Search

Your search keyword '"Chen, Weijia"' showing total 516 results
Start Over Author "Chen, Weijia"
516 results on '"Chen, Weijia"'

1. Artificial Intelligence–Based Multimodal Risk Assessment Model for Surgical Site Infection (AMRAMS): Development and Validation Study

Author

Chen, Weijia, Lu, Zhijun, You, Lijue, Zhou, Lingling, Xu, Jie, and Chen, Ken

Subjects
Computer applications to medicine. Medical informatics, R858-859.7
Abstract

BackgroundSurgical site infection (SSI) is one of the most common types of health care–associated infections. It increases mortality, prolongs hospital length of stay, and raises health care costs. Many institutions developed risk assessment models for SSI to help surgeons preoperatively identify high-risk patients and guide clinical intervention. However, most of these models had low accuracies. ObjectiveWe aimed to provide a solution in the form of an Artificial intelligence–based Multimodal Risk Assessment Model for Surgical site infection (AMRAMS) for inpatients undergoing operations, using routinely collected clinical data. We internally and externally validated the discriminations of the models, which combined various machine learning and natural language processing techniques, and compared them with the National Nosocomial Infections Surveillance (NNIS) risk index. MethodsWe retrieved inpatient records between January 1, 2014, and June 30, 2019, from the electronic medical record (EMR) system of Rui Jin Hospital, Luwan Branch, Shanghai, China. We used data from before July 1, 2018, as the development set for internal validation and the remaining data as the test set for external validation. We included patient demographics, preoperative lab results, and free-text preoperative notes as our features. We used word-embedding techniques to encode text information, and we trained the LASSO (least absolute shrinkage and selection operator) model, random forest model, gradient boosting decision tree (GBDT) model, convolutional neural network (CNN) model, and self-attention network model using the combined data. Surgeons manually scored the NNIS risk index values. ResultsFor internal bootstrapping validation, CNN yielded the highest mean area under the receiver operating characteristic curve (AUROC) of 0.889 (95% CI 0.886-0.892), and the paired-sample t test revealed statistically significant advantages as compared with other models (P

Published
2020
Full Text
View/download PDF

2. LPFormer: LiDAR Pose Estimation Transformer with Multi-Task Network

Author

Ye, Dongqiangzi, Xie, Yufei, Chen, Weijia, Zhou, Zixiang, Ge, Lingting, and Foroosh, Hassan

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Due to the difficulty of acquiring large-scale 3D human keypoint annotation, previous methods for 3D human pose estimation (HPE) have often relied on 2D image features and sequential 2D annotations. Furthermore, the training of these networks typically assumes the prediction of a human bounding box and the accurate alignment of 3D point clouds with 2D images, making direct application in real-world scenarios challenging. In this paper, we present the 1st framework for end-to-end 3D human pose estimation, named LPFormer, which uses only LiDAR as its input along with its corresponding 3D annotations. LPFormer consists of two stages: firstly, it identifies the human bounding box and extracts multi-level feature representations, and secondly, it utilizes a transformer-based network to predict human keypoints based on these features. Our method demonstrates that 3D HPE can be seamlessly integrated into a strong LiDAR perception network and benefit from the features extracted by the network. Experimental results on the Waymo Open Dataset demonstrate the state-of-the-art performance, and improvements even compared to previous multi-modal solutions., Comment: ICRA 2024. Top solution for the Waymo Open Dataset Challenges 2023 - Pose Estimation. CVPR 2023 Workshop on Autonomous Driving

Published
2023

3. LiDARFormer: A Unified Transformer-based Multi-task Network for LiDAR Perception

Author

Zhou, Zixiang, Ye, Dongqiangzi, Chen, Weijia, Xie, Yufei, Wang, Yu, Wang, Panqu, and Foroosh, Hassan

