Feature Engineering in Fine-Grained Image Classification

Thesis (Ph.D.)--University of Washington, 2013

Statistical classification of road pavements using near field vehicle rolling noise measurements

Low noise surfaces have been increasingly considered as a viable and cost-effective alternative to acoustical barriers. However, road planners and administrators frequently lack information on the correlation between the type of road surface and the resulting noise emission profile. To address this problem, a method to identify and classify different types of road pavements was developed, whereby near field road noise is analyzed using statistical learning methods. The vehicle rolling sound signal near the tires and close to the road surface was acquired by two microphones in a special arrangement which implements the Close-Proximity method. A set of features, characterizing the properties of the road pavement, was extracted from the corresponding sound profiles. A feature selection method was used to automatically select those that are most relevant in predicting the type of pavement, while reducing the computational cost. A set of different types of road pavement segments were tested and the performance of the classifier was evaluated. Results of pavement classification performed during a road journey are presented on a map, together with geographical data. This procedure leads to a considerable improvement in the quality of road pavement noise data, thereby increasing the accuracy of road traffic noise prediction models.

Data mining techniques to support the classification of MV electricity customers

This paper describes a methodology that was developed for the classification of Medium Voltage (MV) electricity customers. Starting from a sample of data bases, resulting from a monitoring campaign, Data Mining (DM) techniques are used in order to discover a set of a MV consumer typical load profile and, therefore, to extract knowledge regarding to the electric energy consumption patterns. In first stage, it was applied several hierarchical clustering algorithms and compared the clustering performance among them using adequacy measures. In second stage, a classification model was developed in order to allow classifying new consumers in one of the obtained clusters that had resulted from the previously process. Finally, the interpretation of the discovered knowledge are presented and discussed.

Demand response programs definition supported by clustering and classification techniques

The growing importance and influence of new resources connected to the power systems has caused many changes in their operation. Environmental policies and several well know advantages have been made renewable based energy resources largely disseminated. These resources, including Distributed Generation (DG), are being connected to lower voltage levels where Demand Response (DR) must be considered too. These changes increase the complexity of the system operation due to both new operational constraints and amounts of data to be processed. Virtual Power Players (VPP) are entities able to manage these resources. Addressing these issues, this paper proposes a methodology to support VPP actions when these act as a Curtailment Service Provider (CSP) that provides DR capacity to a DR program declared by the Independent System Operator (ISO) or by the VPP itself. The amount of DR capacity that the CSP can assure is determined using data mining techniques applied to a database which is obtained for a large set of operation scenarios. The paper includes a case study based on 27,000 scenarios considering a diversity of distributed resources in a 33 bus distribution network.

Towards a classification scheme for musical sounds

Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA), 2013

An automatic voice pleasantness classification system based on prosodic and acoustic patterns of voice preference

In the last few years the number of systems and devices that use voice based interaction has grown significantly. For a continued use of these systems the interface must be reliable and pleasant in order to provide an optimal user experience. However there are currently very few studies that try to evaluate how good is a voice when the application is a speech based interface. In this paper we present a new automatic voice pleasantness classification system based on prosodic and acoustic patterns of voice preference. Our study is based on a multi-language database composed by female voices. In the objective performance evaluation the system achieved a 7.3% error rate.

Mapping the Pasture Steppe in Bayankhongor, Mongolia: comparison of classification methods, using Landsat-8 and geophysical data

