NB Algorithms Research Articles

Detection of Cardiovascular Diseases in ECG Images Using Machine Learning and Deep Learning Methods

Cardiovascular diseases (heart diseases) are the leading cause of death worldwide. The earlier they can be predicted and classified; the more lives can be saved. Electrocardiogram (ECG) is a common, inexpensive, and noninvasive tool for measuring the electrical activity of the heart and is used to detect cardiovascular disease. In this article, the power of deep learning techniques was used to predict the four major cardiac abnormalities: abnormal heartbeat, myocardial infarction, history of myocardial infarction, and normal person classes using the public ECG images dataset of cardiac patients. First, the transfer learning approach was investigated using the low-scale pretrained deep neural networks SqueezeNet and AlexNet. Second, a new convolutional neural network (CNN) architecture was proposed for cardiac abnormality prediction. Third, the aforementioned pretrained models and our proposed CNN model were used as feature extraction tools for traditional machine learning algorithms, namely support vector machine, K-nearest neighbors, decision tree, random forest, and Naïve Bayes. According to the experimental results, the performance metrics of the proposed CNN model outperform the exiting works; it achieves 98.23% accuracy, 98.22% recall, 98.31% precision, and 98.21% F1 score. Moreover, when the proposed CNN model is used for feature extraction, it achieves the best score of 99.79% using the NB algorithm.

A Framework for Predicting Airfare Prices Using Machine Learning

Many academics have concentrated on applying machine learning to retrieve information from databases to enable researchers to perform better. A difficult issue in prediction models is the selection of practical strategies that yield satisfactory forecast accuracy. Traditional software testing techniques have been extended to testing machine learning systems; however, they are insufficient for the latter because of the diversity of problems that machine learning systems create. Hence, the proposed methodologies were used to predict flight prices. A variety of artificial intelligence algorithms are used to attain the required, such as Bayesian modeling techniques such as Stochastic Gradient Descent (SGD), Adaptive boosting (ADA), Decision Trees (DT), K-nearest neighbor (KNN), and Logistic Regression (LR), have been used to identify the parameters that allow for effective price estimation. These approaches were tested on a data set of an extensive Indian airline network. When it came to estimating flight prices, the results demonstrate that the Decision tree method is the best conceivable Algorithm for predicting the price of a flight in our particular situation with 89% accuracy. The SGD method had the lowest accuracy, which was 38 %, while the accuracies of the KNN, NB, ADA, and LR algorithms were 69 %, 45 %, and 43 %, respectively. This study's presented methodologies will allow airline firms to predict flight prices more accurately, enhance air travel, and eliminate delay dispersion. Index Terms— Machine learning, Prediction model, Airline price prediction, Software testing,

Prediction of Voltage Sag Relative Location with Data-Driven Algorithms in Distribution Grid

Power quality (PQ) problems, including voltage sag, flicker, and harmonics, are the main concerns for the grid operator. Among these disturbances, voltage sag, which affects the sensitive loads in the interconnected system, is a crucial problem in the transmission and distribution systems. The determination of the voltage sag relative location as a downstream (DS) and upstream (US) is an important issue that should be considered when mitigating the sag problem. Therefore, this paper proposes a novel approach to determine the voltage sag relative location based on voltage sag event records of the power quality monitoring system (PQMS) in the real distribution system. By this method, the relative location of voltage sag is defined by Gaussian naive Bayes (Gaussian NB) and K-nearest neighbors (K-NN) algorithms. The proposed methods are compared with support vector machine (SVM) and artificial neural network (ANN). The results indicate that K-NN and Gaussian NB algorithms define the relative location of a voltage sag with 98.75% and 97.34% accuracy, respectively.

Public sentiments toward COVID-19 vaccines in South African cities: An analysis of Twitter posts.