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

There is a recent trend in the LiDAR perception field towards unifying multiple tasks in a single strong network with improved performance, as opposed to using separate networks for each task. In this paper, we introduce a new LiDAR multi-task learning paradigm based on the transformer. The proposed LiDARFormer utilizes cross-space global contextual feature information and exploits cross-task synergy to boost the performance of LiDAR perception tasks across multiple large-scale datasets and benchmarks. Our novel transformer-based framework includes a cross-space transformer module that learns attentive features between the 2D dense Bird's Eye View (BEV) and 3D sparse voxel feature maps. Additionally, we propose a transformer decoder for the segmentation task to dynamically adjust the learned features by leveraging the categorical feature representations. Furthermore, we combine the segmentation and detection features in a shared transformer decoder with cross-task attention layers to enhance and integrate the object-level and class-level features. LiDARFormer is evaluated on the large-scale nuScenes and the Waymo Open datasets for both 3D detection and semantic segmentation tasks, and it outperforms all previously published methods on both tasks. Notably, LiDARFormer achieves the state-of-the-art performance of 76.4% L2 mAPH and 74.3% NDS on the challenging Waymo and nuScenes detection benchmarks for a single model LiDAR-only method., Comment: ICRA 2024

Published
2023

4. An Empirical Study of the Sunset Employment Needs of Ageing Groups in Mianyang City, Sichuan Province, China, Based on Maslow’s Hierarchy of Needs Theory

Author

Chen, Weijia, Qiu, Guohong, Wang, Jiang, Zhou, Zhenquan, Zhang, Jiaojiao, Qi, Lingling, Striełkowski, Wadim, Editor-in-Chief, Black, Jessica M., Series Editor, Butterfield, Stephen A., Series Editor, Chang, Chi-Cheng, Series Editor, Cheng, Jiuqing, Series Editor, Dumanig, Francisco Perlas, Series Editor, Al-Mabuk, Radhi, Series Editor, Scheper-Hughes, Nancy, Series Editor, Urban, Mathias, Series Editor, Webb, Stephen, Series Editor, Sedon, Mohd Fauzi bin, editor, Khan, Intakhab Alam, editor, Birkök, Mehmet Cüneyt, editor, and Chan, KinSun, editor

Published
2024
Full Text
View/download PDF

5. Research on Challenges and Optimization Suggestions for Digital Transformation of Education in China

Author

Cai, Defa, Chen, Weijia, Striełkowski, Wadim, Editor-in-Chief, Black, Jessica M., Series Editor, Butterfield, Stephen A., Series Editor, Chang, Chi-Cheng, Series Editor, Cheng, Jiuqing, Series Editor, Dumanig, Francisco Perlas, Series Editor, Al-Mabuk, Radhi, Series Editor, Scheper-Hughes, Nancy, Series Editor, Urban, Mathias, Series Editor, Webb, Stephen, Series Editor, Khan, Intakhab Alam, editor, Halili, Siti Hajar, editor, Balakrishnan, Vishalache, editor, and Abd. Rauf, Rose Amnah, editor

Published
2024
Full Text
View/download PDF

7. LidarMultiNet: Towards a Unified Multi-Task Network for LiDAR Perception

Author

Ye, Dongqiangzi, Zhou, Zixiang, Chen, Weijia, Xie, Yufei, Wang, Yu, Wang, Panqu, and Foroosh, Hassan

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

LiDAR-based 3D object detection, semantic segmentation, and panoptic segmentation are usually implemented in specialized networks with distinctive architectures that are difficult to adapt to each other. This paper presents LidarMultiNet, a LiDAR-based multi-task network that unifies these three major LiDAR perception tasks. Among its many benefits, a multi-task network can reduce the overall cost by sharing weights and computation among multiple tasks. However, it typically underperforms compared to independently combined single-task models. The proposed LidarMultiNet aims to bridge the performance gap between the multi-task network and multiple single-task networks. At the core of LidarMultiNet is a strong 3D voxel-based encoder-decoder architecture with a Global Context Pooling (GCP) module extracting global contextual features from a LiDAR frame. Task-specific heads are added on top of the network to perform the three LiDAR perception tasks. More tasks can be implemented simply by adding new task-specific heads while introducing little additional cost. A second stage is also proposed to refine the first-stage segmentation and generate accurate panoptic segmentation results. LidarMultiNet is extensively tested on both Waymo Open Dataset and nuScenes dataset, demonstrating for the first time that major LiDAR perception tasks can be unified in a single strong network that is trained end-to-end and achieves state-of-the-art performance. Notably, LidarMultiNet reaches the official 1st place in the Waymo Open Dataset 3D semantic segmentation challenge 2022 with the highest mIoU and the best accuracy for most of the 22 classes on the test set, using only LiDAR points as input. It also sets the new state-of-the-art for a single model on the Waymo 3D object detection benchmark and three nuScenes benchmarks., Comment: Accepted to AAAI 2023 (Oral). Full-length paper extending our previous technical report of the 1st place solution of the 2022 Waymo Open Dataset 3D Semantic Segmentation challenge, including evaluations on 5 major benchmarks. arXiv admin note: text overlap with arXiv:2206.11428

