Search

Your search keyword '"WANG Chenfei"' showing total 577 results
Start Over Author "WANG Chenfei"
577 results on '"WANG Chenfei"'

1. Regulation of high-fat diet-induced microglial metabolism by transient receptor potential vanilloid type 1

Author

SHA Xudong, WANG Chenfei, LU Jia, and YU Zhihua

Subjects
transient receptor potential vanilloid type 1(trpv1), microglia, metabolism, lipid, mitochondria, Medicine
Abstract

Objective·Transcriptomic and lipidomic analysis techniques were used to investigate the role of transient receptor potential vanilloid type 1 (TRPV1) channel activation in the regulation of high-fat diet-induced microglial metabolism.Methods·Eight-week-old C57BL/6J mice (WT) and Trpv1-/- (KO) mice were used as experimental animals, and fed high-fat diet (HFD) for 3 days, 7 days, and 8 weeks to induce modelling (WT and KO groups, n = 3; WT-HFD and KO-HFD groups, n = 4). TRPV1 channel expression and cellular localisation were measured by immunofluorescence in the brains of mice in the WT-HFD and KO-HFD group. RNA sequencing and liquid chromatography-mass spectrometry were performed to determine the brain phenotype of mice in the WT-HFD and KO-HFD groups.Results·The expression level of Trpv1 mRNA in microglia was significantly increased in mice in the WT-HFD group compared to mice in the WT group. The expression levels of genes related to brain lipid metabolism, mitochondrial function, glucose transfer, and glycolysis were down-regulated in the KO-HFD group of mice compared with the WT-HFD group of mice. Lipidomic analysis showed that although lipids accumulated in the brain tissue of mice in the KO-HFD group, Trpv1 knockdown attenuated HFD-induced microglia activation, and in addition the TRPV1 agonist capsaicin attenuated palmitate-induced depolarisation of mitochondrial membrane potential in vitro.Conclusion·Together, these findings suggest that TRPV1 regulates lipid and glucose metabolism in microglia via fuel availability driven by a mitochondrial mechanism.

Published
2023
Full Text
View/download PDF

3. LightSAGE: Graph Neural Networks for Large Scale Item Retrieval in Shopee's Advertisement Recommendation

Author

Nguyen, Dang Minh, Wang, Chenfei, Shen, Yan, and Zeng, Yifan

Subjects
Computer Science - Information Retrieval, Computer Science - Machine Learning, H.3.3, I.2.4
Abstract

Graph Neural Network (GNN) is the trending solution for item retrieval in recommendation problems. Most recent reports, however, focus heavily on new model architectures. This may bring some gaps when applying GNN in the industrial setup, where, besides the model, constructing the graph and handling data sparsity also play critical roles in the overall success of the project. In this work, we report how GNN is applied for large-scale e-commerce item retrieval at Shopee. We introduce our simple yet novel and impactful techniques in graph construction, modeling, and handling data skewness. Specifically, we construct high-quality item graphs by combining strong-signal user behaviors with high-precision collaborative filtering (CF) algorithm. We then develop a new GNN architecture named LightSAGE to produce high-quality items' embeddings for vector search. Finally, we design multiple strategies to handle cold-start and long-tail items, which are critical in an advertisement (ads) system. Our models bring improvement in offline evaluations, online A/B tests, and are deployed to the main traffic of Shopee's Recommendation Advertisement system.

Published
2023
Full Text
View/download PDF

4. Edge computing task scheduling strategy based on load balancing

Author

Sun Lintan, Li Zigan, Lv Jingxian, Wang Chenfei, Wang Yajuan, Chen Long, and He Dong

Subjects
edge calculation, load balancing, secondary allocation, Engineering (General). Civil engineering (General), TA1-2040
Abstract

With the rapid development and wide application of the Internet of Everything, in order to cope with the increasing amount of data and computational scale of mobile terminal processing, and the imbalance of existing scheduling algorithms and low resource utilization, this paper proposes a task scheduling algorithm based on business priority. The algorithm firstly divides the service according to the priority of the service. Secondly, the standard deviation of the computing task group is used to determine the proportion of long and short services, and the dynamic selection model is established. Finally, according to the idea of secondary allocation, the task of heavy load is assigned to the scheduling strategy of light load resources to execute, and the service redistribution model is established. The simulation results show that compared with the typical algorithm, the proposed algorithm achieves the result of comprehensive consideration of Makespan and load balancing to improve system efficiency.

