Search results

Title: DEVELOPING ALGORITHMIC TRADING STRATEGIES AND EMPIRICAL ANALYSIS WITH HIGH FREQUENCY TRADING DATA
Creator: Lee, Jeonghoe
Date: 2015, 2015-07
Description: The PhD dissertation research topics aim at developing algorithmic trading strategies and demonstrating data analysis skills. To be a...
Show moreThe PhD dissertation research topics aim at developing algorithmic trading strategies and demonstrating data analysis skills. To be a quantitative analyst as well as an academic scholar in financial trading area, these two professional backgrounds are indispensable. In detail, chapter 1 shows multi-objective optimization and spontaneous optimization of design variables. For instance, while conventional trading systems explore a single objective function, multi-objective optimization allows us to manage the essential trade-off among profit, standard deviation and maximum-drop. In addition, design parameters such as trading volume, the amount of historical data, and trading gateways of technical indicators are continuously optimized in real time. In chapter 2, this chapter shows an algorithmic trading system with the concept of machine learning, and demonstrating its various applications. The main purpose of this research is to propose objective numerical development framework in algorithmic trading. Chapter 3 pursues understanding liquidity measures which are critical for algorithmic traders and investors. Various liquidity measures have been suggested and they have different sensitivities to the market. This research analyzes liquidity measures and clarifies the relation between market price return & realized volatility and liquidity measures. In sum, with these three chapters, this dissertation will demonstrate necessary research topics in algorithmic trading.
Ph.D. in Management Science, July 2015
Show less

Title: ACTIVE LEARNING WITH RICH FEEDBACK
Creator: Sharma, Manali
Date: 2017, 2017-07
Description: One of the goals of artificial intelligence is to build predictive models that can learn from examples and make predictions. Predictive models...
Show moreOne of the goals of artificial intelligence is to build predictive models that can learn from examples and make predictions. Predictive models are useful in many domains and applications such as predicting fraud in credit card transactions, predicting whether a patient has heart-disease, predicting whether an email is a spam, predicting crime, recognizing images, recognizing speech, and many more. Building predictive models often requires supervision from a human expert. Since there is a human in the loop, the supervision needs to be as resource-efficient as possible to save the human’s time, cost, and effort in providing supervision. One solution to make the supervision resource-efficient is active learning, in which the active learner interacts with the human to acquire supervision, usually in the form of labels, for a few selected examples to effectively learn a function that can be used to make predictions. In this thesis, I explore more intuitive and effective use of human supervision through richer interactions between the human expert and the learner, so that the human can understand the learner’s reasoning for querying examples, and provide information beyond just the labels for examples. Traditional active learning approaches select informative examples for labeling, but the human does not get to know why those examples are useful to the learner. While interacting with the learner to annotate examples, humans can provide rich feedback, such as provide their prior knowledge and understanding of the domain, explain certain characteristics of the data, suggest important attributes of the data, give rationales for why an example belongs to a certain category, and provide explanations by pointing out features that are indicative of certain labels. The challenge, however, is that traditional supervised learning algorithms can learn from labeled examples, but they are not equipped to readily absorb the rich feedback. In this thesis, we enable the learner to explain its reasons for selecting instances and devise novel methods to incorporate rich feedback from humans into the training of predictive models. Specifically, I build and evaluate four novel active learning frameworks to enrich the interactions between the human and learner. First, I introduce an active learning framework to reveal the learner’s perception of informative instances. Specifically, we enable the learner to provide its reasons for uncertainty on examples and utilize the learner’s perception of uncertainty to select better examples for training the predictive models. Second, I introduce a framework to enrich the interaction between the human and learner for document classification task. Specifically, we ask the human to annotate documents and provide rationales for their annotation by highlighting phrases that convinced them to choose a particular label for a document. Third, I introduce a framework to enrich the interaction between the human and learner for the aviation domain, where we ask subject matter experts to examine flights and provide rationales for why certain flights have safety concerns. Fourth, I introduce a framework to enrich the interaction between the human and learner for document classification task, where we ask humans to provide explanations for classification by highlighting phrases that reinforce their belief in the document’s label and striking-out phrases that weaken their belief in the document’s label. We show that enabling richer interactions between the human and learner and incorporating rich feedback into learning lead to more effective training of predictive models and better utilization of human supervision.
Ph.D. in Computer Science, July 2017
Show less