Published
2022

8. LidarMultiNet: Unifying LiDAR Semantic Segmentation, 3D Object Detection, and Panoptic Segmentation in a Single Multi-task Network

Author

Ye, Dongqiangzi, Chen, Weijia, Zhou, Zixiang, Xie, Yufei, Wang, Yu, Wang, Panqu, and Foroosh, Hassan

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

This technical report presents the 1st place winning solution for the Waymo Open Dataset 3D semantic segmentation challenge 2022. Our network, termed LidarMultiNet, unifies the major LiDAR perception tasks such as 3D semantic segmentation, object detection, and panoptic segmentation in a single framework. At the core of LidarMultiNet is a strong 3D voxel-based encoder-decoder network with a novel Global Context Pooling (GCP) module extracting global contextual features from a LiDAR frame to complement its local features. An optional second stage is proposed to refine the first-stage segmentation or generate accurate panoptic segmentation results. Our solution achieves a mIoU of 71.13 and is the best for most of the 22 classes on the Waymo 3D semantic segmentation test set, outperforming all the other 3D semantic segmentation methods on the official leaderboard. We demonstrate for the first time that major LiDAR perception tasks can be unified in a single strong network that can be trained end-to-end., Comment: Official 1st Place Solution for the Waymo Open Dataset Challenges 2022 - 3D Semantic Segmentation. Official leaderboard: https://waymo.com/open/challenges/2022/3d-semantic-segmentation/. CVPR 2022 Workshop on Autonomous Driving: http://cvpr2022.wad.vision/

Published
2022

23. Point Set Voting for Partial Point Cloud Analysis

Author

Zhang, Junming, Chen, Weijia, Wang, Yuping, Vasudevan, Ram, and Johnson-Roberson, Matthew

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Robotics
Abstract

The continual improvement of 3D sensors has driven the development of algorithms to perform point cloud analysis. In fact, techniques for point cloud classification and segmentation have in recent years achieved incredible performance driven in part by leveraging large synthetic datasets. Unfortunately these same state-of-the-art approaches perform poorly when applied to incomplete point clouds. This limitation of existing algorithms is particularly concerning since point clouds generated by 3D sensors in the real world are usually incomplete due to perspective view or occlusion by other objects. This paper proposes a general model for partial point clouds analysis wherein the latent feature encoding a complete point clouds is inferred by applying a local point set voting strategy. In particular, each local point set constructs a vote that corresponds to a distribution in the latent space, and the optimal latent feature is the one with the highest probability. This approach ensures that any subsequent point cloud analysis is robust to partial observation while simultaneously guaranteeing that the proposed model is able to output multiple possible results. This paper illustrates that this proposed method achieves state-of-the-art performance on shape classification, part segmentation and point cloud completion., Comment: IEEE Robotics and Automation Letters (RA-L)

Published
2020
Full Text
View/download PDF

24. AliMe KBQA: Question Answering over Structured Knowledge for E-commerce Customer Service

Author

Li, Feng-Lin, Chen, Weijia, Huang, Qi, and Guo, Yikun

Subjects
Computer Science - Artificial Intelligence, Computer Science - Computation and Language
Abstract

With the rise of knowledge graph (KG), question answering over knowledge base (KBQA) has attracted increasing attention in recent years. Despite much research has been conducted on this topic, it is still challenging to apply KBQA technology in industry because business knowledge and real-world questions can be rather complicated. In this paper, we present AliMe-KBQA, a bold attempt to apply KBQA in the E-commerce customer service field. To handle real knowledge and questions, we extend the classic "subject-predicate-object (SPO)" structure with property hierarchy, key-value structure and compound value type (CVT), and enhance traditional KBQA with constraints recognition and reasoning ability. We launch AliMe-KBQA in the Marketing Promotion scenario for merchants during the "Double 11" period in 2018 and other such promotional events afterwards. Online results suggest that AliMe-KBQA is not only able to gain better resolution and improve customer satisfaction, but also becomes the preferred knowledge management method by business knowledge staffs since it offers a more convenient and efficient management experience.

