Searcharxiv⌕ Search

arXiv subjects

Ming Dong

Publications and source records attributed to Ming Dong.

53 records · Page 3Linked to original sources
arXiv2021

SA-GAN: Structure-Aware GAN for Organ-Preserving Synthetic CT Generation

In medical image synthesis, model training could be challenging due to the inconsistencies between images of different modalities even with the same patient, typically caused by internal status/tissue changes as different modalities are usually obtained at a different time. This paper proposes a novel deep learning method, Structure-aware Generative Adversarial Network (SA-GAN), that preserves the shapes and locations of in-consistent structures when generating medical images. SA-GAN is employed to generate synthetic computed tomography (synCT) images from magnetic resonance imaging (MRI) with two parallel streams: the global stream translates the input from the MRI to the CT domain while the local stream automatically segments the inconsistent organs, maintains their locations and shapes in MRI, and translates the organ intensities to CT. Through extensive experiments on a pelvic dataset, we demonstrate that SA-GAN provides clinically acceptable accuracy on both synCTs and organ segmentation and supports MR-only treatment planning in disease sites with internal organ status changes.

eess.IV↗
arXiv2021

Generation of In-group Asset Condition Data for Power System Reliability Assessment

In a power system, unlike some critical and standalone assets that are equipped with condition monitoring devices, the conditions of most regular in-group assets are acquired through periodic inspection work. Due to their large quantities, significant amount of manual inspection effort and sometimes data management issues, it is not uncommon to see the asset condition data in a target study area is unavailable or incomplete. Lack of asset condition data undermines the reliability assessment work. To solve this data problem and enhance data availability, this paper explores an unconventional method-generating numerical and non-numerical asset condition data based on condition degradation, condition correlation and categorical distribution models. Empirical knowledge from human experts can also be incorporated in the modeling process. Also, a probabilistic diversification step can be taken to make the generated numerical condition data probabilistic. This method can generate close-to-real asset condition data and has been validated systematically based on two public datasets. An area reliability assessment example based on cables is given to demonstrate the usefulness of this method and its generated data. This method can also be used to conveniently generate hypothetical asset condition data for research purposes.

cs.CE↗
arXiv2021

Attention-Guided Generative Adversarial Network to Address Atypical Anatomy in Modality Transfer

Recently, interest in MR-only treatment planning using synthetic CTs (synCTs) has grown rapidly in radiation therapy. However, developing class solutions for medical images that contain atypical anatomy remains a major limitation. In this paper, we propose a novel spatial attention-guided generative adversarial network (attention-GAN) model to generate accurate synCTs using T1-weighted MRI images as the input to address atypical anatomy. Experimental results on fifteen brain cancer patients show that attention-GAN outperformed existing synCT models and achieved an average MAE of 85.22$\pm$12.08, 232.41$\pm$60.86, 246.38$\pm$42.67 Hounsfield units between synCT and CT-SIM across the entire head, bone and air regions, respectively. Qualitative analysis shows that attention-GAN has the ability to use spatially focused areas to better handle outliers, areas with complex anatomy or post-surgical regions, and thus offer strong potential for supporting near real-time MR-only treatment planning.

eess.IV↗
arXiv2021

Objective Class-based Micro-Expression Recognition through Simultaneous Action Unit Detection and Feature Aggregation

Micro-Expression Recognition (MER) is a challenging task as the subtle changes occur over different action regions of a face. Changes in facial action regions are formed as Action Units (AUs), and AUs in micro-expressions can be seen as the actors in cooperative group activities. In this paper, we propose a novel deep neural network model for objective class-based MER, which simultaneously detects AUs and aggregates AU-level features into micro-expression-level representation through Graph Convolutional Networks (GCN). Specifically, we propose two new strategies in our AU detection module for more effective AU feature learning: the attention mechanism and the balanced detection loss function. With those two strategies, features are learned for all the AUs in a unified model, eliminating the error-prune landmark detection process and tedious separate training for each AU. Moreover, our model incorporates a tailored objective class-based AU knowledge-graph, which facilitates the GCN to aggregate the AU-level features into a micro-expression-level feature representation. Extensive experiments on two tasks in MEGC 2018 show that our approach significantly outperforms the current state-of-the-arts in MER. Additionally, we also report our single model-based micro-expression AU detection results.

