Nearest-neighbor Decision Research Articles

Augmented reality and indoor positioning based mobile production monitoring system to support workers with human-in-the-loop

With the increasing demand for product customization, the exponential increase in large-scale and small-batch production orders has yielded new challenges for the capacity of traditional production lines. Due to the information redundancy and complex production process on the production site of the factory, the traditional monitoring system is incapable of meeting the information interaction requirements between the factory management level and the executive level. Meanwhile, the traditional augmented reality (AR) based on image recognition is not suitable in the complex industrial environments. To address the gap, we propose a novel mobile production monitoring system (AIMPMs) with human-in-the-loop control by leveraging the cutting-edge AR and indoor positioning technique. In the proposed system, Ultra-wideband (UWB) and Inertial Measurement Unit (IMU) fusion indoor positioning technology is proposed, which provides accurate indoor positioning information for the production factors in the factory. Subsequently, we build the lightweight indoor map for positioning that can serve as the location reference and path planning, and a nearest-neighbor decision algorithm with double rejection decision (NN-DRD) is proposed to match the positioning features to trigger virtual monitoring information. Finally, the AIMPMs is applied in a hydraulic cylinder factory to verify its enforceability and effectiveness, and the human factors evaluation model and index system are constructed to evaluate two systems, (1) the mobile monitoring system based on positioning information, and (2) the mobile monitoring system based on image recognition, respectively. The experimental results indicate that after the application of AIMPMs, the physiological and mental fatigue of the production personnel is immensely decreased. Therefore, the system realizes a smarter and highly humanized human-machine interaction mode with human-in-the-loop control.

Global Optimization: Combining Local Loss With Result Ranking Loss in Remote Sensing Image Retrieval

With the explosive growth of remote sensing big data, large-scale remote sensing image retrieval (RSIR) has become one of the most challenging tasks in data mining, attracting more and more attention from researchers. In recent years, deep learning has achieved fruitful results in RSIR. However, there are three major problems. The first problem is due to the imbalanced categories in RSIR data sets. Accordingly, a novel sample mining method is proposed. This method is based on top- <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$k$ </tex-math></inline-formula> “misplaced” samples (Top- <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$k$ </tex-math></inline-formula> MS) along the top- <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$k$ </tex-math></inline-formula> nearest neighbor decision boundary, rather than setting boundary threshold of sample mining and reducing the impact of artificial and objective factors on network training as usual. The second problem comes from the inconsistency between the loss reduction direction and the optimization direction. In response, we additionally propose a novel result ranking loss (RRL) according to the retrieval results in a batch. RRL is used as a plug-in and combined with other local losses. As a result, the retrieval accuracy improved significantly. For the third problem, processing a large number of high-resolution images will increase training time and cause network freeze. To solve the problem, this article proposes a global optimization model based on feature space and retrieval results (FSRR). More specifically, FSRR consists of local loss based on feature space and RRL based on retrieval results, and can be optimized in an end-to-end manner. Experimental results show that our proposed algorithm achieves the best performance when compared with other state-of-the-art deep RSIR algorithms on two benchmark data sets.

On Some Fuzzy Classification Algorithms and the AEC Model

In the paper some fuzzy classification algorithms based upon a nearest neighbor decision rule areconsidered in terms of the pattern recognition algorithms which are based on the computation of estimates (theso-called AEC model). It is shown that the fuzzy K nearest neighbor algorithm can be assigned to the AECclass. In turn, it is found that some standard AEC algorithms, which depend on a number of numericalparameters, can be used as fuzzy classification algorithms. Yet among them there exist algorithms extremalwith respect to these parameters. Such algorithms provide maximum values of the associated performancemeasures.

