JKUAT-SES

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.

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


Resources from this Episode GitHub link.

1. First notebook
2. Second notebook
3. Third notebook
4. More can be found on the TensorFlow official website

• 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

- Digital Principles and Applications by Donald P. Leach and Albert P. Malvino. 

- Memories in Arduino

- Memories of an Arduino by Adafruit

- Digital Electronics: Principles and Integrated Circuits by Anil K. Maini.

- Arduino MemoryFree Github repository.

Laurine Owino, Lamoy, reveals how to integrate memory devices into your projects. Check out his Twitter handle @cee_lamoy. 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-memoryDevices

Amos Wanene reveals how to design and fabricate an audio amplifier using Kicad. Check out his 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/audioAmplifier-2021.

The IC used is the TEA2025B and it is applied in the bridge-tied mode for single speaker application.

https://bestengineeringprojects.com/tone-control-circuit-active-and-passive/ https://www.angelfire.com/electronic/funwithtubes/Amp-Tone-A.html https://www.circuitstoday.com/passive-tone-control-circuit https://learnabout-electronics.org/Amplifiers/amplifiers42.php

https://www.homemade-circuits.com/small-amplifier-circuit/ https://bestengineeringprojects.com/preamplifier-circuit/

Michael Kimani reveals how to design and machine a mechanical product using computer softwares making little or no mistake in production. Check out his Twitter handle @kimanimike99 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-CAM.

Andrew Omolo and Yvonne Mureithi reveal how to design and analyse a mechanical product making little or no mistake in production. Check out their Twitter handles @VonRigz @r3wnad  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-DesignMechanicalSystem.

Kelvin Mwaniki reveals how to build the see devkit board an esp based board able to perform better than the Atmel chip. 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/sesBoardv1.

We put a lot of trust into Arduino, Atmel chip: building our fourth-year applications, tech expo applications even startup rapid prototyping demos. In return, we have faith that the Atmel chip will perform to the best of its ability. That trust didn’t come easily.

Michael Kimani and Felix Wanyoike reveal how stm32 boards and esp family of boards are able to perform better than the Atmel chip.

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/superchargeArduino-2021.