Entries by

Research paper accepted by Knowledge-Based Systems

February 9, 2022 in /by

The poor explainability of deep learning models has hindered their adoption in safety and quality-critical applications. This paper focuses on image classification models and aims to enhance the explainability of deep learning models through the development of an uncertainty quantification-based framework. The proposed methodology consists of three major steps. In the first step, we adopt dropout-based Bayesian neural network to characterize the structure and parameter uncertainty inherent in deep learning models, propagate and represent such uncertainties to the model prediction as a distribution. Next, we employ entropy as a quantitative indicator to measure the uncertainty in model prediction, and develop an Empirical Cumulative Distribution Function (ECDF)-based approach to determine an appropriate threshold value for the purpose of deciding when to accept or reject the model prediction. Secondly, in the cases with high model prediction uncertainty, we combine the prediction difference analysis (PDA) approach with dropout-based Bayesian neural network to quantify the uncertainty in pixel-wise feature importance, and identify the locations in the input image that highly correlate with the model prediction uncertainty. In the third step, we develop a robustness-based design optimization formulation to enhance the relevance between input features and model prediction, and leverage a differential evolution approach to optimize the pixels in the input image with high uncertainty in feature importance. Experimental studies in MNIST and CIFAR-10 image classifications are included to demonstrate the effectiveness of the proposed approach in increasing the explainability of deep learning models.

Research paper accepted by Journal of Mechanical Design

December 8, 2021 in /by

Identifying a reliable path in uncertain environments is essential for designing reliable off-road autonomous ground vehicles (AGV) considering post-design operations. This paper presents a novel bio-inspired approach for model-based multi-vehicle mission planning under uncertainty for off-road AGVs subjected to mobility reliability constraints in dynamic environments. A physics-based vehicle dynamics simulation model is first employed to predict vehicle mobility (i.e., maximum attainable speed) for any given terrain and soil conditions. Based on physics-based simulations, the vehicle state mobility reliability in operation is then analyzed using an adaptive surrogate modeling method to overcome the computational challenges in mobility reliability analysis by adaptively constructing a surrogate. Subsequently, a bio-inspired approach called Physarum-based algorithm is used in conjunction with a navigation mesh to identify an optimal path satisfying a specific mobility reliability requirement. The developed Physarum-based framework is applied to reliability-based path planning for both a single-vehicle and multiple-vehicle scenarios. A case study is used to demonstrate the efficacy of the proposed methods and algorithms. The results show that the proposed framework can effectively identify optimal paths for both scenarios of a single and multiple vehicles. The required computational time is less than the widely used Dijkstra-based method.

ML model in production at FedEx Express

September 20, 2021 in /by

FedEx Express handles more than 6.5 million packages everyday in nearly 220 countries and regions. Customers expect timely and accurate information on their package deliveries. To address customers demand, I have worked with teams across different departments (e.g., IT, market) and colleagues in the Operations Research and Spatial Analytics (ORSA) to develop and deploy a machine learning-based solution to produce customized expected delivery time windows for millions of packages every day. I am proud that the deployed ML model has been in production with reliable performance since March, 2021.

Research paper accepted by Safety Science

June 22, 2021 in /by

In this paper, we apply a set of data-mining and sequential deep learning techniques to accident investigation reports published by the National Transportation Safety Board (NTSB) in support of the prognosis of adverse events. Our focus is on learning with text data that describes the sequences of events. NTSB creates post-hoc investigation reports which contain raw text narratives of their investigation and their corresponding concise event sequences. Classification models are developed for passenger air carriers, that take either an observed sequence of events or the corresponding raw text narrative as input and make predictions regarding whether an accident or an incident is the likely outcome, whether the aircraft would be damaged or not and whether any fatalities are likely or not. The classification models are developed using Word Embedding and the Long Short-term Memory (LSTM) neural network. The proposed methodology is implemented in two steps: (i) transform the NTSB data extracts into labeled dataset for building supervised machine learning models; and (ii) develop deep learning (DL) models for performing prognosis of adverse events like accidents, aircraft damage or fatalities. We also develop a prototype for an interactive query interface for end-users to test various scenarios including complete or partial event sequences or narratives and get predictions regarding the adverse events. The development of sequential deep learning models facilitates safety professionals in auditing, reviewing, and analyzing accident investigation reports, performing what-if scenario analyses to quantify the contributions of various hazardous events to the occurrence of aviation accidents/incidents.

