Efficient Classification Approach Research Articles

Conception and realization of an IoT-enabled deep CNN decision support system for automated arrhythmia classification

Abstract Arrhythmias are irregular heartbeats that may be life-threatening. Proper monitoring and the right care at the right time are necessary to keep the heart healthy. Monitoring electrocardiogram (ECG) patterns on continuous monitoring devices is time-consuming. An intense manual inspection by caregivers is not an option. In addition, such an inspection could result in errors and inter-variability. This article proposes an automated ECG beat classification method based on deep neural networks (DNN) to aid in the detection of cardiac arrhythmias. The data collected by an Internet of Things enabled ECG monitoring device are transferred to a server. They are analysed by a deep learning model, and the results are shared with the primary caregiver. The proposed model is trained using the MIT-BIH ECG arrhythmia database to classify into four classes: normal beat (N), left bundle branch block beat (L), right bundle branch block beat (R), and premature ventricular contraction (V). The received data are sampled with an overlapping sliding window and divided into an 80:20 ratio for training and testing, with tenfold cross-validation. The proposed method achieves higher accuracy with a simple model without any preprocessing when compared with previous works. For the train and test sets, we achieved accuracy rates of 99.09 and 99.03%, respectively. A precision, recall, and F1 scores of 0.99 is obtained. The proposed model achieves its goal of developing a simple and accurate ECG monitoring system with improved performance. This simple and efficient deep learning approach for heartbeat classification could be applied in real-time telehealth monitoring systems.

A Novel and Effective Brain Tumor Classification Model Using Deep Feature Fusion and Famous Machine Learning Classifiers.

Brain tumors are difficult to treat and cause substantial fatalities worldwide. Medical professionals visually analyze the images and mark out the tumor regions to identify brain tumors, which is time-consuming and prone to error. Researchers have proposed automated methods in recent years to detect brain tumors early. These approaches, however, encounter difficulties due to their low accuracy and large false-positive values. An efficient tumor identification and classification approach is required to extract robust features and perform accurate disease classification. This paper proposes a novel multiclass brain tumor classification method based on deep feature fusion. The MR images are preprocessed using min-max normalization, and then extensive data augmentation is applied to MR images to overcome the lack of data problem. The deep CNN features obtained from transfer learned architectures such as AlexNet, GoogLeNet, and ResNet18 are fused to build a single feature vector and then loaded into Support Vector Machine (SVM) and K-nearest neighbor (KNN) to predict the final output. The novel feature vector contains more information than the independent vectors, boosting the proposed method's classification performance. The proposed framework is trained and evaluated on 15,320 Magnetic Resonance Images (MRIs). The study shows that the fused feature vector performs better than the individual vectors. Moreover, the proposed technique performed better than the existing systems and achieved accuracy of 99.7%; hence, it can be used in clinical setup to classify brain tumors from MRIs.

Feature optimization and identification of ovarian cancer using internet of medical things

AbstractOvarian cancer (OC) is one kind of tumour that impacts women's ovaries and is hard to diagnose in the initial phase as a primary cause of cancer death. The ovarian cancer information generated by the Clinical Network has been used, and the Self Organizing Map (SOM) and Optimized Neural Networks have suggested a new method for the distinction between ovarian cancer and remaining cancer. Feature optimization and identification of the ovarian cancer (FOI‐OV) framework are proposed in this research. The SOM algorithm has also been used separately to improve the functional subset, with understandable and intriguing information from participants' health information steps. The SOM‐based collection appears to be tolerable in guided learning strategies due to the lack of different classifiers, which would direct the quest for knowledge specific to the classification algorithm. The classification technique will classify data from ovarian cancer as benign/malignant. By optimizing Neural Network configuration, Advanced Harmony Searching Optimization (AHSO) can enhance the ovarian cancer detection method compared with other methods. This research's suggested model can also diagnose cancer with high precision, and low root means square error (RMSE) early. With 94% precision and 0.029%, RMSE, SOM, and NN techniques have shown identification and precision in ovarian cancer. Optimization (AHSO) has provided an efficient classification approach with a better failure rate.

