Heart auscultation is a simple and inexpensive first-line diagnostic test for the early screening of heart abnormalities. A phonocardiogram (PCG) is a digital recording of an analog heart sound acquired using an electronic stethoscope. A computerized algorithm for PCG analysis can aid in detecting abnormal signal patterns and support the clinical use of auscultation. It is important to detect fundamental components, such as the first and second heart sounds (S1 and S2), to accurately diagnose heart abnormalities. In this study, we developed a fully convolutional hybrid fusion network to identify S1 and S2 locations in PCG. It enables timewise, high-level feature fusion from dimensionally heterogeneous features: 1D envelope and 2D spectral features. For the fusion of heterogeneous features, we proposed a novel convolutional multimodal factorized bilinear pooling approach that enables high-level fusion without temporal distortion. We experimentally demonstrated the benefits of the comprehensive interpretation of heterogeneous features, with the proposed method outperforming other state-of-the-art PCG segmentation methods. To the best of our knowledge, this is the first study to interpret heterogeneous features through a high level of feature fusion in PCG analysis.

Robot technologies have been introduced to computing education to engage learners. This study introduces the concept of co-creation with a robot agent into culturally-responsive computing (CRC). Co-creation with computer agents has previously focused on creating external artifacts. Our work differs by making the robot agent itself the co-created product. Through participatory design activities, we positioned adolescent girls and an agentic social robot as co-creators of the robot’s identity. Taking a thematic analysis approach, we examined how girls embody the role of creator and co-creator in this space. We identified themes surrounding who has the power to make decisions, what decisions are made, and how to maintain social relationship. Our findings suggest that co-creation with robot technology is a promising implementation vehicle for realizing CRC.

Culturally responsive STEM and computing initiatives aim to engage and embolden a diverse range of learners, center their identity and experiences in curriculum, and connect learners to each other and their communities. With an abrupt pivot to online learning at the beginning of 2020, more educational experiences have taken place virtually. We ran a virtual synchronous culturally responsive computing camp and saw that establishing the right environment online to support a good sense of connectedness was challenging. To investigate this further, we interviewed eight K-12 instructors of culturally responsive STEM and computing programs. Three themes emerged on defining and cultivating connectedness in learning experiences, the role of equity in supporting community online, and affordances of being online specific to culturally responsive perspectives. We support our thematic findings with vignettes from the camp data. In this study, we address K-12 culturally responsive STEM and computing instructors' beliefs, experiences, and approaches regarding cultivating connectedness online. This work fills a gap in understanding instructor perspectives on building in-program and broader community connections online from a culturally responsive STEM and computing lens.

Performance analysis is essential for improving classification models. However, existing performance analysis tools do not provide actionable insights such as the cause of misclassification. Machine learning practitioners face difficulties such as prioritizing model, looking over confusion between classes. In addition, existing performance analysis tools that provide feature-level analysis are difficult to apply to image classification problems. This study has been proposed to solve these difficulties. In this paper, we present an interactive visual analytics system for diagnosing the performance of multiclass classification models. Our system is able to compare multiple models, find weaknesses, and obtain actionable insights for improving models. Our visualization consists of three views for analyzing performance at the class, confusion, and instance levels. We demonstrate our system using MNIST handwritten digits data.

Exascale computing promises quantities of data too large to efficiently store and transfer across networks in order to be able to analyze and visualize the results. We investigate compressed sensing (CS) as an in situ method to reduce the size of the data as it is being generated during a large-scale simulation. CS works by sampling the data on the computational cluster within an alternative function space such as wavelet bases and then reconstructing back to the original space on visualization platforms. While much work has gone into exploring CS on structured datasets, such as image data, we investigate its usefulness for point clouds such as unstructured mesh datasets often found in finite element simulations. We sample using a technique that exhibits low coherence with tree wavelets found to be suitable for point clouds. We reconstruct using the stagewise orthogonal matching pursuit algorithm that we improved to facilitate automated use in batch jobs. We analyze the achievable compression ratios and the quality and accuracy of reconstructed results at each compression ratio. In the considered case studies, we are able to achieve compression ratios up to two orders of magnitude with reasonable reconstruction accuracy and minimal visual deterioration in the data. Our results suggest that, compared to other compression techniques, CS is attractive in cases where the compression overhead has to be minimized and where the reconstruction cost is not a significant concern.

During face-to-face conversation, our body is continually in motion, displaying various head, gesture, and posture movements. Based on findings describing the communicative functions served by these nonverbal behaviors, many virtual agent systems have modeled them to make the virtual agent look more effective and believable. One channel of nonverbal behaviors that has received less attention is head movements, despite the important functions served by them. The goal for this work is to build a domain-independent model of speaker's head movements that could be used to generate head movements for virtual agents. In this paper, we present a machine learning approach for learning models of head movements by focusing on when speaker head nods should occur, and conduct evaluation studies that compare the nods generated by this work to our previous approach of using handcrafted rules . To learn patterns of speaker head nods, we use a gesture corpus and rely on the linguistic and affective features of the utterance. We describe the feature selection process and training process for learning hidden Markov models and compare the results of the learned models under varying conditions. The results show that we can predict speaker head nods with high precision (.84) and recall (.89) rates, even without a deep representation of the surface text and that using affective information can help improve the prediction of the head nods (precision: .89, recall: .90). The evaluation study shows that the nods generated by the machine learning approach are perceived to be more natural in terms of nod timing than the nods generated by the rule-based approach.