An optimized model based on convolutional neural networks and orthogonal learning particle swarm optimization algorithm for plant diseases diagnosis

Darwish, Ashraf; Ezzat, Dalia; Hassanien, Aboul Ella

doi:10.1016/j.swevo.2019.100616

Cited by 184 publications

(81 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In contrast, the validation set is utilized to tune the hyper-parameter values and measure the network performance during the training phase. The test set is utilized to assess network performance after completing its training [46].…”

Section: B Artificial Neural Networkmentioning

confidence: 99%

Multi-Objective Hybrid Artificial Intelligence Approach for Fault Diagnosis of Aerospace Systems

et al. 2021

Self Cite

View full text Add to dashboard Cite

Due to the space environment's hazards and challenges, aerospace systems are continuously exposed to many failures, such as the degradation of the subsystem performance, sensor faults, connection loss, or equipment damage. Therefore, the effective fault diagnosis for detecting and identifying any failures or unusual behaviors can be recognized as the fundamental and critical role of aerospace systems' predictive health management process. This paper proposes a novel fault diagnosis approach using Deep Learning (DL) technique. DL has recently become a popular approach in artificial intelligence (AI) due to its supremacy in accuracy and fast inference with the huge amount of data and highest order network structures. The proposed approach consists of two main phases; the feature selection phase by Binary Grasshopper Optimization Algorithm (BGOA), and the learning and prediction phase by Artificial Neural Networks (ANNs) with voting ensemble method. The proposed approach named BGOA-EANNs has been validated and evaluated its efficacy by comparing two existing diagnosis techniques using two types of aerospace health diagnosis datasets; satellite power system and aircraft engines. The experimental results demonstrated the effectiveness and superiority of the proposed approach.

show abstract

Section: B Artificial Neural Networkmentioning

confidence: 99%

Multi-Objective Hybrid Artificial Intelligence Approach for Fault Diagnosis of Aerospace Systems

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…Experimental results proved that the GPSO managed to obtain competitive classification performance over the dataset. An orthogonal learning particle swarm optimization (OLPSO) algorithm that optimized hyperparameters' values for VGG16 and VGG19 CNNs that have been developed for the task of plant disease diagnosis by classifying the leaf images as healthy and unhealthy was presented in [14]. By performing practical simulations, the authors proved that their approach managed to obtain higher performance than other methods that were tested for the same datasets.…”

Section: Metaheuristics Applications For Cnn Optimizationmentioning

confidence: 99%

Optimizing Convolutional Neural Network Hyperparameters by Enhanced Swarm Intelligence Metaheuristics

et al. 2020

View full text Add to dashboard Cite

Computer vision is one of the most frontier technologies in computer science. It is used to build artificial systems to extract valuable information from images and has a broad range of applications in various areas such as agriculture, business, and healthcare. Convolutional neural networks represent the key algorithms in computer vision, and in recent years, they have attained notable advances in many real-world problems. The accuracy of the network for a particular task profoundly relies on the hyperparameters’ configuration. Obtaining the right set of hyperparameters is a time-consuming process and requires expertise. To approach this concern, we propose an automatic method for hyperparameters’ optimization and structure design by implementing enhanced metaheuristic algorithms. The aim of this paper is twofold. First, we propose enhanced versions of the tree growth and firefly algorithms that improve the original implementations. Second, we adopt the proposed enhanced algorithms for hyperparameters’ optimization. First, the modified metaheuristics are evaluated on standard unconstrained benchmark functions and compared to the original algorithms. Afterward, the improved algorithms are employed for the network design. The experiments are carried out on the famous image classification benchmark dataset, the MNIST dataset, and comparative analysis with other outstanding approaches that were tested on the same problem is conducted. The experimental results show that both proposed improved methods establish higher performance than the other existing techniques in terms of classification accuracy and the use of computational resources.

show abstract

“…In this work, six transfer learning models were fine-tuned: AlexNet [18], DenseNet-201 [19], GoogLeNet [20], MobileNet-v2 [21], ResNet-18 [22] and VGG-16 [23]. Transfer learning consists of using a pre-trained model and adapting it to a new dataset [47]. In this work, these models are shallow tuned (only the parameters of the last fully connected layer are tuned) to identify one of two classes: with or without a natural gas leak.…”

Section: Transfer Learningmentioning

confidence: 99%

Applying Convolutional Neural Networks to Detect Natural Gas Leaks in Wellhead Images

2020

View full text Add to dashboard Cite

Detecting natural gas leaks is one of the most important measures in the oil industry for preventing accidents. The literature provides different techniques for detecting natural gas leaks. However, except for previous studies by the authors on this topic, there remains a gap in the literature on leak detection of natural gas using digital images, without the need for sensors or special cameras calibrated for the spectrum of methane molecules. These previous studies used image-processing techniques associated with a novelty filter classifier to detect the presence or absence of visible cloud of hydrocarbon vapors, that is, a natural gas plume in Closed Circuit Television (CCTV) frames installed in onshore wellheads. In this paper, we present a new method for detecting natural gas leaks in oil facilities that enhances the results obtained previously, along with the Gradient-weighted Class Activation Mapping Algorithm (Grad-CAM) to identify natural gas leaks. In this new method, convolutional neural networks (CNN) are applied to classify images (CCTV frames) as belonging to classes with or without natural gas leaks in onshore wellheads. Experimental results showed that the best performance model presented an accuracy of 99.78% and false negative rate of 0.00%.

show abstract

An optimized model based on convolutional neural networks and orthogonal learning particle swarm optimization algorithm for plant diseases diagnosis

Cited by 184 publications

References 24 publications

Multi-Objective Hybrid Artificial Intelligence Approach for Fault Diagnosis of Aerospace Systems

Multi-Objective Hybrid Artificial Intelligence Approach for Fault Diagnosis of Aerospace Systems

Optimizing Convolutional Neural Network Hyperparameters by Enhanced Swarm Intelligence Metaheuristics

Applying Convolutional Neural Networks to Detect Natural Gas Leaks in Wellhead Images

Contact Info

Product

Resources

About