Load Identification Method Based on Interval Analysis and Tikhonov Regularization and Its Application

Liu, Chunsheng; Ren, Chunping; Wang, Nengjian

doi:10.1155/2019/1985025

Cited by 3 publications

(2 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Combining CNN with automatic disease detection for tomato leaves improves recognition accuracy while reducing labour costs. Currently, CNN is mostly employed in crop disease detection for the agriculture area [18][19][20]. A system for classifying illnesses of turmeric plant leaves was suggested by Kuricheti et al [21].…”

Section: Introductionmentioning

confidence: 99%

High-performance deep transfer learning model with batch normalization based on multiscale feature fusion for tomato plant disease identification and categorization

Ramya,

Kumar

2023

Environ. Res. Commun.

View full text Add to dashboard Cite

Deep learning and machine learning are cutting-edge methods for analysing images that have considerable potential. Artificial Neural Networks (A-NNs), one of the most well-known methods of computer intelligence, are now used in machine learning (ML) and deep transfer learning (DL) to raise plant production and quality. Identification and primary prevention of plant diseases at the appropriate time are essential for boosting productivity. Due to the phenomenon of minimally intense data in the background and foreground areas of the image, the extensive colour similarity between regions of unhealthy and normal leaves, the presence of noise in the sampling data, and changes in the location, size, and shape of plant leaf, it is difficult to correctly identify and classify plant diseases. In an effort to address these issues, a reliable technique for classifying plant diseases was developed by using a deep AlexNet CNN architecture as the main network with batch normalisation. In the three-step process, the first annotation is made to obtain the RoI (region of interest). The AlexNet CNN is therefore suggested for deep primary feature extraction in a constructed efficient network. The research demonstrates that the existing strategy is superior to more recent ones in terms of accuracy and dependability in recognising diseases in plants. Based on a deep transfer AlexNet CNN model, this research work developed a model for diseases identification and classification in plant leaves. It is trained using additional datasets that include a variety of plant leaf classifications and background images. From Plant Village and Kaggle, we gathered data on healthy and diseased tomato plant leaves. We are obtaining a near-balanced dataset containing ten different leaf disease kinds, such as bacterial, fungal, viral, and nutrient insufficiency. Ten classes have been considered for this research by gathering a dataset with associated images of the typical and abnormal tomato plant leaves. Considered in this work were the various labels for healthy and diseased tomato leaves, such as early blight, Bacterial spot, late bright mold, healthy, etc. Since deep CNN models have shown notable machine vision results, they are used in this case to diagnose and categorise plant illnesses from their leaves. As a result, the proposed CNN models can thus now be evaluated from confusion matrix using data analysis criteria, primarily focusing on metrics for evaluation like training and validation accuracy, loss, Recall, Precision, F1 score, processing speed, and performance.

show abstract

Section: Introductionmentioning

confidence: 99%

High-performance deep transfer learning model with batch normalization based on multiscale feature fusion for tomato plant disease identification and categorization

Ramya,

Kumar

2023

Environ. Res. Commun.

View full text Add to dashboard Cite

show abstract

“…All these methods involve inverting the matrix of the frequency response function, which more often than not suffers from severe ill-conditioning issues [14,15]. Although scholars have studied numerous regularization methods for ill-conditioned problems [16][17][18][19][20], there are still many difficulties with the implementation details of frequency-domain methods. Nevertheless, frequency-domain methods are still considered by industrial users to be more mature than the other methods.…”

Section: Introductionmentioning

confidence: 99%

A Recurrent Neural Network-Based Method for Dynamic Load Identification of Beam Structures

et al. 2021

View full text Add to dashboard Cite

The determination of structural dynamic characteristics can be challenging, especially for complex cases. This can be a major impediment for dynamic load identification in many engineering applications. Hence, avoiding the need to find numerous solutions for structural dynamic characteristics can significantly simplify dynamic load identification. To achieve this, we rely on machine learning. The recent developments in machine learning have fundamentally changed the way we approach problems in numerous fields. Machine learning models can be more easily established to solve inverse problems compared to standard approaches. Here, we propose a novel method for dynamic load identification, exploiting deep learning. The proposed algorithm is a time-domain solution for beam structures based on the recurrent neural network theory and the long short-term memory. A deep learning model, which contains one bidirectional long short-term memory layer, one long short-term memory layer and two full connection layers, is constructed to identify the typical dynamic loads of a simply supported beam. The dynamic inverse model based on the proposed algorithm is then used to identify a sinusoidal, an impulsive and a random excitation. The accuracy, the robustness and the adaptability of the model are analyzed. Moreover, the effects of different architectures and hyperparameters on the identification results are evaluated. We show that the model can identify multi-points excitations well. Ultimately, the impact of the number and the position of the measuring points is discussed, and it is confirmed that the identification errors are not sensitive to the layout of the measuring points. All the presented results indicate the advantages of the proposed method, which can be beneficial for many applications.

show abstract

Low frequency load identification under high noise level using weighted total least squares

Xin,

Zhu,

et al. 2024

Measurement

View full text Add to dashboard Cite

Load Identification Method Based on Interval Analysis and Tikhonov Regularization and Its Application

Cited by 3 publications

References 32 publications

High-performance deep transfer learning model with batch normalization based on multiscale feature fusion for tomato plant disease identification and categorization

High-performance deep transfer learning model with batch normalization based on multiscale feature fusion for tomato plant disease identification and categorization

A Recurrent Neural Network-Based Method for Dynamic Load Identification of Beam Structures

Low frequency load identification under high noise level using weighted total least squares

Contact Info

Product

Resources

About