Simple Convolutional Neural Network Model Research Articles

Partial Discharge Pattern Recognition Based on an Ensembled Simple Convolutional Neural Network and a Quadratic Support Vector Machine

Partial discharge (PD) is a crucial and intricate electrical occurrence observed in various types of electrical equipment. Identifying and characterizing PDs is essential for upholding the integrity and reliability of electrical assets. This paper proposes an ensemble methodology aiming to strike a balance between the model complexity and the predictive performance in PD pattern recognition. A simple convolutional neural network (SCNN) was constructed to efficiently decrease the model parameters (quantities). A quadratic support vector machine (QSVM) was established and ensembled with the SCNN model to effectively improve the PD recognition accuracy. The input for QSVM consisted of the circular local binary pattern (CLBP) extracted from the enhanced image. A testing prototype with three types of PD was constructed and 3D phase-resolved pulse sequence (PRPS) spectrograms were measured and recorded by ultra-high frequency (UHF) sensors. The proposed methodology was compared with three existing lightweight CNNs. The experiment results from the collected dataset emphasize the benefits of the proposed method, showcasing its advantages in high recognition accuracy and relatively few mode parameters, thereby rendering it more suitable for PD pattern recognition on resource-constrained devices.

Brain tumor prediction and analysis based on simple CNN

The field of brain tumor prediction aims to detect potentially malignant tumors before overt symptoms appear. Early tumor detection can help tailor treatment pathways. To this end, this paper introduces a convolutional neural network (CNN) to construct a simple CNN analysis model. Subtle architectural changes to typical CNN designs are aimed at navigating and solving complex problems unique to medical imaging. Specifically, first, a preprocessing stage converts raw Magnetic Resonance Imaging (MRI) scans into analyzable data. This enables the model to delve into complex patterns in each image. Second, build a simple CNN model and evaluate it. Additionally, comparisons are made with established benchmarks set by traditional CNN architectures. The study further utilizes many available annotated datasets to develop a data augmentation paradigm that improves model resilience and generalizability. At the same time, the study deploys rigorous protocols to address and contain the ubiquitous overfitting threat, thereby enhancing the general applicability of the solution across a variety of healthcare settings. Empirical evaluations shed light on the significant superiority of the proposed simple CNN, especially in specific imaging environments and data structures. At the heart of this research is not only to expand technological horizons but also to reimagine clinical diagnostics to improve the standard of patient care.

Nosocomial transmission of Aspergillus flavus in a neonatal intensive care unit: Long-term persistence in environment and interest of MALDI-ToF mass-spectrometry coupled with convolutional neural network for rapid clone recognition.

Aspergillosis of the newborn remains a rare but severe disease. We report four cases of primary cutaneous Aspergillus flavus infections in premature newborns linked to incubators contamination by putative clonal strains. Our objective was to evaluate the ability of matrix-assisted laser desorption/ionisation time of flight (MALDI-TOF) coupled to convolutional neural network (CNN) for clone recognition in a context where only a very small number of strains are available for machine learning. Clinical and environmental A. flavus isolates (n=64) were studied, 15 were epidemiologically related to the four cases. All strains were typed using microsatellite length polymorphism. We found a common genotype for 9/15 related strains. The isolates of this common genotype were selected to obtain a training dataset (6 clonal isolates/25 non-clonal) and a test dataset (3 clonal isolates/31 non-clonal), and spectra were analysed with a simple CNN model. On the test dataset using CNN model, all 31 non-clonal isolates were correctly classified, 2/3 clonal isolates were unambiguously correctly classified, whereas the third strain was undetermined (i.e., the CNN model was unable to discriminate between GT8 and non-GT8). Clonal strains of A. flavus have persisted in the neonatal intensive care unit for several years. Indeed, two strains of A. flavus isolated from incubators in September 2007 are identical to the strain responsible for the second case that occurred 3 years later. MALDI-TOF is a promising tool for detecting clonal isolates of A. flavus using CNN even with a limited training set for limited cost and handling time.