Analyzing the performance of photovoltaic systems using support vector machine classifier

The performance of a photovoltaic system depends on several parameters such as temperature, clouds, season, etc. This makes the study of Photovoltaic (PV) performance from monitoring databases very complex given the size of the information and the complexity of the phenomena involved. This article proposes an efficient classification and analysis approach based on the Support Vector Machine (SVM) classification in order to simplify and optimize the processing of this data and the study of the performance of PV systems. More precisely, we are applying the SVM; the data changes from variables to multiclass for simplifying the analysis. We have detailed all the calculation steps. Based on the application of artificial intelligence (Classification), the recorded data (output power, temperature of the PV module, solar irradiation, ambient temperature, etc.) can be analyzed and processed easily. The results of the performance analysis of a 270 W mono-crystalline PV module after seven (07) months of monitoring were studied. • Application of classification in the analysis of monitoring database. • SVM method for analyzing the performance of photovoltaic systems. • Simplifier the big data monitoring for analyzing the performance of photovoltaic systems. • Using SVM classification for treated the electrical parameters (P max ).

Development of a chickpea disease detection and classification model using deep learning

Ethiopia is the largest producer of chickpeas in Africa. Crop production and yield in Ethiopia is greatly affected by plant diseases which cause loss of agricultural products every year. One of these plant diseases is chickpea disease which is a fungal disease. Ascochyta blight and Fusarium wilt are the most common chickpea diseases in Ethiopia that affect crop production quality and quantity. The identification of these diseases requires experienced experts or systems. Although numerous methods have been previously adopted in literature, deep learning (DL) is suggested as an efficient approach for disease recognition and classification since it can automatically learn features from the input image. In this paper, a chickpea disease detection model was developed using deep learning techniques by combining Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) for feature extraction and Softmax for classification. To develop the proposed model, various image preprocessing stages such as image resizing, normalization, and noise filtering using a combination of Gaussian filter (GF) and Median filter (MF) were performed. To prevent the problem of overfitting, augmentation was applied, while to train and test the effectiveness of the developed model, 8391 images were used. From the acquired images, 80% of the dataset was used for training, 20% of the dataset was used for testing and out of the 80% training data, 20% was used for validation. The proposed CNN-LSTM performed well in identifying chickpea disease, with an accuracy of 92.55%. According to the study's findings, the proposed CNN-LSTM outperforms existing methods.

An Efficient Approach for Crops Pests Recognition and Classification Based on Novel DeepPestNet Deep Learning Model

Crop pests are to blame for significant economic, social, and environmental losses worldwide. Various pests have different control strategies, and precisely identifying pests has become crucial to pest control and is a significant difficulty in agriculture. Many agricultural professionals are interested in deep learning (DL) models since they have shown significant promise in image recognition. Pest identification approaches in literature have relatively low accuracy in pest recognition and classification due to the complexity of their algorithms and limited data availability. Misclassification of insect pests sometimes leads to using the wrong pesticides, causing harm to agricultural yields and the surrounding environment. It necessitates developing an automated system capable of more accurate pest identification and classification. This paper presents a novel end-to-end DeepPestNet framework for pest recognition and classification. The proposed model has 11 learnable layers, including eight convolutional and three fully connected (FC) layers. We used image rotations techniques to increase the size of the dataset and image augmentations techniques to test the generalizability of the proposed DeepPestNet approach. We used the popular Deng’s crops data set to assess the proposed DeepPestNet framework. We used the proposed method to recognize and classify crop pests into 10-class pests, i.e., Locusta migratoria, Euproctis pseudoconspersa strand, chrysochus Chinensis, empoasca flavescens, Spodoptera exigua, larva of laspeyresia pomonella, parasa lepida, acrida cinerea, larva of S. exigua, and L.pomonella types of insects pests. The proposed method achieved optimal accuracy of 100%. We compared the proposed DeepPestNet approach with traditional pre-trained deep learning (DL) models. To verify the general adaptability of this model, we tested the proposed model on the standard Kaggle dataset “Pest Dataset” to recognize nine types of pests: aphids, armyworm, beetle, bollworm, grasshopper, mites, mosquito, sawfly, and stem borer and achieved an accuracy of 98.92%. The proposed model can provide specialists and farmers with immediate and effective aid in recognizing pests, potentially reducing economic and crop yield losses.

An Efficient CNN-Based Hybrid Classification and Segmentation Approach for COVID-19 Detection

