In the Internet era, more and more courses are taught through a course management system (CMS) or learning management system (LMS). In an asynchronous virtual learning environment, an instructor has the need to beware the progress of discussions in forums, and may intervene if ecessary in order to facilitate students¡¦ learning. This research proposes a discussion forum activity flow tracking system, called FAFT (Forum Activity Flow Tracer), to utomatically monitor the discussion activity flow of threaded forum postings in CMS/LMS. As CMS/LMS is getting popular in facilitating learning activities, the proposedFAFT can be used to facilitate instructors to identify students¡¦ interaction types in discussion forums. FAFT adopts modern data/text mining techniques to discover the patterns of forum discussion activity flows, which can be used for instructors to facilitate the online learning activities. FAFT consists of two subsystems: activity classification (AC) and activity flow discovery (AFD). A posting can be perceived as a type of announcement, questioning, clarification, interpretation, conflict, or assertion. AC adopts a cascade model to classify various activitytypes of posts in a discussion thread. The empirical evaluation of the classified types from a repository of postings in earth science on-line courses in a senior high school shows that AC can effectively facilitate the coding rocess, and the cascade model can deal with the imbalanced distribution nature of discussion postings. AFD adopts a hidden Markov model (HMM) to discover the activity flows. A discussion activity flow can be presented as a hidden Markov model (HMM) diagram that an instructor can adopt to predict which iscussion activity flow type of a discussion thread may be followed. The empirical results of the HMM from an online forum in earth science subject in a senior high school show that FAFT can effectively predict the type of a discussion activity flow. Thus, the proposed FAFT can be embedded in a course management system to automatically predict the activity flow type of a discussion thread, and in turn reduce the teachers¡¦ loads on managing online discussion forums.

Progression and pattern of changes in different biomarkers of Alzheimer’s disease (AD) and frontotemporal lobar degeneration (FTLD) like [18F]fluorodeoxyglucose positron emission tomography (FDG-PET) and magnetic resonance imaging (MRI) have been carefully investigated over the past decades. However, there have been substantially less studies investigating the potential of combining these imaging modalities to make use of multimodal information to further improve understanding, detection and differentiation of various dementia syndromes. Further the role of preprocessing has been rarely addressed in previous research although different preprocessing algorithms have been shown to substantially affect diagnostic accuracy of dementia. In the present work common preprocessing procedures used to scale FDG-PET data were compared to each other. Further, FDG-PET and MRI information were jointly analyzed using univariate and multivariate techniques. The results suggest a highly differential effect of different scaling procedures of FDG-PET data onto detection and differentiation of various dementia syndromes. Additionally, it has been shown that combining multimodal information does further improve automatic detection and differentiation of AD and FTLD.

The objective of the research described in this dissertation is to improve the travel-time prediction process using machine learning methods for the Advanced Traffic In-formation Systems (ATIS). Travel-time prediction has gained significance over the years especially in urban areas due to increasing traffic congestion. The increased demand of the traffic flow has motivated the need for development of improved applications and frameworks, which could alleviate the problems arising due to traffic flow, without the need of addition to the roadway infrastructure. In this thesis, the basic building blocks of the travel-time prediction models are discussed, with a review of the significant prior art. The problem of travel-time prediction was addressed by different perspectives in the past. Mainly the data-driven approach and the traffic flow modeling approach are the two main paths adopted viz. a viz. travel-time prediction from the methodology perspective. This dissertation, works towards the im-provement of the data-driven method. The data-driven model, presented in this dissertation, for the travel-time predic-tion on freeways was based on wavelet packet decomposition and support vector regres-sion (WPSVR), which uses the multi-resolution and equivalent frequency distribution ability of the wavelet transform to train the support vector machines. The results are compared against the classical support vector regression (SVR) method. Our results indi-cate that the wavelet reconstructed coefficients when used as an input to the support vec-tor machine for regression (WPSVR) give better performance (with selected wavelets on-ly), when compared against the support vector regression (without wavelet decomposi-tion). The data used in the model is downloaded from California Department of Trans-portation (Caltrans) of District 12 with a detector density of 2.73, experiencing daily peak hours except most weekends. The data was stored for a period of 214 days accumulated over 5 minute intervals over a distance of 9.13 miles. The results indicate an improvement in accuracy when compared against the classical SVR method. The basic criteria for selection of wavelet basis for preprocessing the inputs of support vector machines are also explored to filter the set of wavelet families for the WDSVR model. Finally, a configuration of travel-time prediction on freeways is present-ed with interchangeable prediction methods along with the details of the Matlab applica-tion used to implement the WPSVR algorithm. The initial results are computed over the set of 42 wavelets. To reduce the compu-tational cost involved in transforming the travel-time data into the set of wavelet packets using all possible mother wavelets available, a methodology of filtering the wavelets is devised, which measures the cross-correlation and redundancy properties of consecutive wavelet transformed values of same frequency band. An alternate configuration of travel-time prediction on freeways using the con-cepts of cloud computation is also presented, which has the ability to interchange the pre-diction modules with an alternate method using the same time-series data. Finally, a graphical user interface is described to connect the Matlab environment with the Caltrans data server for online travel-time prediction using both SVR and WPSVR modules and display the errors and plots of predicted values for both methods. The GUI also has the ability to compute forecast of custom travel-time data in the offline mode.

