Search

Your search keyword '"Li, Jianbo"' showing total 3,942 results
Start Over Author "Li, Jianbo"
3,942 results on '"Li, Jianbo"'

1. Interpretable modulated differentiable STFT and physics-informed balanced spectrum metric for freight train wheelset bearing cross-machine transfer fault diagnosis under speed fluctuations

Author

He, Chao, Shi, Hongmei, Li, Ruixin, Li, Jianbo, and Yu, ZuJun

Subjects
Computer Science - Machine Learning, Electrical Engineering and Systems Science - Signal Processing
Abstract

The service conditions of wheelset bearings has a direct impact on the safe operation of railway heavy haul freight trains as the key components. However, speed fluctuation of the trains and few fault samples are the two main problems that restrict the accuracy of bearing fault diagnosis. Therefore, a cross-machine transfer diagnosis (pyDSN) network coupled with interpretable modulated differentiable short-time Fourier transform (STFT) and physics-informed balanced spectrum quality metric is proposed to learn domain-invariant and discriminative features under time-varying speeds. Firstly, due to insufficiency in extracting extract frequency components of time-varying speed signals using fixed windows, a modulated differentiable STFT (MDSTFT) that is interpretable with STFT-informed theoretical support, is proposed to extract the robust time-frequency spectrum (TFS). During training process, multiple windows with different lengths dynamically change. Also, in addition to the classification metric and domain discrepancy metric, we creatively introduce a third kind of metric, referred to as the physics-informed metric, to enhance transferable TFS. A physics-informed balanced spectrum quality (BSQ) regularization loss is devised to guide an optimization direction for MDSTFT and model. With it, not only can model acquire high-quality TFS, but also a physics-restricted domain adaptation network can be also acquired, making it learn real-world physics knowledge, ultimately diminish the domain discrepancy across different datasets. The experiment is conducted in the scenario of migrating from the laboratory datasets to the freight train dataset, indicating that the hybrid-driven pyDSN outperforms existing methods and has practical value.

Published
2024
Full Text
View/download PDF

3. TASER: Temporal Adaptive Sampling for Fast and Accurate Dynamic Graph Representation Learning

Author

Deng, Gangda, Zhou, Hongkuan, Zeng, Hanqing, Xia, Yinglong, Leung, Christopher, Li, Jianbo, Kannan, Rajgopal, and Prasanna, Viktor

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

Recently, Temporal Graph Neural Networks (TGNNs) have demonstrated state-of-the-art performance in various high-impact applications, including fraud detection and content recommendation. Despite the success of TGNNs, they are prone to the prevalent noise found in real-world dynamic graphs like time-deprecated links and skewed interaction distribution. The noise causes two critical issues that significantly compromise the accuracy of TGNNs: (1) models are supervised by inferior interactions, and (2) noisy input induces high variance in the aggregated messages. However, current TGNN denoising techniques do not consider the diverse and dynamic noise pattern of each node. In addition, they also suffer from the excessive mini-batch generation overheads caused by traversing more neighbors. We believe the remedy for fast and accurate TGNNs lies in temporal adaptive sampling. In this work, we propose TASER, the first adaptive sampling method for TGNNs optimized for accuracy, efficiency, and scalability. TASER adapts its mini-batch selection based on training dynamics and temporal neighbor selection based on the contextual, structural, and temporal properties of past interactions. To alleviate the bottleneck in mini-batch generation, TASER implements a pure GPU-based temporal neighbor finder and a dedicated GPU feature cache. We evaluate the performance of TASER using two state-of-the-art backbone TGNNs. On five popular datasets, TASER outperforms the corresponding baselines by an average of 2.3% in Mean Reciprocal Rank (MRR) while achieving an average of 5.1x speedup in training time., Comment: IPDPS 2024

Published
2024

4. REHG: A Recommender Engine Based on Heterogeneous Graph

Author

Xin, Xiaoyang, Cheng, Zesheng, Wang, Tiankuan, Yan, Mengqiu, Zhao, Ruixuan, Peng, Chong, Li, Jianbo, Goos, Gerhard, Series Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Cai, Zhipeng, editor, Takabi, Daniel, editor, Guo, Shaoyong, editor, and Zou, Yifei, editor

Published
2025
Full Text
View/download PDF

9. Effect of heat treatment on microstructures and properties of Zr-rich α TiZrAl alloy

Author

FU Xiaoyun, WU Baolin, XU Zaidong, WAN Gang, LI Zhou, and LI Jianbo

Subjects
ti-zr alloy, annealing, quenching and aging, phase transformation, microstructure, mechanical property, Materials of engineering and construction. Mechanics of materials, TA401-492
Abstract

The microstructures and properties of two kinds of zirconium-enriched α alloys （Ti60Zr40）97Al3（mass fraction/%，the same below） and （Ti50Zr50）97Al3 via different heat treatments were investigated and analyzed based on optical microscope （OM） observation， differential scanning calorimetric （DSC） measurement， X-ray diffraction （XRD） measurement， scanning electron microscope （SEM） observation and tensile tests at room temperature.The results show that after 850 ℃/40 min annealing， microstructures consisting of basket-weave α phase and a small amount of reticular β phase are formed in the alloys. After 850 ℃/40 min quenching， the acicular α' martensite phase is formed. After 850 ℃/40 min quenching and then 600 ℃/4 h aging， a large part of α' martensite phase converts into α phase， and the microstructures of the alloys consist of α and α'remain phases. The yield strength of the T40Z3A alloy can reach 1100 MPa， with a favourable tensile elongation of 7%. The T50Z3A alloy exhibits higher strength but lower ductility than those of the T50Z3A alloy. Due to the higher content of Zr element， the T50Z3A alloy has more reticular β phase after annealing and more remaining α' martensite phase after quenching and aging， which results in higher strength and lower ductility.