A medoid-based weighting scheme for nearest-neighbor decision rule toward effective text categorization

The k-nearest-neighbor (kNN) decision rule is a simple and robust classifier for text categorization. The performance of kNN decision rule depends heavily upon the value of the neighborhood parameter k. The method categorize a test document even if the difference between the number of members of two competing categories is one. Hence, choice of k is crucial as different values of k can change the result of text categorization. Moreover, text categorization is a challenging task as the text data are generally sparse and high dimensional. Note that, assigning a document to a predefined category for an arbitrary value of k may not be accurate when there is no bound on the margin of majority voting. A method is thus proposed in spirit of the nearest-neighbor decision rule using a medoid-based weighting scheme to deal with these issues. The method puts more weightage on the training documents that are not only lie close to the test document but also lie close to the medoid of its corresponding category in decision making, unlike the standard nearest-neighbor algorithms that stress on the documents that are just close to the test document. The aim of the proposed classifier is to enrich the quality of decision making. The empirical results show that the proposed method performs better than different standard nearest-neighbor decision rules and support vector machine classifier using various well-known text collections in terms of macro- and micro-averaged f-measure.

Novel Algorithm for Hand Gesture Recognition Utilizing a Wrist-Worn Inertial Sensor

In this paper, we propose a dynamic time warping (DTW)-based template matching method with a novel template generation algorithm for hand gesture recognition utilizing a wrist-worn inertial sensor. Hand orientation measurements are utilized to reconstruct gesture trajectories. The DTW technique with the Riemannian distance is employed to perform similarity measurements between gesture orientation trajectories. The proposed gesture recognition algorithm comprises three stages: a data preprocessing stage, a training stage, and a recognition stage. First, a moving intrinsic average filter is introduced to suppress the effects of measurement noise and unconscious hand shaking. Next, a double-threshold segmentation scheme is applied to extract individual gesture segments. In the training stage, to cope with temporal and spatial variations in gestures, an adaptive DTW barycenter averaging algorithm combined with an intrinsic averaging method is developed to generate gesture templates. A suitable rejection threshold is determined according to intra-class DTW distances. In the recognition stage, the rejection percentage between the input gesture and each gesture template is calculated. Finally, the nearest neighbor decision rule is applied to determine the recognition result. Experiments performed on a database of 3600 gesture samples illustrate that the proposed DTW-based gesture template generation and classification algorithm outperforms existing methods.

A Novel Regular-image Mosaic Method

This paper presents a novel regular image mosaic method. Firstly, select the reference images which have the same characteristic. Then, calculate the mean Euclidean distance (or the mean city-block distance) between the reference images and the rest images. Besides, the least Euclidean distance (or the least mean city-block distance) can be found out, as well as the image corresponding to the minimum. Then, put the two images together and check the rationality of the mosaic process according to the nearest neighbor decision rule based on the distance function. Next, repeat the above operations until the final image can be obtained. At last, a experiment has been done to check the rationality of this method. The experimental results show that this image mosaic method is suitable for regular images. This novel image mosaic process is highly-efficient and its accuracy is high.

Condensed Nearest Neighbor Decision Rule Input Weight Sequential Feed-Forward Neural Networks

This paper proposes a new approach is referred to as condensed nearest neighbor decision rule (CNN) input weight sequential feed-forward neural networks (CIW-SFFNS). In this paper, it is firstly shown that the difference of optimization constraints between the extreme learning machine (ELM) and constrained-optimization-based extreme learning machine. For the second time, this paper proposes a method that using CNN to select the hidden-layer weights from example. Moreover, we compare error minimized extreme learning machines (EM-ELM), support vector sequential feed-forward neural networks (SV-SFFNS) and CIW-SFFNS from two aspects:test accuracy and the number of hidden nodes. We present the result of an experimental study on 10 classification sets. The CIW-SFFNS algorithm has a statistically significant improvement in generalization performance than EM-ELM and SV-SFFNS.

Alhazen and the nearest neighbor rule

We show that a clear formulation of the nearest neighbor decision rule for pattern classification can be found, along with other remarkably modern ideas, in an influential medieval treatise on visual perception authored by Alhazen, one of the major figures in the so-called “Islamic golden age.” To put the work in context we provide also a brief description of some of the salient points of Alhazen’s theory.

