JUSTC

2024-1 Contents

2024, 54(1): 1-2.

Article Views:13 HTML (13) Full article PDF

Abstract:

2024-1 Abstract

2024, 54(1): 1-2.

Article Views:13 HTML (13) Full article PDF

Abstract:

BEV-radar: bidirectional radar-camera fusion for 3D object detection

Yuan Zhao, Lu Zhang, Jiajun Deng, Yanyong Zhang

2024, 54(1): 0101. doi: 10.52396/JUSTC-2023-0006

Article Views:611 HTML (611) Full article PDF

Abstract:
Exploring millimeter wave radar data as complementary to RGB images for ameliorating 3D object detection has become an emerging trend for autonomous driving systems. However, existing radar-camera fusion methods are highly dependent on the prior camera detection results, rendering the overall performance unsatisfactory. In this paper, we propose a bidirectional fusion scheme in the bird-eye view (BEV-radar), which is independent of prior camera detection results. Leveraging features from both modalities, our method designs a bidirectional attention-based fusion strategy. Specifically, following BEV-based 3D detection methods, our method engages a bidirectional transformer to embed information from both modalities and enforces the local spatial relationship according to subsequent convolution blocks. After embedding the features, the BEV features are decoded in the 3D object prediction head. We evaluate our method on the nuScenes dataset, achieving 48.2 mAP and 57.6 NDS. The result shows considerable improvements compared to the camera-only baseline, especially in terms of velocity prediction. The code is available at https://github.com/Etah0409/BEV-Radar.

QGAE: an end-to-end answer-agnostic question generation model for generating question-answer pairs

Linfeng Li, Licheng Zhang, Chiwei Zhu, Zhendong Mao

2024, 54(1): 0102. doi: 10.52396/JUSTC-2023-0002

Article Views:319 HTML (319) Full article PDF

Abstract:
Question generation aims to generate meaningful and fluent questions, which can address the lack of a question-answer type annotated corpus by augmenting the available data. Using unannotated text with optional answers as input contents, question generation can be divided into two types based on whether answers are provided: answer-aware and answer-agnostic. While generating questions by providing answers is challenging, generating high-quality questions without providing answers is even more difficult for both humans and machines. To address this issue, we proposed a novel end-to-end model called question generation with answer extractor (QGAE), which is able to transform answer-agnostic question generation into answer-aware question generation by directly extracting candidate answers. This approach effectively utilizes unlabeled data for generating high-quality question-answer pairs, and its end-to-end design makes it more convenient than a multi-stage method that requires at least two pre-trained models. Moreover, our model achieves better average scores and greater diversity. Our experiments show that QGAE achieves significant improvements in generating question-answer pairs, making it a promising approach for question generation.

Robustness benchmark for unsupervised anomaly detection models

Pei Wang, Wei Zhai, Yang Cao

2024, 54(1): 0103. doi: 10.52396/JUSTC-2022-0165

Article Views:289 HTML (289) Full article PDF

Abstract:
Due to the complexity and diversity of production environments, it is essential to understand the robustness of unsupervised anomaly detection models to common corruptions. To explore this issue systematically, we propose a dataset named MVTec-C to evaluate the robustness of unsupervised anomaly detection models. Based on this dataset, we explore the robustness of approaches in five paradigms, namely, reconstruction-based, representation similarity-based, normalizing flow-based, self-supervised representation learning-based, and knowledge distillation-based paradigms. Furthermore, we explore the impact of different modules within two optimal methods on robustness and accuracy. This includes the multi-scale features, the neighborhood size, and the sampling ratio in the PatchCore method, as well as the multi-scale features, the MMF module, the OCE module, and the multi-scale distillation in the Reverse Distillation method. Finally, we propose a feature alignment module (FAM) to reduce the feature drift caused by corruptions and combine PatchCore and the FAM to obtain a model with both high performance and high accuracy. We hope this work will serve as an evaluation method and provide experience in building robust anomaly detection models in the future.

