Emerging technologies, including distributed energy resources (DERs), internet-of-things and advanced distribution management systems, are revolutionizing the power industry. They provide benefits like higher operation flexibility and lower bulk grid dependency, and are moving the modern power grid towards a decentralized, interconnected and intelligent direction. Consequently, the emphasis of the system operation management has been shifted from the supply-side to the demand-side. It calls for a reconsideration of the business model for future retail market operators. To address this need, this dissertation proposes an innovative retail market solution tailored to market environments penetrated with price-responsive DERs. The work is presented from aspects of theoretical study, test-bed platform development, and experimental analysis, within which two topics relevant to the retail market operation are investigated in depth. The first topic covers the modeling of key retail market participants. With regard to price-insensitive participants, fixed loads are treated as the representative. Deep learning-based day-ahead load forecasting models are developed in this study, utilizing both recurrent and convolutional neural networks, to predict the part of demands that keep fixed regardless of the market price. With regard to price-sensitive participants, battery storages are selected as the representative. An optimization-based battery arbitrage model is developed in this study to represent their price-responsive behaviors in response to a dynamic price. The second topic further investigates how the retail market model and pricing strategy should be designed to incentivize these market participants. Different from existing works, this study innovatively proposes a profit-neutral double-price-signal retail market model. Such a design differentiates elastic prosumers, who actively offer flexibilities to the system operation, from normal inelastic consumers/generators, based on their sensitivities to the market price. Two price signals, namely retail grid service price and retail energy price, are then introduced to separately quantify values of the flexibility, provided by elastic participants, and the electricity commodity, sold/bought to/from inelastic participants. Within the proposed retail market, a non-profit retail market operator (RMO) manages and settles the market through determining the price signals and supplementary subsidy to minimize the overall system cost. In response to the announced retail grid service price, elastic prosumers adjust their day-ahead operating schedules to maximize their payoffs. Given the interdependency between decisions made by the RMO and elastic participants, a retail pricing scheme, formulated based on a bi-level optimization framework, is proposed. Additional efforts are made on merging and linearizing the original non-convex bi-level problem into a single-level mixed-integer linear programming problem to ensure the computational efficiency of the retail pricing tool. Case studies are conducted on a modified IEEE 34-bus test-bed system, simulating both physical operations of the power grid and financial interactions inside the retail market. Experimental results demonstrate promising properties of the proposed retail market solution: First of all, it is able to provide cost-saving benefits to inelastic customers and create revenues for elastic customers at the same time, justifying the rationalities of these participants to join the market. Second of all, the addition of the grid service subsidy not only strengthens the profitability of the elastic customer, but also ensures that the benefit enjoyed per customer will not be compromised by the competition brought up by a growing number of participants. Furthermore, it is able to properly capture impacts from line losses and voltage constraints on the system efficiency and stability, so as to derive practical pricing solutions that respect the system operating rules. Last but not least, it encourages the technology improvement of elastic assets as elastic assets in better conditions are more profitable and could better save the electricity bills for inelastic customers. Above all, the superiority of the proposed retail market solution is proven. It can serve as a promising start for the retail electricity market reconstruction. / Doctor of Philosophy / The electricity market plays a critical role in ensuring the economic and secure operation of the power system. The progress made by distributed energy resources (DERs) has reshaped the modern power industry bringing a larger proportion of price-responsive behaviors to the demand-side. It challenges the traditional wholesale-only electricity market and calls for an addition of retail markets to better utilize distributed and elastic assets. Therefore, this dissertation targets at offering a reliable and computational affordable retail market solution to bridge this knowledge gap. Different from existing works, this study assumes that the retail market is managed by a profit-neutral retail market operator (RMO), who oversees and facilitates the system operation for maximizing the system efficiency rather than making profits. Market participants are categorized into two groups: inelastic participants and elastic participants, based on their sensitivity to the market price. The motivation behind this design is that instead of treating elastic participants as normal customers, it is more reasonable to treat them as grid service providers who offer operational flexibilities that benefit the system efficiency. Correspondingly, a double-signal pricing scheme is proposed, such that the flexibility, provided by elastic participants, and the electricity commodity, generated/consumed by inelastic participants, are separately valued by two distinct prices, namely retail grid service price and retail energy price. A grid service subsidy is also introduced in the pricing system to provide supplementary incentives to elastic customers. These two price signals in addition to the subsidy are determined by the RMO via solving a bi-level optimization problem given the interdependency between the prices and reaction of elastic participants. Experimental results indicate that the proposed retail market model and pricing scheme are beneficial for both types of market participants, practical for the network-constrained real-world implementation, and supportive for the technology improvement of elastic assets.

