CMSR Data Miner / Machine Learning / Rule Engine Studio
Predictive Modeling by Machine Learning & Rule Engine & Data Mining

CMSR Data Miner / Machine Learning / Rule Engine Studio (CMSR Studio for short) provides an integrated environment for machine learning, predictive modeling, expert system shell rule engine, and big-data data mining. CMSR is a perfect platform to develop advanced predictive models using deep learning techniques, for business data, combining predictive models and business rules. Deploy models on the web and mobile devices, and embed machine learning predictive models into business applications.

CMSR Studio Screenshots

[CMSR Update] If you already have CMSR Studio, you may need to update your CMSR Studio. Note that Microsoft Internet Explorer which is used to render HTML reports will be removed from your system. New CMSR update will allow you to use Edge Browser. You can update to the latest version. For update download, click CMSR Update Download.

High Performance: In-memory technology and GPU
CMSR employs the following technology to provide high performance;

• In-Memory Technology: Large advanced in-memory data management technology provides high performance.
• Massively Parallel Fine-grained Data Parallel Image Processing: CPU and GPU. Multi-core-threads and GPU computing for image modeling. Both OpenCL and CUDA implemented. Computer vision training can be over hundreds or thousands times fast on GPU than on a single CPU thread! For more, please read OpenCL vs CUDA GPU

SQL Database Support
CMSR supports connections to most standard SQL database systems through JDBC drivers: MySQL, PostgreSQL, SQL Server, MariaDB, Amazon Redshift, Hive/Hadoop, Oracle, DB2, etc. Models can be applied to database tables directly. Data can be imported directly from database tables. Charts can be drawn directly from database tables.

Windows and MacOS Supported
CMSR is developed with Java. It can run on Windows and Mac OS.

Computer Vision and GPU Deployment for Embedded Applications

CMSR Studio can generate computer vision model deployment program source codes for GPU in C++ and Java and Swift and Objective-C for the following GPU API platforms. Note that compute vision models are compute intensive. So GPU deployment is essential.

• OpenCL: Java and C++. Windows, Linux, Android. SBC.
• CUDA: Java and C++. Windows, Linux. SBC.
• OpenGL ES (GLES3): C++. Android, Raspberry Pi. SBC.
• Apple Metal: Swift and Objective-C. MacOS, iOS, iTablet.

Generate source code. Include in your application and call. That's what all it takes! CMSR Computer Viision models include;

• Image classification.
• Image regression: single or multiple output values.
• Bounding boxes object detection, a la YOLO.
• Similarity regression of two images, e.g., face recognition.

For more about edge computing devices, see the following links;

• Raspberry Pi SBC
• Orange Pi SBC

Neural Network Algorithms and Applications

• ANN (Artificial Neural Network): Predictive modeling for statistical data. For application examples, read risk management for credit, finance, insurance, etc.
• CNN (Convolutional Neural Network): Computer vision. Image to classification and probability prediction. For application examples, read Skin Cancer and Machine Learning and try CMSR Powered Skin Cancer Checker website.
• FCN (Fully Convolutional Neural Network): Computer vision. Image to classification and probability prediction.
• M-CNN (Multivariable CNN): Computer vision. Image to (multi-)value prediction. For application examples, read Wildfire/Bushfire detection.
• T-CNN (Twin/Siamese CNN): Computer vision. Image to similarity probability. Application examples include face recognition, similarity analysis, etc.
• OD-CNN (YOLO-like modeling)(Object Detection CNN): Computer vision. Image to object detection. For application examples, read Wildfire/Bushfire detection.
• SOM (Self Organizing Maps): Clustering and customer segmentation.

Other Algorithms and Charts

• Rule engine with machine learning models
• Decision tree modeling
• Regression modeling
• Hotspot drill-down analysis
• Association rules - Apriori algorithm
• Co-items shopping basket analysis
• Confusion map analysis
• Correlation analysis
• Time-series (with regression, seasonal adjustment, charts)
• Time-series similarity analysis
• Group-by reports (with regression, seasonal adjustment, charts)
• Cross table reports
• Visual charts: bars, 3D bars, areas, pies, lines, histograms, Sankey diagram, histobars, scatterplots, boxplots, normal quantile plots, ...
• t-tests, ANOVA, ...
• And more ...

For more information, please click here.

(Note that StarProbe data miner is replaced with CMSR Data Miner / Machine Learning / Rule Engine Studio.)