Published
2020
Full Text
View/download PDF

7. Technical Report on Optimal Linear Multiple Estimation for Landmark-Based Planning via Control Synthesis

Author

Wang, Chenfei and Tron, Roberto

Subjects
Mathematics - Dynamical Systems
Abstract

A common way to implement navigation in mobile robots is through the use of landmarks. In this case, the main goal of the controller is to make progress toward a goal location (stability), while avoiding the boundary of the environment (safety). In our previous work, we proposed a method to synthesize global controllers for environments with a polyhedral decomposition; our solution uses a Quadratically Constrained Quadratic Program with Chance Constraints to take into account the uncertainty in landmark measurements. Building upon this work, we introduce the concept of virtual landmarks, which are defined as linear combinations of actual landmark measurements that minimize the uncertainty in the resulting control actions. Interestingly, our results show that the first minimum-variance landmark is independent of the feedback control matrix, thus decoupling the design of the landmark from the one of the controller; attempting to derive additional, statistically independent landmarks, however, requires solving non-convex problems that involve also the controller. Numerical experiments demonstrate that, by minimizing the variance of the inputs, the resulting controller will be less conservative, and the robot is able to complete navigation tasks more effectively (faster and with less jitter in the trajectory).

Published
2022

21. S-AT GCN: Spatial-Attention Graph Convolution Network based Feature Enhancement for 3D Object Detection

Author

Wang, Li, Wang, Chenfei, Zhang, Xinyu, Lan, Tianwei, and Li, Jun

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

3D object detection plays a crucial role in environmental perception for autonomous vehicles, which is the prerequisite of decision and control. This paper analyses partition-based methods' inherent drawbacks. In the partition operation, a single instance such as a pedestrian is sliced into several pieces, which we call it the partition effect. We propose the Spatial-Attention Graph Convolution (S-AT GCN), forming the Feature Enhancement (FE) layers to overcome this drawback. The S-AT GCN utilizes the graph convolution and the spatial attention mechanism to extract local geometrical structure features. This allows the network to have more meaningful features for the foreground. Our experiments on the KITTI 3D object and bird's eye view detection show that S-AT Conv and FE layers are effective, especially for small objects. FE layers boost the pedestrian class performance by 3.62\% and cyclist class by 4.21\% 3D mAP. The time cost of these extra FE layers are limited. PointPillars with FE layers can achieve 48 PFS, satisfying the real-time requirement.

Published
2021

22. Chance Constraint Robust Control with Control Barrier Functions

Author

Wang, Chenfei, Bahreinian, Mahroo, and Tron, Roberto

Subjects
Mathematics - Optimization and Control
Abstract

In this paper, we propose a novel approach to synthesize linear feedback controllers for navigating in polygonal environments using noisy measurements and a convex cell decomposition. Our method is based on formulating chance constraints for the convergence and collision avoidance condition. In particular, the stability and safety guarantees come from chance Control Barrier Function (CBF) constraints and chance Control Lyapunov Function (CLF) constraints, respectively. We use convex over-approximations to get upper bounds of the constraints, leading to a convex robust quadratic program for finding the controller. We apply and provide simulation results for equilibrium control and path control. The result shows that the controller is robust with the noise input.

Published
2020

23. Proteogenomic characterization of small cell lung cancer identifies biological insights and subtype-specific therapeutic strategies

Author

Liu, Qian, Zhang, Jing, Guo, Chenchen, Wang, Mengcheng, Wang, Chenfei, Yan, Yilv, Sun, Liangdong, Wang, Di, Zhang, Lele, Yu, Huansha, Hou, Likun, Wu, Chunyan, Zhu, Yuming, Jiang, Gening, Zhu, Hongwen, Zhou, Yanting, Fang, Shanhua, Zhang, Tengfei, Hu, Liang, Li, Junqiang, Liu, Yansheng, Zhang, Hui, Zhang, Bing, Ding, Li, Robles, Ana I., Rodriguez, Henry, Gao, Daming, Ji, Hongbin, Zhou, Hu, and Zhang, Peng

Published
2024
Full Text
View/download PDF

24. BGC: Multi-Agent Group Belief with Graph Clustering

Author

Zhou, Tianze, Zhang, Fubiao, Tang, Pan, and Wang, Chenfei

Subjects
Computer Science - Artificial Intelligence, Computer Science - Machine Learning
Abstract