Traffic accidents are of concern for traffic safety; 1.25 million deaths are reported each year. Hence, it is crucial to have access to real-time data and rapidly detect or predict accidents. Predicting the occurrence of a highway car accident accurately any significant length of time into the future is not feasible since the vast majority of crashes occur due to unpredictable human negligence and/or error. However, rapid traffic incident detection could reduce incident-related congestion and secondary crashes, alleviate the waste of vehicles’ fuel and passengers’ time, and provide appropriate information for emergency response and field operation. While the focus of most previously proposed techniques is predicting the number of accidents in a certain region, the problem of predicting the accident occurrence or fast detection of the accident has been little studied. To address this gap, we propose a deep learning approach and build a deep neural network model based on long short term memory (LSTM). We apply it to forecast the expected speed values on freeways’ links and identify the anomalies as potential accident occurrences. Several detailed features such as weather, traffic speed, and traffic flow of upstream and downstream points are extracted from big datasets. We assess the proposed approach on a traffic dataset from Sacramento, California. The experimental results demonstrate the potential of the proposed approach in identifying the anomalies in speed value and matching them with accidents in the same area. We show that this approach can handle a high rate of rapid accident detection and be implemented in real-time travelers’ information or emergency management systems. / M.S. / Rapid traffic accident detection/prediction is essential for scaling down non-recurrent conges- tion caused by traffic accidents, avoiding secondary accidents, and accelerating emergency system responses. In this study, we propose a framework that uses large-scale historical traffic speed and traffic flow data along with the relevant weather information to obtain robust traffic patterns. The predicted traffic patterns can be coupled with the real traffic data to detect anomalous behavior that often results in traffic incidents in the roadways. Our framework consists of two major steps. First, we estimate the speed values of traffic at each point based on the historical speed and flow values of locations before and after each point on the roadway. Second, we compare the estimated values with the actual ones and introduce the ones that are significantly different as an anomaly. The anomaly points are the potential points and times that an accident occurs and causes a change in the normal behavior of the roadways. Our study shows the potential of the approach in detecting the accidents while exhibiting promising performance in detecting the accident occurrence at a time close to the actual time of occurrence.

Unsupervised anomaly detection is the task of identifying examples that differ from the normal or expected pattern without the use of labeled training data. Our research addresses shortcomings in two existing anomaly detection algorithms, Kernel Principal Component Analysis (KPCA) and Autoencoders (AE), and proposes novel solutions to improve both of their performances in the unsupervised settings. Anomaly detection has several useful applications, such as intrusion detection, fault monitoring, and vision processing. More specifically, anomaly detection can be used in autonomous driving to identify obscured signage or to monitor intersections. Kernel techniques are desirable because of their ability to model highly non-linear patterns, but they are limited in the unsupervised setting due to their sensitivity of parameter choices and the absence of a validation step. Additionally, conventionally KPCA suffers from a quadratic time and memory complexity in the construction of the gram matrix and a cubic time complexity in its eigendecomposition. The problem of tuning the Gaussian kernel parameter, $sigma$, is solved using the mini-batch stochastic gradient descent (SGD) optimization of a loss function that maximizes the dispersion of the kernel matrix entries. Secondly, the computational time is greatly reduced, while still maintaining high accuracy by using an ensemble of small, textit{skeleton} models and combining their scores. The performance of traditional machine learning approaches to anomaly detection plateaus as the volume and complexity of data increases. Deep anomaly detection (DAD) involves the applications of multilayer artificial neural networks to identify anomalous examples. AEs are fundamental to most DAD approaches. Conventional AEs rely on the assumption that a trained network will learn to reconstruct normal examples better than anomalous ones. In practice however, given sufficient capacity and training time, an AE will generalize to reconstruct even very rare examples. Three methods are introduced to more reliably train AEs for unsupervised anomaly detection: Cumulative Error Scoring (CES) leverages the entire history of training errors to minimize the importance of early stopping and Percentile Loss (PL) training aims to prevent anomalous examples from contributing to parameter updates. Lastly, early stopping via Knee detection aims to limit the risk of over training. Ultimately, the two new modified proposed methods of this research, Unsupervised Ensemble KPCA (UE-KPCA) and the modified training and scoring AE (MTS-AE), demonstrates improved detection performance and reliability compared to many baseline algorithms across a number of benchmark datasets. / Master of Science / Anomaly detection is the task of identifying examples that differ from the normal or expected pattern. The challenge of unsupervised anomaly detection is distinguishing normal and anomalous data without the use of labeled examples to demonstrate their differences. This thesis addresses shortcomings in two anomaly detection algorithms, Kernel Principal Component Analysis (KPCA) and Autoencoders (AE) and proposes new solutions to apply them in the unsupervised setting. Ultimately, the two modified methods, Unsupervised Ensemble KPCA (UE-KPCA) and the Modified Training and Scoring AE (MTS-AE), demonstrates improved detection performance and reliability compared to many baseline algorithms across a number of benchmark datasets.