cs.CV↗
arXiv2020

FREA-Unet: Frequency-aware U-net for Modality Transfer

While Positron emission tomography (PET) imaging has been widely used in diagnosis of number of diseases, it has costly acquisition process which involves radiation exposure to patients. However, magnetic resonance imaging (MRI) is a safer imaging modality that does not involve patient's exposure to radiation. Therefore, a need exists for an efficient and automated PET image generation from MRI data. In this paper, we propose a new frequency-aware attention U-net for generating synthetic PET images. Specifically, we incorporate attention mechanism into different U-net layers responsible for estimating low/high frequency scales of the image. Our frequency-aware attention Unet computes the attention scores for feature maps in low/high frequency layers and use it to help the model focus more on the most important regions, leading to more realistic output images. Experimental results on 30 subjects from Alzheimers Disease Neuroimaging Initiative (ADNI) dataset demonstrate good performance of the proposed model in PET image synthesis that achieved superior performance, both qualitative and quantitative, over current state-of-the-arts.

eess.IV↗
arXiv2020

SPA-GAN: Spatial Attention GAN for Image-to-Image Translation

Image-to-image translation is to learn a mapping between images from a source domain and images from a target domain. In this paper, we introduce the attention mechanism directly to the generative adversarial network (GAN) architecture and propose a novel spatial attention GAN model (SPA-GAN) for image-to-image translation tasks. SPA-GAN computes the attention in its discriminator and use it to help the generator focus more on the most discriminative regions between the source and target domains, leading to more realistic output images. We also find it helpful to introduce an additional feature map loss in SPA-GAN training to preserve domain specific features during translation. Compared with existing attention-guided GAN models, SPA-GAN is a lightweight model that does not need additional attention networks or supervision. Qualitative and quantitative comparison against state-of-the-art methods on benchmark datasets demonstrates the superior performance of SPA-GAN.

cs.CV↗
arXiv2020

Estimating Asset Class Health Indices in Power Systems

Power systems have widely adopted the concept of health index to describe asset health statuses and choose proper asset management actions. The existing application and research works have been focused on determining the current or near-future asset health index based on the current condition data. For preventative asset management, it is highly desirable to estimate asset health indices, especially for asset classes in which the assets share similar electrical and/or mechanical characteristics. This important problem has not been sufficiently addressed. This paper proposes a sequence learning based method to estimate health indices for power asset classes. A comprehensive data-driven method based on sequence learning is presented and solid tests are conducted based on real utility data. The proposed method revealed superior performance with comparison to other Estimation methods.

cs.CE↗
arXiv2020

A hybridizable discontinuous Galerkin method for simulation of electrostatic problems with floating potential conductors

In an electrostatic simulation, an equipotential condition with an undefined/floating potential value has to be enforced on the surface of an isolated conductor. If this conductor is charged, a nonzero charge condition is also required. While implementation of these conditions using a traditional finite element method (FEM) is not straightforward, they can be easily discretized and incorporated within a discontinuous Galerkin (DG) method. However, DG discretization results in a larger number of unknowns as compared to FEM. In this work, a hybridizable DG (HDG) method is proposed to alleviate this problem. Floating potential boundary conditions, possibly with different charge values, are introduced on surfaces of each isolated conductor and are weakly enforced in the global problem of HDG. The unknowns of the global HDG problem are those only associated with the nodes on the mesh skeleton and their number is much smaller than the total number of unknowns required by DG. Numerical examples show that the proposed method is as accurate as DG while it improves the computational efficiency significantly.

math.NA↗
arXiv2020

Multi-year Long-term Load Forecast for Area Distribution Feeders based on Selective Sequence Learning