Multi-spectral images have the advantage of providing complementary information to resolve some ambiguities. But, the challenge is how to make use of the multi-spectral images effectively. In this thesis, our study focuses on the fusion of multi-spectral images by extracting the most useful features to obtain the best segmentation with the least cost in time. The Support Vector Machine (SVM) classification integrated with a selection of the features in a kernel space is proposed. The selection criterion is defined by the kernel class separability. Based on this SVM classification, a framework to follow up brain tumor evolution is proposed, which consists of the following steps: to learn the brain tumors and select the features from the first magnetic resonance imaging (MRI) examination of the patients; to automatically segment the tumor in new data using a multi-kernel SVM based classification; to refine the tumor contour by a region growing technique; and to possibly carry out an adaptive training. The proposed system was tested on 13 patients with 24 examinations, including 72 MRI sequences and 1728 images. Compared with the manual traces of the doctors as the ground truth, the average classification accuracy reaches 98.9%. The system utilizes several novel feature selection methods to test the integration of feature selection and SVM classifiers. Also compared with the traditional SVM, Fuzzy C-means, the neural network and an improved level set method, the segmentation results and quantitative data analysis demonstrate the effectiveness of our proposed system.

Mapping ice and open water in ocean bodies is important for numerous purposes including environmental analysis and ship navigation. The Canadian Ice Service (CIS) currently has several expert ice analysts manually generate ice maps on a daily basis. The CIS would like to augment their current process with an automated ice-water discrimination algorithm capable of operating on dual-pol synthetic aperture radar (SAR) images produced by RADARSAT-2. Automated methods can provide mappings in larger volumes, with more consistency, and in finer resolutions that are otherwise impractical to generate. We have developed such an automated ice-water discrimination system called MAGIC. The algorithm first classifies the HV scene using the glocal method, a hierarchical region-based classification method. The glocal method incorporates spatial context information into the classification model using a modified watershed segmentation and a previously developed MRF classification algorithm called IRGS. Second, a pixel-based support vector machine (SVM) using a nonlinear RBF kernel classification is performed exploiting SAR grey-level co-occurrence matrix (GLCM) texture and backscatter features. Finally, the IRGS and SVM classification results are combined using the IRGS approach but with a modified energy function to accommodate the SVM pixel-based information. The combined classifier was tested on 61 ground truthed dual-pol RADARSAT-2 scenes of the Beaufort Sea containing a variety of ice types and water patterns across melt, summer, and freeze-up periods. The average leave-one-out classification accuracy with respect to these ground truths is 95.8% and MAGIC attains an accuracy of 90% or above on 88% of the scenes. The MAGIC system is now under consideration by CIS for operational use.

