- Research Article
1
- 10.1016/j.cjph.2024.05.036
Convolutional and hybrid neural network for cluster membership
- Jun 04, 2024
- Chinese Journal of Physics
- Yasuhiro Hashimoto + 1 more +1
Convolutional and hybrid neural network for cluster membership
RETRACTED: DL-SCA: An deep learning based approach for intra-class CutMix data augmentation
Convolutional and hybrid neural network for cluster membership
Convolutional and hybrid neural network for cluster membership
Identification of slightly sprouted wheat kernels using hyperspectral imaging technology and different deep convolutional neural networks
Identification of slightly sprouted wheat kernels using hyperspectral imaging technology and different deep convolutional neural networks
Read moreHuman Posture Detection Using Image Augmentation and Hyperparameter-Optimized Transfer Learning Algorithms
With the advancement in pose estimation techniques, human posture detection recently received considerable attention in many applications, including ergonomics and healthcare. When using neural network models, overfitting and poor performance are prevalent issues. Recently, convolutional neural networks (CNNs) were successfully used for human posture recognition from human images due to their superior multiscale high-level visual representations over hand-engineering low-level characteristics. However, calculating millions of parameters in a deep CNN requires a significant number of annotated examples, which prohibits many deep CNNs such as AlexNet and VGG16 from being used on issues with minimal training data. We propose a new three-phase model for decision support that integrates CNN transfer learning, image data augmentation, and hyperparameter optimization (HPO) to address this problem. The model is used as part of a new decision support framework for the optimization of hyperparameters for AlexNet, VGG16, CNN, and multilayer perceptron (MLP) models for accomplishing optimal classification results. The AlexNet and VGG16 transfer learning algorithms with HPO are used for human posture detection, while CNN and Multilayer Perceptron (MLP) were used as standard classifiers for contrast. The HPO methods are essential for machine learning and deep learning algorithms because they directly influence the behaviors of training algorithms and have a major impact on the performance of machine learning and deep learning models. We used an image data augmentation technique to increase the number of images to be used for model training to reduce model overfitting and improve classification performance using the AlexNet, VGG16, CNN, and MLP models. The optimal combination of hyperparameters was found for the four models using a random-based search strategy. The MPII human posture datasets were used to test the proposed approach. The proposed models achieved an accuracy of 91.2% using AlexNet, 90.2% using VGG16, 87.5% using CNN, and 89.9% using MLP. The study is the first HPO study executed on the MPII human pose dataset.
Read moreGraph convolutional network – Long short term memory neural network- multi layer perceptron- Gaussian progress regression model: A new deep learning model for predicting ozone concertation
Graph convolutional network – Long short term memory neural network- multi layer perceptron- Gaussian progress regression model: A new deep learning model for predicting ozone concertation
Read moreOptimization of horizontal axis wind turbine performance with the dimpled blades by using CNN and MLP models
Optimization of horizontal axis wind turbine performance with the dimpled blades by using CNN and MLP models
Prediction of I–V Characteristic Curve for Photovoltaic Modules Based on Convolutional Neural Network
Photovoltaic (PV) modules are exposed to the outside, which is affected by radiation, the temperature of the PV module back-surface, relative humidity, atmospheric pressure and other factors, which makes it difficult to test and analyze the performance of photovoltaic modules. Traditionally, the equivalent circuit method is used to analyze the performance of PV modules, but there are large errors. In this paper—based on machine learning methods and large amounts of photovoltaic test data—convolutional neural network (CNN) and multilayer perceptron (MLP) neural network models are established to predict the I–V curve of photovoltaic modules. Furthermore, the accuracy and the fitting degree of these methods for current–voltage (I–V) curve prediction are compared in detail. The results show that the prediction accuracy of the CNN and MLP neural network model is significantly better than that of the traditional equivalent circuit models. Compared with MLP models, the CNN model has better accuracy and fitting degree. In addition, the error distribution concentration of CNN has better robustness and the pre-test curve is smoother and has better nonlinear segment fitting effects. Thus, the CNN is superior to MLP model and the traditional equivalent circuit model in complex climate conditions. CNN is a high-confidence method to predict the performance of PV modules.
