Feature Selection Neural Network Research Articles

Recognition of Disease in Leaves Using Genetic Algorithm and Neural Network Based Feature Selection

Objectives : To suggest a suitable image recognition approach for the early recognition of leaf diseases using hybrid features with genetic algorithm and neural network feature selection technique to maximize the accuracy. Methods: Various image processing techniques are utilized to recognize disease in the leaf. In the pre-processing phase, CNN based de-noising is utilized to remove noise from the image. Next, disease part of the leaf is segmented by Pixel wise Classification approach with an optimization technique. Then, the colour and the segmented area of an image is used to remove out texture features. With GLCM and SIFT technique. Then the appropriate features are selected by Genetic Algorithm and Neural Network based feature selection. Extracted features are classified using an Ensemble classifier for recognizing disease in the leaf. For this experiment images are taken from the plant village data set. In this work, the disease caused by Alternaria solani and Pytopthara infestans pathogens is considered for recognizing the disease in the leaf. 1500 leaves are used. From each image, 1654 features are extracted. There is a 70% training and 30% test data split. Classification accuracy, precision and recall measures are considered for evaluating the proposed work’s performance. Findings: The proposed work gives 97.7% classification accuracy, 97.3% precision and 97.5% recall measures with various visual feature descriptors and GANN feature selection. Novelty: The in-depth investigation compares the proposed descriptor GANN_SVM and GANN ES detection and classification technique to local and global SVMs. The suggested descriptor outperforms current approaches for diagnosing Alternaria solani and Pytopthara infestans leaves and the method can be applied to all plants infected leaves. Keywords: Genetic Algorithm; Leaf disease detection; Image processing; Neural Network; ensemble classifier

Feature selection in molecular graph neural networks based on quantum chemical approaches

Feature selection is an important topic that has been widely studied in data science.

A Novel Anomaly-Based Intrusion Detection Model Using PSOGWO-Optimized BP Neural Network and GA-Based Feature Selection

Intrusion detection systems (IDS) are crucial for network security because they enable detection of and response to malicious traffic. However, as next-generation communications networks become increasingly diversified and interconnected, intrusion detection systems are confronted with dimensionality difficulties. Prior works have shown that high-dimensional datasets that simulate real-world network data increase the complexity and processing time of IDS system training and testing, while irrelevant features waste resources and reduce the detection rate. In this paper, a new intrusion detection model is presented which uses a genetic algorithm (GA) for feature selection and optimization algorithms for gradient descent. First, the GA-based method is used to select a set of highly correlated features from the NSL-KDD dataset that can significantly improve the detection ability of the proposed model. A Back-Propagation Neural Network (BPNN) is then trained using the HPSOGWO method, a hybrid combination of the Particle Swarm Optimization (PSO) and Grey Wolf Optimization (GWO) algorithms. Finally, the hybrid HPSOGWO-BPNN algorithm is used to solve binary and multi-class classification problems on the NSL-KDD dataset. The experimental outcomes demonstrate that the proposed model achieves better performance than other techniques in terms of accuracy, with a lower error rate and better ability to detect different types of attacks.

Hybrid PSO (SGPSO) with the Incorporation of Discretization Operator for Training RBF Neural Network and Optimal Feature Selection

Hybrid PSO (SGPSO) with the Incorporation of Discretization Operator for Training RBF Neural Network and Optimal Feature Selection

Diabetic Retinopathy Detection Using Genetic Algorithm-Based CNN Features and Error Correction Output Code SVM Framework Classification Model

Diabetic retinopathy (DR) is a type of eye disease that may be caused in individuals suffering from diabetes which results in vision loss. DR identification and routine diagnosis is a challenging task and may need several screenings. Early identification of DR has the potential to prevent or delay vision loss. For real-time applications, an automated DR identification approach is required to assist and reduce possible human mistakes. In this research work, we propose a deep neural network and genetic algorithm-based feature selection approach. Five advanced convolutional neural network architectures are used to extract features from the fundus images, i.e., AlexNet, NASNet-Large, VGG-19, Inception V3, and ShuffleNet, followed by genetic algorithm for feature selection and ranking features into high rank (optimal) and lower rank (unsatisfactory). The nonoptimal feature attributes from the training and validation feature vectors are then dropped. Support vector machine- (SVM-) based classification model is used to develop diabetic retinopathy recognition model. The model performance is evaluated using accuracy, precision, recall, and F1 score. The proposed model is tested on three different datasets: the Kaggle dataset, a self-generated custom dataset, and an enhanced custom dataset with 97.9%, 94.76%, and 96.4% accuracy, respectively. In the enhanced custom dataset, data augmentation has been performed due to the smaller size of the dataset and to eliminate the noise in fundus images.

