Multi Class Research Articles

Monitoring chest compressions using finger photoplethysmography in out-of-hospital cardiac arrest

Quality cardiopulmonary resuscitation (CPR) is crucial to increase the probability of survival during out-of-hospital cardiac arrest (OHCA). Continuous chest compressions (CCs) provided with appropriate rate are recommended by the guidelines. Currently, defibrillators and monitors may integrate additional hardware to monitor CCs and give feedback to the rescuer to align CC rate with recommended values. Photoplethysmogram (PPG) obtained with pulse oximeters measures the oxygen saturation in the blood using non invasive and inexpensive technology. This study proposes a method based on the finger PPG to detect the presence of CCs and compute the CC rate. A total of 153 segments from 66 OHCA patients, with 470min and 48496 CCs, were analyzed. The algorithm classifies 5s windows as either CC or CC-pause using a logistic regression classifier with Lasso regularization based on time, spectral, correlation, statistical and entropy features. The rate was computed for windows with CCs using the autocorrelation function. Results were compared to the ground truth obtained from the compression depth signal derived from an sternal accelerometer. The method was evaluated using 10 fold cross-validation, and the median(IQR) for 5 feature model were 90.7(6.3)% sensitivity, 98.3(1.3)% positive predictive value, 94.6(3.1)% F1 and 94.4(4.8)% area under the curve. The median(IQR) of the absolute error in CC rate was 1.7(2.7)min−1, with 2.6(9.1)% of the windows with errors above 10%. This is the first approach that analyzes the feasibility of the PPG to monitor CPR, and an accurate automated solution based on a multifeature classification model was demonstrated.

Diabetic Retinopathy Detection and Multi Stage Classification using Deep Learning Models: A Quick Review

Diabetic Retinopathy Detection and Multi Stage Classification using Deep Learning Models: A Quick Review

A Multi-Stage Faster RCNN-Based iSPLInception for Skin Disease Classification Using Novel Optimization.

Nowadays, skin cancer is considered a serious disorder in which early identification and treatment of the disease are essential to ensure the stability of the patients. Several existing skin cancer detection methods are introduced by employing deep learning (DL) to perform skin disease classification. Convolutional neural networks (CNNs) can classify melanoma skin cancer images. But, it suffers from an overfitting problem. Therefore, to overcome this problem and to classify both benign and malignant tumors efficiently, the multi-stage faster RCNN-based iSPLInception (MFRCNN-iSPLI) method is proposed. Then, the test dataset is used for evaluating the proposed model performance. The faster RCNN is employed directly to perform image classification. This may heavily raise computation time and network complications. So, the iSPLInception model is applied in the multi-stage classification. In this, the iSPLInception model is formulated using the Inception-ResNet design. For candidate box deletion, the prairie dog optimization algorithm is utilized. We have utilized two skin disease datasets, namely, ISIC 2019 Skin lesion image classification and the HAM10000 dataset for conducting experimental results. The methods' accuracy, precision, recall, and F1 score values are calculated, and the results are compared with the existing methods such as CNN, hybrid DL, Inception v3, and VGG19. With 95.82% accuracy, 96.85% precision, 96.52% recall, and 0.95% F1 score values, the output analysis of each measure verified the prediction and classification effectiveness of the method.

Clustered ensemble feature selection with M-GRU classification for efficient intrusion detection system of industrial systems

Industrial Control Systems (ICS) are susceptible to threats or attacks, and even minor changes or manipulation could cause major damage to industrial operations. Industrial control system cybersecurity is vital owing to the severe negative effects it could have on the economy, the environment, people, and politics. Therefore, it’s also crucial to design intrusion detection systems for industrial control systems. In this paper, an efficient intrusion detection system with clustered ensemble feature selection and a Multi-Level Modified Gated Recurrent Unit (M-GRU) classification model is proposed. This intrusion detection system with a general framework for clustered ensemble feature ranking approach is proposed to effectively find the best feature subset in network packet traffic data. The features designated are fed into a multi class classification algorithm Multi-Level Modified Gated Recurrent Unit (M-GRU) to efficiently detect the cyberattacks. Evaluation criteria including precision, accuracy, recall and F1 score are assessed and compared to other cutting-edge algorithms to assess the performance of the proposed model. The proposed model attained an average accuracy of 98.21 %. Results show that the suggested model increased the attack detection accuracy by an average of 5.935% and 0.116% when compared to the Gated Recurrent Unit, Long Short Term Memory, random forest and naïve bayes models.

