Practical, Computation Efficient High-Order Neural Network for Rotation and Shift Invariant Pattern Recognition

In this paper, a modification for the high-order neural network (HONN) is presented. Third order networks are considered for achieving translation, rotation and scale invariant pattern recognition. They require however much storage and computation power for the task. The proposed modified HONN takes into account a priori knowledge of the binary patterns that have to be learned, achieving significant gain in computation time and memory requirements. This modification enables the efficient computation of HONNs for image fields of greater that 100 × 100 pixels without any loss of pattern information.

About New Pattern Recognition Method for the Universal Program System “Recognition”

In this work the new pattern recognition method based on the unification of algebraic and statistical approaches is described. The main point of the method is the voting procedure upon the statistically weighted regularities, which are linear separators in two-dimensional projections of feature space. The report contains brief description of the theoretical foundations of the method, description of its software realization and the results of series of experiments proving its usefulness in practical tasks.

Detection of seismic damage in buildings using time series analysis and pattern recognition

Peer reviewed

The application of PCA as a movement pattern recognition technique: A proof of principle

Quantitative methods can help us understand how underlying attributes contribute to movement patterns. Applying principal components analysis (PCA) to whole-body motion data may provide an objective data-driven method to identify unique and statistically important movement patterns. Therefore, the primary purpose of this study was to determine if athletes’ movement patterns can be differentiated based on skill level or sport played using PCA. Motion capture data from 542 athletes performing three sport-screening movements (i.e. bird-dog, drop jump, T-balance) were analyzed. A PCA-based pattern recognition technique was used to analyze the data. Prior to analyzing the effects of skill level or sport on movement patterns, methodological considerations related to motion analysis reference coordinate system were assessed. All analyses were addressed as case-studies. For the first case study, referencing motion data to a global (lab-based) coordinate system compared to a local (segment-based) coordinate system affected the ability to interpret important movement features. Furthermore, for the second case study, where the interpretability of PCs was assessed when data were referenced to a stationary versus a moving segment-based coordinate system, PCs were more interpretable when data were referenced to a stationary coordinate system for both the bird-dog and T-balance task. As a result of the findings from case study 1 and 2, only stationary segment-based coordinate systems were used in cases 3 and 4. During the bird-dog task, elite athletes had significantly lower scores compared to recreational athletes for principal component (PC) 1. For the T-balance movement, elite athletes had significantly lower scores compared to recreational athletes for PC 2. In both analyses the lower scores in elite athletes represented a greater range of motion. Finally, case study 4 reported differences in athletes’ movement patterns who competed in different sports, and significant differences in technique were detected during the bird-dog task. Through these case studies, this thesis highlights the feasibility of applying PCA as a movement pattern recognition technique in athletes. Future research can build on this proof-of-principle work to develop robust quantitative methods to help us better understand how underlying attributes (e.g. height, sex, ability, injury history, training type) contribute to performance.

Age estimation in common sole Solea solea larvae: validation of daily increments and evaluation of a pattern recognition technique

Close similarities have been found between the otoliths of sea-caught and laboratory-reared larvae of the common sole Solea solea (L.), given appropriate temperatures and nourishment of the latter. But from hatching to mouth formation. and during metamorphosis, sole otoliths have proven difficult to read because the increments may be less regular and low contrast. In this study, the growth increments in otoliths of larvae reared at 12 degrees C were counted by light microscopy to test the hypothesis of daily deposition, with some results verified using scanning electron microscopy (SEM), and by image analysis in order to compare the reliability of the 2 methods in age estimation. Age was first estimated (in days posthatch) from light micrographs of whole mounted otoliths. Counts were initiated from the increment formed at the time of month opening (Day 4). The average incremental deposition rate was consistent with the daily hypothesis. However, the light-micrograph readings tended to underestimate the mean ages of the larvae. Errors were probably associated with the low-contrast increments: those deposited after the mouth formation during the transition to first feeding, and those deposited from the onset of eye migration (about 20 d posthatch) during metamorphosis. SEM failed to resolve these low-contrast areas accurately because of poor etching. A method using image analysis was applied to a subsample of micrograph-counted otoliths. The image analysis was supported by an algorithm of pattern recognition (Growth Demodulation Algorithm, GDA). On each otolith, the GDA method integrated the growth pattern of these larval otoliths to averaged data from different radial profiles, in order to demodulate the exponential trend of the signal before spectral analysis (Fast Fourier Transformation, FFT). This second method both allowed more precise designation of increments, particularly for low-contrast areas, and more accurate readings but increased error in mean age estimation. The variability is probably due to a still rough perception of otolith increments by the GDA method, counting being achieved through a theoretical exponential pattern and mean estimates being given by FFT. Although this error variability was greater than expected, the method provides for improvement in both speed and accuracy in otolith readings.