An Instance Selection Algorithm Based On Reverse k Nearest Neighbor

Classification is one of the most important data mining techniques. It belongs to supervised learning. The objective of classification is to assign class label to unlabelled data. As data is growing rapidly, handling it has become a major concern. So preprocessing should be done before classification and hence data reduction is essential. Data reduction is to extract a subset of features from a set of features of a data set. Data reduction helps in decreasing the storage requirement and increases the efficiency of classification. A way to measure data reduction is reduction rate. The main thing here is choosing representative samples to the final data set. There are many instance selection algorithms which are based on nearest neighbor decision rule (NN). These algorithms select samples on incremental strategy or decremental strategy. Both the incremental algorithms and decremental algorithms take much processing time as they iteratively scan the dataset. There is another instance selection algorithm, reverse nearest neighbor reduction (RNNR) based on the concept of reverse nearest neighbor (RNN). RNNR does not iteratively scan the data set. In this paper, we extend the RNN to RkNN and we use the concept of RNNR to RkNN. RkNN finds the query objects that has the query point as their k nearest-neighbors. Our approach utilizes the advantage of RNN and proposes to use the concept of RkNN. We have taken the dataset of theatres, hospitals and restaurants and extracted the sample set. Classification has been done the resultant sample data set. We observe two parameters here they are classification accuracy and reduction rate.

Nearest Neighbor-Based Classification of Uncertain Data

This work deals with the problem of classifying uncertain data. With this aim we introduce the Uncertain Nearest Neighbor (UNN) rule, which represents the generalization of the deterministic nearest neighbor rule to the case in which uncertain objects are available. The UNN rule relies on the concept of nearest neighbor class, rather than on that of nearest neighbor object. The nearest neighbor class of a test object is the class that maximizes the probability of providing its nearest neighbor. The evidence is that the former concept is much more powerful than the latter in the presence of uncertainty, in that it correctly models the right semantics of the nearest neighbor decision rule when applied to the uncertain scenario. An effective and efficient algorithm to perform uncertain nearest neighbor classification of a generic (un)certain test object is designed, based on properties that greatly reduce the temporal cost associated with nearest neighbor class probability computation. Experimental results are presented, showing that the UNN rule is effective and efficient in classifying uncertain data.

Classification of Man-Made Targets via Invariant Coherency-Matrix Eigenvector Decomposition of Polarimetric SAR/ISAR Images

In this paper, the problem of classifying nonhomogeneous man-made targets is investigated by performing a macroscopic and detailed target analysis. The Cloude-Pottier H/ α <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ML</sub> decomposition is used as a starting point in order to find orientation-invariant feature vectors that are able to represent the average polarimetric structure of complex targets. A novel supervised classification scheme based on nearest neighbor decision rule is then designed, which makes use of the feature space. A validation process is performed by analyzing experimental data of simple targets collected in an anechoic chamber and airborne EMISAR images of eight ships. Three classification robustness performance indicators have been evaluated for each feature vector by performing the leaves-one-out-method described by Mitchell and Westerkamp. The robustness of the classifier has been tested with respect to the ability to reject unknown targets and to correctly identify known targets.

Supervised classification of multispectral remote sensing images based on the nearest reduced convex hull approach

In this paper, we propose a novel learning algorithm, the nearest reduced convex hull (NRCH), to tackle the issue of limited training information in practical remote sensing. Before classification, the "underlying" prototypes in the training subspace of each class are approximated by constrained convex combinations of the "existing" ones of this class. By this means, the original training set of each class is eventually expanded to a reduced convex hull (RCH) manifold through which the representational capacity of the training set is greatly enlarged. During this process, good separations of different classes are well maintained by the reduced factor. Based on these RCHs, the nearest neighbor decision rule is then utilized to classify a query sample. Experimental results, obtained on different kinds of data (synthetic data and real multispectral images), show the potential of NRCH for remote sensing classification in comparison with some famous traditional classifiers including Maximum Likelihood Classifier (MLC), Back-propagation Neural Network Classifier (BP), and Support Vector Machine (SVM).