A novel data augmentation approach for enhancement of ECG signal classification

The use of deep learning models in the classification of medical diseases has evolved drastically in recent years. One such prominent application was in the classification of ECG data with the goal of achieving high accuracy and computational efficiency. However, several challenges remain to be resolved to achieve this goal, such as finding a generalized model, data imbalance, and preserving patient privacy. This research aims to overcome the first two challenges. The novelty of the proposed work is to introduce unique data augmentation for time series ECG signal data based on simple segmentation and then re-arrangement of them. Simple in nature makes it more convenient to use minimal memory for the processing and allows to obtain well-distinguished synthetic signals. Additionally, a less computationally expensive four layers convolutional neural network (CNN) model has also been proposed. The original ECG signal wrapped in a Numpy array was divided into segments of identical length. During segment re-organization, a few section values are investigated, crucial for joining the segments back into a proper signal structure. The proposed algorithm has been evaluated in two ways, including similarity & features measure and classification accuracy through customized CNN & transfer learning model with five-fold cross-validation. The study results revealed that the proposed augmentation algorithm achieved a validation accuracy of 89.87% with 88.99% recall and 0.291 loss by the four layers CNN model. The presented work can be implemented in two ways, i.e., ECG signals dataset enhancement and better utilization of computational resources through the simple CNN model architecture.

Shaped patch based nonparametric discriminant analysis for hyperspectral image classification through the CNN model

ABSTRACT Convolutional neural network (CNN) has shown superior classification results for hyperspectral image classification. Due to high dimensionality of the hyperspectral image, usually a feature reduction method is applied to the hyperspectral data before feeding it to the CNN model. Principal component analysis is the most widely used approach to this end. However, it has two main disadvantages. It uses the mean square error measure and ignores the class separability. Moreover, it is a pixel-based method, which does not utilize the spatial information. To deal with these weaknesses, the patch-based nonparametric discriminant analysis method is proposed for hyperspectral image feature reduction in this work. However, due to the complex and heterogeneous nature of the hyperspectral images, the use of fixed square patches is not so appropriate. To deal with this difficulty, a shaping approach is introduced for the generation of adaptive patches with consistent shapes in each local region. The input patches of the CNN model are also weighted according to the spectral similarity and class boundaries information. Moreover, a simple residual CNN model is suggested for the classification of the extracted shaped input patches. The efficiency of the proposed framework is assessed in different cases using various evaluation measures on six real hyperspectral images.

OFPI: Optical Flow Pose Image for Action Recognition

Most approaches to action recognition based on pseudo-images involve encoding skeletal data into RGB-like image representations. This approach cannot fully exploit the kinematic features and structural information of human poses, and convolutional neural network (CNN) models that process pseudo-images lack a global field of view and cannot completely extract action features from pseudo-images. In this paper, we propose a novel pose-based action representation method called Optical Flow Pose Image (OFPI) in order to fully capitalize on the spatial and temporal information of skeletal data. Specifically, in the proposed method, an advanced pose estimator collects skeletal data before locating the target person and then extracts skeletal data utilizing a human tracking algorithm. The OFPI representation is obtained by aggregating these skeletal data over time. To test the superiority of OFPI and investigate the significance of the model having a global field of view, we trained a simple CNN model and a transformer-based model, respectively. Both models achieved superior outcomes. Because of the global field of view, especially in the transformer-based model, the OFPI-based representation achieved 98.3% and 94.2% accuracy on the KTH and JHMDB datasets, respectively. Compared with other advanced pose representation methods and multi-stream methods, OFPI achieved state-of-the-art performance on the JHMDB dataset, indicating the utility and potential of this algorithm for skeleton-based action recognition research.

Towards generalizable prediction of antibody thermostability using machine learning on sequence and structure features.

Over the last three decades, the appeal for monoclonal antibodies (mAbs) as therapeutics has been steadily increasing as evident with FDA's recent landmark approval of the 100th mAb. Unlike mAbs that bind to single targets, multispecific biologics (msAbs) have garnered particular interest owing to the advantage of engaging distinct targets. One important modular component of msAbs is the single-chain variable fragment (scFv). Despite the exquisite specificity and affinity of these scFv modules, their relatively poor thermostability often hampers their development as a potential therapeutic drug. In recent years, engineering antibody sequences to enhance their stability by mutations has gained considerable momentum. As experimental methods for antibody engineering are time-intensive, laborious, and expensive, computational methods serve as a fast and inexpensive alternative to conventional routes. In this work, we show two machine learning approaches - one with pre-trained language models (PTLM), and second, a supervised convolutional neural network (CNN) trained with Rosetta energetic features - to better classify thermostable scFv variants from sequence. Both of these models are trained over temperature-specific data (TS50 measurements) derived from multiple libraries of scFv sequences. On out-of-distribution (blind) sequences, we show that a sufficiently simple CNN model (ρ = 0.40) performs better than general pre-trained language (ρ = 0.15) and as well as an antibody-specific language model (ρ = 0.52). Further, we demonstrate that for an independent mAb with available thermal melting temperatures for 20 experimentally characterized thermostable mutations, these models could identify 18 residue positions and 5 identical amino-acid mutations showing remarkable generalizability. Our results suggest that such models can be broadly applicable for improving the biological characteristics of antibodies. Further, transferring such models for alternative physico-chemical properties of scFvs can have potential applications in optimizing large-scale production of msAbs.

