Dissertations / Theses on the topic 'Machine Learning,Customer Segmentation'

With the ever-growing concerns of environmental and climate concerns for energy consumption in our society, it is crucial to develop novel solutions that improve the efficient utilization of distributed energy resources for energy efficiency and demand response (DR). As such, there is a need to develop targeted energy programs, which not only meet the requirement of energy goals for a community but also take the energy use patterns of individual households into account. To this end, a sound understanding of the energy behavior of customers at the neighborhood level is needed, which requires operational analytics on the wealth of energy data from customers and devices. In this dissertation, we focus on data-driven solutions for customer energy behavior characterization with applications to distributed energy management and flexibility provision. To do so, the following problems were studied: (1) how different customers can be segmented for DR events based on their energy-saving potential and balancing peak and off-peak demand, (2) what are the opportunities for extracting Time-of-Use of specific loads for automated DR applications from the whole-house energy data without in-situ training, and (3) how flexibility in customer demand adoption of renewable and distributed resources (e.g., solar panels, battery, and smart loads) can improve the demand-supply problem. In the first study, a segmentation methodology form historical energy data of households is proposed to estimate the energy-saving potential for DR programs at a community level. The proposed approach characterizes certain attributes in time-series data such as frequency, consistency, and peak time usage. The empirical evaluation of real energy data of 400 households shows the successful ranking of different subsets of consumers according to their peak energy reduction potential for the DR event. Specifically, it was shown that the proposed approach could successfully identify the 20-30% of customers who could achieve 50-70% total possible demand reduction for DR. Furthermore, the rebound effect problem (creating undesired peak demand after a DR event) was studied, and it was shown that the proposed approach has the potential of identifying a subset of consumers (~5%-40% with specific loads like AC and electric vehicle) who contribute to balance the peak and off-peak demand. A projection on Austin, TX showed 16MWh reduction during a 2-h event can be achieved by a justified selection of 20% of residential customers. In the second study, the feasibility of inferring time-of-use (ToU) operation of flexible loads for DR applications was investigated. Unlike several efforts that required considerable model parameter selection or training, we sought to infer ToU from machine learning models without in-situ training. As the first part of this study, the ToU inference from low-resolution 15-minute data (smart meter data) was investigated. A framework was introduced which leveraged the smart meter data from a set of neighbor buildings (equipped with plug meters) with similar energy use behavior for training. Through identifying similar buildings in energy use behavior, the machine learning classification models (including neural network, SVM, and random forest) were employed for inference of appliance ToU in buildings by accounting for resident behavior reflected in their energy load shapes from smart meter data. Investigation on electric vehicle (EV) and dryer for 10 buildings over 20 days showed an average F-score of 83% and 71%. As the second part of this study, the ToU inference from high-resolution data (60Hz) was investigated. A self-configuring framework, based on the concept of spectral clustering, was introduced that automatically extracts the appliance signature from historical data in the environment to avoid the problem of model parameter selection. Using the framework, appliance signatures are matched with new events in the electricity signal to identify the ToU of major loads. The results on ~1500 events showed an F-score of >80% for major loads like AC, washing machine, and dishwasher. In the third study, the problem of demand-supply balance, in the presence of varying levels of small-scale distributed resources (solar panel, battery, and smart load) was investigated. The concept of load complementarity between consumers and prosumers for load balancing among a community of ~250 households was investigated. The impact of different scenarios such as varying levels of solar penetration, battery integration level, in addition to users' flexibility for balancing the supply and demand were quantitatively measured. It was shown that (1) even with 100% adoption of solar panels, the renewable supply cannot cover the demand of the network during afternoon times (e.g., after 3 pm), (2) integrating battery for individual households could improve the self-sufficiency by more than 15% during solar generation time, and (3) without any battery, smart loads are also capable of improving the self-sufficiency as an alternative, by providing ~60% of what commercial battery systems would offer. The contribution of this dissertation is through introducing data-driven solutions/investigations for characterizing the energy behavior of households, which could increase the flexibility of the aggregate daily energy load profiles for a community. When combined, the findings of this research can serve to the field of utility-scale energy analytics for the integration of DR and improved reshaping of network energy profiles (i.e., mitigating the peaks and valleys in daily demand profiles).