Amidst the COVID-19 vaccination, Twitter is one of the most popular platforms for discussions about the COVID-19 vaccination. These types of discussions most times lead to a compromise of public confidence toward the vaccine. The text-based data generated by these discussions are used by researchers to extract topics and perform sentiment analysis at the provincial, country, or continent level without considering the local communities. The aim of this study is to use clustered geo-tagged Twitter posts to inform city-level variations in sentiments toward COVID-19 vaccine-related topics in the three largest South African cities (Cape Town, Durban, and Johannesburg). VADER, an NLP pre-trained model was used to label the Twitter posts according to their sentiments with their associated intensity scores. The outputs were validated using NB (0.68), LR (0.75), SVMs (0.70), DT (0.62), and KNN (0.56) machine learning classification algorithms. The number of new COVID-19 cases significantly positively correlated with the number of Tweets in South Africa (Corr = 0.462, P < 0.001). Out of the 10 topics identified from the tweets using the LDA model, two were about the COVID-19 vaccines: uptake and supply, respectively. The intensity of the sentiment score for the two topics was associated with the total number of vaccines administered in South Africa (P < 0.001). Discussions regarding the two topics showed higher intensity scores for the neutral sentiment class (P = 0.015) than for other sentiment classes. Additionally, the intensity of the discussions on the two topics was associated with the total number of vaccines administered, new cases, deaths, and recoveries across the three cities (P < 0.001). The sentiment score for the most discussed topic, vaccine uptake, differed across the three cities, with (P = 0.003), (P = 0.002), and (P < 0.001) for positive, negative, and neutral sentiments classes, respectively. The outcome of this research showed that clustered geo-tagged Twitter posts can be used to better analyse the dynamics in sentiments toward community–based infectious diseases-related discussions, such as COVID-19, Malaria, or Monkeypox. This can provide additional city-level information to health policy in planning and decision-making regarding vaccine hesitancy for future outbreaks.

An Image Processing Approach for Detection of Prenatal Heart Disease.

Prenatal heart disease, generally known as cardiac problems (CHDs), is a group of ailments that damage the heartbeat and has recently now become top deaths worldwide. It connects a plethora of cardiovascular diseases risks to the urgent in need of accurate, trustworthy, and effective approaches for early recognition. Data preprocessing is a common method for evaluating big quantities of information in the medical business. To help clinicians forecast heart problems, investigators utilize a range of data mining algorithms to examine enormous volumes of intricate medical information. The system is predicated on classification models such as NB, KNN, DT, and RF algorithms, so it includes a variety of cardiac disease-related variables. It takes do with an entire dataset from the medical research database of patients with heart disease. The set has 300 instances and 75 attributes. Considering their relevance in establishing the usefulness of alternate approaches, only 15 of the 75 criteria are examined. The purpose of this research is to predict whether or not a person will develop cardiovascular disease. According to the statistics, naïve Bayes classifier has the highest overall accuracy.

Construction and Application of Automatic Attendance Prediction System for Classroom Education Teaching Based on Random Matrix Theory

Random matrix theory, as a theoretical tool for statistical processing of complex systems and high-dimensional data, has been more and more combined with big data technology and applied to automatic attendance prediction analysis of classroom education. Firstly, the basic definition of the random matrix is introduced. Secondly, the single ring theorem of the random matrix is introduced. Based on this, the random matrix model of data is established. However, few undergraduate or graduate students in physics have been exposed to this theory. By introducing the basic concept of random matrix theory, this paper analyzes the necessity and feasibility of introducing random matrix theory into automatic attendance prediction teaching in classroom education. As a biometrics technology, random matrix theory technology has been widely used in various fields of the identity verification system, and classroom attendance system is an important field of random matrix theory technology application. The traditional random matrix theory class attendance has the problem of slow recognition speed and low accuracy. With the popularity of deep learning, the random matrix theory based on deep learning has gradually replaced the traditional random matrix theory. In this paper, the SSD target detection algorithm, NB algorithm, and RF algorithm based on deep learning are used to improve and optimize the traditional random matrix theory class attendance system, which effectively improves the efficiency and accuracy of random matrix theory attendance. Then, aiming at the low recall rate and recognition rate of random matrix theory in low-pixel images, we try to apply the random matrix theory of single image resolution reconstruction method to face detection and random matrix theory and give a calculation method to deal with outliers and noise.

