Author name cluster

Zhishan Guo

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

7 papers

1 author row

AAAI Conference 2026 Conference Paper

CertMask: Certifiable Defense Against Adversarial Patches via Theoretically Optimal Mask Coverage

Xuntao Lyu
Ching-Chi Lin
Abdullah Al Arafat
Georg von der Brüggen
Jian-Jia Chen
Zhishan Guo

Adversarial patch attacks inject localized perturbations into images to mislead deep vision models. These attacks can be physically deployed, posing serious risks to real-world applications. In this paper, we propose CertMask, a certifiably robust defense that constructs a provably sufficient set of binary masks to neutralize patch effects with strong theoretical guarantees. While the state-of-the-art approach (PatchCleanser) requires two rounds of masking and incurs O(n^2) inference cost, CertMask performs only a single round of masking with O(n) time complexity, where n is the cardinality of the mask set to cover an input image. Our proposed mask set is computed using a mathematically rigorous coverage strategy that ensures each possible patch location is covered at least k times, providing both efficiency and robustness. We offer a theoretical analysis of the coverage condition and prove its sufficiency for certification. Experiments on ImageNet, ImageNette, and CIFAR-10 show that CertMask improves certified robust accuracy by up to +13.4% over PatchCleanser, while maintaining clean accuracy nearly identical to the vanilla model.

PDF Details DOI

JBHI Journal 2023 Journal Article

Estimation of Lower Extremity Joint Moments and 3D Ground Reaction Forces Using IMU Sensors in Multiple Walking Conditions: A Deep Learning Approach

Md Sanzid Bin Hossain
Zhishan Guo
Hwan Choi

Human kinetics, specifically joint moments and ground reaction forces (GRFs) can provide important clinical information and can be used to control assistive devices. Traditionally, collection of kinetics is mostly limited to the lab environment because it relies on data that are measured from a motion capture system and floor-embedded force plates to calculate the dynamics via musculoskeletal models. This spatially limited method makes it extremely challenging to measure kinetics outside the laboratory in a variety of walking conditions due to the expensive device setup and large space required. Recently, employing machine learning with IMU sensors are suggested as an alternative method for biomechanical analyses. Although these methods enable estimating human kinetic data outside the laboratory by linking IMU sensor data with kinetics dataset, they are limited to show inaccurate kinetic estimates even in highly repeatable single walking conditions due to the employment of generic deep learning algorithms. Thus, this paper proposes a novel deep learning model, Kinetics-FM-DLR-Ensemble-Net for single limb prediction of hip, knee, and ankle joint moments and 3-dimensional GRFs using three IMU sensors on the thigh, shank, and foot under several representatives walking conditions in daily living, such as treadmill, level-ground, stair, and ramp. This is the first study that implements both joint moments and GRFs in multiple walking conditions using IMU sensors via deep learning. Our deep learning model is versatile and accurate for identifying human kinetics across diverse subjects and walking conditions and outperforms state-of-the-art deep learning model for kinetics estimation by a large margin.

Details DOI

JBHI Journal 2023 Journal Article

Wearable Motion Capture: Reconstructing and Predicting 3D Human Poses From Wearable Sensors

Md Moniruzzaman
Zhaozheng Yin
Md Sanzid Bin Hossain
Hwan Choi
Zhishan Guo

Reconstructing and predicting 3D human walking poses in unconstrained measurement environments have the potential to use for health monitoring systems for people with movement disabilities by assessing progression after treatments and providing information for assistive device controls. The latest pose estimation algorithms utilize motion capture systems, which capture data from IMU sensors and third-person view cameras. However, third-person views are not always possible for outpatients alone. Thus, we propose the wearable motion capture problem of reconstructing and predicting 3D human poses from the wearable IMU sensors and wearable cameras, which aids clinicians' diagnoses on patients out of clinics. To solve this problem, we introduce a novel Attention-Oriented Recurrent Neural Network (AttRNet) that contains a sensor-wise attention-oriented recurrent encoder, a reconstruction module, and a dynamic temporal attention-oriented recurrent decoder, to reconstruct the 3D human pose over time and predict the 3D human poses at the following time steps. To evaluate our approach, we collected a new WearableMotionCapture dataset using wearable IMUs and wearable video cameras, along with the musculoskeletal joint angle ground truth. The proposed AttRNet shows high accuracy on the new lower-limb WearableMotionCapture dataset, and it also outperforms the state-of-the-art methods on two public full-body pose datasets: DIP-IMU and TotalCaputre.