Brain tumor detection system using neural networks

This research paper proposes a brain tumor detection system using neural networks. The authors use a dataset of Brain MRI Images for Brain Tumor Detection obtained from Kaggle.com and compare the performance of two models of Convolutional Neural Network (CNN). The first model is a simple CNN, and the second model is a model of hybrid deep learning Long-Short-Term Memory in Convolutional Neural Networks (CNN-LSTM). The experiments show that the CNN-LSTM model outperforms the simple CNN model in terms of accuracy, sensitivity, and specificity. The proposed system achieves high accuracy and can be used for accurate and efficient brain tumor detection.Cancer detection is a crucial task in the field of the health imaging. Traditional methods of detecting brain tumors are time-consuming and require a lot of expertise. With the advent of deep learning and neural networks, the detection of brain tumors has become more efficient and accurate. The use of neural networks for brain tumor detection has the potential to revolutionize the field of medical imaging and improve patient outcomes.

Enhancing classification of cells procured from bone marrow aspirate smears using generative adversarial networks and sequential convolutional neural network

Background and Objective: Leukemia represents 30% of all pediatric cancers and is considered the most common malignancy affecting adults and children. Cell differential count obtained from bone marrow aspirate smears is crucial for diagnosing hematologic diseases. Classification of these cell types is an essential task towards analyzing the disease, but it is time-consuming and requires intensive manual intervention. While machine learning has shown excellent outcomes in automating medical diagnosis, it needs ample data to build an efficient model for real-world tasks. This paper aims to generate synthetic data to enhance the classification accuracy of cells obtained from bone marrow aspirate smears. Methods: A three-stage architecture has been proposed. We first collaborate with experts from the medical domain to prepare a dataset that consolidates microscopic cell images obtained from bone marrow aspirate smears from three different sources. The second stage involves a generative adversarial networks (GAN) model to generate synthetic microscopic cell images. We propose a GAN model consisting of three networks; generator discriminator and classifier. We train the GAN model with the loss function of Wasserstein GAN with gradient penalty (WGAN-GP). Since our GAN has an additional classifier and was trained using WGAN-GP, we named our model C-WGAN-GP. In the third stage, we propose a sequential convolutional neural network (CNN) to classify cells in the original and synthetic dataset to demonstrate how generating synthetic data and utilizing a simple sequential CNN model can enhance the accuracy of cell classification. Results: We validated the proposed C-WGAN-GP and sequential CNN model with various evaluation metrics and achieved a classification accuracy of 96.98% using the synthetic dataset. We have presented each cell type’s accuracy, specificity, and sensitivity results. The sequential CNN model achieves the highest accuracy for neutrophils with an accuracy rate of 97.5%. The highest value for sensitivity and specificity are 97.1% and 97%. Our proposed GAN model achieved an inception score of 14.52 ± 0.10, significantly better than the existing GAN models. Conclusions: Using three network GAN architecture produced more realistic synthetic data than existing models. Sequential CNN model with the synthetic data achieved higher classification accuracy than the original data.

Feature Extraction From Images Using Integrated Photonic Convolutional Kernel

Optical neural networks are expected to solve the problems of computational efficiency and energy consumption in neural networks. Herein, we experimentally implemented a 2 × 2 photonic convolutional kernel (PCK) using four on-chip micro-ring resonators (MRRs) and demonstrated feature extraction for images with different convolutional kernels. We trained a simple convolutional neural network model to recognize the MNIST dataset and used our PCK devices for processing in the first convolutional layer, achieving a recognition rate of 91%, which further verified the feasibility of MRRs for convolution operations. In addition to the source, all silicon photonic devices used can be monolithically integrated and feature good scalability, which is important for realizing large-scale, low-cost optical neural networks.

