Connect with us

Tech-Film

AI tool can recommend workouts based on fitness tracker data

The Kashmir Monitor

Published

🕒

on

IST

Scientists have developed an artificial intelligence tool that can make recommendations for workouts based on data from your fitness trackers. The tool, called FitRec, was trained on a dataset of more than 250,000 workout records for more than 1,000 runners, according to scientists from the University of California San Diego in the US. This allowed computer scientists to build a model that analysed past performance to predict speed and heart rate given specific future workout times and routes.

FitRec also is capable of identifying important features that affect workout performance, such as whether a route has hills and the user’s level of fitness. The tool can recommend alternate routes for runners who want to achieve a specific target heart rate. It also is capable of making short-term predictions, such as telling runners when to slow down to avoid exceeding their desired maximum heart rate.

The team was able to develop the tool partially because they were among the first to collect and model a massive fitness dataset for academic research. However, developing FitRec was no easy feat as the fitness dataset has a huge number of workout records, but only a small number of data points per individual.

 

“Personalisation is crucial in models of fitness data because individuals vary widely in many areas, including heart rate and ability to adapt to different exercises,” said Julian McAuley, a professor at UC San Diego.

“The main challenge in building this type of model is that the dynamics of heart rates as people exercise are incredibly complex, requiring sophisticated techniques to model,” researchers said.

To build an effective model, computer scientists needed a tool that uses all of the data to learn but at the same time can learn personalised dynamics from a small number of data points per user. Enter a deep learning architecture called long short-term memory networks (or LSTM), which the researchers adapted to capture the individual dynamic behaviours of each user in the dataset.

Researchers fed the networks a subset of a public dataset from endomondo.com, an app and website that function as a workout diary. After cleaning up the data, researchers wound up with more than 100,000 workout records to train the networks. They validated FitRec’s predictions by comparing them with existing workout records that were not part of the training dataset.

In the future, FitRec could be trained to include other data, such as the way users’ fitness levels evolve over time, to make its predictions. The tool could also be applied to more complex recommendation routes, for example safety-aware routes. However, in order for the tool to be used in commercial fitness apps, researchers would need to have access to more detailed fitness tracking data and deal with various data quality issues.


The Kashmir Monitor is the fastest growing newspaper as well as digitial platform covering news from all angles.

Advertisement
Loading...
Comments

Tech-Film

Infinix S4 Smartphone With Triple Rear Cameras, X Band 3 Fitness Band Launched

The Kashmir Monitor

Published

on

Infinix S4 has now been launched in India, after the launch of the Smart 3 Plus last month. The phone sports a triple rear camera setup, a rear fingerprint sensor, and a waterdrop-style notch. The Infinix S4 key features include the MediaTek Helio P22 SoC, a 6.21-inch large display, Android 9 Pie software, a 32-megapixel selfie sensor, and a 4,000mAh battery. The company also launched the X Band 3 fitness band alongside the smartphone, and it comes with real-time heart rate monitoring and up to 20-day battery life.

Infinix S4, X Band 3 price in India

Infinix S4 is priced in India at Rs. 8,999. The phone will be available on Flipkart from May 28 at 12pm (noon) IST. It will be available in Nebula Blue, Space Grey, and Twilight Purple colour options. The X Band 3, on the other hand, is priced in India at Rs. 1,599 and will be available on Flipkart from June 4.

 

Infinix S4 specifications

As for specifications, the dual-SIM Infinix S4 runs on Android Pie-based XOS 5.0. The phone features a 6.21-inch HD+ (720×1520 pixels) display with 19.5:9 aspect ratio, and 2.5D curved glass display protection. The phone is powered by the 2GHz MediaTek Helio P22 octa-core processor with 3GB RAM. Internal storage is at 32GB with the option to expand further using a dedicated microSD card (up to 256GB).

