripeness classification increased with the number of sensors. The location of the wireless sensors was determined based on the heights of the stacked plastic baskets using the CLNN + LSTM model. This work presents a process for optimizing sensor placement and evaluating kimchi quality during storage and fermentation using clustering and deep learning techniques to maintain optimal quality.

The effectiveness of using the competitive learning method in improving the performance of student teachers at the College of Music Education

The effectiveness of using the competitive learning method in improving the performance of student teachers at the College of Music Education

Gradient-Based Competitive Learning: Theory

Deep learning has been recently used to extract the relevant features for representing input data also in the unsupervised setting. However, state-of-the-art techniques focus mostly on algorithmic efficiency and accuracy rather than mimicking the input manifold. On the contrary, competitive learning is a powerful tool for replicating the input distribution topology. It is cognitive/biologically inspired as it is founded on Hebbian learning, a neuropsychological theory claiming that neurons can increase their specialization by competing for the right to respond to/represent a subset of the input data. This paper introduces a novel perspective by combining these two techniques: unsupervised gradient-based and competitive learning. The theory is based on the intuition that neural networks can learn topological structures by working directly on the transpose of the input matrix. At this purpose, the vanilla competitive layer and its dual are presented. The former is representative of a standard competitive layer for deep clustering, while the latter is trained on the transposed matrix. The equivalence of the layers is extensively proven both theoretically and experimentally. The dual competitive layer has better properties. Unlike the vanilla layer, it directly outputs the prototypes of the data inputs, while still allowing learning by backpropagation. More importantly, this paper proves theoretically that the dual layer is better suited for handling high-dimensional data (e.g., for biological applications), because the estimation of the weights is driven by a constraining subspace which does not depend on the input dimensionality, but only on the dataset cardinality. This paper has introduced a novel approach for unsupervised gradient-based competitive learning. This approach is very promising both in the case of small datasets of high-dimensional data and for better exploiting the advantages of a deep architecture: the dual layer perfectly integrates with the deep layers. A theoretical justification is also given by using the analysis of the gradient flow for both vanilla and dual layers.

XL1R-Net: Explainable AI-driven improved [formula omitted]-regularized deep neural architecture for NSCLC biomarker identification

Background and Objective:Non-small cell lung cancer (NSCLC) exhibits intrinsic molecular heterogeneity, primarily driven by the mutation of specific biomarkers. Identification of these biomarkers would assist not only in distinguishing NSCLC into its major subtypes — Adenocarcinoma and Squamous Cell Carcinoma, but also in developing targeted therapy. Medical practitioners use one or more types of omic data to identify these biomarkers, copy number variation (CNV) being one such type. CNV provides a measure of genomic instability, which is considered a hallmark of carcinoma. However, the CNV data has not received much attention for biomarker identification. This paper aims to identify biomarkers for NSCLC using CNV data. Methods:An eXplainable AI (XAI)-driven L1-regularized deep learning architecture, XL1R-Net, is proposed that introduces a novel modification of the standard L1-regularized gradient descent algorithm to arrive at an improved deep neural classifier for NSCLC subtyping. Further, XAI-based feature identification has been used to leverage the trained classifier to uncover a set of twenty NCSLC-relevant biomarkers. Results:The identified biomarkers are evaluated based on their classification performance and clinical relevance. Using Multilayer Perceptron (MLP)-based model, a classification accuracy of 84.95% using 10-fold cross-validation is achieved. Moreover, the statistical significance test on the classification performance also revealed the superiority of the MLP model over the competitive machine learning models. Further, the publicly available Drug–Gene Interaction Database reveals twelve of the identified biomarkers as potentially druggable. The K–M Plotter tool was used to verify eighteen of the identified biomarkers with a high probability of predicting NSCLC patients’ likelihood of survival. While nine of the identified biomarkers confirm the recent literature, five find mention in the OncoKB Gene List. Conclusion:A set of seven novel biomarkers that have not been reported in the literature could be investigated for their potential contribution towards NSCLC therapy. Given NSCLC’s genetic diversity, using only one omics data type may not adequately capture the tumor’s complexity. Multiomics data and its integration with other sources will be examined in the future to better understand NSCLC heterogeneity.

