Accuracy Of Machine Learning Methods Research Articles

Interpretable machine learning for creditor recovery rates

Machine learning methods have achieved great success in modeling complex patterns in finance such as asset pricing and credit risk that enable them to outperform statistical models. In addition to the predictive accuracy of machine learning methods, the ability to interpret what a model has learned is crucial in the finance industry. We address this challenge by adapting interpretable machine learning to the context of corporate bond recovery rate modeling. In addition to the best performance, we show the value of interpretable machine learning by finding drivers of recovery rates and their relationship that cannot be discovered by the use of traditional machine learning methods. Our findings are financially meaningful and consistent with the findings in the existing credit risk literature.

Predictive deep learning models for analyzing discrete fractional dynamics from noisy and incomplete data

We study the accuracy of machine learning methods for inferring the parameters of noisy fractional Wu–Baleanu trajectories with some missing initial terms. Our model is based on a combination of convolutional and recurrent neural networks (LSTM), which permits the extraction of characteristics from trajectories while preserving time dependency. We show that these approach exhibit good accuracy results despite the poor quality of the data.

Machine Learning Classification of Event-Related Brain Potentials during a Visual Go/NoGo Task.

Machine learning (ML) methods are increasingly being applied to analyze biological signals. For example, ML methods have been successfully applied to the human electroencephalogram (EEG) to classify neural signals as pathological or non-pathological and to predict working memory performance in healthy and psychiatric patients. ML approaches can quickly process large volumes of data to reveal patterns that may be missed by humans. This study investigated the accuracy of ML methods at classifying the brain's electrical activity to cognitive events, i.e., event-related brain potentials (ERPs). ERPs are extracted from the ongoing EEG and represent electrical potentials in response to specific events. ERPs were evoked during a visual Go/NoGo task. The Go/NoGo task requires a button press on Go trials and response withholding on NoGo trials. NoGo trials elicit neural activity associated with inhibitory control processes. We compared the accuracy of six ML algorithms at classifying the ERPs associated with each trial type. The raw electrical signals were fed to all ML algorithms to build predictive models. The same raw data were then truncated in length and fitted to multiple dynamic state space models of order nx using a continuous-time subspace-based system identification algorithm. The 4nx numerator and denominator parameters of the transfer function of the state space model were then used as substitutes for the data. Dimensionality reduction simplifies classification, reduces noise, and may ultimately improve the predictive power of ML models. Our findings revealed that all ML methods correctly classified the electrical signal associated with each trial type with a high degree of accuracy, and accuracy remained high after parameterization was applied. We discuss the models and the usefulness of the parameterization.

Artificial Intelligent-Based Wake Word Detection at Edge Device

Deep Neural Network based wake word (such as Hi Alexa or Hey Siri) systems allow increasingly accurate speech communication between humans and machines. However, this setup requires high processing power or cloud services which may not be accessible by edge devices. Currently, the accuracy of machine learning methods for cloudless edge devices in voice activation hovers below 90%. This paper explores wake word implementation on edge devices using a 2-Dimensional Convolutional Neural Network (CNN) with improved and balanced accuracy and latency. The proposed CNN model is created, trained and quantized using TensorFlow on a PC and exported to a Raspberry Pi Zero 2 W. The quantization method reduces the model size by 20% and spectral gating is adopted to lower wake word inaccuracy detection in moderately noisy environment. The proposed system achieved more than 90% wake word detection accuracy across 30 to 50 dB background noise with an average of 1.03 second of response time for the intended user. The result shows low-powered edge device still offers competitive performance for detecting wake word without cloud services.

Playing the pipes: acoustic sensing and machine learning for performance feedback during endotracheal intubation simulation.