<br>Doctor of Philosophy<br>Buildings account for more than 70% of electricity consumption in the U.S., in which more than 40% is associated with the residential sector. During recent years, with the advancement in Information and Communication Technologies (ICT) and the proliferation of data from consumers and devices, data-driven methods have received increasing attention for improving the energy-efficiency initiatives. With the increased adoption of renewable and distributed resources in buildings (e.g., solar panels and storage systems), an important aspect to improve the efficiency by matching the demand and supply is to add flexibility to the energy consumption patterns (e.g., trying to match the times of high energy demand from buildings and renewable generation). In this dissertation, we introduced data-driven solutions using the historical energy data of consumers with application to the flexibility provision. Specific problems include: (1) introducing a ranking score for buildings in a community to detect the candidates that can provide higher energy saving in the future events, (2) estimating the operation time of major energy-intensive appliances by analyzing the whole-house energy data using machine learning models, and (3) investigating the potential of achieving demand-supply balance in communities of buildings under the impact of different levels of solar panels, battery systems, and occupants energy consumption behavior. In the first study, a ranking score was introduced that analyzes the historical energy data from major loads such as washing machines and dishwashers in individual buildings and group the buildings based on their potential for energy saving at different times of the day. The proposed approach was investigated for real data of 400 buildings. The results for EV, washing machine, dishwasher, dryer, and AC show that the approach could successfully rank buildings by their demand reduction potential at critical times of the day. In the second study, machine learning (ML) frameworks were introduced to identify the times of the day that major energy-intensive appliances are operated. To do so, the input of the model was considered as the main circuit electricity information of the whole building either in lower-resolution data (smart meter data) or higher-resolution data (60Hz). Unlike previous studies that required considerable efforts for training the model (e.g, defining specific parameters for mathematical formulation of the appliance model), the aim was to develop data-driven approaches to learn the model either from the same building itself or from the neighbors that have appliance-level metering devices. For the lower-resolution data, the objective was that, if a few samples of buildings have already access to plug meters (i.e., appliance level data), one could estimate the operation time of major appliances through ML models by matching the energy behavior of the buildings, reflected in their smart meter information, with the ones in the neighborhood that have similar behaviors. For the higher-resolution data, an algorithm was introduced that extract the appliance signature (i.e., change in the pattern of electricity signal when an appliance is operated) to create a processed library and match the new events (i.e., times that an appliance is operated) by investigating the similarity with the ones in the processed library. The investigation on major appliances like AC, EV, dryer, and washing machine shows the >80% accuracy on standard performance metrics. In the third study, the impact of adding small-scale distributed resources to individual buildings (solar panels, battery, and users' practice in changing their energy consumption behavior) for matching the demand-supply for the communities was investigated. A community of ~250 buildings was considered to account for realistic uncertain energy behavior across households. It was shown that even when all buildings have a solar panel, during the afternoon times (after 4 pm) in which still ~30% of solar generation is possible, the community could not supply their demand. Furthermore, it was observed that including users' practice in changing their energy consumption behavior and battery could improve the utilization of solar energy around >10%-15%. The results can serve as a guideline for utilities and decision-makers to understand the impact of such different scenarios on improving the utilization of solar adoption. These series of studies in this dissertation contribute to the body of literature by introducing data-driven solutions/investigations for characterizing the energy behavior of households, which could increase the flexibility in energy consumption patterns.