Research paper accepted by Reliability Engineering and Systems Safety

November 26, 2020 in /by

Safety assurance is of paramount importance in the air transportation system. In this paper, we analyze the historical passenger airline accidents that happened from 1982 to 2006 as reported in the National Transportation Safety Board (NTSB) aviation accident database. A four-step procedure is formulated to construct a Bayesian network to capture the causal relationships embedded in the sequences of these accidents. First of all, with respect to each accident, a graphical representation is developed to facilitate the visualization of the escalation of initiating events into aviation accidents in the system. Next, we develop a Bayesian network representation of all the accidents by aggregating the accident-wise graphical representations together, where the causal and dependent relationships among a wide variety of contributory factors and outcomes in terms of aircraft damage and personnel injury are captured. In the Bayesian network, the prior probabilities are estimated based on the accident occurrence times and the aircraft departure data from the Bureau of Transportation Statistics (BTS). To estimate the conditional probabilities in the Bayesian network, we develop a monotonically increasing function, whose parameters are calibrated using the probability information on single events in the available data. Finally, we develop a computer program to automate the generation of the Bayesian network in compliance with the XML format used in the commercial GeNIe modeler. The constructed Bayesian network is then fed into GeNIe modeler for accident analysis. The mapping of the NTSB data to a Bayesian network facilitates both forward propagation and backward inference in probabilistic analysis, thereby supporting accident investigations and risk analysis. Several accident cases are used to demonstrate the developed approach.

Research paper accepted by IEEE Transactions on Reliability

May 13, 2020 in /by

Resilience is an important capability for many complex systems to mitigate the impact of extreme events as well as timely restoration of system performance in the aftermath of a disruptive event. In this paper, we investigate a bi-level pre-disaster resilience-based design optimization approach for the configuration of logistics service centers. In the bi-level program, the upper-level model considers the impact of potential disruptive events, and characterizes system planners’ decision regarding possible service center configuration that consists of two decision variables: construction of service center at candidate sites and their specific capacities. The optimization in the upper-level model considers both the travel time of each customer from their origins to the service centers and the within-center service time including average waiting time in the queue and mean processing time. The lower-level model captures customers’ behavior in choosing the distribution center to fulfill their requests with the goal of minimizing the cumulative travel time for all the customers. The objective of the formulated bi-level program is to maximize the resilience of the service center configuration, thereby increasing the ability of the system to withstand unexpected events. To tackle this NP-hard optimization problem, an adaptive importance sampling approach – cross entropy-based method – is leveraged to generate samples that gradually concentrates all its mass in the proximity of the optimal solution in an iterative way. A numerical example is used to illustrate the procedures of the developed method and demonstrate the effectiveness of the proposed methodology.

Research project funded by ARPA-E

April 24, 2020 in /by

The increasing role of renewable energy sources is challenging grid operations, which have traditionally relied on highly predictable load and generation. Future grid operations must balance generation costs and system-level risk, shifting from deterministic to stochastic optimization and risk management. The Risk-Aware Market Clearing (RAMC) project will provide a blueprint for an end-to-end, data-driven approach where risk is explicitly modeled, quantified, and optimized, striking a trade-off between cost and system-level risk minimization. The RAMC project focuses on challenges arising from increased stochasticity in generation, load, flow interchanges with adjacent markets, and extreme weather. RAMC addresses these challenges through innovations in machine learning, sampling, and optimization. Starting with the risk quantification of each individual asset obtained from historical data, RAMC learns the correlations between the performance and risk of individual assets, optimizes the selection of asset bundles, and quantifies the system-level risk.