Objective: In emergency medicine, airway management is a core skill that includes endotracheal intubation (ETI), a common technique that can result in ineffective ventilation and laryngotracheal injury if executed incorrectly. We present a method for automatically generating performance feedback during ETI simulator training, potentially augmenting training outcomes on robotic simulators. Method: Electret microphones recorded ultrasonic echoes pulsed through the complex geometry of a simulated airway during ETI performed on a full-size patient simulator. As the endotracheal tube is inserted deeper and the cuff is inflated, the resulting changes in geometry are reflected in the recorded signal. We trained machine learning models to classify 240 intubations distributed equally between six conditions: three insertion depths and two cuff inflation states. The best performing models were cross validated in a leave-one-subject-out scheme. Results: Best performance was achieved by transfer learning with a convolutional neural network pre-trained for sound classification, reaching global accuracy above 98% on 1-second-long audio test samples. A support vector machine trained on different features achieved a median accuracy of 85% on the full label set and 97% on a reduced label set of tube depth only. Significance: This proof-of-concept study demonstrates a method of measuring qualitative performance criteria during simulated ETI in a relatively simple way that does not damage ecological validity of the simulated anatomy. As traditional sonar is hampered by geometrical complexity compounded by the introduced equipment in ETI, the accuracy of machine learning methods in this confined design space enables application in other invasive procedures. By enabling better interaction between the human user and the robotic simulator, this approach could improve training experiences and outcomes in medical simulation for ETI as well as many other invasive clinical procedures.

A Decision-Fusion-Based Ensemble Approach for Malicious Websites Detection

Malicious websites detection is one of the cyber-security tasks that protects sensitive information such as credit card details and login credentials from attackers. Machine learning (ML)-based methods have been commonly used in several applications of cyber-security research. Although there are some methods and approaches proposed in the state-of-the-art studies, the advancement of the most effective solution is still of research interest and needs to be improved. Recently, decision fusion methods play an important role in improving the accuracy of ML methods. They are broadly classified based on the type of fusion into a voting decision fusion technique and a divide and conquer decision fusion technique. In this paper, a decision fusion ensemble learning (DFEL) model is proposed based on voting technique for detecting malicious websites. It combines the predictions of three effective ensemble classifiers, namely, gradient boosting (GB) classifier, extreme gradient boosting (XGB) classifier, and random forest (RF) classifier. We use these classifiers because their advantages to perform well for class imbalanced and data with statistical noises such as in the case of malicious websites detection. A weighted majority-voting rule is utilized for generating the final decisions of used classifiers. The experimental results are conducted on a publicly available large dataset of malicious and benign websites. The comparative study exposed that the DFEL model achieves high accuracies, which are 97.25% on average of 10-fold cross-validation test and 98.50% on a holdout of 30% test set. This confirms the ability of proposed approach to improve the detection rate of malicious websites.

Predictions of Tesla Stock Price based on Linear Regression, SVM, Random Forest, LSTM and ARIMA

The stock market of a country is an important financial market. A booming stock market promotes the effective use of social capital, the prudent deployment of economic resources, and the expansion of the country's macroeconomics. Making more informed decisions as an investor is made possible by the development of trustworthy equity market models. A trading model allows market participants to select corporations that pay the highest dividend payments while lowering the risks associated with investing. However, batch processing methodologies make stock market research more challenging as a result of the strong connection between stock prices. The advent of technological achievements like universal digitization has elevated share market forecasting into a highly advanced age. Through the research and comparison of several methodologies, this article tries to discover the most accurate approach for predicting Tesla stock closing prices. Predictions are made using statistical approaches such as ARIMA and machine learning methods such as SVM , Linear Regression, Random Forests, and LSTM. Following a thorough examination of all approaches, it was discovered that the accuracy of machine learning methods in predicting stocks is higher than that of statistical methods and integrated algorithm technologies like Random Forest have excellent anti-interference and anti-overfitting characteristics, which are more suitable for evaluating high-volatility stocks like Tesla.

Аналіз методів і засобів забезпечення кібербезпеки веб-сервісів з використанням штучного інтелекту

A thorough analysis of literary sources on the application of artificial intelligence (AI) in cyber security was carried out. During the examination, the most significant attention was paid to sources describing the use of AI-based applications to analyze and evaluate existing systems for vulnerabilities, as well as to sources that consider the features of using built-in AI mechanisms for searching, detecting, classifying, and combating attacks on the system during her works. The types, impacts, and features of attacks on web services are defined. The features of the application of AI for the classification of web services under test are considered, with the aim of further justifying the selection of the best tools for ensuring their cyber security. The methods of using AI in the cyber security of web services during the introduction of built-in mechanisms and models for searching, detecting, classifying, and countering threats are analyzed. The accuracy of machine learning methods used to detect intrusions was compared. Directions for further research can cover: the development of methods, models, and applications based on the use of AI for analyzing the source code for possible vulnerabilities of a web service with support for various programming languages and the development of mechanisms for search and classification of threats based on the use of AI built into the web service.

