My part of the event has been focused on two presentations (they will be available to download any day soon), which I had already at SIOUG 2023 in June, however I've added some new facts and new demos since then:
My view on Oracle’s position in Gartner Magic Quadrants for Analytics and Business Intelligence Platforms
Gartner has published its Magic Quadrants for Analytics and Business Intelligence Platforms (Gartner, 2023) report for 2023, on April 5th. As usually, it presents how various analytics and BI vendors position regarding the completeness of their vision and ability to execute. It is considered as “the go-to resource” when evaluating and comparing these technologies.
In their report, Gartner says that the key Oracle’s strengths are in (Gartner, 2023):
- Enterprise cloud data and analytics,
- Augmented capabilities throughout and
- Comprehensive data management.
So what exactly is meant by that? We will dig a bit deeper to discuss Oracle’s position and explain why Oracle is placed where it is placed - in Visionaries quadrant. Of course, everything in this presentation will be my personal view and experience.
OCI Vision and Oracle Analytics: Just like a Box of Chocolates
OCI Vision is a self-service AI Service, which applies computer vision to analyze image-based content. It allows developers easily integrate pre-trained models into their applications with APIs or custom training models to meet their specific use cases.
In our example, I will explore how to use OCI Vision service to create a custom-built model to detect pneumonia infected lungs on a fresh dataset of X-ray images. In this example, I am using rather large dataset of X-ray images found on Kaggle.com. Oracle Analytics is then used as a front-end tool to use the model to classify new images for pneumonia.
What to expect to see in this presentation?
In the first place, we will demonstrate and explore the whole process from “plain” X-ray image to identifying pneumonia infected lungs using OCI services:
- Gathering and storing images to OCI Object Storage.
- Labeling images depending on whether they represent normal or pneumonia infected lungs using Data Labeling service.
- Building and training an image classification model using OCI Vision.
- Registering an OCI Vision model with Oracle Analytics.
- Applying a model in Oracle Analytics’ Data Flows.
- Visualizing everything at the end by using Oracle Analytics Data Visualization.
Why is this relevant?
Firstly, it shows the flexibility and usability of the OCI ecosystem, specifically Data Lakehouse services. Secondly, the whole process (with exception of data labeling which is done programmatically) is codeless, with not too many steps in the process, and the process itself is really very simple to use. This implies possibilities which can be explored by much wider range of users comparing to the situation today, where all depends on skilled developers and data scientists. And the bottom line, this can have very positive impact on business.