Alert button
Picture for Long Wang

Long Wang

Alert button

Spatio-Temporal Anomaly Detection with Graph Networks for Data Quality Monitoring of the Hadron Calorimeter

Nov 07, 2023
Mulugeta Weldezgina Asres, Christian Walter Omlin, Long Wang, David Yu, Pavel Parygin, Jay Dittmann, Georgia Karapostoli, Markus Seidel, Rosamaria Venditti, Luka Lambrecht, Emanuele Usai, Muhammad Ahmad, Javier Fernandez Menendez, Kaori Maeshima, the CMS-HCAL Collaboration

The compact muon solenoid (CMS) experiment is a general-purpose detector for high-energy collision at the large hadron collider (LHC) at CERN. It employs an online data quality monitoring (DQM) system to promptly spot and diagnose particle data acquisition problems to avoid data quality loss. In this study, we present semi-supervised spatio-temporal anomaly detection (AD) monitoring for the physics particle reading channels of the hadronic calorimeter (HCAL) of the CMS using three-dimensional digi-occupancy map data of the DQM. We propose the GraphSTAD system, which employs convolutional and graph neural networks to learn local spatial characteristics induced by particles traversing the detector, and global behavior owing to shared backend circuit connections and housing boxes of the channels, respectively. Recurrent neural networks capture the temporal evolution of the extracted spatial features. We have validated the accuracy of the proposed AD system in capturing diverse channel fault types using the LHC Run-2 collision data sets. The GraphSTAD system has achieved production-level accuracy and is being integrated into the CMS core production system--for real-time monitoring of the HCAL. We have also provided a quantitative performance comparison with alternative benchmark models to demonstrate the promising leverage of the presented system.

* 23 pages, 15 figures, 3 tables 
Viaarxiv icon

CCAE: A Corpus of Chinese-based Asian Englishes

Oct 09, 2023
Yang Liu, Melissa Xiaohui Qin, Long Wang, Chao Huang

Language models have been foundations in various scenarios of NLP applications, but it has not been well applied in language variety studies, even for the most popular language like English. This paper represents one of the few initial efforts to utilize the NLP technology in the paradigm of World Englishes, specifically in creating a multi-variety corpus for studying Asian Englishes. We present an overview of the CCAE -- Corpus of Chinese-based Asian English, a suite of corpora comprising six Chinese-based Asian English varieties. It is based on 340 million tokens in 448 thousand web documents from six regions. The ontology of data would make the corpus a helpful resource with enormous research potential for Asian Englishes (especially for Chinese Englishes for which there has not been a publicly accessible corpus yet so far) and an ideal source for variety-specific language modeling and downstream tasks, thus setting the stage for NLP-based World Englishes studies. And preliminary experiments on this corpus reveal the practical value of CCAE. Finally, we make CCAE available at \href{https://huggingface.co/datasets/CCAE/CCAE-Corpus}{this https URL}.

* NLPCC'2023 (12 pages, 3 figures, 4 charts) 
Viaarxiv icon

Long-term Visual Localization with Mobile Sensors

Apr 16, 2023
Shen Yan, Yu Liu, Long Wang, Zehong Shen, Zhen Peng, Haomin Liu, Maojun Zhang, Guofeng Zhang, Xiaowei Zhou

Figure 1 for Long-term Visual Localization with Mobile Sensors
Figure 2 for Long-term Visual Localization with Mobile Sensors
Figure 3 for Long-term Visual Localization with Mobile Sensors
Figure 4 for Long-term Visual Localization with Mobile Sensors

Despite the remarkable advances in image matching and pose estimation, image-based localization of a camera in a temporally-varying outdoor environment is still a challenging problem due to huge appearance disparity between query and reference images caused by illumination, seasonal and structural changes. In this work, we propose to leverage additional sensors on a mobile phone, mainly GPS, compass, and gravity sensor, to solve this challenging problem. We show that these mobile sensors provide decent initial poses and effective constraints to reduce the searching space in image matching and final pose estimation. With the initial pose, we are also able to devise a direct 2D-3D matching network to efficiently establish 2D-3D correspondences instead of tedious 2D-2D matching in existing systems. As no public dataset exists for the studied problem, we collect a new dataset that provides a variety of mobile sensor data and significant scene appearance variations, and develop a system to acquire ground-truth poses for query images. We benchmark our method as well as several state-of-the-art baselines and demonstrate the effectiveness of the proposed approach. The code and dataset will be released publicly.

