Evaluating the use of mobile collaborative augmented reality within field service networks: the case of Océ Italia – Canon Group

The adoption of Augmented Reality (AR) technologies can make the provision of field services to industrial equipment more effective. In these situations, the cost of deploying skilled technicians in geographically dispersed locations must be accurately traded off with the risks of not respecting the service level agreements with the customers. This paper, through the case study of a leading OEM in the production printing industry, presents the challenges that have to be faced in order to favour the adoption of a particular kind of AR named Mobile Collaborative Augmented Reality (MCAR). In particular, this study uses both qualitative and quantitative research. Firstly, a demonstration to show how MCAR can support field service was settled in order to achieve information about the use experience of the people involved. Then, the entire field force of Océ Italia – Canon Group was surveyed in order to investigate quantitatively the technicians’ perceptions about the usefulness and ease of use of MCAR, as well as their intentions to use this technology.

An SVM-Fuzzy system design for diabetes risk classification

OC-OT-LIBS: A novel approach to the chemical characterization of single particles

Spectral identification of individual micro- and nano-sized particles by the sequential intervention of optical catapulting, optical trapping and laser-induced breakdown spectroscopy is presented [1]. The three techniques are used for different purposes. Optical catapulting (OC) serves to put the particulate material under inspection in aerosol form [2-4]. Optical trapping (OT) permits the isolation and manipulation of individual particles from the aerosol, which are subsequently analyzed by laser-induced breakdown spectroscopy (LIBS). Once catapulted, the dynamics of particle trapping depends on the laser beam characteristics (power and intensity gradient) and on the particle properties (size, mass and shape). Particles are stably trapped in air at atmospheric pressure and can be conveniently manipulated for a precise positioning for LIBS analysis. The spectra acquired from the individually trapped particles permit a straightforward identification of the inspected material. The current work focuses on the development of a procedure for simultaneously acquiring dual information about the particle under study via LIBS and time-resolved plasma images by taking advantage of the aforementioned features of the OC-OT-LIBS instrument to align the multiple lines in a simple yet highly accurate way. The plasma imaging does not only further reinforce the spectral data, but also allows a better comprehension of the chemical and physical processes involved during laser-particle interaction. Also, a thorough determination of the optimal excitation conditions generating the most information out of each laser event was run along the determination of parameters such as the width of the optical trap, its stability as a function of the laser power and the laser wavelength. The extreme sensibility of the presented OC-OT-LIBS technology allows a detection power of attograms for single/individual particle analysis.

High-dimensional and large-scale anomaly detection using a linear one-class SVM with deep learning

High-dimensional problem domains pose significant challenges for anomaly detection. The presence of irrelevant features can conceal the presence of anomalies. This problem, known as the '. curse of dimensionality', is an obstacle for many anomaly detection techniques. Building a robust anomaly detection model for use in high-dimensional spaces requires the combination of an unsupervised feature extractor and an anomaly detector. While one-class support vector machines are effective at producing decision surfaces from well-behaved feature vectors, they can be inefficient at modelling the variation in large, high-dimensional datasets. Architectures such as deep belief networks (DBNs) are a promising technique for learning robust features. We present a hybrid model where an unsupervised DBN is trained to extract generic underlying features, and a one-class SVM is trained from the features learned by the DBN. Since a linear kernel can be substituted for nonlinear ones in our hybrid model without loss of accuracy, our model is scalable and computationally efficient. The experimental results show that our proposed model yields comparable anomaly detection performance with a deep autoencoder, while reducing its training and testing time by a factor of 3 and 1000, respectively.

Detection and classification of anomaly intrusion using hierarchy clustering and SVM

Anomaly detection as a kind of intrusion detection is good at detecting the unknown attacks or new attacks, and it has attracted much attention during recent years. In this paper, a new hierarchy anomaly intrusion detection model that combines the fuzzy c-means (FCM) based on genetic algorithm and SVM is proposed. During the process of detecting intrusion, the membership function and the fuzzy interval are applied to it, and the process is extended to soft classification from the previous hard classification. Then a fuzzy error correction sub interval is introduced, so when the detection result of a data instance belongs to this range, the data will be re-detected in order to improve the effectiveness of intrusion detection. Experimental results show that the proposed model can effectively detect the vast majority of network attack types, which provides a feasible solution for solving the problems of false alarm rate and detection rate in anomaly intrusion detection model.