Patients with macular degeneration (MD) often fixate with a preferred retinal locus (PRL). Eye movements made while fixating with the PRL (in MD patients) has been observed to be maladaptive compared to those made while fixating with the fovea (normal sighted individuals). For example, in MD patients, PRL eye movements negatively affect fixation stability and re-fixation precision; consequently creating difficulty in reading and limits to their execution of other everyday activities. Abnormal eye movements from the PRL affect research on the physiological adaptations to MD. Specifically, previous research on cortical reorganization using functional magnetic resonance imaging (fMRI), indicates a critical need to accurately determine a MD patient's point of gaze in order to better infer existence of cortical reorganization. Unfortunately, standard MR compatible hardware eye-tracking systems do not work well with these patients. Their reduction in fixation stability often overwhelms the tracking algorithms used by these systems. This research investigates the use of an existing magnetic resonance imaging (MRI) based technique called Predictive Eye Estimation Regression (PEER) to determine the point of gaze of MD patients and thus control for fixation instability. PEER makes use of the fluctuations in the MR signal caused by eye movements to identify position of gaze. Engineering adaptations such as temporal resolution and brain coverage were applied to tailor PEER to MD patients. Also participants were evaluated on different fixation protocols and the results compared to that of the micro-perimeter MP-1 to test the efficacy of PEER. The fixation stability results obtained from PEER were similar to that obtained from the eye tracking results of the micro-perimeter MP-1. However, PEER's point of gaze estimations was different from the MP-1's in the fixation tests. The difference in this result cannot be concluded to be specific to PEER. In order to resolve this issue, advancements to PEER by the inclusion of an eye tracker in the scanner to run concurrently with PEER could provide more evidence of PEER's reliability. In addition, increasing the diversity of AMD patients in terms of the different scotoma types will help provide a better estimate of PEER flexibility and robustness.

The notion of designing circuits based on charge sensing, charge adaptation, and charge programming is explored in this research. This design concept leads to a low-power capacitive sensing interface circuit that has been designed and tested with a MEMS microphone and a capacitive micromachined ultrasonic transducer. Moreover, by using the charge programming technique, a designed floating-gate based large-scale field-programmable analog array (FPAA) containing a universal sensor interface sets the stage for reconfigurable smart sensory systems. Based on the same charge programming technique, a compact programmable analog radial-basis-function (RBF) based classifier and a resultant analog vector quantizer have been developed and tested. Measurement results have shown that the analog RBF-based classifier is at least two orders of magnitude more power-efficient than an equivalent digital processor. Furthermore, an adaptive bump circuit that can facilitate unsupervised learning in the analog domain has also been proposed. A projection neural network for a support vector machine, a powerful and more complicated binary classification algorithm, has also been proposed. This neural network is suitable for analog VLSI implementation and has been simulated and verified on the transistor level. These analog classifiers can be integrated at the interface to build smart sensory systems.