Wearable Real-Time Gesture Recognition Scheme Based on A-Mode Ultrasound.

A-mode ultrasound has the advantages of high resolution, easy calculation and low cost in predicting dexterous gestures. In order to accelerate the popularization of A-mode ultrasound gesture recognition technology, we designed a human-machine interface that can interact with the user in real-time. Data processing includes Gaussian filtering, feature extraction and PCA dimensionality reduction. The NB, LDA and SVM algorithms were selected to train machine learning models. The whole process was written in C++ to classify gestures in real-time. This paper conducts offline and real-time experiments based on HMI-A (Human-machine interface based on A-mode ultrasound), including ten subjects and ten common gestures. To demonstrate the effectiveness of HMI-A and avoid accidental interference, the offline experiment collected ten rounds of gestures for each subject for ten-fold cross-validation. The results show that the offline recognition accuracy is 96.92% ± 1.92%. The real-time experiment was evaluated by four online performance metrics: action selection time, action completion time, action completion rate and real-time recognition accuracy. The results show that the action completion rate is 96.0% ± 3.6%, and the real-time recognition accuracy is 83.8% ± 6.9%. This study verifies the great potential of wearable A-mode ultrasound technology, and provides a wider range of application scenarios for gesture recognition.

Predicting 1-Year Mortality after Hip Fracture Surgery: An Evaluation of Multiple Machine Learning Approaches.

Postoperative death within 1 year following hip fracture surgery is reported to be up to 27%. In the current study, we benchmarked the predictive precision and accuracy of the algorithms support vector machine (SVM), naïve Bayes classifier (NB), and random forest classifier (RF) against logistic regression (LR) in predicting 1-year postoperative mortality in hip fracture patients as well as assessed the relative importance of the variables included in the LR model. All adult patients who underwent primary emergency hip fracture surgery in Sweden, between 1 January 2008 and 31 December 2017 were included in the study. Patients with pathological fractures and non-operatively managed hip fractures, as well as those who died within 30 days after surgery, were excluded from the analysis. A LR model with an elastic net regularization were fitted and compared to NB, SVM, and RF. The relative importance of the variables in the LR model was then evaluated using the permutation importance. The LR model including all the variables demonstrated an acceptable predictive ability on both the training and test datasets for predicting one-year postoperative mortality (Area under the curve (AUC) = 0.74 and 0.74 respectively). NB, SVM, and RF tended to over-predict the mortality, particularly NB and SVM algorithms. In contrast, LR only over-predicted mortality when the predicted probability of mortality was larger than 0.7. The LR algorithm outperformed the other three algorithms in predicting 1-year postoperative mortality in hip fracture patients. The most important predictors of 1-year mortality were the presence of a metastatic carcinoma, American Society of Anesthesiologists(ASA) classification, sex, Charlson Comorbidity Index (CCI) ≤ 4, age, dementia, congestive heart failure, hypertension, surgery using pins/screws, and chronic kidney disease.

Energy management of hybrid energy system sources based on machine learning classification algorithms

Hybrid energy systems (HES) that contain renewable energy sources, such as wind and solar energy help to minimize CO2 emissions. Therefore, studying these systems to improve their performance has become one of the critical needs these days due to the environmental crisis. Within HES, energy management (EM) of HES is an essential topic that has been covered in detail by numerous studies, as errors in EM can lead to HES blackouts. Recent research has experimented with energy management strategy (EMS) to achieve optimal EM. This work aims to generate a robust forecasting model for one hour ahead of EM. The present research work has two main objectives. The first objective is to determine which energy source should supply the demand side, using different machine-learning algorithms such as Random Forest (RF), Decision Tree (DT), Gaussian Naive Bayes (Gaussian NB) and K-Nearest Neighbors (KNN). The second objective is to compare the results of these algorithms to choose the algorithm with the best performance and to rank them based on performance as well as accuracy. The work is validated using different algorithms. The results show that DT algorithm has achieved the best performance compared to the RF and Gaussian NB algorithms. KNN algorithm gives the lowest accuracy especially over class 3. The results proof that RF, DT, and Gaussian NB algorithms are reliable.