Read moreComparative Analysis of MLP, CNN, and RNN Models in Automatic Speech Recognition: Dissecting Performance Metric
This study conducts a comparative analysis of three prominent machine learning models: Multi-Layer Perceptrons (MLP), Convolutional Neural Networks (CNN), and Recurrent Neural Networks (RNN) with Long Short-Term Memory (LSTM) in the field of automatic speech recognition (ASR). This research is distinct in its use of the LibriSpeech 'test-clean' dataset, selected for its diversity in speaker accents and varied recording conditions, establishing it as a robust benchmark for ASR performance evaluation. Our approach involved preprocessing the audio data to ensure consistency and extracting Mel-Frequency Cepstral Coefficients (MFCCs) as the primary features, crucial for capturing the nuances of human speech. The models were meticulously configured with specific architectural details and hyperparameters. The MLP and CNN models were designed to maximize their pattern recognition capabilities, while the RNN (LSTM) was optimized for processing temporal data. To assess their performance, we employed metrics such as precision, recall, and F1-score. The MLP and CNN models demonstrated exceptional accuracy, with scores of 0.98 across these metrics, indicating their effectiveness in feature extraction and pattern recognition. In contrast, the LSTM variant of RNN showed lower efficacy, with scores below 0.60, highlighting the challenges in handling sequential speech data. The results of this study shed light on the differing capabilities of these models in ASR. While the high accuracy of MLP and CNN suggests potential overfitting, the underperformance of LSTM underscores the necessity for further refinement in sequential data processing. This research contributes to the understanding of various machine learning approaches in ASR and paves the way for future investigations. We propose exploring hybrid model architectures and enhancing feature extraction methods to develop more sophisticated, real-world ASR systems. Additionally, our findings underscore the importance of considering model-specific strengths and limitations in ASR applications, guiding the direction of future research in this rapidly evolving field.
Read moreImpact of Data Augmentation Techniques on the Implementation of a Combination Model of Convolutional Neural Network (CNN) and Multilayer Perceptron (MLP) for the Detection of Diseases in Rice Plants
Detection of disease in rice plants is important to avoid damage and reduce yields. In this study, the influence of data augmentation techniques on the application of a combination model of Convolutional Neural Network (CNN) and Multilayer Perceptron (MLP) was carried out to detect diseases in rice plants. This study uses a dataset of rice images for disease detection which contains 6034 images of rice with five categories, namely Bacterial Leaf Bligh, Blast, Brown Spot, normal, and tungro. This dataset is divided into three parts, namely training data, validation data and test data. The data augmentation techniques used are rotation, brightness and zoom on rice images. The combination model of CNN and MLP is built using the Python programming language and the TensorFlow deep learning framework. In measuring the success rate of the built model, it can be measured using the accuracy, precision and recall values obtained in the model test. Several scenarios were carried out to produce the best model, namely the use of data augmentation techniques, the number of layers and the number of iterations (epochs). From the experiments that have been carried out which have been tested with data as many as 25 digital images, the best model is obtained with an testing accuracy of 92%, 94% precision and 92% recall. This model applies a random zoom augmentation technique with a value of 0.5 – 1.0, CNN+MLP with 3 layers and a dataset ratio of 80:20 and an epoch early stop, This result has increased by more than 10%.
