Wyniki wyszukiwania - BazTech

1

Learning novelty detection outside a class of random curves with application to COVID-19 growth

Rafajłowicz Wojciech

Journal of Artificial Intelligence and Soft Computing Research

|

2021

|

Vol. 11, No. 3

195--215

EN

Let a class of proper curves is specified by positive examples only. We aim to propose a learning novelty detection algorithm that decides whether a new curve is outside this class or not. In opposite to the majority of the literature, two sources of a curve variability are present, namely, the one inherent to curves from the proper class and observations errors’. Therefore, firstly a decision function is trained on historical data, and then, descriptors of each curve to be classified are learned from noisy observations.When the intrinsic variability is Gaussian, a decision threshold can be established from T2 Hotelling distribution and tuned to more general cases. Expansion coefficients in a selected orthogonal series are taken as descriptors and an algorithm for their learning is proposed that follows nonparametric curve fitting approaches. Its fast version is derived for descriptors that are based on the cosine series. Additionally, the asymptotic normality of learned descriptors and the bound for the probability of their large deviations are proved. The influence of this bound on the decision threshold is also discussed.The proposed approach covers curves described as functional data projected onto a finite-dimensional subspace of a Hilbert space as well a shape sensitive description of curves, known as square-root velocity (SRV). It was tested both on synthetic data and on real-life observations of the COVID-19 growth curves.

2

Wykrywanie anomalii bazujące na wskazanych przykładach

Kwiatkowski W.

Przegląd Teleinformatyczny

|

2018

|

T. 6, Nr 1-2 (46)

3--21

PL

Rozpatrywany jest problem wykrywania anomalii na podstawie zarejestrowanych obserwacji zachowania systemu. Problem jest sformułowany jako zadanie rozpoznawania wzorców zachowania normalnego i zachowania nietypowego. Obydwa wzorce są określane przez wskazanie odpowiednich przykładów. Osobliwość rozwiązywanego zadania wynika z faktu, że zwykle liczebność przykładów jest dużo mniejsza od wymiaru wektora obserwacji. W artykule zostały przedstawione dwie metody detekcji anomalii bazujące na wyznaczaniu rzutów obserwacji na podprzestrzenie wzorców. Wyróżnikiem pierwszej metody jest wykorzystywanie odległości wektora obserwacji od podprzestrzeni wzorców. Druga metoda polega na przeniesieniu zadania rozpoznawania wzorców do podprzestrzeni wzorców.

EN

The paper considers the issue of anomalies detection based on registered observations of a system behavior. The problem is formulated as recognition of normal and anomalous behavior patterns. Both types of patterns are identified by indication of appropriate examples. A peculiarity of this task is that usually the number of examples is far lower than the dimension of vectors describing the observations. Two methods to solve this task have been presented in the paper, based on projecting the observations on the subspace of examples. The first method is based on a distance of the observation vector from the subspace of examples. The second method is based on transferring the pattern recognition problem to the subspace of examples.

3

A novelty detection approach to monitoring of epicyclic gearbox health

Dworakowski Z., Dziedziech K., Jabłoński A.

Metrology and Measurement Systems

|

2018

|

Vol. 25, nr 3

459--473

EN

Reliable monitoring for detection of damage in epicyclic gearboxes is a serious concern for all industries in which these gearboxes operate in a harsh environment and in variable operational conditions. In this paper, autonomous multidimensional novelty detection algorithms are used to estimate the gearbox’ health state based on vectors of features calculated from the vibration signal. The authors examine various feature vectors, various sources of data and many different damage scenarios in order to compare novel detection algorithms based on three different principles of operation: a distance in the feature space, a probability distribution, and an ANN (artificial neural network)-based model reconstruction approach. In order to compensate for non-deterministic results of training of neural networks, which may lead to different network performance, the ensemble technique is used to combine responses from several networks. The methods are tested in a series of practical experiments involving implanting a damage in industrial epicyclic gearboxes, and acquisition of data at variable speed conditions.

4

Fabric Defect Detection Using a Hybrid and Complementary Fractal Feature Vector and FCM-based Novelty Detector

Zhou J., Wang J., Bu H.

