TECH OFFERS

Most existing training applications offer good programmes for guiding users to achieve individual fitness goals, some even come with guided video workouts led by professional trainers. However, such applications lack or have limited capability to assess whether the correct posture is maintained during exercise - poor posture can reduce exercise effectiveness and may even cause injury, e.g. arched back during push-ups. This solution is a synergistic combination of video/image processing, human pose recognition, and machine learning technologies to deliver a solution that addresses the twin challenges of accurate count and correct execution of exercises in an automated manner, without having to wear any additional hardware/sensors. The software-only solution is able to advise users on the correct execution of repetitive movement sequences, e.g. sit-ups, and push-ups, and is deployable on a wide range of affordable camera-enabled hardware devices such as mobile phones, tablets, and laptops, and it can be easily integrated into existing applications to enhance functionality. It is applicable to the sports and healthcare industry to help users perform exercises correctly and effectively in an unencumbered manner. This software-only solution is able to identify the correct or incorrect execution of repetitive movement sequences using camera inputs from devices such as mobile phones, tablets, or laptops. The solution can be deployed on any Python and JavaScript-capable platform; providing flexibility for deployment across a range of devices and operating systems, including web browsers. Video/Image Processing Pre-processing of video frames as inputs for Human Pose Estimation and Machine Learning Built-in algorithm used to assess real-time movement direction, i.e., up, down, right and left, thereby providing inputs for a more accurate count Human Pose Estimation Based on BlazePose, OpenCV and TensorFlow for real-time tracking of up to 32 human pose keypoints, e.g. shoulder, wrist, hip, knee, ankle, etc Measurement of angles between pose keypoints as input parameters to determine correct posture, e.g. is the user's back straight, are the knees bent Enhances original image from camera with accentuated pose keypoints and connections between keypoints, i.e., stickman diagram, used as input AI classification to determine correct posture. Machine Learning Train and test AI models using human subject video footage for correct and automatic classification of exercises AI models classify exercise based on angles and distance of pose landmarks and enhanced images with accentuated pose landmarks and connections between landmarks   Primarily for fitness and healthcare (rehabilitation) industries - can also be applied for any activity that requires assessment of posture Repetitive exercise-specific counting e.g. push-up, sit-up, additional exercises can be included, requiring specific customisation Posture assessment and analysis of the movement of human subjects - personalised calibration to initial posture can be explored  Enables intelligent coaching functionality in fitness/healthcare applications to promote healthy or active living Enables real-time posture assessment and monitoring Does not require additional body-worn sensors or wearables; simply requires a camera-enabled mobile device Provides value added-service to an existing healthcare/fitness application to help end-users perform exercises correctly and effectively in an unencumbered manner  Provides remote assessment of exercise without any over-reliance on the expertise of a professional coach The technology partner is looking for test-bedding opportunities in the fitness and rehabilitation industries, which would involve studying specific exercises individually. Additionally, the technology owner is looking for co-development with companies that have adjacent use for this posture assessment software, e.g. heavy load lifting, combining the software with additional body-worn sensors to detect uneven weight distribution on the workman's back. Human Pose Estimation, OpenCV, Tensorflow, Dense Optical Flow, Sports and Leisure, Rehabiliation Infocomm, Video/Image Analysis & Computer Vision, Artificial Intelligence, Personal Care, Wellness & Spa, Data Processing

