Machine Learning

Predictive maintenance via Knime - Exploratory Data Analysis (Part 2)

In the previous part of the blog, we saw how to read data from text files and preprocess it. Do have a look at the previous block before processing further. Now in this part, we will see the EDA for Anomaly Detection for predictive maintenance.

Exploratory data Analysis(EDA) Exploratory data analysis is the crucial process of doing first investigations on data in order to find patterns, identify anomalies, test hypotheses, and validate assumptions using summary statistics and graphical representations. Data scientists use exploratory data analysis (EDA), which frequently makes use of data visualization techniques, to examine and analyze data sets and summarise their key properties. It makes it simpler for data scientists to find patterns, identify anomalies, test hypotheses, or verify assumptions by determining how to modify data sources to achieve the answers they need.

6d0758b2-b976-444f-878b-5c23610ab154.avif Predictive maintenance

Predictive Maintenance and Anomaly Detection (Data reading and preprocessing via Knime Part-1)

4.avif KNIME is now the most widely used open-source tool for visual programming, which uses drag and drop to create complete Machine Learning Models without writing any code. It is one of the tools that is becoming more and more well-known among statisticians, data scientists, and domain experts from different industries (manufacturing, pharmacy, farming, oil & gas) who receive data via IoT for the delivery of quick solutions without the need for Python or R programmers.


Smart home appliances like thermostats and security systems frequently spring to mind when people in general think about the Internet of Things. However, the Industrial Internet of Things has emerged as a result of the IoT ecosystem’s expansion far beyond the sphere of consumer use.

The industrial IoT, or IIoT for short, links equipment and devices in industries where maintaining equipment functionality are essential for productivity and safety. IIoT technology is used by businesses to automate formerly manual operations and manage their assets remotely, finding new cost- and time-saving opportunities along the way. more

Automating Knime Workflows to Send Mails of Reports and Predictions

17.avif When it comes to Visual Programming to implement end to end Machine Learning Models, without writing any code and following the drag and drop approach, the most popular open source tool these days is KNIME.

It is one of the tools getting famous amongst the statisticians and Data Scientists for Quick Prototyping.

Since Data Science gets used in many sectors from Humanities, Economics, Life Sciences , Pharma, Healthcare, Finance etc, I feel fortunate to work with different companies and different customers as a freelancer consultant or independent contractor for Machine Learning Projects, getting to learn a lot about the sector itself along with implementation via ML.

I hold a Post Graduate degree in Statistics, followed after Computer Science , and am a hardcore Statistics’ lover, I feel teaching is learning twice and hence I work as a Bootcamp Instructor for Analysts working in Corporates who want to Upgrade themselves to Knime .


Knime Deep Learning Installation

1.avif When executing the Keras Learner Network node, which is depicted below, if you see the dependency error. Error in Keras Network Learner Node. 2.avif Tensorflow dependency error Let’s see the solution regarding this. MORE

Implementing Random Erasing upon PostDam Dataset

3.avif Random Erasing is a new data augmentation method for training the convolutional neural network (CNN). Contents: Introduction to Random Erasing Steps to achieve Random Erasing

In training, Random Erasing randomly selects a rectangle region in an image and erases its pixels with random values. In this process, training images with various levels of occlusion are generated, which reduces the risk of over-fitting and makes the model robust to occlusion. Random Erasing is parameter learning free, easy to implement, and can be integrated with most of the CNN-based recognition models.


Using LiveGrep for Fast Searching of text across Teraby

4.avif Working with massive amounts of data every day now entails a lot of searching, sorting, and analyzing data. As a result, there are numerous techniques for automating such tasks, but they are inefficient when dealing with massive amounts of data ( BIG DATA you can say). So we used another method to solve this problem - LIVEGREP 5.avif

Using Auto-encoder for Fraud detection implemented in Knime

8.avif Auto-encoders are an unsupervised learning technique using neural networks to learn representations.

Specifically, we will design a neural network architecture with a bottleneck that forces a compressed knowledge representation of the original input. This compression and subsequent reconstruction would be complicated if the input features were completely independent of one another. However, if some structure exists in the data (ie. correlations between input features), this structure can be learned and consequently leveraged when forcing the input through the network’s bottleneck. more

Implementing Neural Networks in Knime Workflows

9.avif On the well-known iris dataset, we will perform the neural network operation here without writing a single line of Python code. Sounds great right? For this, we will use the Knime Analytics platform. Neural Networks

The KNIME Analytics Platform is open-source data science software. KNIME, which is intuitive, open, and constantly integrating new developments, makes data science workflows and reusable components accessible to everyone. more