COVID-19 remains to proliferate precipitously in the world. It has significantly influenced public health, the world economy, and the persons’ lives. Hence, there is a need to speed up the diagnosis and precautions to deal with COVID-19 patients. With this explosion of this pandemic, there is a need for automated diagnosis tools to help specialists based on medical images. This paper presents a hybrid Convolutional Neural Network (CNN)-based classification and segmentation approach for COVID-19 detection from Computed Tomography (CT) images. The proposed approach is employed to classify and segment the COVID-19, pneumonia, and normal CT images. The classification stage is firstly applied to detect and classify the input medical CT images. Then, the segmentation stage is performed to distinguish between pneumonia and COVID-19 CT images. The classification stage is implemented based on a simple and efficient CNN deep learning model. This model comprises four Rectified Linear Units (ReLUs), four batch normalization layers, and four convolutional (Conv) layers. The Conv layer depends on filters with sizes of 64, 32, 16, and 8. A 2 × 2 window and a stride of 2 are employed in the utilized four max-pooling layers. A soft-max activation function and a Fully-Connected (FC) layer are utilized in the classification stage to perform the detection process. For the segmentation process, the Simplified Pulse Coupled Neural Network (SPCNN) is utilized in the proposed hybrid approach. The proposed segmentation approach is based on salient object detection to localize the COVID-19 or pneumonia region, accurately. To summarize the contributions of the paper, we can say that the classification process with a CNN model can be the first stage a highly-effective automated diagnosis system. Once the images are accepted by the system, it is possible to perform further processing through a segmentation process to isolate the regions of interest in the images. The region of interest can be assesses both automatically and through experts. This strategy helps so much in saving the time and efforts of specialists with the explosion of COVID-19 pandemic in the world. The proposed classification approach is applied for different scenarios of 80%, 70%, or 60% of the data for training and 20%, 30, or 40% of the data for testing, respectively. In these scenarios, the proposed approach achieves classification accuracies of 100%, 99.45%, and 98.55%, respectively. Thus, the obtained results demonstrate and prove the efficacy of the proposed approach for assisting the specialists in automated medical diagnosis services.

Semiconductor Multivariate Time-Series Anomaly Classification based on Machine Learning Ensemble Techniques*

This paper proposes an efficient multivariate time-series fault detection and classification approach aiming to detect faulty wafers (i.e. pieces of silicon) during semiconductor manufacturing process. This approach is based on using Independent Component Analysis (ICA) and several Machine Learning Ensemble Techniques. The main objective is to extract the most useful information from each time-series and combine them to build a set of fully concatenated features. Thereafter, Extra Trees, Random Forest, Gradient Boosting and Extreme Gradient Boosting, one of the prevalent evolutions of tree-based algorithms, are fitted to the extracted features subset to design and implement an efficient anomaly detection strategy. The obtained results show that the proposed technique is very efficient and very promising.

Constrained Naïve Bayes with application to unbalanced data classification

The Naïve Bayes is a tractable and efficient approach for statistical classification. In general classification problems, the consequences of misclassifications may be rather different in different classes, making it crucial to control misclassification rates in the most critical and, in many realworld problems, minority cases, possibly at the expense of higher misclassification rates in less problematic classes. One traditional approach to address this problem consists of assigning misclassification costs to the different classes and applying the Bayes rule, by optimizing a loss function. However, fixing precise values for such misclassification costs may be problematic in realworld applications. In this paper we address the issue of misclassification for the Naïve Bayes classifier. Instead of requesting precise values of misclassification costs, threshold values are used for different performance measures. This is done by adding constraints to the optimization problem underlying the estimation process. Our findings show that, under a reasonable computational cost, indeed, the performance measures under consideration achieve the desired levels yielding a user-friendly constrained classification procedure.

An MRI-based deep learning approach for efficient classification of brain tumors

An MRI-based deep learning approach for efficient classification of brain tumors

An efficient approach for clustering and classification for fraud detection using bankruptcy data in IoT environment

An efficient approach for clustering and classification for fraud detection using bankruptcy data in IoT environment

機械学習によるクラシフィケーションと気液二相流への応用

Gas-liquid two-phase flow is seen in various engineering disciplines and understanding of its interfacial structure is a great importance for proper model development. Flow regime maps have been developed by various researchers in the past. However, identification of flow regime involves subjectivity and technical difficulty as the nature of flow regime transition mechanism and criteria are still yet unknown. In the present article, various two-phase flow regime identification methods utilizing machine learning (ML) approach will be reviewed. Two-phase flow features such as two-phase mixture impedance, dynamic force signal, and high-resolution images from high-speed camera were selected for the ML model training and testing. For the machine learning models, artificial neural network (ANN), convolutional neural network (CNN), and convolutional long short-term memory (ConvLSTM) were tested, depending on the feature types. As a result, the ML approach can identify two-phase flow regime with high accuracy. There still remains issues related to ML usage, including hyperparameter selection, and ability to explain its decisions. However, adaptation of ML tools for multiphase flow research fields may provide utmost benefits for efficient signal and image classification approach.