Viaarxiv icon

A Redundancy Resolution Method for Free-Floating Underwater Manipulation

Feb 28, 2023
Justin L. Sitler, Long Wang

Figure 1 for A Redundancy Resolution Method for Free-Floating Underwater Manipulation
Figure 2 for A Redundancy Resolution Method for Free-Floating Underwater Manipulation
Figure 3 for A Redundancy Resolution Method for Free-Floating Underwater Manipulation
Figure 4 for A Redundancy Resolution Method for Free-Floating Underwater Manipulation

Underwater manipulation with free-floating autonomous underwater vehicles (AUVs) is an under-explored research area that this paper addresses. The open-source mechanical, electrical, and software designs of an AUV and continuum manipulator system are provided as a platform for performing this research. The underwater robot system has high degrees of freedom including the vehicle body motion and the manipulator joints. Therefore, when performing a manipulation task, the robot has many different potential trajectories which satisfy the task constraints, and this kinematic redundancy needs to be resolved. This paper provides a method for solving the redundancy problem. The relevant kinematic models are derived in order to build an algorithm to calculate desired joint velocities in real time. Different methods to optimize the algorithm for specific tasks are proposed, including a basic weighting method and a gradient projection method to optimize a user-defined objective function. Both simulation and experimental results are analyzed to assess the performance of this algorithm.

* 8 pages, submitted to IEEE RA-L, under review 
Viaarxiv icon

Design Project of an Open-Source, Low-Cost, and Lightweight Robotic Manipulator for High School Students

Feb 21, 2023
Isabella Huang, Qianwen Zhao, Maxine Fontaine, Long Wang

Figure 1 for Design Project of an Open-Source, Low-Cost, and Lightweight Robotic Manipulator for High School Students
Figure 2 for Design Project of an Open-Source, Low-Cost, and Lightweight Robotic Manipulator for High School Students
Figure 3 for Design Project of an Open-Source, Low-Cost, and Lightweight Robotic Manipulator for High School Students
Figure 4 for Design Project of an Open-Source, Low-Cost, and Lightweight Robotic Manipulator for High School Students

In recent years, there is an increasing interest in high school robotics extracurriculars such as robotics clubs and robotics competitions. The growing demand is a result of more ubiquitous open-source software and affordable off-the-shelf hardware kits, which significantly help lower the barrier for entry-level robotics hobbyists. In this project, we present an open-source, low-cost, and lightweight robotic manipulator designed and developed by a high school researcher under the guidance of a university faculty and a Ph.D. student. We believe the presented project is suitable for high school robotics research and educational activities. Our open-source package consists of mechanical design models, mechatronics specifications, and software program source codes. The mechanical design models include CAD (Computer Aided Design) files that are ready for prototyping (3D printing technology) and serve as an assembly guide accommodated with a complete bill of materials. Electrical wiring diagrams and low-level controllers are documented in detail as part of the open-source software package. The educational objective of this project is to enable high school student teams to replicate and build a robotic manipulator. The engineering experience that high school students acquire in the proposed project is full-stack, including mechanical design, mechatronics, and programming. The project significantly enriches their hands-on engineering experience in a project-based environment. Throughout this project, we discovered that the high school researcher was able to apply multidisciplinary knowledge from K-12 STEM courses to build the robotic manipulator. The researcher was able to go through a system engineering design and development process and obtain skills to use professional engineering tools including SolidWorks and Arduino microcontrollers.

