I build contactless radar sensing systems to measure Alzheimer’s progression.

Custom mmWave hardware, the embedded stack that runs it, the clinical platform that receives it, and the family of movement, sleep and vital-sign indices derived from the returns. A memory care study at a Minneapolis facility is in University review.

FMCW: 60 GHzFMCW
dual-radar PCB: 8-layerdual-radar PCB
frames / 24 h soak: 2.28 Mframes / 24 h soak
defined indices: 8defined indices

Fig. 1Micro-Doppler return, 60 GHz FMCW. The steady horizontal band is torso velocity; the arcs above and below it are limbs. Gait signature recorded on the bench hardware.

What I have built.

Selected systems

Four systems, each a layer of the same instrument: the radar hardware, the software that runs on it, the platform that receives it, and the facility it is installed in.

Dual-radar sensing board

Hardware designEVT-0.3, in build

Invent

A single room-mounted node cannot see a fall and measure breathing at the same time. The radar configurations that resolve a body in motion and the ones that resolve sub-millimetre chest displacement are mutually exclusive, and switching between them on one sensor wedges the device.

Build

An 8-layer board carrying two TI IWR6843AOP antenna-on-package radars on an Octavo OSD6254 system-in-package host, each radar on its own UART so the two configurations run concurrently rather than in sequence. RF front-end bring-up, power tree, and reset topology done in-house.

Deploy

The third engineering revision, EVT-0.3, is being built now at EI Microcircuits in Mankato, Minnesota. Each revision is checked against the datasheets and the schematic before release, and the dual-radar architecture was validated on bench hardware before the first layout.

Radar: 2 × TI IWR6843AOP, 60 GHz FMCW
Host: Octavo OSD6254 SiP (TI AM6254)
Stack-up: 8-layer, controlled impedance
Topology: Independent UART per radar

Embedded acquisition and edge inference

Firmware and signal processingValidated, 24 h continuous

Invent

Fall detection that phones home to a server introduces latency and a dependency on the building’s network at the exact moment neither can be trusted. The decision has to happen on the device.

Build

Yocto-built embedded Linux on TI AM62x. A UART parser decodes the radar TLV stream into point clouds, tracks, and vital-sign estimates, feeding on-device classification for falls and long-lie events. A watchdog and self-heal path recover the radar without a power cycle.

Deploy

A 24.1-hour continuous dual-node soak recorded 2,283,608 frames. The vitals node logged an unbroken sequence. The tracking node showed four gaps totalling 38 frames, for 99.997 percent sequence continuity.

OS: Yocto / embedded Linux, TI AM62x
Tracking node: 15.2 frames/s, 1,320,216 frames
Vitals node: 11.1 frames/s, 963,392 frames, unbroken
Volume: 74 MB per device-day, both nodes

Clinical data platform

Cloud architectureLive

Invent

Continuous radar from occupied rooms is protected health information the moment it can be linked to a person. The pipeline has to be de-identified at the edge, not cleaned up downstream.

Build

A Terraform landing zone under seventeen CDK application stacks on AWS. Devices publish over MQTT to IoT Core; telemetry lands as partitioned Parquet in S3 and is queried through Athena. A FastAPI service layer fronts the API, and a Bedrock-backed narrative service turns movement data into plain-language summaries for care staff.

Deploy

Running in us-east-1 under a HIPAA BAA. Resident identity never enters the pipeline; records are coded and re-identifiable only inside the facility.

IaC: Terraform landing zone, 17 CDK stacks
Ingest: MQTT → AWS IoT Core → S3 Parquet
Query: Athena, partition-projected
Inference: Amazon Bedrock narrative service

Memory care deployment

Clinical systems integrationIn University review

Invent

Every measurement in the literature that predicts cognitive decline, gait speed most of all, is taken in a clinic on the day of the appointment. The signal that matters is what the person does the other 364 days, and it cannot cost them a wearable they will take off or a camera they would refuse.

Build

Three sensing nodes per resident room, split by what each room has to answer: presence and vitals at the bed and bath, presence and movement quality in the living space. Installation, calibration, and per-room zone learning happen on site.

Deploy

A study protocol at a Minneapolis memory care facility, scoped to ten resident rooms and thirty devices, is in review with the University's IRB, Health Information Privacy and Compliance Office, and vendor risk assessment. Deployment starts on approval.

Site: Memory care facility, Minneapolis
Review: IRB, privacy office and vendor risk, pending
Scope: 10 resident rooms, 30 devices
Per room: 3 nodes: bed, bath, living space

Validation of the built systems.

Research

Nine peer-reviewed publications and conference abstracts. The through-line is validation: each one tests whether a contactless measurement holds up against a clinical one.