Read moreA Convolutional Neural Network Based Classification Approach for Breast Cancer Detection
Thousands of women worldwide are diagnosed with breast cancer yearly, which may be fatal if not treated. The diagnosis of the condition may take years, by which time the patient has little choice except to have the affected breast removed. Early diagnosis and treatments are the best ways to stop this disease's spread. In this study, the authors presented a Computer Aided Diagnosis (CAD) system to assist in breast cancer diagnosis. The study uses the Wisconsin breast cancer dataset to classify benign and malignant data. For the classification, three pre-trained Deep learning algorithms: Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Multilayer Perceptron (MLP), were used. A novel CNN model that exceeds the performance efficiency of three pre-trained models and requires minimal compilation time is proposed. A number of evaluation matrices are used to analyze the models' classification abilities. Upon closer inspection, it has been established that the proposed CNN model outperforms CNN, LSTM, and MLP models with validation accuracy of 97.85%. CNN and LSTM performed with accuracies of 94.12% with the Adagrad optimizer and 93.5% with the Adam optimizer, respectively. Furthermore, MLP performance with 92.44% accuracy using the Adam optimizer. The proposed CNN model achieves the lowest Loss value and compilation time. In addition, the models' recall value, precision, and f1-score are computed to pick out the most effective model for diagnosing breast cancer on numeric data.
Read moreCreation of wildfire susceptibility maps in the Mediterranean Region (Turkey) using convolutional neural networks and multilayer perceptron techniques
Creation of wildfire susceptibility maps in the Mediterranean Region (Turkey) using convolutional neural networks and multilayer perceptron techniques
Read moreAnalysis of Multi-class Classification of EEG Signals Using Deep Learning
After promising results of deep learning in numerous fields, researchers have started exploring Electroencephalography (EEG) data for human behaviour and emotion recognition tasks that have a wide range of practical applications. But it has been a huge challenge to study EEG data collected in a non-invasive manner due to its heterogeneity, vulnerability to various noise signals and variant nature to different subjects and mental states. Though several methods have been applied to classify EEG data for the aforementioned tasks, multi-class classification like digit recognition, using this type of data is yet to show satisfactory results. In this paper we have tried to address these issues using different data representation and modelling techniques for capturing as much information as possible for the specific task of digit recognition, paving the way for Brain Computer Interfacing (BCI). A public dataset collected using the MUSE headband with four electrodes (TP9, AF7, AF8, TP10) has been used for this work of categorising digits (0–9). Popular deep learning methodologies like CNN (Convolutional Neural Network) model on DWT (Discrete Wavelet Transform) scalogram, CNN model on connectivity matrix (mutual information of time series against another), MLP (Multilayer Perceptron) model on extracted statistical features from EEG signals and 1D CNN on time domain EEG signals have been well experimented with in this study. Additionally, methodologies like SVC (Support Vector Classifier), Random Forest and AdaBoost on extracted features have also been showcased. Nevertheless, the study provides an insight in choosing the best suited methodology for multi-class classification of EEG signals like digit recognition for further studies.
Read moreLevering machine learning to distinguish between optimal and suboptimal basketball shooting forms
Basketball is a highly competitive sport and good shooting form is crucial to a player’s success. For high shooting accuracy, several body parts must be aligned, including proper leg positioning, elbow placement, hand posture, and shooting wrist curvature. With the progress in machine learning, Artificial Intelligence (AI) tools can be developed to provide feedback and personalized guidance on basketball shooting form. In this research, we compared Multilayer Perceptron (MLP), Recurrent Neural Networks (RNN), and Convolutional Neural Networks (CNN) to identify the most suitable model for integration into AI tools meant for basketball shooting form analysis. We hypothesized that CNN models will perform significantly better for basketball shooting form analysis than RNN or MLP models because CNN models are known to be better suited for Human Action Recognition (HAR) than other models. We evaluated five models to test our hypothesis - an MLP and an RNN model using Cartesian coordinates of body joints, an MLP model using angles of body joints, and two video-based CNN models using raw and cropped video data. Contrary to initial expectations, the accuracy of the MLP model with Cartesian coordinates of body joints outperformed the CNN model with cropped video (88.3% versus 83.3%). Since MLP models typically require less computational resources, they can be used to build efficient AI tools for basketball shooting form analysis in resource-constrained environments such as mobile phones.
