Deep Learning in Diabetic Foot Ulcers Detection: A Comprehensive Evaluation

There has been a substantial amount of research on computer methods and technology for the detection and recognition of diabetic foot ulcers (DFUs), but there is a lack of systematic comparisons of state-of-the-art deep learning object detection frameworks applied to this problem. With recent development and data sharing performed as part of the DFU Challenge (DFUC2020) such a comparison becomes possible: DFUC2020 provided participants with a comprehensive dataset consisting of 2,000 images for training each method and 2,000 images for testing them. The following deep learning-based algorithms are compared in this paper: Faster R-CNN, three variants of Faster R-CNN and an ensemble method; YOLOv3; YOLOv5; EfficientDet; and a new Cascade Attention Network. For each deep learning method, we provide a detailed description of model architecture, parameter settings for training and additional stages including pre-processing, data augmentation and post-processing. We provide a comprehensive evaluation for each method. All the methods required a data augmentation stage to increase the number of images available for training and a post-processing stage to remove false positives. The best performance is obtained Deformable Convolution, a variant of Faster R-CNN, with a mAP of 0.6940 and an F1-Score of 0.7434. Finally, we demonstrate that the ensemble method based on different deep learning methods can enhanced the F1-Score but not the mAP. Our results show that state-of-the-art deep learning methods can detect DFU with some accuracy, but there are many challenges ahead before they can be implemented in real world settings.

Simulating multi-exit evacuation using deep reinforcement learning

Conventional simulations on multi-exit indoor evacuation focus primarily on how to determine a reasonable exit based on numerous factors in a changing environment. Results commonly include some congested and other under-utilized exits, especially with massive pedestrians. We propose a multi-exit evacuation simulation based on Deep Reinforcement Learning (DRL), referred to as the MultiExit-DRL, which involves in a Deep Neural Network (DNN) framework to facilitate state-to-action mapping. The DNN framework applies Rainbow Deep Q-Network (DQN), a DRL algorithm that integrates several advanced DQN methods, to improve data utilization and algorithm stability, and further divides the action space into eight isometric directions for possible pedestrian choices. We compare MultiExit-DRL with two conventional multi-exit evacuation simulation models in three separate scenarios: 1) varying pedestrian distribution ratios, 2) varying exit width ratios, and 3) varying open schedules for an exit. The results show that MultiExit-DRL presents great learning efficiency while reducing the total number of evacuation frames in all designed experiments. In addition, the integration of DRL allows pedestrians to explore other potential exits and helps determine optimal directions, leading to the high efficiency of exit utilization.

A GRU-based Mixture Density Network for Data-Driven Dynamic Stochastic Programming

The conventional deep learning approaches for solving time-series problem such as long-short term memory (LSTM) and gated recurrent unit (GRU) both consider the time-series data sequence as the input with one single unit as the output (predicted time-series result). Those deep learning approaches have made tremendous success in many time-series related problems, however, this cannot be applied in data-driven stochastic programming problems since the output of either LSTM or GRU is a scalar rather than probability distribution which is required by stochastic programming model. To fill the gap, in this work, we propose an innovative data-driven dynamic stochastic programming (DD-DSP) framework for time-series decision-making problem, which involves three components: GRU, Gaussian Mixture Model (GMM) and SP. Specifically, we devise the deep neural network that integrates GRU and GMM which is called GRU-based Mixture Density Network (MDN), where GRU is used to predict the time-series outcomes based on the recent historical data, and GMM is used to extract the corresponding probability distribution of predicted outcomes, then the results will be input as the parameters for SP. To validate our approach, we apply the framework on the car-sharing relocation problem. The experiment validations show that our framework is superior to data-driven optimization based on LSTM with the vehicle average moving lower than LSTM.

Towards Deeper Graph Neural Networks with Differentiable Group Normalization

Graph neural networks (GNNs), which learn the representation of a node by aggregating its neighbors, have become an effective computational tool in downstream applications. Over-smoothing is one of the key issues which limit the performance of GNNs as the number of layers increases. It is because the stacked aggregators would make node representations converge to indistinguishable vectors. Several attempts have been made to tackle the issue by bringing linked node pairs close and unlinked pairs distinct. However, they often ignore the intrinsic community structures and would result in sub-optimal performance. The representations of nodes within the same community/class need be similar to facilitate the classification, while different classes are expected to be separated in embedding space. To bridge the gap, we introduce two over-smoothing metrics and a novel technique, i.e., differentiable group normalization (DGN). It normalizes nodes within the same group independently to increase their smoothness, and separates node distributions among different groups to significantly alleviate the over-smoothing issue. Experiments on real-world datasets demonstrate that DGN makes GNN models more robust to over-smoothing and achieves better performance with deeper GNNs.