Improving the Classification Accuracy in Label-Free Flow Cytometry Using Event-Based Vision and Simple Logistic Regression

Event-based cameras are novel bio-inspired vision sensors that do not follow the mechanism of traditional frame-based cameras. In the field of data acquisition, the replacement of CMOS cameras with event-based cameras has proved to enhance the accuracy of machine learning methods in situations where critical lighting conditions and rapid dynamics are paramount. In this paper, we investigate for the first time the use of extreme learning machines on data coming from event-based cameras in the context of flow cytometry. Except for the image sensor, the experimental setup is similar to a setup we used in (Lugnan et al., 2020) where we showed that a simple linear classifier can achieve around 10% error rate on background-subtracted cell frames. Here, we show that the the error rate of this simple imaging flow cytometer could be decreased to less than 2% just by making use of the capabilities of an event camera. Moreover, additional benefits like more sensitivity and efficient memory usage are gained. Finally, we suggest further possible improvements to the experimental setup used to record events from flowing micro-particles allowing for more accurate and stable cellx sorting.

A New Approach of Hybrid Sampling SMOTE and ENN to the Accuracy of Machine Learning Methods on Unbalanced Diabetes Disease Data

A New Approach of Hybrid Sampling SMOTE and ENN to the Accuracy of Machine Learning Methods on Unbalanced Diabetes Disease Data

DOES MACHINE LEARNING PREDICTION DAMPEN THE INFORMATION ASYMMETRY FOR NON-LOCAL INVESTORS?

In this study, we examine the prediction accuracy of machine learning methods to estimate commercial real estate transaction prices. Using machine learning methods, including Random Forest (RF), Gradient Boosting Machine (GBM), Support Vector Machine (SVM), and Deep Neural Networks (DNN), we estimate the commercial real estate transaction price by comparing relative prediction accuracy. Data consist of 19,640 transaction-based office properties provided by Costar corresponding to the 2004–2017 period for 10 major U.S. CMSA (Consolidated Metropolitan Statistical Area). We conduct each machine learning method and compare the performance to identify a critical determinant model for each office market. Furthermore, we depict a partial dependence plot (PD) to verify the impact of research variables on predicted commercial office property value. In general, we expect that results from machine learning will provide a set of critical determinants to commercial office price with more predictive power overcoming the limitation of the traditional valuation model. The result for 10 CMSA will provide critical implications for the out-of-state investors to understand regional commercial real estate market.

Prediction Method for Mine Earthquake in Time Sequence Based on Clustering Analysis

Under the background of the intelligent construction of a coal mine, how to efficiently extract effective information from the massive monitoring data of mine earthquakes, and improve prediction accuracy, is a research hotspot in the field of coal mine safety production. In view of this problem, more and more machine learning methods are being applied to the prediction on mine earthquakes. Considering that clustering analysis can enhance the correlation between microseism data, we propose a method whose main idea is to cluster microseism data before establishing the prediction model, and then train the model, so as to improve prediction accuracy. Specifically, microseism events on a working face are divided into clusters in advance by the Spatial Temporal-DBSCAN(ST-DBSCAN) algorithm, then a prediction model is established with Support Vector Regression (SVR) to predict the occurrence location and daily frequency of high-energy mine earthquake events. A set of engineering experiments were conducted in H Coal Mine, and the results show that the spatial-temporal clustering analysis of microseism events can indeed improve the prediction accuracy of machine learning methods on mine earthquakes.

Learning by neural networks under physical constraints for simulation in fluid mechanics

The Physical Informed Neural Networks (PINN) model is one of the emerging and promising Deep Learning approaches to predict physical phenomena governed by PDEs such as fluid flow dynamics. The PINN model is indeed of great importance for improving the accuracy of machine learning methods for predicting mass transfer problems. However, it is sensitive to the accuracy of input datasets, and also struggles to predict phenomena occurring in complex geometries. These two weaknesses could limit the application of the PINN model. In this article, we improve the use of the PINN model by combining it with a One-hot matrix model to better take into account the boundary conditions on complex geometries. The use of the One-hot matrix is also investigated with non-uniform weights from physics. We indeed used the Q-criterion as a non-uniform weight to enforce the vortical structure location by the neural network. The proposed model more accurately predicts the two-dimensional flow around sharp rectangular obstacles from low-resolution datasets.

