Thank you for visiting the MathWorks booth. If you are interested in the Loren's presentation or have any questions, please feel free to send us a private message or contact us from the MathWorks website.  Presenter: Loren Shure, Ph.D. in geophysics, MathWorks

Overview:
MATLAB has many features that make handling and viewing geospatial data much easier and require much less coding. During this talk, Loren, a geophysicist by training and a MATLAB expert by day, will use MATLAB to demonstrate two different earthquake case studies including:
  - Accessing and visualizing geospatial data
  - Work with big data
  - Reproducible research

Presenter Bio:
Loren has worked at MathWorks for over 30 years. For the first 27 of these years, Loren co-authored several MathWorks products in addition to adding core functionality to MATLAB, including major contributions to the design of the MATLAB language. She is currently part of the Application Engineering team, enabling Loren to spend more time and energy working with customers.

Loren graduated from MIT with a B.Sc. in physics and has a Ph.D. in marine geophysics from the University of California, San Diego, Scripps Institution of Oceanography. She is a Senior Member of IEEE; and she is co-author on several patent inventions. Loren writes about MATLAB on her blog, The Art of MATLAB Deep learning is increasingly used to analyze various images, such as satellite images and photographs taken during fieldwork, as well as one-dimensional signals such as seismic and radar signals. MATLAB has Deep Learning Toolbox as an add-on product, that runs deep learning from start to end in a one-stop environment.


Example of Deep Learning: Semantic Segmentation of multispectral imagery



MATLAB Oil and Gas Conference 2019: Seismic Analysis with Wavelets and Deep Learning You can process according to general workflow from labeling, to building the network, learning, and then implementing the finished network. MATLAB is designed with ease of use in mind. The GUI-based application, which allows you to select a dataset and learn all at once, supports you. We're ready to implement your ideas right away.



Deep Learning Toolbox also covers one-dimensional signals. There are several methods for this. One is using LSTM, a deep neural network that takes time information into account. The other is two-dimensionalization of signals, then application of image deep learning. You can also use the Signal Labeler app for labeling signals. MATLAB has apps that can perform various processing and analysis with GUI. The registration app is used to register two images to align the subject by superimposing them. This type of alignment is sometimes useful as a pre-processing step in deep learning to improve accuracy. We also have a variety of other apps that will save time in your analysis.



Signal Processing
Signal Processing Toolbox is used best for pre-processing and analysis of 1D signals such as seismic waves. You can do time synchronization of multiple signals, noise reduction, the extraction of obviously valid features and so on.



Time-Frequency Analysis
One-dimensional signals can also be made two-dimensional by obtaining the spectrum of each time, and applied to image deep learning, such as classification and detection. You can do all these conversions with the functions in Signal Processing Toolbox and Audio Toolbox.

Noise Reduction with Wavelet Transform
Wavelet Transform allows you to decompose the signals and images into different levels of resolution. By using this technique, you can effectively reduce noise while keeping the edges and singularity that the low-pass filter using the Fourier transform will inevitably degrades. You can feel the effect easily using Wavelet Toolbox app and functions.



There are many more features in MATLAB. Please find more videos on MathWorks website and YouTube.
  - Videos on MathWorks website
  - YouTube MATLAB Channel Using MathWorks cloud tools, you can engage students even in remote classes. For example, using MATLAB Online, students can access to MATLAB without installation.

MATLAB Drive is a cloud-based file sharing system that makes it easy to share files between faculty and students.

Using a smartphone application called MATLAB Mobile, it is possible to acquire sensor data and conduct experiments and data analysis using MATLAB even in remote classes.