Predictive Healthcare Analytics Platform

Predictive Healthcare Analytics Platform

Predictive Healthcare Analytics Platform and solutions is a part of advanced analytics that is used to predict future events. Predictive analytics practices many ways from data mining, statistics, modeling, machine learning, and artificial intelligence to examine current data to make forecasts about the future.

• Good healthcare boosts the economy of the nation. Precision medicine along with Big Data is leveraging in building better patient profiles as well as predictive models to diagnose and treat diseases.
• TeleMedicine and AI in healthcare is indeed a miracle remotely performing treatment of patients using Pattern Recognition, optimizing duty allocation, monitoring live data.
• Real-Time Big Data for Infection Control to predict and prevent infections through networks creating safer environments.
• Patient Data Analytics for a patient dealing and preventing readmissions and better pharmaceutical supply chain management and delivery.

Challenges for Building Predictive Analytics Platform

• Interface for the patient to search nearby doctors by particular Healthcare categories.
• Enable patient visibility to see doctor’s availability online and communicate via text chat, audio or video call.
• Visible allotment number to the patient in the waiting queue.
• Communicate with the doctor as well as test or medicine suggestions to the patient.
• Interface for the patient to contact nearby labs to collect a sample and upload test reports on the server followed by the push notification when the report is ready.
• Share report with a doctor followed by a prescription to the patient.
• Search for nearby medical stores and place an order for the prescription got from the doctor.

Solution Offerings for Real-Time Monitoring

Develop a Healthcare platform to fully automate using the latest technologies and distributed Agile development methods.

Real-Time Monitoring of User’s Events

Apache Kafka & Spark Streaming to achieve high concurrency, set up low latency messaging platform Apache Kafka to receive Real-Time user requests from REST APIs (acting as Kafka producer).

Apache Spark Streaming (processing and Computing engine) Spark-Cassandra connector, stored 1 million events per second in Cassandra. Built Analytics Data Pipeline using Kafka and Spark Streaming to capture user’s clicks, cookies, and other data to know users better.

Microservices using Spring Cloud, NetFlix OSS, Consul, Docker, and Kubernetes

Develop REST API’s using Microservices architecture with Spring Cloud and Spring Boot Framework using Java language. Moreover, use Async support of the Spring framework to create Async controllers that make REST API easily scalable.

Spring to deploy REST and use Kubernetes for secure containers and their management. For API gateway, use NetFlix Eureka Server which acts as a proxy for REST API and the lot of Microservices, Consul as DNS enables auto-discovery of Microservices.

Source: XenonStack/Use-Cases

Solutions for Building IoT based Smart Meters

Introduction to Smart Meters

In the Energy Upgrade solution, IoT is playing a significant role. The use of smart meters is increasing, which enables the intelligent and efficient use of energy at homes and businesses. Many grid power supply companies, small and large industries, private residential sector are also implementing the smart solution for energy efficiency and sustainability.

Business Challenge for Building the Analytics Platform

We need to build a complete analytical solution that can be used for the energy-saving recommendation based on the usages for the large buildings and industries. Also, the challenges were to filter the results found on floors, buildings, heat, water, electric. Along with the dashboard, alerting for usage also should be used based on usage.

Solution Approach for Building IoT based Smart Meters

Complete Smart meter based analytical dashboards which include -

• Recommendation for energy saving
• Predictive results for Energy Bills
• Real-time alerting on some defined alerting rules
• Analytical results on the base of historical data

Smart Manufacturing and IoT Solutions

Introduction to Smart Manufacturing

Smart manufacturing is a technology-driven approach that uses Internet-connected machinery to observe the production process. The purpose of SM is to recognize the possibilities for automating processes and use data analytics to enhance manufacturing execution.

• Machines have threshold values for the different parameters like Temperature, Oil pressure, and Amperage which should not be crossed.
• Implementation of the Internet of Things (IoT) enables proactive maintenance breaks on the machines to enable manufacturing for smart manufacturing. The collection of data in Real-Time is an excellent solution.
• Smart Manufacturing industries reduce the risks

Challenge for Building the IoT Platform

Scalable Solution for smart manufacturing to manage all the machines at a single central point and handle sizeable Real-Time streaming data from sensors that can provide the alerts and trigger to turn off the motor in very minimum time.

Solution Offered Real-Time Data and IoT Platform

Installation of the sensor to collect each value (Temperature, Oil pressure, Amperage) in Real-Time using Google Cloud Platform.