Detecting loss of excitation condition of synchronous generator in the presence of unified power flow controller based on data mining method

Loss-of-excitation (LOE) conditions may cause devastating effects on both the generator and power system. If LOE is not meticulously detected, two dangerous events may emerge: 1. unnecessary trip signal, 2. not detecting this abnormal condition or detecting it with time delay. Both mentioned flaws have considerable harmful consequences on the generator and power system. Conventional techniques for detecting LOE conditions are based on impedance measurement. The presence of flexible alternating current transmission (FACT) system devices can considerably affect the impedance characteristic of the system and as a result, the operation of impedance-based relays. This paper simulates LOE and stable power swing (SPS) conditions causing failures and errors in the LOE protection in the presence or absence of a unified power flow compensator (UPFC), and parameters with different behaviors are determined. Then, the most sensitive parameters are combined using an intelligent method. The single parameter, achieved from a combination of features in the previous process, is applied to a learning vector quantization (LVQ) neural network. The LVQ is a type of artificial neural network that is based on a prototype supervised learning classification algorithm and trained its network through a competitive learning algorithm. The simulation results show that, in a single machine infinitive bus (SMIB) test system, R-X directional scheme has 2 mal-operations and the proposed algorithm has no mal-operation without UPFC in the system. With UPFC in the system, the R-X directional scheme has four mal-operations and the proposed algorithm has no mal-operation. In the IEEE 9-bus test system, the R-X directional scheme has five mal-operations and the proposed algorithm has no mal-operation. Moreover, applying the proposed algorithm, LOE is detected very quickly in the presence or absence of the UPFC in the system and this approach prevents electrical and mechanical stresses enforced to the machine and power system. © 2017 Elsevier Inc. All rights reserved.

The Interplay of Sex and Learning Method Selection: A Study on the Reciprocal Influence on Cognitive Abilities

As the society continues to evolve, the demand for top-notch education has grown in tandem. Understanding the interplay of sex, learning method selection, and cognitive abilities in cognitive development is crucial for optimizing educational strategies and outcomes. This study aimed to investigate the relationship among sex, different learning methods, and cognitive abilities across different cognitive domains. A diverse body of literature was systematically examined, which includes studies employing various cognitive tests and learning method assessments in different sex and age cohort. As predicted, results revealed a significant interaction between sex and learning method selections in cognitive abilities. Females have the advantage of the influences of hormones and timing of cognitive maturation in cognitive abilities, leading to better performance in verbal memory tasks, more efficient responding, and better inhibitory control. As males perform best in competitive learning environments and females in cooperative environments, implying the interaction between sex and cognition in learning method selections. The findings of this review highlighted the complex interplay between sex, learning methods, and cognitive abilities, underscoring the need to take individual strengths and sex differences into account when selecting learning methods. Insights from this study have implications for educational practices and policymaking, suggesting the potential for a more personalized learning approach to enhance cognitive abilities and academic performance. Further research direction and limitations are also discussed.

Feature Selection for Efficient Local-to-global Bayesian Network Structure Learning

Local-to-global learning approach plays an essential role in Bayesian network (BN) structure learning. Existing local-to-global learning algorithms first construct the skeleton of a DAG (directed acyclic graph) by learning the MB (Markov blanket) or PC (parents and children) of each variable in a dataset, then orient edges in the skeleton. However, existing MB or PC learning methods are often computationally expensive especially with a large-sized BN, resulting in inefficient local-to-global learning algorithms. To tackle the problem, in this article, we link feature selection with local BN structure learning and develop an efficient local-to-global learning approach using filtering feature selection. Specifically, we first analyze the rationale of the well-known Minimum-Redundancy and Maximum-Relevance (MRMR) feature selection approach for learning a PC set of a variable. Based on the analysis, we propose an efficient F2SL (feature selection-based structure learning) approach to local-to-global BN structure learning. The F2SL approach first employs the MRMR approach to learn the skeleton of a DAG, then orients edges in the skeleton. Employing independence tests or score functions for orienting edges, we instantiate the F2SL approach into two new algorithms, F2SL-c (using independence tests) and F2SL-s (using score functions). Compared to the state-of-the-art local-to-global BN learning algorithms, the experiments validated that the proposed algorithms in this article are more efficient and provide competitive structure learning quality than the compared algorithms.

