Analysis of unsupervised learning techniques for face recognition

Face recognition has always been a fascinating research area. It has drawn the attention of many researchers because of its various potential applications such as security systems, entertainment, criminal identification etc. Many supervised and unsupervised learning techniques have been reported so far. Principal component analysis (PCA) is a classical and successful method for face recognition. Self organizing map (SOM) has also been used for face space representation. This paper makes an attempt to integrate the two techniques for dimensionality reduction and feature extraction and to see the performance when the two are combined. Simulation results show that, though, the individual techniques SOM and PCA itself give excellent performance but the combination of these two can also be utilized for face recognition. The advantage in combining the two techniques is that the reduction in data is higher but at the cost of recognition rate

For last two decades, clustering is well-recognized area in the research field of data mining. Data clustering plays the major research at pattern recognition, Signal processing, bioinformatics and Artificial Intelligence. Clustering process is an unsupervised learning techniques where it generates a group of object based on their similarity in such a way that the objects belonging to other groups are similar and those belonging to other are dissimilar. This paper analysis the three different data types clustering techniques like K-Means, Principal components analysis (PCA) and Independent component analysis (ICA) in real and simulated data. The recent developments by considering a rather unexpected application of the theory of Independent component analysis (ICA) found in data clustering, outlier detection and multivariate data visualization. Accurate identification of data clustering plays an important role in statistical analysis. In this paper we explore the connection among these three techniques to identify multivariate data clustering and develop a new method k-means on PCA or ICA then the result shows that ICA based clustering performs well than others.

Machine recognition has drawn considerable interest and attention from researches in intelligent system design and computer vision communities over the recent past. Understandably there are a large number of commercial, law enforcement, control and forensic applications to this. We human beings have natural ability to recognize persons at a glance. Motivated by our remarkable ability, a series of attempts [1–4] have been made to simulate this ability in machines. The development of human recognition system in machines is quite difficult because the natural objects are complex, multidimensional, and corresponds to environmental changes [3, 5–7]. There are two important issues that need to be addressed in machine recognition: (1) how the features are adopted to represent an object under environmental changes and (2) how we classify an object image based on a chosen representation. Over the years, researches have developed a number of methods for feature extraction and classification. All of these, however, have their own merits and demerits. Most of the work is related to the real domain. The outperformance of complex-valued neuron over conventional neuron has been well established in previous chapters. Few researchers have recently tried multivariate statistical techniques in the complex domain, like complex principal component analysis (PCA) for 2D vector field analysis [8] and complex independent component analysis (ICA) for performing source separation on functional magnetic resonance imaging data [9, 10]. But, no attempts have been made to develop techniques for feature extraction using their concepts. This chapter presents formal procedures for feature extraction using unsupervised learning techniques in complex domain. Efficient learning and better precision in result offered by feature extractor and classifier, considering simulations in complex domain, figure out their technical benefits over conventional methods. Notably, the success of machine recognition is limited by variations in features resulting from the natural environment. These may be due to instrument distortion, acquisition in an outdoor environment, different noises, complex background, occlusion and illumination. A solid set of examples presented in this chapter demonstrate the superiority of feature representation and classification in complex domain.KeywordsFeature ExtractionIndependent Component AnalysisIndependent Component AnalysisComplex DomainFalse Acceptance RateThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Face technologies which can be applied to access control and surveillance, are essential to intelligent vision-based human computer interaction. The research efforts in this field include face detecting, face recognition, face retrieval, etc. However, these tasks are challenging because of variability in view point, lighting, pose and expression of human faces. The ideal face representation should consider the variability so as to we can develop robust algorithms for our applications. Independent Component Analysis (ICA) as an unsupervised learning technique has been used to find such a representation and obtained good performances in some applications. In the first part of this paper, we depict the models of ICA and its extensions: Independent Subspace Analysis (ISA) and Topographic ICA (TICA).Then we summaraize the process in the applications of ICA and its extension in Face images. At last we propose a promising direction for future research.

We live in a world of text. Yet the sheer magnitude of social media data, coupled with a need to measure complex psychological constructs, has made this important source of data difficult to use. Researchers often engage in costly hand coding of thousands of texts using supervised techniques or rely on unsupervised techniques where the measurement of predefined constructs is difficult. We propose a novel approach that we call ‘super-unsupervised’ learning and demonstrate its usefulness by measuring the psychologically complex construct of online political hostility based on a large corpus of tweets. This approach accomplishes the feat by combining the best features of supervised and unsupervised learning techniques: measurements of complex psychological constructs without a single labelled data source. We first outline the approach before conducting a diverse series of tests that include: (i) face validity, (ii) convergent and discriminant validity, (iii) criterion validity, (iv) external validity, and (v) ecological validity.

