Momega Ltd — Blog

Why one sensor is not enough: measuring posture and movement second by second

2026-09-21T09:00:00.000Z

Most wearable movement research uses one sensor. A wrist-, hip- or ankle-worn accelerometer is cheap, easy to put on, and good at what it was designed for: measuring the overall amount of activity, sedentary time or sleep. It is the basis of a large literature, and for those questions it works.

MAIJU uses four sensors, one on each limb, because it answers a different question. Not how much did the infant move, but what were they doing, second by second: lying on their back, on their front, sitting, crawling, standing, still or moving, and how skilfully. That kind of question has a different set of requirements, and a recent study measured them directly.

Posture is a whole-body configuration

An accelerometer measures two things about the place it is attached to: its orientation relative to gravity, and how it is accelerating. A gyroscope adds how fast it is rotating. Neither says anything about the rest of the body.

That is enough to count movement. It is not enough to tell postures apart, because a posture is a relationship between body parts. An infant sitting and an infant lying on their back can hold their arms in exactly the same way; a thigh looks much the same in crawl position as in prone. What separates them is how the arms and legs are placed relative to each other — which only a sensor on each end of the body can see.

Movement quality has the same problem. Telling rolling from pivoting, or wobbling in place from crawling, depends on how the limbs move together over a few seconds, not on the intensity at any one of them.

What the evidence shows

The question of how many sensors are needed, and where, was tested systematically on MAIJU recordings of 41 infants aged 4 to 18 months, with synchronised video annotated by trained human observers as the benchmark (JMIR mHealth uHealth 2025). The same classifier was retrained on reduced versions of the data — fewer sensors, lower sampling rates, accelerometer without gyroscope — and each version was scored against the video.

Classifier agreement with human video annotation (Cohen's κ) for different sensor setups
Sensor setup	Posture, κ	Movement, κ
Four sensors, both arms and legs	0.90–0.92	0.56–0.58
Two sensors, one arm and one leg	0.89–0.91	0.50–0.53
One sensor, arm or leg	below 0.75	below 0.45

Agreement between the classifier and human video annotation, as Cohen's κ. Movement categories are harder for people too: two trained annotators agree on them at around κ = 0.60, against about 0.95 for posture (Communications Medicine 2022).

The authors' conclusion is plain: single-sensor configurations were not feasible for second-by-second posture and movement detection. The ranking was the same for posture and for movement — all four limbs best, then three, then one arm and one leg, then both legs, with arm-only and single-sensor setups last — and leg sensors did better than arm sensors. The minimum that still worked was one upper-limb and one lower-limb sensor.

It shows up in the summary numbers too

One might hope that second-level errors average out over a long recording. They partly do, but not enough. When the classifications were summed into the time spent in each posture, four sensors, and one arm with one leg, matched the human annotation closely for every posture (r = 0.96–0.999, except side lying at r = 0.73 for two sensors). A single leg sensor fell below r = 0.9 for four of the categories, and a single arm sensor below r = 0.8 for five.

The same held for the overall motor score. The BABA Infant Motor Score computed from four sensors was indistinguishable from the two-sensor version (r = 0.98), but single sensors reached only r = 0.78–0.79 against the reference, with individual errors of up to 45–50 points on the 0–100 scale. The errors were largest in exactly the period that matters most: the move from floor-based postures to sitting and standing, when an infant's repertoire changes fastest.

The gyroscope, and what does not matter

Two other design choices were tested. Dropping the gyroscope hardly affected posture, but hurt movement detection: with raw accelerometer data alone, four-sensor movement agreement fell from κ = 0.58 to 0.27. Rotation is much of what distinguishes one movement from another.

Sampling rate, by contrast, barely mattered. With four sensors, results were unchanged from 52 Hz down to 6 Hz, because the classifier reads the posture from orientation and the movement from its context over tens of seconds. That is useful in practice: a lower rate means smaller files, longer recordings in the sensor's own memory and a longer battery life.

Where actigraphy fits

None of this makes activity counts wrong. They measure intensity, and they are the right tool for questions about intensity. The large growth-chart study computed actigraphy-style counts from the MAIJU leg sensors alongside the posture analysis, and the two turned out to complement each other (Sci Transl Med 2026).

Split by posture, the counts told a clearer story than the total. Activity while in crawl position jumped around 9 months and activity while standing around 12 months — the ages at which fluent crawling and walking emerge — while activity while sitting barely changed across the whole age range. Leg activity during crawl posture tracked fluent crawling (r = 0.83), and activity while standing tracked fluent walking (r = 0.91). The study's own summary: activity counts become physiologically and developmentally interpretable once they are complemented by the context of postures and movement quality. And that context, the authors note, is only available from multiple sensors in fixed body positions.

Consumer fitness wearables seem to contradict this, since they recognise walking or cycling from a single wrist sensor. But they do it over minutes, and on long, rhythmic, repetitive movement. An infant's play is neither: video annotation shows postures and movements changing from one second to the next, and much of it is not rhythmic at all (JMIR mHealth uHealth 2025). A measurement that averages over minutes misses the behaviour it is trying to describe.

What this means for MAIJU

MAIJU puts four sensors on the upper arms and thighs, in pockets that hold them at a fixed position and orientation. Four rather than the minimum two is deliberate. Four sensors are the best-performing setup, and they add redundancy: a home recording where one sensor drops out still has three, and the analyses are trained to tolerate that. A recording is analysed when at least three sensors were working. Further, having symmetric placements open the possibility of studying movement asymmetry, which is an important clinical marker.

