TECHINNOVATION TECH OFFERS

Timely and adequate rehabilitation is critical in facilitating post-stroke recovery. However, the organisation and delivery of rehabilitation are resource-demanding, and are only available in ~25% of stroke survivors in low-middle-income countries. Therefore, innovative solutions are urgently required to improve access to stroke rehabilitation services. Our team developed a platform to assist remote dissemination of physio- and occupational therapy services. Our platform enables post-stroke rehabilitation services to be delivered using consumer-grade devices (e.g., smartphones and tablet devices) and artificial intelligence technology, thereby breaking many physical and resource barriers to rehabilitation service access. Our platform is designed for hospitals, rehabilitation centres and post-stroke service providers. The system consists of two interfaces – the therapist portal and patient application. Portal system enables remote prescription of exercises and monitor exercise performance and progress, whereas the patient application acts as a “smart therapist” in providing real-time instructions and feedback. The system addresses limitations faced by the conventional phone interview- and video conference style of telemedicine, which mainly relies on self-reporting and subjective recall. Using devices’ built-in camera and relevant Internet of Things (IoTs), we automated the evaluation process using algorithms with key features identified by professional therapists for providing “supervision” through real-time feedback.

There is an increasing requirement for systems that can detect people in built up space. The requirements come from diverse fields such as safety, security and sustainability. In the field of safety, video cameras or wearables have conventionally been used and both come with significant downsides. Video cameras are highly dependent on the line of sight and are privacy invasive while wearables introduce a burden on the end user. Microwave radar-based solutions are a field of research which can overcome the downsides by being accurate, not burdening the end user and by removing the requirement of line-of-sight. The company provides algorithmic solution in this space based on microwave radar in a Multi Input Multi Output (MIMO) configuration. The solution utilizes biological activity including respiration and heartbeat and consequently does not require measurement of the static environment in advance.

Keratins are naturally occurring proteins found in hair, feathers, wool and other external protective tissues of animals. They are highly abundant, naturally produced and generally underutilized. At the same time, keratins offer versatile chemical properties that allow interactions with themselves or with other materials to improve behaviour. The technology provider has developed sustainable, biodegradable plastic materials by upcycling keratins derived from hair and feathers. In the preliminary studies, the technology provider has found ways to produce films that have the potential to be used as packaging materials. These films do not disintegrate readily in water, yet they fully degrade in soil within a week. They can be made in combination with other waste-derived biopolymers to improve strength to meet the needs of specific use cases. This technology is available for R&D collaboration, IP licensing, or IP acquisition, with industrial partners who are looking for a green packaging solution and to explore specific-use-case products. The technology provider is also interested to collaborate with the OEM partners having the keratin extraction facility from feathers and hair for the deployment of this technology.

Vision-based Artificial Intelligence (AI) models require substantial time to train, fine-tune and deploy in production. After production, this process is still required when performance degrades and re-training on a new dataset becomes necessary; this maintenance process exists throughout the model's lifetime to ensure optimal performance. Rather than embarking on the time-consuming and painful process of collecting/acquiring data to train and tune the AI model, many organisations have turned to the use of pre-trained models to accelerate the AI model development process. This technology consists of a suite of pre-trained models that are intended to detect food, human behaviours, facial features and count people. These AI models are operable on video footage and static images obtained from cameras. Models are tuned and trained on various use-cases and are accessible via API calls or embedded within software as a Software Development Kit (SDK) library. These models can be deployed as AI as a Service on Microservices platform providing customer data protection with blockchain technology. With customer protection enhanced with blockchain technology, AI Model performance can further be enhanced to meet customer requirement.