Authentification biométrique par dynamique de frappe pour évaluation à distance utilisant SVM à une classe

La machine à vecteurs de support à une classe est un algorithme non-supervisé qui est capable d’apprendre une fonction de décision à partir de données d’une seule classe pour la détection d’anomalie. Avec les données d’entraînement d’une seule classe, elle peut identifier si une nouvelle donnée est similaire à l’ensemble d’entraînement. Dans ce mémoire, nous nous intéressons à la reconnaissance de forme de dynamique de frappe par la machine à vecteurs de support à une classe, pour l’authentification d’étudiants dans un système d’évaluation sommative à distance à l’Université Laval. Comme chaque étudiant à l’Université Laval possède un identifiant court, unique qu’il utilise pour tout accès sécurisé aux ressources informatiques, nous avons choisi cette chaîne de caractères comme support à la saisie de dynamique de frappe d’utilisateur pour construire notre propre base de données. Après avoir entraîné un modèle pour chaque étudiant avec ses données de dynamique de frappe, on veut pouvoir l’identifier et éventuellement détecter des imposteurs. Trois méthodes pour la classification ont été testées et discutées. Ainsi, nous avons pu constater les faiblesses de chaque méthode dans ce système. L’évaluation des taux de reconnaissance a permis de mettre en évidence leur dépendance au nombre de signatures ainsi qu’au nombre de caractères utilisés pour construire les signatures. Enfin, nous avons montré qu’il existe des corrélations entre le taux de reconnaissance et la dispersion dans les distributions des caractéristiques des signatures de dynamique de frappe.

Prognosis of bearing failure based on health state estimation

This paper proposes a new prognosis model based on the technique for health state estimation of machines for accurate assessment of the remnant life. For the evaluation of health stages of machines, the Support Vector Machine (SVM) classifier was employed to obtain the probability of each health state. Two case studies involving bearing failures were used to validate the proposed model. Simulated bearing failure data and experimental data from an accelerated bearing test rig were used to train and test the model. The result obtained is very encouraging and shows that the proposed prognostic model produces promising results and has the potential to be used as an estimation tool for machine remnant life prediction.

Integrated Diagnosis and Prognosis Model for High Pressure LNG Pump

In condition-based maintenance (CBM), effective diagnostics and prognostics are essential tools for maintenance engineers to identify imminent fault and to predict the remaining useful life before the components finally fail. This enables remedial actions to be taken in advance and reschedules production if necessary. This paper presents a technique for accurate assessment of the remnant life of machines based on historical failure knowledge embedded in the closed loop diagnostic and prognostic system. The technique uses the Support Vector Machine (SVM) classifier for both fault diagnosis and evaluation of health stages of machine degradation. To validate the feasibility of the proposed model, the five different level data of typical four faults from High Pressure Liquefied Natural Gas (HP-LNG) pumps were used for multi-class fault diagnosis. In addition, two sets of impeller-rub data were analysed and employed to predict the remnant life of pump based on estimation of health state. The results obtained were very encouraging and showed that the proposed prognosis system has the potential to be used as an estimation tool for machine remnant life prediction in real life industrial applications.

Rough set-based reasoning and pattern mining for information filtering

An information filtering (IF) system monitors an incoming document stream to find the documents that match the information needs specified by the user profiles. To learn to use the user profiles effectively is one of the most challenging tasks when developing an IF system. With the document selection criteria better defined based on the users’ needs, filtering large streams of information can be more efficient and effective. To learn the user profiles, term-based approaches have been widely used in the IF community because of their simplicity and directness. Term-based approaches are relatively well established. However, these approaches have problems when dealing with polysemy and synonymy, which often lead to an information overload problem. Recently, pattern-based approaches (or Pattern Taxonomy Models (PTM) [160]) have been proposed for IF by the data mining community. These approaches are better at capturing sematic information and have shown encouraging results for improving the effectiveness of the IF system. On the other hand, pattern discovery from large data streams is not computationally efficient. Also, these approaches had to deal with low frequency pattern issues. The measures used by the data mining technique (for example, “support” and “confidences”) to learn the profile have turned out to be not suitable for filtering. They can lead to a mismatch problem. This thesis uses the rough set-based reasoning (term-based) and pattern mining approach as a unified framework for information filtering to overcome the aforementioned problems. This system consists of two stages - topic filtering and pattern mining stages. The topic filtering stage is intended to minimize information overloading by filtering out the most likely irrelevant information based on the user profiles. A novel user-profiles learning method and a theoretical model of the threshold setting have been developed by using rough set decision theory. The second stage (pattern mining) aims at solving the problem of the information mismatch. This stage is precision-oriented. A new document-ranking function has been derived by exploiting the patterns in the pattern taxonomy. The most likely relevant documents were assigned higher scores by the ranking function. Because there is a relatively small amount of documents left after the first stage, the computational cost is markedly reduced; at the same time, pattern discoveries yield more accurate results. The overall performance of the system was improved significantly. The new two-stage information filtering model has been evaluated by extensive experiments. Tests were based on the well-known IR bench-marking processes, using the latest version of the Reuters dataset, namely, the Reuters Corpus Volume 1 (RCV1). The performance of the new two-stage model was compared with both the term-based and data mining-based IF models. The results demonstrate that the proposed information filtering system outperforms significantly the other IF systems, such as the traditional Rocchio IF model, the state-of-the-art term-based models, including the BM25, Support Vector Machines (SVM), and Pattern Taxonomy Model (PTM).