Long-term load forecast (LTLF) for area distribution feeders is one of the most critical tasks frequently performed in electric distribution utility companies. For a specific planning area, cost-effective system upgrades can only be planned out based on accurate feeder LTLF results. In our previous research, we established a unique sequence prediction method which has the tremendous advantage of combining area top-down, feeder bottom-up and multi-year historical data all together for forecast and achieved a superior performance over various traditional methods by real-world tests. However, the previous method only focused on the forecast of the next one-year. In our current work, we significantly improved this method: the forecast can now be extended to a multi-year forecast window in the future; unsupervised learning techniques are used to group feeders by their load composition features to improve accuracy; we also propose a novel selective sequence learning mechanism which uses Gated Recurrent Unit network to not only learn how to predict sequence values but also learn to select the best-performing sequential configuration for each individual feeder. The proposed method was tested on an actual urban distribution system in West Canada. It was compared with traditional methods and our previous sequence prediction method. It demonstrates the best forecasting performance as well as the possibility of using sequence prediction models for multi-year component-level load forecast.

eess.SY↗
arXiv2020

A Data-Driven Residential Transformer Overloading Risk Assessment Method

Residential transformer population is a critical type of asset that many electric utility companies have been attempting to manage proactively and effectively to reduce unexpected failures and life losses that are often caused by transformer overloading. Within the typical power asset portfolio, the residential transformer asset is often large in population, having lowest reliability design, lacking transformer loading data and susceptible to customer loading behaviors such as adoption of distributed energy resources and electric vehicles. On the bright side, the availability of more residential operation data along with the advancement of data analytics techniques have provided a new path to further our understanding of local residential transformer overloading risks statistically. This research developed a new data-driven method to combine clustering analysis and the simulation of transformer temperature rise and insulation life loss to quantitatively and statistically assess the overloading risk of residential transformer population in one area and suggest proper risk management measures according to the assessment results. Case studies from an actual Canadian utility company have been presented and discussed in detail to demonstrate the applicability and usefulness of the proposed method.

cs.CE↗
arXiv2020

A Data-driven Dynamic Rating Forecast Method and Application for Power Transformer Long-term Planning

This paper presents a data-driven method for producing annual continuous dynamic rating of power transformers to serve the long-term planning purpose. Historically, research works on dynamic rating have been focused on real-time/near-future system operations. There has been a lack of research for long-term planning oriented applications. Currently, most utility companies still rely on static rating numbers when planning power transformers for the next few years. In response, this paper proposes a novel and comprehensive method to analyze the past 5-year temperature, loading and load composition data of existing power transformers in a planning region. Based on such data and the forecasted area load composition, a future power transformer loading profile can be constructed by using Gaussian Mixture Model. Then according to IEEE std. C57.91-2011, a power transformer thermal aging model can be established to incorporate future loading and temperature profiles. As a result, annual continuous dynamic rating profiles under different temperature scenarios can be determined. The profiles can reflect the long-term thermal overloading risk in a much more realistic and granular way, which can significantly improve the accuracy of power transformer planning. A real utility application example in Canada has been presented to demonstrate the practicality and usefulness of this method.

cs.CE↗
arXiv2020

Combining Modified Weibull Distribution Models for Power System Reliability Forecast

In recent years, under deregulated environment, electric utility companies have been encouraged to ensure maximum system reliability through the employment of cost-effective long-term asset management strategies. To help achieve this goal, this research proposes a novel statistical approach to forecast power system asset population reliability. It uniquely combines a few modified Weibull distribution models to build a robust joint forecast model. At first, the classic age based Weibull distribution model is reviewed. In comparison, this paper proposes a few modified Weibull distribution models to incorporate special considerations for power system applications. Furthermore, this paper proposes a novel method to effectively measure the forecast accuracy and evaluate different Weibull distribution models. As a result, for a specific asset population, the suitable model(s) can be selected. More importantly, if more than one suitable model exists, these models can be mathematically combined as a joint forecast model to forecast future asset reliability. Finally, the proposed methods were applied to a Canadian utility company for the reliability forecast of electromechanical relays and the results are discussed in detail to demonstrate the practicality and usefulness of this research.

cs.CE↗
arXiv2020

Combining Unsupervised and Supervised Learning for Asset Class Failure Prediction in Power Systems

