SeamFit: The Smart Tshirt for Fitness Tracking

Track your workout, count your reps, and toss it in the wash- SeamFit is the AI-powered fitness tracker woven right into your tee.

Highlights:

SeamFit uses conductive thread and AI to track posture, exercises, and reps- no wearables needed
Unlike bulky fitness suits or wearables, SeamFit feels and functions like an everyday T-shirt
Its 93.4% movement detection accuracy opens doors for smart, non-intrusive AI-human interaction

A new sort of smart clothing that can track a person's posture and exercise regimen while looking, wearing, and washing like a conventional shirt has been developed by Cornell University researchers. The new technique, known as SeamFit, incorporates flexible conductive threads into the neck, arm, and side seams of a normal short-sleeved T-shirt ().

Smart Clothing Could Now Help You Stay Cool on a Hot Sunny Day
Forget air conditioners, smart clothing of the future may help you stay cool on a hot summer day.

‘Did you know?
Your next gym buddy might be your T-shirt! SeamFit can detect bicep curls, lunges, and even sit-ups- then go straight into the wash. #smartclothing #seamfit #aiwearables #fitnesstech #medindia’

Benefits of SeamFit- the Novel Smart Clothing that Tracks Exercise

The user does not need to manually log their activity since an artificial intelligence pipeline detects movements, recognizes exercises, and counts reps. After that, the user just removes a circuit board from the back neckline and places the sweaty shirt in the washing machine.

AirDresser Launched by Samsung Claims to Kill 99.9% Bacteria
Samsung launches 'AirDresser', an advanced smart clothing care solution, which claims to eliminate 99.9% of viruses and bacteria including, influenza, adenovirus and herpes virus.

Cons of Existing Body-Tracking Suits

According to Catherine Yu, doctorate student and project lead researcher, the majority of existing body-tracking clothes are either tight and restrictive or integrated with bulky sensors.

"We were interested in how we can make clothing smart without making it bulky or unusable," Yu told me, "and to push the practicality, so that people can treat it the way they would usually treat their clothing."

Athletes can also use fitness trackers, such as smartwatches or rings, although these are additional devices that people may not want to wear while training and do not track movement throughout the body.

The work, titled "SeamFit: Towards Practical Smart Clothing for Automatic Exercise Logging," was published in the ACM Proceedings on Interactive, Mobile, Wearable, and Ubiquitous Technologies and will be presented at the UbiComp/ISWC 2025 symposium in October.

Wearable Cooling and Heating Patch Could Serve as Personal Thermostat, Save Energy: Study
Newly developed wearable cooling and heating patch could serve as a personal thermostat and also help save energy on air conditioning and heating, reveals a new study.

How AI Tracks Human Movement

To evaluate the shirts' performance, the researchers recruited participants to undertake a series of 14 exercises while wearing SeamFit, including lunges, sit-ups, and bicep curls. Without any calibration or training for each user, SeamFit's model identified the workouts with 93.4% accuracy and effectively counted reps, with average errors of less than one.

SeamFit works because as individuals exercise, the threads' capacitance (or ability to store charge) varies as they move, deform, and interact with the human body. The capacitances are measured by the circuit board at the back of the neckline and transmitted to a computer via Bluetooth. The movements are then deciphered using a specialized, lightweight signal processing and machine learning pipeline.

Wearables Get Smarter for Shaping the Future of Fitness and Wellness
Wearables with advanced artificial intelligence technology can monitor many aspects of fitness and wellness in real-time to provide personalized health recommendations.

Improving Human-AI Interaction

More broadly, this type of technology could improve human-AI interaction by tracking human movements and activities, allowing AI to better understand when to interact and when to wait, for as when someone is eating or sleeping.

"While this paper demonstrated the approach for a simple garment, we believe it can easily be adapted to a wide range of garments and could take advantage of the complex seam patterns of advanced sportswear," said co-author François Guimbretière, an information science professor.

Reference: