RESUMEN
Medical decision making often relies on accurately forecasting future patient trajectories. Conventional approaches for patient progression modeling often do not explicitly model treatments when predicting patient trajectories and outcomes. In this paper, we propose Alternating Transformer (AL-Transformer) to jointly model treatment and clinical outcomes over time as alternating sequential models. We leverage causal convolution in the self-attention mechanism of AL-Transformer to incorporate local spatial information in the sequence, thus enhancing the model's ability to capture local contextual information of the sequence. Additionally, to predict the sparse treatment, a constraint learned by a convolutional neural network (CNN) is used to constrain the sparse treatment output. Experimental results on two datasets from patients with sepsis and respiratory failure extracted from the Medical Information Mart for Intensive Care (MIMIC) database demonstrate the effectiveness of the proposed approach, outperforming existing state-of-the-art methods.
Asunto(s)
Cuidados Críticos , Suministros de Energía Eléctrica , Humanos , Resultado del Tratamiento , Bases de Datos Factuales , AprendizajeRESUMEN
Recently, the emerging concept of "unmanned retail" has drawn more and more attention, and the unmanned retail based on the intelligent unmanned vending machines (UVMs) scene has great market demand. However, existing product recognition methods for intelligent UVMs cannot adapt to large-scale categories and have insufficient accuracy. In this article, we propose a method for large-scale categories product recognition based on intelligent UVMs. It can be divided into two parts: 1) first, we explore the similarities and differences between products through manifold learning, and then we build a hierarchical multigranularity label to constrain the learning of representation; and 2) second, we propose a hierarchical label object detection network, which mainly includes coarse-to-fine refine module (C2FRM) and multiple granularity hierarchical loss (MGHL), which are used to assist in capturing multigranularity features. The highlights of our method are mine potential similarity between large-scale category products and optimization through hierarchical multigranularity labels. Besides, we collected a large-scale product recognition dataset GOODS-85 based on the actual UVMs scenario. Experimental results and analysis demonstrate the effectiveness of the proposed product recognition methods.
RESUMEN
The high rate of false arrhythmia alarms in Intensive Care Units (ICUs) can lead to disruption of care, negatively impacting patients' health through noise disturbances, and slow staff response time due to alarm fatigue. Prior false-alarm reduction approaches are often rule-based and require hand-crafted features from physiological waveforms as inputs to machine learning classifiers. Despite considerable prior efforts to address the problem, false alarms are a continuing problem in the ICUs. In this work, we present a deep learning framework to automatically learn feature representations of physiological waveforms using convolutional neural networks (CNNs) to discriminate between true vs. false arrhythmia alarms. We use Contrastive Learning to simultaneously minimize a binary cross entropy classification loss and a proposed similarity loss from pair-wise comparisons of waveform segments over time as a discriminative constraint. Furthermore, we augment our deep models with learned embeddings from a rule-based method to leverage prior domain knowledge for each alarm type. We evaluate our method using the dataset from the 2015 PhysioNet Computing in Cardiology Challenge. Ablation analysis demonstrates that Contrastive Learning significantly improves the performance of a combined deep learning and rule-based-embedding approach. Our results indicate that the final proposed deep learning framework achieves superior performance in comparison to the winning entries of the Challenge.
Asunto(s)
Alarmas Clínicas , Arritmias Cardíacas/diagnóstico , Electrocardiografía/métodos , Reacciones Falso Positivas , Humanos , Unidades de Cuidados Intensivos , Monitoreo Fisiológico/métodosRESUMEN
The state-of-the-art multitask multiview (MTMV) learning tackles a scenario where multiple tasks are related to each other via multiple shared feature views. However, in many real-world scenarios where a sequence of the multiview task comes, the higher storage requirement and computational cost of retraining previous tasks with MTMV models have presented a formidable challenge for this lifelong learning scenario. To address this challenge, in this article, we propose a new continual multiview task learning model that integrates deep matrix factorization and sparse subspace learning in a unified framework, which is termed deep continual multiview task learning (DCMvTL). More specifically, as a new multiview task arrives, DCMvTL first adopts a deep matrix factorization technique to capture hidden and hierarchical representations for this new coming multiview task while accumulating the fresh multiview knowledge in a layerwise manner. Then, a sparse subspace learning model is employed for the extracted factors at each layer and further reveals cross-view correlations via a self-expressive constraint. For model optimization, we derive a general multiview learning formulation when a new multiview task comes and apply an alternating minimization strategy to achieve lifelong learning. Extensive experiments on benchmark data sets demonstrate the effectiveness of our proposed DCMvTL model compared with the existing state-of-the-art MTMV and lifelong multiview task learning models.
Asunto(s)
Aprendizaje Automático , Algoritmos , Clasificación/métodos , Interpretación Estadística de Datos , Humanos , Modelos Teóricos , Redes Neurales de la Computación , Análisis de Regresión , Instituciones AcadémicasRESUMEN
By using GLOPEM-CEVSA model, the spatiotemporal pattern and its affecting factors of the vegetation net primary productivity (NPP) in Northeast China in 2000-2008 were simulated, and, taking four forest ecosystem stations (Daxing' anling, Laoyeling, Liangshui and Changbai Mountains) as the cases, the seasonal changes and their main driving force of forest NPP in Northeast China were studied. In 2000-2008, the annual averaged vegetation NPP in the region was 445 g C x m(-2) x a(-1), being the highest in the areas from Changbai Mountains to Xiaoxing' anling Mountains and parts of Sanjiang Plain, followed by in the areas from Changbai Mountains to Liaohe River Plain, eastern Songnen Plain, Sanjiang Plain, and Daxing' anling Mountain, and the lowest in the sparse grass and desert areas in the west. Forest ecosystem had the highest annual averaged NPP, followed by shrub, cropland and grassland, and desert. In forest ecosystem, coniferous and broad-leaf mixed forests had the highest annual averaged NPP (722 g C x m(-2) x a(-1)), while deciduous needle-leaf forest had the lowest one (451 g C x m(-2) x a(-1)). During the study period, no significant inter-annual changes were observed in the forest NPP though it was higher in 2007 and 2008 probably due to the increased air temperature (1 degrees C-2 degrees C higher than that in other years). The beginning time of forest growth season in Northeast China advanced gradually from north to south, and the growth season became longer.