Ensemble Bagged Tree Research Articles

Hybrid Method for Power Transformers Faults Diagnosis Based on Ensemble Bagged Tree Classification and Training Subsets Using Rogers and Gouda Ratios

Hybrid Method for Power Transformers Faults Diagnosis Based on Ensemble Bagged Tree Classification and Training Subsets Using Rogers and Gouda Ratios

A New Voltage Based Fault Detection Technique for Distribution Network Connected to Photovoltaic Sources Using Variational Mode Decomposition Integrated Ensemble Bagged Trees Approach

The increasing integration of renewable sources into distributed networks results in multiple protection challenges that would be insufficient for conventional protection strategies to tackle because of the characteristics and functionality of distributed generation. These challenges include changes in fault current throughout various operating modes, different distribution network topologies, and high-impedance faults. Therefore, the protection and reliability of a photovoltaic distributed network relies heavily on accurate and adequate fault detection. The proposed strategy utilizes the Variational Mode Decomposition (VMD) and ensemble bagged trees method to tackle these problems in distributed networks. Primarily, VMD is used to extract intrinsic mode functions from zero-, positive-, and negative-sequence components of a three-phase voltage signal. Next, the acquired intrinsic mode functions are supplied into the ensemble bagged trees mechanism for detecting fault events in a distributed network. Under both radial and mesh-soft normally open-point (SNOP) topologies, the outcomes are investigated and compared in the customarily connected and the island modes. Compared to four machine learning mechanisms, including linear discriminant, linear support vector mechanism (SVM), cubic SVM and ensemble boosted tree, the ensemble bagged trees mechanism (EBTM) has superior accuracy. Furthermore, the suggested method relies mainly on local variables and has no communication latency requirements. Therefore, fault detection using the proposed strategy is reasonable. The simulation outcomes show that the proposed strategy provides 100 percent accurate symmetrical and asymmetrical fault diagnosis within 1.25 ms. Moreover, this approach accurately identifies high- and low-impedance faults.

A Novel Fault Detection and Classification Strategy for Photovoltaic Distribution Network Using Improved Hilbert–Huang Transform and Ensemble Learning Technique

Due to the increased integration of distributed generations in distributed networks, their development and operation are facing protection challenges that traditional protection systems are incapable of addressing. These problems include variations in the fault current during various operation modes, diverse distributed network topology, and high impedance faults. Therefore, appropriate and reasonable fault detection is highly encouraged to improve the protection and dependability of the distributed network. This paper proposes a novel technique that employs an improved Hilbert–Huang Transform (HHT) and ensemble learning techniques to resolve these challenges in a photovoltaic distributed network. First, improved HHT is utilized to extract energy features from the current signal. Second, variational mode decomposition (VMD) is applied to extract the intrinsic mode function from the zero component of the current signal. Then, the acquired energy feature and intrinsic mode function are input to the ensemble learning technique for fault detection and classification. The proposed technique is implemented using MATLAB software environment, including a classification learner app and SIMULINK. An evaluation of the results is conducted under normal connected mode (NCM) and island mode (ISM) for radial and mesh-soft normally open point (SNOP) configurations. The accuracy of the ensemble bagged trees technique is higher when compared to the narrow-neural network, fine tree, quadratic SVM, fine-gaussian SVM, and wide-neural network. The presented technique depends only on local variables and has no requirements for connection latency. Consequently, the detection and classification of faults using the proposed technology are reasonable. The simulation results demonstrate that the proposed technique is superior to the neural network and support vector machine, achieving 100%, 99.2% and 99.7% accurate symmetrical and unsymmetrical fault detection and classification throughout NCM, ISM, and dynamic operation mode, respectively. Moreover, the developed technique protects DN effectively in radial and mesh-SNOP topologies. The suggested strategy can detect and classify faults accurately in DN with/without DGs. Additionally, this technique can precisely detect high and low impedance faults within 4.8 ms.