Human face recognition is an important area in the field of biometrics. It has been an active area of research for several decades, but still remains a challenging problem because of the complexity of the human face. In this thesis we describe fully automatic solutions that can locate faces and then perform identification and verification. We present a solution for face localisation using eye locations. We derive an efficient representation for the decision hyperplane of linear and nonlinear Support Vector Machines (SVMs). For this we introduce the novel concept of $\rho$ and $\eta$ prototypes. The standard formulation for the decision hyperplane is reformulated and expressed in terms of the two prototypes. Different kernels are treated separately to achieve further classification efficiency and to facilitate its adaptation to operate with the fast Fourier transform to achieve fast eye detection. Using the eye locations, we extract and normalise the face for size and in-plane rotations. Our method produces a more efficient representation of the SVM decision hyperplane than the well-known reduced set methods. As a result, our eye detection subsystem is faster and more accurate. The use of fractals and fractal image coding for object recognition has been proposed and used by others. Fractal codes have been used as features for recognition, but we need to take into account the distance between codes, and to ensure the continuity of the parameters of the code. We use a method based on fractal image coding for recognition, which we call the Fractal Neighbour Distance (FND). The FND relies on the Euclidean metric and the uniqueness of the attractor of a fractal code. An advantage of using the FND over fractal codes as features is that we do not have to worry about the uniqueness of, and distance between, codes. We only require the uniqueness of the attractor, which is already an implied property of a properly generated fractal code. Similar methods to the FND have been proposed by others, but what distinguishes our work from the rest is that we investigate the FND in greater detail and use our findings to improve the recognition rate. Our investigations reveal that the FND has some inherent invariance to translation, scale, rotation and changes to illumination. These invariances are image dependent and are affected by fractal encoding parameters. The parameters that have the greatest effect on recognition accuracy are the contrast scaling factor, luminance shift factor and the type of range block partitioning. The contrast scaling factor affect the convergence and eventual convergence rate of a fractal decoding process. We propose a novel method of controlling the convergence rate by altering the contrast scaling factor in a controlled manner, which has not been possible before. This helped us improve the recognition rate because under certain conditions better results are achievable from using a slower rate of convergence. We also investigate the effects of varying the luminance shift factor, and examine three different types of range block partitioning schemes. They are Quad-tree, HV and uniform partitioning. We performed experiments using various face datasets, and the results show that our method indeed performs better than many accepted methods such as eigenfaces. The experiments also show that the FND based classifier increases the separation between classes. The standard FND is further improved by incorporating the use of localised weights. A local search algorithm is introduced to find a best matching local feature using this locally weighted FND. The scores from a set of these locally weighted FND operations are then combined to obtain a global score, which is used as a measure of the similarity between two face images. Each local FND operation possesses the distortion invariant properties described above. Combined with the search procedure, the method has the potential to be invariant to a larger class of non-linear distortions. We also present a set of locally weighted FNDs that concentrate around the upper part of the face encompassing the eyes and nose. This design was motivated by the fact that the region around the eyes has more information for discrimination. Better performance is achieved by using different sets of weights for identification and verification. For facial verification, performance is further improved by using normalised scores and client specific thresholding. In this case, our results are competitive with current state-of-the-art methods, and in some cases outperform all those to which they were compared. For facial identification, under some conditions the weighted FND performs better than the standard FND. However, the weighted FND still has its short comings when some datasets are used, where its performance is not much better than the standard FND. To alleviate this problem we introduce a voting scheme that operates with normalised versions of the weighted FND. Although there are no improvements at lower matching ranks using this method, there are significant improvements for larger matching ranks. Our methods offer advantages over some well-accepted approaches such as eigenfaces, neural networks and those that use statistical learning theory. Some of the advantages are: new faces can be enrolled without re-training involving the whole database; faces can be removed from the database without the need for re-training; there are inherent invariances to face distortions; it is relatively simple to implement; and it is not model-based so there are no model parameters that need to be tweaked.

