Related Experiment Video
Updated: Dec 28, 2025
04:04
Asthma Detection Research Based on Voice Signal Processing and Machine Learning
Published on: July 22, 2025
822
Classification of VLF/LF Lightning Signals Using Sensors and Deep Learning Methods
Jiaquan Wang1,2, Qijun Huang1, Qiming Ma2
1School of Physics and Technology, Wuhan University, Wuhan 430072, China.
Sensors (Basel, Switzerland)
|February 21, 2020
Summary
This study introduces an accurate deep learning method for classifying lightning waveforms using a one-dimensional convolutional neural network (1D-CNN). The model achieved high accuracy, aiding in lightning observation and disaster investigation.
Area of Science:
- Atmospheric Physics
- Electrical Engineering
- Computer Science
Background:
- Lightning waveform analysis is crucial for observation, location, and disaster investigation.
- Existing methods require accurate and automatic lightning waveform classification.
- Deep learning offers potential for advanced waveform analysis.
Purpose of the Study:
- To develop an automatic and accurate lightning waveform classification method.
- To utilize deep learning for distinguishing various lightning waveform types.
- To enhance lightning monitoring and positioning capabilities.
Main Methods:
- Collected and categorized 50,000 lightning waveform samples.
- Designed a multi-layer one-dimensional convolutional neural network (1D-CNN).
- Employed the 1D-CNN to automatically extract features and classify waveforms.
Main Results:
- Achieved 99.11% overall accuracy on the lightning dataset.
- Attained 97.55% overall accuracy during a thunderstorm process.
- Demonstrated the model's effectiveness in distinguishing diverse lightning types.
Conclusions:
- The developed 1D-CNN model accurately classifies lightning waveforms.
- This method significantly improves lightning observation and disaster investigation.
- The model is suitable for integration into lightning sensors for real-time monitoring.
Related Concept Videos
01:30Classification of Signals
1.2K
In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
1.2K
01:22Force Classification
2.2K
Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
2.2K
02:16Light Acquisition
9.3K
In order to produce glucose, plants need to capture sufficient light energy. Many modern plants have evolved leaves specialized for light acquisition. Leaves can be only millimeters in width or tens of meters wide, depending on the environment. Due to competition for sunlight, evolution has driven the evolution of increasingly larger leaves and taller plants, to avoid shading by their neighbors with contaminant elaboration of root architecture and mechanisms to transport water and nutrients.
9.3K