A new cyclical generative adversarial network based data augmentation method for multiaxial fatigue life prediction

To meet the requirement of large experimental data for machine learning (ML) methods on multiaxial life prediction, a cyclical Generative Adversarial Network (named cGAN) integrating Fourier transformation and other semi-empirical equations, was proposed to augment data following physical knowledge. Two samples of each loading path can be augmented into hundreds of good quality samples. Consequently, the accuracy of ML methods for multiaxial fatigue life of 316L stainless steel can been improved by 35%-91%. The new method can definitely balance time cost of bigger sample size and prediction accuracy well.

Application of Artificial Intelligence Techniques for the Determination of Groundwater Level Using Spatio-Temporal Parameters.

Increasing the depth of mining leads to the location of the mine pit below the groundwater level. The entry of groundwater into the mining pit increases costs as well as reduces efficiency and the level of work safety. Prediction of the groundwater level is a useful tool for managing groundwater resources in the mining area. In this study, to predict the groundwater level, multilayer perceptron, cascade forward, radial basis function, and generalized regression neural network models were developed. Moreover, four optimization algorithms, including Bayesian regularization, Levenberg–Marquardt, resilient backpropagation, and scaled conjugate gradient, are used to improve the performance and prediction ability of the multilayer perception and cascade forward neural networks. More than 1377 data points including 12 spatial parameters divided into two categories of sediments and bedrock (longitude, latitude, hydraulic conductivity of sediments and bedrock, effective porosity of sediments and bedrock, the electrical resistivity of sediments and bedrock, depth of sediments, surface level, bedrock level, and fault), and besides, 6 temporal parameters are used (day, month, year, drainage, evaporation, and rainfall). Also, to determine the best models and combine them, 165 extra validation data points are used. After identifying the best models from the three candidate models with a lower average absolute relative error (AARE) value, the committee machine intelligence system (CMIS) model has been developed. The proposed CMIS model predicts groundwater level data with high accuracy with an AARE value of less than 0.11%. Sensitivity analysis indicates that the electrical resistivity of sediments had the highest effect on the groundwater level. Outliers’ estimation applying the Leverage approach suggested that only 2% of the data points could be doubtful. Eventually, the results of modeling and estimating groundwater level fluctuations with low error indicate the high accuracy of machine learning methods that can be a good alternative to numerical modeling methods such as MODFLOW.

Rapid seed viability prediction of Sophora japonica by improved successive projection algorithm and hyperspectral imaging

Hyperspectral imaging technology (HSI) is considered to be a promising technology to detect and predict seed viability quickly and without damage. This research aimed to use HSI combined with deep learning methods to identify the seed viability of Sophora japonica. After simulating natural aging, high-viability, low-viability and non-viability seeds were distinguished, and then data collection continued for the first 10 h of seed imbibition. The validation set accuracy of machine learning methods (support vector machine (SVM) and random forest (RF)) without preprocessing was less than 80%, while the one-dimensional deep learning methods (convolutional neural network (CNN), recurrent neural network (RNN) and its superposition) were above 95%. An improvement was proposed on the basis of the original successive projection algorithm (SPA) and compared with three typical algorithms. When Autoregressive locally optimized successive projection algorithm (ALO-SPA) was combined with RNN, the detection model worked best. Therefore, based on this model, the vitality prediction was established using the data of swelling 0 h, and its effect was better than that of detection model. The results show that hyperspectral imaging combined with deep learning model can more accurately predict the seed viability of Sophora japonica.

Application of machine learning methods in photovoltaic output power prediction: A review

As the proportion of photovoltaic (PV) power generation rapidly increases, accurate PV output power prediction becomes more crucial to energy efficiency and renewable energy production. There are numerous approaches for PV output power prediction. Many researchers have previously summarized PV output power prediction from different angles. However, there are relatively few studies that use machine learning methods as a means to conduct a separate review of PV output power prediction. This review classifies machine learning methods from different perspectives and provides a systematic and critical review of machine learning methods for recent PV output power applications in terms of the temporal and spatial scales of prediction and finds that the artificial neural network and support vector machine are used much more frequently than other methods. In addition, this study examines the differences between the output power prediction of individual PV plants and regional PV stations and the benefits of regional PV plant prediction, while this paper presents some performance evaluation matrices commonly used for PV output power prediction. In addition, to further improve the accuracy of machine learning methods for PV output power prediction, some researchers suggest preprocessing the input data of the prediction models or considering hybrid machine learning methods. Furthermore, the potential advantages of machine model optimization for prediction performance improvement are discussed and explored in detail.