Emden: A novel method integrating graph and transformer representations for predicting the effect of mutations on clinical drug response

Precision medicine based on personalized genomics provides promising strategies to enhance the efficacy of molecular-targeted therapies. However, the clinical effectiveness of drugs has been severely limited due to genetic variations that lead to drug resistance. Predicting the impact of missense mutations on clinical drug response is an essential way to reduce the cost of clinical trials and understand genetic diseases. Here, we present Emden, a novel method integrating graph and transformer representations that predicts the effect of missense mutations on drug response through binary classification with interpretability. Emden utilized protein sequences-based features and drug structures as inputs for rapid prediction, employing competitive representation learning and demonstrating strong generalization capabilities and robustness. Our study showed promising potential for clinical drug guidance and deep insight into computer-assisted precision medicine. Emden is freely available as a web server at https://www.psymukb.net/Emden.

Perceptions of Online Learning Among Instructors: How to Maximize Instructors’ Competencies in Virtual and Blended Learning

Purpose: This study aims to evaluate instructors' perceptions of e-learning at the Public Authority For Applied Education and Training (PAAET) in Kuwait. It sheds light on the effectiveness of Ms-Teams as a learning management tool used by instructors and students. The outcome of the study will help to introduce guidelines for enhancing the role of instructors in virtual and blended learning. . Theoretical framework: Information technology will change education if used properly by skilled teachers. Technology's rapid adoption and investment have changed education, and instructors are crucial to 21st-century learning standards and methods. Because AI, advanced technology, and automation will rule the future, the next generation of workers must be tech-savvy. This study will identify instructors' digital skills and provide recommendations and a road map to support advanced technological tools and new innovative learning strategies in human resource management. Design/Methodology/Approach: The research used both qualitative and quantitative methods. A focus group session was conducted to investigate further, and the results of the session helped shape a survey questionnaire that was distributed to 161 instructors at PAAET. The survey aimed to identify the challenges and opportunities presented by online learning. Findings: Instructors have a positive view of online learning and Ms Teams as a learning management. The study also found some obstacles to online learning platform implementation. These issues include poor helpdesk support, training, management motivation, and electronic educational resources. These obstacles must be overcome for PAAET to adopt a learning system that improves academic performance. No significant gender differences in instructors' perceptions are found. Originality/Value: This study should help education policymakers be more brave when investing in IT and human resources "Instructors" to create a better and more competitive teaching and learning environment. This study proposes an HRM-based framework to improve digital instructors and the educational process.

A feature-weighted suppressed possibilistic fuzzy c-means clustering algorithm and its application on color image segmentation

The possibilistic fuzzy c-means clustering (PFCM) algorithm is a hybridization of possibilistic c-means clustering (PCM) and fuzzy c-means clustering (FCM) algorithms. However, there are two main problems in PFCM. One is that the Euclidean distance employed in PFCM always disregards the imbalance among sample features because it treats all features of data equally, which easily causes misclassification for feature-imbalanced multidimensional data. The other is that PFCM always produces significant center deviations and overlapping centers for multiclass datasets with strong noise injection, due to the difficulty of PFCM in the membership-weight parameter setting and the lack of between-class relationships in possibilistic memberships. Therefore, a feature-weighted suppressed possibilistic fuzzy c-means clustering (FW-S-PFCM) algorithm is presented by introducing a feature-weighted method and “suppressed competitive learning” strategy into the PFCM algorithm in this paper. First, the FW-S-PFCM algorithm introduces a feature-weight matrix into the objective function that can automatically assign feature-weight values to different features and different clusters according to the distribution of samples, thus overcoming the influence of feature imbalance and improving clustering effects for noisy multidimensional datasets. Second, combined with the feature-weight matrix, a “suppressed competitive learning” strategy is designed to resolve the center-overlapping problem in noisy multiclass dataset clustering. Specifically, partial crucial points of each class near the center are selected according to a cluster core generated by a cross-section of a threshold on the possibilistic membership surface. Third, their possibilistic memberships participate in the suppressed learning process to overcome the lack of between-class relationships. Last, a segmentation algorithm for noisy color images based on FW-S-PFCM is proposed combined with the feature-weight method and noise-identification ability of possibilistic memberships. Experiments on synthetic data, UCI data and color image segmentation demonstrate that the proposed FW-S-PFCM algorithm can overcome the partial center-overlapping problem and improve clustering performance on complex datasets with feature imbalance and strong noise injection. The proposed algorithm can also reduce the iteration number, sensitivity to membership weights, and initializations of PFCM.