Published
2019

36. Deep Reinforcement Learning for Multi-Resource Multi-Machine Job Scheduling

Author

Chen, Weijia, Xu, Yuedong, and Wu, Xiaofeng

Subjects
Computer Science - Distributed, Parallel, and Cluster Computing, Computer Science - Learning, Computer Science - Performance
Abstract

Minimizing job scheduling time is a fundamental issue in data center networks that has been extensively studied in recent years. The incoming jobs require different CPU and memory units, and span different number of time slots. The traditional solution is to design efficient heuristic algorithms with performance guarantee under certain assumptions. In this paper, we improve a recently proposed job scheduling algorithm using deep reinforcement learning and extend it to multiple server clusters. Our study reveals that deep reinforcement learning method has the potential to outperform traditional resource allocation algorithms in a variety of complicated environments.

Published
2017

40. How learners’ achievement goal motivation influences their metacognitive skills in online social annotations context?

Author

Niu, Xiaojie, Chen, Weijia, Li, Luyue, Zhang, Wenmei, Gao, Shurui, He, Chun, and Zhang, Jingjing

Subjects
*GOAL (Psychology), *ACHIEVEMENT motivation, *SOCIAL skills, *SOCIAL context, *ONLINE education, *SELF-regulated learning
Abstract

Online learning requires high self-regulated abilities facilitated by metacognitive skills. Achievement goal motivation impacts metacognition, but their relationship in online learning contexts lacks consensus. One of the components of achievement goal orientation is mastery goal orientation which focuses on learning and self-improvement. The other component, performance goal orientation, emphasises demonstrating competence. This quantitative study collected questionnaire and behavioural log data from 39 learners and examined the interplay between achievement goal motivation and metacognitive skills within an online social annotation environment. Findings revealed that mastery goal orientation positively correlated with metacognitive planning and regulation, while performance goal orientation was predominantly associated with metacognitive regulation. Neither goals significantly correlated with metacognitive monitoring. Cluster analysis indicated that ‘balanced achievers’ with higher performance goal orientation may play a pivotal role in promoting social cognition. These insights deepen understanding of motivating learners and creating effective online learning approaches by leveraging the influence of achievement goal motivation on metacognitive strategies. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

42. Network Pharmacology and Transcriptomics to Explore the Pharmacological Mechanisms of 20(S)-Protopanaxatriol in the Treatment of Depression.

Author

Guo, Xiangjuan, Su, Lili, Shi, Meiling, Sun, Li, Chen, Weijia, Geng, Jianan, Li, Jianming, Zong, Ying, He, Zhongmei, and Du, Rui

Subjects
TRANSCRIPTOMES, BRAIN-derived neurotrophic factor, GENE expression, TREATMENT effectiveness, PHARMACOLOGY
Abstract

Depression is one of the most common psychological disorders nowadays. Studies have shown that 20(S)-protopanaxatriol (PPT) can effectively improve depressive symptoms in mice. However, its mechanism needs to be further explored. In this study, we used an integrated approach combining network pharmacology and transcriptomics to explore the potential mechanisms of PPT for depression. First, the potential targets and pathways of PPT treatment of depression were screened through network pharmacology. Secondly, the BMKCloud platform was used to obtain brain tissue transcription data of chronic unpredictable mild stress (CUMS) model mice and screen PPT-altered differential expression genes (DEGs). Gene ontology (GO) analysis and the Kyoto Encyclopedia of Genes and Genomes (KEGG) analysis were performed using network pharmacology and transcriptomics. Finally, the above results were verified by molecular docking, Western blotting, and quantitative real-time polymerase chain reaction (qRT-PCR). In this study, we demonstrated that PPT improved depression-like behavior and brain histopathological changes in CUMS mice, downregulated nitric oxide (NO) and interleukin-6 (IL-6) levels, and elevated serum levels of 5-hydroxytryptamine (5-HT) and brain-derived neurotrophic factor (BDNF) after PPT treatment compared to the CUMS group. Eighty-seven potential targets and 350 DEGs were identified by network pharmacology and transcriptomics. Comprehensive analysis showed that transthyretin (TTR), klotho (KL), FOS, and the phosphatidylinositol 3-kinase–protein kinase B (PI3K-AKT) signaling pathway were closely associated with the therapeutic effects of PPT. Molecular docking results showed that PPT had a high affinity for PI3K, AKT, TTR, KL, and FOS targets. Gene and protein level results showed that PPT could increase the expression of PI3K, phosphorylation of PI3K (p-PI3K), AKT, phosphorylation of AKT (p-AKT), TTR, and KL and inhibit the expression level of FOS in the brain tissue of depressed mice. Our data suggest that PPT may achieve the treatment of depression by inhibiting the expression of FOS, enhancing the expression of TTR and KL, and modulating the PI3K-AKT signaling pathway. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

43. Analysis of the Distribution Pattern of Phenacoccus manihoti in China under Climate Change Based on the Biomod2 Model.