Abstract : Malignant brain tumors are the second leading cause of cancer related deaths in children under 20. There are nearly 700,000 people in the U.S. living with a brain tumor and 17,000 people are likely to loose their lives due to primary malignant and central nervous system brain tumor every year. To identify whether a patient is diagnosed with brain tumor in a non-invasive way, an MRI scan of the brain is acquired followed by a manual examination of the scan by an expert who looks for lesions (i.e. cluster of cells which deviate from healthy tissue). For treatment purposes, the tumor and its sub-regions are outlined in a procedure known as brain tumor segmentation . Although brain tumor segmentation is primarily done manually, it is very time consuming and the segmentation is subject to variations both between observers and within the same observer. To address these issues, a number of automatic and semi-automatic methods have been proposed over the years to help physicians in the decision making process. Methods based on machine learning have been subjects of great interest in brain tumor segmentation. With the advent of deep learning methods and their success in many computer vision applications such as image classification, these methods have also started to gain popularity in medical image analysis. In this thesis, we explore different machine learning and deep learning methods applied to brain tumor segmentation.<br>Résumé: Les tumeurs malignes au cerveau sont la deuxième cause principale de décès chez les enfants de moins de 20 ans. Il y a près de 700 000 personnes aux États-Unis vivant avec une tumeur au cerveau, et 17 000 personnes sont chaque année à risque de perdre leur vie suite à une tumeur maligne primaire dans le système nerveu central. Pour identifier de façon non-invasive si un patient est atteint d'une tumeur au cerveau, une image IRM du cerveau est acquise et analysée à la main par un expert pour trouver des lésions (c.-à-d. un groupement de cellules qui diffère du tissu sain). Une tumeur et ses régions doivent être détectées à l'aide d'une segmentation pour aider son traitement. La segmentation de tumeur cérébrale et principalement faite à la main, c'est une procédure qui demande beaucoup de temps et les variations intra et inter expert pour un même cas varient beaucoup. Pour répondre à ces problèmes, il existe beaucoup de méthodes automatique et semi-automatique qui ont été proposés ces dernières années pour aider les praticiens à prendre des décisions. Les méthodes basées sur l'apprentissage automatique ont suscité un fort intérêt dans le domaine de la segmentation des tumeurs cérébrales. L'avènement des méthodes de Deep Learning et leurs succès dans maintes applications tels que la classification d'images a contribué à mettre de l'avant le Deep Learning dans l'analyse d'images médicales. Dans cette thèse, nous explorons diverses méthodes d'apprentissage automatique et de Deep Learning appliquées à la segmentation des tumeurs cérébrales.

Amadeus is providing solutions to travel businesses. Today, messages from customers are received by one team who dispatches them manually.This team is making a lot of mistakes. The purpose of this thesisis to study, design and prototype a tool to analyse automatically these messages and send them to the right team. This paper studies differentsmachine learning methods to learn the classification from previous messages.Besides, we will use several text processing optimisation methods to improve our results.

This thesis is concerned with the problem of how to outline regions of interest in medical images, when the boundaries are weak or ambiguous and the region shapes are irregular. The focus on machine learning and interactivity leads to a common theme of the need to balance conflicting requirements. First, any machine learning method must strike a balance between how much it can learn and how well it generalises. Second, interactive methods must balance minimal user demand with maximal user control. To address the problem of weak boundaries,methods of supervised texture classification are investigated that do not use explicit texture features. These methods enable prior knowledge about the image to benefit any segmentation framework. A chosen dynamic contour model, based on probabilistic boundary tracking, combines these image priors with efficient modes of interaction. We show the benefits of the texture classifiers over intensity and gradient-based image models, in both classification and boundary extraction. To address the problem of irregular region shape, we devise a new type of statistical shape model (SSM) that does not use explicit boundary features or assume high-level similarity between region shapes. First, the models are used for shape discrimination, to constrain any segmentation framework by way of regularisation. Second, the SSMs are used for shape generation, allowing probabilistic segmentation frameworks to draw shapes from a prior distribution. The generative models also include novel methods to constrain shape generation according to information from both the image and user interactions. The shape models are first evaluated in terms of discrimination capability, and shown to out-perform other shape descriptors. Experiments also show that the shape models can benefit a standard type of segmentation algorithm by providing shape regularisers. We finally show how to exploit the shape models in supervised segmentation frameworks, and evaluate their benefits in user trials.