Google Cloud IoT Core to ingest data from all sensors attached to different machines. The data collected from the sensors contain the machine identification number to differentiate the received data.

Google Cloud IoT Core sends the collected data to Google Cloud Pub/Sub. This data stream routes at multiple locations. Store the raw data into BigQuery and also to Google Cloud Function.

Detect whether the collected data values are higher than the threshold values. Implement Google Cloud Function and Google Pub/Sub as the trigger. Google Cloud function is an event-driven serverless compute platform to deploy Function As a Service which is auto-scalable, highly available and fault-tolerant.

Cloud function triggers the configuration changes to the Google Cloud IoT Core if data values are higher than the threshold value, for another sensor which controls the motor of the machine.

Google Cloud IoT Core sends the trigger to the device to turn off the machine and have a maintenance break.

Technology Stack

• Google Pub/Sub
• Google IoT Core
• Google Cloud Function
• Google Cloud DataFlow

Source: XenonStack/Use-Cases

What is Fast Data?

What is Streaming and Real-Time Data

Stream & Real Time Processing Frameworks

Why Real-Time Streaming

Why we Need Real-Time  Streaming?

Use Of Reactive Programming & Functional Programming

Streaming Architecture Matters

• Lambda Architecture:

  This architecture was introduced by Nathan Marz in which we have three layers to provide real-time streaming and compensate any data error occurs if any. The three layers are Batch Layer, Speed layer, and Serving Layer.
  

• What type of data it is

• Format of content of data required

• Whether data is transactional data, historical data or master data

• The Speed or Frequency at which data made to be available

• How to process the data i.e. whether in real time or in batch mode

5 V’s to Define BigData

Additional 5V’s to Define BigData

Data Ingestion and Data Transformation

• Data type: Type of data

• Transactional

• Historical

• Master Data and others

• Data Content Format: Format of data

• Structured (RDBMS)

• Unstructured (audio, video, and images)

• Semi-Structured

• Data Sizes: Data size like Small, Medium, Large and Extra Large which means we can receive data having sizes in Bytes, KBs, MBs or even in GBs.

• Data Throughput and Latency: How much data is expected and at what frequency does it arrive. Data throughput and latency depend on data sources:

• On demand, as with Social Media Data

• Continuous feed, Real-Time (Weather Data, Transactional Data)

• Time series (Time-Based Data)

• Processing Methodology: The type of technique to be applied for processing data (e.g. Predictive Analytics, Ad-Hoc Query and Reporting).

• Data Sources: Data generated Sources

• The Web and Social Media

• Machine-Generated

• Human-Generated etc

• Data Consumers: A list of all possible consumers of the processed data:

• Business processes

• Business users

• Enterprise applications

• Individual people in various business roles

• Part of the process flows

• Other data repositories or enterprise applications

Major Industries Impacted with BigData

What is Data Integration?

• Discovering the Data

• Profiling the Data

• Understanding the Data

• Improving the Data

• Transforming the Data

• Ingest Data from different sources where data resides in multiple formats.

• Transform Data means converting data into a single format so that one can easily be able to manage his problem with that unified data records. Data Pipeline is the main component used for Integration or Transformation.

• MetaData Management: Centralized Data Collection.

• Store Transform Data so that analyst can exactly get when the business needs it, whether it is in batch or real time.



Why Data Integration is required

• Make Data Records Centralized: As data is stored in different formats like in Tabular, Graphical, Hierarchical, Structured, Unstructured form. For making the business decision, a user has to go through all these formats before reaching a conclusion. That’s why a single image is the combination of different format helpful in better decision making.

• Format Selecting Freedom: Every user has different way or style to solve a problem. User are flexible to use data in whatever system and in whatever format they feel better.

• Reduce Data Complexity: When data resides in different formats, so by increasing data size, complexity also increases that degrade decision making capability and one will consume much more time in understanding how one should proceed with data.

• Prioritize the Data: When one have a single image of all the data records, then prioritizing the data what's very much useful and what's not required for business can easily find out.

• Better Understanding of Information: A single image of data helps non-technical user also to understand how effectively one can utilize data records. While solving any problem one can win the game only if a non-technical person is able to understand what he is saying.

• Keeping Information Up to Date: As data keeps on increasing on daily basis. So many new things come that become necessary to add on with existing data, so Data Integration makes easy to keep the information up to date.