Research paper accepted by Decision Support Systems

January 2, 2020 in /by

Safety, as the most important concern in civil aviation, needs to be maintained at an acceptable level at all times in the air transportation system. This paper aims to increase en-route flight safety through the development of deep learning models for trajectory prediction, where model prediction uncertainty is characterized following a Bayesian approach. The proposed methodology consists of four steps. In the first step, a large volume of raw messages in Flight Information Exchange Model (FIXM) format streamed from Federal Aviation Administration are processed with a distributed computing engine Apache Spark to extract trajectory information in an efficient manner. In the second step, two types of deep learning models are trained to predict flight trajectory from different perspectives. Specifically, deep feedforward neural networks (DNN) are trained to make a one-step-ahead prediction on the deviation along latitude and longitude between the actual flight trajectory and target flight trajectory. In parallel, deep Long Short-Term Memory (LSTM) neural networks are trained to make longer-term predictions on the flight trajectory over several subsequent time instants. The DNN model is more accurate but has a single-step prediction horizon, whereas the LSTM model is less accurate but longer prediction horizon. Therefore, in the third step, the two different types of deep learning models are blended together to create a multi-fidelity prediction. After quantifying the discrepancy between the two model predictions in the current time instant, the DNN prediction is used to correct the LSTM prediction of flight trajectory along subsequent time instants accordingly. The multi-fidelity approach is expanded to multiple flights, and is then used to assess safety based on horizontal and vertical separation distance between two flights. Computational results illustrate the promising performance of the blended model in predicting the flight trajectory and assessing en-route flight safety.

Research paper published in Decision Support Systems

October 11, 2019 in /by

We facilitate the “proactive safety” paradigm to increase system safety with a focus on predicting the severity of abnormal aviation events in terms of their risk levels. To accomplish this goal, a predictive model needs to be developed to examine a wide variety of possible cases and quantify the risk associated with the possible outcome. By utilizing the incident reports available in the Aviation Safety Reporting System (ASRS), we build a hybrid model consisting of support vector machine and an ensemble of deep neural networks to quantify the risk associated with the consequence of each hazardous cause. The proposed methodology is developed in four steps. First, we categorize all the events, based on the level of risk associated with the event consequence, into five groups: high risk, moderately high risk, medium risk, moderately medium risk, and low risk. Secondly, a support vector machine model is used to discover the relationships between the event synopsis in text format and event consequence. In parallel, an ensemble of deep neural networks is trained to model the intricate associations between event contextual features and event outcomes. Thirdly, an innovative fusion rule is developed to blend the prediction results from the two types of trained machine learning models, thereby improving the prediction. Finally, the prediction on risk level categorization is extended to event-level outcomes through a probabilistic decision tree. By comparing the performance of the developed hybrid model against another three individual models with ten-fold cross-validation and statistical tests, we demonstrate the effectiveness of hybrid model in quantifying the risk related to the consequences of hazardous events.

Research paper published in Risk Analysis

October 10, 2019 in /by

We develop a bi-level mathematical optimization model to maximize the transportation system resilience and restore its performance through two network reconfiguration schemes: contraflow (also referred to as lane reversal), and crossing elimination at intersections. Mathematical models are developed to represent the two reconfiguration schemes and characterize the interactions between traffic operators and passengers. Specifically, traffic operators act as leaders to determine the optimal system reconfiguration to minimize the total travel time for all the users (both evacuees and regular commuters), while passengers act as followers by freely choosing the path with the minimum travel time, which eventually converges to a user equilibrium state. For each given network reconfiguration, the lower level problem is formulated as a traffic assignment problem (TAP) where each user tries to minimize his/her own travel time. To tackle the lower-level optimization problem, a gradient projection method is leveraged to shift the flow from other non-shortest paths to the shortest path between each origin-destination pair, eventually converging to the user equilibrium traffic assignment. The upper-level problem is formulated as a constrained discrete optimization problem, and a probabilistic solution discovery algorithm is used to obtain the near-optimal solution. Two numerical examples are used to demonstrate the effectiveness of the proposed method in restoring the traffic system performance.