Read moreModeling ring current proton distribution using MLP, CNN, LSTM, and transformer networks
This study aims at developing ring current proton flux models using four neural network architectures: a multilayer perceptron (MLP), a convolutional neural network (CNN), a long short-term memory (LSTM) network, and a Transformer network. All models take time sequences of geomagnetic indices as inputs. Experimental results demonstrate that the LSTM and Transformer models consistently outperform the MLP and CNN models by achieving lower mean squared errors on the test set, possibly due to their intrinsic capability to process temporal sequential input data. Unlike MLP and CNN models, which require a fixed input history length even though proton lifetime varies with altitude, the LSTM and Transformer models accommodate variable-length sequences during both training and inference. Our findings indicate that the LSTM and Transformer architectures are well suited for modeling ring current proton behavior when GPU resources are available, and the Transformer slightly underperforms the LSTM model due to the restriction on the number of total heads. For resource-constrained environments, however, the MLP model offers a practical alternative, with faster training and inference times, while maintaining competitive accuracy.
Read moreImproving Deep Learning Parkinson’s Disease Detection Through Data Augmentation Training
Deep learning has been successfully applied to different classification applications where large data are available. However, the lack of data makes it more difficult to predict Parkinson’s disease (PD) with the deep models, which requires enough number of training data. Online handwriting dynamic signals can provide more detailed and complex information for PD detection task. In our previous work [1], two different deep models were studied for time series classification; the convolutional neural network (CNN) and the convolutional neural network- bidirectional long short term memory network (CNN-BLSTM). Different approaches were applied to encode pen-based signals into images for the CNN model while the raw time series are used directly with the CNN-BLSTM model. We have showed that both CNN model with spectrogram images as input and CNN-BLSTM model, improve the performance of time series classification applied for early PD stage detection. However, these approaches did not outperform classical support vector machine (SVM) classification applied on pre-engineered features. In this paper we investigate transfer learning and data augmentation approaches in order to train these models for PD detection on large-scale data. Various data augmentation methods for pen-based signals are proposed. Our experimental results show that the CNN-BLSTM model used with the combination of Jittering and Synthetic data augmentation methods provides promising results in the context of early PD detection, with accuracy reaching 97.62%. We have illustrated that deep architecture can surpass the models trained on pre-engineered features even though the available data is small.
Read moreCLASSIFICATION OF FRESH AND ROTTEN FRUITS USING DIFFERENT CNN MODELS
Fruit freshness automated classification is crucial to the agricultural sector. In the traditional procedure, a human being grades the fruit. Additionally, this process is labor-intensive, time-consuming, and ineffective. Additionally, it raises production costs. Therefore, a quick, precise, and automated system that may lessen human effort, enhance production, and decrease manufacturing time and cost is needed for industrial applications. The deep learning- based model for classifying fruit freshness is used in the current work. Various Convolution Neural Network (CNN) models are proposed, and they are implemented using the publicly available "fruit fresh and rotten for classification" kaggle dataset. Three fresh fruit varieties (Apple, Banana, and Oranges) and their rotting category are employed in an experiment using the dataset. From the given fruit photos, traits or attributes are extracted using a CNN model based on deep learning. The input photos are then divided into fresh and rotting categories by a softmax method. The classification of fresh and rotten fruits uses a variety of CNN models, including Resnet50 (50 Layers), InceptionV3 (48 Layers), and VGG16 (16 Layers). The proposed various CNN models accurately and efficiently evaluate the dataset. Later, the accuracy of the proposed CNN models is compared and the highest accuracy among the three CNN models is identified. In this way, the best accuracy CNN models will be identified for classifying the fresh and rotten fruits. KEYWORDS: Deep learning, CNN model, Inception V3, Resnet50, VGG16.
Read more