THE SZNAJD MODEL WITH TEAM WORK

In 2000, Sznajd-weron and Sznajd introduced a model for the simulation of a closed democratic community with a two-party system, and it is found that a closed community has to evolve either to a dictatorship or a stalemate state. In this paper, we continued to study on this model. All the neighboring individuals holding the same opinion is defined as a team, which will influence its nearest neighbor's decision and realize the opinion evolution. After some time-steps, a steady state appeared and the stalemate state in original model is eliminated. Moreover, the demand of time-steps has decreased dramatically. In addition, we also analyzed the effect of the various dispersal degree of the initial opinion on the opinion converging at the probability of one steady state. Finally we analyzed the effect of noise on convergence and found that the ability of anti-noise was increased about 1000 times compared with Sznajd model.

Fast Nearest Neighbor Condensation for Large Data Sets Classification

This work has two main objectives, namely, to introduce a novel algorithm, called the fast condensed nearest neighbor (FCNN) rule, for computing a training-set-consistent subset for the nearest neighbor decision rule and to show that condensation algorithms for the nearest neighbor rule can be applied to huge collections of data. The FCNN rule has some interesting properties: it is order independent, its worst-case time complexity is quadratic but often with a small constant prefactor, and it is likely to select points very close to the decision boundary. Furthermore, its structure allows for the triangle inequality to be effectively exploited to reduce the computational effort. The FCNN rule outperformed even here-enhanced variants of existing competence preservation methods both in terms of learning speed and learning scaling behavior and, often, in terms of the size of the model while it guaranteed the same prediction accuracy. Furthermore, it was three orders of magnitude faster than hybrid instance-based learning algorithms on the MNIST and Massachusetts Institute of Technology (MIT) Face databases and computed a model of accuracy comparable to that of methods incorporating a noise-filtering pass.

Visual Artificial Tongue for Quantitative Metal‐Cation Analysis by an Off‐the‐Shelf Dye Array

A chemical-probe array composed of 47 off-the-shelf dyes was prepared in solution format (New York Tongue 1: NYT-1) and was tested in the identification and quantitation of 47 cation analytes, including 44 metal ions, in addition to H(+), NH(4) (+), and tetrabutylammonium (TBA). The cation solutions were tested in a series of concentrations and the fold-change in effective absorbance was analyzed by principal-component analysis (PCA), hierarchical-cluster analysis (HCA), and nearest-neighbor decision to determine both identity and quantity of the analytes. Apart from alkali-metal ions (Na(+), K(+), Li(+), Cs(+), and Rb(+)), which behave very similarly to each other due mainly to their low response, most of the cations were clearly distinguishable at 10 mM concentration. The practical detection limit of each analyte was also determined by a sequential dilution and the nearest-neighbor decision method. In the finalized working analyte concentration range (approximately 10 mM down to 0.33 microM), by considering alkali metals as one analyte group, most of the analytes were correctly identified (99.4 %). Furthermore, the success rate at which the concentration of each analyte was correctly determined was also high (96.8 %).

GEOMETRIC PROXIMITY GRAPHS FOR IMPROVING NEAREST NEIGHBOR METHODS IN INSTANCE-BASED LEARNING AND DATA MINING

In the typical nonparametric approach to classification in instance-based learning and data mining, random data (the training set of patterns) are collected and used to design a decision rule (classifier). One of the most well known such rules is the k-nearest-neighbor decision rule (also known as lazy learning) in which an unknown pattern is classified into the majority class among its k nearest neighbors in the training set. Several questions related to this rule have received considerable attention over the years. Such questions include the following. How can the storage of the training set be reduced without degrading the performance of the decision rule? How should the reduced training set be selected to represent the different classes? How large should k be? How should the value of k be chosen? Should all k neighbors be equally weighted when used to decide the class of an unknown pattern? If not, how should the weights be chosen? Should all the features (attributes) we weighted equally and if not how should the feature weights be chosen? What distance metric should be used? How can the rule be made robust to overlapping classes or noise present in the training data? How can the rule be made invariant to scaling of the measurements? How can the nearest neighbors of a new point be computed efficiently? What is the smallest neural network that can implement nearest neighbor decision rules? Geometric proximity graphs such as Voronoi diagrams and their many relatives provide elegant solutions to these problems, as well as other related data mining problems such as outlier detection. After a non-exhaustive review of some of the classical canonical approaches to these problems, the methods that use proximity graphs are discussed, some new observations are made, and open problems are listed.

