Search

Your search keyword '"Zhao, Jiancheng"' showing total 199 results
Start Over Author "Zhao, Jiancheng" Publication Year Range Last 10 years
199 results on '"Zhao, Jiancheng"'

1. Less but Better: Enabling Generalized Zero-shot Learning Towards Unseen Domains by Intrinsic Learning from Redundant LLM Semantics

Author

Yue, Jiaqi, Zhao, Jiancheng, and Zhao, Chunhui

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Generalized zero-shot learning (GZSL) focuses on recognizing seen and unseen classes against domain shift problem (DSP) where data of unseen classes may be misclassified as seen classes. However, existing GZSL is still limited to seen domains. In the current work, we pioneer cross-domain GZSL (CDGZSL) which addresses GZSL towards unseen domains. Different from existing GZSL methods which alleviate DSP by generating features of unseen classes with semantics, CDGZSL needs to construct a common feature space across domains and acquire the corresponding intrinsic semantics shared among domains to transfer from seen to unseen domains. Considering the information asymmetry problem caused by redundant class semantics annotated with large language models (LLMs), we present Meta Domain Alignment Semantic Refinement (MDASR). Technically, MDASR consists of two parts: Inter-class Similarity Alignment (ISA), which eliminates the non-intrinsic semantics not shared across all domains under the guidance of inter-class feature relationships, and Unseen-class Meta Generation (UMG), which preserves intrinsic semantics to maintain connectivity between seen and unseen classes by simulating feature generation. MDASR effectively aligns the redundant semantic space with the common feature space, mitigating the information asymmetry in CDGZSL. The effectiveness of MDASR is demonstrated on the Office-Home and Mini-DomainNet, and we have shared the LLM-based semantics for these datasets as the benchmark., Comment: This work is submitted to IEEE TMM

Published
2024

2. Learning to better see the unseen: Broad-Deep Mixed Anti-Forgetting Framework for Incremental Zero-Shot Fault Diagnosis

Author

Zhao, Jiancheng, Yue, Jiaqi, and Zhao, Chunhui

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

Zero-shot fault diagnosis (ZSFD) is capable of identifying unseen faults via predicting fault attributes labeled by human experts. We first recognize the demand of ZSFD to deal with continuous changes in industrial processes, i.e., the model's ability to adapt to new fault categories and attributes while avoiding forgetting the diagnosis ability learned previously. To overcome the issue that the existing ZSFD paradigm cannot learn from evolving streams of training data in industrial scenarios, the incremental ZSFD (IZSFD) paradigm is proposed for the first time, which incorporates category increment and attribute increment for both traditional ZSFD and generalized ZSFD paradigms. To achieve IZSFD, we present a broad-deep mixed anti-forgetting framework (BDMAFF) that aims to learn from new fault categories and attributes. To tackle the issue of forgetting, BDMAFF effectively accumulates previously acquired knowledge from two perspectives: features and attribute prototypes. The feature memory is established through a deep generative model that employs anti-forgetting training strategies, ensuring the generation quality of historical categories is supervised and maintained. The diagnosis model SEEs the UNSEEN faults with the help of generated samples from the generative model. The attribute prototype memory is established through a diagnosis model inspired by the broad learning system. Unlike traditional incremental learning algorithms, BDMAFF introduces a memory-driven iterative update strategy for the diagnosis model, which allows the model to learn new faults and attributes without requiring the storage of all historical training samples. The effectiveness of the proposed method is verified by a real hydraulic system and the Tennessee-Eastman benchmark process.