Detecting stressful older adults-environment interactions to improve neighbourhood mobility: A multimodal physiological sensing, machine learning, and risk hotspot analysis-based approach

Not only is the global population ageing, but also the built environment infrastructure in many cities and communities are approaching their design life or showing significant deterioration. Such built environment conditions often become an environmental barrier that can either cause stress and/or limit the mobility of older adults in their neighbourhood. Current approaches to detecting stressful environmental interactions are less effective in terms of time, cost, labour, and individual stress detection. This study harnesses the recent advances in wearable sensing technologies, machine learning intelligence and hotspot analysis to develop and test a more efficient approach to detecting older adults' stressful interactions with the environment. Specifically, this study monitored older adults' physiological reactions (Photoplethysmogram and electrodermal activity) and global positioning system (GPS) trajectory using wearable sensors during an outdoor walk. Machine learning algorithms, including Gaussian Support Vector Machine, Ensemble bagged tree, and deep belief network were trained and tested to detect older adults' stressful interactions from their physiological signals, location and environmental data. The Ensemble bagged tree achieved the best performance (98.25% accuracy). The detected stressful interactions were geospatially referenced to the GPS data, and locations with high-risk clusters of stressful interactions were detected as risk stress hotspots for older adults. The detected risk stress hotspot locations corresponded to the places the older adults encountered environmental barriers, supported by site inspections, interviews and video records. The findings of this study will facilitate a near real-time assessment of the outdoor neighbourhood environment, hence improving the age-friendliness of cities and communities.

EEG-based cross-subject emotion recognition using Fourier-Bessel series expansion based empirical wavelet transform and NCA feature selection method

Automated emotion recognition using brain electroencephalogram (EEG) signals is predominantly used for the accurate assessment of human actions as compared to facial expression or speech signals. Various signal processing methods have been used for extracting representative features from EEG signals for emotion recognition. However, the EEG signals are non-stationary and vary across the subjects as well as in different sessions of the same subject; hence it exhibits poor generalizability and low classification accuracy for an emotion classification of cross subjects. In this paper, EEG signals-based automated cross-subject emotion recognition framework is proposed using the Fourier-Bessel series expansion-based empirical wavelet transform (FBSE-EWT) method. This method is used to decompose the EEG signals from each channel into four sub-band signals. Manually ten channels are selected from the frontal lobe, from which entropy and energy features are extracted from each sub-band signal. The subject variability is reduced using an average moving filter method on each channel to obtain the smoothened feature vector of size 80. The three feature selection techniques, such as neighborhood component analysis (NCA), relief-F, and mRMR, are used to obtain an optimal feature vector. The machine learning models, such as artificial neural network (ANN), k-nearest neighborhood (k-NN) with two (fine and weighted) functions, and ensemble bagged tree classifiers are trained by the obtained feature vectors. The experiments are performed on two publicly accessible databases, named SJTU emotion EEG dataset (SEED) and dataset for emotion analysis using physiological signals (DEAP). The training and testing of the models have been performed using 10-fold cross-validation and leave-one-subject-out-cross-validation (LOSOCV). The proposed framework based on FBSE-EWT and NCA feature selection approach shows superior results for classifying human emotions compared to other state-of-art emotion classification models.

Bagged tree ensemble modelling with feature selection for isometric EMG-based force estimation

EMG-based force estimation is crucial in applications, such as control of powered prosthetic and rehabilitation devices. Most previous studies focus on intra-subject force modelling. However, a generalized EMG-force estimation model, which is capable of estimating force across users, is needed for surgical and rehabilitation robotics. In this study, EMG signals are recorded from the long head and short head of the biceps brachii, and brachioradialis using 3 linear surface electrode arrays, during isometric elbow flexions, at different joint angles and forearm postures, while recording the induced force at the wrist. The recorded EMGs are pre-processed and segmented, and 336 time and frequency domain features are extracted from 21 EMG channels. We explore developing a model that can perform well across subjects, where Bagged Tree Ensemble (BTE) models are used to learn the non-linear, complex relationships between the EMG and force data. The BTE models are compared with several machine learning approaches. The BTE model performs best, giving an average normalized mean squared error (%NMSE) of 5.65±16.24%. To reduce the dimensionality of the feature space and improve force estimation performance, a novel feature selection technique, called modified sequential feature selection (MSFS) is implemented and compared to other commonly used feature selection methods. Results show that the MSFS algorithm outperformed other methods tested, significantly reducing the force estimation error. We also found that there was no effect of forearm posture and joint angle on force modelling accuracy, permitting the development of an isometric force estimation model generalized across participants and arm positions.

