Statistics and Machine Learning Applications

Apply statistics and machine learning methods to industry-specific workflows

Statistics and Machine Learning Toolbox™ provides tools to describe, analyze, and model data. Apply these tools, in combination with other MATLAB^® toolboxes, to perform industry-specific workflows. Some of the application areas include:

Aerospace — Explore radar and other signals, detect anomalies, and build predictive models.
Biotechnology and Pharmaceutical — Analyze clinical data, and perform modeling and simulation for drug discovery and development.
Communications and Signal Processing — Classify audio and other signals, and model wireless devices and integrated circuits.
Energy Production — Forecast energy demand, monitor production equipment, and optimize processing of chemicals in oil and gas.
Industrial Automation and Machinery — Apply multivariate statistics and predictive modeling to industrial process data, monitor manufacturing processes and product quality, and improve utilization and yields.
Medical Devices — Build interpretable machine learning algorithms on biomedical time series and image data for developing applications while complying with regulatory standards.
Quantitative Finance and Risk Management — Train, compare, and optimize models for algorithmic trading, asset allocation, credit risk, and fraud detection.

Aerospace

Radar Target Classification Using Machine Learning and Deep Learning (Radar Toolbox)

Classify radar returns using machine and deep learning approaches.

Biotechnology and Pharmaceutical

High-Throughput Sequencing

Identifying Differentially Expressed Genes from RNA-Seq Data (Bioinformatics Toolbox)
Use a negative binomial model to test RNA-Seq data for differentially expressed genes.
Exploring Protein-DNA Binding Sites from Paired-End ChIP-Seq Data (Bioinformatics Toolbox)
This example shows how to perform a genome-wide analysis of a transcription factor in the Arabidopsis Thaliana (Thale Cress) model organism.

Drug Discovery and Quantitative Systems Pharmacology

Perform PK/PD Modeling and Simulation to Guide Dosing Strategy for Antibiotics (SimBiology)
This example shows how to perform a Monte Carlo simulation of a pharmacokinetic/pharmacodynamic (PK/PD) model for an antibacterial agent.
Simulate the Glucose-Insulin Response (SimBiology)
Simulate and analyze a physiologically based glucose-insulin model for normal and diabetic patients.

Communications and Signal Processing

Data Analysis on S-Parameters of RF Data Files (RF Toolbox)

Perform statistical analysis on S-parameter data files using magnitude, mean, and standard deviation.

Wavelet Time Scattering with GPU Acceleration — Spoken Digit Recognition (Wavelet Toolbox)

Extract features on your GPU for signal classification.

Feature Selection for Audio Classification (Audio Toolbox)

Perform audio feature selection to select a feature set for either speaker recognition or word recognition tasks.

Speaker Identification Using Pitch and MFCC (Audio Toolbox)

Use machine learning to identify people based on features extracted from recorded speech.

Speaker Diarization Using x-vectors (Audio Toolbox)

Speaker diarization is the process of partitioning an audio signal into segments according to speaker identity.

Generate Synthetic Signals Using Conditional GAN (Signal Processing Toolbox)

Use a conditional generative adversarial network to produce synthetic signals.

Human Activity Recognition Using Signal Feature Extraction and Machine Learning (Signal Processing Toolbox)

Extract features from smartphone sensor signals and use them to classify human activity.

Energy Production

Predictive Analytics for Asset Management

Wind Turbine High-Speed Bearing Prognosis (Predictive Maintenance Toolbox)
Build an exponential degradation model to predict the Remaining Useful Life (RUL) of a wind turbine bearing in real time. The exponential degradation model predicts the RUL based on its parameter priors and the latest measurements.

Energy Trading and Risk Management (ETRM)

Model and Simulate Electricity Spot Prices Using the Skew-Normal Distribution (Econometrics Toolbox)
This example shows how to simulate the future behavior of electricity spot prices from a time series model fitted to historical data.
Hedging Strategies Using Spread Options (Financial Instruments Toolbox)
This example shows different hedging strategies to minimize exposure in the Energy market using Crack Spread Options.
Pricing Swing Options Using the Longstaff-Schwartz Method (Financial Instruments Toolbox)
This example shows how to price a swing option using a Monte Carlo simulation and the Longstaff-Schwartz method.

Industrial Automation and Machinery

Fault Detection Using Data Based Models (Predictive Maintenance Toolbox)

Use a data-based modeling approach for fault detection.