Teaching Machine Comprehension with Compositional Explanations

Advances in extractive machine reading comprehension (MRC) rely heavily on the collection of large scale human-annotated training data (in the form of "question-paragraph-answer span"). A single question-answer example provides limited supervision, while an explanation in natural language describing human's deduction process may generalize to many other questions that share similar solution patterns. In this paper, we focus on "teaching" machines on reading comprehension with (a small number of) natural language explanations. We propose a data augmentation framework that exploits the compositional nature of explanations to rapidly create pseudo-labeled data for training downstream MRC models. Structured variables and rules are extracted from each explanation and formulated into neural module teacher, which employs softened neural modules and combinatorial search to handle linguistic variations and overcome sparse coverage. The proposed work is particularly effective when limited annotation effort is available, and achieved a practicable F1 score of 59.80% with supervision from 52 explanations on the SQuAD dataset.

TriggerNER: Learning with Entity Triggers as Explanations for Named Entity Recognition

Training neural models for named entity recognition (NER) in a new domain often requires additional human annotations (e.g., tens of thousands of labeled instances) that are usually expensive and time-consuming to collect. Thus, a crucial research question is how to obtain supervision in a cost-effective way. In this paper, we introduce "entity triggers," an effective proxy of human explanations for facilitating label-efficient learning of NER models. An entity trigger is defined as a group of words in a sentence that helps to explain why humans would recognize an entity in the sentence. We crowd-sourced 14k entity triggers for two well-studied NER datasets. Our proposed model, Trigger Matching Network, jointly learns trigger representations and soft matching module with self-attention such that can generalize to unseen sentences easily for tagging. Our framework is significantly more cost-effective than the traditional neural NER frameworks. Experiments show that using only 20% of the trigger-annotated sentences results in a comparable performance as using 70% of conventional annotated sentences.

DDKSP: A Data-Driven Stochastic Programming Framework for Car-Sharing Relocation Problem

Car-sharing issue is a popular research field in sharing economy. In this paper, we investigate the car-sharing relocation problem (CSRP) under uncertain demands. Normally, the real customer demands follow complicating probability distribution which cannot be described by parametric approaches. In order to overcome the problem, an innovative framework called Data-Driven Kernel Stochastic Programming (DDKSP) that integrates a non-parametric approach - kernel density estimation (KDE) and a two-stage stochastic programming (SP) model is proposed. Specifically, the probability distributions are derived from historical data by KDE, which are used as the input uncertain parameters for SP. Additionally, the CSRP is formulated as a two-stage SP model. Meanwhile, a Monte Carlo method called sample average approximation (SAA) and Benders decomposition algorithm are introduced to solve the large-scale optimization model. Finally, the numerical experimental validations which are based on New York taxi trip data sets show that the proposed framework outperforms the pure parametric approaches including Gaussian, Laplace and Poisson distributions with 3.72% , 4.58% and 11% respectively in terms of overall profits.

Translating multispectral imagery to nighttime imagery via conditional generative adversarial networks

Nighttime satellite imagery has been applied in a wide range of fields. However, our limited understanding of how observed light intensity is formed and whether it can be simulated greatly hinders its further application. This study explores the potential of conditional Generative Adversarial Networks (cGAN) in translating multispectral imagery to nighttime imagery. A popular cGAN framework, pix2pix, was adopted and modified to facilitate this translation using gridded training image pairs derived from Landsat 8 and Visible Infrared Imaging Radiometer Suite (VIIRS). The results of this study prove the possibility of multispectral-to-nighttime translation and further indicate that, with the additional social media data, the generated nighttime imagery can be very similar to the ground-truth imagery. This study fills the gap in understanding the composition of satellite observed nighttime light and provides new paradigms to solve the emerging problems in nighttime remote sensing fields, including nighttime series construction, light desaturation, and multi-sensor calibration.