Cross Validation Analysis of Convolutional Neural Network Variants with Various White Blood Cells Datasets for the Classification Task

White Blood Cells (WBCs) analysis is an important procedure to detect diseases is that closely related to human immunity system. Manual WBCs analysis is laborious and hence computer aided system (CAD) is a better option to alleviate the shortcoming. Since conventional segmentation-classification approach is tedious to configure, a Convolutional Neural Network (CNN) become recent trend for WBCs classification. Previously, there are many works proposed for WBCs identification. However, the models that can be generalised to works well among various datasets is remain vague. In this paper, an analysis of various CNN models which are simple Alexnet, embedded friendly Mobilenet, inception based Googlenet, systematic architecture VGG-16 and skip connection based model (Resnet & Densenet), are tested with three major WBCs datasets (Kaggle, LISC and IDB-2). From the rigorous experiments, it can be concluded that simple CNN model of Alexnet performs well across all three datasets with 98.08% accuracy on Kaggle, 96.34% accuracy on IDB-2 and 84.52% on LISC. This outcome can be utilise as a basis to improve the CNN classification model that can be generalize to works under various WBCs datasets.

A Security- and Privacy-Preserving Approach Based on Data Disturbance for Collaborative Edge Computing in Social IoT Systems

The Internet of things (IoT) has certainly become one of the hottest technology frameworks of the year. It is deep in many industries, affecting people’s lives in all directions. The rapid development of the IoT technology accelerates the process of the era of “Internet of everything” but also changes the role of terminal equipment at the edge of the network. It has changed from a single data user to a dual role of both producing and using data. And collaborative edge computing (CEC) has been born in time. CEC itself can not only solve the problem of computing and storage but also combines with the deep learning (DL) model to make full use of edge computing ability. However, as the core of DL, the robustness of neural network is often not high. In addition, edge devices of CEC are facing a highly dynamic environment, which can easily cause the edge network to be attacked by malicious devices. Therefore, user privacy protection and security issues for CEC deserve more attention. To avoid privacy leakage and security crisis of CEC in social IoT systems, a data protection method based on data disturbance method and adversarial training viewpoint is introduced in this article. Besides, a new adversarial sample generation method based on the firefly algorithm (FA) is proposed. This method reduces the time complexity of traditional by an order for magnitude compared with traditional generative adversarial network (GAN) generation. Since sentences, information on CEC in the IoT system is characterized by a large amount of data, strict confidentiality, and high-security requirements, and they are usually high-risk information on privacy leakage. The proposed method is conducted to the sentence similarity analysis model based on a convolutional neural network (CNN) in the CEC scene to test the feasibility of the method. Compared with the original CNN, the accuracy of the model using the confrontation training method is improved by 4.8%. At the same time, the security value of our model is 2.1% higher than that of the simple CNN model, and it has the best security performance among the four comparison models. Further experiments have demonstrated that the model performs better in its capacity of resisting disturbance and can effectively help multiple organizations to implement data usage and sentence information on the requirements of user privacy protection, data security, and government regulations.

Development of a Machine Learning Model for Image-based Email Spam Detection

Combatting email spam has remained a very daunting task. Despite the over 99% accuracy in most non-image-based spam email detection, studies on image-based spam hardly attain such a high level of accuracy as new email spamming techniques that defeat existing spam filters emerges from time to time. The number of email spams sent out daily has remained a key factor in the continued use of spam. In this paper, a simple convolutional neural network model, 123DNet was developed and trained with 28,929 images drawn from 2 public datasets and a Personally Generated dataset. The model was optimized to the least set of layers to have 1 input layer, 2 embedded Convolutional layers as a hidden layer, and 3 neural network layers. The model was tested with a total of 4,339 images of the three dataset samples and then with a separate set of 1,200 images to test performance on never-seen-before images. A Classification Performance analysis was carried out using the confusion matrix. Performance metrics including Accuracy, Precision, True Negative Accuracy, Sensitivity, Specificity, and F1 Measure were computed to ascertain the model’s performance. The Model returned an F1 Score of 97% on a public dataset’s test sample and 88% on Never-seen-before test samples outperforming some pre-existing models while performing significantly well on the newly generated image test samples. It is recommended that a model that performed so well with new never-seen-before spam images be integrated into spam filtering systems. Keywords- Convolutional Neural Network, Deep Learning, Image-based Spam Detection

Prediction and validation of the transverse mechanical behavior of unidirectional composites considering interfacial debonding through convolutional neural networks

