The literature review reports on programs and interventions that address postpartum depression (PPD) in African American women. African American women are at a higher risk of developing PPD compared to white women. The review will highlight and recommend approaches that may render positive outcomes in the future for this population. A systematic scoping literature review was conducted using Academic Search Complete, CINAHL, APA PsycArticles, APA PsychInfo, PubMed, Social Services Abstracts, and Social Work Abstracts. Keywords used in the search included "postpartum depression," "African American," and "interventions OR programs OR therapy OR treatment." Fourteen studies were selected, analyzed, and included in the review. Group psychosocial, individual psychosocial, internet-based, and integrated care interventions were included. While many articles noted within group changes in depression symptoms, fewer studies documented between group differences. Studies that investigated subsamples of "high risk" participants or those that used "culturally tailored" approaches showed promise. The literature review yielded some examples of programs/interventions that target postpartum depression in African American women; however, results were mixed. More research is needed to confirm the most effective interventions to address postpartum depression in African American women.

Deepwater basins around the world contain shallow sequences of overpressured, sand-prone sediments that can result in shallow water flow (SWF) events. These events have frequently resulted in wellbore instability and increased man-hour exposure to potential health, safety, security, and environment risks, as well as nonproductive time, and they have sometimes been the cause of the loss of a well while drilling the shallow (riserless) section for oil and gas exploration or development projects. Methods previously established to classify the magnitude of an SWF event have been used with partial success to identify the onset of an SWF event. The need existed to develop a system enabling early prediction, detection, and mitigation of SWF events while drilling. Real-time monitoring of the riserless section of a marine well for SWF requires a system using a plurality of data feeds that we defined as the SYSTEM. The data feeds include seismic data, remotely operated vehicle video, and surface and downhole logging measurements. An SWF surveillance methodology, which we defined as a discharge category model (DCM), has been developed for early detection of an SWF event, prior to the onset of wellbore instability. DCM focuses on baseline discharge categories (ranging from no flow to minor flow) prior to wellbore instability and taking into account the U-tube effects. Real-time monitoring of data feeds coupled with DCM in the context of SYSTEM has helped to mitigate SWF events. There have been no wells lost due to SWF events that have used DCM in the context of SYSTEM in various basins throughout the world. In total, 154 wells have been monitored globally using DCM with 46 SWF events detected and mitigated before reaching a severity level that might compromise well integrity from 2012 to 2019.

Real physical plants for control experimentation are valuable tools in a control laboratory. This paper describes a prototype pneumatic active suspension system, which was designed and built over a number of years as a sequence of student projects. The physical plant, which models a quarter-car suspension, consists of a wheel, coil springs, a pneumatic actuator for active damping, position, and velocity sensors, and an alternating current (AC) motor for simulating road disturbance input signal. An electronic subsystem is used to process the sensor signals which are sent to a Motorola 68HC16 microcontroller-based evaluation board. The microcontroller controls a four-bit automatic binary regulator that controls airflow to the pneumatic actuator for damping. A mathematical model of the suspension system was derived analytically and validated experimentally. MATLAB and Simulink (MathWorks, Inc., Natick, MA 01760 USA) were used to analyze and design a digital state feedback plus integral controller for the system. The digital controller was implemented on a Motorola 68HC16 microcontroller. The controller was able to reject a physically generated 0.01143-m negative step road disturbance input. The details of the design construction, modeling, analysis, computer simulation, controller implementation, and experimental results are presented.

Despite their unprecedented performance in various domains, utilization of Deep Neural Networks (DNNs) in safety-critical environments is severely limited in the presence of even small adversarial perturbations. The present work develops a randomized approach to detecting such perturbations based on minimum uncertainty metrics that rely on sampling at the hidden layers during the DNN inference stage. Inspired by Bayesian approaches to uncertainty estimation, the sampling probabilities are designed for effective detection of the adversarially corrupted inputs. Being modular, the novel detector of adversaries can be conveniently employed by any pre-trained DNN at no extra training overhead. Selecting which units to sample per hidden layer entails quantifying the amount of DNN output uncertainty, where the overall uncertainty is expressed in terms of its layer-wise components - what also promotes scalability. Sampling probabilities are then sought by minimizing uncertainty measures layer-by-layer, leading to a novel convex optimization problem that admits an exact solver with superlinear convergence rate. By simplifying the objective function, low-complexity approximate solvers are also developed. In addition to valuable insights, these approximations link the novel approach with state-of-the-art randomized adversarial detectors. The effectiveness of the novel detectors in the context of competing alternatives is highlighted through extensive tests for various types of adversarial attacks with variable levels of strength.