A Biometric Authentication Technique Using Smartphone Fingertip Photoplethysmography Signals

Biometric Authentication (BA) is the process by which physiological measurements can be used to identify a specific person. BA has been implemented in various applications such as financial transactions, data privacy, and access control. Photoplethysmography (PPG) signals can be acquired from devices such as smartphones, smartwatches, or web cameras, which allow biometric signals to be readily captured. In this paper, we developed a BA classifier method for smart devices, which first reduces motion and noise artifacts (MNAs) in raw PPG signals, and then identifies subjects using the MNA-reduced PPG signals. Specifically, our BA classifier algorithm adopts an ensemble bagged trees (EBT) classifier with 16 PPG signal features from time and frequency domains. In the BA context, false positive (FP) and false negative (FN) rates are very important measurements to be considered. Acceptable FP and FN values were obtained. Experimental results show that our EBT-based BA algorithm achieved accuracy levels of 98.0% and 95.0%. Also, equal error rates (EER) measurements accomplished acceptable values of 2.42% and 5.90%.

An Automated Wavelet-Based Sleep Scoring Model Using EEG, EMG, and EOG Signals with More Than 8000 Subjects.

Human life necessitates high-quality sleep. However, humans suffer from a lower quality of life because of sleep disorders. The identification of sleep stages is necessary to predict the quality of sleep. Manual sleep-stage scoring is frequently conducted through sleep experts’ visually evaluations of a patient’s neurophysiological data, gathered in sleep laboratories. Manually scoring sleep is a tough, time-intensive, tiresome, and highly subjective activity. Hence, the need of creating automatic sleep-stage classification has risen due to the limitations imposed by manual sleep-stage scoring methods. In this study, a novel machine learning model is developed using dual-channel unipolar electroencephalogram (EEG), chin electromyogram (EMG), and dual-channel electrooculgram (EOG) signals. Using an optimum orthogonal filter bank, sub-bands are obtained by decomposing 30 s epochs of signals. Tsallis entropies are then calculated from the coefficients of these sub-bands. Then, these features are fed an ensemble bagged tree (EBT) classifier for automated sleep classification. We developed our automated sleep classification model using the Sleep Heart Health Study (SHHS) database, which contains two parts, SHHS-1 and SHHS-2, containing more than 8455 subjects with more than 75,000 h of recordings. The proposed model separated three classes if sleep: rapid eye movement (REM), non-REM, and wake, with a classification accuracy of 90.70% and 91.80% using the SHHS-1 and SHHS-2 datasets, respectively. For the five-class problem, the model produces a classification accuracy of 84.3% and 86.3%, corresponding to the SHHS-1 and SHHS-2 databases, respectively, to classify wake, N1, N2, N3, and REM sleep stages. The model acquired Cohen’s kappa () coefficients as 0.838 with SHHS-1 and 0.86 with SHHS-2 for the three-class classification problem. Similarly, the model achieved Cohen’s of 0.7746 for SHHS-1 and 0.8007 for SHHS-2 in five-class classification tasks. The model proposed in this study has achieved better performance than the best existing methods. Moreover, the model that has been proposed has been developed to classify sleep stages for both good sleepers as well as patients suffering from sleep disorders. Thus, the proposed wavelet Tsallis entropy-based model is robust and accurate and may help clinicians to comprehend and interpret sleep stages efficiently.

Abiotic stress classification through spectral analysis of enhanced electrophysiological signals of plants