While interest and demand for blockchain-related technologies continue to gain popularity and spurs the exponential growth in adoption of blockchain in areas such as payment, documents and digital identities, not just in finance, but in industries such as logistics, supply chain as well. Many emerging areas that rely on blockchain as a core technology lack the manpower needed to sustain budding development, this lack of technical skillset required for blockchain development is the primary hurdle to successful blockchain application development - less than 1% of the tech workforce is skilled or competent in blockchain-related development. The characteristic of blockchain technology, which enables a permanent record of digital information such that it cannot be modified by any single entity renders it well suited as a digital ledger of online transactions. As such, blockchain is a core technology for many emerging areas such as Decentralised Finance (DeFi) and Decentralised Autonomous Organisation (DAO). This technology offer consists of a platform tool and a set of zero-configuration REST APIs that abstract away the complexity of blockchain technology and enables any developer to easily build blockchain-based applications or integrate blockchain functionality into their existing systems. Intended as a low-code platform, it addresses the skills gaps traditionally required for blockchain development and deployment and allows companies to realise their blockchain ideas, enhance business operations and expand solution offerings.   The core of this technology is a chain-agnostic, node-wrapping, enterprise-grade middleware that includes a suite of documented REST APIs, developer tools, and frameworks required for the development of blockchain-based applications and their integration into a company’s existing systems. It includes the following features: Supports both permissioned (private) and permissionless (public) blockchain networks Orchestration between the nodes and synchronisation are handled by the platform Flexible Scalability - enabling scale in/out, scale up/down Integrates with a decentralised peer-to-peer file storage system to ensure data is stored off-chain (InterPlanetary File System, IPFS) Integrated development environment (IDE) for custom code port-in from an external repository Library of ready-to-use smart contracts (fungible tokens, non-fungible tokens) Selectable blockchain protocol (Ethereum, Ethereum Mainnet, Corda, Hyperledger Fabric) Decentralised application can be deployed on any cloud provider (Google Cloud Platform, Amazon Web Services and Microsoft Azure) This technology allows for the development and deployment of blockchain use cases for any industry. The following areas have benefited from this technology, and are readily available as working smart contracts for use on the platform: Food and vaccine safety/quality/authenticity traceability Circular economy, digital asset tokenization Green financing/loans, green bonds, carbon credit tokenization Any use-case which is able to leverage on blockchain's inherent properties of immutable traceability and auditable trails will benefit from this technology, including the following benefits: Low-code platform simplifies blockchain application development, deployment and integration, especially for businesses that want to use blockchain but don't necessarily have the know-how Automatically encompasses the best practices for blockchain development  Eliminates the repetitive tasks and overhead required to build robust blockchain applications Reduces the time from use-case ideation, to development and PoC deployment in just 1~2 months - speeding up the testing of an actual use case allows businesses to quickly gauge the blockchain use-case’s impact and make data-driven decisions Industry-agnostic - build any use-case with a library of ready-to-use smart contract templates, enabling rapid development, configuration and deployment in a single platform Applicable for asset tokenization, supply chain traceability, trade finance, etc. that would benefit from immutable blockchains and auditable trails including, but not limited to sustainability initiatives blockchain, low code, traceability, esg, sustainability Infocomm, Blockchain & Other Distributed Ledgers

The current clean meat technologies grow lab meat with conventional 2D cell culture. However, the conventional cell culture technique has an overall low yield of cells, as the cells are restricted to growth on surface areas.  A new 3D scaffolding method has been developed to overcome this problem with the use of microcarrier beads that provide cells with additional surface area to attach onto and proliferate. The microcarrier beads are suspended in the cell culture thus maximizing the 3D volume of the cell culture, leading to an increased yield. A microcarrier type has been identified to yield the highest number of porcine cells. The conditions of the cell culturing process have been optimised to improve the cell viability in a 3D environment Companies interested in cell-cultured meat development could consider using this method to grow cell-cultured meat at a larger scale with a potentially lower cost of production. The technology developer is seeking companies that are keen to scale up lab-grown meat applications.  The technology owner uses microcarrier beads, which are small (approx. 75 um diameter) polymer beads. They collectively provide a significantly larger surface area than standard tissue culture flasks for cell growth. Typically used in the pharmaceutical industry to scale up cells for protein expression, the use of microcarrier beads for the scale-up of cell-cultured meat is a relatively new application.   Some key features of the technology: Increases cell yield by 7-fold from lab-scale Microcarrier beads hold their shape throughout Made up of inert and food grade material  Different cell types require specific types of microcarrier beads to optimize growth The method is suitable for:   Clean meat industry / Cultured meat companies Pharmaceutical companies that apply such technologies towards protein manufacturing, drug discovery or antibody production. Other potential clean meat applications using other cell line sources. With the increasing demand for meat production for population consumption, there is a need to look at other more sustainable meat source. Lab grown ‘clean meat’ can be an alternative to livestock farming. The development of ‘clean-meat’ can help to reduce carbon footprint, improve animal welfare and prevent foodborne illnesses. The cultured meat market size was valued at $1.6 million in 2021 and is projected to reach $27 billion by 20301.   1Cultured meat market size, share - global industry report, 2022-2030. Allied Market Research. April 2021.   Increased yield of viable cells as compared to 2D cell culture Scalable Up to 7x lower in cost of production at a larger scale Pathogen-free source of meat produced High reproducibility Low usage of microcarrier beads: 10g microcarriers/20 litres of cell culture clean meat, microcarrier, dynamic culture, cultured, meat, scaffolding, 3d, scaffold Chemicals, Polymers, Foods, Ingredients, Processes