The potential of remote sensing of cover crops to benefit sustainable and precision fertilization

Cover crops and precision fertilization are two core strategies to advance sustainable agriculture. Based on a review of proven achievements in remote sensing of vegetation, a novel approach is proposed to use remote-sensing of cover crops to map soil nutrient availability and to produce prescription maps for precision basal fertilization prior to sowing the following cash crop. The first goal of this manuscript is to introduce the concept of using remote-sensing of cover crops as ‘reflectors’ or ‘bio-indicators’ of soil nutrient availability. This concept has two components: 1. mapping nitrogen availability using remote-sensing of cover crops; 2. using remotely-detected visual symptoms of cover crops' nutrient deficiencies to guide sampling schemes. The second goal was to describe two case studies that initially evaluated the feasibility of this concept in a 20 ha field. In the first case study, cover crops mixtures containing legumes and cereals were sown during two seasons in soils with different nitrogen levels. Cereals dominated the mixture when soil nitrogen levels were low, while legumes dominated when levels were high. Plant height and texture analysis derived from UAV-RGB-images were used to measure differences between the dominant species as an indicator of soil nitrogen availability. In the second case study, in an oat cover crop, three different appearances of visual symptoms (phenotypes) were observed throughout the field, and laboratory analysis showed they significantly differed in their nutrient levels. Spectral vegetation indices and plant height derived from UAV-RGB-images were analyzed by a multi-stage classification procedure to differentiate between the phenotypes. The classified product was interpreted and interpolated to generate a high-resolution map showing nutrient uptake for the whole field. The suggested concept essentially elevates the services cover crops can provide to benefit sustainable agriculture if incorporated with remote-sensing. The potentials, limitations and open questions concerning the suggested concept are discussed.

Machine-learning-based personal thermal comfort modeling for heat recovery using environmental parameters

Thermal comfort modeling based on average response of occupants has been of interest in building performance assessment for many years. Energy consumption optimization was the main concern initially, but recently, it was shown that poor health was significantly associated with thermal discomfort. It is crucial to control hospitals’ thermal comfort requirements, particularly when the patient and the caregiver have to stay in the same room for a long time. These goals may be obtained if personal comfort models, that predict individuals’ comfort responses, are considered instead. The primary goal in this study was to investigate the effects of physiological and environmental factors on individuals’ thermal preferences in indoor environments using datasets collected for the Green Buildings Innovation Cluster (GBIC) project. Hence, several feature sets were created considering various combinations of the physiological, environmental and personal factors and several machine learning classification algorithms were utilized to develop personal comfort models, including Random Forest (RF), Support Vector Machine (SVM), K-Nearest Neighbor (KNN) and an ensemble algorithm in two different approaches: multi classification and binary classification. Models’ Performances were evaluated and compared employing several metrics. The median accuracies of 0.89 and 0.84 were obtained considering the models with the best performances on the cross-validation sets in multi-classification and binary classification approaches, respectively. Furthermore, more complex models such as RF and SVM predicted individuals’ thermal preferences more precisely yet required more computational time than other classifiers. The results in this study indicated that skin temperature is a strong predictor of personal thermal preferences and a combination of several physiological parameters, including metabolic rate and heart rate, with the skin temperature data as inputs for the models would provide higher predicting accuracies.

Alzheimer’s Disease Detection from Fused PET and MRI Modalities Using an Ensemble Classifier

Alzheimer’s disease (AD) is an old-age disease that comes in different stages and directly affects the different regions of the brain. The research into the detection of AD and its stages has new advancements in terms of single-modality and multimodality approaches. However, sustainable techniques for the detection of AD and its stages still require a greater extent of research. In this study, a multimodal image-fusion method is initially proposed for the fusion of two different modalities, i.e., PET (Positron Emission Tomography) and MRI (Magnetic Resonance Imaging). Further, the features obtained from fused and non-fused biomarkers are passed to the ensemble classifier with a Random Forest-based feature selection strategy. Three classes of Alzheimer’s disease are used in this work, namely AD, MCI (Mild Cognitive Impairment) and CN (Cognitive Normal). In the resulting analysis, the Binary classifications, i.e., AD vs. CN and MCI vs. CN, attained an accuracy (Acc) of 99% in both cases. The class AD vs. MCI detection achieved an adequate accuracy (Acc) of 91%. Furthermore, the Multi Class classification, i.e., AD vs. MCI vs. CN, achieved 96% (Acc).