Electrical activity in plants undergoes potential changes in interpreting the plant's physiological state. These electrical signals show arbitrary and probabilistic dynamics in which stress can be detected and analysed in the early stages of symptom appearance in plants. Evaluation of uncertainty in plant signals by signal strength enhancement is stress-specific. In this paper, we considered physiological signals from 15 days old soybean plants that endured three types of stress (cold, osmotic and lowlight). A novel enhancement methodology is proposed to pre-process the stress information present in the electrical signals. Sixteen spectral features were computed from spectrograms of enhanced signals to attain a better hypothesis. To verify the performance metrics of pre and post-enhancement methods, classification is done in two levels (Multi-class, Binary-class) using machine learning algorithms (Decision Trees (DT), K- Nearest Neighbors (KNN), Support Vector Machines (SVM), Ensemble Boosted Tree (EBT), Ensemble Bagged Tree (EBGT), Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA)). Superlative feature pairs showing classification accuracy greater than 95% after 5-fold cross-validation were nominated. The results obtained by the SVM classifier in cold stress and KNN in lowlight stress are accurate to 98% after enhancement. The successful premises taken from this work assure early-stage detection and classification of plant stress, thereby suggesting future requirements to develop enhancement & classification techniques according to the type of stress. • Plant electrical signals play a significant role in comprehending plant stresses. • Accuracies improved after processing signals by enhancement methods. • Spectral feature extraction and feature pairing structured the classification model. • Classification performance is greatly improved after enhancement. • Various ML classifiers obtained results greater than 95% in classifying abiotic stress.

Alzheimer’s disease detection from optimal EEG channels and Tunable Q-Wavelet Transform

Alzheimer’s disease (AD) is a non-curable neuro-degenerative disorder that has no cure to date. However, it can be delayed through daily activity assessment using a robust Electroencephalogram (EEG) based system at an early stage. A selection tech- nique using a Shannon entropy to signal energy ratio is proposed to select optimal EEG channels for AD detection. A threshold for channel selection is calculated using the best detection accuracy during backward elimination. The selected EEG channels are decomposed using Tunable Q-wavelet transform (TQWT) into nine different sub- bands (SBs). Four features: Katz’s fractal dimension, Tsallis entropy, Relyi’s entropy, and kurtosis are extracted for each SB. These features are used to train and test sup- port vector machine, k-nearest neighbor, Ensemble bagged tree (EBT), decision tree, and neural network for detecting AD patients from normal subjects. 16-channel EEG signals from 12 AD and 11 normal subjects recorded using the 10-20 electrode place- ment method are used for evaluation. Ten optimized channels are selected, resulting in 32.5% compression. The experimental results of the proposed method showed promis- ing classification accuracy of 96.20% with the seventh SB features and EBT classifier. The significance of these features was inspected by using the Kruskal-Wallis test.

A Comparative Study to Predict Bearing Degradation Using Discrete Wavelet Transform (DWT), Tabular Generative Adversarial Networks (TGAN) and Machine Learning Models

Prognostics and health management (PHM) is a framework to identify damage prior to its occurrence which leads to the reduction of both maintenance costs and safety hazards. Based on the data collected in condition monitoring, the degradation of the part is predicted. Studies show that most failures are caused by faults in rolling element bearing, which highlights that a bearing is one of the most important mechanical components of any machine. Thus, it becomes important to monitor bearing degradation to make sure that it is utilized properly. Generally, machine learning (ML) or deep learning (DL) techniques are utilized to predict bearing degradation using a data-driven approach, where signals are captured from the machine. There should be a large amount of data to apply either ML or DL techniques, but it is difficult to collect that amount of data directly from any machine. In this study, health assessment is carried out using the correlation coefficient to divide the bearing life into two degradation stages. The raw signal is processed using discrete wavelet transform (DWT), where mutual information (MI) is used to rank and select the base wavelet, after which tabular generative adversarial networks (TGAN) are used to generate the artificial coefficients. Statistical features are calculated from the real data (DWT coefficients) and the artificial data (generated from TGAN). The constructed feature vector is then used as an input to train machine learning models, namely ensemble bagged tree (EBT) and Gaussian process regression with the squared exponential kernel function (SEGPR), to estimate bearing degradation conditions. Both the machine learning models were validated on the publicly available experimental data of FEMTO bearing. Obtained results showed that the developed EBT and SEGPR models accurately predicted the bearing degradation conditions with the average lowest RMSE value of 0.0045 and MAE value of 0.0037.

