Giving users what they want, when they want it

Enhancing quality of experience for content-rich sites

Parvez Ahammad
Waiter image via Shutterstock

When it comes to satisfying users of image rich web applications, the speed and quality of every single image matters. Parvez Ahammad looks at the ways machine-learning algorithms and cloud application delivery solutions can improve the quality of experience.

In the age of “IWWIWWIWI” (I want what I want when I want it), smartphones are increasingly becoming the go-to device for accessing websites, videos and applications, in addition to traditional desktop and laptop devices. According to a recent eMarketer study, the number of smartphone users worldwide will surpass 2 billion by next year.

Depending on the generation of devices, users will also experience varying speeds and feeds in web application delivery of photos and videos. Simultaneously, applications continue to offer increasingly enhanced, rich experiences with HD video and complex images. As a result, websites and applications are becoming fat and resulting in slow download speeds and suboptimal experiences.

For the end user, the quality of experience (QoE) is defined by the speed and quality of multimedia content delivered to devices. When it comes to image-rich web applications, every single image matters – the speed and quality of a video or image received on users’ devices determines their level and time of engagement with the application. Offering individually tuned settings for optimal content delivery ensures the user’s quality of experience is not compromised with the scaling up to millions of videos and images across the entire web delivery pipeline.

Intuitive, context-aware media delivery

The longer users wait for images to fully download in an application, the more likely they are to “multi-browse” and move away from the current application, being distracted by another. QoE for video streaming is measured by two main factors: the bitrate, or the bandwidth being used to deliver the content; and the rebuffer rate, or how often video playback is interrupted to reload more content. A video pausing to buffer due to bitrate interrupts the user experience and is also cause for tuning to another video or application.

Rather than waiting for an entire video or image to be completely downloaded and queued in the delivery pipeline, modern cloud application delivery solutions are continually exploring how to optimize the delivery approach to serve users with the essential content first. For rich video content, open caching provides a solution to delivering rich video content, even during high network congestion. By identifying data frequently sent in network traffic and locally caching, applications are able to deliver content from the network edge, rather than calling back to the provider. Proprietary data can also be used to measure and predict user behaviour to optimize and customize the viewing experience, as Netflix has explored.

SEE ALSO: Netflix proudly displays its developers’ ‘Dirty Laundry’

For images, machine-learning algorithms can be designed to determine which parts of an image need to be delivered first, based on the user’s web delivery service, so that the importance of every part of an image can be determined in an automated fashion. Delivering the most essential parts of an image first, rather than waiting for an entire image to load, provides engaging user experiences and eliminates delay and lag time that can result in users navigating away from an application or website.

At Instart Logic, we’ve taken precisely such an approach to optimizing the quality and speed of application delivery. Our SmartVision technology determines the optimal threshold on the server-side, sending the part of the image file that delivers the best results for the user compared to the original quality of the application first, while filling in the rest of the image in the background. This approach dramatically improves user engagement without sacrificing the visual experience.

Using machine learning algorithms to automatically determine the most essential components of media delivery is one of the latest developments in application delivery, and can dramatically improve the delivery pipeline and QoE for users, increasing overall customer engagement.

Parvez Ahammad
Parvez Ahammad is the Senior Staff Data Scientist at Instart Logic and has an extensive background in computer vision, machine learning and signal processing with applications to camera sensor networks, web application delivery, bioinformatics and neuroscience. He’s also the creator of novel algorithmic technologies such as smartVision at Instart Logic, OpSIN and Salient Watershed at HHMI-Janelia, to name a few.

Inline Feedbacks
View all comments