Title: EVALUATION OF COMPUTER ALGORITHMS FOR THE ANALYSIS AND RECONSTRUCTION OF CARDIAC IMAGES
Creator: Parages, Felipe M.
Date: 2017, 2017-05
Description: In the medical imaging field, image processing algorithms must be evaluated by measuring performance at some clinically-relevant task of...
Show moreIn the medical imaging field, image processing algorithms must be evaluated by measuring performance at some clinically-relevant task of interest (i.e. task-based quality assessment). This dissertation relies on the task-based paradigm to evaluate motion-estimation and image-reconstruction methods, respectively, for two cardiac-imaging modalities, namely: cardiac-gated tagged Magnetic Resonance Imaging (MRI), and Single Photon Emission Computerized Tomography for Myocardial Perfusion Imaging (SPECT-MPI). First, a task-based approach is followed to evaluate three motion-estimation methods for clinical cardiac-gated tagged MRI, namely: non-rigid registration using a Deformable Mesh Model (DMM), Strain from Unwrapped Harmonic Phase (SUPHARP), and Feature-Based (FB) algorithms. More specifically, the goal is to quantify and rank their performances at both detection and estimation tasks. For detection, methods are evaluated per their ability to discern between normal and abnormal motion patterns in known cardiomyopathies (e.g. hypertension and mitral regurgitation). For estimation tasks, methods are evaluated per their accuracy at estimating several rotation/twist and strain features of clinical interest; since true values for these features are generally unknown, a statistical Regression Without Truth (RWT) model is adopted, which does not assume the existence of a “gold-standard” method to use as a ground-truth reference. Moreover, the RWT model provides with an objective figure-of-merit that allows ranking methods in absolute fashion. Second, a novel anthropomorphic Model Observer (MO) is proposed for optimization of SPECT-MPI reconstruction algorithms such as Filtered Back-projection (FBP) and Ordered-subsets Expectation Maximization (OSEM). MOs are computer models that aim to mimic the performance of human readers (typically radiologists) at some clinically relevant task of interest. The proposed MO is based on supervised machine-learning classification, for the diagnostic tasks of detection, localization and assessment of perfusion defects. The MO is trained using an ensemble of synthetic cases whose perfusion were scored (i.e. labeled) by human specialists. The trained MO is subsequently applied on images not read by humans (both synthetic and clinical), aiming to predict their diagnostic scores. Results show that the proposed MO accurately predicts human diagnostic performances. Furthermore, it generalizes well to new images not used during training, not only from different reconstruction algorithms, but also from synthetic to clinical cases.
Ph.D. in Electrical and Computer Engineering, May 2017
Show less

Title: LIGHTLY SUPERVISED MACHINE LEARNING FOR CLASSIFYING ONLINE SOCIAL DATA
Creator: Mohammady Ardehaly, Ehsan
Date: 2017, 2017-05
Description: Classifying latent attributes of social media users has many applications in public health, politics, and marketing. For example, web-based...
Show moreClassifying latent attributes of social media users has many applications in public health, politics, and marketing. For example, web-based studies of public health require monthly estimates of the health status and demographics of users based on their public communications. Most existing approaches are based on supervised learning. Supervised learning requires human annotated labeled data, which can be expensive and many attributes such as health are hard to annotate at the user level. In this thesis, we investigate classification algorithms that use population statistical constraints such as demographics, names, polls, and social network followers to predict individual user attributes. For example, the racial makeup of counties is a source of light supervision came from the U.S. Census to train classification models. These statistics are usually easy to obtain, and a large amount of unlabeled data from social media sites (e.g. Twitter) are available. Learning from Label Proportions (LLP) is a lightly supervised approach when the training data is multiple sets of unlabeled samples and only label distributions of them are known. Because social media users are not a representative sample of the population and constraints are too noisy, using existing LLP models (e.g. linear models, label regularization) is insufficient. We develop several new LLP algorithms to extend LLP to deal with this bias, including bag selection and robust classification models. Also, we propose a scalable model to infer political sentiment from the high temporal big data, and estimate the daily conditional probability of different attributes as a supplement method to polls, for social scientists. Because, constraints are not often available in some domains (e.g. blogs), we propose a self-training algorithm to gradually adapt a classifier trained on social media to a different but similar field. We also extend our framework to deep learning and provide empirical results for demographic classification using the user profile image. Finally, when both textual and profile image are available for a user, we provide a co-training algorithm to iteratively improve both image and text classifications accuracy, and apply an ensemble method to achieve the highest precision.
Ph.D. in Computer Science, May 2017
Show less

