Structural risk minimization of rough set-based classifier

Liu, Jinfu; Bai, Mingliang; Jiang, Na; Yu, Daren

doi:10.1007/s00500-019-04038-8

Cited by 19 publications

(6 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Take the complex number of the above equation, it is transformed into the minimization problem min θ 􏽐 N i�1 −log P(y i | x i ; 􏽮 θ) + log1/g(θ)}. Define the loss function as L(x i , P(y i | x i ; θ)) � −log P(y i | x i ; θ), the coefficient as λ � 1/N, the penalty term as J(f) � log1/g(θ), the equation is equal to form (2), which is structural risk minimization [30].…”

Section: Structural Risk Minimizationmentioning

confidence: 99%

A Diagnosis Framework for High‐reliability Equipment with Small Sample Based on Transfer Learning

et al. 2022

View full text Add to dashboard Cite

Conventional methods for fault diagnosis typically require a substantial amount of training data. However, for equipment with high reliability, it is arduous to form a large-scale well-annotated dataset due to the expense of data acquisition and costly annotation. Besides, the generated data have a large number of redundant features which degraded the performance of models. To overcome this, we proposed a feature transfer scenario that transfers knowledge from similar fields to enhance the accuracy of fault diagnosis with small sample. To reduces the redundant information, data were filtered according to manifold consistency. Then, features were extracted based on CNN and feature transfer was conducted. For adequate fitness, the joint adaptation of conditional distribution and marginal distribution was used between the two domains. Minimum structural risk and MMD of adaptation were two indicators weighted for training the model. To test the efficiency of the model, we built an airborne fuel pump testbed, and contributed a new dataset that contained 15 categories of fault data, which serves as the small sample dataset in this research. Then the proposed model was applied in our experimental data. As a result, the fault diagnosis rate increases by 28.6% through our proposed model, which is more precise than other classical methods. The results of feature visualization further demonstrate that the features are more distinguished through the proposed method. All code and data are accessible on my GitHub.

show abstract

Section: Structural Risk Minimizationmentioning

confidence: 99%

A Diagnosis Framework for High‐reliability Equipment with Small Sample Based on Transfer Learning

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Liu et al obtained through research that the massive database in high-dimensional space not only makes the search space larger but also makes it easier to find pattern errors. Therefore, make full use of relevant knowledge to change the dimension, reduce the dimension, and delete redundant data so as to make the data mining algorithm more efficient [ 11 ]. Oliva et al said that the algorithm for providing knowledge from massive spatial data should be testable and efficient [ 12 ].…”

Section: Literature Reviewmentioning

confidence: 99%

Multimedia Technology of Spatial Data Mining Based on Genetic Algorithm

Sun

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

In order to make key decisions more conveniently according to the massive data information obtained, a spatial data mining technology based on a genetic algorithm is proposed, which is combined with the k-means algorithm. The immune principle and adaptive genetic algorithm are introduced to optimize the traditional genetic algorithm, and the K-means, GK, and IGK algorithms are compared and analyzed. The results show that, in two different datasets, the objective functions obtained by the K-means algorithm are 94.05822 and 4.10373 × 10 6 , respectively, while the objective functions obtained by the GK and IGK algorithms are 89.8619 and 3.9088 × 10 6 , respectively. The difference between the three algorithms can also be reflected in the data comparison of the number of iterations. The number of iterations required for k-means to reach the optimal solution is 8.21 and 8.4, respectively, which is the most among the three algorithms, while the number of iterations required for IGK to reach the optimal solution is 5.84 and 4.9, respectively, which is the least. Although the time required for K-means is short, by comparison, the IGK algorithm we use can get the optimal solution in relatively less time.

show abstract

“…As shown in Fig. 1(a), a domainshared classifier ( ) f  has been just trained with source domain samples using the structural risk minimization theory [20], which means that it can complete the classification task based on the learned features. This classifier is also expected to be well applied in the target domain.…”

Section: Min ( ( ( )) ( ( ))mentioning

confidence: 99%

Deep Transfer Network With Multi-Kernel Dynamic Distribution Adaptation for Cross-Machine Fault Diagnosis

Liu

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Recently, various deep learning models, which are mainly based on data-driven algorithms, have received more and more attention in the field of intelligent fault diagnosis and prognostics. However, there are two major assumptions accepted by default in the existing studies: 1) The training (source domain) and testing (target domain) data sets obey the same feature distribution; 2) Sufficient labeled data with fault information is available for model training. In real industrial scenarios, especially for different machines, these assumptions are mostly invalid, which makes it a huge challenge to build reliable diagnostic model. Motivated by transfer learning, we present a novel intelligent method named deep transfer network (DTN) with multi-kernel dynamic distribution adaptation (MDDA) to address the problem of cross-machine fault diagnosis. In the proposed approach, the DTN has wide first-layer convolutional kernel and several small convolutional layers, which is utilized to extract transferable features across different machines and suppress high frequency noise. Then, the MDDA method constructs a weighted mixed kernel function to map different transferable features to a unified feature space, and the relative importance of the marginal and conditional distributions are also evaluated dynamically. The proposed method is verified by three transfer learning tasks of bearings, in which the health states of wind turbine bearings in real scenario are identified by using diagnosis knowledge from two different bearings in laboratories. The results show that the proposed method can achieve higher diagnosis accuracy and better transfer performance even under different noisy environment conditions than many other state-of-the-art methods. The presented framework offers a promising approach for cross-machine fault diagnosis. INDEX TERMS Deep transfer network, multi-kernel dynamic distribution adaptation, cross-machine fault diagnosis, transfer learning, bearings.

show abstract

Structural risk minimization of rough set-based classifier

Cited by 19 publications

References 56 publications

A Diagnosis Framework for High‐reliability Equipment with Small Sample Based on Transfer Learning

A Diagnosis Framework for High‐reliability Equipment with Small Sample Based on Transfer Learning

Multimedia Technology of Spatial Data Mining Based on Genetic Algorithm

Deep Transfer Network With Multi-Kernel Dynamic Distribution Adaptation for Cross-Machine Fault Diagnosis

Contact Info

Product

Resources

About