Signal Classification using Long Short-Term Memory Networks

From: ₹200.00

Last day of registration: 7th May, 2025

 

Clear
SKU: 10th May, 2025 Categories: ,

Description of the Course

This workshop provides a comprehensive, hands-on experience in deep learning techniques for signal classification using a Long Short-Term Memory (LSTM) network, a type of Recurrent Neural Network (RNN). Throughout the workshop, the participants will use MATLAB, they will begin by importing and visualizing signals in the time domain to understand their features. They will then move on to learn essential techniques for preparing signals for training the model, such as filling in missing data points, standardizing sequence lengths, and dividing the dataset into training, validation, and test sets. Following this, participants will design and train an LSTM network, setting key training parameters and evaluating its performance using appropriate metrics. Finally, participants will learn how to improve model accuracy and efficiency, gaining a comprehensive understanding of LSTMs and their application in signal classification.

Profile of the Instructor(s)

Ms Shanthi is an experienced educator and online content developer at MathWorks, specializing in MATLAB for signal processing. She holds a master’s degree in Signal Processing. Shanthi’s professional interests span across subjects including Digital Signal Processing, Image Processing, Neural Networks, and Wireless Communication. Her scholarly contributions include publications in international journals on topics such as Video Compression Standards and their implementation in MATLAB and Background Subtraction Techniques in Image Processing. She started her career by training engineering graduates and has developed learning content for specialization courses using instructional design principles. At MathWorks, she creates online learning content related to MATLAB for signal processing and AI.

Ms Sragdhara is an online content developer at MathWorks focused on developing Simulink-based learning content. She holds a PhD degree in Control Systems. Her research areas include robust control, multi-rate control, cooperative control of multi-agent systems, decentralized control, and control of cyber physical systems. She has published papers in international journals and conferences in the domain of her research. She is also an AI enthusiast and is currently exploring the applications of machine learning and deep learning in the areas of signal and image processing and developing course content.

Eligibility Criteria & Intended Audience

Intended Audience:

Engineering Students, Researchers, and industry professionals working on Signal
Processing and AI Applications.

Eligibility :

Any Undergraduate or Masters Engineering Students, Researchers and Industry professionals working on Signal Processing and AI Applications can attend this workshop.

Prerequisites:

Basic MATLAB knowledge, Basics of Signal processing.

Modules Covered

  • Getting Started with MATLAB Online
  • Overview of Deep Learning for Signal Processing
  • Importing and Visualizing Signals
  • Signal Preprocessing
  • Splitting the Data into Training, Test, and Validation
  • LSTM Network
  • Train the LSTM Network
  • Evaluate the LSTM Network
  • Improve the Network Performance

Concepts Covered

  • Deep learning workflow
  • Application areas
  • Importing signals and labels
  • Visualize signals in the time domain
  • Fill missing data
  • Standardize signal length
  • Splitting the data into training, testing, and validation
  • LSTM networks
  • Sequence-to- label networks
  • Define the training options
  • Train the LSTM network
  • Calculate the prediction score, Training Accuracy
  • Confusion chart
  • Adjust the training options
  • Use BiLSTM layer

Learning Outcomes

  • Familiarize with the different stages in the Deep Learning workflow.
  • Import signals and corresponding labels within a cell array structure for further processing and analysis.
  • Plot signals in the time domain to gain insights into their characteristics.
  • Preprocess signal data by filling missing data points, ensuring datasets are clean and uniform for analysis.
  • Standardize the sequence length through signal padding and truncation to ensure consistency in the signal input.
  • Split signals into training, validation, and test sets to ensure the model is trained and evaluated correctly.
  • Evaluate and compare the performance of different CNN models for signal classification tasks.
  • Create a Long Short-Term Memory (LSTM) network architecture tailored for signal classification.
  • Train the LSTM network by setting the key training options that influence model learning.
  • Evaluate the performance of the trained LSTM model using relevant metrics.
  • Improve the model accuracy by adjusting the training options or using a Bidirectional LSTM (Bi-LSTM) layer.

Fees for the Workshop

Fees :

Students : Rs 236 (Rs 200 + 18% GST)

Faculty : Rs 590 (Rs 500 + 18% GST)

Industry : Rs 1180 (Rs 1000 + 18% GST)

Mode of Workshop : Online

Date of Workshop : 10th May, 2025

Timings: 10:00 a.m. to 01:00 p.m. (IST)

Certification

Certificates will be provided to all the participants who attends the workshop

Reviews

There are no reviews yet.

Be the first to review “Signal Classification using Long Short-Term Memory Networks”