Automated security management has been a critical but difficult issue in the field of network research. Among various artificial-intelligence techniques, traditional learning techniques based on supervision are not suitable for automated network management, particularly in terms of detecting temporal changes in network intrusion patterns and characteristics, because supervised learning requires a manager. In this regard, unsupervised learning techniques such as the self-organizing map (SOM) are more suitable for automated network management in terms of their configuration, performance, and anomaly detection capability. This paper proposes an automated security management system based on a hierarchical SOM that groups similar data and visualizes their clusters. The proposed system labels maps produced by the SOM based on correlations between features for automated network management. The experimental results for the proposed system based on the 1999 KDD Cup data set indicate that the system shows reasonable misclassification rates and takes 0.5 second to determine whether a behavior is a normal one or an attack.

Developed for studying long, periodic records of various measured quantities, time series analysis methods are inherently suited and offer interesting possibilities for Structural Health Monitoring (SHM) applications. However, their use in SHM can still be regarded as an emerging application and deserves more studies. In this research, Autoregressive (AR) models were used to fit experimental acceleration time histories from two experimental structural systems, a 3- storey bookshelf-type laboratory structure and the ASCE Phase II SHM Benchmark Structure, in healthy and several damaged states. The coefficients of the AR models were chosen as damage sensitive features. Preliminary visual inspection of the large, multidimensional sets of AR coefficients to check the presence of clusters corresponding to different damage severities was achieved using Sammon mapping - an efficient nonlinear data compression technique. Systematic classification of damage into states based on the analysis of the AR coefficients was achieved using two supervised classification techniques: Nearest Neighbor Classification (NNC) and Learning Vector Quantization (LVQ), and one unsupervised technique: Self-organizing Maps (SOM). This paper discusses the performance of AR coefficients as damage sensitive features and compares the efficiency of the three classification techniques using experimental data.

It is normally understood in the industry that permeability and porosity are related but relationship can be strong or weak based on heterogeneity, anisotropy and lithology of the reservoir. So far linear models have been arbitrarily being tried to fit and matched with the data thereby resulting in a poor relationship. This paper seeks to explore data mining techniques for pattern recognition including Kohonen self-organizing maps and other unsupervised learning techniques. Kohonen self-organizing maps and principal component analysis are applied over permeability –porosity data to first cluster the data into various sets. This data can then be linked back to the formations and a predictor can be built thereby giving a tool for reservoir characterization. Then a linear model is to be built with the linearity being assessed by Shapiro Wilk Test and Quantile – Quantile (Q-Q) plot. This technique develops a relationship with a much better fit between permeability and porosity in respective ranges and thereby creating a higher cue-efficient of determination i.e. R squared value.

Customer relationship management (CRM) is the tool to enhance customer relationship in any business. Due to the exponential growth of data volume, in any field, it is significant to develop new techniques to discover the customer knowledge, automation of the system and moreover customer satisfaction to win customer lifetime value. CRM with machine learning could bring a catalytic change in business. Several supervised and unsupervised machine learning techniques are utilized to improve the customer experience and profitability of business. This paper reviews the available literature on the CRM with machine learning techniques for customer identification, customer attraction, and customer retention and customer development. This study reveals that supervised learning techniques are 48.48% utilized, unsupervised learning techniques are utilized 15.15%, and 9.09% utilized other techniques in CRM. Paradigm is also shifted toward the deep learning from machine learning as 28.28% text has been reported to deep learning. Decision tree-based algorithm and support vector machine algorithms are most utilized algorithm of supervised learning. E-commerce and telecommunication sectors are the most important areas identified with the exponential growth of the users and hence need a suitable machine learning techniques for customer satisfaction and business profitability.

The self-organization map is an unsupervised learning technique that discovers patterns and relationships in data without requiring labeled training data. Inspired by the self-organization map, Self-Organization Granular encoding has been proven effec

Operational modal analysis (OMA) is required to maintain large-scale and necessary civil infrastructures. The non-contact method of OMA using digital image correlation and point tracking algorithms requires a speckle pattern placed on the structure. Alternatively, advanced computer vision methods like optical flow and phase-based video motion magnification (PBVMM) techniques are used to measure modal parameters. Despite the importance of PBVMM, the users should know the range of frequencies in which the natural structure frequency lies. A methodology based on an unsupervised machine learning technique is developed to extract the modal parameters blindly from its recorded digital video. The proposed methodology uses complex steerable pyramids and an unsupervised machine learning technique, also known as principal component analysis, and analytical mode decomposition with a random decrement technique to blindly extract the modal parameters of a structure. This study validated the proposed methodology using a multi-degree of freedom (DOF) numerical model. The results are compared with theoretical and estimated values and are in good agreement. Furthermore, it is implemented on a laboratory benchmark SDOF, MDOF, and real-time videos of the London Millennium and Tacoma Narrows bridges for blindly extracting the modal frequencies and damping ratios.