Optimizing weighted lazy learning and Naive Bayes classification using differential evolution algorithm

Naive Bayes is a well-known classification algorithm in machine learning area. Since it is based on combinations of efficiently computable probability estimates, NB is often a good choice for high-dimensional problems such as text classification. However, NB is based on a conditional independence assumption between attributes which is often violated in real-world applications. Accordingly, lots of work has been done to improve the performance of NB, such as structure extension, attribute selection, attribute weighting, instance weighting and instance selection. An alternative strategy to address the limitations of NB is to apply NB only over the neighbors of the instance that needs to be classified, where the independence assumption may be more justified. However, this introduces another practical problem – the high variance resulting from insufficient training data when building the NB model only over the neighbors rather than the original training dataset. In this paper, a new learning algorithm named Weighted Lazy Naive Bayes (WLNB) is presented. WLNB is designed to address the variance issue by augmenting the nearest neighbors of a test instance. Then, a self-adaptive evolutionary process is applied to automatically learn two key parameters in WLNB. In this way, a method named Evolutionary Weighted Lazy Naive Bayes (EWLNB) is formed. EWLNB uses Differential Evolution to search optimal values for parameters, which makes the method quite effective. Experimental evaluations on 56 UCI machine learning benchmark datasets demonstrate that EWLNB significantly outperforms NB and several other improved NB algorithms in terms of classification accuracy and class probability estimation.

Wise-local response convolutional neural network based on Naïve Bayes theorem for rotating machinery fault classification

Fault identification is a vital task to ensure the integrity and reliability of rotating machinery. The vibration signals produced by the defective system components typically bear a significant amount of noise, including non-linear and non-stationary characteristics induced by the intricate operational environment. Advanced signal processing technologies still have difficulty in detecting faults in mechanical systems. This paper presents a wise local response convolution neural network-based Naive Bayes algorithm (WCNN-NB) to identify multiple faults in rotating machines. In WCNN-NB, the WCNN structure is first used to characterize the features of the gray-scale images transformed from the original vibration signals. The nonlinearity parameter value of WCNN is explored in order to enhance learning efficiency. The NB algorithm is then used as a robust steady-state method to identify the learned features. Experimental data regarding helical gears and bearing test rigs are used to validate the feasibility of the WCNN-NB model. The superiority of the classification results is verified by comparing the current model with the WCNN-support vector machine, WCNN-random forest, standard CNN, the support vector machine (SVM) and the neural backpropagation network (BP) models. The results demonstrate that the classification accuracy is 99.68%, 92.5% and 97.5% for three data sets with tolerable misclassification rates under all operational conditions.

Alleviating NB conditional independence using Multi-stage variable selection(MSVS): Banking customer dataset application

Customer research is one of the important aspects of understanding customer behavior patterns with business enterprises and predicate how consumer satisfaction is achieved. Customer analysis brings out various underlying information about the customer patterns with enterprises and analysis decision helps to make better marketing strategies to improve the customer lifetime and also enhance the business profit. To perform effective customer analysis in this research Naive Bayes an ML algorithm is applied. The efficiency of NB comes from its conditional independence assumption and the violation of NB assumption results in poor prediction. But in most real-time customer datasets, the NB assumption is violated due to the presence of correlated, irrelevant, and noisy variables. To improve NB prediction with these customer customers, in this research Multi-Stage Variable Selection(MSVS) is proposed to select the relevant variables from the customer dataset which helps to predicate the customer patterns wisely. The proposed approach consists of two stages in selecting the relevant variable subset from the customer datasets. Further variable subset obtained from the proposed MSVS approach is experimented with using the NB algorithm and the results obtained are compared using the wrapper and filter approaches. From the results, it clearly shows the proposed MSVS approach performs better in selecting the variable subset and improves the NB prediction in customer analysis efficiency compare to wrapper and filter approaches. Further, the proposed approach works efficiently in time and less computational compare to wrapper and filter approaches.