A Deep Learning-Based Framework for Human Activity Recognition in Smart Homes

Human behavior modeling in smart environments is a growing research area treating several challenges related to ubiquitous computing, pattern recognition, and ambient assisted living. Thanks to recent progress in sensing devices, it is now possible to design computational models able of accurate detection of residents’ activities and daily routines. For this goal, we introduce in this paper a deep learning-based framework for activity recognition in smart homes. This framework proposes a detailed methodology for data preprocessing, feature mining, and deep learning techniques application. The novel framework was designed to ensure a deep exploration of the feature space since three main approaches are tested, namely, the all-features approach, the selection approach, and the reduction approach. Besides, the framework proposes the evaluation and the comparison of several well-chosen deep learning techniques such as autoencoder, recurrent neural networks (RNN), and some of their derivatives models. Concretely, the framework was applied on the “Orange4Home” dataset which represents a recent dataset specially designed for smart homes research. Our main findings show that the best approach for efficient classification is the selection approach. Furthermore, our overall results outperformed baseline models based on random forest classifiers and the principal component analysis technique, especially the results of our RNN-based model for the all-features approach and the results of our autoencoder-based model for the feature reduction approach.

Deep learning-based improved snapshot ensemble technique for COVID-19 chest X-ray classification.

COVID-19 has proven to be a deadly virus, and unfortunately, it triggered a worldwide pandemic. Its detection for further treatment poses a severe threat to researchers, scientists, health professionals, and administrators worldwide. One of the daunting tasks during the pandemic for doctors in radiology is the use of chest X-ray or CT images for COVID-19 diagnosis. Time is required to inspect each report manually. While a CT scan is the better standard, an X-ray is still useful because it is cheaper, faster, and more widely used. To diagnose COVID-19, this paper proposes to use a deep learning-based improved Snapshot Ensemble technique for efficient COVID-19 chest X-ray classification. In addition, the proposed method takes advantage of the transfer learning technique using the ResNet-50 model, which is a pre-trained model. The proposed model uses the publicly accessible COVID-19 chest X-ray dataset consisting of 2905 images, which include COVID-19, viral pneumonia, and normal chest X-ray images. For performance evaluation, the model applied the metrics such as AU-ROC, AU-PR, and Jaccard Index. Furthermore, it also obtained a multi-class micro-average of 97% specificity, 95% f1-score, and 95% classification accuracy. The obtained results demonstrate that the performance of the proposed method outperformed those of several existing methods. This method appears to be a suitable and efficient approach for COVID-19 chest X-ray classification.

HeartNetEC: a deep representation learning approach for ECG beat classification.

One of the most crucial and informative tools available at the disposal of a Cardiologist for examining the condition of a patient's cardiovascular system is the electrocardiogram (ECG/EKG). A major reason behind the need for accurate reconstruction of ECG comes from the fact that the shape of ECG tracing is very crucial for determining the health condition of an individual. Whether the patient is prone to or diagnosed with cardiovascular diseases (CVDs), this information can be gathered through examination of ECG signal. Among various other methods, one of the most helpful methods in identifying cardiac abnormalities is a beat-wise categorization of a patient's ECG record. In this work, a highly efficient deep representation learning approach for ECG beat classification is proposed, which can significantly reduce the burden and time spent by a Cardiologist for ECG Analysis. This work consists of two sub-systems: denoising block and beat classification block. The initial block is a denoising block that acquires the ECG signal from the patient and denoises that. The next stage is the beat classification part. This processes the input ECG signal for finding out the different classes of beats in the ECG through an efficient algorithm. In both stages, deep learning-based methods have been employed for the purpose. Our proposed approach has been tested on PhysioNet's MIT-BIH Arrhythmia Database, for beat-wise classification into ten important types of heartbeats. As per the results obtained, the proposed approach is capable of making meaningful predictions and gives superior results on relevant metrics.

Touch Modality Classification Using Recurrent Neural Networks

Recurrent Neural Networks (RNNs) are mainly designed to deal with sequence prediction problems and they show their effectiveness in processing data originally represented as time series. This paper investigates the time series characteristics of RNNs to classify touch modalities represented as spatio temporal 3D tensor data. Different approaches are followed in order to propose efficient RNN models aimed at tactile data classification. The main idea is to capture long-term dependence from data that can be used to deal with long sequences represented by employing Gated Recurrent Unit (GRU) and Long Short-Term Memory (LSTM) architectures. Moreover, a case specific approach to dataset organization of the 3D tensor data is presented. The target is to provide efficient hardware-friendly touch modality classification approaches suitable for embedded applications. To this end, the proposed work achieves effective performance in terms of hardware complexity by reducing the FLOPS by 99.98% and the memory storage by 98.34%, with respect to the state-of-art solutions on the same benchmark dataset. This directly affects the time latency and energy consumption of the embedded hardware. Besides, the implemented models shows a classification accuracy higher than those state-of-art solutions. Results demonstrate that the proposed computing architecture is scalable showing acceptable complexity when the system is scaled up in terms of input matrix size and number of classes to be recognized.