The triple rear camera setup at the back houses – a primary 13-megapixel snapper with f/1.8 aperture, another 8-megapixel 120 degrees ultra-wide camera with f/2.2 aperture, and a last 2-megapixel camera as well. The rear setup is accompanied by a Quad-LED flash. Up front, the Infinix S4 will have a 32-megapixel selfie camera with f/2.0 aperture and screen flash. Features include auto scene detection across eight modes including portrait, text, night, backlight HDR, blue sky, sports and others.

The phone packs a 4,000mAh battery, the dimensions measure at 156x75x7.9mm, and it weighs 155 grams. Connectivity options include Bluetooth v5, Micro-USB port, Wi-Fi 802.11 a/b/g/n, 3.5mm audio jack, and more. The phone supports Face Unlock and a rear fingerprint sensor as well. Sensors on board include a G-sensor, proximity sensor, light sensor, and compass.

Continue Reading

Tech-Film

Google Glass Enterprise Edition 2 Announced With Improved Camera and More

The Kashmir Monitor

Published

on

Google is bringing the second edition of its eye-wearable device — Google Glass Enterprise Edition 2, with improved camera, USB Type-C port and safety frames.

Google Glass is a small, lightweight wearable computer with a transparent display that brings information into your line of sight.

“Glass Enterprise Edition 2 helps businesses further improve the efficiency of their employees,” Jay Kothari, Project Lead, Glass at Google, wrote in a blog post on Monday.

 

To enable significant power-saving, support for computer vision and advanced Machine Learning (ML) capabilities, the Glass Enterprise Edition 2 is built on the Qualcomm Snapdragon XR1 platform that comes with a multi-core CPU.

The company says, Glass Enterprise Edition 2 is easier to develop for and deploy. In order to support scaled deployments, Google has also added support for Android Enterprise Mobile Device Management to the wearable.

The price of the second edition of Google Glass remain undisclosed as of now.

“Enterprise businesses interested in using Glass Enterprise Edition 2 can contact our sales team or our network of Glass Enterprise solution partners starting today.

We’re excited to see how our partners and customers will continue to use Glass to shape the future of work,” Kothari added.

In August 2017, Streye, a “Glass for Work” partner started selling the eye-wearable device Google Glass Enterprise Edition starting from $1,829 (roughly Rs. 1.3 lakhs).

Google sells the eye-wearable device with “Glass for Work” partners which are authorised to develop and deliver enterprise solutions for Glass customers.

The device has been known to be helping scientists study brain disease, during emergency and teach Morse code in four hours.

The first Google Glass was introduced with much fanfare in 2014. At $1,500, it promised a new, bold era for information.

People, however, realised the device was not yet ready to be part of their lives. There were safety and health concerns. The built-in camera raised privacy and piracy issues too.

Continue Reading

Tech-Film

Juhi Chawla supports her kids dreams

The Kashmir Monitor

Published

on

Actress Juhi Chawla says her son Arjun is good at mimicking accents and that he is hilarious, so sometimes she feels that he can probably try his hand at acting.

Juhi is currently living out of a suitcase, swinging between Mumbai, Kolkata and the UK where her teenaged children are put up in a boarding school.

In times when star kids have a ready launch-pad for their Bollywood career to take off, Juhi has shared about her children’s interests.

 

“My small monkey Arjun has clearly told us, ‘Mom don’t even think about it’. With Jahnavi, I’m not so sure. Arjun is quite funny and good with mimicking accents. He’s actually hilarious, so I feel sometimes that he could maybe try,” Juhi said in a statement.

“Jahnavi is an avid reader. If there is anything she likes in this world, and if you ask her what she wants as a gift, it will be a book. She said she wanted to be a writer.

“Then she went through a phase where she said ‘Okay I want to be a model’. Tomorrow she might say ‘I want to be an actress’. Then she might say she wants to drop all this and do sports. I don’t know, but I have learnt one thing that you have to let your children do what they want,” she added.

Continue Reading