arXiv subjects

Ming Liu

Publications and source records attributed to Ming Liu.

At least 397 records · Page 22Linked to original sources

arXiv2020

Wound and episode level readmission risk or weeks to readmit: Why do patients get readmitted? How long does it take for a patient to get readmitted?

The Affordable care Act of 2010 had introduced Readmission reduction program in 2012 to reduce avoidable re-admissions to control rising healthcare costs. Wound care impacts 15 of medicare beneficiaries making it one of the major contributors of medicare health care cost. Health plans have been exploring proactive health care services that can focus on preventing wound recurrences and re-admissions to control the wound care costs. With rising costs of Wound care industry, it has become of paramount importance to reduce wound recurrences & patient re-admissions. What factors are responsible for a Wound to recur which ultimately lead to hospitalization or re-admission? Is there a way to identify the patients at risk of re-admission before the occurrence using data driven analysis? Patient re-admission risk management has become critical for patients suffering from chronic wounds such as diabetic ulcers, pressure ulcers, and vascular ulcers. Understanding the risk & the factors that cause patient readmission can help care providers and patients avoid wound recurrences. Our work focuses on identifying patients who are at high risk of re-admission & determining the time period with in which a patient might get re-admitted. Frequent re-admissions add financial stress to the patient & Health plan and deteriorate the quality of life of the patient. Having this information can allow a provider to set up preventive measures that can delay, if not prevent, patients' re-admission. On a combined wound & episode-level data set of patient's wound care information, our extended autoprognosis achieves a recall of 92 and a precision of 92 for the predicting a patient's re-admission risk. For new patient class, precision and recall are as high as 91 and 98, respectively. We are also able to predict the patient's discharge event for a re-admission event to occur through our model with a MAE of 2.3 weeks.

cs.LG↗

arXiv2020

GMMLoc: Structure Consistent Visual Localization with Gaussian Mixture Models

Incorporating prior structure information into the visual state estimation could generally improve the localization performance. In this letter, we aim to address the paradox between accuracy and efficiency in coupling visual factors with structure constraints. To this end, we present a cross-modality method that tracks a camera in a prior map modelled by the Gaussian Mixture Model (GMM). With the pose estimated by the front-end initially, the local visual observations and map components are associated efficiently, and the visual structure from the triangulation is refined simultaneously. By introducing the hybrid structure factors into the joint optimization, the camera poses are bundle-adjusted with the local visual structure. By evaluating our complete system, namely GMMLoc, on the public dataset, we show how our system can provide a centimeter-level localization accuracy with only trivial computational overhead. In addition, the comparative studies with the state-of-the-art vision-dominant state estimators demonstrate the competitive performance of our method.

cs.RO↗

arXiv2020

Smart-Inspect: Micro Scale Localization and Classification of Smartphone Glass Defects for Industrial Automation

The presence of any type of defect on the glass screen of smart devices has a great impact on their quality. We present a robust semi-supervised learning framework for intelligent micro-scaled localization and classification of defects on a 16K pixel image of smartphone glass. Our model features the efficient recognition and labeling of three types of defects: scratches, light leakage due to cracks, and pits. Our method also differentiates between the defects and light reflections due to dust particles and sensor regions, which are classified as non-defect areas. We use a partially labeled dataset to achieve high robustness and excellent classification of defect and non-defect areas as compared to principal components analysis (PCA), multi-resolution and information-fusion-based algorithms. In addition, we incorporated two classifiers at different stages of our inspection framework for labeling and refining the unlabeled defects. We successfully enhanced the inspection depth-limit up to 5 microns. The experimental results show that our method outperforms manual inspection in testing the quality of glass screen samples by identifying defects on samples that have been marked as good by human inspection.

cs.CV↗

arXiv2020

Loop-box: Multi-Agent Direct SLAM Triggered by Single Loop Closure for Large-Scale Mapping

In this paper, we present a multi-agent framework for real-time large-scale 3D reconstruction applications. In SLAM, researchers usually build and update a 3D map after applying non-linear pose graph optimization techniques. Moreover, many multi-agent systems are prevalently using odometry information from additional sensors. These methods generally involve intensive computer vision algorithms and are tightly coupled with various sensors. We develop a generic method for the keychallenging scenarios in multi-agent 3D mapping based on different camera systems. The proposed framework performs actively in terms of localizing each agent after the first loop closure between them. It is shown that the proposed system only uses monocular cameras to yield real-time multi-agent large-scale localization and 3D global mapping. Based on the initial matching, our system can calculate the optimal scale difference between multiple 3D maps and then estimate an accurate relative pose transformation for large-scale global mapping.