This chapter introduces some recent trends in generative and deep-learning (DL) models for hybrid recommendation systems that have proven to be extremely effective in integrating different modalities of data. It is organized into three main sections. The first section considers classic algorithms such as probabilistic matrix factorization and latent Dirichlet allocation and illustrates the generative principle of a hybrid recommendation model called collaborative topic regression that jointly models the latent interests of users and items. The second section presents recommendation models that are exclusively based on DL techniques. This includes models such as Restricted Boltzmann-machine-based CF, autoencoder (AE)-based recommendation, neural CF and recurrent recommender network. Finally, the third section explains models such as collaborative denoising AE and collaborative variational AE that integrates PGMs with DL to create a generative DL framework.

DNA is an emerging medium for digital data and its adoption can be accelerated by synthesis processes specialized for storage applications. Here, we describe a de novo enzymatic synthesis strategy designed for data storage which harnesses the template-independent polymerase terminal deoxynucleotidyl transferase (TdT) in kinetically controlled conditions. Information is stored in transitions between non-identical nucleotides of DNA strands. To produce strands representing user-defined content, nucleotide substrates are added iteratively, yielding short homopolymeric extensions whose lengths are controlled by apyrase-mediated substrate degradation. With this scheme, we synthesize DNA strands carrying 144 bits, including addressing, and demonstrate retrieval with streaming nanopore sequencing. We further devise a digital codec to reduce requirements for synthesis accuracy and sequencing coverage, and experimentally show robust data retrieval from imperfectly synthesized strands. This work provides distributive enzymatic synthesis and information-theoretic approaches to advance digital information storage in DNA.

Despite their well-documented learning capabilities in clean environments, deep convolutional neural networks (CNNs) are extremely fragile in adversarial settings, where carefully crafted perturbations created by an attacker can easily disrupt the task at hand. Numerous methods have been proposed for designing effective attacks, while the design of effective defense schemes is still an open area. This work leverages randomization-based defense schemes to introduce a sampling mechanism for strong and efficient defense. To this end, sampling is proposed to take place over the matricized mid-layer data in the neural network, and the sampling probabilities are systematically obtained via variance minimization. The proposed defense only requires adding sampling blocks to the network in the inference phase without extra overhead in the training. In addition, it can be utilized on any pre-trained network without altering the weights. Numerical tests corroborate the improved defense against various attack schemes in comparison with state-of-the-art randomized defenses.

In this paper, we present a fully automatic pipeline for generating and stylizing high geometric and textural quality facial rigs. They are automatically rigged with facial blendshapes for animation, and can be used across platforms for applications including virtual reality, augmented reality, remote collaboration, gaming and more. From a set of input facial photos, our approach is to be able to create a photorealistic, fully rigged character in less than seven minutes. The facial mesh reconstruction is based on state-of-the art photogrammetry approaches. Automatic landmarking coupled with ICP registration with regularization provide direct correspondence and registration from a given generic mesh to the acquired facial mesh. Then, using deformation transfer, existing blendshapes are transferred from the generic to the reconstructed facial mesh. The reconstructed face is then fit to the full body generic mesh. Extra geometry such as jaws, teeth and nostrils are retargeted and transferred to the character. An automatic iris color extraction algorithm is performed to colorize a separate eye texture, animated with dynamic UVs. Finally, an extra step applies a style to the photorealis-tic face to enable blending of personalized facial features into any other character. The user's face can then be adapted to any human or non-human generic mesh. A pilot user study was performed to evaluate the utility of our approach. Up to 65% of the participants were successfully able to discern the presence of one's unique facial features when the style was not too far from a humanoid shape.

Recommendation in the modern world is not only about capturing the interaction between users and items, but also about understanding the relationship between items. Besides improving the quality of recommendation, it enables the generation of candidate items that can serve as substitutes and supplements of another item. For example, when recommending Xbox, PS4 could be a logical substitute and the supplements could be items such as game controllers, surround system, and travel case. Therefore, given a network of items, our objective is to learn their content features such that they explain the relationship between items in terms of substitutes and supplements. To achieve this, we propose a generative deep learning model that links two variational autoencoders using a connector neural network to create Linked Variational Autoencoder (LVA). LVA learns the latent features of items by conditioning on the observed relationship between items. Using a rigorous series of experiments, we show that LVA significantly outperforms other representative and state-of-the-art baseline methods in terms of prediction accuracy. We then extend LVA by incorporating collaborative filtering (CF) to create CLVA that captures the implicit relationship between users and items. By comparing CLVA with LVA we show that inducing CF-based features greatly improve the recommendation quality of substitutable and supplementary items on a user level.

A common problem in large-scale data analysis is to approximate a matrix using a combination of specifically sampled rows and columns, known as CUR decomposition. In many real-world environments, the ability to sample specific individual rows or columns of the matrix is limited by either system constraints or cost. In this paper, we consider matrix approximation by sampling predefined blocks of columns (or rows) from the matrix. We present an algorithm for sampling useful column blocks and provide novel guarantees for the quality of the approximation. We demonstrate the effectiveness of the proposed algorithms for computing the Block CUR decomposition of large matrices in a distributed setting with multiple nodes in a compute cluster and in a biometric data analysis setting using real-world user data from content testing.