Title: DEEP LEARNING IN ENGINEERING MECHANICS: WAVE PROPAGATION AND DYNAMICS IMPLEMENTATIONS
Creator: Finol Berrueta, David
Date: 2019
Description: With the advent of Artiﬁcial Intelligence research in the 1960s, the need for intelligent systems that are able to truly comprehend the...
Show moreWith the advent of Artiﬁcial Intelligence research in the 1960s, the need for intelligent systems that are able to truly comprehend the physical world around them became relevant. Signiﬁcant milestones in the realm of machine learning and, in particular, deep learning during the past decade have led to advanced data-driven models that are able to approximate complex functions from pure observations. When it comes to the application of physics-based scenarios, the vast majority of these models rely on statistical and optimization constructs, leaving minimal room in their development for the physics-driven frameworks that more traditional engineering and science ﬁelds have been developing for centuries. On the other hand, the more traditional engineering ﬁelds, such as mechanics, have evolved on a diﬀerent set of modeling tools that are mostly based on physics driven assumptions and equations, typically aided by statistical tools for uncertainty handling. Deep learning models can provide signiﬁcant implementation advantages in commercial systems over traditional engineering modeling tools in the current economies of scale, but they tend to lack the strong reliability their counterparts naturally allow. The work presented in this thesis is aimed at assessing the potential of deep learning tools, such as Convolutional Neural Networks and Long Short-Term Memory Networks, as data-driven models in engineering mechanics, with a major focus on vibration problems. In particular, two implementation cases are presented: a data driven surrogate model to a Phononic eigenvalue problem, and a physics-learning model in rigid-body dynamics scenario. Through the applications presented, this work that shows select deep learning architectures can appropriately approximate complex functions found in engineering mechanics from a system’s time history or state and generalize to set expectations outside training domains. In spatio-temporal systems, it is also that shown local learning windows along space and time can provide improved model reliability in their approximation and generalization performance
Show less

Title: Learning Stochastic Governing Laws from Noisy Data Using Normalizing Flows
Creator: McClure, William Jacob
Date: 2021
Description: With the increasing availability of massive collections of data, researchers in all sciences need tools to synthesize useful and pertinent...
Show moreWith the increasing availability of massive collections of data, researchers in all sciences need tools to synthesize useful and pertinent descriptors of the systems they study. Perhaps the most fundamental knowledge of a dynamical system is its governing laws, which describe its evolution through time and can be lever-aged for a number of analyses about its behavior. We present a novel technique for learning the infinitesimal generator of a Markovian stochastic process from large, noisy datasets generated by a stochastic system. Knowledge of the generator in turn allows us to find the governing laws for the process. This technique relies on normalizing flows, neural networks that estimate probability densities, to learn the density of time-dependent stochastic processes. We establish the efficacy of this technique on multiple systems with Brownian noise, and use our learned governing laws to perform analysis on one system by solving for its mean exit time. Our approach also allows us to learn other dynamical behaviors such as escape probability and most probable pathways in a system. The potential impact of this technique is far-reaching, since most stochastic processes in various fields are assumed to be Markovian, and the only restriction for applying our method is available data from a time near the beginning of an experiment or recording.
Show less

Title: DATA-DRIVEN OPTIMIZATION OF NEXT GENERATION HIGH-DENSITY WIRELESS NETWORKS
Creator: Khairy, Sami
Date: 2021
Description: The Internet of Things (IoT) paradigm is poised to advance all aspects of modern society by enabling ubiquitous communications and...
Show moreThe Internet of Things (IoT) paradigm is poised to advance all aspects of modern society by enabling ubiquitous communications and computations. In the IoT era, an enormous number of devices will be connected wirelessly to the internet in order to enable advanced data-centric applications. The projected growth in the number of connected wireless devices poses new challenges to the design and optimization of future wireless networks. For a wireless network to support a massive number of devices, advanced physical layer and channel access techniques should be designed, and high-dimensional decision variables should be optimized to manage network resources. However, the increased network scale, complexity, and heterogeneity, render the network unamenable to traditional closed-form mathematical analysis and optimization, which makes future high-density wireless networks seem unmanageable. In this thesis, we study the design and data-driven optimization of future high-density wireless networks operating over the unlicensed band, including Radio Frequency (RF)-powered wireless networks, solar-powered Unmanned Aerial Vehicle (UAV)-based wireless networks, and random Non-Orthogonal Multiple Access (NOMA) wireless networks. For each networking scenario, we first analyze network dynamics and identify performance trade-offs. Next, we design adaptive network controllers in the form of high-dimensional multi-objective optimization problems which exploit the heterogeneity in users' wireless propagation channels and energy harvesting to maximize the network capacity, manage battery energy resources, and achieve good user capacity fairness. To solve the high-dimensional optimization problems and learn the optimal network control policy, we propose novel, cross-layer, scalable, model-based and model-free data-driven network optimization and resource management algorithms that integrate domain-specific analyses with advanced machine learning techniques from deep learning, reinforcement learning, and uncertainty quantification. Furthermore, convergence of the proposed algorithms to the optimal solution is theoretically analyzed using mathematical results from metric spaces, convex optimization, and game theory. Finally, extensive simulations have been conducted to demonstrate the efficacy and superiority of our network optimization and resource management techniques compared with existing methods. Our research contributions provide practical insights for the design and data-driven optimization of next generation high-density wireless networks.
Show less