Innate immune humoral factors, C1q and factor H, with differential pattern recognition properties, alter macrophage response to carbon nanotubes

Interaction between the complement system and carbon nanotubes (CNTs) can modify their intended biomedical applications. Pristine and derivatised CNTs can activate complement primarily via the classical pathway which enhances uptake of CNTs and suppresses pro-inflammatory response by immune cells. Here, we report that the interaction of C1q, the classical pathway recognition molecule, with CNTs involves charge pattern and classical pathway activation that is partly inhibited by factor H, a complement regulator. C1q and its globular modules, but not factor H, enhanced uptake of CNTs by macrophages and modulated the pro-inflammatory immune response. Thus, soluble complement factors can interact differentially with CNTs and alter the immune response even without complement activation. Coating CNTs with recombinant C1q globular heads offers a novel way of controlling classical pathway activation in nanotherapeutics. Surprisingly, the globular heads also enhance clearance by phagocytes and down-regulate inflammation, suggesting unexpected complexity in receptor interaction. From the Clinical Editor: Carbon nanotubes (CNTs) maybe useful in the clinical setting as targeting drug carriers. However, it is also well known that they can interact and activate the complement system, which may have a negative impact on the applicability of CNTs. In this study, the authors functionalized multi-walled CNT (MWNT), and investigated the interaction with the complement pathway. These studies are important so as to gain further understanding of the underlying mechanism in preparation for future use of CNTs in the clinical setting.

Pattern recognition methods for EMG prosthetic control

In this work we focus on pattern recognition methods related to EMG upper-limb prosthetic control. After giving a detailed review of the most widely used classification methods, we propose a new classification approach. It comes as a result of comparison in the Fourier analysis between able-bodied and trans-radial amputee subjects. We thus suggest a different classification method which considers each surface electrodes contribute separately, together with five time domain features, obtaining an average classification accuracy equals to 75% on a sample of trans-radial amputees. We propose an automatic feature selection procedure as a minimization problem in order to improve the method and its robustness.

Tecniche di apprendimento automatico per la ricerca di eventi top-top con l’esperimento ATLAS a LHC

Il Modello Standard è attualmente la teoria che meglio spiega il comportamento della fisica subnucleare, includendo la definizione delle particelle e di tre delle quattro forze fondamentali presenti in natura; risulta però una teoria incompleta sulle cui integrazioni i fisici stanno lavorando in diverse direzioni: uno degli approcci più promettenti nella ricerca di nuova fisica risulta essere quello delle teorie di campo efficaci. Il vertice di interazione del processo di produzione di coppie di quark top dello stesso segno a partire da protoni è fortemente soppresso nel Modello Standard e deve quindi essere interpretato con le teorie di campo efficaci. Il presente elaborato si concentra su questo nuovo approccio per la ricerca di quark top same-sign e si focalizza sull’utilizzo di una rete neurale per discriminare il segnale dal fondo. L’obiettivo è capire se le prestazioni di quest’ultima cambino quando le vengono fornite in ingresso variabili di diversi livelli di ricostruzione. Utilizzando una rete neurale ottimizzata per la discriminazione del segnale dal fondo, le si sono presentati tre set di variabili per l’allenamento: uno di alto livello, il secondo strettamente di basso livello, il terzo copia del secondo con aggiunta delle due variabili principali di b-tagging. Si è dimostrato che la performance della rete in termini di classificazione segnale-fondo rimane pressoché inalterata: la curva ROC presenta aree sottostanti le curve pressoché identiche. Si è notato inoltre che nel caso del set di variabili di basso livello, la rete neurale classifica come input più importanti gli angoli azimutali dei leptoni nonostante questi abbiano distribuzioni identiche tra segnale e fondo: ciò avviene in quanto la rete neurale è in grado di sfruttare le correlazioni tra le variabili come caratteristica discriminante. Questo studio preliminare pone le basi per l’ottimizzazione di un approccio multivariato nella ricerca di eventi con due top dello stesso segno prodotti a LHC.