Author

Huang, Yumeng, Li, Tong, Chen, Weijia, Zhang, Yuan, Xu, Yanling, Guo, Tengda, Wang, Shuping, Liu, Jingyuan, and Qin, Yujia

Subjects
ECOLOGICAL niche, AGRICULTURAL productivity, MEALYBUGS, PLANT parasites, WAREHOUSES
Abstract

Simple Summary: The cassava mealybug (Phenacoccus manihoti) represents a significant quarantine pest affecting cassavas. This study seeks to elucidate the patterns of the suitable habitat and distribution centers of cassava mealybugs in China, as well as their dynamic ecological niche in invaded areas under the influence of climate change. Climate factors have primarily concentrated suitable habitats for cassava mealybugs in the southern regions of China, with minimal observed changes and a slight northward expansion. The dynamic ecological niche is also projected to expand slightly. Based on these predictions, relevant quarantine agencies can implement measures to prevent the introduction and spread of cassava mealybugs. The changing global climate has significantly impacted the spread of plant pests. The cassava mealybug (Phenacoccus manihoti) is among the most dangerous quarantine pests affecting cassavas worldwide, causing substantial losses in agricultural production and food security across several regions. Although China is currently free of the cassava mealybug, its proximity to affected countries and extensive trade with these regions necessitate a detailed understanding of the pest's distribution pattern and dynamic ecological niche changes. Using the Biomod2 model, we selected two historical climate scenarios and two future climate scenarios (SSP1-2.6 and SSP5-8.5) to investigate the distribution patterns, potential habitats, distribution centers, and dynamic ecological niches of cassava mealybugs in China. Key environmental variables influencing the distribution were identified, including bio4, bio8, bio12, bio18, and bio19. The potential habitat of cassava mealybugs is mainly located in several provinces in southern China. In the future, the suitable habitat is projected to expand slightly under the influence of climate change, maintaining the overall trend, but the distribution center of suitable areas will shift northward. Dynamic ecological niche prediction results indicate the potential for further expansion; however, the ecological niches may be unequal and dissimilar in the invaded areas. The predictions could serve as a valuable reference for early warning systems and management strategies to control the introduction of cassava mealybugs. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

44. Paeoniflorin alleviates depression by inhibiting the activation of NLRP3 inflammasome via promoting mitochondrial autophagy.

Author

SU, Lili, GUO, Pengli, GUO, Xiangjuan, HE, Zhongmei, ZHAO, Yan, ZONG, Ying, LI, Jianming, CHEN, Weijia, and DU, Rui

Abstract

Depression ranks among the most common neuropsychiatric disorders globally. Current studies examining the roles of inflammation and mitochondrial autophagy in the antidepressant efficacy of paeoniflorin (PF) are sparse. This study aimed to elucidate PF's antidepressant mechanism by promoting autophagy and inhibiting NLRP3 inflammasome activation using chronic unpredictable mild stimulation (CUMS)-induced C57BL/6 mouse models in vivo and corticosterone (CORT)-induced HT22 cell models in vitro. Results demonstrated that PF enhanced the viability of HT22 cells following CORT exposure, restored mitochondrial membrane potential (MMP), reduced reactive oxygen species accumulation, increased LC3 fluorescence intensity, and suppressed inflammatory cytokine secretion and inflammation activation. Additionally, PF ameliorated depressive behaviors induced by CUMS and improved damage in hippocampal neurons. It also reduced the expression of NLRP3, ASC, Caspase-1, IL-1β, and the assembly of the NLRP3 inflammasome. Moreover, PF upregulated the expression of autophagy-related proteins in the hippocampus, facilitating the clearance of damaged mitochondria and enhancing autophagy. The role of autophagy in PF's antidepressant effects was further confirmed through the use of the autophagy inhibitor 3-methyladenine (3-MA), which reduced the efficacy of PF. In conclusion, PF effectively improved depressive behaviors in CUMS-induced mice and reduced NLRP3-mediated inflammation both in vivo and in vitro , likely via the induction of autophagy. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results