Title: KERNEL FREE BOUNDARY INTEGRAL METHOD AND ITS APPLICATIONS
Creator: Cao, Yue
Date: 2022
Description: We developed a kernel-free boundary integral method (KFBIM) for solving variable coefficients partial differential equations (PDEs) in a...
Show moreWe developed a kernel-free boundary integral method (KFBIM) for solving variable coefficients partial differential equations (PDEs) in a doubly-connected domain. We focus our study on boundary value problems (BVP) and interface problems. A unique feature of the KFBIM is that the method does not require an analytical form of the Green’s function for designing quadratures, but rather computes boundary or volume integrals by solving an equivalent interface problem on Cartesian mesh. We decompose the problem defined in a doubly-connected domain into two separate interface problems. Then we evaluate integrals using a Krylov subspace iterative method in a finite difference framework. The method has second-order accuracy in space, and its complexity is linearly proportional to the number of mesh points. Numerical examples demonstrate that the method is robust for variable coefficients PDEs, even for cases when diffusion coefficients ratio is large and when two interfaces are close. We also develop two methods to compute moving interface problems whose coefficients in governing equations are spatial functions. Variable coefficients could be a non-homogeneous viscosity in Hele-Shaw problem or an uptake rate in tumor growth problems. We apply the KFBIM to compute velocity of the interface which allows more flexible boundary condition in a restricted domain instead of free space domain. A semi-implicit and an implicit methods were developed to evolve the interface. Both methods have few restrictions on the time step regardless of numerical stiffness. Theyalso could be extended to multi-phase problem, e.g., annulus domain. The methods have second-order accuracy in both space and time. Machine learning techniques have achieved magnificent success in the past decade. We couple the KFBIM with supervised learning algorithms to improve efficiency. In the KFBIM, we apply a finite difference scheme to find dipole density of the boundary integral iteratively, which is quite costly. We train a linear model to replace the finite difference solver in GMRES iterations. The cost, measured in CPU time, is significantly reduced. We also developed an efficient data generator for training and derived an empirical rule for data set size. In the future work, the model could be expanded to moving interface problems. The linear model will be replaced by neural network models, e.g., physics-informed neural networks (PINNs).
Show less

Title: Exploiting contextual information for deep learning based object detection
Creator: Zhang, Chen
Date: 2020
Description: Object detection has long been an important research topic in computer vision area. It forms the basis of many applications. Despite the great...
Show moreObject detection has long been an important research topic in computer vision area. It forms the basis of many applications. Despite the great progress made in recent years, object detection is still a challenging task. One of the keys to improving the performance of object detection is to utilize the contextual information from the image itself or from a video sequence. Contextual information is defined as the interrelated condition in which something exists or occurs. In object detection, such interrelated condition can be related background/surroundings, support from image segmentation task, and the existence of the object in the temporal domain for video-based object detection. In this thesis, we propose multiple methods to exploit contextual information to improve the performance of object detection from images and videos.First, we focus on exploiting spatial contextual information in still-image based object detection, where each image is treated independently. Our research focuses on extracting contextual information using different approaches, which includes recurrent convolutional layer with feature concatenation (RCL-FC), 3-D recurrent neural networks (3-D RNN), and location-aware deformable convolution. Second, we focus on exploiting pixel-level contextual information from a related computer vision task, namely image segmentation. Our research focuses on applying a weakly-supervised auxiliary multi-label segmentation network to improve the performance of object detection without increasing the inference time. Finally, we focus on video object detection, where the temporal contextual information between video frames are exploited. Our first research involves modeling short-term temporal contextual information using optical flow and modeling long-term temporal contextual information using convLSTM. Another research focuses on creating a two-path convLSTM pyramid to handle multi-scale temporal contextual information for dealing with the change in object's scale. Our last work is the event-aware convLSTM that forces convLSTM to learn about the event that causes the performance to drop in a video sequence.
Show less