Comparison of EEG signals from epilepsy patients with Bump modeling

Background: l’epilessia è una malattia cerebrale che colpisce oggigiorno circa l’1% della popolazione mondiale e causa, a chi ne soffre, convulsioni ricorrenti e improvvise che danneggiano la vita quotidiana del paziente. Le convulsioni sono degli eventi che bloccano istantaneamente la normale attività cerebrale; inoltre differiscono tra i pazienti e, perciò, non esiste un trattamento comune generalizzato. Solitamente, medici neurologi somministrano farmaci, e, in rari casi, l’epilessia è trattata con operazioni neurochirurgiche. Tuttavia, le operazioni hanno effetti positivi nel ridurre le crisi, ma raramente riescono a eliminarle del tutto. Negli ultimi anni, nel campo della ricerca scientifica è stato provato che il segnale EEG contiene informazioni utili per diagnosticare l'arrivo di un attacco epilettico. Inoltre, diversi algoritmi automatici sono stati sviluppati per rilevare automaticamente le crisi epilettiche. Scopo: lo scopo finale di questa ricerca è l'applicabilità e l'affidabilità di un dispositivo automatico portatile in grado di rilevare le convulsioni e utilizzabile come sistema di monitoraggio. L’analisi condotta in questo progetto, è eseguita con tecniche di misure classiche e avanzate, in modo tale da provare tecnicamente l’affidabilità di un tale sistema. La comparazione è stata eseguita sui segnali elettroencefalografici utilizzando due diversi sistemi di acquisizione EEG: il metodo standard utilizzato nelle cliniche e il nuovo dispositivo portatile. Metodi: è necessaria una solida validazione dei segnali EEG registrati con il nuovo dispositivo. I segnali saranno trattati con tecniche classiche e avanzate. Dopo le operazioni di pulizia e allineamento, verrà utilizzato un nuovo metodo di rappresentazione e confronto di segnali : Bump model. In questa tesi il metodo citato verrà ampiamente descritto, testato, validato e adattato alle esigenze del progetto. Questo modello è definito come un approccio economico per la mappatura spazio-frequenziale di wavelet; in particolare, saranno presenti solo gli eventi con un’alta quantità di energia. Risultati: il modello Bump è stato implementato come toolbox su MATLAB dallo sviluppatore F. Vialatte, e migliorato dall’Autore per l’utilizzo di registrazioni EEG da sistemi diversi. Il metodo è validato con segnali artificiali al fine di garantire l’affidabilità, inoltre, è utilizzato su segnali EEG processati e allineati, che contengono eventi epilettici. Questo serve per rilevare la somiglianza dei due sistemi di acquisizione. Conclusioni: i risultati visivi garantiscono la somiglianza tra i due sistemi, questa differenza la si può notare specialmente comparando i grafici di attività background EEG e quelli di artefatti o eventi epilettici. Bump model è uno strumento affidabile per questa applicazione, e potrebbe essere utilizzato anche per lavori futuri (ad esempio utilizzare il metodo di Sincronicità Eventi Stocas- tici SES) o differenti applicazioni, così come le informazioni estratte dai Bump model potrebbero servire come input per misure di sincronicità, dalle quali estrarre utili risultati.

Prion crystalization model and its application to recognition pattern

This paper introduces APA (?Artificial Prion Assembly?): a pattern recognition system based on artificial prion crystalization. Specifically, the system exhibits the capability to classify patterns according to the resulting prion self- assembly simulated with cellular automata. Our approach is inspired in the biological process of proteins aggregation, known as prions, which are assembled as amyloid fibers related with neurodegenerative disorders.