* Submitted to ASEE Zone 1 Conference, under review 
Viaarxiv icon

A Lightweight Modular Continuum Manipulator with IMU-based Force Estimation

Nov 21, 2022
Guoqing Zhang, Qianwen Zhao, Long Wang

Figure 1 for A Lightweight Modular Continuum Manipulator with IMU-based Force Estimation
Figure 2 for A Lightweight Modular Continuum Manipulator with IMU-based Force Estimation
Figure 3 for A Lightweight Modular Continuum Manipulator with IMU-based Force Estimation
Figure 4 for A Lightweight Modular Continuum Manipulator with IMU-based Force Estimation

Most aerial manipulators use serial rigid-link designs, which results in large forces when initiating contacts during manipulation and could cause flight stability difficulty. This limitation could potentially be improved by the compliance of continuum manipulators. To achieve this goal, we present the novel design of a compact, lightweight, and modular cable-driven continuum manipulator for aerial drones. We then derive a complete modeling framework for its kinematics, statics, and stiffness (compliance). The modeling framework can guide the control and design problems to integrate the manipulator to aerial drones. In addition, thanks to the derived stiffness (compliance) matrix, and using a low-cost IMU sensor to capture deformation angles, we present a simple method to estimate manipulation force at the tip of the manipulator. We report preliminary experimental validations of the hardware prototype, providing insights on its manipulation feasibility. We also report preliminary results of the IMU-based force estimation method.

* 12 pages, submitted to ASME Journal of Mechanisms and Robotics 2022, under review. arXiv admin note: substantial text overlap with arXiv:2206.06246 
Viaarxiv icon

Shape Estimation of Continuum Robots via Modal Parameterization and Dual Extended Kalman Filter

Oct 16, 2022
Guoqing Zhang, Long Wang

Figure 1 for Shape Estimation of Continuum Robots via Modal Parameterization and Dual Extended Kalman Filter
Figure 2 for Shape Estimation of Continuum Robots via Modal Parameterization and Dual Extended Kalman Filter
Figure 3 for Shape Estimation of Continuum Robots via Modal Parameterization and Dual Extended Kalman Filter
Figure 4 for Shape Estimation of Continuum Robots via Modal Parameterization and Dual Extended Kalman Filter

The equilibrium shape of a continuum robot is resulted from both its internal actuation and the external physical interaction with a surrounding environment. A fast and accurate shape estimation method (i) can be used as a feedback to compensate for more accurate motion; and (ii) can reveal rich information about physical interactions (e.g. instrument-anatomy contacts / forces during a surgery). From a prior work that demonstrated an offline calibration of continuum robots, we adopt its shape modal representation and error propagation models that include identification Jacobians. In this work, we present an iterative observer approach to enable online shape estimation. We develop a dual Extended Kalman Filter (EKF) to estimate both the robot state and the shape modal parameters. The dual EKF provides robust estimation on (i) the configuration space variables that are controllable and driven by internal actuation; and (ii) the modal coefficients representing homotopies of shape families that are governed by the physical interactions with the environment. We report results from simulation studies in this work, and plan to investigate methods in the future to use the proposed approach for predicting physical interactions.

* 8 pages, submitted to 2023 American Control Conference (ACC), under review 
Viaarxiv icon

A Modular Continuum Manipulator for Aerial Manipulation and Perching

Jun 13, 2022
Qianwen Zhao, Guoqing Zhang, Hamidreza Jafarnejadsani, Long Wang

Figure 1 for A Modular Continuum Manipulator for Aerial Manipulation and Perching
Figure 2 for A Modular Continuum Manipulator for Aerial Manipulation and Perching
Figure 3 for A Modular Continuum Manipulator for Aerial Manipulation and Perching
Figure 4 for A Modular Continuum Manipulator for Aerial Manipulation and Perching