Emotion recognition model based on CLSTM and channel attention mechanism

In this paper, we propose an emotion recognition model based on convolutional neural network (CNN), long short term memory (LSTM) and channel attention mechanism, aiming at the low classification accuracy of machine learning methods and the uneven spatial distribution of electroencephalogram (EEG) electrodes. This model can effectively integrate the frequency, space and time information of EEG signals, and improve the accuracy of emotion recognition by adding channel attention mechanism after the last convolutional layer of the model. Firstly, construct a 4-dimensional structure representing EEG signals. Then, a CLSTM model structure combining CNN and LSTM is designed. CNN is used to extract frequency and spatial information from 4-dimensional input, and LSTM is used to extract time information. Finally, the channel attention module is added after the last convolutional layer of CLSTM model structure to allocate the weight of different electrodes. In this paper, an emotion recognition model based on CLSTM and channel attention mechanism was proposed from the perspective of integrating the frequency, space and time 3-dimensional information of EEG signals. The average classification accuracy of the model on SEED public data set reached 93.36%, which was significantly improved over the existing CNN and LSTM emotion recognition models.

Predicting COVID-19 mortality risk in Toronto, Canada: a comparison of tree-based and regression-based machine learning methods

BackgroundCoronavirus disease (COVID-19) presents an unprecedented threat to global health worldwide. Accurately predicting the mortality risk among the infected individuals is crucial for prioritizing medical care and mitigating the healthcare system’s burden. The present study aimed to assess the predictive accuracy of machine learning methods to predict the COVID-19 mortality risk.MethodsWe compared the performance of classification tree, random forest (RF), extreme gradient boosting (XGBoost), logistic regression, generalized additive model (GAM) and linear discriminant analysis (LDA) to predict the mortality risk among 49,216 COVID-19 positive cases in Toronto, Canada, reported from March 1 to December 10, 2020. We used repeated split-sample validation and k-steps-ahead forecasting validation. Predictive models were estimated using training samples, and predictive accuracy of the methods for the testing samples was assessed using the area under the receiver operating characteristic curve, Brier’s score, calibration intercept and calibration slope.ResultsWe found XGBoost is highly discriminative, with an AUC of 0.9669 and has superior performance over conventional tree-based methods, i.e., classification tree or RF methods for predicting COVID-19 mortality risk. Regression-based methods (logistic, GAM and LASSO) had comparable performance to the XGBoost with slightly lower AUCs and higher Brier’s scores.ConclusionsXGBoost offers superior performance over conventional tree-based methods and minor improvement over regression-based methods for predicting COVID-19 mortality risk in the study population.

Study on the Estimation of Forest Volume Based on Multi-Source Data.

We performed a comparative analysis of the prediction accuracy of machine learning methods and ordinary Kriging (OK) hybrid methods for forest volume models based on multi-source remote sensing data combined with ground survey data. Taking Larix olgensis, Pinus koraiensis, and Pinus sylvestris plantations in Mengjiagang forest farms as the research object, based on the Chinese Academy of Forestry LiDAR, charge-coupled device, and hyperspectral (CAF-LiTCHy) integrated system, we extracted the visible vegetation index, texture features, terrain factors, and point cloud feature variables, respectively. Random forest (RF), support vector regression (SVR), and an artificial neural network (ANN) were used to estimate forest volume. In the small-scale space, the estimation of sample plot volume is influenced by the surrounding environment as well as the neighboring observed data. Based on the residuals of these three machine learning models, OK interpolation was applied to construct new hybrid forest volume estimation models called random forest Kriging (RFK), support vector machines for regression Kriging (SVRK), and artificial neural network Kriging (ANNK). The six estimation models of forest volume were tested using the leave-one-out (Loo) cross-validation method. The prediction accuracies of these six models are better, with values above 0.6, and the prediction accuracy values of the hybrid models are all improved to different extents. Among the six models, the RFK hybrid model had the best prediction effect, with an reaching 0.915. Therefore, the machine learning method based on multi-source remote sensing factors is useful for forest volume estimation; in particular, the hybrid model constructed by combining machine learning and the OK method greatly improved the accuracy of forest volume estimation, which, thus, provides a fast and effective method for the remote sensing inversion estimation of forest volume and facilitates the management of forest resources.