Published
2024

3. Addressing Domain Shift via Knowledge Space Sharing for Generalized Zero-Shot Industrial Fault Diagnosis

Author

Zhao, Jiancheng, Yue, Jiaqi, Feng, Liangjun, Zhao, Chunhui, and Ding, Jinliang

Subjects
Computer Science - Artificial Intelligence
Abstract

Fault diagnosis is a critical aspect of industrial safety, and supervised industrial fault diagnosis has been extensively researched. However, obtaining fault samples of all categories for model training can be challenging due to cost and safety concerns. As a result, the generalized zero-shot industrial fault diagnosis has gained attention as it aims to diagnose both seen and unseen faults. Nevertheless, the lack of unseen fault data for training poses a challenging domain shift problem (DSP), where unseen faults are often identified as seen faults. In this article, we propose a knowledge space sharing (KSS) model to address the DSP in the generalized zero-shot industrial fault diagnosis task. The KSS model includes a generation mechanism (KSS-G) and a discrimination mechanism (KSS-D). KSS-G generates samples for rare faults by recombining transferable attribute features extracted from seen samples under the guidance of auxiliary knowledge. KSS-D is trained in a supervised way with the help of generated samples, which aims to address the DSP by modeling seen categories in the knowledge space. KSS-D avoids misclassifying rare faults as seen faults and identifies seen fault samples. We conduct generalized zero-shot diagnosis experiments on the benchmark Tennessee-Eastman process, and our results show that our approach outperforms state-of-the-art methods for the generalized zero-shot industrial fault diagnosis problem.

Published
2023

4. A Systematic Evaluation and Benchmark for Embedding-Aware Generative Models: Features, Models, and Any-shot Scenarios

Author

Feng, Liangjun, Zhao, Jiancheng, and Zhao, Chunhui

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Embedding-aware generative model (EAGM) addresses the data insufficiency problem for zero-shot learning (ZSL) by constructing a generator between semantic and visual feature spaces. Thanks to the predefined benchmark and protocols, the number of proposed EAGMs for ZSL is increasing rapidly. We argue that it is time to take a step back and reconsider the embedding-aware generative paradigm. The main work of this paper is two-fold. First, the embedding features in benchmark datasets are somehow overlooked, which potentially limits the performance of EAGMs, while most researchers focus on how to improve EAGMs. Therefore, we conduct a systematic evaluation of ten representative EAGMs and prove that even embarrassedly simple modifications on the embedding features can improve the performance of EAGMs for ZSL remarkably. So it's time to pay more attention to the current embedding features in benchmark datasets. Second, based on five benchmark datasets, each with six any-shot learning scenarios, we systematically compare the performance of ten typical EAGMs for the first time, and we give a strong baseline for zero-shot learning (ZSL) and few-shot learning (FSL). Meanwhile, a comprehensive generative model repository, namely, generative any-shot learning (GASL) repository, is provided, which contains the models, features, parameters, and scenarios of EAGMs for ZSL and FSL. Any results in this paper can be readily reproduced with only one command line based on GASL.

Published
2023

28. Ultrastructural characteristics and morphological relationships of cardiomyocytes and telocytes in the myocardium of the bullfrog (Rana catesbeiana).

Author

Wang, Zifan, Xu, Yizhen, Huang, Ling, Zhao, Jiancheng, Ye, Yaqiong, Liu, Canying, Wang, Bingyun, Zhao, Haiquan, and Zhang, Hui

Subjects
BULLFROG, MYOCARDIUM, SATELLITE cells, INTERSTITIAL cells, TIGHT junctions, JOINTS (Engineering)
Abstract

Telocytes (TCs) are distinctive interstitial cells due to their characteristic structures and heterogeneity. They are suggested to participate in tissue repair/regeneration. TCs have been identified in many organs of various mammals. However, data on TCs in lower animals are still very limited. In this work, TCs were identified in the myocardium of the bullfrog (Rana catesbeiana) by light and transmission electron microscopy (TEM). The structural relationships between TCs and neighbouring cell types were measured using the ImageJ (FiJi) morphometric software. TCs with slender Tps (telepodes) were located around cardiomyocytes (CMC). TEM revealed TCs with long Tps in the stroma between CMC. The homocellular tight junctions were observed between the Tps. The Tps were also very close to the neighbouring CMC. The distance between Tps and CMC was 0.15 ± 0.08 μm. Notably, Tps were observed to adhere to the periphery of the satellite cells. The Tps and the satellite cells established heterocellular structural connections by tight junctions. Additionally, Tps were frequently observed in close proximity to mast cells (MCs). The distance between the Tps and the MCs was 0.19 ± 0.09 μm. These results confirmed that TCs are present in the myocardium of the bullfrog, and that TCs established structural relationships with neighbouring cell types, including satellite cells and MCs. These findings provide the anatomical evidence to support the note that TCs are involved in tissue regeneration. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