An expert system for automated classification of phases in cyclic alternating patterns of sleep using optimal wavelet‐based entropy features

AbstractHumans spend a significant portion of their time in the state of sleep, and therefore one's’sleep health’ is an important indicator of the overall health of an individual. Non‐invasive methods such as electroencephalography (EEG) are used to evaluate the ’sleep health’ as well as associated disorders such as nocturnal front lobe epilepsy, insomnia, and narcolepsy. A long‐duration and repetitive activity, known as a cyclic alternating pattern (CAP), is observed in the EEG waveforms which reflect the cortical electrical activity during non‐rapid eye movement (NREM) sleep. The CAP sequences involve various, continuing periods of phasic activation (phase‐A) and deactivation (phase‐B). The manual analysis of these signals performed by clinicians are prone to errors, and may lead to the wrong diagnosis. Hence, automated systems that can classify the two phases (viz. Phase A and Phase B accurately can eliminate any human involvement in the diagnosis. The pivotal aim of this study is to evaluate the usefulness of stopband energy minimized biorthogonal wavelet filter bank (BOWFB) based entropy features in the identification of CAP phases. We have employed entropy features obtained from six wavelet subbands of EEG signals to develop a machine learning (ML) based model using various supervised ML algorithms. The proposed model by us yielded an average classification accuracy of 74.40% with 10% hold‐out validation with the balanced dataset, and maximum accuracy of 87.83% with the unbalanced dataset using ensemble bagged tree classifier. The developed expert system can assist the medical practitioners to assess the person's cerebral activity and quality of sleep accurately.

Classification of Partial Discharges Originating From Multilevel PWM Using Machine Learning

A partial discharge (PD) is a small, localized breakdown which often appears in high-voltage insulation systems. PDs can be initiated within material defects such as voids or cracks when exposed to sufficiently high electric field levels. In this research work, we study and propose a machine learning (ML) approach to detect and classify PDs originating from multilevel pulsewidth modulation (PWM) waveforms as utilized in power electronic devices, such as inverters and variable frequency drives. Due to the increased use of power conversion units, new types of higher magnitude PDs have been observed to increase insulation degradation. By creating a cavity placed at different locations within the test object and exposing it to PWM voltage waveforms with two different rise times, a total of 345 660 PD events are recorded and organized into ten different classes. The maximum PD amplitude, duration, the time distance between consecutive PDs, and the area under the PD are used as features for PD classification. A unique way of concatenating a sequence of the extracted features to capture the temporal dependence of consecutive PDs is also presented. It is observed that when creating a sequence of information from consecutive observed PDs, a significant increase in classification accuracy can be obtained. Trained classifiers based on ensemble bagged decision trees (DTs) and long short-term memory (LSTM) architecture resulted in 95.3% and 98.5% average classification accuracy on test data respectively.

A complete framework for accurate recognition and prognosis of COVID-19 patients based on deep transfer learning and feature classification approach.

The sudden appearance of COVID-19 has put the world in a serious situation. Due to the rapid spread of the virus and the increase in the number of infected patients and deaths, COVID-19 was declared a pandemic. This pandemic has its destructive effect not only on humans but also on the economy. Despite the development and availability of different vaccines for COVID-19, scientists still warn the citizens of new severe waves of the virus, and as a result, fast diagnosis of COVID-19 is a critical issue. Chest imaging proved to be a powerful tool in the early detection of COVID-19. This study introduces an entire framework for the early detection and early prognosis of COVID-19 severity in the diagnosed patients using laboratory test results. It consists of two phases (1) Early Diagnostic Phase (EDP) and (2) Early Prognostic Phase (EPP). In EDP, COVID-19 patients are diagnosed using CT chest images. In the current study, 5, 159 COVID-19 and 10, 376 normal computed tomography (CT) images of Egyptians were used as a dataset to train 7 different convolutional neural networks using transfer learning. Data augmentation normal techniques and generative adversarial networks (GANs), CycleGAN and CCGAN, were used to increase the images in the dataset to avoid overfitting issues. 28 experiments were applied and multiple performance metrics were captured. Classification with no augmentation yielded 99.61% accuracy by EfficientNetB7 architecture. By applying CycleGAN and CC-GAN Augmentation, the maximum reported accuracies were 99.57% and 99.14% by MobileNetV1 and VGG-16 architectures respectively. In EPP, the prognosis of the severity of COVID-19 in patients is early determined using laboratory test results. In this study, 25 different classification techniques were applied and from the different results, the highest accuracies were 98.70% and 97.40% reported by the Ensemble Bagged Trees and Tree (Fine, Medium, and Coarse) techniques respectively.

