JKUAT-SES jkuatses

Bernice Ngethe reveals how to do image classification. Check out her Twitter handle.  If you want to read up on some of our research, you can check out all our bonus material over at https://github.com/JKUATSES/2021-image-classification



Image classification is pattern recognition in image data using algorithms. Two methods may be used:

* Deep learning - uses convolution neural networks to progressively extract higher- and higher-level representations of the image content

The CNN comprises a stack of modules, each of which performs three operations.

1. Convolution -extracts tiles of the input feature map, and applies filters to them to compute new features, producing an output feature map, or convolved feature (which may have a different size and depth than the input feature map). Convolutions are defined by two parameters:

*Size of the tiles that are extracted (typically 3x3 or 5x5 pixels).

*The depth of the output feature map, which corresponds to the number of filters that are applied.

2. Rectified Linear Unit (ReLU)- the CNN applies a  transformation to the convolved feature following each convolution operation, in order to introduce nonlinearity into the model

3. Pooling - the CNN downsamples the convolved feature (to save on processing time), reducing the number of dimensions of the feature map, while still preserving the most critical feature information. A common algorithm used for this process is called max pooling.

* Transfer learning using pre-trained models

In this image classification, both methods were used comparatively and transfer learning had way better performance.

REFERENCES

* https://medium.com/analytics-vidhya/image-equalization-contrast-enhancing-in-python-82600d3b371c

* https://www.mygreatlearning.com/blog/introduction-to-image-pre-processing/

* https://jannik-zuern.medium.com/using-a-tpu-in-google-colab-54257328d7da

* https://towardsdatascience.com/image-enhancement-techniques-using-opencv-and-python-9191d5c30d45

* https://machinelearningmastery.com/how-to-control-the-speed-and-stability-of-training-neural-networks-with-gradient-descent-batch-size/

* https://developers.google.com/machine-learning/practica/image-classification/convolutional-neural-networks

* https://www.kdnuggets.com/2019/08/introduction-image-segmentation-k-means-clustering.html

* https://machinelearningmastery.com/how-to-improve-performance-with-transfer-learning-for-deep-learning-neural-networks/

Tinega Chris reveals how to do electrical simulations for your project. Check out his Twitter handle @tinegachris  If you want to read up on some of our research, you can check out all our bonus material over at https://github.com/JKUATSES/2021-electricalSimulation

Kelvin Mwaniki reveals how to build binary phase-shift keying which can be used by Kenya Power. Check out his Twitter handle @mwaniki169  If you want to read up on some of our research, you can check out all our bonus material over at https://github.com/JKUATSES/2021-DSS.

We are discussing what are Artificial Intelligence Space in Kenya. To aid in our discussion, I have Felix Wanyoike, Bernice Ng’ethe and Gladys Gachoka.

In today’s episode, we cover the fundamentals of image classification.


Resources from this Episode GitHub link.


First notebook
Second notebook
Third notebook
More can be found on the TensorFlow official website

Everything you need to get you started with the control theory is discussed here. We will cover Introduction into control systems, Types of control systems, PID control, State Space representation, Drone control (example), Self balancing robot (example) and adaptive cruise control (example).

Resources:  


Types of contro systems: 
Introduction to control systems:   
State-space represenbtation and controllability: 
Thrust vector control for rockets using PID:   
Drone flight dynamics: 
PID control tuning for self balancing robots:   
Inverted pendulum on a cart demostartion: 
Control system design for autonomous cars: 
Adaptive cruise control:     
Adaptive Cruise Control Project Using MATLAB and Arduino Uno Board: 
Introduction to fuzzy logic: 

I must say this is fun.

Jeff Mboya, reveals how to integrate control theory into your projects. Check out his Twitter handle @AnginaMboya. If you want to read up on some of our research, you can check out all our bonus material over at https://github.com/JKUATSES/2021-ControlTheory