In power systems, an asset class is a group of power equipment that has the same function and shares similar electrical or mechanical characteristics. Predicting failures for different asset classes is critical for electric utilities towards developing cost-effective asset management strategies. Previously, physical age based Weibull distribution has been widely used to failure prediction. However, this mathematical model cannot incorporate asset condition data such as inspection or testing results. As a result, the prediction cannot be very specific and accurate for individual assets. To solve this important problem, this paper proposes a novel and comprehensive data-driven approach based on asset condition data: K-means clustering as an unsupervised learning method is used to analyze the inner structure of historical asset condition data and produce the asset conditional ages; logistic regression as a supervised learning method takes in both asset physical ages and conditional ages to classify and predict asset statuses. Furthermore, an index called average aging rate is defined to quantify, track and estimate the relationship between asset physical age and conditional age. This approach was applied to an urban distribution system in West Canada to predict medium-voltage cable failures. Case studies and comparison with standard Weibull distribution are provided. The proposed approach demonstrates superior performance and practicality for predicting asset class failures in power systems.

stat.AP↗
arXiv2020

A Hybrid Distribution Feeder Long-Term Load Forecasting Method Based on Sequence Prediction

Distribution feeder long-term load forecast (LTLF) is a critical task many electric utility companies perform on an annual basis. The goal of this task is to forecast the annual load of distribution feeders. The previous top-down and bottom-up LTLF methods are unable to incorporate different levels of information. This paper proposes a hybrid modeling method using sequence prediction for this classic and important task. The proposed method can seamlessly integrate top-down, bottom-up and sequential information hidden in multi-year data. Two advanced sequence prediction models Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) networks are investigated in this paper. They successfully solve the vanishing and exploding gradient problems a standard recurrent neural network has. This paper firstly explains the theories of LSTM and GRU networks and then discusses the steps of feature selection, feature engineering and model implementation in detail. In the end, a real-world application example for a large urban grid in West Canada is provided. LSTM and GRU networks under different sequential configurations and traditional models including bottom-up, ARIMA and feed-forward neural network are all implemented and compared in detail. The proposed method demonstrates superior performance and great practicality.

cs.LG↗
arXiv2019

Partial Discharge Detection on Aerial Covered Conductors Using Time-Series Decomposition and Long Short-term Memory Network

Nowadays, aerial covered conductors (CC) are increasingly used in many places of the world due to their higher operational reliability, reduced construction space and effective protection for wildlife animals. In spite of these advantages, a major challenge of using CC is that the ordinary upstream protection devices are not able to detect the phase-to-ground faults and the frequent tree/tree branch hitting conductor events on such conductors. This is because these events only lead to partial discharge (PD) activities rather than overcurrent signatures typically seen on bare conductors. To solve this problem, in recent years, ENET Center in Czech Republic (ENET) devised a simple meter to measure the voltage signal of the electric stray field along CC, aiming to detect the above hazardous PD activities. In 2018, ENET shared a large amount of waveform data recorded by their meter on Kaggle, the world's largest data science collaboration platform, encouraging worldwide experts to develop an effective pattern recognition method for the acquired signals. In response, we developed a unique method based on time-series decomposition and Long Short-Term Memory Network (LSTM) in addition to unique feature engineering process to recognize PD activities on CC. The proposed method is tested on the ENET public dataset and compared to various traditional classification methods. It demonstrated superior performance and great practicality.

eess.SP↗
arXiv2019

A Pattern Recognition Method for Partial Discharge Detection on Insulated Overhead Conductors

Today,insulated overhead conductors are increasingly used in many places of the world due to the higher operational reliability, elimination of phase-to-phase contact, closer distances between phases and stronger protection for animals. However, the standard protection devices are often not able to detect the conductor phase-to-ground fault and the more frequent tree/tree branch hitting conductor events as these events only lead to partial discharge (PD) activities instead of causing overcurrent seen on bare conductors. To solve this problem, in recent years, Technical University of Ostrava (VSB) devised a special meter to measure the voltage signal of the stray electrical field along the insulated overhead conductors, hoping to detect the above hazardous PD activities. In 2018, VSB published a large amount of waveform data recorded by their meter on Kaggle, the world's largest data science collaboration platform, looking for promising pattern recognition methods for this application. To tackle this challenge, we developed a unique method based on Seasonal and Trend decomposition using Loess (STL) and Support Vector Machine (SVM) to recognize PD activities on insulated overhead conductors. Different SVM kernels were tested and compared. Satisfactory classification rates on VSB dataset were achieved with the use of Gaussian radial basis kernel.

eess.SP↗