Integrated meta-analysis and machine learning approach identifies acyl-CoA thioesterase with other novel genes responsible for biofilm development in Staphylococcus aureus.

Biofilm forming Staphylococcus aureus is a major threat to the health-care industry. It is important to understand the differences between planktonic and biofilm growth forms in the pathogen since conventional treatments targeting the planktonic forms are not effective against biofilms. The current study conducts a meta-analysis of three public transcriptomic profiles to examine the differences in gene expression between the planktonic and biofilm states of S. aureus using random-effects modeling. Mean effect sizes were calculated for 2847 genes among which 726 differentially expressed genes were taken for further analysis. Major genes that are discriminatory between the two conditions were mined using supervised learning techniques and validated by high-accuracy classifiers. Ten different feature selection algorithms were applied and used to rank the most important genes in S. aureus biofilms. Finally, an optimal set of 36 genes are presented as candidate genes in biofilm formation or development while throwing light on the novel roles of an acyl-CoA thioesterase enzyme and 10 hypothetical proteins in biofilms. The relevance of the identified gene set was further validated by building five different classification models using SVM, RF, kNN, NB and DT algorithms that were compared with models built from other relevant gene sets and by reviewing the functional role of 25 previously known genes in biofilm development. The study combines meta-analysis of differential expression with supervised machine learning strategies and feature selection for the first time to identify and validate a discriminatory set of genes important in biofilms of S. aureus. The functional roles of the identified genes predicted to be important in biofilms are further scrutinized and can be considered as a signature target list to develop anti-biofilm therapeutics in S. aureus.

Gojek and Grab User Sentiment Analysis on Google Play Using Naive Bayes Algorithm And Support Vector Machine Based Smote Technique

As the online Ojek services, people often talk about them by giving their opinions and opinions through various media, one of which is Google Play opinion given by the public to the services of online Ojek also diverse. Users provide review reviews or comments about the application, of course users will choose an app that has a good review. But monitoring the reviews of the general public is not easy, because the amount is very much to be processed so that researchers want to know the extent of the user review analysis of Gojek and Grab applications based on the review of user comments using the classification technique is using the NB algorithm and SVM based technique Smote. The results of the test with the highest accuracy result 81.09% and AUC value = 0.922 is the application Gojek while for application test results grab accuracy value of 73.20% and AUC value = 0.848. To that end, the implementation of the Support Vector Machine based Smote technique in this study has higher accuracy so that it can be used to provide solution to the sentiment analysis problems in the review user comments online Ojek application

Feature Dependent Naïve Bayes For Network Intrusion Detection System

The intrusion detection system is an important component that performs the analysis for. the problem arising from the IDS is a collection of data sets in a computer network. to increase the high level and low false positive level of approach with the learning machine in applied. The data mining algorithm used is Naïve bayes one of the most widely used algorithms in space due to its simplicity, efficiency and effectiveness. NB has high accuracy and speed when applied into the database with large data. However, the NB algorithm assumes independent attributes (free) and is very sensitive to the selection of many features that interfere with the performance or accuracy of the NB to be low but in practice, the possibilities of the feature are interrelated. The Feature Dependent Naïve Bayes (FDNB) method is an effective method used to solve existing problems in NB by computing features as pairs and creating dependencies between each other as well as by applying learning models implemented to cross-validation, Feature Selection and data steps preprocessing that gives better accuracy results. After testing with two models of Naïve bayes and FDNB, the results obtained from the Naïve Bayes algorithm resulted in an accuracy of 84.42%, while for FDNB and oversampling (CFS + GS) the accuracy was 94.58%, FDNB and oversampling (CFS + BFS) the accuracy value of 94.69%, FDNB and SMOTE (CFS + GS) and FDNB and SMOTE (CFS + BFS) has an accuracy value of 93.27%. For the average per attack type DOS attack shows the highest result for its accuracy value of 97.86% and U2R attack produces the best accuracy when classifying U2R with 93.80% accuracy, U-F size of 96.26% U2R can be considered as a very result nice. Because U2R attack is considered very dangerous.

