YEYING ZHU

Dr. YEYING ZHU


Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 August 2014 in Journal of Causal Inference
Verified
Journal Article
Closed access
YZYEYING ZHU
YEYING ZHU
DCDonna L. Coffman
Donna L. Coffman
DGDebashis Ghosh
Debashis Ghosh
In this article, we study the causal inference problem with a continuous treatment variable using propensity score-based methods. For a continuous treatment, the generalized propensity score is defined as the conditional density of the treatment-level given covariates (confounders). The dose–response function is then estimated by inverse probability weighting, where the weights are calculated from the estimated propensity scores. When the dimension of the covariates is large, the traditional nonparametric density estimation suffers from the curse of dimensionality. Some researchers have suggested a two-step estimation procedure by first modeling the mean function. In this study, we suggest a boosting algorithm to estimate the mean function of the treatment given covariates. In boosting, an important tuning parameter is the number of trees to be generated, which essentially determines the trade-off between bias and variance of the causal estimator. We propose a criterion called average absolute correlation coefficient (AACC) to determine the optimal number of trees. Simulation results show that the proposed approach performs better than a simple linear approximation or L2 boosting. The proposed methodology is also illustrated through the Early Dieting in Girls study, which examines the influence of mothers’ overall weight concern on daughters’ dieting behavior.

18 July 2023 in IEEE Open Journal of the Communications Society
Verified
Journal Article
Open access
AAAtefeh Hajijamali Arani
Atefeh Hajijamali Arani
PHPeng Hu
Peng Hu
YZYEYING ZHU
YEYING ZHU
The integrated use of non-terrestrial network (NTN) entities such as the high-altitude platform station (HAPS) and low-altitude platform station (LAPS) has become essential elements in the space-air-ground integrated networks (SAGINs). However, the complexity, mobility, and heterogeneity of NTN entities and resources present various challenges from system design to deployment. This paper proposes a novel approach to designing a heterogeneous network consisting of HAPSs and unmanned aerial vehicles (UAVs) being LAPS entities. Our approach involves jointly optimizing the three-dimensional trajectory and channel allocation for aerial base stations, with a focus on ensuring fairness and the provision of quality of service (QoS) to ground users. Furthermore, we consider the load on base stations and incorporate this information into the optimization problem. The proposed approach utilizes a combination of deep reinforcement learning and fixed-point iteration techniques to determine the UAV locations and channel allocation strategies. Simulation results reveal that our proposed deep learning-based approach significantly outperforms learning-based and conventional benchmark models.

6 October 2021 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
AAAtefeh Hajijamali Arani
Atefeh Hajijamali Arani
MAM. Mahdi Azari
M. Mahdi Azari
PHPeng Hu
Peng Hu
YZYEYING ZHU
YEYING ZHU
HYHalim Yanikomeroglu
Halim Yanikomeroglu
SSSafieddin Safavi-Naeini
Safieddin Safavi-Naeini
Integrating unmanned aerial vehicles (UAVs) as aerial base stations (BSs) into terrestrial cellular networks has emerged as an effective solution to provide coverage and complement communication services in a fast and cost-effective manner. The three-dimensional (3-D) trajectories of UAVs have a remarkable impact on the performance of such networks. On the other hand, UAVs are battery limited, and thus optimizing their energy consumption is of high importance. In this regard, we propose a novel trajectory design mechanism for rotary-wing UAV-BSs in 3-D space to improve the energy efficiency of the network. In this approach, UAVs aim at maximizing an objective function that captures the tradeoff between energy consumption and throughput, while satisfying their ground users’ quality-of-service requirements. Using reinforcement learning, we model our problem as a multiarmed bandit and propose an upper confidence bound-based algorithm to solve the problem. In our proposed mechanism, UAVs autonomously choose their velocities and update their locations adapted to the system conditions without requiring the prior and full knowledge of the system. Simulation results show that our proposed approach yields significant performance gains reaching up to 33.85% in terms of improving the network throughput, and up to 95% of enhancing the energy efficiency compared to a learning-based benchmark. Comparing to a nonlearning-based approach, our proposed approach improves the throughput and energy efficiency by 46.61% and 110%, respectively.

23 January 2017 in Biometrika
Verified
Journal Article
Closed access
PDF file
WLWei Luo
Wei Luo
YZYEYING ZHU
YEYING ZHU
DGDebashis Ghosh
Debashis Ghosh
In many causal inference problems the parameter of interest is the regression causal effect, defined as the conditional mean difference in the potential outcomes given covariates. In this paper we discuss how sufficient dimension reduction can be used to aid causal inference, and we propose a new estimator of the regression causal effect inspired by minimum average variance estimation. The estimator requires a weaker common support condition than propensity score-based approaches, and can be used to estimate the average causal effect, for which it is shown to be asymptotically super-efficient. Its finite-sample properties are illustrated by simulation.

24 May 2021 in IEEE Access
Verified
Journal Article
Open access
AAAtefeh Hajijamali Arani
Atefeh Hajijamali Arani
PHPeng Hu
Peng Hu
YZYEYING ZHU
YEYING ZHU
The integration of space and air components considering satellites and unmanned aerial vehicles (UAVs) into terrestrial networks in a space-terrestrial integrated network (STIN) has been envisioned as a promising solution to enhancing the terrestrial networks in terms of fairness, performance, and network resilience. However, employing UAVs introduces some key challenges, among which backhaul connectivity, resource management, and efficient three-dimensional (3D) trajectory designs of UAVs are very crucial. In this paper, low-Earth orbit (LEO) satellites are employed to alleviate the backhaul connectivity issues with UAV networks, where we address the problem of jointly determining backhaul-aware 3D trajectories of UAVs, resource management, and associations between users, satellites and base stations (BSs) in an STIN while satisfying ground users' quality-of-experience requirements and provisioning fairness concerning users' data rates. The proposed approach maximizes a novel objective function with joint consideration for BS's load and fairness, which can be categorized as a non-deterministic polynomial time hard (NP-hard) problem. To tackle this issue, we leverage a reinforcement learning framework, in which our problem is modeled as a multi-armed bandit problem. Accordingly, BSs learn the environment and its dynamics and then make decisions under an upper confidence bound based method. Simulation results show that our proposed approach outperforms the benchmark methods in terms of fairness, throughput, and load.

22 September 2022 in IEEE Transactions on Aerospace and Electronic Systems
Verified
Journal Article
Closed access
MSMohammad Amin Maleki Sadr
Mohammad Amin Maleki Sadr
YZYEYING ZHU
YEYING ZHU
PHPeng Hu
Peng Hu
Recently, there has been a significant amount of interest in satellite telemetry anomaly detection (AD) using neural networks (NN). For AD purposes, the current approaches focus on either forecasting or reconstruction of the time series, and they cannot measure the level of reliability or the probability of correct detection. Although the Bayesian neural network (BNN)-based approaches are well known for time series uncertainty estimation, they are computationally intractable. In this paper, we present a tractable approximation for BNN based on the Monte Carlo (MC) dropout method for capturing the uncertainty in the satellite telemetry time series, without sacrificing accuracy. For time series forecasting, we employ an NN, which consists of several Long Short-Term Memory (LSTM) layers followed by various dense layers. We employ the MC dropout inside each LSTM layer and before the dense layers for uncertainty estimation. With the proposed uncertainty region and by utilizing a post-processing filter, we can effectively capture the anomaly points. Numerical results show that our proposed time series AD approach outperforms the existing methods from both prediction accuracy and AD perspectives.