cs.RO↗

arXiv2020

MLOD: Awareness of Extrinsic Perturbation in Multi-LiDAR 3D Object Detection for Autonomous Driving

Extrinsic perturbation always exists in multiple sensors. In this paper, we focus on the extrinsic uncertainty in multi-LiDAR systems for 3D object detection. We first analyze the influence of extrinsic perturbation on geometric tasks with two basic examples. To minimize the detrimental effect of extrinsic perturbation, we propagate an uncertainty prior on each point of input point clouds, and use this information to boost an approach for 3D geometric tasks. Then we extend our findings to propose a multi-LiDAR 3D object detector called MLOD. MLOD is a two-stage network where the multi-LiDAR information is fused through various schemes in stage one, and the extrinsic perturbation is handled in stage two. We conduct extensive experiments on a real-world dataset, and demonstrate both the accuracy and robustness improvement of MLOD. The code, data and supplementary materials are available at: https://ram-lab.com/file/site/mlod

cs.CV↗

arXiv2020

Learning Flow-based Feature Warping for Face Frontalization with Illumination Inconsistent Supervision

Despite recent advances in deep learning-based face frontalization methods, photo-realistic and illumination preserving frontal face synthesis is still challenging due to large pose and illumination discrepancy during training. We propose a novel Flow-based Feature Warping Model (FFWM) which can learn to synthesize photo-realistic and illumination preserving frontal images with illumination inconsistent supervision. Specifically, an Illumination Preserving Module (IPM) is proposed to learn illumination preserving image synthesis from illumination inconsistent image pairs. IPM includes two pathways which collaborate to ensure the synthesized frontal images are illumination preserving and with fine details. Moreover, a Warp Attention Module (WAM) is introduced to reduce the pose discrepancy in the feature level, and hence to synthesize frontal images more effectively and preserve more details of profile images. The attention mechanism in WAM helps reduce the artifacts caused by the displacements between the profile and the frontal images. Quantitative and qualitative experimental results show that our FFWM can synthesize photo-realistic and illumination preserving frontal images and performs favorably against the state-of-the-art results.

cs.CV↗

arXiv2020

Unpaired Learning of Deep Image Denoising

We investigate the task of learning blind image denoising networks from an unpaired set of clean and noisy images. Such problem setting generally is practical and valuable considering that it is feasible to collect unpaired noisy and clean images in most real-world applications. And we further assume that the noise can be signal dependent but is spatially uncorrelated. In order to facilitate unpaired learning of denoising network, this paper presents a two-stage scheme by incorporating self-supervised learning and knowledge distillation. For self-supervised learning, we suggest a dilated blind-spot network (D-BSN) to learn denoising solely from real noisy images. Due to the spatial independence of noise, we adopt a network by stacking 1x1 convolution layers to estimate the noise level map for each image. Both the D-BSN and image-specific noise model (CNN\_est) can be jointly trained via maximizing the constrained log-likelihood. Given the output of D-BSN and estimated noise level map, improved denoising performance can be further obtained based on the Bayes' rule. As for knowledge distillation, we first apply the learned noise models to clean images to synthesize a paired set of training images, and use the real noisy images and the corresponding denoising results in the first stage to form another paired set. Then, the ultimate denoising model can be distilled by training an existing denoising network using these two paired sets. Experiments show that our unpaired learning method performs favorably on both synthetic noisy images and real-world noisy photographs in terms of quantitative and qualitative evaluation.

eess.IV↗

arXiv2020

SNE-RoadSeg: Incorporating Surface Normal Information into Semantic Segmentation for Accurate Freespace Detection

Freespace detection is an essential component of visual perception for self-driving cars. The recent efforts made in data-fusion convolutional neural networks (CNNs) have significantly improved semantic driving scene segmentation. Freespace can be hypothesized as a ground plane, on which the points have similar surface normals. Hence, in this paper, we first introduce a novel module, named surface normal estimator (SNE), which can infer surface normal information from dense depth/disparity images with high accuracy and efficiency. Furthermore, we propose a data-fusion CNN architecture, referred to as RoadSeg, which can extract and fuse features from both RGB images and the inferred surface normal information for accurate freespace detection. For research purposes, we publish a large-scale synthetic freespace detection dataset, named Ready-to-Drive (R2D) road dataset, collected under different illumination and weather conditions. The experimental results demonstrate that our proposed SNE module can benefit all the state-of-the-art CNNs for freespace detection, and our SNE-RoadSeg achieves the best overall performance among different datasets.

