Scribd
Upload
2 views

Developing a Laboratory on Biomedical Signal Processing_group_2

The document outlines a laboratory framework for processing and analyzing biomedical signals to improve healthcare applications, including tools for diagnosis and real-time monitoring. It details experiments on signal preprocessing, machine learning classification, noise removal, and cancer cell detection, specifying objectives, equipment, methods, and expected outcomes for each experiment. The document emphasizes the importance of signal analysis techniques and machine learning in enhancing the understanding of biomedical signals.

Uploaded by

Dhiraj kumar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
2 views

Developing a Laboratory on Biomedical Signal Processing_group_2

The document outlines a laboratory framework for processing and analyzing biomedical signals to improve healthcare applications, including tools for diagnosis and real-time monitoring. It details experiments on signal preprocessing, machine learning classification, noise removal, and cancer cell detection, specifying objectives, equipment, methods, and expected outcomes for each experiment. The document emphasizes the importance of signal analysis techniques and machine learning in enhancing the understanding of biomedical signals.

Uploaded by

Dhiraj kumar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 9

Laboratory on

Biomedical Signal
Processing

Presented by:-
Hariom shankar
Dhiraj kumar
Shikha Sharma
Abhishek kumar choubey
Avinash kumar
Abhishek kumar
OBJECTIVE
•To develop a laboratory framework for processing,
analyzing, and interpreting biomedical signals to
enhance understanding and applications in healthcare.

•To create tools that facilitate signal analysis for


diagnosis, treatment, and real-time monitoring.

•Analysis of speech signal for Cancer detection.


Experiment 1- Signal Preprocessing

Objective:
Understand how to acquire biomedical signals and preprocess them for analysis.

Equipment:
Devices: ECG/EEG/EMG sensors.
Software: MATLAB, Python and signal processing tools.

Method:
Signal Acquisition: Record real ECG or EEG signals using an appropriate bio-signal
amplifier.
Preprocessing: Convert raw signals into a usable format (e.g., resample, filter out
low/high frequencies).
Normalization: Normalize signals for better analysis (e.g., scaling amplitudes).

Expected Outcome:
Successfully acquire raw biomedical signals and prepare them for further processing.
A deeper understanding of the preprocessing steps required for effective signal analysis.
Machine Learning)
Objective:
Implement machine learning techniques to classify biomedical signals
(e.g., classifying normal vs. abnormal ECG or EEG).

Equipment:
Datasets: Labeled datasets
Software: Python (libraries like TensorFlow, Keras).

Method:
Data Preprocessing: Perform preprocessing and feature extraction (e.g., time-domain features,
frequency-domain features).
Model Training: Train a classifier (e.g., Support Vector Machine, Random Forest, or Neural Network)
using labeled data.
Evaluation: Evaluate the model's performance using metrics like accuracy, sensitivity, and
specificity.

Expected Outcome:
A trained machine learning model that can classify abnormal signals (e.g., detecting arrhythmias in ECG or seizures in
Experiment 3- Noise Removal
and Filtering

Objective:
Apply signal processing techniques to remove noise from biomedical
signals.

Equipment:
Devices: ECG/EEG/EMG signal containing noise.
Software: MATLAB, Python and signal processing tools.

Method:
Bandpass Filtering: Apply a bandpass filter to remove unwanted
noise (e.g., high-frequency noise or baseline wander).
Notch Filtering: Use a notch filter to remove 50/60 Hz power-line
interference.
Wavelet Denoising: Apply wavelet transforms to remove noise
without affecting the signal’s important features.
Experiment 3- ….Continued
Expected Outcome:

Cleaned signals with noise removed, improving the quality of the data for
further analysis.
Cell Detection.
Objective:
Implement a holographic technique to detect cancer.

Equipment:
Software: Python, matlab.
Equipment: Microscope, laser light.

Method:
• Take a dead cancer cell.
•Transfer cells into petri dishes under sterile conditions.
•Monitor cell size growth for 2-3 week.

Expected Outcome:
Links
•ECG Heartbeat Categorization Dataset (kagg
le.com)
• Datasets | CRDC (cancer.gov)
•Datasets — Cancer Genomics Cloud
•Bing Videos

You might also like