Tech Bundle

AI In Healthcare

Artificial Intelligence (AI) in healthcare explores the AI systems which can be consisted of sensors, AI hardware and AI software. Sensors explore detection tools that integrated with AI system to diagnose and monitor one’s health. AI Hardware explores the chipset design and architecture, rather than algorithms, to achieve the next big breakthrough in AI. AI software explores computer program which mimics human behaviour by learning various data patterns and insights. Shaped by the AI systems, AI-powered technologies and its applications, such as personalized implants, AI-assisted personalized rehabilitation, AI-assisted robotic surgery, wireless body sensor networks and AI-powered assistive technologies may soon become a reality.

Physical Distancing via Mobile Phones and Badges
COVID-19 has triggered the need for physical distancing. It is not always easy to be aware of respecting physical distance in all circumstances. We have developed a mobile application that triggers our designed badge or the smartphones flash and vibrate when the distance of 2m does not comply. The software development kit (SDK) is integrated into any Android and iOS mobile app.
Self-powered Sub-nanowatt Microcontroller with On-chip Solar Cell for IoT Devices
This technology offer is a sub-nanowatt microcontroller that can continue to operate even when the device battery runs out of energy. A novel power management technique allows the microcontroller to self-start and continue to function under dim light conditions, without any battery assistance, by using a tiny on-chip solar cell. As such, this design is battery-indifferent. This design can facilitate the size reduction of batteries used to power IoT sensor nodes, making them potentially 10 times smaller and cheaper to produce.
Face Recognition Solution
The facial recognition solution is based on more than 10 years of vision work to design a state-of-the-art system coupled with neuromorphic artificial intelligence to detect and recognize multiple faces in milliseconds with more than 98% accuracy. The solution provides a platform to integrate into industry for commercialization requiring nothing more than a camera for vision on the edge.
Bioinformatics Platform for Genomics-based Precision Medicine
Next Generation Sequencing (NGS) has ushered in a sequencing data tsunami because of the cost effetiveness. As a result there’s a ‘omics’ data deluge. Now it’s trivial to generate BIG ‘omics’ data but very difficult to manage, analyse and visualise the ‘omics’ data. Our invention precisely solves this bottleneck by providing a cloud based interactive digital platform with automated and dynamic workflows with unique UI that is highly scalable and hosted on a Supercomputer.
Wireless Monitoring of the Muscle Blood Flow in Low Back Pain Population
Prolonged sitting has been identified as one of the risk factors associated with lower back pain (LBP). Slumped sitting posture, commonly observed in daily activities, results in spine flexion and increases the erector spinae (ES) muscle activity. This in turn elevates the joint compressive forces and the intra-muscular pressure, disrupting ES muscle blood flow and muscle oxygenation. Association has been established between muscle blood flow and fatigue. The near infrared spectroscopy (NIRS) is commonly used to measure muscle oxygenation. This non-invasive technology is commonly used by researchers due to its high accuracy. It is based on the absorption of near infrared light between the oxygenated and non-oxygenated hemoglobin and myoglobin. However, this is not well applicable in clinical settings due to its high costs and bulkiness.
Miniaturized Digital Spectrometer for Non-invasive Health Monitoring Consumer Devices
Non-invasive, continuous and accurate health monitoring is a must, to detect early symptoms and prevent possible disasters, and to personalize the healthcare while dramatically reducing ever growing healthcare cost. The optical spectrometer, widely used in various industries, can do such non-invasive and accurate measurement.  For example, blood glucose level, can be measured just by shining a light on skin, measuring the internally reflected light and analyzing the unique spectral fingerprint of glucose contents.  However, optical spectrometers tend to be far been too bulky, expensive and difficult to use in consumer devices. A Korean startup has developed a spectrometer that is tiny, affordable and easy to use. This spectrometer-on-a-chip is 1% the size of conventional solutions and can be incorporated easily into consumer devices and smart appliances (mobile phone, wearable, etc) as part of the Internet of Things (IOT).
Flexible Electric Skin
A thin layer flexible electric skin can detect force applied on it. The skin’s electrical resistance varies with applied force, and there is a relationship between the resistance and applied force. By measuring the skin’s electrical resistance, the applied force can be obtained. The skin can be made stretchable to cover irregular and curved surfaces.
Non-invasive Wearable Monitor for Continuous Blood Pressure Monitoring
Abnormalities in blood pressure are often an indicator of illnesses. The current gold standard for blood pressure measurement is through the use of a cuffed sphygmomanometer. Such traditional cuff systems for blood pressure measurements have many disadvantages. Not only are they uncomfortable, they also do not allow for continuous blood pressure measurements which is important for the accuracy of diagnosis of chronic hypertension. In critically ill patients where continuous blood pressure monitoring is required, only invasive methods are used which could have implications such as infection and ischemia.  To address this, a non-invasive blood pressure wearable consisting of several chest-based sensors including continuous wave radar, PPG and some others which allows for continuous blood pressure measurement is developed. 
Battery-free Wireless Body Sensor Networks for Human Physiological Signs Monitoring
Networks of sensors placed on the skin can provide continuous measurement of human physiological signals for applications in clinical diagnostics, athletics, and human-machine interfaces. Wireless and battery-free sensors are particularly desirable for reliable long-term monitoring, but current approaches for achieving this mode of operation rely on near-field technologies that require close proximity (at most a few centimeters) between each sensor and a wireless readout device. Our near-field-enabled clothing capable of establishing wireless power and data connectivity between multiple distant points (up to meter scale) on the body to create a network of battery-free sensors interconnected by proximity to functional textile patterns. The clothing, which is fabricated by using computer-controlled embroidery to integrate conductive threads with near-field-responsive patterns on normal textiles, is completely fabric-based and free of fragile silicon components. Network systems based on the near-field-enabled clothing have been demonstrated for the real-time, multi-node measurement of spinal posture and continuous sensing of temperature and gait during exercise.