Anomaly Detection in Industrial Machinery Using Three-Axis Vibration Data (Predictive Maintenance Toolbox)

Detect anomalies in industrial-machine vibration data using machine learning and deep learning.

Build Condition Model for Industrial Machinery and Manufacturing Processes

Train a binary classification model using Classification Learner App to detect anomalies in sensor data collected from an industrial manufacturing machine.

Rolling Element Bearing Fault Diagnosis (Predictive Maintenance Toolbox)

Perform fault diagnosis of a rolling element bearing based on acceleration signals.

Fault Diagnosis of Centrifugal Pumps Using Residual Analysis (Predictive Maintenance Toolbox)

Use a model parity-equations-based approach for detection and diagnosis of faults in a pumping system.

Air Compressor Fault Detection Using Wavelet Scattering (Wavelet Toolbox)

Classify faults in acoustic recordings of air compressors using a wavelet scattering network and a support vector machine.

Predict Battery State of Charge Using Machine Learning

Train a Gaussian process regression model to predict the state of charge of a battery in automotive engineering.

Deploy Neural Network Regression Model to FPGA/ASIC Platform

Predict in Simulink^® using a neural network regression model, and deploy the Simulink model to an FPGA/ASIC platform by using HDL code generation.

Monitor Equipment State of Health Using Drift-Aware Learning

This example shows how to automate the process of monitoring the state of health for a cooling system using an incremental drift-aware learning model and Streaming Data Framework for MATLAB® Production Server™.

Medical Devices

Wavelet Time Scattering for ECG Signal Classification (Wavelet Toolbox)

Classify human electrocardiogram signals using wavelet time scattering and a support vector machine classifier.

Wavelet Time Scattering Classification of Phonocardiogram Data (Wavelet Toolbox)

Classify human phonocardiogram recordings using wavelet time scattering and a support vector machine classifier.

Human Activity Recognition Simulink Model for Smartphone Deployment

Generate code from a classification Simulink model prepared for deployment to a smartphone.

Human Activity Recognition Simulink Model for Fixed-Point Deployment

Generate code from a classification Simulink model prepared for fixed-point deployment.

Quantitative Finance and Risk Management

Algorithmic Trading

Machine Learning for Statistical Arbitrage: Introduction (Financial Toolbox)
Get an overview of the workflow for statistical arbitrage and then follow a series of examples to see how capabilities in MATLAB apply.
Machine Learning for Statistical Arbitrage II: Feature Engineering and Model Development (Financial Toolbox)
Create a continuous-time Markov model of limit order book (LOB) dynamics, and develop a strategy for algorithmic trading based on patterns observed in the data.

Credit Risk

Forecasting Corporate Default Rates (Financial Toolbox)
This example shows how to build a forecasting model for corporate default rates.
Credit Scoring Using Logistic Regression and Decision Trees (Risk Management Toolbox)
Create and compare two credit scoring models, one based on logistic regression and the other based on decision trees.

Portfolio Optimization and Asset Allocation

Portfolio Optimization Using Factor Models (Financial Toolbox)
This example shows two approaches for using a factor model to optimize asset allocation under a mean-variance framework.

Econometric Modeling

Time Series Regression I: Linear Models (Econometrics Toolbox)
This example introduces basic assumptions behind multiple linear regression models.
Time Series Regression III: Influential Observations (Econometrics Toolbox)
This example shows how to detect influential observations in time series data and accommodate their effect on multiple linear regression models.

Featured Examples

Forecasting Corporate Default Rates

Build a forecasting model for corporate default rates.

Radar Target Classification Using Machine Learning and Deep Learning

Classify radar returns using machine and deep learning approaches.

Rolling Element Bearing Fault Diagnosis

Perform fault diagnosis of a rolling element bearing based on acceleration signals.

Data Analysis on S-Parameters of RF Data Files

Perform statistical analysis on S-parameter data files using magnitude, mean, and standard deviation.

Hedging Strategies Using Spread Options

Different hedging strategies to minimize exposure in the Energy market using Crack Spread Options.

Human Activity Recognition Simulink Model for Smartphone Deployment

Generate code from a classification Simulink model prepared for deployment to a smartphone.

Open Live Script

Perform PK/PD Modeling and Simulation to Guide Dosing Strategy for Antibiotics

Perform a Monte Carlo simulation of a pharmacokinetic/pharmacodynamic (PK/PD) model for an antibacterial agent. This example is adapted from Katsube et al. [1] This example also shows how to use the SimBiology® SimFunction object to perform parameter scans in parallel.