PSO Optimized CNN-SVM Architecture for Covid -19 Classification

This paper presents a hybrid model that utilizes PSO particle swarm optimization, Convolution Neural Networks (CNN) and (SVM) Support Vector Machine architecture for recognition of Covid19.The planned model extracts optimized structures with particle swarm optimization then passes to Convolution Neural Network for automatic feature extraction, while the SVM serves as a Multi classifier. The dataset comprises Covid 19, Pneumonia and Normal Chest X-Ray pictures used to hone and evaluate the suggested algorithm. The most distinct traits are automatically extracted by the algorithm from these photographs. Experimental results show that the suggested framework is effective, with an average recognition accuracy of 97.42%.The most successful SVM Kernel was RBF.

A WOA-CNN-BiLSTM-based multi-feature classification prediction model for smart grid financial markets

Introduction: Smart grid financial market forecasting is an important topic in deep learning. The traditional LSTM network is widely used in time series forecasting because of its ability to model and forecast time series data. However, in long-term time series forecasting, the lack of historical data may lead to a decline in forecasting performance. This is a difficult problem for traditional LSTM networks to overcome.Methods: In this paper, we propose a new deep-learning model to address this problem. This WOA-CNN-BiLSTM model combines bidirectional long short-term memory network BiLSTM and convolution Advantages of Neural Network CNN. We replace the traditional LSTM network with a bidirectional long short-term memory network, BiLSTM, to exploit its ability in capturing long-term dependencies. It can capture long-term dependencies in time series and is bidirectional modelling. At the same time, we use a convolutional neural network (CNN) to extract features of time series data to better represent and capture patterns and regularity in the data. This method combining BiLSTM and CNN can learn the characteristics of time series data more comprehensively, thus improving the accuracy of prediction. Then,to further improve the performance of the CNN-BiLSTM model, we optimize the model using the whale algorithm WOA. This algorithm is a new optimization algorithm, which has good global search ability and convergence speed, and can complete the optimization of the model in a short time.Results: Optimizing the CNN-BiLSTM model through the WOA algorithm can reduce its calculation and training speed, improve the prediction accuracy of the smart grid financial market, and improve the prediction ability of the smart grid financial market. Experimental results show that our proposed CNN-BiLSTM model has better prediction accuracy than other models and can effectively deal with the problem of missing historical data in long-term sequence forecasting.Discussion: This provides necessary help for the development of smart grid financial markets and risk management services, and can promote the development and growth of the smart grid industry. Our research results are of great significance in deep learning, and provide an effective method and idea for solving the financial market forecasting problem of smart grid.

ConvoHER2: A Deep Neural Network for Multi-Stage Classification of HER2 Breast Cancer

Generally, human epidermal growth factor 2 (HER2) breast cancer is more aggressive than other kinds of breast cancer. Currently, HER2 breast cancer is detected using variety of medical test which are most expensive. Therefore, the aim of this study was to develop a computational model named convoHER2 for detecting HER2 breast cancer with image data using convolution neural network (CNN). Hematoxylin and eosin (H&E) and immunohistochemical (IHC) stained images were used as raw data from the Bayesian information criterion (BIC) benchmark dataset. This dataset consists of 4873 images of H&E and IHC. Among all images of the dataset, 3896 and 977 images were applied to train and test the convoHER2 model, respectively. All images of this dataset are resized due to high resolution of the image for forming better detection performance of convoHER2 model. Moreover, the dataset is classified into four different labels (0+, 1+, 2+, 3+) for identifying the grade of detected HER2 breast cancer. The convoHER2 model is able to detect HER2 cancer and its grade with accuracy 85% and 88% using H&E images and IHC images, respectively. The outcomes of this study determined that the HER2 cancer detecting rates of the convoHER2 model are much enough to provide better diagnosis to the patient for recovering their HER2 breast cancer in future.