Efficient secure aggregation for privacy-preserving federated learning based on secret sharing

Xuan Jin, Yuanzhi Yao, Nenghai Yu

2024, 54(1): 0104. doi: 10.52396/JUSTC-2022-0116

Article Views:479 HTML (479) Full article PDF

Abstract:
Federated learning allows multiple mobile participants to jointly train a global model without revealing their local private data. Communication-computation cost and privacy preservation are key fundamental issues in federated learning. Existing secret sharing-based secure aggregation mechanisms for federated learning still suffer from significant additional costs, insufficient privacy preservation, and vulnerability to participant dropouts. In this paper, we aim to solve these issues by introducing flexible and effective secret sharing mechanisms into federated learning. We propose two novel privacy-preserving federated learning schemes: federated learning based on one-way secret sharing (FLOSS) and federated learning based on multi-shot secret sharing (FLMSS). Compared with the state-of-the-art works, FLOSS enables high privacy preservation while significantly reducing the communication cost by dynamically designing secretly shared content and objects. Meanwhile, FLMSS further reduces the additional cost and has the ability to efficiently enhance the robustness of participant dropouts in federated learning. Foremost, FLMSS achieves a satisfactory tradeoff between privacy preservation and communication-computation cost. Security analysis and performance evaluations on real datasets demonstrate the superiority of our proposed schemes in terms of model accuracy, privacy preservation, and cost reduction.

Dual-modality smart shoes for quantitative assessment of hemiplegic patients’ lower limb muscle strength

Huajun Long, Jie Li, Rui Li, Xinfeng Liu, Jingyuan Cheng

2024, 54(1): 0105. doi: 10.52396/JUSTC-2022-0161

Article Views:119 HTML (119) Full article PDF

Abstract:
Stroke can lead to the impaired motor function in patients’ lower limbs and hemiplegia. Accurate assessment of lower limb motor ability is important for diagnosis and rehabilitation. To digitalize such assessments so that each test can be traced back at any time and subjectivity can be avoided, we test how dual-modality smart shoes equipped with pressure-sensitive insoles and inertial measurement units can be used for this purpose. A 5 m walking test protocol, including the left and right turns, is designed. The data are collected from 23 patients and 17 healthy subjects. For the lower limbs’ motor ability, the tests are performed by two physicians and assessed using the five-grade Medical Research Council scale for muscle examination. The average of two physicians’ scores for the same patient is used as the ground truth. Using the feature set we developed, 100% accuracy is achieved in classifying the patients and healthy subjects. For patients’ muscle strength, a mean absolute error of 0.143 and a maximum error of 0.395 are achieved using our feature set and the regression method; these values are closer to the ground truth than the scores from each physician (mean absolute error: 0.217, maximum error: 0.5). We thus validate the possibility of using such smart shoes to objectively and accurately evaluate the muscle strength of the lower limbs of stroke patients.

Constitutive modeling of the magnetic-dependent nonlinear dynamic behavior of isotropic magnetorheological elastomers

Bochao Wang, Yan Li, Haoming Pang, Zhenbang Xu, Xinglong Gong

2024, 54(1): 0106. doi: 10.52396/JUSTC-2022-0173

Article Views:301 HTML (301) Full article PDF

Abstract:
Isotropic magnetorheological elastomers (MREs) are smart materials fabricated by embedding magnetizable particles randomly into a polymer matrix. Under a magnetic field, its modulus changes rapidly, reversibly, and continuously, offering wide application potential in the vibration control area. Experimental observations show that there is a strong frequency, strain amplitude, and magnetic dependence of the dynamic behavior of isotropic MRE. Although important for potential applications, the magnetic-dependent nonlinear dynamic behavior of isotropic MRE has received little theoretical attention. To accurately evaluate the dynamic performance of isotropic MRE and to guide the design of isotropic MRE-based products, a new constitutive model based on continuum mechanics theory is developed to depict the magnetic-dependent nonlinear dynamic behavior of isotropic MRE. Subsequently, the numerical implementation algorithm is developed, and the prediction ability of the model is examined. The model provides a deeper understanding of the underlying mechanics of the magnetic-dependent nonlinear viscoelastic behavior of isotropic MRE. Furthermore, the model can be utilized to predict the magnetomechanical coupling behavior of isotropic MRE and therefore serves as a useful platform to promote the design and application of isotropic MRE-based devices.

2024 Vol. 54, No. 1

STAY CONNECTED

News

JUSTC Culture

Authors

Browse

Contact Us

About