Grasslands in semi-arid regions, like Mongolian steppes, are facing desertification and degradation processes, due to climate change. Mongolia’s main economic activity consists on an extensive livestock production and, therefore, it is a concerning matter for the decision makers. Remote sensing and Geographic Information Systems provide the tools for advanced ecosystem management and have been widely used for monitoring and management of pasture resources. This study investigates which is the higher thematic detail that is possible to achieve through remote sensing, to map the steppe vegetation, using medium resolution earth observation imagery in three districts (soums) of Mongolia: Dzag, Buutsagaan and Khureemaral. After considering different thematic levels of detail for classifying the steppe vegetation, the existent pasture types within the steppe were chosen to be mapped. In order to investigate which combination of data sets yields the best results and which classification algorithm is more suitable for incorporating these data sets, a comparison between different classification methods were tested for the study area. Sixteen classifications were performed using different combinations of estimators, Landsat-8 (spectral bands and Landsat-8 NDVI-derived) and geophysical data (elevation, mean annual precipitation and mean annual temperature) using two classification algorithms, maximum likelihood and decision tree. Results showed that the best performing model was the one that incorporated Landsat-8 bands with mean annual precipitation and mean annual temperature (Model 13), using the decision tree. For maximum likelihood, the model that incorporated Landsat-8 bands with mean annual precipitation (Model 5) and the one that incorporated Landsat-8 bands with mean annual precipitation and mean annual temperature (Model 13), achieved the higher accuracies for this algorithm. The decision tree models consistently outperformed the maximum likelihood ones.

Segmentation and Clustering of Textual Sequences: a Typological Approach

The long term goal of this research is to develop a program able to produce an automatic segmentation and categorization of textual sequences into discourse types. In this preliminary contribution, we present the construction of an algorithm which takes a segmented text as input and attempts to produce a categorization of sequences, such as narrative, argumentative, descriptive and so on. Also, this work aims at investigating a possible convergence between the typological approach developed in particular in the field of text and discourse analysis in French by Adam (2008) and Bronckart (1997) and unsupervised statistical learning.

Urban image classification with semisupervised multiscale cluster kernels

This paper presents a semisupervised support vector machine (SVM) that integrates the information of both labeled and unlabeled pixels efficiently. Method's performance is illustrated in the relevant problem of very high resolution image classification of urban areas. The SVM is trained with the linear combination of two kernels: a base kernel working only with labeled examples is deformed by a likelihood kernel encoding similarities between labeled and unlabeled examples. Results obtained on very high resolution (VHR) multispectral and hyperspectral images show the relevance of the method in the context of urban image classification. Also, its simplicity and the few parameters involved make the method versatile and workable by unexperienced users.

Automatic Mallampati Classification Using Active Appearance Models

Difficult tracheal intubation assessment is an important research topic in anesthesia as failed intubations are important causes of mortality in anesthetic practice. The modified Mallampati score is widely used, alone or in conjunction with other criteria, to predict the difficulty of intubation. This work presents an automatic method to assess the modified Mallampati score from an image of a patient with the mouth wide open. For this purpose we propose an active appearance models (AAM) based method and use linear support vector machines (SVM) to select a subset of relevant features obtained using the AAM. This feature selection step proves to be essential as it improves drastically the performance of classification, which is obtained using SVM with RBF kernel and majority voting. We test our method on images of 100 patients undergoing elective surgery and achieve 97.9% accuracy in the leave-one-out crossvalidation test and provide a key element to an automatic difficult intubation assessment system.

Health problems among detainees in Switzerland: a study using the ICPC-2 classification.

BACKGROUND: Little is known about the health status of prisoners in Switzerland. The aim of this study was to provide a detailed description of the health problems presented by detainees in Switzerland's largest remand prison. METHODS: In this retrospective cross-sectional study we reviewed the health records of all detainees leaving Switzerland's largest remand prison in 2007. The health problems were coded using the International Classification for Primary Care (ICPC-2). Analyses were descriptive, stratified by gender. RESULTS: A total of 2195 health records were reviewed. Mean age was 29.5 years (SD 9.5); 95% were male; 87.8% were migrants. Mean length of stay was 80 days (SD 160). Illicit drug use (40.2%) and mental health problems (32.6%) were frequent, but most of these detainees (57.6%) had more generic primary care problems, such as skin (27.0%), infectious diseases (23.5%), musculoskeletal (19.2%), injury related (18.3%), digestive (15.0%) or respiratory problems (14.0%). Furthermore, 7.9% reported exposure to violence during arrest by the police. CONCLUSION: Morbidity is high in this young, predominantly male population of detainees, in particular in relation to substance abuse. Other health problems more commonly seen in general practice are also frequent. These findings support the further development of coordinated primary care and mental health services within detention centers.