Spatio-temporal modelling with multi-gradient features and elongated quinary pattern descriptor for dynamic facial expression recognition

We propose a new spatio-temporal modelling approach for Dynamic Facial Expression Recognition (DFER). We first convert the domain of the spatial images in the sequence to the gradient of magnitude and angle images at different orientations. Robust gradient components are developed to deal with difficult types of illuminations, such as darkness, by forming the eight edge responses of the Gaussian mask. To describe the dynamic Facial Expression (FE) changes we extend the Elongated Quinary Pattern (EQP) descriptor to encode separately the anisotropic structure of the uniform patterns from Three Orthogonal Planes (TOP) of each gradient sequence. Then each encoded sequence is divided into a stack of block volumes in the XY, XT and YT planes. For each plane, the co-occurrence of histogram features are calculated from each block volume and concatenated together. Simple three-dimensional histogram features are generated by concatenating the histogram features of all planes. A Multi Classifier System (MCS) based on a multi-class Support Vector Machine (SVM) is adopted to combine all scores for the encoded sequences. The proposed approach is evaluated with the challenging MMI and Oulu-CASIA databases with different set-ups and advantage has been shown in terms of generalisation to different databases, together with robustness against difficult pose variations and illumination changes. In terms of Recognition Accuracy (RA), a comparison is established with DFER methods in the literature. A high recognition rate of 79.23% is attained in the case of six classes when applied to the MMI database which surpasses all the state-of-the-art results.

Voltage sag source location based on sag event amplitude information

Voltage sag source location provides a solution to improve the operation and maintenance efficiency and resolve disputes between power supply and consumption. The existing sag source locating methods are based on the fault recording system’s sampling value waveform data, which requires more storage space and transmission channels. Based on sag event list with easy access and high real-time performance and takes the line as the location result, this paper proposes a voltage sag source locating method based on sag event amplitude information. Firstly, Based on the voltage amplitude of the monitoring nodes recorded in the sag event list, a matrix of voltage amplitude of disturbed monitoring nodes is formed. Secondly, the voltage amplitude and fault type of the disturbed nodes are used as inputs, and the line number is used as a classification number. The multi-classifier model based on multi-layer perceptron is trained to locate the voltage sag source. Finally, the method in this paper is verified by IEEE39 node simulation model and the actual monitoring data of sag events in an area in East China. The results show that the method is effective and feasible. Compared with the existing commonly used multi classification algorithms, it is found that the accuracy of sag source location in this method is 10% ∼ 20% higher than other multi classification algorithms.

AN ALGORITHM FOR DETECTING PRECIPITATION IN COMPUTER PROCESSING OF VIDEO IMAGES

The importance of detecting and reducing the visibility of precipitation in video images obtained by fixed cameras is shown. A statistical analysis of the geometric (area, shape factor, and orientation deviation from the frame average), and color–brightness (intensity and color saturation) characteristics of rain and snow particles is performed in order to substantiate decision rules for detecting pixels corresponding to precipitation particles. This analysis consists in obtaining distributions of the particle parameters and approximating them by known distribution laws using the family of Pearson’s curves, the Kolmogorov criterion, and the Nelder–Mead simplex algorithm. An algorithm for detecting raindrops and snowflakes in video sequences is developed, which is supposed to be used as part of an algorithm for reducing the visibility of precipitation. The proposed approach is presented in the form of a multistage classification of frame pixels into zones with moving objects and regions of a stationary background distorted and undistorted by precipitation particles in accumulated frames. Depending on the region to which the processed pixel belongs, the final decision to assign it to the class of precipitation is made using the proposed decision rules or the developed thresholding procedure with automatic determination of local threshold values. The proposed algorithm is experimentally investigated and, using a two-criteria approach, the optimal values for the number of accumulated frames for the correct operation of the algorithm are determined—100 frames for video images with rain and 140 frames for video with snow. The gain of the developed approach in comparison with the known estimates of the probabilities of false positives and false negatives is up to 1.7% and 9.1%, respectively.

