Ensemble Learning for Fetal Health Classification

Cardiotocography(CTG)represents the fetus’s health inside the womb during labor.However,assessment of its readings can be a highly subjective process depending on the expertise of the obstetrician.Digital signals from fetal monitors acquire parameters(i.e.,fetal heart rate,contractions,acceleration).Objective:This paper aims to classify the CTG readings containing imbalanced healthy,suspected,and pathological fetus readings.Method:We perform two sets of experiments.Firstly,we employ five classifiers:Random Forest(RF),Adaptive Boosting(AdaBoost),Categorical Boosting(CatBoost),Extreme Gradient Boosting(XGBoost),and Light Gradient Boosting Machine(LGBM)without over-sampling to classify CTG readings into three categories:healthy,suspected,and pathological.Secondly,we employ an ensemble of the above-described classifiers with the oversamplingmethod.We use a random over-sampling technique to balance CTG records to train the ensemble models.We use 3602 CTG readings to train the ensemble classifiers and 1201 records to evaluate them.The outcomes of these classifiers are then fed into the soft voting classifier to obtain the most accurate results.Results:Each classifier evaluates accuracy,Precision,Recall,F1-scores,and Area Under the Receiver Operating Curve(AUROC)values.Results reveal that the XGBoost,LGBM,and CatBoost classifiers yielded 99%accuracy.Conclusion:Using ensemble classifiers over a balanced CTG dataset improves the detection accuracy compared to the previous studies and our first experiment.A soft voting classifier then eliminates the weakness of one individual classifier to yield superior performance of the overall model.

Home Energy Management System Using NILM and Low-Cost HAN

Home energy management systems （HEMs） are used to provide comfortable life for consumers as well as to save energy. An essential component of HEMs is a home area network （HAN） that is used to remotely control the electric devices at homes and buildings. Although HAN prices have dropped in ~ecent years but they are still expensive enough to prohibit a mass scale deployments. In this paper, a very low cost alternative to the expensive HANs is presented. We have applied a combination of non-intrusive load monitoring （NILM） and very low cost one-way HAN to develop a HEM. By using NILM and machine learning algorithms we find the status of devices and their energy consumption from a central meter and communicate with devices through the one-way HAN. The evaluations show that the proposed machine learning algorithm for NILM achieves up to 99% accuracy in certain cases. On the other hand our radio frequency （RF）-based one-way HAN achieves a range of 80 feet in all settings.

Noisy ECG Signal Data Transformation to Augment Classification Accuracy

In this era of electronic health,healthcare data is very important because it contains information about human survival.In addition,the Internet of Things(IoT)revolution has redefined modern healthcare systems and management by providing continuous monitoring.In this case,the data related to the heart is more important and requires proper analysis.For the analysis of heart data,Electrocardiogram(ECG)is used.In this work,machine learning techniques,such as adaptive boosting(AdaBoost)is used for detecting normal sinus rhythm,atrial fibrillation(AF),and noise in ECG signals to improve the classification accuracy.The proposed model uses ECG signals as input and provides results in the form of the presence or absence of disease AF,and classifies other signals as normal,other,or noise.This article derives different features from the signal using Maximal Information Coefficient(MIC)and minimum Redundancy Maximum Relevance(mRMR)technique,and then classifies them based on their attributes.Since the ECG contains some kind of noise and irregular data streams so the purpose of this study is to remove artifacts from the ECG signal by deploying the method of Second-Order-Section(SOS)(filter)and correctly classify them.Several features were extracted to improve the detection of ECG data.Compared with existing methods,this work gives promising results and can help improve the classification accuracy of the ECG signals.

Grain Yield Predict Based on GRA-AdaBoost-SVR Model

Grain yield security is a basic national policy of China,and changes in grain yield are influenced by a variety of factors,which often have a complex,non-linear relationship with each other.Therefore,this paper proposes a Grey Relational Analysis-Adaptive Boosting-Support Vector Regression(GRA-AdaBoost-SVR)model,which can ensure the prediction accuracy of the model under small sample,improve the generalization ability,and enhance the prediction accuracy.SVR allows mapping to high-dimensional spaces using kernel functions,good for solving nonlinear problems.Grain yield datasets generally have small sample sizes and many features,making SVR a promising application for grain yield datasets.However,the SVR algorithm’s own problems with the selection of parameters and kernel functions make the model less generalizable.Therefore,the Adaptive Boosting(AdaBoost)algorithm can be used.Using the SVR algorithm as a training method for base learners in the AdaBoost algorithm.Effectively address the generalization capability problem in SVR algorithms.In addition,to address the problem of sensitivity to anomalous samples in the AdaBoost algorithm,the GRA method is used to extract influence factors with higher correlation and reduce the number of anomalous samples.Finally,applying the GRA-AdaBoost-SVR model to grain yield forecasting in China.Experiments were conducted to verify the correctness of the model and to compare the effectiveness of several traditional models applied to the grain yield data.The results show that the GRA-AdaBoost-SVR algorithm improves the prediction accuracy,the model is smoother,and confirms that the model possesses better prediction performance and better generalization ability.