Recent advances have witnessed that value decomposed-based multi-agent reinforcement learning methods make an efficient performance in coordination tasks. Most current methods assume that agents can make communication to assist decisions, which is impractical in some situations. In this paper, we propose a semi-communication method to enable agents can exchange information without communication. Specifically, we introduce a group concept to help agents learning a belief which is a type of consensus. With this consensus, adjacent agents tend to accomplish similar sub-tasks to achieve cooperation. We design a novel agent structure named Belief in Graph Clustering(BGC), composed of an agent characteristic module, a belief module, and a fusion module. To represent each agent characteristic, we use an MLP-based characteristic module to generate agent unique features. Inspired by the neighborhood cognitive consistency, we propose a group-based module to divide adjacent agents into a small group and minimize in-group agents' beliefs to accomplish similar sub-tasks. Finally, we use a hyper-network to merge these features and produce agent actions. To overcome the agent consistent problem brought by GAT, a split loss is introduced to distinguish different agents. Results reveal that the proposed method achieves a significant improvement in the SMAC benchmark. Because of the group concept, our approach maintains excellent performance with an increase in the number of agents., Comment: 7 pages, 5 figures

Published
2020

34. BGC: Multi-agent Group Belief with Graph Clustering

Author

Zhou, Tianze, Zhang, Fubiao, Tang, Pan, Wang, Chenfei, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Woeginger, Gerhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Chen, Jie, editor, Lang, Jérôme, editor, Amato, Christopher, editor, and Zhao, Dengji, editor

Published
2022
Full Text
View/download PDF

47. Network Traffic Classification Method Fused with Flow Energy Model.

Author

DU Wenyong, XU Liyang, WANG Chenfei, ZHAO Wenhua, ZHANG Shuo, XIE Ruinan, CAO Pengcheng, and LI Xiaohong

Subjects
COMPUTER network traffic, MACHINE learning, DISTRIBUTION (Probability theory), TRAFFIC monitoring, STATISTICAL learning, SIMPLE machines
Abstract

Abnormal network traffic detection is a key cybersecurity technology that assists in identifying and preventing malicious network attacks. Existing methods for detecting abnormal network traffic typically rely on complex machine learning models and a large amount of labeled data. Consequently, these methods are challenging to apply to different scenarios without retraining the model and cannot effectively handle large-scale, ongoing network attacks in real-time. To address these issues, this paper proposes a classification method based on a network flow energy model. It utilizes a reverse statistical physics model to learn target traffic features in the network, allowing it to be based on macroscopic real observations or real data without the need for manual labeling. Subsequently, the paper combines the concept of the energy model to construct a network traffic recognition model. This model judges whether a sample conforms to the main statistical distribution. Specifically, the method describes individual behavior characteristics and interaction features between traffic packets through the local field and coupling field in the energy model. By combining these two features, the method calculates the sample' s energy. If the energy is below a threshold, the sample aligns with the main distribution, indicating normal data; otherwise, it is considered abnormal data. As this method does not rely on manual labeling, it can adapt to various network environments without the need for repetitive training. This addresses current issues in traffic abnormality detection methods, which struggle to adapt to different scenarios and require extensive labeling. To evaluate the effectiveness of this method, the paper validates it using the Kitsune-2018 and CTU-13 datasets. Experimental results demonstrate that the proposed method achieves good classification performance and overall effectiveness in network traffic classification tasks. This further indicates its accuracy in performing network flow classification tasks and its adaptability to changing scenarios. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

48. Facile Construction of Flame-Resistant and Thermal-Insulating Sodium Alginate Aerogel Incorporating N- and P-Elements.

Author

Liu, Ju, Zhan, Huanhui, Song, Jianan, Wang, Chenfei, Zhao, Tong, and Fu, Bo

Subjects
FIREPROOFING agents, PHYTIC acid, SODIUM alginate, THERMAL insulation, AEROGELS
Abstract

In this study, sodium alginate (SA) aerogel cross-linked with Ca2+ was selected as the basic skeleton to construct a lightweight, flame retardant, and thermal insulating composite aerogel via modification with melamine and phytic acid. The resulting aerogel, SA-1.0 MP, achieved a thermal conductivity as low as 0.0379 W/(m·K). Compared to pristine SA aerogel, SA-1.0 MP demonstrated improved fire resistance, evidenced by a substantial increase in the limiting oxygen index (LOI) from 21.5% to 48.8% and a V-0 rating in the UL-94 test. Furthermore, a synergistic mechanism was proposed to explain its remarkable flame-retardant capability. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results