Great progress has been made to leverage the improvements made in natural language processing and machine learning to better mine data from journals, conference proceedings, and other digital library documents. However, these advances do not extend well to book-length documents such as electronic theses and dissertations (ETDs). ETDs contain extensive research data; stakeholders -- including researchers, librarians, students, and educators -- can benefit from increased access to this corpus. Challenges arise while working with this corpus owing to the varied nature of disciplines covered as well as the use of domain-specific language. Prior systems are not tuned to this corpus. This research aims to increase the accessibility of ETDs by the automatic classification of chapters of an ETD using machine learning and deep learning techniques. This work utilizes an ETD-centric target classification system. It demonstrates the use of custom trained word and document embeddings to generate better vector representations of this corpus. It also describes a methodology to leverage extractive summaries of chapters of an ETD to aid in the classification process. Our findings indicate that custom embeddings and the use of summarization techniques can increase the performance of the classifiers. The chapter-level labels generated by this research help to identify the level of interdisciplinarity in the corpus. The automatic classifiers can also be further used in a search engine interface that would help users to find the most appropriate chapters. / Master of Science / Electronic Theses and Dissertations (ETDs) are submitted by students at the end of their academic study. These works contain research information pertinent to a given field. Increasing the accessibility of such documents will be beneficial to many stakeholders including students, researchers, librarians, and educators. In recent years, a great deal of research has been conducted to better extract information from textual documents with the use of machine learning and natural language processing. However, these advances have not been applied to increase the accessibility of ETDs. This research aims to perform the automatic classification of chapters extracted from ETDs. That will reduce the human effort required to label the key parts of these book-length documents. Additionally, when considered by search engines, such categorization can aid users to more easily find the chapters that are most relevant to their research.

This work aims to develop a deep learning model for land cover quantification through hyperspectral unmixing using an unsupervised autoencoder. Land cover identification and classification is instrumental in urban planning, environmental monitoring and land management. With the technological advancements in remote sensing, hyperspectral imagery which captures high resolution images of the earth's surface across hundreds of wavelength bands, is becoming increasingly popular. The high spectral information in these images can be analyzed to identify the various target materials present in the image scene based on their unique reflectance patterns. An autoencoder is a deep learning model that can perform spectral unmixing by decomposing the complex image spectra into its constituent materials and estimating their abundance compositions. The advantage of using this technique for land cover quantification is that it is completely unsupervised and eliminates the need for labelled data which generally requires years of field survey and formulation of detailed maps. We evaluate the performance of the autoencoder on various synthetic and real hyperspectral images consisting of different land covers using similarity metrics and abundance maps. The scalability of the technique with respect to landscapes is assessed by evaluating its performance on hyperspectral images spanning across 100m x 100m, 200m x 200m, 1000m x 1000m, 4000m x 4000m and 5000m x 5000m regions. Finally, we analyze the performance of this technique by comparing it to several supervised learning methods like Support Vector Machine (SVM), Random Forest (RF) and multilayer perceptron using F1-score, Precision and Recall metrics and other unsupervised techniques like K-Means, N-Findr, and VCA using cosine similarity, mean square error and estimated abundances. The land cover classification obtained using this technique is compared to the existing United States National Land Cover Database (NLCD) classification standard. / Master of Science / This work aims to develop an automated deep learning model for identifying and estimating the composition of the different land covers in a region using hyperspectral remote sensing imagery. With the technological advancements in remote sensing, hyperspectral imagery which captures high resolution images of the earth's surface across hundreds of wavelength bands, is becoming increasingly popular. As every surface has a unique reflectance pattern, the high spectral information contained in these images can be analyzed to identify the various target materials present in the image scene. An autoencoder is a deep learning model that can perform spectral unmixing by decomposing the complex image spectra into its constituent materials and estimate their percent compositions. The advantage of this method in land cover quantification is that it is an unsupervised technique which does not require labelled data which generally requires years of field survey and formulation of detailed maps. The performance of this technique is evaluated on various synthetic and real hyperspectral datasets consisting of different land covers. We assess the scalability of the model by evaluating its performance on images of different sizes spanning over a few hundred square meters to thousands of square meters. Finally, we compare the performance of the autoencoder based approach with other supervised and unsupervised deep learning techniques and with the current land cover classification standard.