ELIS++: a shapelet learning approach for accurate and efficient time series classification

In recent years, time series classification with shapelets, due to the high accuracy and good interpretability, has attracted considerable interests. These approaches extract or learn shapelets from the training time series. Although they can achieve higher accuracy than other approaches, there still confront some challenges. First, they may suffer from low accuracy in the case of small training dataset. Second, they must manually set some parameters, like the number of shapelets and the length of each shapelet beforehand, and some hyper-parameters, like learning rate and regulation weight, which are difficult to set without prior knowledge. Third, extracting or learning shapelets incurs a huge computation cost, due to the huge search space. In this paper, we extend our previous shapelet learning approach ELIS to ELIS++. To improve the accuracy on the small training dataset, we propose a data augmentation approach. To learn the higher quality shapelets, based on the PAA shapelet candidates search technique proposed in ELIS, ELIS++ first propose a novel entropy-based approach shapelet candidate selection mechanism to discover shapelet candidates, and then applies the logistic regression model to adjust shapelets.To avoid setting other parameters manually, we propose a Bayesian Optimization based approach. Moreover, two techniques are proposed to improve the efficiency, coarse-grained shapelet adjustment and SIMD-based parallel computation. We conduct extensive experiments on 35 UCR datasets, and results verify the effectiveness and efficiency of ELIS++.

A Matrix Determinant Feature Extraction Approach for Decoding Motor and Mental Imagery EEG in Subject-Specific Tasks

This study introduces a novel matrix determinant feature extraction approach for efficient classification of motor and mental imagery activities from electroencephalography (EEG) signals. First, the multiscale principal component analysis was utilized to obtain clean EEG signals. Second, denoised data were sequentially arranged to form a square matrix of different orders (e.g.,10, 13, 16, and 20) and determinant was computed for each order matrix. Finally, the extracted matrix determinant features were provided to several machine learning and neural network classification models for classification. All experiments were carried out using a 10-fold cross-validation approach on three publicly accessible data sets: 1) data set IV-a; 2) data set IV-b; and 3) data set V of BCI competition III. Also, this study designs a computerized automatic detection of motor and mental imagery graphical user interface that can assist physicians/experts to efficiently analyses motor and mental imagery data. The experimental results reveal that the highest average classification accuracy of 99.55% (for data set IV-a), 99.52% (for data set IV-b), and 91.80% (for data set V) was obtained for motor and mental imagery, respectively, with 20-order matrix determinant using a feedforward neural network classifier. The experimental results suggest that the proposed framework provides a robust biomarker with the least computational complexity for the development of automated brain–computer interfaces.

Developing intelligent medical image modality classification system using deep transfer learning and LDA

Rapid advancement in imaging technology generates an enormous amount of heterogeneous medical data for disease diagnosis and rehabilitation process. Radiologists may require related clinical cases from medical archives for analysis and disease diagnosis. It is challenging to retrieve the associated clinical cases automatically, efficiently and accurately from the substantial medical image archive due to diversity in diseases and imaging modalities. We proposed an efficient and accurate approach for medical image modality classification that can used for retrieval of clinical cases from large medical repositories. The proposed approach is developed using transfer learning concept with pre-trained ResNet50 Deep learning model for optimized features extraction followed by linear discriminant analysis classification (TLRN-LDA). Extensive experiments are performed on challenging standard benchmark ImageCLEF-2012 dataset of 31 classes. The developed approach yields improved average classification accuracy of 87.91%, which is higher up-to 10% compared to the state-of-the-art approaches on the same dataset. Moreover, hand-crafted features are extracted for comparison. Performance of TLRN-LDA system demonstrates the effectiveness over state-of-the-art systems. The developed approach may be deployed to diagnostic centers to assist the practitioners for accurate and efficient clinical case retrieval and disease diagnosis.

Quality Evaluation of Reverberant Speech Based on Deep Learning

This paper presents an efficient approach for classification of speech signals as reverberant or not. The reverberation is a severe effect encountered in closed room. So, it may affect subsequent processes and deteriorate speech processing system performance. The spectrograms are utilized as images generated from speech signals to be classified with deep convolutional neural networks. Spectrogram and MFCC are used as features to be classified with Long Short Term Recurrent Neural Network (LSTM RNN). Two models are presented and compared. Simulation results up to 100% classification accuracy are obtained. This can help in perform an initial step in any speech processing system that comprises quality level classification.