Title: BIG DATA AS A SERVICE WITH PRIVACY AND SECURITY
Creator: Hou, Jiahui
Date: 2020
Description: With the increase of data production sources like IoT devices (e.g., smartwatches, smartphones) and data from smart home (health sensor,...
Show moreWith the increase of data production sources like IoT devices (e.g., smartwatches, smartphones) and data from smart home (health sensor, energy sensors), truly mind-boggling amounts of data are generated daily. Building a big data as a service system, that combines big data technologies and cloud computing, will enhance the huge value of big data and tremendously boost the economic growth in various areas. Big data as a service has evolved into a booming market, but with the emergence of larger privacy and security challenges. Privacy and security concerns limit the development of big data as a service and increasingly become one of the main reasons why most data are not shared and well utilized. This dissertation aims to build a new incrementally deployable middleware for the current and future big data as a service eco-system in order to guarantee privacy and security. This middleware will retain privacy and security in the data querying and ensure privacy preservation in data analysis. In addition, emerging cloud computing contributes to providing valuable services associated with machine learning (ML) techniques. We consider privacy issues in both traditional queries and ML queries (i.e., ML classification) in this dissertation. The final goal is to design and develop a demonstrable system that can be deployed in the big data as a service system in order to guarantee the privacy of data/ service owners as well as users, enabling secure data analysis and services.Firstly, we consider a private dataset composed of a set of individuals, and the data is outsourced to a remote cloud server. We revisit the classic query auditing problem in the outsourcing scenario. Secondly, we study privacy preserving neural network classification where source data is randomly partitioned. Thirdly, we concern the privacy of confidential training dataset and models which are typically trained in a centralized cloud server but publicly accessible, \ie online ML-as-a-Service (MLaaS). Lastly, we consider the offline MLaaS systems. We design, implement, and evaluate a secure ML framework to enable MLaaS on clients' edge devices, where a ``encrypted'' ML models are stored locally.
Show less

Title: Optimization methods and machine learning model for improved projection of energy market dynamics
Creator: Saafi, Mohamed Ali
Date: 2023
Description: Since signing the legally binding Paris agreement, governments have been striving to fulfill the decarbonization mission. To reduce carbon...
Show moreSince signing the legally binding Paris agreement, governments have been striving to fulfill the decarbonization mission. To reduce carbon emissions from the transportation sector, countries around the world have created a well-defined new energy vehicle development strategy that is further expanding into hydrogen vehicle technologies. In this study, we develop the Transportation Energy Analysis Model (TEAM) to investigate the impact of the CO2 emissions policies on the future of the automotive industries. On the demand side, TEAM models the consumer choice considering the impacts of technology cost, energy cost, refueling/charging availability, consumer travel pattern. On the supply side, the module simulates the technology supply by the auto-industry with the objective of maximizing industry profit under the constraints of government policies. Therefore, we apply different optimization methods to guarantee reaching the optimal automotive industry response each year up to 2050. From developing an upgraded differential evolution algorithm, to applying response surface methodology to simply the objective function, the goal is to enhance the optimization performance and efficiency compared to adopting the standard genetic algorithm. Moreover, we investigate TEAM’s robustness by applying a sensitivity analysis to find the key parameters of the model. Finally based on the key sensitive parameters that drive the automotive industry, we develop a neural network to learn the market penetration model and predict the market shares in a competitive time by bypassing the total cost of ownership analysis and profit optimization. The central motivating hypothesis of this thesis is that modern optimization and modeling methods can be applied to obtain a computationally-efficient, industry-relevant model to predict optimal market sales shares for light-duty vehicle technologies. In fact, developing a robust market penetration model that is optimized using sophisticated methods is a crucial tool to automotive companies, as it quantifies consumer’s behavior and delivers the optimal way to maximize their profits by highlighting the vehicles technologies that they could invest in. In this work, we prove that TEAM reaches the global solution to optimize not only the industry profits but also the alternative fuels optimized blends such as synthetic fuels. The time complexity of the model has been substantially improved to decrease from hours using the genetic algorithm, to minutes using differential evolution, to milliseconds using neural network.
Show less

repository.iit

Search the repository

Enabled Filters

Refine Results

Type

Date

Department

Subject

Creator

Rights