31. Ammonia volatilization and nitrogen runoff losses from moso bamboo forests after different fertilization practices

Author

Zhao, Jiancheng, Su, Wenhui, Fan, Shaohui, Cai, Chunju, Su, Haoran, and Zeng, Xianli

Subjects
Ammonia -- Environmental aspects, Bamboo -- Environmental aspects, Forest soils -- Analysis, Nitrogen (Chemical element) -- Environmental aspects, Runoff -- Environmental aspects, Forests, Earth sciences
Abstract

Moso bamboo (Phyllostachys edulis (Carriere) J. Houz.) is a major giant bamboo species. Unreasonable fertilization and nitrogen (N) loss is a serious problem. A field experiment was conducted to determine the effects of application methods (furrow and hole) and depths (0-20 and 20-40 cm) on ammonia (N[H.sub.3]) volatilization and N runoff losses from June to December, 2015. Ammonia volatilization was detected as a single peak curve after fertilization. Three weeks later, fluxes of all fertilization treatments were similar to those of the control and remained stable. After the experiment, the cumulative N[H.sub.3] volatilization was 17.2-21.4 kg x [ha.sup.-1]. Approximately 90% of N[H.sub.3] volatilization occurred within the first two weeks. The N[H.sub.4.sup.+]-N loss was higher than the N[O.sub.3.sup.-]-N loss, and the total runoff losses were relatively low. For the same application method, with the increase of application depth, the N[H.sub.3] volatilization and N runoff losses reduced; for the same application depth, the N[H.sub.3] volatilization and N runoff losses after furrow application were lower than those after hole application. Therefore, the deep and furrow application methods were effective in reducing N loss through N[H.sub.3] volatilization and runoff. In the present study, furrow application at a 20-40 cm depth has been appropriate for field practice. Key words: Phyllostachys edulis, fertilization method, fertilization depth, N[H.sub.3] volatilization, runoff. Le bambou moso (Phyllostachys edulis (Carriere) J. Houz.) est une importante espece de bambou geant. Une fertilisation deraisonnable et la perte d'azote (N) sont des problemes serieux. Une experience a ete realisee sur le terrain pour determiner les effets de la methode d'application (dans des sillons ou dans des trous) et de la profondeur (0-20 et 20-40 cm) sur la volatilisation de l'ammoniaque (N[H.sub.3]) et les pertes de N par ruissellement de juin a decembre 2015. La volatilisation de N[H.sub.3] a ete detectee par l'unique sommet dans la courbe apres la fertilisation. Trois semaines plus tard, les flux de tous les traitements de fertilisation etaient similaires a ceux du temoin et sont demeures stables par la suite. A la suite de l'experience, la volatilisation cumulative de N[H.sub.3] atteignait 17,2-21,4 kg x [ha.sup.-1]. Approximativement 90 % de la volatilisation de N[H.sub.3] est survenue durant les deux premieres semaines. La perte de N-N[H.sub.4.sup.+] etait plus elevee que la perte de N-N[O.sub.3.sup.-] et les pertes totales par ruissellement etaient relativement faibles. Pour la meme methode d'application, l'augmentation de la profondeur d'application a reduit la volatilisation de N[H.sub.3] et les pertes de N par ruissellement. Peu importe la profondeur d'application, la volatilisation de N[H.sub.3] et les pertes de N par ruissellement etaient moins elevees apres l'application dans des sillons plutot que dans des trous. Par consequent, l'application en profondeur dans des sillons etait efficace pour reduire les pertes de N par la volatilisation de N[H.sub.3] et le ruissellement. Dans le cadre de cette etude, la fertilisation dans des sillons a une profondeur de 20-40 cm etait appropriee pour la pratique sur le terrain. [Traduit par la Redaction] Mots-cles : Phyllostachys edulis, methode de fertilisation, profondeur de fertilisation, volatilisation de N[H.sub.3], ruissellement., Introduction Bamboo forests are one of the important and widely spread forest types in Southern China. According to the 8th national forest inventory, bamboo forests cover an area of 6.0 [...]

