Sold by: MphasisÂ
Deployed on AWS
This solution is a deep learning-based trainable algorithm which can classify data from multiple sensors and impute missing values.
Overview
This solution utilizes an Autoencoder model to learn and understand the data distribution which can fill in missing values once trained. Its objective is to classify the events based on the patterns and observations collected for data from multiple sensors. In production, the solution can handle missing information in sensor data and can still generate the correct classification for a given data point.
Highlights
- When dealing with multiple sensors as data sources, there might be interruptions to the data stream if one or more of them stop working at any point in time. A denoising autoencoder is modelled to learn the distribution of the data by training to recreate it identically so that it can account for these changes, ensuring the model can work sustainably despite any such issues with the devices. After training using data without missing values and with added synthetic masking noise, the developed model is robust to any such disappearances in the data.
- The trained model can be made use of for classification tasks with the incoming data which could be from a variety of sources. Even if the data is of different types arising from many different sensors, devices, machines or meters, this solution is designed to take this into consideration and give out accurate classification results. This finds its applications in various industries like IT infrastructure, production and manufacturing where key business decisions are based on the information collected from such sensors.
- InfraGraf is a patented Cognitive infrastructure automation platform that optimizes enterprise technology infrastructure investments. It diagnoses and predicts infrastructure failures. Need customized Machine Learning and Deep Learning solutions? Get in touch!
Details
Sold by
Delivery method
Latest version
Deployed on AWS
Unlock automation with AI agent solutions
Fast-track AI initiatives with agents, tools, and solutions from AWS Partners.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/host/hour |
|---|---|---|
ml.m5.large Inference (Batch) Recommended | Model inference on the ml.m5.large instance type, batch mode | $20.00 |
ml.m5.large Inference (Real-Time) Recommended | Model inference on the ml.m5.large instance type, real-time mode | $10.00 |
ml.m5.large Training Recommended | Algorithm training on the ml.m5.large instance type | $10.00 |
ml.m4.4xlarge Inference (Batch) | Model inference on the ml.m4.4xlarge instance type, batch mode | $20.00 |
ml.m5.4xlarge Inference (Batch) | Model inference on the ml.m5.4xlarge instance type, batch mode | $20.00 |
ml.m4.16xlarge Inference (Batch) | Model inference on the ml.m4.16xlarge instance type, batch mode | $20.00 |
ml.m5.2xlarge Inference (Batch) | Model inference on the ml.m5.2xlarge instance type, batch mode | $20.00 |
ml.p3.16xlarge Inference (Batch) | Model inference on the ml.p3.16xlarge instance type, batch mode | $20.00 |
ml.m4.2xlarge Inference (Batch) | Model inference on the ml.m4.2xlarge instance type, batch mode | $20.00 |
ml.c5.2xlarge Inference (Batch) | Model inference on the ml.c5.2xlarge instance type, batch mode | $20.00 |
Vendor refund policy
Currently we do not support refunds, but you can cancel your subscription to the service at any time.
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA)Â .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
Amazon SageMaker algorithm
An Amazon SageMaker algorithm is a machine learning model that requires your training data to make predictions. Use the included training algorithm to generate your unique model artifact. Then deploy the model on Amazon SageMaker for real-time inference or batch processing. Amazon SageMaker is a fully managed platform for building, training, and deploying machine learning models at scale.
Deploy the model on Amazon SageMaker AI using the following options:
Version release notes
bug fixes
Additional details
Inputs
- Summary
- A training data file with numerical columns and limited missing values should be provided. Along with this, a text file (.txt) containing the list of sensors is required with the sensor names matching the column names in the training and testing files.
- Include data with minimal null/missing values in the training file to ensure that the maximum amount of patterns can be learnt on this clean data. Test data can have a greater proportion of missing values.
- Input MIME type
- text/csv, text/plain, application/zip
https://github.com/Mphasis-ML-Marketplace/IoT-Sensors-Data-Imputer-and-Classifier/blob/main/training/train.zip
https://github.com/Mphasis-ML-Marketplace/IoT-Sensors-Data-Imputer-and-Classifier/blob/main/training/train.zip
Input data descriptions
The following table describes supported input data fields for real-time inference and batch transform.
Field name | Description | Constraints | Required |
|---|---|---|---|
train | • The input data should only be in numerical format. There should not be any columns of string data type.
• For the initial training data, there should be minimal null/missing values for optimal training performance on maximum clean data from which the model can learn necessary patterns
• Null values should not be present as empty strings (" ") as these will not be detected during the processing for this solution
• The expected target values should be present in a column named 'label' | Type: Continuous | Yes |
sensor_list | • Along with the training file, a text file named 'sensor_list.txt' needs to be uploaded which contains a list of sensors in a list format, eg. ['sensor_1', 'sensor_2', 'sensor_3'].
• The names of the sensors in this list should also be present in the column names to indicate which sensor a particular column belongs to. | Type: FreeText | Yes |
Resources
Vendor resources
Support
Vendor support
For any assistance reach out to us at:
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
In this consulting offer, TensorIoT will provide your team with expert guidance to accelerate architecting and implementing an IoT platform for all your “things”
IoT Platform provides starter kit for building IoT platform and integration with edge node. Starter kit provides inference layer built in cloud and on edge, and comes with anomaly detection application on top of it.
IoT Bridge is an AMI product that rapidly connects OT data from Industrial Operations to Snowflake with minimal configuration and zero coding.
A Public Key Infrastructure (PKI) for the Internet of Things (IoT) designed to run on both commodity hardware and cloud infrastructure.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.