Details DOI

JBHI Journal 2022 Journal Article

DeepBBWAE-Net: A CNN-RNN Based Deep SuperLearner for Estimating Lower Extremity Sagittal Plane Joint Kinematics Using Shoe-Mounted IMU Sensors in Daily Living

Md Sanzid Bin Hossain
Joseph Dranetz
Hwan Choi
Zhishan Guo

Measurement of human body movement is an essential step in biomechanical analysis. The current standard for human motion capture systems uses infrared cameras to track reflective markers placed on a subject. While these systems can accurately track joint kinematics, the analyses are spatially limited to the lab environment. Though Inertial Measurement Units (IMUs) can eliminate these spatial limitations, those systems are impractical for use in daily living due to the need for many sensors, typically one per body segment. Due to the need for practical and accurate estimation of joint kinematics, this study implements a reduced number of IMU sensors and employs a machine learning algorithm to map sensor data to joint angles. Our developed algorithm estimates hip, knee, and ankle angles in the sagittal plane using two shoe-mounted IMU sensors in different practical walking conditions: treadmill, overground, stair, and slope conditions. Specifically, we propose five deep learning networks that use combinations of Convolutional Neural Networks (CNN) and Gated Recurrent Unit (GRU) based Recurrent Neural Networks (RNN) as base learners for our framework. Using those five baseline models, we propose a novel framework, DeepBBWAE-Net, that implements ensemble techniques such as bagging, boosting, and weighted averaging to improve kinematic predictions. DeepBBWAE-Net predicts joint kinematics for the three joint angles for each of the walking conditions with a Root Mean Square Error (RMSE) 6. 93-29. 0% lower than the base models individually. This is the first study that uses a reduced number of IMU sensors to estimate kinematics in multiple walking environments.

Details DOI

I&C Journal 2021 Journal Article

Narrowing the speedup factor gap of partitioned EDF

Xingwu Liu
Xin Han
Liang Zhao
Zhishan Guo

Schedulability is a fundamental problem in analyzing real-time systems, but it often has to be approximated because of the intrinsic computational hardness. Partitioned earliest deadline first (EDF) is one of the most popular polynomial-time and practical scheduler on multiprocessor platforms, and it was shown to have a speedup factor of at most 2. 6322 − 1 / m. This paper further improves the factor to 2. 5556 − 1 / m for both the constrained-deadline case and the arbitrary-deadline case, and it is very close to the known (non-tight) lower bound of 2. 5 − 1 / m. The key ideas are that we develop a novel method to discretize and regularize sporadic task sets that are schedulable on uniprocessors, and we find that the ratio (ρ) of the approximate demand bound value to the machine capacity is upper-bounded by 1. 5556 for the arbitrary-deadline case, which plays an important role in estimating the speed factor of partitioned EDF.

Details DOI

AAAI Conference 2019 Conference Paper

SpHMC: Spectral Hamiltonian Monte Carlo

Haoyi Xiong
Kafeng Wang
Jiang Bian
Zhanxing Zhu
Cheng-Zhong Xu
Zhishan Guo
Jun Huan

Stochastic Gradient Hamiltonian Monte Carlo (SGHMC) methods have been widely used to sample from certain probability distributions, incorporating (kernel) density derivatives and/or given datasets. Instead of exploring new samples from kernel spaces, this piece of work proposed a novel SGHMC sampler, namely Spectral Hamiltonian Monte Carlo (SpHMC), that produces the high dimensional sparse representations of given datasets through sparse sensing and SGHMC. Inspired by compressed sensing, we assume all given samples are low-dimensional measurements of certain high-dimensional sparse vectors, while a continuous probability distribution exists in such high-dimensional space. Specifically, given a dictionary for sparse coding, SpHMC first derives a novel likelihood evaluator of the probability distribution from the loss function of LASSO, then samples from the high-dimensional distribution using stochastic Langevin dynamics with derivatives of the logarithm likelihood and Metropolis–Hastings sampling. In addition, new samples in low-dimensional measuring spaces can be regenerated using the sampled high-dimensional vectors and the dictionary. Extensive experiments have been conducted to evaluate the proposed algorithm using real-world datasets. The performance comparisons on three real-world applications demonstrate the superior performance of SpHMC beyond baseline methods.

PDF Details

IJCAI Conference 2018 Conference Paper

De-biasing Covariance-Regularized Discriminant Analysis

Haoyi Xiong
Wei Cheng
Yanjie Fu
Wenqing Hu
Jiang Bian
Zhishan Guo

Fisher's Linear Discriminant Analysis (FLD) is a well-known technique for linear classification, feature extraction and dimension reduction. The empirical FLD relies on two key estimations from the data -- the mean vector for each class and the (inverse) covariance matrix. To improve the accuracy of FLD under the High Dimension Low Sample Size (HDLSS) settings, Covariance-Regularized FLD (CRLD) has been proposed to use shrunken covariance estimators, such as Graphical Lasso, to strike a balance between biases and variances. Though CRLD could obtain better classification accuracy, it usually incurs bias and converges to the optimal result with a slower asymptotic rate. Inspired by the recent progress in de-biased Lasso, we propose a novel FLD classifier, DBLD, which improves classification accuracy of CRLD through de-biasing. Theoretical analysis shows that DBLD possesses better asymptotic properties than CRLD. We conduct experiments on both synthetic datasets and real application datasets to confirm the correctness of our theoretical analysis and demonstrate the superiority of DBLD over classical FLD, CRLD and other downstream competitors under HDLSS settings.

PDF Details