An Unsupervised Neural Network Feature Selection and 1D Convolution Neural Network Classification for Screening of Parkinsonism.

Parkinson’s disease (PD) is the second most common neurodegenerative disorder after Alzheimer’s disease. It has a slow progressing neurodegenerative disorder rate. PD patients have multiple motor and non-motor symptoms, including vocal impairment, which is one of the main symptoms. The identification of PD based on vocal disorders is at the forefront of research. In this paper, an experimental study is performed on an open source Kaggle PD speech dataset and novel comparative techniques were employed to identify PD. We proposed an unsupervised autoencoder feature selection technique, and passed the compressed features to supervised machine-learning (ML) algorithms. We also investigated the state-of-the-art deep learning 1D convolutional neural network (CNN-1D) for PD classification. In this study, the proposed algorithms are support vector machine, logistic regression, random forest, naïve Bayes, and CNN-1D. The classifier performance is evaluated in terms of accuracy score, precision, recall, and F1 score measure. The proposed 1D-CNN model shows the highest result of 0.927%, and logistic regression shows 0.922% on the benchmark dataset in terms of F1 measure. The major contribution of the proposed approach is that unsupervised neural network feature selection has not previously been investigated in Parkinson’s detection. Clinicians can use these techniques to analyze the symptoms presented by patients and, based on the results of the above algorithms, can diagnose the disease at an early stage, which will allow for improved future treatment and care.

Article Classification Using Convolutional Neural Network (CNN) And Chi-Square Feature Selection

Article Classification Using Convolutional Neural Network (CNN) And Chi-Square Feature Selection

Differentiating Crohn’s disease from intestinal tuberculosis using a fusion correlation neural network

Crohn’s disease (CD) and intestinal tuberculosis (ITB) have many similarities and overlaps in their clinical manifestations and medical imaging features, which makes it difficult to accurately differentiate CD from ITB. Random forests have unique advantages in discovering specific indicators and measuring relevance. By fusing the attributes and the correlation information between the sample and training set, we propose a fusion correlation neural network (FCNN) to diagnose CD and ITB patients. A total of 287 cases with fifty-nine indicators were collected from the Second Xiangya Hospital of Central South University. An FCNN allows one to explain the feature selection and learning classification rules in neural networks. The experiments show that perianal fistulas, skin and mucosal lesions, intestinal perforation, comb sign, and cobblestone appearance tend to be associated with CD; and ascites show a higher association with intestinal tuberculosis. These conclusions are consistent with the experience of clinicians. Finally, the age, disease course, white blood cell, hemoglobin, platelets, C-reactive protein, and T-SPOT of patients were used to train the FCNN. The average accuracy of the FCNN exceeds 91%, showing better performance than existing linear regression standards and other machine learning models.

Correction to: A Fused Heterogeneous Deep Neural Network and Robust Feature Selection Framework for Human Actions Recognition

A Correction to this paper has been published: 10.1007/s13369-021-05881-4

Big data-enabled intelligent synchronisation for the complex production logistics system under the opti-state control strategy

Diversified customer needs make the production system more susceptible to high-frequency fluctuations of uncertain factors (UFs), which puts forward higher requirements for the real-time and systematic decision-making of the system. The opti-state control strategy enables the system to maintain the adaptive optimal state after being disturbed. The core intelligent synchronisation of the opti-state control strategy needs to perceive the state of the affected system and its degree of change. Aiming at the challenge of difficulty in evaluating the uncertain factors impact degree (UFID) of the complex production logistics system, this work proposes a big data-enabled intelligent synchronisation under the opti-state control strategy. Based on the simulation data of system operation, big data is used to mine the relationship between the UFID and the system states, then use wrapper GA-DNN (Deep Neural Network) feature selection and classification method evaluates the UFID, which will be applied to the synchronisation decision. The results show that the method can accurately evaluate the UFID and avoid the waste of resources and the increase in operating costs caused by excessive evaluation of the UFID, thereby also improves the effectiveness and efficiency of the opti-state control strategy.