Submitted by Emerson Leão Júnior null (emerson.leaojr@gmail.com) on 2017-12-05T18:07:16Z No. of bitstreams: 1 leao_ej_me_prud.pdf: 4186679 bytes, checksum: ee186b23411343c3e2d782d622226699 (MD5) / Approved for entry into archive by ALESSANDRA KUBA OSHIRO null (alessandra@fct.unesp.br) on 2017-12-06T10:52:22Z (GMT) No. of bitstreams: 1 leaojunior_e_me_prud.pdf: 4186679 bytes, checksum: ee186b23411343c3e2d782d622226699 (MD5) / Made available in DSpace on 2017-12-06T10:52:22Z (GMT). No. of bitstreams: 1 leaojunior_e_me_prud.pdf: 4186679 bytes, checksum: ee186b23411343c3e2d782d622226699 (MD5) Previous issue date: 2017-04-25 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES) / Considerando o cenário durante a crise hídrica de 2014 e a situação crítica dos reservatórios do sistema Cantareira no estado de São Paulo, este estudo realizado no reservatório Jaguari-Jacareí, consistiu na extração de informações a partir de imagens multiespectrais e análise da qualidade da informação relacionada com a acurácia no cálculo do volume de água do reservatório. Inicialmente, a superfície do espelho d’água foi obtida pela classificação da cobertura da terra a partir de imagens multiespectrais RapidEye tomadas antes e durante a crise hídrica (2013 e 2014, respectivamente), utilizando duas abordagens distintas: classificação orientada a objeto (Object-based Image Analysis - OBIA) e classificação baseada em pixel (Support Vector Machine – SVM). A acurácia do usuário por classe permitiu expressar o erro para detectar a superfície do espelho d’água para cada abordagem de classificação de 2013 e 2014. O segundo componente da estimação do volume foi a representação do relevo submerso, que considerou duas fontes de dados na construção do modelo numérico do terreno (MNT): dados topográficos provenientes de levantamento batimétrico disponibilizado pela Sabesp e o modelo de superfície AW3D30 (ALOS World 3D 30m mesh), para complementar a informação não disponível além da cota 830,13 metros. A comparação entre as duas abordagens de classificação dos tipos de cobertura da terra do entorno do reservatório Jaguari-Jacareí mostrou que SVM resultou em indicadores de acurácia ligeiramente superiores à OBIA, para os anos de 2013 e 2014. Em relação à estimação de volume do reservatório, incorporando a informação do nível de água divulgado pela Sabesp, a abordagem SVM apresentou menor discrepância relativa do que OBIA. Apesar disso, a qualidade da informação produzida na estimação de volume, resultante da propagação da variância associada aos dados envolvidos no processo, ambas as abordagens produziram valores similares de incerteza, mas com uma sutil superioridade de OBIA, para alguns dos cenários avaliados. No geral, os métodos de classificação utilizados nesta dissertação produziram informação acurada e adequada para o monitoramento de recursos hídricos e indicou que a abordagem SVM teve um desempenho sutilmente superior na classificação dos tipos de cobertura da terra, na estimação do volume e em alguns dos cenários considerados na propagação da incerteza. / This study aims to extract information from multispectral images and to analyse the information quality in the water volume estimation of Jaguari-Jacareí reservoir. The presented study of changes in the volume of the Jaguari-Jacareí reservoir was motivated by the critical situation of the reservoirs from Cantareira System in São Paulo State caused by water crisis in 2014. Reservoir area was extracted from RapidEye multispectral images acquired before and during the water crisis (2013 and 2014, respectively) through land cover classification. Firstly, the image classification was carried out in two distinct approaches: object-based (Object-based Image Analysis - OBIA) and pixel-based (Support Vector Machine - SVM) method. The classifications quality was evaluated through thematic accuracy, in which for every technique the user accuracy allowed to express the error for the class representing the water in 2013 and 2014. Secondly, we estimated the volume of the reservoir’s water body, using the numerical terrain model generated from two additional data sources: topographic data from a bathymetric survey, available from Sabesp, and the elevation model AW3D30 (to complement the information in the area where data from Sabesp was not available). When compare the two classification techniques, it was found that in the image classification, SVM performance slightly overcame the OBIA classification technique for 2013 and 2014. In the volume calculation considering the water level estimated from the generated DTM, the result obtained by SVM approach was better in 2013, whereas OBIA approach was more accurate in 2014. Considering the quality of the information produced in the volume estimation, both approaches presented similar values of uncertainty, with the OBIA method slightly less uncertain than SVM. In conclusion, the classification methods used in this dissertation produced accurate information to monitor water resource, but SVM had a subtly superior performance in the classification of land cover types, volume estimation and some of the scenarios considered in the propagation of uncertainty.

A diesel particulate filter (DPF) is designed to physically remove diesel particulate matter or soot from the exhaust gas of a diesel engine. Frequently replacing DPF is a waste of resource and waiting for full utilization is risky and very costly, so, what is the optimal time/milage to change DPF? Answering this question is very difficult without knowing when the DPF is changed in a vehicle. We are finding the answer with supervised machine learning algorithms for detecting anomalies in vehicles off-board sensor data (operational data of vehicles). Filter change is considered an anomaly because it is rare as compared to normal data. Non-sequential machine learning algorithms for anomaly detection like oneclass support vector machine (OC-SVM), k-nearest neighbor (K-NN), and random forest (RF) are applied for the first time on DPF dataset. The dataset is unbalanced, and accuracy is found misleading as a performance measure for the algorithms. Precision, recall, and F1-score are found good measure for the performance of the machine learning algorithms when the data is unbalanced. RF gave highest F1-score of 0.55 than K-NN (0.52) and OCSVM (0.51). It means that RF perform better than K-NN and OC-SVM but after further investigation it is concluded that the results are not satisfactory. However, a sequential approach should have been tried which could yield better result.