Machine learning classification algorithms for inadequate wastewater treatment risk mitigation

Continuous monitoring of wastewater treatment processes is key to mitigate the risk of inadequately treated wastewater on the environment and public health. However, effective control of wastewater treatment processes is challenging because of the numerous relevant variables and their complex physio-chemical-biological interdependence. Most published related studies focused on correlating the effluent concentration of chemical oxygen demand and/or suspended solids using only a limited number of wastewater influent variables. In addition, recent machine learning- (ML) based studies in wastewater treatment systems considered some individual classification algorithms rather than providing a comparison between different algorithm performances. In the current study, different algorithms were developed to categorize a range of wastewater treatment effluent characteristics based on multiple influent variables. To demonstrate their application, 23 ML classification algorithms were deployed on a wastewater treatment reactor-generated dataset and their performances were evaluated considering two different group of metrics related to the removal efficiency and effluent quality. The analysis results showed that, among all considered algorithms, the ensemble bagged trees algorithm had the most superior performance in terms of its overall classification accuracy. An interpretability analysis was further performed on the treatment process variables to detect the correlation between the input and output variables and to assess variable importance. In practice, the developed algorithms can facilitate optimal operation and effective management of wastewater treatment plants. ML algorithms also present efficient tools for rapidly classifying the effluent characteristics in lieu of typical sampling and laboratory analysis processes.

Non-Invasive Classification of Blood Glucose Level for Early Detection Diabetes Based on Photoplethysmography Signal

Monitoring systems for the early detection of diabetes are essential to avoid potential expensive medical costs. Currently, only invasive monitoring methods are commercially available. These methods have significant disadvantages as patients experience discomfort while obtaining blood samples. A non-invasive method of blood glucose level (BGL) monitoring that is painless and low-cost would address the limitations of invasive techniques. Photoplethysmography (PPG) collects a signal from a finger sensor using a photodiode, and a nearby infrared LED light. The combination of the PPG electronic circuit with artificial intelligence makes it possible to implement the classification of BGL. However, one major constraint of deep learning is the long training phase. We try to overcome this limitation and offer a concept for classifying type 2 diabetes (T2D) using a machine learning algorithm based on PPG. We gathered 400 raw datasets of BGL measured with PPG and divided these points into two classification levels, according to the National Institute for Clinical Excellence, namely, “normal” and “diabetes”. Based on the results for testing between the models, the ensemble bagged trees algorithm achieved the best results with an accuracy of 98%.

Automated identification of sleep disorders using wavelet-based features extracted from electrooculogram and electromyogram signals

Sleep is imperative for a healthy life as it rejuvenates memory, cognitive performance, cell repair and eliminates waste from the muscles. Sleep-related disorders such as insomnia, narcolepsy, sleep-disordered breathing (SDB), periodic leg movement (PLM), and bruxism lead to hormonal imbalance, slower reaction time, memory problems, depression, and headaches. This adversity of sleep disorder gained the attention of many sleep researchers. To examine the reasons for sleep disorders, it is imperative to monitor and analyze the sleep of the affected patients. The conventional method of monitoring sleep and identifying the sleep disorders using polysomnographic (PSG) recording is a complicated and cumbersome task in which multiple physiological signals with multiple modalities are recorded for a long (overnight) duration. The PSG recordings are carried out in sophisticated sleep laboratories and cannot be considered suitable for real-time sleep monitoring. Thus, a simple and patient-convenient system is highly desirable to monitor and analyze the quality of sleep. We proposed an automatic detection of sleep disorders using single modal electrooculogram (EOG) and electromyogram (EMG) signals. We have used a new maximally flat multiplier-less biorthogonal filter bank for obtaining discrete wavelet transform of the signals. We computed Hjorth parameters (HOP) such as activity, mobility, and complexity from the wavelet sub-bands. Highly discriminative HOP features are fed to different machine learning classifiers to develop the model. Our results show that the developed system can classify insomnia, narcolepsy, NFLE, PLM, and REM behaviour disorder (RBD) against normal healthy subjects with an accuracy of 99.7%, 97.6%, 97.5%, 97.5%, and 98.3%, respectively using combined features from EOG and EMG signal. The proposed model has yielded an accuracy of 94.3% in classifying six classes using an ensemble bagged trees classifier (EBTC) with a 10-fold cross-validation technique. Hence, EOG and EMG-based proposed methods can be deployed in a portable home-based environment to identify the type of sleep disorders automatically.