Unfavorable environmental and (or) human displacement may engender the need for Search and Rescue (SAR). Challenges such as inaccessibility, large search areas, and heavy reliance on available responder count, limited equipment and training makes SAR a challenging problem. Additionally, SAR operations also pose significant risk to involved responders. This opens a remarkable opportunity for robotic systems to assist and augment human understanding of the harsh environments. A large body of work exists on the introduction of ground and aerial robots in visual and temporal inspection of search areas with varying levels of autonomy. Unfortunately, limited autonomy is the norm in such systems, due to the limitations presented by on-board UAV resources and networking capabilities. In this work we propose a new multi-agent approach to SAR and introduce a wearable compute cluster in the form factor of a backpack. The backpack allows offloading compute intensive tasks such as Lost Person Behavior Modelling, Path Planning and Deep Neural Network based computer vision applications away from the UAVs and offers significantly high performance computers to execute them. The backpack also provides for a strong networking backbone and task orchestrators which allow for enhanced coordination and resource sharing among all the agents in the system. On the basis of our benchmarking experiments, we observe that the backpack can significantly boost capabilities and success in modern SAR responses. / Master of Science / Unfavorable environmental and (or) human displacement may engender the need for Search and Rescue (SAR). Challenges such as inaccessibility, large search areas, and heavy reliance on available responder count, limited equipment and training makes SAR a challenging problem. Additionally, SAR operations also pose significant risk to involved responders. This opens a remarkable opportunity for robotic systems to assist and augment human understanding of the harsh environments. A large body of work exists on the introduction of ground and aerial robots in visual and temporal inspection of search areas with varying levels of autonomy. Unfortunately, limited autonomy is the norm in such systems, due to the limitations presented by on-board UAV resources and networking capabilities. In this work we propose a new multi-agent approach to SAR and introduce a wearable compute cluster in the form factor of a backpack. The backpack allows offloading compute intensive tasks such as Lost Person Behavior Modelling, Path Planning and Deep Neural Network based computer vision applications away from the UAVs and offers significantly high performance computers to execute them. The backpack also provides for a strong networking backbone and task orchestrators which allow for enhanced coordination and resource sharing among all the agents in the system. On the basis of our benchmarking experiments, we observe that the backpack can significantly boost capabilities and success in modern SAR responses.

Neuroscience as a field is collecting more data than at any other time in history. The scale of this data allows us to ask fundamental questions about the mechanisms of brain function, the basis of behavior, and the development of disorders. Our ambitious goals as well as the abundance of data being recorded call for reproducible, reliable, and accessible systems to push the field forward. While we have made great strides in building reproducible and accessible machine learning (ML) systems for neuroscience, reliability remains a major issue. In this dissertation, we show that we can leverage existing data and domain expert knowledge to build more reliable ML systems to study animal behavior. First, we consider animal pose estimation, a crucial component in many scientific investigations. Typical transfer learning ML methods for behavioral tracking treat each video frame and object to be tracked independently. We improve on this by leveraging the rich spatial and temporal structures pervasive in behavioral videos. Our resulting weakly supervised models achieve significantly more robust tracking. Our tools allow us to achieve improved results when we have imperfect, limited data while requiring users to label fewer training frames and speeding up training. We can more accurately process raw video data and learn interpretable units of behavior. In turn, these improvements enhance performance on downstream applications. Next, we consider a ubiquitous approach to (attempt to) improve the reliability of ML methods, namely combining the predictions of multiple models, also known as deep ensembling. Ensembles of classical ML predictors, such as random forests, improve metrics such as accuracy by well-understood mechanisms such as improving diversity. However, in the case of deep ensembles, there is an open methodological question as to whether, given the choice between a deep ensemble and a single neural network with similar accuracy, one model is truly preferable over the other. Via careful experiments across a range of benchmark datasets and deep learning models, we demonstrate limitations to the purported benefits of deep ensembles. Our results challenge common assumptions regarding the effectiveness of deep ensembles and the “diversity” principles underpinning their success, especially with regards to important metrics for reliability, such as out-of-distribution (OOD) performance and effective robustness. We conduct additional studies of the effects of using deep ensembles when certain groups in the dataset are underrepresented (so-called “long tail” data), a setting whose importance in neuroscience applications is revealed by our aforementioned work. Altogether, our results demonstrate the essential importance of both holistic systems work and fundamental methodological work to understand the best ways to apply the benefits of modern machine learning to the unique challenges of neuroscience data analysis pipelines. To conclude the dissertation, we outline challenges and opportunities in building next-generation ML systems.