Injury bulletin 105 : skateboard injury

Summary of findings: QISU estimates that approximately 1,000 skateboard-associated injuries are seen at emergency departments each year in Queensland. 10-14 year old males are the most likely group to present to a QISU ED with a skateboard related injury. The peak time for skateboard injuries to occur is on the weekend and in the late afternoon. Only 19% of skateboard injuries occur at skate park facilities, with the remainder oc-curring in non-skate parks, on roads and footpaths. Risk factors associated with more severe injuries are, age less than 10 years and involvement in a motor vehicle crash The most common types of injuries are fractures and sprains of the upper limbs. Isolated head injuries represent approximately 5% of skateboarding injuries, but 60% of serious injuries requiring resuscitation. These injuries may be minimized or pre-vented with helmet use.

Thin film deposition and characterization of pure and iron-doped electron-beam evaporated tungsten oxide for gas sensors

Pure Tungsten Oxide (WO3) and Iron-doped (10 at%) Tungsten Oxide (WO3:Fe) nanostructured thin films were prepared using a dual crucible Electron Beam Evaporation techniques. The films were deposited at room temperature in high vacuum condition on glass substrate and post-heat treated at 300 oC for 1 hour. From the study of X-ray diffraction and Raman the characteristics of the as-deposited WO3 and WO3:Fe films indicated non-crystalline nature. The surface roughness of all the films showed in the order of 2.5 nm as observed using Atomic Force Microscopy (AFM). X-Ray Photoelectron Spectroscopy (XPS) analysis revealed tungsten oxide films with stoichiometry close to WO3. The addition of Fe to WO3 produced a smaller particle size and lower porosity as observed using Transmission Electron Microscopy (TEM). A slight difference in optical band gap energies of 3.22 eV and 3.12 eV were found between the as-deposited WO3 and WO3:Fe films, respectively. However, the difference in the band gap energies of the annealed films were significantly higher having values of 3.12 eV and 2.61 eV for the WO3 and WO3:Fe films, respectively. The heat treated samples were investigated for gas sensing applications using noise spectroscopy and doping of Fe to WO3 reduced the sensitivity to certain gasses. Detailed study of the WO3 and WO3:Fe films gas sensing properties is the subject of another paper.

QUT speaker identity verification system for EVALITA 2009

This document outlines the system submitted by the Speech and Audio Research Laboratory at the Queensland University of Technology (QUT) for the Speaker Identity Verication: Application task of EVALITA 2009. This submission consisted of a score-level fusion of three component systems, a joint-factor GMM system and two SVM systems using GLDS and GMM supervector kernels. Development and evaluation results are presented, demonstrating the effectiveness of this fused system approach.

Exploiting multiple feature sets in data-driven impostor dataset selection for speaker verification

This study assesses the recently proposed data-driven background dataset refinement technique for speaker verification using alternate SVM feature sets to the GMM supervector features for which it was originally designed. The performance improvements brought about in each trialled SVM configuration demonstrate the versatility of background dataset refinement. This work also extends on the originally proposed technique to exploit support vector coefficients as an impostor suitability metric in the data-driven selection process. Using support vector coefficients improved the performance of the refined datasets in the evaluation of unseen data. Further, attempts are made to exploit the differences in impostor example suitability measures from varying features spaces to provide added robustness.

Analysis and detection of cognitive load and frustration in drivers' speech

Non-driving related cognitive load and variations of emotional state may impact a driver’s capability to control a vehicle and introduces driving errors. Availability of reliable cognitive load and emotion detection in drivers would benefit the design of active safety systems and other intelligent in-vehicle interfaces. In this study, speech produced by 68 subjects while driving in urban areas is analyzed. A particular focus is on speech production differences in two secondary cognitive tasks, interactions with a co-driver and calls to automated spoken dialog systems (SDS), and two emotional states during the SDS interactions - neutral/negative. A number of speech parameters are found to vary across the cognitive/emotion classes. Suitability of selected cepstral- and production-based features for automatic cognitive task/emotion classification is investigated. A fusion of GMM/SVM classifiers yields an accuracy of 94.3% in cognitive task and 81.3% in emotion classification.