Home / Software & Service News / Machine learning could put an end to your streaming woes

Machine learning could put an end to your streaming woes

Whether you’re watching a YouTube video, streaming media, or playing games, the telltale sync signal associated with buffering can unload some severe existential dread.

Nothing takes you out of the experience and entertainment faster than a buffer circle continuously animated, seemingly to infinity. If you’ve fallen victim to buffering in the middle of an important moment in your favorite show or game, you’re not alone. More than 500 million hours of video are streamed per day which means the audiences of streaming services likely encounter a metric ton of buffering.

Buffer haters alike will be rejoiced to learn MIT researchers may have come up with a solution, that will hopefully end slow load times once and for all. They have developed a unique artificial intelligence system that can optimize video streaming, making the process reliable and devoid of animated icons.

To understand how it works, first, you must understand what buffering is and why it happens.

The tech behind the annoyance

Internet traffic or data is sent in units called packets, also referred to as chunks.

When it comes to video, streaming or the loading of said data happens in segments.

Over time, fragments come in as sequential portions of a whole file, which are then stitched together — that’s why you can often start watching a video with little to no interruptions but run into them soon after. At least to start, the content is played back to you at the same time it’s being downloaded.

During the process, if your connection drops or lessens, those chunks may stop flowing in, resulting in reduced performance for the entire file or video.

The idea is to continuously download these pieces and stitch the footage together in the background, as you watch. When the process is interrupted for whatever reason, you encounter buffering and the dreaded spinning circle.

This is exacerbated depending on the strength of a wireless signal, internet connection or nearby traffic. Watching a video on a public network that’s crowded, for instance, could result in significant buffering and performance issues.

Services like YouTube, Vimeo, and even social media platforms, rely on algorithms called Adaptive Bitrate, or ABR for short. They initially measure the connection speeds, total bandwidth availability, and the resolution of the content to deliver a constant flow or stream of media.

Higher resolutions, obviously, require more resources, so sometimes you can offset buffering by lowering the quality or resolution of the content — that’s why Netflix sometimes seems blurrier or worse than usual. The service or app has toned down the resolution of the content to match a higher connection demand.

So, how can this be solved through AI?

MIT’s solution

The team at the MIT Computer Science and Artificial Intelligence Lab (CSAIL) rely on an automated intelligence system to swap between the appropriate algorithms. The neural network — digital, of course — can analyze and decide when a connection requires one particular algorithm over another.

The team trained the AI system through a reward and penalty based system.

Over the course of a month, they played streams of video content and left the system to do its thing. Failures resulted in a penalty, while successes were rewarded.

This eventually allowed the AI system to work out which algorithms work best for various scenarios, and when it’s time to swap between them. They give it a virtual education.

Even more promising is the fact that the system can be adjusted and tweaked, depending on what a service, connection or media type calls for.

Content providers — such as Netflix — could opt to always select quality over performance or vice versa. The system would take this into account and make the right choices, through automation and regular monitoring.

The professor of the crew, Mohammad Alizadeh, says it can be completely customized. This would allow users to personalize “their own streaming experience based on whether they want to prioritize rebuffering versus resolution.”

This is great for haters of buffering sure, but the implications for other areas of media streaming are incredible.

Imagine being able to stream a high-resolution and intense gaming experience over VR using this system. Without it, it’d be nearly impossible because the continually shifting resolutions and qualities would cause some severe nausea and take users out of the experience.

This is pretty cool news, indeed.

Of course, the part about no more buffering is also exciting. Finally, streamers can say goodbye to that dreaded spinning circle, once and for all.

Kayla Matthews is a technology writer interested in AI, chatbots, and tech news. She writes for VentureBeat, MakeUseOf, The Week, and TechnoBuffalo.

Click Here For Original Source Of The Article

About Ms. A. C. Kennedy

Ms. A. C. Kennedy
My name is Ms A C Kennedy and I am a Health practitioner and Consultant by day and a serial blogger by night. I luv family, life and learning new things. I especially luv learning how to improve my business. I also luv helping and sharing my information with others. Don't forget to ask me anything!

Check Also

Existing EV batteries could be recharged five times faster

Lithium-ion batteries have massively improved in the last half-decade, but there are still issues. The biggest, especially for EVs, is that charging takes too long to make them as useful as regular cars for highway driving. Researchers from the University of Warwick (WMG) have discovered that we may not need to be so patient, though. They developed a new type of sensor that measures internal battery temperatures and discovered that we can probably recharge them up to five times quicker without overheating problems.

Overcharging a lithium-ion battery anode can lead to lithium buildup, which can break through a battery's separator, create a short-circuit and cause catastrophic failure. That can cause the electrolyte to emit gases and literally blow up the battery, so manufacturers impose strict charging power limits to prevent it.

Those limits are based on hard-to-measure internal temperatures, however, which is where the WMG probe comes in. It's a fiber optic sensor, protected by a chemical layer that can be directly inserted into a lithium-ion cell to give highly precise thermal measurements without affecting its performance.

The team tested the sensor on standard 18650 li-ion cells, used in Tesla's Model S and X, among other EVs. They discovered that they can be charged five times faster than previously thought without damage. Such speeds would reduce battery life, but if used judiciously, the impact would be minimized, said lead researcher Dr. Tazdin Amietszajew.

Faster charging as always comes at the expense of overall battery life but many consumers would welcome the ability to charge a vehicle battery quickly when short journey times are required and then to switch to standard charge periods at other times.

There's still some work to do. While the research showed the li-ion cells can support higher temperatures, EVs and charging systems would have to have "precisely tuned profiles/limits" to prevent problems. It's also not clear how battery makers would install the sensors in the cells.

Nevertheless, it shows a lot of promise for much faster charging speeds in the near future. Even if battery capacities stayed the same, charging in 5 minutes instead of 25 could flip a lot of drivers over to the green side.

Via: Clean Technica

Source: University of Warwick