Three-dimensional distortion-tolerant object recognition using integral imaging

This paper addresses 3D distortion-tolerant object recognition using Integral Imaging (II). II is one of the techniques considered for 3D image recording and display. Multiple elemental images are captured to record different but continuous viewing zones of 3D scenes. We develop a distortion-tolerant 3D object recognition by using the II capture system. We adopt Principal Component Analysis (PCA) and Fisher Linear Discriminant (FLD) classifier followed by the nearest neighbor decision rule and the statistical distance metric. Performance is analyzed in terms of probability of correct decision, Root Mean Square Error (RMSE) between raw input vectors and reconstructed vectors from the PCA subspace and the PCA-FLD cost function. Decision strategies are compared by the varying number of training data.

A counterexample to Tomek's consistency theorem for a condensed nearest neighbor decision rule

The condensed nearest neighbor rule (CNN) was proposed by Hart (1968) as a method to reduce the storage requirements of the original data set D for the efficient implementation of the nearest neighbor decision rule in pattern classification problems. Tomek (1976a) suggested two modifications of CNN in order to improve its performance. As a first step in Tomek's second method he computes a subset C of D, for subsequent use in CNN, and claims that C is training-set-consistent, i.e., that all data points in D are correctly classified by the nearest neighbor rule using C. In this note we provide a counterexample to this claim. We also analyze Tomek's algorithm in the context of more recent graph-theoretical condensing schemes.

Minimal consistent set (MCS) identification for optimal nearest neighbor decision systems design

A new approach is presented in this study for tackling the problem of high computational demands of nearest neighbor (NN) based decision systems. The approach, based on the concept of an optimal subset selection from a given training data set, derives a consistent subset which is aimed to be minimal in size. This minimal consistent subset (MCS) selection, in contrast to most of the other previous attempts of this nature, leads to an unique solution irrespective of the initial order of presentation of the data. Further, consistency property is assured at every iteration. Also, unlike under most prior approaches, the samples are selected here in the order of significance of their contribution for enabling the consistency property. This provides insight into the relative significance of the samples in the training set. Experimental results based on a number of independent training and test data sets are presented and discussed to illustrate the methodology and bring to focus its benefits. These results show that the nearest neighbor decision system performance suffers little degradation when the given large training set is replaced by its much smaller MCS in the operational phase of testing with an independent test set. A direct experimental comparison with a prior approach is also furnished to further strengthen the case for the new methodology.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

Differential competitive learning for centroid estimation and phoneme recognition

A comparison is made of a differential-competitive-learning (DCL) system with two supervised competitive-learning (SCL) systems for centroid estimation and for phoneme recognition. DCL provides a form of unsupervised adaptive vector quantization. Standard stochastic competitive-learning systems learn only if neurons win a competition for activation induced by randomly sampled patterns. DCL systems learn only if the competing neurons change their competitive signal. Signal-velocity information provides unsupervised local reinforcement during learning. The sign of the neuronal signal derivative rewards winners and punishes losers. Standard competitive learning ignores instantaneous win-rate information. Synaptic fan-in vectors adaptively quantize the randomly sampled pattern space into nearest-neighbor decision classes. More generally, the synaptic-vector distribution estimates the unknown sampled probability density function p( x). Simulations showed that unsupervised DCL-trained synaptic vectors converged to class centroids at least as fast as, and wandered less about these centroids than, SCL-trained synaptic vectors did. Simulations on a small set of English phonemes favored DCL over SCL for classification accuracy.