Why Jane likes to read and John does not. How parents and schools stimulate girls’ and boys’ intrinsic reading motivation

Student's intrinsic reading motivation is key to their reading proficiency and spills over to other domains of development. Prior studies show that girls are more intrinsically motivated to read than boys but little is known about how reading socialization in families and schools relate to gender inequality in reading motivation. This study investigates a) how reading socialization activities in families and schools relate to girls’ and boys’ intrinsic reading motivation and b) whether schools can compensate for poor family reading socialization especially among boys. Analyses are performed on a sample from PISA 2018 containing 28,747 students in 1,581 schools. Results reveal that girls benefit more from family reading socialization and a good disciplinary climate in classrooms than boys. Boys benefit more than girls from a competitive learning climate in school and teachers’ active stimulation of reading engagement. The latter particularly stimulates the intrinsic reading motivation of boys who received little family reading socialization.

Feature Extraction Methods by Various Concepts using SOM

Image retrieval systems gained traction with the increased use of visual and media data. It is critical to understand and manage big data, lot of analysis done in image retrieval applications. Given the considerable difficulty involved in handling big data using a traditional approach, there is a demand for its efficient management, particularly regarding accuracy and robustness. To solve these issues, we employ content-based image retrieval (CBIR) methods within both supervised , unsupervised pictures. Self-Organizing Maps (SOM), a competitive unsupervised learning aggregation technique, are applied in our innovative multilevel fusion methodology to extract features that are categorised. The proposed methodology beat state-of-the-art algorithms with 90.3% precision, approximate retrieval precision (ARP) of 0.91, and approximate retrieval recall (ARR) of 0.82 when tested on several benchmark datasets.

Utilizing Teams Games Tournament in Teaching Reading to Enhance Students’ Comprehension on Narrative Texts

The present study has the main objective to test whether the Teams Games Tournament (TGT) method can improve students' reading comprehension on narrative texts. To answer the formulation of the problem, this study utilized a quasi-experimental method by involving an experimental class and a control class with data collection techniques through observation, reading comprehension test, and interviews. The results of this study reveal three main points: First, a comparison between the results of the t-test and t-table at a significant level of 5% showed tt > t0 or 9.13 > 1.67. This means that the Teams Games Tournament can enhance students' reading comprehension on narrative texts. Second, the TGT method can increase student cooperation, train courage to express opinions, build discipline, caution, and tolerance towards fellow students. Third, this method can also create a competitive learning climate and encourage students to become active learners.

A dynamic core evolutionary clustering algorithm based on saturated memory

Because the number of clustering cores needs to be set before implementing the K-means algorithm, this type of algorithm often fails in applications with increasing data and changing distribution characteristics. This paper proposes an evolutionary algorithm DCC, which can dynamically adjust the number of clustering cores with data change. DCC algorithm uses the Gaussian function as the activation function of each core. Each clustering core can adjust its center vector and coverage based on the response to the input data and its memory state to better fit the sample clusters in the space. The DCC algorithm model can evolve from 0. After each new sample is added, the winning dynamic core can be adjusted or split by competitive learning, so that the number of clustering cores of the algorithm always maintains a better adaptation relationship with the existing data. Furthermore, because its clustering core can split, it can subdivide the densely distributed data clusters. Finally, detailed experimental results show that the evolutionary clustering algorithm DCC based on the dynamic core method has excellent clustering performance and strong robustness.