A hybrid system to predict brain stroke using a combined feature selection and classifier

Background Brain stroke is a serious health issue that requires timely and accurate prediction for effective treatment and prevention.This study described a hybrid system that used the best feature selection method and classifier to predict brain stroke.Methods The Stroke Prediction Dataset from Kaggle was used for this study.Synthetic minority over-sampling technique(SMOTE)analysis was used to accomplish class balancing.Accuracy,sensitivity,specificity,precision,and the F-Measure were the main performance parameters considered for investigation.To determine the best combination for predicting brain stroke,the performance of five classifiers,Naïve Bayes(NB),support vector machine(SVM),random forest(RF),adaptive boosting(Adaboost),and extreme gradient boosting(XGBoost),was compared along with three feature selection techniques,mutual information(MI),Pearson correlation(PC),and feature importance(FI).The performance parameters were assessed using k-fold cross-validation.Results The hybrid system proposed in this study identified a reduced set of features that were able to effectively predict brain stroke.FI provided a feature reduction ratio of 36.3%.The most successful hybrid system for predicting brain stroke used FI as the feature selection technique and RF as the classifier,achieving an accuracy of 97.17%.Conclusion The proposed system predicted brain stroke with high accuracy.These findings could be used to inform the early detection and prevention of brain stroke,allowing healthcare professionals to provide timely and targeted care to at-risk patients.

Beyond bag of latent topics: spatial pyramid matching for scene category recognition

We propose a heterogeneous, mid-level feature based method for recognizing natural scene categories. The proposed feature introduces spatial information among the latent topics by means of spatial pyramid, while the latent topics are obtained by using probabilistic latent semantic analysis （pLSA） based on the bag-of-words representation. The proposed feature always performs better than standard pLSA because the performance of pLSA is adversely affected in many cases due to the loss of spatial information. By combining various interest point detectors and local region descriptors used in the bag-of-words model, the proposed feature can make further improvement for diverse scene category recognition tasks. We also propose a two-stage framework for multi-class classification. In the first stage, for each of possible detector/descriptor pairs, adaptive boosting classifiers are employed to select the most discriminative topics and further compute posterior probabilities of an unknown image from those selected topics. The second stage uses the prod-max rule to combine information coming from multiple sources and assigns the unknown image to the scene category with the highest ＇final＇ posterior probability. Experimental results on three benchmark scene datasets show that the proposed method exceeds most state-of-the-art methods.

Skin Detection Method Based on Cascaded AdaBoost Classifier

Skin detection has been considered as the principal step in many machine vision systems,such as face detection and adult image filtering.Among all these techniques,skin color is the most welcome cue because of its robustness.However,traditional color-based approaches poorly perform on the classification of skin-like pixels.In this paper,we propose a new skin detection method based on the cascaded adaptive boosting(AdaBoost) classifier,which consists of minimum-risk based Bayesian classifier and models in different color spaces such as HSV(hue-saturation-value),YCgCb(brightness-green-blue) and YCgCr(brightness-green-red).In addition,we have constructed our own database that is larger and more suitable for training and testing on filtering adult images than the Compaq data set.Experimental results show that our method behaves better than the state-ofthe-art pixel-based skin detection techniques on processing images with skin-like background.

Cross-project software defect prediction based on multi-source data sets

Cross-project defect prediction(CPDP) uses one or more source projects to build a defect prediction model and applies the model to the target project. There is usually a big difference between the data distribution of the source project and the target project, which makes it difficult to construct an effective defect prediction model. In order to alleviate the problem of negative migration between the source project and the target project in CPDP, this paper proposes an integrated transfer adaptive boosting(TrAdaBoost) algorithm based on multi-source data sets(MSITrA). The algorithm uses an existing two-stage data filtering algorithm to obtain source project data related to the target project from multiple source items, and then uses the integrated TrAdaBoost algorithm proposed in the paper to build a CPDP model. The experimental results of Promise’s 15 public data sets show that: 1) The cross-project software defect prediction model proposed in this paper has better performance in all tested CPDP methods;2) In the within-project software defect prediction(WPDP) experiment, the proposed CPDP method has achieved the better experimental results than the tested WPDP method.