cs.CV↗

arXiv2020

Applying Surface Normal Information in Drivable Area and Road Anomaly Detection for Ground Mobile Robots

The joint detection of drivable areas and road anomalies is a crucial task for ground mobile robots. In recent years, many impressive semantic segmentation networks, which can be used for pixel-level drivable area and road anomaly detection, have been developed. However, the detection accuracy still needs improvement. Therefore, we develop a novel module named the Normal Inference Module (NIM), which can generate surface normal information from dense depth images with high accuracy and efficiency. Our NIM can be deployed in existing convolutional neural networks (CNNs) to refine the segmentation performance. To evaluate the effectiveness and robustness of our NIM, we embed it in twelve state-of-the-art CNNs. The experimental results illustrate that our NIM can greatly improve the performance of the CNNs for drivable area and road anomaly detection. Furthermore, our proposed NIM-RTFNet ranks 8th on the KITTI road benchmark and exhibits a real-time inference speed.

cs.CV↗

arXiv2020

ATG-PVD: Ticketing Parking Violations on A Drone

In this paper, we introduce a novel suspect-and-investigate framework, which can be easily embedded in a drone for automated parking violation detection (PVD). Our proposed framework consists of: 1) SwiftFlow, an efficient and accurate convolutional neural network (CNN) for unsupervised optical flow estimation; 2) Flow-RCNN, a flow-guided CNN for car detection and classification; and 3) an illegally parked car (IPC) candidate investigation module developed based on visual SLAM. The proposed framework was successfully embedded in a drone from ATG Robotics. The experimental results demonstrate that, firstly, our proposed SwiftFlow outperforms all other state-of-the-art unsupervised optical flow estimation approaches in terms of both speed and accuracy; secondly, IPC candidates can be effectively and efficiently detected by our proposed Flow-RCNN, with a better performance than our baseline network, Faster-RCNN; finally, the actual IPCs can be successfully verified by our investigation module after drone re-localization.

cs.CV↗

arXiv2020

Deep Learning Detection of Inaccurate Smart Electricity Meters: A Case Study

Detecting inaccurate smart meters and targeting them for replacement can save significant resources. For this purpose, a novel deep-learning method was developed based on long short-term memory (LSTM) and a modified convolutional neural network (CNN) to predict electricity usage trajectories based on historical data. From the significant difference between the predicted trajectory and the observed one, the meters that cannot measure electricity accurately are located. In a case study, a proof of principle was demonstrated in detecting inaccurate meters with high accuracy for practical usage to prevent unnecessary replacement and increase the service life span of smart meters.

eess.SP↗

arXiv2020

COVID-19 Docking Server: A meta server for docking small molecules, peptides and antibodies against potential targets of COVID-19

Motivation: The coronavirus disease 2019 (COVID-19) caused by a new type of coronavirus has been emerging from China and led to thousands of death globally since December 2019. Despite many groups have engaged in studying the newly emerged virus and searching for the treatment of COVID-19, the understanding of the COVID-19 target-ligand interactions represents a key chal-lenge. Herein, we introduce COVID-19 Docking Server, a web server that predicts the binding modes between COVID-19 targets and the ligands including small molecules, peptides and anti-bodies. Results: Structures of proteins involved in the virus life cycle were collected or constructed based on the homologs of coronavirus, and prepared ready for docking. The meta platform provides a free and interactive tool for the prediction of COVID-19 target-ligand interactions and following drug discovery for COVID-19.

q-bio.BM↗

arXiv2020

SummPip: Unsupervised Multi-Document Summarization with Sentence Graph Compression

Obtaining training data for multi-document summarization (MDS) is time consuming and resource-intensive, so recent neural models can only be trained for limited domains. In this paper, we propose SummPip: an unsupervised method for multi-document summarization, in which we convert the original documents to a sentence graph, taking both linguistic and deep representation into account, then apply spectral clustering to obtain multiple clusters of sentences, and finally compress each cluster to generate the final summary. Experiments on Multi-News and DUC-2004 datasets show that our method is competitive to previous unsupervised methods and is even comparable to the neural supervised approaches. In addition, human evaluation shows our system produces consistent and complete summaries compared to human written ones.

cs.CL↗

arXiv2020

Self-Supervised Drivable Area and Road Anomaly Segmentation using RGB-D Data for Robotic Wheelchairs