Data serves as the foundation in building effective deep learning algorithms, yet the process of annotation and curation to maintain high data quality is time-intensive. The challenges arise from the vast diversity and large amount of data, and the inherent complexity in labeling each sample. Then, relying on manual effort to construct high-quality data is implausible and not sustainable in the real world. Instead, this thesis introduces a set of novel techniques to effectively learn from the data with less curation, which is more practical in building AI applications. In this thesis, we systematically study different directions in learning from low-quality data, with a specific focus on visual understanding and being robust to complicated label bias & noise. We first examine the bias exhibited in the whole dataset for image classification, and derive the debiasing algorithms based on representation learning that explores the geometry and distribution of embeddings. In this way, we mitigate the uneven performance over image classes caused by data imbalance, and suppress the spurious correlation between the input images and output predictions such that the model can be better generalized to new classes and maintain robust accuracy with a small number of labeled samples as reference. Then, we extend our analysis to the open-text description of each sample and explore the noisy label in multi-modal pre-training. We build our framework upon contrastive language-image pretraining to learn a common representation space and improve the training effectiveness by automatically eliminating false negative labels and correcting the false positives. Additionally, our approaches show the potential to tackle the label bias in multi-modal training data. Throughout this dissertation, the unifying focus is on the effective approach for learning from low-quality data, which has considered the learning issues from two complementary aspects of data labeling, i.e., the bias in global distribution and the noise in annotation for each sample (local). Different from prior research that are developed on the data with biased & noisy label but artificially simulated from well-curated datasets, our approach has been validated to be resilient to the complex bias and noise in the real-world scenario. We hope our approach can offer contributions to the field of multi-modal machine learning with applications involving real-world low-quality data and the need to avoid manual effort in data construction.

No description available.

Visual recognition tasks have witnessed vast improvements in performance since the advent of deep learning. Despite the gains in performance, image understanding algorithms are still not completely robust to partial occlusion. In this work, we propose a novel object classification method based on compositional modeling and explore its effect in the context of the newly introduced panoptic segmentation task. The panoptic segmentation task combines both semantic and instance segmentation to perform labelling of the entire image. The novel classification method replaces the object detection pipeline in UPSNet, a Mask R-CNN based design for panoptic segmentation. We also discuss an issue with the segmentation mask prediction of Mask R-CNN that affects overlapping instances. We perform extensive experiments and showcase results on the complex COCO and Cityscapes datasets. The novel classification method shows promising results for object classification on occluded instances in complex scenes. / Master of Science / Visual recognition tasks have witnessed vast improvements in performance since the advent of deep learning. Despite making significant improvements, algorithms for these tasks still do not perform well at recognizing partially visible objects in the scene. In this work, we propose a novel object classification method that uses compositional models to perform part based detection. The method first looks at individual parts of an object in the scene and then makes a decision about its identity. We test the proposed method in the context of the recently introduced panoptic segmentation task. The panoptic segmentation task combines both semantic and instance segmentation to perform labelling of the entire image. The novel classification method replaces the object detection module in UPSNet, a Mask R-CNN based algorithm for panoptic segmentation. We also discuss an issue with the segmentation mask prediction of Mask R-CNN that affects overlapping instances. After performing extensive experiments and evaluation, it can be seen that the novel classification method shows promising results for object classification on occluded instances in complex scenes.