A deep learning approach for multi‐stage classification of brain tumor through magnetic resonance images

AbstractBrain tumor is the 10th major cause of death among humans. The detection of brain tumor is a significant process in the medical field. Therefore, the objective of this research work is to propose a fully automated deep learning framework for multistage classification. Besides, this study focuses on to develop an efficient and reliable system using a convolutional neural network (CNN). In this study, the fast bounding box technique is used for segmentation. Moreover, the CNN layers‐based three models are developed for multistage classification through magnetic resonance images on three publicly available datasets. The first dataset is obtained from Kaggle Repository (Dataset‐1), the second dataset is known as Figshare (Dataset‐2), and the third dataset is called REMBRANDT (Dataset‐3) to classify the MR images into different grades. Different augmentation techniques are applied to increase the data size of MR images. In pre‐processing, the proposed models achieved higher Peak Signal‐to‐Noise ratio to remove noise. The first proposed deep CNN framework mentioned as Classification‐1 has obtained 99.40% accuracy, which classified MR images into two classes, that is (i) normal and (ii) abnormal, while the second proposed CNN framework mentioned as Classification‐2 has obtained 97.78% accuracy, which classified brain tumor into three types, which are meningioma, glioma, and pituitary. Similarly, the third developed CNN framework mentioned as Classification‐3 has obtained 98.91% accuracy that further classified MR images of tumors into four different classes as: Grade I, Grade II, Grade III, and Grade IV. The results demonstrate that the proposed models achieved better performance on three large and diverse datasets. The comparison of obtained outcomes shows that the developed models are more efficient and effective than state‐of‐the‐art methods.

Emotion Detection on Social Media

Abstract: We proposed combine approach of BiLSTM and CNN to capture the emotional information from the words we are going to train BiLSTM model to get the semantic information from the words and parallelly we will be training CNN to get emotional information from the words. We will be using FastText word vector method for obtaining vectors from words unlike Word2Vec it operates at more minute level with character n grams. CNN and RNN are more efficient in finding the patterns out of large dataset. Due to the Word2Vec it opened entirely new approach to NLP. LSTM algorithms are quite popular in NLP field there were used in many emotion detection model due to their ability to find semantic meaning of words but they fail to capture information about the words. CNN models are quite fascinating and due to their ability to find the complex pattern among the images they are getting lot of attention in NLP. But, they are subjected to many limitations as network is designed to handle single dimension so it became vague how they are going to generalizes multi class prediction.

RETRACTED ARTICLE: Evaluation of image segmentation and multi class object recognition algorithm based on machine learning

This paper mainly updates the image segmentation and multi-target recognition algorithm through the support vector machine algorithm in ML, and verifies the reliability of the new proposed algorithm through simulation experiments, and determines that the ML-based image segmentation and multi-target recognition algorithm can have stronger processing capability in image recognition and processing. Finally, the performance of traditional image segmentation and multi class object recognition algorithms and the image segmentation and multi class object recognition algorithms proposed in this paper were compared through experiments. The results showed that the performance of the ML based image segmentation and multi class object recognition algorithms proposed in this paper has increased by 29.1% on average in all aspects.

Survey of Recent Deep Neural Networks with Strong Annotated Supervision in Histopathology

Deep learning (DL) and convolutional neural networks (CNNs) have achieved state-of-the-art performance in many medical image analysis tasks. Histopathological images contain valuable information that can be used to diagnose diseases and create treatment plans. Therefore, the application of DL for the classification of histological images is a rapidly expanding field of research. The popularity of CNNs has led to a rapid growth in the number of works related to CNNs in histopathology. This paper aims to provide a clear overview for better navigation. In this paper, recent DL-based classification studies in histopathology using strongly annotated data have been reviewed. All the works have been categorized from two points of view. First, the studies have been categorized into three groups according to the training approach and model construction: 1. fine-tuning of pre-trained networks for one-stage classification, 2. training networks from scratch for one-stage classification, and 3. multi-stage classification. Second, the papers summarized in this study cover a wide range of applications (e.g., breast, lung, colon, brain, kidney). To help navigate through the studies, the classification of reviewed works into tissue classification, tissue grading, and biomarker identification was used.