The segmentation of drivable areas and road anomalies are critical capabilities to achieve autonomous navigation for robotic wheelchairs. The recent progress of semantic segmentation using deep learning techniques has presented effective results. However, the acquisition of large-scale datasets with hand-labeled ground truth is time-consuming and labor-intensive, making the deep learning-based methods often hard to implement in practice. We contribute to the solution of this problem for the task of drivable area and road anomaly segmentation by proposing a self-supervised learning approach. We develop a pipeline that can automatically generate segmentation labels for drivable areas and road anomalies. Then, we train RGB-D data-based semantic segmentation neural networks and get predicted labels. Experimental results show that our proposed automatic labeling pipeline achieves an impressive speed-up compared to manual labeling. In addition, our proposed self-supervised approach exhibits more robust and accurate results than the state-of-the-art traditional algorithms as well as the state-of-the-art self-supervised algorithms.

cs.CV↗

arXiv2020

Isomorphism between the R-matrix and Drinfeld presentations of quantum affine algebra: type C

An explicit isomorphism between the $R$-matrix and Drinfeld presentations of the quantum affine algebra in type $A$ was given by Ding and I. Frenkel (1993). We show that this result can be extended to types $B$, $C$ and $D$ and give a detailed construction for type $C$ in this paper. In all classical types the Gauss decomposition of the generator matrix in the $R$-matrix presentation yields the Drinfeld generators. To prove that the resulting map is an isomorphism we follow the work of E. Frenkel and Mukhin (2002) in type $A$ and employ the universal $R$-matrix to construct the inverse map. A key role in our construction is played by a homomorphism theorem which relates the quantum affine algebra of rank $n-1$ in the $R$-matrix presentation with a subalgebra of the corresponding algebra of rank $n$ of the same type.

math.QA↗

arXiv2020

MoBoAligner: a Neural Alignment Model for Non-autoregressive TTS with Monotonic Boundary Search

To speed up the inference of neural speech synthesis, non-autoregressive models receive increasing attention recently. In non-autoregressive models, additional durations of text tokens are required to make a hard alignment between the encoder and the decoder. The duration-based alignment plays a crucial role since it controls the correspondence between text tokens and spectrum frames and determines the rhythm and speed of synthesized audio. To get better duration-based alignment and improve the quality of non-autoregressive speech synthesis, in this paper, we propose a novel neural alignment model named MoboAligner. Given the pairs of the text and mel spectrum, MoboAligner tries to identify the boundaries of text tokens in the given mel spectrum frames based on the token-frame similarity in the neural semantic space with an end-to-end framework. With these boundaries, durations can be extracted and used in the training of non-autoregressive TTS models. Compared with the duration extracted by TransformerTTS, MoboAligner brings improvement for the non-autoregressive TTS model on MOS (3.74 comparing to FastSpeech's 3.44). Besides, MoboAligner is task-specified and lightweight, which reduces the parameter number by 45% and the training time consuming by 30%.

eess.AS↗

arXiv2020

Isomorphism between the $R$-Matrix and Drinfeld Presentations of Quantum Affine Algebra: Types $B$ and $D$

Following the approach of Ding and Frenkel [Comm. Math. Phys. 156 (1993), 277-300] for type $A$, we showed in our previous work [J. Math. Phys. 61 (2020), 031701, 41 pages] that the Gauss decomposition of the generator matrix in the $R$-matrix presentation of the quantum affine algebra yields the Drinfeld generators in all classical types. Complete details for type $C$ were given therein, while the present paper deals with types $B$ and $D$. The arguments for all classical types are quite similar so we mostly concentrate on necessary additional details specific to the underlying orthogonal Lie algebras.

math.QA↗

arXiv2020

Isomorphism between the $R$-matrix and Drinfeld presentations of Yangian in types $B$, $C$ and $D$

It is well-known that the Gauss decomposition of the generator matrix in the $R$-matrix presentation of the Yangian in type $A$ yields generators of its Drinfeld presentation. Defining relations between these generators are known in an explicit form thus providing an isomorphism between the presentations. It has been an open problem since the pioneering work of Drinfeld to extend this result to the remaining types. We give a solution for the classical types $B$, $C$ and $D$ by constructing an explicit isomorphism between the $R$-matrix and Drinfeld presentations of the Yangian. It is based on an embedding theorem which allows us to consider the Yangian of rank $n-1$ as a subalgebra of the Yangian of rank $n$ of the same type.

math.QA↗