L2M – AI Powered Seed Analysis

As part of the Lab2Market program, this project explores the commercialization potential of the group’s previous research pertaining to the use of computer vision, artificial intelligence and machine learning to precisely detect and identify seeds. Over the 4-month duration of the project, the team will participate in Lab2Market workshops, panels, and lectures from successful founders […]

Read More
L2M – NexusNeuro Portable EEG Validation

Diagnosing neurological conditions like epilepsy is often difficult because clinicians rely on brief, in-clinic brain activity recordings, which may miss crucial events. To solve this, our company, NexusNeuro, is developing a “Neurological Holter Monitor” — a discreet, wearable EEG device that allows for continuous, long-term brain monitoring in a patient’s everyday environment. While we have […]

Read More
L2M – Multi-layered Collagen Scaffolds for Periodontal Regeneration

This project is developing a new type of collagen-based material that can help reattach loose teeth caused by severe gum disease or injury. When gum tissue and bone are damaged, teeth can loosen or fall out because the natural structures that anchor them are destroyed. Current treatments only partially repair this damage and often fail […]

Read More
AI based Animal Behavior Recognition: Dog Pose and Labeling

This project will develop a real-time Artificial Intelligence based system that accurately estimates 3D skeletal pose from monocular video of dogs and reliably classifies fundamental behaviors to support veterinary health monitoring and behavioral assessment applications. Recent research has demonstrated significant progress in automated animal behavior recognition. The intersection of computer vision, animal behavior analysis, and […]

Read More
L2M – SeeVita: AI-Powered Contactless Realtime Vital Sign Estimation

Accurate and accessible blood pressure monitoring remains a challenge for individuals, wellness providers, and organizations such as insurers that require reliable health data. Existing cuff-based devices are often inconvenient, intrusive, and unsuitable for continuous or large-scale use. There is a growing demand in the wellness, fitness, and insurance industries for technologies that make health monitoring […]

Read More
MoCaP–ScoRe: Markerless Motion Capture for Precision Scoliosis Rehabilitation

Adolescent idiopathic scoliosis (AIS) is a common spinal condition that affects posture, movement, and quality of life. Deficiencies in proprioception, the body’s sense of position and movement, may play a role by disrupting balance and postural control, contributing to spinal misalignment. Scoliosis is typically assessed with static images such as X-rays, which cannot show how […]

Read More
L2M – Designing and validating an AI-based, user-centered tool to assess discourse skills in individuals with aphasia

Up to 40% of stroke survivors can experience aphasia, a language disorder that affects a person’s ability to speak, understand, read, or write. However, one of the most effective ways to accurately assess aphasia, discourse analysis, remains underutilized. Discourse analysis is usually time-consuming and performed manually, leading to varying results between clinicians. It can also […]

Read More
L2M ParkinSense

This project aims to validate and strategically position an innovative digital health solution designed to monitor tremors in individuals with Parkinson’s disease. The system integrates a wearable sensor and a mobile application to provide continuous, objective measurements of tremor severity and patterns — data that are traditionally collected subjectively and infrequently during clinical visits. Over […]

Read More
L2M- Protvac

Protvac aims to unlock the dark proteome against cancer by uncovering novel therapeutic targets. Studies show the non-coding DNA (dark genome) that has been thought to be irrelevant till now can translate into previously unannotated targets. In one proteogenomic study of human tumors, nearly 90% of tumor-specific antigens came from non-coding regions areas that standard […]

Read More
Linguistic Cues for the Extraction and Synthesis of Speech in Extreme Noise

Malaspina Labs Inc. develops algorithms for enhancing speech in extremely noisy audio signals for real-time applications such as hearing aids and mobile devices. Many classical approaches to speech enhancement are not applicable to these domains because of severe hardware and psychoacoustics constraints such as far-field, single microphone use cases (no beamforming),

Read More
Security Investigation and Solutions to Online Advertising Fraud Problems

The market share of online advertising, also known as Internet advertising, has been increasing dramatically in recent years. On the other hand, malicious behaviors, such as click fraud, have degraded the effectiveness of online advertising. Via fraud clicks, a considerable amount of revenues have been lost to fraud conductors. For instance, based on a report […]

Read More