Most aerial manipulators use serial rigid-link designs, which results in large forces when initiating contacts during manipulation and could cause flight stability difficulty. This limitation could potentially be improved by the compliance of continuum manipulators. To achieve this goal, we present the novel design of a compact, lightweight, and modular cable-driven continuum manipulator for aerial drones. We then derive a complete modeling framework for its kinematics, statics, and stiffness (compliance). The framework is essential for integrating the manipulator to aerial drones. Finally, we report preliminary experimental validations of the hardware prototype, providing insights on its manipulation feasibility. Future work includes the integration and test of the proposed continuum manipulator with aerial drones.

* 10 pages, accepted for International Design Engineering Technical Conferences & Computers and Information in Engineering Conference (IDETC-CIE 2022). 46th Mechanisms and Robotics Conference (MR) 
Viaarxiv icon

BUDA-SAGE with self-supervised denoising enables fast, distortion-free, high-resolution T2, T2*, para- and dia-magnetic susceptibility mapping

Sep 09, 2021
Zijing Zhang, Long Wang, Jaejin Cho, Congyu Liao, Hyeong-Geol Shin, Xiaozhi Cao, Jongho Lee, Jinmin Xu, Tao Zhang, Huihui Ye, Kawin Setsompop, Huafeng Liu, Berkin Bilgic

Figure 1 for BUDA-SAGE with self-supervised denoising enables fast, distortion-free, high-resolution T2, T2*, para- and dia-magnetic susceptibility mapping
Figure 2 for BUDA-SAGE with self-supervised denoising enables fast, distortion-free, high-resolution T2, T2*, para- and dia-magnetic susceptibility mapping
Figure 3 for BUDA-SAGE with self-supervised denoising enables fast, distortion-free, high-resolution T2, T2*, para- and dia-magnetic susceptibility mapping
Figure 4 for BUDA-SAGE with self-supervised denoising enables fast, distortion-free, high-resolution T2, T2*, para- and dia-magnetic susceptibility mapping

To rapidly obtain high resolution T2, T2* and quantitative susceptibility mapping (QSM) source separation maps with whole-brain coverage and high geometric fidelity. We propose Blip Up-Down Acquisition for Spin And Gradient Echo imaging (BUDA-SAGE), an efficient echo-planar imaging (EPI) sequence for quantitative mapping. The acquisition includes multiple T2*-, T2'- and T2-weighted contrasts. We alternate the phase-encoding polarities across the interleaved shots in this multi-shot navigator-free acquisition. A field map estimated from interim reconstructions was incorporated into the joint multi-shot EPI reconstruction with a structured low rank constraint to eliminate geometric distortion. A self-supervised MR-Self2Self (MR-S2S) neural network (NN) was utilized to perform denoising after BUDA reconstruction to boost SNR. Employing Slider encoding allowed us to reach 1 mm isotropic resolution by performing super-resolution reconstruction on BUDA-SAGE volumes acquired with 2 mm slice thickness. Quantitative T2 and T2* maps were obtained using Bloch dictionary matching on the reconstructed echoes. QSM was estimated using nonlinear dipole inversion (NDI) on the gradient echoes. Starting from the estimated R2 and R2* maps, R2' information was derived and used in source separation QSM reconstruction, which provided additional para- and dia-magnetic susceptibility maps. In vivo results demonstrate the ability of BUDA-SAGE to provide whole-brain, distortion-free, high-resolution multi-contrast images and quantitative T2 and T2* maps, as well as yielding para- and dia-magnetic susceptibility maps. Derived quantitative maps showed comparable values to conventional mapping methods in phantom and in vivo measurements. BUDA-SAGE acquisition with self-supervised denoising and Slider encoding enabled rapid, distortion-free, whole-brain T2, T2* mapping at 1 mm3 isotropic resolution in 90 seconds.

Viaarxiv icon