In this work, we propose a prediction model of the transverse mechanical behavior of unidirectional (UD) composites containing complex microstructure with the help of a convolutional neural network (CNN). For this prediction, a total of 900 representative volume elements (RVE) samples were generated by constructing 300 RVEs for each V f of 40%, 50%, and 60% with the random sequential expansion (RSE) algorithm. The stress-strain (S–S) curves in terms of transverse elastic modulus , transverse tensile strength , and toughness considering interphase debonding were obtained by a finite element (FE) simulation with the RVE samples. After converting FE models with 900 RVE samples to corresponding microstructural binary images , CNN modeling was employed to construct a prediction model on the microstructural images. To demonstrate the performance of the proposed CNN model, we predicted the transverse mechanical behavior in terms of the S–S curves on various test datasets . Prediction accuracy was verified in terms of the loss functions and the error of the S–S curve. The prediction results were in excellent agreement with the test datasets, and the transverse mechanical behavior was quickly predicted for other microstructures. This confirmed that the proposed CNN model is simple and powerful and can efficiently clarify the relationship between the microstructure and transverse mechanical behavior of UD composites. • A simple and powerful data-driven CNN model is developed to predict the transverse mechanical behavior. • Interfacial debonding of UD composites and elastic-plastic behavior of matrix in composite materials is considered. • A convergence study of the CNN model is conducted according to the image resolution and the number of RVE samples. • The predicted nonlinear stress-strain curves showed excellent agreement with those of FE simulation.

Auto-detection of acoustic emission signals from cracking of concrete structures using convolutional neural networks: Upscaling from specimen

Acoustic emission (AE) monitoring has gained significant interest as a promising method for monitoring of changes in structural integrity and durability. Long-term AE monitoring needs to detect and distinguish crack signals from ambient noise (or dummy) signals; however, it is still a daunting task which currently limits field implementation of the AE method. Herein, we explore the feasibility of using convolutional neural network (CNN) models to detect AE crack signals from ambient signals. The trained models are validated both with noise-embedded synthesized signals and with upscaled physical model experiments simulating earthquake loading to a scaled model foundation by using a large-scale shaking table. The 2D CNN model trained the laboratory-synthesized signal sets effectively captured the crack and crack-free signals in all cases including the upscaled physical model experiments. This study presents a simple but robust CNN model for pre-filtering of crack signals and a novel training method for enhanced accuracy, which can be applied for real-time structural health monitoring of concrete-based structures.

ASSESSMENT OF COMBINING CONVOLUTIONAL NEURAL NETWORKS AND OBJECT BASED IMAGE ANALYSIS TO LAND COVER CLASSIFICATION USING SENTINEL 2 SATELLITE IMAGERY (TENES REGION, ALGERIA)

Abstract. Land cover maps can provide valuable information for various applications, such as territorial monitoring, environmental protection, urban planning and climate change prevention. In this purpose, remote sensing based on image classification approaches undergoing a high revolution can be dedicated to land cover mapping tasks. Similarly, deep learning models are considerably applied in remote sensing applications; which can automatically learn features from large amounts of data. Prevalently, the Convolutional Neural Network (CNN), have been increasingly performed in image classification. The aim of this study is to apply a new approach to analyse land cover, and extract its features. Experiments carried out on a coastal town located in north-western Algeria (Ténès region). The study area is chosen because of its importance as a part of the national strategy to combat natural hazards, specifically floods. As well as, a simple CNN model with two hidden layers was constructed, combined with an Object-Based Image Analysis (OBIA). In this regard, a Sentinel-2 image was used, to perform the classification, using spectral index combinations. Furthermore, to compare the performance of the proposed approach, an OBIA based on machines learning algorithms mainly Random Forest (RF) and Support Vector Machine (SVM), was provided. Results of accuracy assessment of classification showed good values in terms of Overall accuracy and Kappa Index, which reach to 93.1% and 0.91, respectively. As a comparison, CNN-OBIA approach outperformed OBIA based on RF algorithm. Therefore, Final land cover maps can be used as a support tool in regional and national decisions.

Automatic defect detection for fabric printing using a deep convolutional neural network

ABSTRACT Defect detection is a crucial step in textile and apparel quality control. An efficient defect detection system can ensure the overall quality of the processes and products that are acceptable to consumers. Existing techniques for real-time defect detection tend to vary according to unique manufacturing processes, focal defects and computational algorithms. Although the need is high, research related to automatic printed fabric defect detection processes is not prevalent in academic literatures. This research proposes a novel methodology that demonstrates the application of convolutional neural network (CNN) to classify printing defects based on the fabric images collected from industries. The research also integrated visual geometric group (VGG), DenseNet, Inception and Xception deep learning networks to compare model performance. The results exhibit that the VGG-based models perform better compared to a simple CNN model, suggesting promise for automatic defect detection (ADD) of printed fabrics that can improve profitability in fashion supply chains.