Fibres & Textiles in Eastern Europe

|

2017

|

Vol. 25, no. 6 (126)

46--52

EN

Automated detect detection in woven fabrics for quality control is still a challenging novelty detection problem. This work presents five novel fractal features based on the box-counting dimension to address the novelty detection of fabric defect. Making use of the formation of woven fabric, the fractal features are extracted in a one-dimension series obtained by projecting a fabric image along the warp and weft directions, where their complementarity in discriminating defects is taken into account. Furthermore a new novelty detector based on fuzzy c-means (FCM) is devised to deal with one-class classification of the features extracted. Finally, by jointly applying the features proposed and the FCM based novelty detector, we evaluate the method proposed for eight datasets with different defects and textures, where satisfying results are achieved with a low overall missing detection rate.

PL

Automatyczne wykrywanie defektów tkanin w celu kontroli ich jakości mimo wielu dotychczasowych badań nadal stanowi wyzwanie. Mając na celu opracowanie nowatorskiej metody wykrywaniem wad tkanin przedstawiono pięć cech fraktalnych. W celu klasyfikacji wyodrębnionych cech opracowano detektor wad tkanin oparty na zbiorze rozmytym wartości średnich (FCM). Poprzez wspólne zastosowanie proponowanych cech i opartego na FCM detektorze sprawdzono proponowaną metodę dla ośmiu zestawów danych z różnymi defektami i teksturami. Stwierdzono, że otrzymane wyniki są na satysfakcjonującym poziomie.

5

Human gait pattern changes detection system: A multimodal vision-based and novelty detection learning approach

Paulo J., Asvadi A., Peixoto P., Amorim P.

Biocybernetics and Biomedical Engineering

|

2017

|

Vol. 37, no. 4

701--717

EN

This paper proposes a novel gait rehabilitation analysis system, based on an innovative multimodal vision-based sensor setup, focused on detecting gait pattern changes over time. The proposed setup is based on inexpensive technologies, without compromising performance, and was designed to be deployed on walkers, which are a typical assistive aid used in gait rehabilitation. In the medical field the evaluation of a patient's rehabilitation progress is typically performed by a medical professional through subjective techniques based on the professional's visual perception and experience. In this context, we are proposing an automatic system to detect the progress of patients undergoing rehabilitation therapy. Our approach is able to perform novelty detection for gait pattern classification based on One- Class Support Vector Machines (OC-SVM). Using point-cloud and RGB-D data, we detect the lower limbs (waist, legs and feet) by using Weighted Kernel-Density Estimation and Weighted Least-Squares to segment the legs into several parts (thighs and shins), and by fitting 3D ellipsoids to model them. Feet are detected using k-means clustering and a Circular Hough Transform. A temporal analysis of the feet's depth is also performed to detect heel strike events. Spatiotemporal and kinematic features are extracted from the lower limbs' model and fed to a classifier based on the fusion of several OC-SVMs. Experiments with volunteers using the robotic walker platform ISR-AIWALKER, where the proposed system was deployed, revealed a lower limbs tracking accuracy of 38 and that our novelty detection approach successfully identified novel gait patterns, evidencing an overall 97.89% sensitivity.

6

Gaussian mixture model for time series-based structural damage detection

Słoński M.

Computer Assisted Methods in Engineering and Science

|

2012

|

Vol. 19, no. 4

331-338

EN

In this paper, a time series-based damage detection algorit hm is proposed using Gaussian mixture model (GMM) and expectation maximization (EM) framework. The vib ration time series from the structure are modelled as the autoregressive (AR) processes. The first AR coefficients are used as a feature vector for novelty detection. To test the efficacy of the damage detec tion algorithm, it has been tested on the pseudo-experimental data obtained from the FEM model of the ASCE benchmark frame structure. Results suggest that the presented approach is able to detect mainly major and moderate damage patterns

7

Random projection RBF nets for multidimensional density estimation

Skubalska-Rafajłowicz E.

International Journal of Applied Mathematics and Computer Science

|

2008

|

Vol. 18, no 4

455-464

EN

The dimensionality and the amount of data that need to be processed when intensive data streams are observed grow rapidly together with the development of sensors arrays, CCD and CMOS cameras and other devices. The aim of this paper is to propose an approach to dimensionality reduction as a first stage of training RBF nets. As a vehicle for presenting the ideas, the problem of estimating multivariate probability densities is chosen. The linear projection method is briefly surveyed. Using random projections as the first (additional) layer, we are able to reduce the dimensionality of input data. Bounds on the accuracy of RBF nets equipped with a random projection layer in comparison to RBF nets without dimensionality reduction are established. Finally, the results of simulations concerning multidimensional density estimation are briefly reported.