At KAISPE, we pride ourselves on our innovation, expertise, and our continued commitment to ensuring delivery of the highest quality products to our customers. As a Microsoft Certified Partner, we provide solutions backed by industry best practices and standards. We are Microsoft Co-Sell partner and have strong presence on Microsoft marketplaces with our remarkable apps and services.

To learn more, visit https://testing.kaispe.com or call (315) 791-4472. Connect with us on Twitter, LinkedIn, and Facebook.

The post KAISPE Azure Machine Learning PoC Offering is now available on Microsoft Marketplace appeared first on KAISPE.

We provide Predictive Maintenance through Microsoft Azure Machine Learning in just a few easy steps.

• Trained Models according to the need of the different types of data using Azure Machine Learning.
• Real-Time Data from Machines are going to the Azure IoT Hub.
• Filter the Real-Time Data according to the user requirement using Stream Analytics.
• We Consumed Azure Machine Learning Trained Model according to the user environment.
• Finally, we have a comparison analysis between Real-Time Data and Our Trained Model Data and gives you the future operational Performance using KAISPE IoT Web Portal.

Now, we are going to demonstrate how KAISPE helps Air Compressor Industry to achieve Predictive Maintenance Feature.

We trained our model using Different Air Compressors Datasets.

Now we consumed Trained Model Web Service API for the Real-Time Prediction.

Now there are different types of Air Compressors that send different types of data to the Azure IoT Hub.

We have a target feature which is Vibration Analysis so we will extract the label features that’s are:

Pressure, Angular Speed and Piston Speed in our Azure Machine Learning Model.

We filtered Real-Time data according to the above features using Azure Stream Analytics.

We have a comparison analysis between Real-Time Data and our Trained Model API to make the Prediction for the Air Compressor Vibration Analysis and stored the relevant device information and Prediction Values in the Azure Storage and shows in the KAISPE IoT Web Portal and gives advance notice of the possibility of the failure in Real-Time.

Azure Table Storage that stores Comparison Analyses between Real-Time and Trained Model.

KAISPE IoT Web Portal that helps you to Visualize Real-Time Prediction for the Possibility of the Future Failure.

I hope you liked this blog post. Keep in touch with us at info@kaispe.com

The post Predictive Maintenance Feature in KAISPE IoT Web Portal appeared first on KAISPE.

Today we will be evaluating the difference between of Azure Machine Learning Services and Azure Machine Learning Studio that will help us to choose the best option to develop our Machine Learning solution.

First lets start with Azure Machine Learning Studio which offers a robust set of tools designed to develop, deploy and manage machine learning projects.

Azure Machine Learning Studio

• Azure Machine Learning Studio is a collaborative, drag-and-drop environment where you have No Coding is required and It’s a tool where you can use to build, test, and deploy predictive analytics solutions on your data.
• Uses pre-build and pre-configured machine learning algorithm and data handling modules as well as proprietary compute platform.
• Azure Machine Learning Studio does not have much control on training scalability.
• It has standard experiments but you can get quick results in lesser time.

Second, we have is Azure Machine Learning Services which you can find in two flavors, a Python SDK and a drag-and-drop style Visual Interface(preview).

Azure Machine Learning Service

• Azure Machine Learning Service provides both SDKs (Code based) and visual interface to quickly prepare data, train and deploy machine learning models.
• We can have the same drag-and drop experience to Machine Learning Studio, however, unlike proprietary compute platform of studio, the Visual Interface uses your own compute resources.
• It integrates with python environment, frameworks and tools and it does not restrict you what you need to use.
• Azure Machine Learning Service have full control on training scalability with custom compute targets.

Now, as we have got the idea about both Azure Machine Learning Studio and Azure Machine Learning Service, we can assume that from being a developer Azure Machine Learning Service is more flexible compare to Azure Machine Learning Studio.

I hope this short post has helped you get a better idea about Microsoft Azure Machine Learning offering products. If you have any questions, please feel free to contact me muhammad.ahmad@kaispe.com

The post Comparison between Microsoft Azure Machine Learning Service and ML Studio appeared first on KAISPE.

We will use Anomaly Detection algorithm for our solution that comes with Azure Machine Learning and is useful for detecting different types of anomalous patterns in time series data.

So, in the first step we will upload the dataset on Azure Machine Learning Studio in the CSV file format. In order to do that, open Azure Machine Learning home page and Click +NEW at the bottom of the window -> Select DATASET -> Select FROM LOCAL FILE.

In the Upload a new dataset dialog, click Browse, and find the Agricultural_Data updated.csv file you created.

Now in the next step we will create an experiment in Machine Learning Studio that uses the dataset you uploaded. So, click +NEW at the bottom of the window and Select EXPERIMENT, and then select “Blank Experiment”.

Select the default experiment name at the top and rename it to IoT Measurements and in the module palette to the left of the experiment page, expand Saved Datasets. Find the dataset you created under My Datasets and drag it onto the main page.

Now let’s prepare the data by using Apply SQL Transformation which was used to separate out the timestamps by date and time using SQLite.

After Apply SQL Transformation, we will search and drag Select Columns in Dataset, and in the Properties pane to the right page, click Launch column selector and select the following columns:

Next, In the module palette, Search  and drag Edit Metadata onto the main page and connect the Select Columns in dataset to the Edit Metadata. Select Edit Metadata, and in the Properties pane to the right page, click Launch column selector and select the following column:

Now, back in the Properties pane, we will look for the New column names parameter. In this field, enter processDate in new column names and select DateTime as our data type.

So, now in the next step we will apply separate Time Series Anomaly Detection for Temperature, Humidity, Soil Moisture and pH Level, which we mean to identify the increase or decrease of each of these variables and to evaluate against various parameters of the anomaly detection module.

After we applied separate Time Series Anomaly Detection for Temperature, Humidity, Soil Moisture and pH Level, you can get the result using R code which you can find and drag the Execute R Script module onto the experiment page and connect the output port of the time series anomaly detection to the first input port of the Execute R Script module and at the same time connect the output port of the Apply SQL Transformation to the second input port of the Execute R Script module.

Note: The purpose of creating the RScripts is for visualization of the influence and behavior of the variables.

Now we can see the visualization and the behavior of all variables:

For Temperature:

For Humidity:

For Soil Moisture:

For pH Level:

I hope you found this blog post helpful. If you have any questions, please feel free to contact me muhammad.ahmad@kaispe.com

The post Anomaly Detection for IoT Measurements using Azure Machine Learning appeared first on KAISPE.