Published
2024
Full Text
View/download PDF

10. Object Detection for Caries or Pit and Fissure Sealing Requirement in Children's First Permanent Molars

Author

Jiang, Chenyao, Zhai, Shiyao, Song, Hengrui, Ma, Yuqing, Fan, Yachen, Fang, Yancheng, Yu, Dongmei, Zhang, Canyang, Han, Sanyang, Wang, Runming, Liu, Yong, Li, Jianbo, and Qin, Peiwu

Subjects
Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition
Abstract

Dental caries is one of the most common oral diseases that, if left untreated, can lead to a variety of oral problems. It mainly occurs inside the pits and fissures on the occlusal/buccal/palatal surfaces of molars and children are a high-risk group for pit and fissure caries in permanent molars. Pit and fissure sealing is one of the most effective methods that is widely used in prevention of pit and fissure caries. However, current detection of pits and fissures or caries depends primarily on the experienced dentists, which ordinary parents do not have, and children may miss the remedial treatment without timely detection. To address this issue, we present a method to autodetect caries and pit and fissure sealing requirements using oral photos taken by smartphones. We use the YOLOv5 and YOLOX models and adopt a tiling strategy to reduce information loss during image pre-processing. The best result for YOLOXs model with tiling strategy is 72.3 mAP.5, while the best result without tiling strategy is 71.2. YOLOv5s6 model with/without tiling attains 70.9/67.9 mAP.5, respectively. We deploy the pre-trained network to mobile devices as a WeChat applet, allowing in-home detection by parents or children guardian.

Published
2023

21. Experimental Study on Sintering and Melting Characteristics and Mineral Transformation Law of Synthetic Biomass Ash

Author

LUO Yongjun, LI Jianbo, and ZHU Hongyan

Subjects
biomass, fluidized bed, synthetic ash, sintering and melting, potassium salt, Applications of electric power, TK4001-4102, Production of electric energy or power. Powerplants. Central stations, TK1001-1841, Science
Abstract

ObjectiveThe coking problem of biomass in fluidized bed combustion process was studied, and the influence of potassium salt form and content on the sintering and melting characteristics of biomass ash was analyzed.MethodsThe sintering and melting characteristics and the mineral transformation law of synthetic biomass ash were analyzed by experiments with scanning electron microscope coupled energy dispersive spectrometer, X-ray diffractometer, X-ray fluorescence, and FactSage thermodynamic calculation software.ResultsIn the typical operating temperature range of 750-950 ℃, the sintering and melting degree of synthetic biomass ash aggravates with the increase of temperature and potassium salt mass fraction. In addition, the effects of different forms of potassium salt on the sintering and melting characteristics of biomass synthetic ash are also significantly different. When the potassium salt is in the form of K2CO3, the liquid phase in the synthetic ash could reach up to 34.36%, leading consequently to severe sintering of the ash. When the potassium salt is in the form of KCl, most of K and Cl elements escape at 750-850 ℃, and the sintering degree of synthetic ash is weakened in comparison with the K2CO3 situation. When the potassium salt is in the form of K2SO4, the liquid phase in the synthetic ash is the least, and the sintering and melting degree is also the weakest.ConclusionChanging the form of potassium salt and controlling the temperature of fluidized bed are expected to alleviate the coking problem of biomass in fluidized bed combustion.

Published
2024
Full Text
View/download PDF

22. Power Allocation of Relay-Aided NOMA V2V System with Imperfect SIC

Author

Liang, Xiaolin, Shi, Xujing, Li, Jianbo, Ma, Jiaxu, Angrisani, Leopoldo, Series Editor, Arteaga, Marco, Series Editor, Chakraborty, Samarjit, Series Editor, Chen, Jiming, Series Editor, Chen, Shanben, Series Editor, Chen, Tan Kay, Series Editor, Dillmann, Rüdiger, Series Editor, Duan, Haibin, Series Editor, Ferrari, Gianluigi, Series Editor, Ferre, Manuel, Series Editor, Jabbari, Faryar, Series Editor, Jia, Limin, Series Editor, Kacprzyk, Janusz, Series Editor, Khamis, Alaa, Series Editor, Kroeger, Torsten, Series Editor, Li, Yong, Series Editor, Liang, Qilian, Series Editor, Martín, Ferran, Series Editor, Ming, Tan Cher, Series Editor, Minker, Wolfgang, Series Editor, Misra, Pradeep, Series Editor, Mukhopadhyay, Subhas, Series Editor, Ning, Cun-Zheng, Series Editor, Nishida, Toyoaki, Series Editor, Oneto, Luca, Series Editor, Panigrahi, Bijaya Ketan, Series Editor, Pascucci, Federica, Series Editor, Qin, Yong, Series Editor, Seng, Gan Woon, Series Editor, Speidel, Joachim, Series Editor, Veiga, Germano, Series Editor, Wu, Haitao, Series Editor, Zamboni, Walter, Series Editor, Tan, Kay Chen, Series Editor, Dong, Jian, editor, Zhang, Long, editor, and Cheng, Deqiang, editor

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results