Binary Class Image Classification Deep Learning Model for Meat Quality Assessment Using TensorFlow Take 2

Template Credit: Adapted from a template made available by Dr. Jason Brownlee of Machine Learning Mastery.

SUMMARY: This project aims to construct a predictive model using a TensorFlow convolutional neural network (CNN) and document the end-to-end steps using a template. The Meat Quality Assessment dataset is a binary classification situation where we attempt to predict one of two possible outcomes.

INTRODUCTION: The research team collected the dataset to develop a meat quality assessment system based on deep learning. The published paper explains all of the experimental results, proving the usability of the dataset and model. This dataset contains fresh and spoiled red meat samples from a supermarket in Izmir, Turkey, for a university-industry collaboration project at the Izmir University of Economics.

For this modeling project, we will predict whether an image represents a fresh or spoiled meat case. In this iteration, we will construct a CNN model based on the ResNet152V2 architecture to make predictions.

ANALYSIS: In this iteration, the ResNet152V2 model’s performance achieved an accuracy score of 98.88% after 15 epochs using the training dataset. The same model processed the validation dataset with an accuracy rate of 88.10%.

CONCLUSION: In this iteration, the ResNet152V2-based CNN model appeared to be suitable for modeling this dataset. We should consider experimenting with TensorFlow for further modeling.

Dataset Used: Meat Quality Assessment

Dataset ML Model: Binary classification with numerical attributes

Dataset Reference: https://www.kaggle.com/crowww/meat-quality-assessment-based-on-deep-learning

One potential source of performance benchmarks: https://ieeexplore.ieee.org/abstract/document/8946388

The HTML formatted report can be found here on GitHub.

Binary Class Image Classification Deep Learning Model for Meat Quality Assessment Using TensorFlow Take 1

Template Credit: Adapted from a template made available by Dr. Jason Brownlee of Machine Learning Mastery.

SUMMARY: This project aims to construct a predictive model using a TensorFlow convolutional neural network (CNN) and document the end-to-end steps using a template. The Meat Quality Assessment dataset is a binary classification situation where we attempt to predict one of two possible outcomes.

INTRODUCTION: The research team collected the dataset to develop a meat quality assessment system based on deep learning. The published paper explains all of the experimental results, proving the usability of the dataset and model. This dataset contains fresh and spoiled red meat samples from a supermarket in Izmir, Turkey, for a university-industry collaboration project at the Izmir University of Economics.

For this modeling project, we will predict whether an image represents a fresh or spoiled meat case. In this iteration, we will construct a CNN model based on the InceptionV3 architecture to make predictions.

ANALYSIS: In this iteration, the InceptionV3 model’s performance achieved an accuracy score of 99.80% after 15 epochs using the training dataset. The same model processed the validation dataset with an accuracy rate of 92.86%.

CONCLUSION: In this iteration, the InceptionV3-based CNN model appeared to be suitable for modeling this dataset. We should consider experimenting with TensorFlow for further modeling.

Dataset Used: Meat Quality Assessment

Dataset ML Model: Binary classification with numerical attributes

Dataset Reference: https://www.kaggle.com/crowww/meat-quality-assessment-based-on-deep-learning

One potential source of performance benchmarks: https://ieeexplore.ieee.org/abstract/document/8946388

The HTML formatted report can be found here on GitHub.

Seth Godin on Survival Is Not Enough, Part 1

In his book, Survival Is Not Enough: Why Smart Companies Abandon Worry and Embrace Change, Seth Godin discusses how innovative organizations and individuals can apply prudent strategies in adapting and positioning themselves for the constant changes.

These are some of my favorite concepts and takeaways from reading the book.

Chapter 1, Change

In this chapter, Seth discusses why change is no longer something we can control with absolute certainty and the better strategies to deal with changes. He offers the following observations and recommendations for us to think about:

  • Many companies are not organized for change because they have never needed to be. Growing and profiting from stable times was a terrific strategy.
  • Unfortunately, change is now constant. The fundamental ideas we have used to build our companies and careers are quickly going out of style. The world is changing on our watch, and it is not fun.
  • Seth outlines the four structural changes in the business that have taken place in the last several decades:
    • “The speed at which we make decisions is now the factor that limits the speed of business.” Our decisions are on the critical path of getting things done, and the lead time for many things we do has shrunk dramatically.
    • “The Net has made information close to free and close to ubiquitous, further fueling the need for speed.”
    • Our worldview of having islands of stability is disappearing. “There’s only one market, and it’s the whole world.”
    • “Metcalfe’s law (networks get more powerful when they connect more people) has reached infinity.” As a result, we are all virtually connected.
  • For a long time, owning physical plants and factories has been the best way to get rich. However, with rich connectivity and cheap shipping, the factory-centric model is dying. Being factory-centric does not increase our profits but decreases them. The Factory-centric model also does not lessen our time to market; it now likely increases it.
  • Surviving change is a noble goal, but we need to find ways to embrace changes and get better results. We need to turn working with changes into a positive feedback loop.
  • When people start interacting in a positive feedback loop, the loop can get amplified and enter a stage called runaway. Even though runaway cannot last forever, it is fun while it lasts. So our job should be to figure out how to trigger a runaway, do it again later, and create a never-ending series of positive feedback loops and runaway successes.
  • Our fear of changing a used-to-be successful winning strategy combined with our reliance on command-and-control tactics makes it hard for us to embrace change. Evolution (inheritable modifications over many generations) is the most potent tactic for dealing with change. We should apply this proven, organic technique to embrace change, not fight it.

In summary, Seth suggests that we take an active role in embracing change. “Change is out of our control, and the way we deal with change is outmoded and ineffective. Our organizations assume that we live with a different, slower time cycle.”

用努力去追求質量

(從我一個尊敬的作家,賽斯·高汀

質量的定義是始終符合規範。並做出與遵守可衡量的承諾。

努力是當我們超出正常速度時會發生的事情。當我們進行體力或情感勞動來深入挖掘,並且專注在與眾不同的事情時。努力與滑行是相反的。

我們經常被教導質量是努力的結果。如果你只是更加努力地嘗試,你就會更接近需要滿足的規範。

然而,當我們查看以質量著稱的組織、品牌或個人時,我們完全不清楚他們是否付出了更多的努力。因為這種努力是根本不可能永久持續的下。

在凌志工廠工作的人在一天結束時並不比製造凱迪拉克的工人來的更累。這與努力無關。對於從不錯過交貨的 Dabbawalla 來說也是如此。事實上,如果只專注於努力(以及您團隊的努力),這幾乎可以保證您的質量問題將持續存在。

持續存在的質量問題是一個系統性問題,如果您不在系統上下功夫,您就不會改進不了它。

“我們該怎麼做這項工作?”是比一個“我們該怎麼更努力去做?”更好的問題。

Web Scraping of NeurIPS Conference Proceedings 2020 Using Python and BeautifulSoup

SUMMARY: The purpose of this project is to practice web scraping by extracting specific pieces of information from a website. The web scraping Python code leverages the BeautifulSoup module.

INTRODUCTION: The Conference on Neural Information Processing Systems (NeurIPS) covers a wide range of topics in neural information processing systems and research for the biological, technological, mathematical, and theoretical applications. Neural information processing is a field that benefits from a combined view of biological, physical, mathematical, and computational sciences. This web scraping script will automatically traverse through the entire web page and collect all links to the PDF and PPTX documents.

Starting URL: https://proceedings.neurips.cc/paper/2020

The source code and HTML output can be found here on GitHub.

Multi-Class Analytics Project Template Using Python and TensorFlow Decision Forests Version 1

As I work on practicing and solving machine learning (ML) problems, I find myself repeating a set of steps and activities repeatedly.

Thanks to Dr. Jason Brownlee’s suggestions on creating a machine learning template, I have pulled together a project template that I use to experiment with modeling ML problems using Python and TensorFlow Decision Forests.

You will find the Python templates on the Analytics Project Templates page.

Binary Classification Analytics Project Template Using Python and TensorFlow Decision Forests Version 1

As I work on practicing and solving machine learning (ML) problems, I find myself repeating a set of steps and activities repeatedly.

Thanks to Dr. Jason Brownlee’s suggestions on creating a machine learning template, I have pulled together a project template that I use to experiment with modeling ML problems using Python and TensorFlow Decision Forests.

Version 1 of the Decision Forests template contains structures and features that are similar to the Scikit-Learn templates. I designed the Decision Forests template to address binary classification modeling exercises from beginning to end.

You will find the Python templates on the Analytics Project Templates page.

Regression Analytics Project Template Using Python and TensorFlow Decision Forests Version 1

As I work on practicing and solving machine learning (ML) problems, I find myself repeating a set of steps and activities repeatedly.

Thanks to Dr. Jason Brownlee’s suggestions on creating a machine learning template, I have pulled together a project template that I use to experiment with modeling ML problems using Python and TensorFlow Decision Forests.

Version 1 of the Decision Forests template contains structures and features that are similar to the Scikit-Learn templates. I designed the Decision Forests template to address regression modeling exercises from beginning to end.

You will find the Python templates on the Analytics Project Templates page.