Distribution-dependent feature selection for deep neural networks

Distribution-dependent feature selection for deep neural networks

A comparative analysis of meta-heuristic optimization algorithms for feature selection and feature weighting in neural networks

A comparative analysis of meta-heuristic optimization algorithms for feature selection and feature weighting in neural networks

RETRACTED ARTICLE: A Fused Heterogeneous Deep Neural Network and Robust Feature Selection Framework for Human Actions Recognition

RETRACTED ARTICLE: A Fused Heterogeneous Deep Neural Network and Robust Feature Selection Framework for Human Actions Recognition

Performance prediction of proton-exchange membrane fuel cell based on convolutional neural network and random forest feature selection

For optimizing the performance of the proton exchange membrane fuel cells (PEMFCs), the I–V polarization curve is generally used as an important evaluation metric, which can represent many important properties of PEMFCs such as current density, specific power, etc. However, a vast number of experiments for achieving I-V polarization curves are conducted, which consumes a lot of resources, since the membrane electrode assembly (MEA) in PEMFCs involves complex electrochemical, thermodynamic, and hydrodynamic processes. To solve the issues, this paper utilizes deep learning (DL) to design a performance prediction method based on the random forest algorithm (RF) and convolutional neural networks (CNN), which can reduce unnecessary experiments for MEA development. In the proposed method, to improve the high quality of the training dataset, the RF algorithm is adopted to select the important factors as the input feature of the model, and the selected factors are further verified by the previous studies. CNN is used to construct the performance prediction model which outputs the I-V polarization curve. In particular, batch normalization and dropout methods are applied to enhance model generalization. The effectiveness of the CNN-based prediction model is evaluated on the real I-V polarization curve dataset. Experiment results indicate that the prediction curves of the proposed model have good agreement with the real curves. Our study demonstrates the deep learning technologies are powerful complements for optimizing the PEMFCs.

Quality prediction for aluminum diecasting process based on shallow neural network and data feature selection technique

This paper aims to develop a prediction algorithm for better product quality of the diecasting process, one of the most essential aspects of quality management in traditional manufacturing industries. Shallow neural network (SNN) architecture has been applied as a regressive classifier engine in order to predict product quality of the manufacturing process to renovate the conventional technology adopted by the mainstream fundamental manufacturing industries. The results obtained have been contrasted with classical multilayer perceptron to establish the efficacy of the proposed strategy. In addition to the predictive classifier, various aspects of the research on the prediction algorithm and optimal input selection for successful yield have also been investigated for the aforementioned process using Fuzzy C Means clustering approach. As a case study for validation, the proposed algorithm applies for data set from an aluminum die-casting process. The results reflect that the proposed analytic model can prove to be an effective tool for the prediction and optimization of the product quality of various fundamental manufacturing processes.

Adaptive co-optimization of artificial neural networks using evolutionary algorithm for global radiation forecasting

Global radiation is not a regularly measured parameter in any weather station relative to other meteorological parameters due to measurement costs. This study has proposed hybrid artificial neural network models that predicted monthly radiation using typical weather and geographic data. Two datasets and six artificial neural network models were respectively built for indigenous and widespread regions around the world. The referred models co-optimized the artificial neural network properties and feature selection. For this purpose, an adaptive evolutionary algorithm improving prediction performance was developed to train the neural networks. This novel approach has yielded promising results compared to the developed deep learning models in this study. The results revealed that while the indigenous models had common features of longitude, sunshine durations, precipitation, and wind speed, the widespread models involved those of latitude, sunshine durations, and mean daily maximum air temperature. The proposed hybrid model had respectively the best mean absolute percentage errors of 2.45% and 9.93% for validation dataset and 3.75% and 11.03% for testing dataset of the indigenous and widespread regions, respectively. The present findings showed that the proposed hybrid model could be evaluated as a generic model and could improve the forecasting accuracy with the specified optimization parameters.