Data-driven Signal Processing per Jamming Detection in Sistemi Satellitari

In questo elaborato vengono analizzate differenti tecniche per la detection di jammer attivi e costanti in una comunicazione satellitare in uplink. Osservando un numero limitato di campioni ricevuti si vuole identificare la presenza di un jammer. A tal fine sono stati implementati i seguenti classificatori binari: support vector machine (SVM), multilayer perceptron (MLP), spectrum guarding e autoencoder. Questi algoritmi di apprendimento automatico dipendono dalle features che ricevono in ingresso, per questo motivo è stata posta particolare attenzione alla loro scelta. A tal fine, sono state confrontate le accuratezze ottenute dai detector addestrati utilizzando differenti tipologie di informazione come: i segnali grezzi nel tempo, le statistical features, le trasformate wavelet e lo spettro ciclico. I pattern prodotti dall’estrazione di queste features dai segnali satellitari possono avere dimensioni elevate, quindi, prima della detection, vengono utilizzati i seguenti algoritmi per la riduzione della dimensionalità: principal component analysis (PCA) e linear discriminant analysis (LDA). Lo scopo di tale processo non è quello di eliminare le features meno rilevanti, ma combinarle in modo da preservare al massimo l’informazione, evitando problemi di overfitting e underfitting. Le simulazioni numeriche effettuate hanno evidenziato come lo spettro ciclico sia in grado di fornire le features migliori per la detection producendo però pattern di dimensioni elevate, per questo motivo è stato necessario l’utilizzo di algoritmi di riduzione della dimensionalità. In particolare, l'algoritmo PCA è stato in grado di estrarre delle informazioni migliori rispetto a LDA, le cui accuratezze risentivano troppo del tipo di jammer utilizzato nella fase di addestramento. Infine, l’algoritmo che ha fornito le prestazioni migliori è stato il Multilayer Perceptron che ha richiesto tempi di addestramento contenuti e dei valori di accuratezza elevati.

Recognition of noisy images by PLL networks

We use networks composed of three phase-locked loops (PLLs), where one of them is the master, for recognizing noisy images. The values of the coupling weights among the PLLs control the noise level which does not affect the successful identification of the input image. Analytical results and numerical tests are presented concerning the scheme performance. (c) 2008 Elsevier B.V. All rights reserved.

Human cortical processing of colour and pattern

The present study investigates human visual processing of simple two-colour patterns using a delayed match to sample paradigm with positron emission tomography (PET). This study is unique in that we specifically designed the visual stimuli to be the same for both pattern and colour recognition with all patterns being abstract shapes not easily verbally coded composed of two-colour combinations. We did this to explore those brain regions required for both colour and pattern processing and to separate those areas of activation required for one or the other. We found that both tasks activated similar occipital regions, the major difference being more extensive activation in pattern recognition. A right-sided network that involved the inferior parietal lobule, the head of the caudate nucleus, and the pulvinar nucleus of the thalamus was common to both paradigms. Pattern recognition also activated the left temporal pole and right lateral orbital gyrus, whereas colour recognition activated the left fusiform gyrus and several right frontal regions. (C) 2001 Wiley-Liss, Inc.

A new approach to real time traffic sign recognition based on colour information

The automatic interpretation of conventional traffic signs is very complex and time consuming. The paper concerns an automatic warning system for driving assistance. It does not interpret the standard traffic signs on the roadside; the proposal is to incorporate into the existing signs another type of traffic sign whose information will be more easily interpreted by a processor. The type of information to be added is profuse and therefore the most important object is the robustness of the system. The basic proposal of this new philosophy is that the co-pilot system for automatic warning and driving assistance can interpret with greater ease the information contained in the new sign, whilst the human driver only has to interpret the "classic" sign. One of the codings that has been tested with good results and which seems to us easy to implement is that which has a rectangular shape and 4 vertical bars of different colours. The size of these signs is equivalent to the size of the conventional signs (approximately 0.4 m2). The colour information from the sign can be easily interpreted by the proposed processor and the interpretation is much easier and quicker than the information shown by the pictographs of the classic signs

Assessment of Severe Apnoea through Voice Analysis, Automatic Speech, and Speaker Recognition Techniques

This study is part of an ongoing collaborative effort between the medical and the signal processing communities to promote research on applying standard Automatic Speech Recognition (ASR) techniques for the automatic diagnosis of patients with severe obstructive sleep apnoea (OSA). Early detection of severe apnoea cases is important so that patients can receive early treatment. Effective ASR-based detection could dramatically cut medical testing time. Working with a carefully designed speech database of healthy and apnoea subjects, we describe an acoustic search for distinctive apnoea voice characteristics. We also study abnormal nasalization in OSA patients by modelling vowels in nasal and nonnasal phonetic contexts using Gaussian Mixture Model (GMM) pattern recognition on speech spectra. Finally, we present experimental findings regarding the discriminative power of GMMs applied to severe apnoea detection. We have achieved an 81% correct classification rate, which is very promising and underpins the interest in this line of inquiry.