Toggle light / dark theme

Can smartphones apps be used to monitor a user’s mental health? This is what a recently submitted study scheduled to be presented at the 2024 ACM CHI Conference on Human Factors in Computing Systems hopes to address as a collaborative team of researchers from Dartmouth College have developed a smartphone app known as MoodCapture capable of evaluating signs of depression from a user with the front-facing camera. This study holds the potential to help scientists, medical professionals, and patients better understand how to identify signs of depression so proper evaluation and treatment can be made.

For the study, the researchers enlisted 177 participants for a 90-day trial designed to use their front-facing camera to capture facial images throughout their daily lives and while the participants answered a survey question with, “I have felt, down, depressed, or hopeless.” All participants consented to the images being taken at random times, not only when they used the camera to unlock their phone. During the study period, the researchers obtained more than 125,000 images and even accounted for the surrounding environment in their final analysis. In the end, the researchers found that MoodCapture exhibited 75 percent accuracy when attempting to identify early signs of depression.

“This is the first time that natural ‘in-the-wild’ images have been used to predict depression,” said Dr. Andrew Campbell, who is a professor in the Computer Science Department at Dartmouth and a co-author on the study. “There’s been a movement for digital mental-health technology to ultimately come up with a tool that can predict mood in people diagnosed with major depression in a reliable and non-intrusive way.”

SpaceX plans to place its first direct-to-cellular phone Starlink constellation in orbit by the end of August.

The company aims to initially provide text messaging services over its low-Earth-orbit satellites to T-Mobile customers using unmodified cellphones operating with standard LTE/4G protocols. Service is expected to start this year, according to SpaceX’s website.

The rocket and satellite manufacturer lofted its first 21 direct-to-cellphone Starlink satellites on Jan. 2. Its plan to have the constellation orbiting Earth by the end of August was announced by Jon Edwards, SpaceX vice president of Falcon Launch Vehicles, on Feb. 26 on the social media website X.

Real-Time Artist and Unreal Engine specialist Ayoub Attache, known to many for his jaw-dropping experiments with Epic Games’ game creation tool, has once again blurred the line between the digital realm and real life with a brand-new project.

This time, he has developed an incredible setup for simulating earthquakes in Unreal Engine 5 by simply shaking a smartphone attached to a cutting board surrounded by RC car shock absorbers, which mimic the ground’s movement. The shaking data, including acceleration and gyroscope readings, is then sent via a UDP server straight to Unreal Engine, where it simulates an earthquake affecting a construction site.

Google’s Gemini implementation for AI image generation is facing a lot of criticism. But that isn’t stopping the search and mobile giant from riding the AI wave and rolling it out to more of its services. Today, Google announced a new set of features for phones, cars, and wearables — using Gemini to craft messages, AI-generated captions for images, summarizing texts through AI for Android Auto, along with access to passes on Wear OS.

The new features were unveiled at Mobile World Congress (MWC) in Barcelona — an event where Google, as the company behind Android, has figured strongly for years.

The company said that starting this week, Google Messages will get a feature that lets you access Gemini in the app. The feature is currently in beta and only supports English.

Security experts at the University of Florida, in collaboration with CertiK, a security audit company, have uncovered a potential cybersecurity threat that could result in smartphones catching fire when placed on wireless chargers.

According to TechXplore, this discovery highlights vulnerabilities in the Qi communication-based feedback control system used in inductive chargers, which wirelessly transfer energy to devices through electromagnetic fields.

Google Pay, the digital payment app for desktop, mobile apps, and in stores, was pretty much phased out by the introduction of Google Wallet in 2022. Google Wallet, which is a mobile app for Android users, is used five times more than Google Pay, according to the announcement. Since Wallet can also house credit cards for tap-to-pay, as well as digital IDs, and public transit passes, it’s proven to be the more useful alternative.

It’s somewhat typical for Google to launch products only to shut them down or roll them into other products after a few years due to lack of demand or commercial interest. The Google graveyard includes Jamboard, its cloud gaming service Stadia, and Google Play Music. So this is just one of many Google products to bite the dust. But Google Pay users won’t be left stranded.

If you’re a Google Pay user, you can still use the U.S. version of the app until June 4. But you can still transfer funds from your account into your bank account through the Google Pay website after June 4. After that, Google Pay users will no longer be able to send, request, or transfer money through the app.

The Seva Sustainable Sanitation innovation is a smart, electro-chemical toilet unit, which is suitable for use in off-grid rural areas of developing countries. It can turn toilet wastewater into disinfected water, using the power from its mounted solar panels to sterilise and clarify it. Macronutrients such as carbon, nitrogen, and phosphorus can be nearly fully recovered from the waste, leaving nothing but water that is recycled for flushing or irrigation. The toilet unit is also equipped with sensors, a mobile phone-based maintenance guide, and smart grid technology that empowers anyone in the community to repair the system when necessary. When a toilet is out of order, the technology automatically directs users to other nearby sanitation systems. So far, the solution has been deployed in four countries.

The landscape of artificial intelligence (AI) applications has traditionally been dominated by the use of resource-intensive servers centralized in industrialized nations. However, recent years have witnessed the emergence of small, energy-efficient devices for AI applications, a concept known as tiny machine learning (TinyML).

We’re most familiar with consumer-facing applications such as Siri, Alexa, and Google Assistant, but the limited cost and small size of such devices allow them to be deployed in the field. For example, the technology has been used to detect mosquito wingbeats and so help prevent the spread of malaria. It’s also been part of the development of low-power animal collars to support conservation efforts.

Small size, big impact Distinguished by their small size and low cost, TinyML devices operate within constraints reminiscent of the dawn of the personal-computer era—memory is measured in kilobytes and hardware can be had for as little as US$1. This is possible because TinyML doesn’t require a laptop computer or even a mobile phone. Instead, it can instead run on simple microcontrollers that power standard electronic components worldwide. In fact, given that there are already 250 billion microcontrollers deployed globally, devices that support TinyML are already available at scale.