Published
2019
Full Text
View/download PDF

34. Similarity Makes Difference: SSHTN for Generalized Zero-Shot Industrial Fault Diagnosis by Leveraging Auxiliary Set

Author

Yue, Jiaqi, Zhao, Jiancheng, and Zhao, Chunhui

Abstract

The generalized zero-shot diagnosis (GZSD) has attracted rising attention from researchers, but faces a major bottleneck: the domain shift problem (DSP), which causes most unseen faults to be misclassified as seen. In this study, we propose a novel method termed semisupervised hybrid triplet network (SSHTN) with high resistance toward DSP to achieve GZSD by first introducing auxiliary set. To leverage the unlabeled data of auxiliary set, which is different from known faults (both seen and unseen), SSHTN defines relative boundaries of seen and unseen faults in the similarity space and comprises two branches: the data–data branch (DDB) and the data–semantic branch (DSB). For DDB, it constructs homogeneous and heterogeneous data pairs to learn data–data similarity. With the support of auxiliary set, the semisupervised similarity learning mechanism is constructed. Specifically, DDB analyzes differences between data pairs mixed by seen and auxiliary fault data to narrow down the decision boundaries of seen faults. Meanwhile, similarities between data pairs formed by disturbing auxiliary set data are learned to improve the generalization of DDB. For DSB, it learns data–semantic similarity by matching fault data with corresponding descriptions and extends SSHTN discriminative ability toward unseen faults. The SSHTN obtained from the comprehensive learning of similarity by the two branches could determine the boundaries of seen and unseen faults more accurately, thereby alleviating the effect of DSP. Experiments are implemented on the Tennessee Eastman process and a real thermal power plant process, and results show the superior performance of SSHTN over state-of-the-art ZSD methods.

Published
2024
Full Text
View/download PDF

44. Optimizing BiLSTM Network Attack Prediction Based on Improved Gray Wolf Algorithm.

Author

Qiu, Shaoming, Wang, Yahui, Lv, Yana, Chen, Fen, and Zhao, Jiancheng

Subjects
PREDICTION models, FORECASTING, TIME series analysis, STIMULUS & response (Psychology), GREY Wolf Optimizer algorithm
Abstract

Aiming at the problems of low accuracy of network attack prediction and long response time of attack detection, bidirectional long short-term memory (BiLSTM) was used to predict network attacks. However, BiLSTM has the problems of difficulty in parameter setting and low accuracy of the prediction model. This paper first proposes the Improved Grey Wolf algorithm (IGWO) to optimize the BiLSTM (IGWO-BiLSTM). First, IGWO uses Dimension Learning Hunting (DLH) strategy to construct the wolf neighborhood. In the established wolf neighborhood, the BiLSTM parameters are iteratively optimized to obtain a prediction model with fast convergence speed and small reconstruction error. Secondly, the dataset is preprocessed, and the IP packet statistical signature (IPDCF) is defined according to the characteristics of denial of service (DOS) and distributed denial of service (DDOS) attacks. IPDCF was used to establish the time series model and network traffic time series data were input into IGWO-BiLSTM to get the prediction results. Finally, the DOS and DDOS network packets were input into the trained prediction model to obtain the prediction results of attack data. By comparing the predicted values of IGWO-BiLSTM normal network packets and attack packets, a reasonable threshold is set to provide the basis for the subsequent attack prediction. Experiments show that the IGWO-BiLSTM can reach 99.05% of the fitting degree and accurately distinguish network attacks from normal network demand increases. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results