A New Medical Decision Support System for Diagnosing HFrEF and HFpEF Using ECG and Machine Learning Techniques

As heart failure (HF) is a growing epidemic, no case should be overlooked in the diagnosis of HF. Two subtypes by left ventricular ejection fraction (LVEF) of HF are HF with reduced ejection fraction (HFrEF) (LVEF ≤ 40%) and HF with preserved ejection fraction (HFpEF) (LVEF ≥ 50%). HFrEF is easier to diagnose. However, the diagnosis of HFpEF is more complex and difficult even for specialists. The diagnosis of HFpEF is a problem that is being tried to be solved in medicine. Since LVEF appears normal (LVEF ≥ 50% in healthy individuals), HFpEF can be confused with chest diseases due to some similar symptoms. The diagnosis of HF subtypes is ideally made using echocardiography. Echocardiography should be performed in all patients with HF; however, it is expensive and requires specialists. Even in high-resource regions, this test is not always performed, and treatment may need to be initiated before the echocardiographic data are obtained. For such situations, economical and practical systems are required. In this study, a medical decision support system was developed to detect HFrEF and HFpEF cases using only 3-lead ECG. From the ECG data of 61 volunteers, 37 features were extracted, of which 16 were Yule-Walker and Burg’s method parameters, and 21 were in the time domain. Consequently, 37 features were reduced by feature selection and triple classification was performed with only 4 features with maximum accuracy. The aim of this study was to determine whether the individuals with HF symptoms were HFrEF, HFpEF, or healthy. Four machine learning algorithms were used for classification. The best classification accuracy rate was 100% for k-NN, and significant results were obtained from the other three algorithms: SVMs, Decision Trees, and Ensemble Bagged Trees.

Speed Efficient Fast Fourier Transform for Signal Processing of Nucleotides to Detect Diabetic Retinopathy Using Machine Learning

Diabetic Retinopathy (DR) is a complicated disease of diabetes, which specifically affects the retina. The human-intensive analysis mechanism of DR infected retina are likely to diagnose wrongly compared to computer-intensive diagnosis systems. In this paper, in order to aid the computer based approach for the diagnosis of DR, a model based on machine learning algorithm is proposed. The nucleotides of the human retina are processed with the help of signal processing methodologies. A speed efficient Fast Fourier transform is proposed to work out the FFT of huge amount of samples with higher pace. The improvement in speed is achieved in 98% of the samples. The prediction parameters, derived from these samples are utilized to classify the healthy retina sequence and an infected retina. In this study, Fine Tree, KNN Fine, Weighted KNN, Ensemble Bagged Trees and Ensemble Subspace KNN classifiers are employed to build the models. The simulated results using MATLAB software show that the accuracy is 98% which is better than image processing based methods which were used earlier. The performance parameters such as sensitivity and specificity are determined for each model. The faithfulness of the model is studied by deriving the ROC Curve.

Automatic learning algorithm for troubleshooting in hydraulic machinery

<span>In Peru, there are many companies linked to the category of heavy machinery maintenance, in which, on the one hand, although it is true they generate a record of events linked to equipment maintenance indicators, on the other hand they do not make efficient use of these data generating operational patterns, through machine learning, that contribute to the improvement of processes linked to the service. In this sense, the objective of this article is to generate a tool based on automatic learning algorithms that allows predicting the location of faults in hydraulic excavators, in order to improve the management of the maintenance service. When developing the research, it was obtained that the algorithm that assembles bagged trees presents an accuracy of 97.15%, showing a level of specificity of 99.04%, an accuracy of 98.56% and a sensitivity of 97.12%. Therefore, the predictive model using the ensemble bagged trees algorithm shows significant performance in locating the system where failures occur in hydraulic excavator fleets. It is concluded then that it was possible to improve aspects associated with the planning and availability of supplies or components of the maintenance service, also optimizing the continuity and response capacity in the maintenance process.</span>