Architecture Design of Emotion Recognition Early Warning System Based on AE-TAN Algorithm

In order to improve the analysis effect of human emotion text data, this paper proposed NB algorithm, TAN algorithm and AE-TAN algorithm model method. In addition, three index parameters, precision, recall and F1 value, are compared and analyzed under three different algorithm model scenarios. The experimental results show that the AE-TAN algorithm is superior to the other two algorithms in Chinese text emotion analysis. Based on the AE-TAN algorithm, the architecture design scheme of emotion recognition early warning system was proposed in this paper, which has the characteristics of high concurrency and high availability, thus laying a technical foundation for the system that can quickly and accurately warn people of psychological problems.

Exploring multinomial naïve Bayes for Yorùbá text document classification

The recent increase in the emergence of Nigerian language text online motivates this paper in which the problem of classifying text documents written in Yorùbá language into one of a few pre-designated classes is considered. Text document classification/categorization research is well established for English language and many other languages; this is not so for Nigerian languages. This paper evaluated the performance of a multinomial Naive Bayes model learned on a research dataset consisting of 100 samples of text each from business, sporting, entertainment, technology and political domains, separately on unigram, bigram and trigram features obtained using the bag of words representation approach. Results show that the performance of the model over unigram and bigram features is comparable but significantly better than a model learned on trigram features. The results generally indicate a possibility for the practical application of NB algorithm to the classification of text documents written in Yorùbá language.&#x0D; Keywords: Supervised learning, text classification, Yorùbá language, text mining, BoW Representation

Automatic Dialogue System of Marriage Law Based on the Parallel C4.5 Decision Tree

In order to realize real-time marriage legal consultation automatically, a marriage legal dialogue system based on the parallel C4.5 decision tree was designed in this paper. Firstly, the legal consultation problem is transformed into a classification task. Secondly, a legal consultation classification prediction model based on the parallel C4.5 decision tree algorithm was trained with MapReduce by collected data. Finally, a model based on the SVM algorithm, which has a strategy that was designed to provide automatic interaction for users, was designed to extract attribute value from the user's input. When a new user comes to consult, an automatic legal dialogue is launched to respond to user intelligently. The proposed system works well in some real applications, such as the divorce problem, and the experimental results show that it is outperforming the SVM and NB algorithm and more applicable than the other two algorithms. Moreover, the system can return consultation results with fewer questions asked to the user than some automatic legal consultation websites, which improves the efficiency of consultation.

A novel differential evolution algorithm integrating opposition-based learning and adjacent two generations hybrid competition for parameter selection of SVM

Generalization performance of support vector machines (SVM) with Gaussian kernel is influenced by its model parameters, both the error penalty parameter and the Gaussian kernel parameter. The differential evolution (DE) algorithms have strong search ability and easy to implement. But it falls into local optimum easily. Hence a novel differential evolution algorithm which integrating opposition-based learning and hybrid competition between adjacent two generations is put forward for parameter selection of SVM (DGODE-SVM). In DGODE-SVM algorithm, opposition-based learning and hybrid competition between adjacent two generations are inserted into the differential evolution process. Nineteen experimental results on UCI datasets distinctly show that, compared with ODE-SVM, SaDE-SVM, DE-SVM, SVM, C4.5, KNN and NB algorithms, the proposed algorithm has higher classification accuracy.

Application of Naïve Bayes, Decision Tree, and K-Nearest Neighbors for Automated Text Classification

Nowadays, many applications that use large data have been developed due to the existence of the Internet of Things. These applications are translated into different languages and require automated text classification (ATC). The ATC process depends on the content of one or more predefined classes. However, this process is problematic for the Arabic translation of the data. This study aims to solve this issue by investigating the performances of three classification algorithms, namely, k-nearest neighbor (KNN), decision tree (DT), and na&amp;iuml;ve Bayes (NB) classifiers, on Saudi Press Agency datasets. Results showed that the NB algorithm outperformed DT and KNN algorithms in terms of precision, recall, and F1. In future works, a new algorithm that can improve the handling of the ATC problem will be developed.