Pearson Correlation-Based Feature Selection for Document Classification Using Balanced Training.

Documents are stored in a digital form across several organizations. Printing this amount of data and placing it into folders instead of storing digitally is against the practical, economical, and ecological perspective. An efficient way of retrieving data from digitally stored documents is also required. This article presents a real-time supervised learning technique for document classification based on deep convolutional neural network (DCNN), which aims to reduce the impact of adverse document image issues such as signatures, marks, logo, and handwritten notes. The proposed technique’s major steps include data augmentation, feature extraction using pre-trained neural network models, feature fusion, and feature selection. We propose a novel data augmentation technique, which normalizes the imbalanced dataset using the secondary dataset RVL-CDIP. The DCNN features are extracted using the VGG19 and AlexNet networks. The extracted features are fused, and the fused feature vector is optimized by applying a Pearson correlation coefficient-based technique to select the optimized features while removing the redundant features. The proposed technique is tested on the Tobacco3482 dataset, which gives a classification accuracy of 93.1% using a cubic support vector machine classifier, proving the validity of the proposed technique.

Deep Neural Network Feature Selection Approaches for Data-Driven Prognostic Model of Aircraft Engines

Predicting Remaining Useful Life (RUL) of systems has played an important role in various fields of reliability engineering analysis, including in aircraft engines. RUL prediction is critically an important part of Prognostics and Health Management (PHM), which is the reliability science that is aimed at increasing the reliability of the system and, in turn, reducing the maintenance cost. The majority of the PHM models proposed during the past few years have shown a significant increase in the amount of data-driven deployments. While more complex data-driven models are often associated with higher accuracy, there is a corresponding need to reduce model complexity. One possible way to reduce the complexity of the model is to use the features (attributes or variables) selection and dimensionality reduction methods prior to the model training process. In this work, the effectiveness of multiple filter and wrapper feature selection methods (correlation analysis, relief forward/backward selection, and others), along with Principal Component Analysis (PCA) as a dimensionality reduction method, was investigated. A basis algorithm of deep learning, Feedforward Artificial Neural Network (FFNN), was used as a benchmark modeling algorithm. All those approaches can also be applied to the prognostics of an aircraft gas turbine engines. In this paper, the aircraft gas turbine engines data from NASA Ames prognostics data repository was used to test the effectiveness of the filter and wrapper feature selection methods not only for the vanilla FFNN model but also for Deep Neural Network (DNN) model. The findings show that applying feature selection methods helps to improve overall model accuracy and significantly reduced the complexity of the models.

Diabetic Peripheral Neuropathy Risk Assessment using Digital Fundus Photographs and Machine Learning.

In this work, we demonstrate a novel approach to assessing the risk of Diabetic Peripheral Neuropathy (DPN) using only the retinal images of the patients. Our methodology consists of convolutional neural network feature extraction, dimensionality reduction and feature selection with random projections, combination of image features to case-level representations, and the training and testing of a support vector machine classifier. Using clinical diagnosis as ground truth for DPN, we achieve an overall accuracy of 89% on a held-out test set, with sensitivity reaching 78% and specificity reaching 95%.

Feature Selection for Neural Networks Using Group Lasso Regularization

We propose an embedded/integrated feature selection method based on neural networks with Group Lasso penalty. Group Lasso regularization is considered to produce sparsity on the inputs to the network, i.e., for selection of useful features. Lasso based feature selection using a multi-layer perceptron usually requires an additional set of weights, while our Group Lasso formulation does not require that. However, Group Lasso penalty is non-differentiable at the origin. This may lead to oscillations in numerical simulations and make it difficult to analyze theoretically. To address this issue, four smoothing Group Lasso penalties are introduced. A rigorous proof for the convergence of the proposed algorithm is presented under suitable assumptions. To verify the effectiveness, a three-step algorithmic architecture is adopted in implementation. Experimental results on several datasets validate the theoretical results and demonstrate the competitive performance of the proposed method.