Technological developments have affected the decision-making phase in football matches. The viewing pleasure of fans and the result of the match is a matter of debate determined by the referees. Throughout time, the objectiveness of referees was questioned by the technological tools. Video Assistant Referee (VAR) is an example approach to ensure whether the referees react to similar positions of different matches in the same manner or not. One of the problems of this topic is the controversial decisions of some referees leading to unexpected results. In this research, as a different approach to the referees’ objectivity problem, referees are tried to be classified based on the statistical outcome of the matches using unsupervised machine learning techniques. Meaningful clusters should not be found to be able to state the referees are objective. This study is conducted on 10-years English Premier League between 2009–2018 data. Principal Component Analysis is going to be used for grouping the variables to perform exploratory data analysis. K-Means, hierarchical clustering, and Fuzzy C-Means are going to be used for dividing the referees into various subgroups. R programming language is used for examining data. In conclusion of the analysis, four different referee groups are defined.KeywordsFootballEnglish Premier LeagueRefereeClusteringMachine learningUnsupervised learning

In a previous study {Takagi, T. et al., Chem. Pharm. Bull., 52(12), 1427-1432 (2004)}, we applied a slightly revised neural Independent Component Analysis (ICA) for profiling illegally distributed methamphetamine. Using ICA and an hourglass type Hierarchical Neural Network (HNN), we obtained better classification results than by using Principal Component Analysis (PCA), CATegorical PCA (CATPCA) and the MultiDimensional Scaling method (MDS). The HNN is a nonlinear machine learning method, and the ICA applied in that study exhibited nonlinear characteristics. The results indicated that nonlinear analysis is more efficient than linear analysis for profiling confiscated methamphetamine. Consequently, in this study, we applied Self-Organizing Maps (SOMs) to impurity profiling of methamphetamine. While SOM is currently a frequently employed nonlinear classification method, the ordinary SOM uses only that information contained by the winner neuron for classification and the information of other grid points is neglected. We therefore attempted to simultaneously utilize the information of loser neurons in order to avoid information loss. First, we visualized the resultant reference vectors using a contour map of each sample. Although considerable information can be visually compared using the SOM contour maps, metric comparisons are difficult. We therefore used MDS to construct a similarity matrix using the data of the resultant reference vectors to visualize metric data. To assess the results, we assumed that there are four synthetic routes (Nagai, Leuckart, Emde and reductive amination methods), and that each of these can be identified by comparing route-specific impurities.

Numerical models provide a way to evaluate groundwater systems, but determining the hydrostratigraphic units (HSUs) used in constructing these models remains subjective, nonunique, and uncertain. A three-step machine-learning approach is proposed in which fusion, estimation, and clustering operations are performed on different data sets to arrive at HSUs at different scales. In step one, data fusion is performed by training a self-organizing map (SOM) with sparse borehole hydrogeologic (lithology, hydraulic conductivity, aqueous field parameters, dissolved constituents) and geophysical (gamma, spontaneous potential, and resistivity) measurements. Estimation is handled by iterative least-squares minimization of the SOM quantization and topographical errors. Application of the Davies-Bouldin criteria to k-means clustering of SOM nodes is used to determine the number and location of discontinuous borehole HSUs with low lateral density (based on borehole spacing at 100 s m) and high vertical density (based on cm-scale logging). In step two, a scaling network is trained using the estimated borehole HSUs, airborne electromagnetic measurements, and numerically inverted resistivity profiles. In step three, independent airborne electromagnetic measurements are applied to the scaling network, and the estimation performed to arrive at a set of continuous HSUs with high lateral density (based on sounding locations at meter (m) spacing) and medium vertical density (based on m-layer modeled structure). Performance metrics are used to evaluate each step of the approach. Efficacy of the proposed approach is demonstrated to map local-to-regional scale HSUs using hydrogeophysical data collected at a heterogeneous surficial aquifer in northwestern Nebraska, USA.

Enhancing the content and structure of a web site is a very important task which can help to maintain people visiting a web site and gain new visits (or customers). Web mining area helps to enhance a web site organization and contents using data mining algorithms. In particular we may perform Web Mining using a Self Organizing Feature Map (SOFM or SOM) it is always needed an analysis phase by experts. To help analysts to perform this phase after SOFMs' training, many post-processing techniques have been developed (component planes, labels, etc.); however, none of these techniques are useful when working in web mining for off-line enhancements of a web site. In this paper an algorithm called Reverse Cluster Analysis (RCA) will be provided. It aims to identify important web pages based on a self organizing feature map (SOFM) when performing web text mining (WTM) and web usage mining (WUM). We successfully applied this technique in a real web site to show its effectiveness. We have extended previous work performing a comparison with another unsupervised technique, administrators survey and an extended survey.