Adaptive multi-objective competitive swarm optimization algorithm based on kinematic analysis for municipal solid waste incineration

Multi-objective optimization for the municipal solid waste incineration process is considered as a valuable technique to improve energy recovery and reduce pollutant emission. However, the complex mechanism analysis and multimodal problem of the municipal solid waste incineration process set challenges for both the modeling and optimization studies. To overcome this problem, an adaptive multi-objective optimization for the municipal solid waste incineration process is proposed in this paper. First, a bi-objective model of the municipal solid waste incineration, the basis for optimization, is established based on mass balance and energy balance, which takes furnace temperature and flue gas oxygen content as decision variables to mathematically deduce the generated heat and exhaust gases. Second, an adaptive multi-objective competitive swarm optimization algorithm is proposed for the optimization of the municipal solid waste incineration process. Two-step competition and multi-strategy learning are designed to provide a clear division of labor for particles and a novel idea for detecting evolutionary environment is proposed based on kinematic analysis of particles. Finally, relevant experiments are conducted on benchmark instances and the municipal solid waste incineration optimization model. The proposed algorithm shows promising convergence, diversity, fastness by comparing with several representative and state-of-the-art algorithms. The proposed algorithm achieves the optimization effects with 4.36% improvement of the available heat for power generation and 4.13% reduction of the exhaust gas assessment in the optimization of the municipal solid waste incineration process.

Instructors’ Digital Competencies for Innovative Learning: Human Resource Management Perspectives

Purpose: This paper reviews related literature, including models and frameworks that focus on the skills of the digital instructor in the innovative learning environment. The study also tries to identify, key areas and missing factors, and thus locate digital skills and future avenues for education and satisfy the needs of digital-age learners. Theoretical framework: Information technology will have a significant impact on education if operated properly by competent and capable instructors. The accelerated application and investment in technology have altered education, and instructors play a crucial role in the transition to 21st-century learning standards and methods. This is especially important because the future will be dominated by artificial intelligence (AI), advanced technology, and automation, which will require the next generation of employees to be tech-savvy. Therefore, this study will locate digital skills for instructors and provide recommendations and a road map that support both the advanced technological tools and the new innovative learning strategies in the context of human resource management. Design/Methodology/Approach: The researchers took a literature review as a method to determine the current situation, success factors of online learning, instructors’ skills in the context of HRM. In addition, a qualitative analysis was conducted in the form of a focus group discussion, to spotlights on issues related to instructors needs to practice their roles in the e-learning environment. Findings: The results of this study have provided evidence that instructors' proficiency in IT “Digital Instructors” will transform teaching and learning to satisfy the 4th industrial revolution which is based on digital skills and contribute to the digital economy. Originality/Value: The results of this study are expected to be useful input for policymakers in education to be more courageous in making decisions when investing in IT resources and human resources “Instructors” in order to create superior and competitive teaching and learning environment. A framework is proposed in this study with consideration of HRM issues that will work effectively to enhance the role of digital education in society and contribute to the development of the educational process.

Wind turbine contaminant classification using machine learning techniques

It has been well established in the literature that surface contamination can adversely affect the aerodynamic performance of aerofoils and hence the efficiency with which turbines can convert wind to electrical power. Hence it is critical to ensure that turbine blades are kept as free as possible of contaminants. In this manuscript, we discuss LIBS and machine learning techniques on contaminated wind turbine blades with a view to the possibility of integrating these methods into a standoff laser ablation setup in the future. A LIBS signal will be a key step in the decision process, i.e., to determine if a wind turbine blade has been fouled in the first place. Relatedly one must also determine the point at which the laser has adequately removed contaminants from the current Area of Irradiation (AoI) before moving to the adjacent AoI, i.e., interim end-point-detection. For both steps (presence / absence of fouling) we are investigating laser-induced breakdown spectroscopy (LIBS) to discriminate clean from fouled wind turbine blade samples. In particular we have performed LIBS in both the Vacuum Ultraviolet (VUV) and Ultraviolet Visible (UV–Vis) spectral ranges. Analysis of the spectra showed only slight variations in the constituent materials between clean and contaminated blade samples. In order to address this challenge, the efficacy of a number of machine learning and statistical methods for clean versus contaminated blade classification was investigated. Four methods (Partial Least Squares Discriminant Analysis (PLS-DA), Support Vector Machines (SVM), Competitive Learning (CL), and Convolutional Neural Networks (CNN)) were evaluated. The spectral regions where machine learning algorithms were applied was determined via a volumetric ellipsoid overlap test based on Principal Component Analysis (PCA). It was found that SVMs provided the most accurate methodology for binary classification of clean vs contaminated blades whilst also yielding the shortest run time.