Detection and classification of DC and feeder faults in DC microgrid using new morphological operators with multi class AdaBoost algorithm

DC microgrids with energy storage systems based on photovoltaic (PV) and wind energy are gaining popularity as a means to offer users with reliable supply in either a stand-alone or grid connected mode. However, because DC and AC side faults have similar current–voltage profiles, developing a viable safety strategy for the proposed integrated DC microgrid is difficult. Traditional protection techniques based on pre-defined thresholds are unable to discriminate between DC and AC side faults, and so fail to offer independent control actions in both circumstances. In this context, new morphological operators with improved AdaBoost algorithm is proposed for detecting and classifying the AC and DC side faults in the proposed DC microgrid. To explore this, current signals are captured at the DC bus of the proposed integrated DC microgrid. The captured signals comprise background noise which is eliminated by dilation erosion difference operator (DEDO) and opening closing difference (OCDO) operators. The two operators work together to meet the accurate fault detection to avoid nuisance tripping by multiscale operation of structuring element (SE). For effective outcomes the multiple scales are optimized by sparse kurtosis (SK) index. The optimized scales are passes through target features to retrieve the data. The acquired data is sent into the multi-class AdaBoost approach, which recognizes faults by modifying the distribution of data and iteratively adjusting the weight of each instance. The proposed system's efficacy is tested using the MATLAB/Simulink platform under various operating situations such as load variation, irradiation and fault resistance changes. The proposed algorithm's superiority is demonstrated by comparing it to existing approaches using confusion matrix (CM) parameters.

Airline flight delays using artificial intelligence in COVID-19 with perspective analytics

This study envisages assessing the effects of the COVID-19 on the on-time performance of US-airlines industry in the disrupted situations. The deep learning techniques used are neural network regression, decision forest regression, boosted decision tree regression and multi class logistic regression. The best technique is identified. In the perspective data analytics, it is suggested what the airlines should do for the on-time performance in the disrupted situation. The performances of all the methods are satisfactory. The coefficient of determination for the neural network regression is 0.86 and for decision forest regression is 0.85, respectively. The coefficient of determination for the boosted decision tree is 0.870984. Thus boosted decision tree regression is better. Multi class logistic regression gives an overall accuracy and precision of 98.4%. Recalling/remembering performance is 99%. Thus multi class logistic regression is the best model for prediction of flight delays in the COVID-19. The confusion matrix for the multi class logistic regression shows that 87.2% flights actually not delayed are predicted not delayed. The flights actually not delayed but wrongly predicted delayed are12.7%. The strength of relation with departure delay, carrier delay, late aircraft delay, weather delay and NAS delay, are 94%, 53%, 35%, 21%, and 14%, respectively. There is a weak negative relation (almost unrelated) with the air time and arrival delay. Security delay and arrival delay are also almost unrelated with strength of 1% relationship. Based on these diagnostic analytics, it is recommended as perspective to take due care reducing departure delay, carrier delay, Late aircraft delay, weather delay and Nas delay, respectively, considerably with effect of 94%, 53%, 35%, 21%, and 14% in disrupted situations. The proposed models have MAE of 2% for Neural Network Regression, Decision Forest Regression, Boosted Decision Tree Regression, respectively, and, RMSE approximately, 11%, 12%, 11%, respectively.

DETECTION OF PNEUMONIA FROM X-RAY IMAGES USING DEEP LEARNING TECHNIQUES

X-ray images is one of the most common utilities used by health care specialists for detecting healthy problems in patients’ chest. In this work, deep learning techniques have been adopted for diagnosing and detecting of lung diseases. First, an experimental study has been conducted for selecting the best artificial neural network ANN model that can be used for lung X-Ray image classification. The obtained best model has been used for classifying the lung X-Ray images into three classes (Multi class classification) namely bacterial pneumonia, viral pneumonia, and healthy lung. After that, three well-known CNN architectures, namely ResNet, Inception, and MobileNet have been adopted and used as a feature extractor for the selected best ANN model. Moreover, the above-mentioned ANN model (both with and without the features extraction phase) has been used for classifying the lung X-Ray images as healthy and pneumonia lungs (Binary classification). As a result of the study, the proposed ANN model with ResNet feature extraction phase gave the highest classification accuracy rate of 81.67% when multi-class classification has been conducted on the lung X-Ray dataset. On the other hand, the proposed ANN model with MobileNet feature extraction phase gave the highest accuracy rate of 95.67% when a binary classification has been conducted on the X-Ray image dataset.