Alzheimer’s & Dementia (Wiley)

2025
A Novel Framework for Synthesizing Biosensor Data and the Minimum Data Set to Improve Alzheimer’s Care
Johnson, B. B.·Alzheimer’s & Dementia
DOI
2024
Establishing a Remote Patient Monitoring Infrastructure with Starlink in Indonesia for the Aging Population to Improve Alzheimer’s and Dementia Care
Kresnasandi, I. B., Johnson, B. B.·Alzheimer’s & Dementia
DOI
2024
Cyclomatic Complexity: A Novel Approach for Analyzing Movement with Machine Learning to Predict Mild Cognitive Impairment
Johnson, B. B., Bolstad, B. A.·Alzheimer’s & Dementia
DOI
2024
A Novel Approach to Identify Sundowning with Cyclomatic Complexity Movement Analysis and Noninvasive Ambient Sensors
Johnson, B. B., Jamadagni, R. S., Kresnasandi, I. B., Bolstad, B. A.·Alzheimer’s & Dementia (AAIC)
DOI
2024
Integrating Noninvasive Radiofrequency Monitoring Technology Into Clinical Decision-Making
Bolstad, B. A., Johnson, B. B.·Alzheimer’s & Dementia (AAIC)
DOI
2023
Contactless Fall Detection with Radio Frequency Sensors for the Aging Population
Khan, A. A., Johnson, B. B., Snyder, K.·Alzheimer’s & Dementia (AAIC)
DOI

ASME Design of Medical Devices

2025
Evaluation of a Contactless Pulse and Respiration Rate Monitor Using Frequency Modulated Continuous Wave (FMCW) Radar to Reduce Sudden Infant Death Syndrome (SIDS)
Johnson, B. B.·ASME Design of Medical Devices Conference, University of Minnesota
DOI
2024
Noninvasive Patient Monitoring with Ambient Sensors to Monitor Physical and Cognitive Health for Individuals Living with Alzheimer’s Disease
Johnson, B. B.·ASME Design of Medical Devices Conference, University of Minnesota
DOI

AAIC Advancements

2023
Biomechanical Classification of Elderly Falls and Improving Long Lie Collapse Events with Contactless Radio Frequency Sensors
Johnson, B. B., Snyder, K.·AAIC Advancements: Toward Health Equity in Alzheimer’s Disease and Related Dementias

Full reference list at ORCID 0000-0002-4799-6007.

Research direction

The same instrument, further from help.

A resident with dementia cannot report a fall. A crew nine months from Earth cannot wait twenty-two minutes for a second opinion. Both are the same engineering problem: the measurement has to happen without cooperation, and the decision has to happen without a link.

Spaceflight already runs on the constraint I designed the memory care system around. NASA’s in-flight sensor requirements list minimal human interaction alongside low power and compact size. Its Exploration Medical Capability programme exists because one-way comms delay to Mars reaches twenty-two minutes, which ends real-time telemedicine and obliges the crew to detect and treat on their own. That is the argument for on-device inference, stated by someone else, about somewhere else.

01
Measured today by
Wrist-worn actigraphy, worn for the whole mission
Rest-activity and sleep timing from the room
Crew rest-activity is measured today with a wearable. The same rhythm, fragmentation, and sleep timing fall out of radar with nothing worn and no compliance to maintain.
02
Measured today by
Doubly labeled water, then mass spectrometry on Earth
Continuous energy expenditure from movement
Crew run a chronic energy deficit, up to 5.7 MJ per day, and have lost 1.5 to 10 percent of body mass on nearly every mission. The reference standard needs isotope-ratio mass spectrometry of returned samples, and there is no sample return from Mars.
03
Measured today by
Weekly vigilance tests and self-report questionnaires
Passive behavioural markers as a supplement
Vigilance tests cost crew time and questionnaires depend on self-report, which degrades exactly when a crewmember is struggling. Circadian phase shift is among the strongest known predictors of mood episodes, and it is measurable passively.

Not duplicating

NASA already has contactless vital signs: UWB biodetectors read respiration and heart rate through a suit. Repeating that is not the contribution. The open ground is the layer above it, where continuous movement becomes a functional and behavioural state estimate over months, which is the same problem as tracking decline in memory care.

What transfers

The memory care pilot is the analogue. Same sensor class, same zero-cooperation constraint, same need to hold calibration over months in a room nobody is supervising, and a population that cannot be relied on to report its own condition.

Where things stand.

Now · October 2026

Role: Research Professional, Biomedical Engineering, and Research Scholar, Earl E. Bakken Medical Devices Center, University of Minnesota. Founder and Principal Engineer, Ambient Intelligence Inc.
Degree: MS, Medical Device Innovation, University of Minnesota. Conferred May 2025, 3.98 GPA.
Funding: Technical lead on the ODAT-funded memory care study ($248,000, awarded to the University of Minnesota), which runs through March 2027. Helped secure Maslowski Foundation funding for neonatal monitoring.
Translational: Minnesota Partnership translational funding, a State of Minnesota program with the University of Minnesota and Mayo Clinic.
Under review: Principal Investigator on two NIH SBIR Phase I applications submitted September 2026: NIA (contactless gait and mobility biomarkers) and NICHD (contactless neonatal vital signs).
Clinical: Memory care study at a Minneapolis facility, pending IRB, Health Information Privacy and Compliance Office, and vendor risk assessment approval.
Recognition: Minnesota Cup 2026 semifinalist, Impact Ventures division: 92 companies selected from 1,262 statewide.

Composer and performer.

Since 2008

I have released nine albums and more than 160 tracks under the name Brian Bradley, with millions of plays on Spotify, and performed a live audiovisual show synchronized with NASA and SpaceX footage.

albums: 9albums
tracks released: 160+tracks released
composing since: 2008composing since

Brian Bradley on Apple Music

Coda

I started this because of what a room can tell you when nobody is asking anything of the person in it. A resident with dementia cannot reliably report a fall, or a bad night, or the slow week that came before it. The instrument has to do the noticing, and it has to do it without asking them to wear, press, or remember anything. That constraint is the whole engineering problem, and it is the reason I would rather build the sensor than buy one.