The same reasoning explains why our other garment, NAPPA, uses a single sensor. It answers a different question — sleep, breathing and body position through the night — where one sensor at the waist is the right tool. The number of sensors should follow from the question, not the other way round.

For the details of the classifier and its validation, see the posture and movement profile.

What MAIJU changes about measuring motor development

2026-09-19T09:00:00.000Z

Gross motor development is one of the most closely watched parts of early childhood, and one of the hardest to measure well. The standard way is a visit: a trained assessor watches the infant for a short while in a clinic and scores what they see. That works, but it is a snapshot — taken in an unfamiliar room, limited by how often a family can come in, and scored by eye.

MAIJU takes the measurement to the child instead. Here is what that changes, with the evidence for each point.

It measures the ordinary day

The family puts the suit on at home and the infant plays as usual while four sensors record every movement. No assessor is in the room and no visit is needed. Published sessions average around two hours of free play, far more than any clinic observation (Sci Transl Med 2026), and the method works well outside a laboratory setting: in a concurrent validity study all 67 at-home measurements were technically successful (Dev Med Child Neurol 2026), and in rural Malawi 94% of 121 measurements were (Pediatr Res 2026).

It agrees with the clinical standard

The BABA Infant Motor Score condenses a recording into one number from 0 to 100. Compared with the Alberta Infant Motor Scale scored by an experienced paediatric physiotherapist, the two correlated at ρ = 0.97. Used to flag infants below the 5th and 10th centile, they agreed at κ = 0.81 — in a cohort where more than half the infants came from a neurodevelopmental follow-up clinic (Dev Med Child Neurol 2026).

It does not depend on who is watching

The analysis is automatic: every second of the recording is classified into postures and movements by an algorithm that matches the agreement two trained human annotators reach with each other (Commun Med 2022); with all four sensors, posture classification reaches a Cohen's κ of about 0.90 (JMIR mHealth uHealth 2025). The same recording always gives the same result, so a change between two visits is a change in the child rather than a change in the rater.

It follows a child over time

Because the score moves gradually rather than jumping between milestones, it can be repeated and plotted on a growth chart, the way height and weight are. In a direct comparison, a single motor measurement placed a child's development as precisely as a length measurement does (a spread of 1.4 months against 1.5), and more precisely than weight or head circumference (eBioMedicine 2023). The score also keeps rising after scales such as the AIMS have reached their ceiling (Dev Med Child Neurol 2026). The BIMS page shows one infant's trajectory against the normative chart.

It sees detail a score leaves out

Behind the single number is a second-by-second record: time in each posture, how the infant moves within it, how often they change position. From 580 recordings of 92 typically developing infants, 220 such metrics have been charted against age, and in an independent clinical cohort 55% of them separated infants with abnormal development from the rest (Sci Transl Med 2026).

It connects to development beyond movement

Motor development does not happen in isolation. In a longitudinal study of 107 infants, those whose motor maturity ran ahead of their age were also ahead in prelinguistic and social development (Pediatr Res 2025). That makes MAIJU a useful measure for studies whose main question is not motor development at all.

What it is not

MAIJU is not a diagnosis. It measures gross motor performance, in detail and over time; interpreting what a result means for a particular child remains a clinical judgement. It is built for infants from lying supine to walking fluently, and its published validation covers 4 to 22 months of age (Pediatrics 2025).

Every claim above comes from a peer-reviewed paper, and all of them are listed on the research page. If you are planning a study or a follow-up service, tell us what you want to measure.

Momega Ltd is founded, and the site is open

2026-09-19T08:00:00.000Z

Momega Ltd was founded in Helsinki in 2026 by members of the research group at the BABA Center, New Children's Hospital, Helsinki University Hospital. This site opens with it.

Where it comes from

For several years the BABA Center has been developing wearables that measure infants where they actually live — at home, during ordinary days and nights — instead of during a short visit to a clinic. Two of them are ready to leave the laboratory:

MAIJU, a suit with four movement sensors that measures gross motor development during play.
NAPPA, a wearable diaper cover that follows an infant's sleep, respiration and position through the night.

The work has gone step by step, and every step has been published. For MAIJU, the most extensively studied so far, that meant first showing that a four-sensor garment could record ordinary play reliably, then that an algorithm could classify postures and movements as well as trained observers, then that the results held up against established clinical scales, physical growth charts and independent cohorts — in Helsinki homes and in rural Malawi. The group has published nineteen peer-reviewed papers on these wearables since 2019, all of them listed on the research page. More wearables are in development at the BABA Center, and they will follow the same route.

Why a company

A published method is not yet something another team can use. They need garments made in the right sizes, sensors that arrive paired and working, an analysis service that is kept running and versioned, instructions a family can follow, and someone to answer when a recording goes wrong. That is what a research group or a clinic needs before it can plan around a method, and a university project is not built to provide it. Momega is.

The science stays where it was. Members of the team that developed and validated these methods are building the company, and the analyses offered here are the ones described in the papers. As new wearables from the BABA Center are validated, this is where they will become available.

What is on the site

Garments — MAIJU for motor development and NAPPA for sleep, with their sizes, materials and care.
Cloud analytics — what a recording returns, from the BABA Infant Motor Score and normative growth charts to sleep detection, and how long a recording needs to be.
Research — every publication, with the measure each one validated.
Resources — instructions and answers to common questions.

Get in touch

If you are planning a study or a follow-up service and want to know which of our wearables fits it, request a quote or write to info@momega.fi. Tell us the age range and what you want to measure; that is usually enough to give a useful first answer.