Search for: All records

The COVID-19 pandemic has intensified the need for home-based cardiac health monitoring systems. Despite advancements in electrocardiograph (ECG) and phonocardiogram (PCG) wearable sensors, accurate heart sound segmentation algorithms remain understudied. Existing deep learning models, such as convolutional neural networks (CNN) and recurrent neural networks (RNN), struggle to segment noisy signals using only PCG data. We propose a two-step heart sound segmentation algorithm that analyzes synchronized ECG and PCG signals. The first step involves heartbeat detection using a CNN-LSTM-based model on ECG data, and the second step focuses on beat-wise heart sound segmentation with a 1D U-Net that incorporates multi-modal inputs. Our method leverages temporal correlation between ECG and PCG signals to enhance segmentation performance. To tackle the label-hungry issue in AI-supported biomedical studies, we introduce a segment-wise contrastive learning technique for signal segmentation, overcoming the limitations of traditional contrastive learning methods designed for classification tasks. We evaluated our two-step algorithm using the PhysioNet 2016 dataset and a private dataset from Bayland Scientific, obtaining a 96.43 F1 score on the former. Notably, our segment-wise contrastive learning technique demonstrated effective performance with limited labeled data. When trained on just 1% of labeled PhysioNet data, the model pre-trained on the full unlabeled dataset only dropped 2.88 in the F1 score, outperforming the SimCLR method. Overall, our proposed algorithm and learning technique present promise for improving heart sound segmentation and reducing the need for labeled data. 

Research has shown that trigger-action programming (TAP) is an intuitive way to automate smart home IoT devices, but can also lead to undesirable behaviors. For instance, if two TAP rules have the same trigger condition, but one locks a door while the other unlocks it, the user may believe the door is locked when it is not. Researchers have developed tools to identify buggy or undesirable TAP programs, but little work investigates the usability of the different user-interaction approaches implemented by the various tools. This paper describes an exploratory study of the usability and utility of techniques proposed by TAP security analysis tools. We surveyed 447 Prolific users to evaluate their ability to write declarative policies, identify undesirable patterns in TAP rules (anti-patterns), and correct TAP program errors, as well as to understand whether proposed tools align with users’ needs. We find considerable variation in participants’ success rates writing policies and identifying anti-patterns. For some scenarios over 90% of participants wrote an appropriate policy, while for others nobody was successful. We also find that participants did not necessarily perceive the TAP anti-patterns flagged by tools as undesirable. Our work provides insight into real smart-home users’ goals, highlights the importance of more rigorous evaluation of users’ needs and usability issues when designing TAP security tools, and provides guidance to future tool development and TAP research. 

Retinal organoids are three-dimensional (3D) structures derived from human pluripotent stem cells (hPSCs) that mimic the retina’s spatial and temporal differentiation, making them useful as in vitro retinal development models. Retinal organoids can be assembled with brain organoids, the 3D self-assembled aggregates derived from hPSCs containing different cell types and cytoarchitectures that resemble the human embryonic brain. Recent studies have shown the development of optic cups in brain organoids. The cellular components of a developing optic vesicle-containing organoids include primitive corneal epithelial and lens-like cells, retinal pigment epithelia, retinal progenitor cells, axon-like projections, and electrically active neuronal networks. The importance of retinal organoids in ocular diseases such as age-related macular degeneration, Stargardt disease, retinitis pigmentosa, and diabetic retinopathy are described in this review. This review highlights current developments in retinal organoid techniques, and their applications in ocular conditions such as disease modeling, gene therapy, drug screening and development. In addition, recent advancements in utilizing extracellular vesicles secreted by retinal organoids for ocular disease treatments are summarized. 

Auxetic materials are the materials that can display negative Poisson's ratio that describes the degree to which a material contracts (or expands) transversally when axially strained. Human stem cells sense the mechanical properties of the microenvironment, including material surface properties, stiffness, and Poisson's ratio. In this study, six different auxetic polyurethane (PU) foams with different elastic modulus (0.7–1.8 kPa) and Poisson's ratio (−0.1 to −0.5) are used to investigate lineage specification of human induced pluripotent stem cells (hiPSCs). The surfaces of the foams are modified with chitosan or heparin to enhance the adhesion and proliferation of hiPSCs. Then, the vascular and neural differentiation of hiPSCs are investigated on different foams with distinct elastic modulus and Poisson's ratio. With different auxetic foams, cells show differential adherent density and differentiation capacity. Chitosan and heparin surface functionalization promote the hindbrain and hippocampal markers, but not forebrain markers during neural patterning of hiPSCs. Properly surface engineered auxetic scaffolds can also promote vascular differentiation of hiPSCs. This study represents a versatile and multifunctional scaffold fabrication approach and can lead to a suitable system for establishing hiPSC culture models in applications of neurovascular disease modeling and drug screening.