Codeless Deep Learning of COVID-19 Chest X-Ray Image Dataset with KNIME Analytics Platform.

ObjectivesThis paper proposes a method for computer-assisted diagnosis of coronavirus disease 2019 (COVID-19) through chest X-ray imaging using a deep learning model without writing a single line of code using the Konstanz Information Miner (KNIME) analytics platform.MethodsWe obtained 155 samples of posteroanterior chest X-ray images from COVID-19 open dataset repositories to develop a classification model using a simple convolutional neural network (CNN). All of the images contained diagnostic information for COVID-19 and other diseases. The model would classify whether a patient was infected with COVID-19 or not. Eighty percent of the images were used for model training, and the rest were used for testing. The graphic user interface-based programming in the KNIME enabled class label annotation, data preprocessing, CNN model training and testing, performance evaluation, and so on.Results1,000 epochs training were performed to test the simple CNN model. The lower and upper bounds of positive predictive value (precision), sensitivity (recall), specificity, and f-measure are 92.3% and 94.4%. Both bounds of the model’s accuracies were equal to 93.5% and 96.6% of the area under the receiver operating characteristic curve for the test set.ConclusionsIn this study, a researcher who does not have basic knowledge of python programming successfully performed deep learning analysis of chest x-ray image dataset using the KNIME independently. The KNIME will reduce the time spent and lower the threshold for deep learning research applied to healthcare.

Shoulder muscle activation pattern recognition based on sEMG and machine learning algorithms

Background and ObjectiveSurface electromyography (sEMG) has been used for robotic rehabilitation engineering for volitional control of hand prostheses or elbow exoskeleton, however, using sEMG for volitional control of an upper limb exoskeleton has not been perfectly developed. The long-term goal of our study is to process shoulder muscle bio-electrical signals for rehabilitative robotic assistive device motion control. The purposes of this study included: 1) to test the feasibility of machine learning algorithms in shoulder motion pattern recognition using sEMG signals from shoulder and upper limb muscles, 2) to investigate the influence of motion speed, individual variability, EMG recording device, and the amount of EMG datasets on the shoulder motion pattern recognition accuracy. MethodsA novel convolutional neural network (CNN) structure was constructed to process EMG signals from 12 muscles for the pattern recognition of upper arm motions including resting, drinking, backward-forward motion, and abduction motion. The accuracy of the CNN models for pattern recognition under different motion speeds, among individuals, and by EMG recording devices was statistically analyzed using ANOVA, GLM Univariate analysis, and Chi-square tests. The influence of EMG dataset number used for CNN model training on recognition accuracy was studied by gradually increasing dataset number until the highest accuracy was obtained. ResultsResults showed that the accuracy of the normal speed CNN model in motion pattern recognition was 97.57% for normal speed motions and 97.07% for fast speed motions. The accuracy of the cross-subjects CNN model in motion pattern recognition was 79.64%. The accuracy of the cross-device CNN model in motion pattern recognition was 88.93% for normal speed motion and 80.87% for mixed speed. There was a statistical difference in pattern recognition accuracy between different CNN models. ConclusionThe EMG signals of shoulder and upper arm muscles from the upper limb motions can be processed using CNN algorithms to recognize the identical motions of the upper limb including drinking, forward/backward, abduction, and resting. A simple CNN model trained by EMG datasets of a designated motion speed accurately detected the motion patterns of the same motion speed, yielding the highest accuracy compared with other mixed CNN models for various speeds of motion pattern recognition. Increase of the number of EMG datasets for CNN model training improved the pattern recognition accuracy.

Comparison of Convolutional Neural Network Model in Classification of Diabetic Retinopathy

<p class="JGI-AbstractIsi">Untreated diabetes mellitus will cause complications, and one of the diseases caused by it is Diabetic Retinopathy (DR). Machine learning is one of the methods that can be used to classify DR. Convolutional Neural Network (CNN) is a branch of machine learning that can classify images with reasonable accuracy. The Messidor dataset, which has 1,200 images, is often used as a dataset for the DR classification. Before training the model, we carried out several data preprocessing, such as labeling, resizing, cropping, separation of the green channel of images, contrast enhancement, and changing image extensions. In this paper, we proposed three methods of DR classification: Simple CNN, Le-Net, and DRnet model. The accuracy of testing of the several models of test data was 46.7%, 51.1%, and 58.3% Based on the research, we can see that DR classification must use a deep architecture so that the feature of the DR can be recognized. In this DR classification, DRnet achieved better accuracy with an average of 9.4% compared to Simple CNN and Le-Net model.</p>