Defense Research · Rapid Prototyping

From raw signal to actionable result at record speed.

SigVis Solutions builds high-fidelity prototypes for the hardest problems in defense research: AI, deep learning, signal processing, computer vision, radar, and sonar. We close the gap between paper and deployable system.

Request capability briefing → View projects

Domains Signal, vision, AI

Turnaround Weeks, not quarters

Fidelity Research-grade

CHANNEL · LIVE FEED ● ACQUIRED

CH-01 / ECG 72 bpm

CH-02 / 440 Hz −3.1 dB

CH-03 / NOISE σ 0.42

CH-04 / CLK 2.4 kHz

CH-05 / SONAR τ 12.4 ms

CH-06 / DOPPLER +18 m/s

CH-07 / SPECT 512 bins

CH-08 / BASE DC 0.0V

FS · 48 kHz SNR · 24.6 dB CHANNELS · 08 / 08

01 / Capabilities

A slice of what we do.

The areas below are some of where we go deepest — not a complete list. Most engagements combine several across the full sensor-to-decision pipeline. Each one is hands-on expertise, backed by published research and production code.

AI & Deep Learning

Machine Learning

Signal Processing

Computer Vision

Tracking

Radar

Sonar

Generative AI

02 / Featured Work

Multi-agent sonar tracking.

Two reference systems for cooperative underwater target tracking — one from passive range-amplitude signals, one from multi-agent sonar imagery.

● PROPRIETARY PASSIVE SONAR RNN TRACKING

Multi-agent passive sonar tracker

Long-range passive sonar target tracking in a 2D simulated environment. A novel recurrent neural network architecture turns per-agent range-amplitude signals into both target position and bearing-angle predictions, scaling to any number of agents and targets. Time-series modeling sharpens the track — confidence improves the longer the target is observed.

Reproducible on commodity hardware. Code, simulation, and write-up.

Request briefing → All projects

SIM · SCENE + SIGNALS ● TRACKING

Multi-agent passive sonar tracker — scene plot with predicted trajectory and bearings, plus per-agent range-amplitude signals

AGENTS · 03 TARGET · 01 RANGE-AMPLITUDE

DomainUnderwater acoustics

MethodNovel recurrent neural network

PredictsPosition + bearing angle

AgentsAny number, configurable

SignalRange-amplitude, passive

LanguagePython · PyTorch · NumPy

Status● Active

● PROPRIETARY SONAR IMAGING MULTI-AGENT TRACKING

Multi-agent sonar imaging tracker

Cooperative target tracking from multi-agent sonar imagery. Several agents fuse their individual sonar views to localize and follow a moving target across the scene, demonstrating the geometry and information-sharing that drive performance in distributed sensing.

Proprietary simulation. Runs on commodity hardware.

Request briefing → See demos

SIM · LIVE CAPTURE ● TRACKING

Multi-agent sonar imaging tracker — agents converging on a moving target

MULTI-AGENT TARGET · 01 SONAR IMAGING

DomainUnderwater acoustics

MethodMulti-agent sonar imaging

TaskCooperative target tracking

AgentsMultiple, configurable

LanguagePython

Status● Active

03 / Principals

Three researchers. Direct line from the bench to your problem.

No layers, no account managers. You work with the people writing the code.

Alex Berian

Founder · Principal Investigator PhD researcher · Electrical & Computer Engineering

Researcher in AI, deep learning, generative AI, machine learning, signal processing, computer vision, and 3D vision. Brings academic rigor and end-to-end systems experience to defense-research prototyping.

AI Deep Learning Generative AI Signal Processing Computer Vision 3D Vision

Google Scholar ↗

JhihYang Wu

Co-Founder · Research Engineer MS · Electrical & Computer Engineering
Former xAI

JhihYang worked as a full-time engineer at xAI while completing his master’s thesis in 3D computer vision, AI, and generative modeling. That frontier-lab experience — building and shipping at scale — is what he now brings to bear on smaller, sharper, defense-research-scale prototypes.

3D Computer Vision Deep Learning Generative AI Machine Learning AI Systems

Google Scholar ↗

Daniel Brignac

Co-Founder · Research Engineer PhD researcher · Electrical & Computer Engineering

Daniel is a PhD researcher working on machine learning, signal processing, and computer vision for sensing applications. His internship experience spans both sides of the defense-research ecosystem: the U.S. Air Force Research Laboratory (AFRL) and, currently, Areté — a direct line into the program offices and primes that drive the field.

Machine Learning Deep Learning Signal Processing Computer Vision AFRL Areté

Google Scholar ↗

04 / Engagement

Have a defense-research problem? Let’s scope it.

Email is the fastest channel. Send us the problem, the constraints, and a target turnaround — we’ll come back with a scoping note within 48 hours.

Email [email protected]

Entity SigVis Solutions LLC

HQ Tucson, Arizona · USA

Response ● Within 48 hours