This technology offer presents an autonomous materials handling system. The technology could reduce manual labor requirements and increase working efficiency. The solution consists of a Lidar Elevator Stand (LES) system, which will trigger the autonomous actuators (e.g., trolley puller, tray return robots) via the robot command center whenever no goods (e.g., trolley, tray, and stock) is detected in the designated area. Currently, the technology has been demonstrated in autonomous trolley return solutions. Generally, trolley replenishment requires deploying manual labour to monitor the available quantity at the trolley bay and replenishing it by physically operating an electric trolley puller to transport the new stack of trolleys. Therefore, the system was developed to solve the problem by triggering an autonomous trolley puller to replenish the new stack of trolleys whenever the trolley quantity is depleting. The system can be further customized and repositioned based on clients’ requirements. The  Machine-to-Machine communication protocol for Lidar Elevator Stand system (Client), remote autonomous trolley puller (Client) and Robot Command Centre (Server). The 2D Lidar sensor has a field-of-view in Lidar Elevator Stand (LES) system with detection range from 0.05m to 10m, and a horizontal aperture angle of 200 degree, which is suitable for deployment in the application at airport Ability to avoid false triggering requests for trolleys replenishment from LES System. LES system’s operations and processing are able to work under different lighting conditions. Replenishment of trolleys can be customised for multiple location points. Material handling with delivery in airports, supermarkets, warehouses, logistics, hotels and factories. Improve and simplify work operations. Free up existing manpower to take up new higher value-added tasks. Seamless communication between monitoring and replenishment of trolley. Safe mobility replenishment of trolleys, trolleys, material handling, autonomous trolley puller, trolley puller, trolley Infocomm, Networks & Communications, Mobility, Robotics & Automation, Logistics, Inventory Management, Transportation

The proliferation of e-commerce, ride-hailing and food-delivery services have fueled the need for more accurate and reliable estimation of delivery times. The current common estimation of delivery time is based on Estimated Time of Arrival (ETA) which relies on route distance that is calculated between the origin and the desired destination. It only considers the duration from pick up to drop off, and does not consider the additional time needed for preparing and offloading the goods. This technology offer is a Machine Learning (ML) model that is able to calculate the stop duration (job completion duration), which together with the ETA, provides the Estimated Time of Completion (ETC). This ML model is for Singapore use only. For the Machine Learning (ML) model to calculate the stop duration, users will need to key in the input parameters such as building name, block number, road name, postal code, day of week, day of month and time. The system will predict the stop duration (job completion duration) in minutes. ML model enables prediction of ETC based on historical data and a small set of input parameters Highly correlated with ETA which can be easily obtained from API services such as Google or Onemap Takes in consideration of temporal data including hours of the day and day of the week. Can be integrated with existing web/mobile based solutions. Apart from being a productive tool for route planning systems, the software can also be used in various situations such as: Customer Services/Call Centres Fleet Management  Loading Bay Assignment This model can be used to improve the existing route planning systems as it provides additional job completion duration prediction on top of estimated ETA.  Low cost - the model is easy to implement and incorporate into other applications. Simple to use - only a small set of input parameters are required. Able to predict the stop duration (job completion duration) with reasonable accuracy. The technology owner is keen to out-license this technology to collaborators in the field of last mile-logistics, or collaborators who are providers of software for last-mile logistics. This ML model is for Singapore use only. Last Mile Delivery, Estimated Time of Completion (ETC) Infocomm, Artificial Intelligence, Logistics, Delivery & Distribution, Value-Added Services

After a skin injury or surgery, a scar may form as the wound heals. In this body's repair mechanism, the myofibroblast cells produce new collagens and they form an extracellular matrix (ECM) to repair a wound. Over time, most scars become flat and pale. However, in some abnormal cases, the body produces excessive collagens. The excessive ECM formation and deposition of these scar tissue will result in raised scars such as hypertrophic scar and keloid scar. These raised scars may leave lifelong marks on the skin. Although the raised scars are not dangerous or life-threatening, they create aesthetic concern, restrict physical movement and may also lead to itching, tenderness, pain or even depression and anxiety. The currently available scar removal products such as silicon patches and topical products may cause skin irritation, which has led researchers to look for safer and more effective solutions. The present technology is a series of phytonutrient-based remedial fluids, which can be used as a general topical agent or complemented with a nano sprayer for the management of raised scars. The product developed from this technology is a safe, non-invasive and convenient approach to suppress hypertrophic and keloid scars. The technology provider is looking for collaboration opportunities to co-develop skincare products incorporated with this series of plant-based remedial fluids for scar management, collaborators for conducting clinical studies to evaluate effects of the current prototypes as well as other partnership mode including IP licensing.  Hypertrophic and keloid scars are two different fibroproliferative disorders of the dermal tissue upon skin injury. The activation and local proliferation of myofibroblasts in the dermal layer is considered prerequisite for excessive ECM formation, including the overproduction of collagens for filling up the wounds. The phytonutrient-based remedial fluids consist of small-molecule flavanol glycosides extracted from ferns. Experimental results showed that these plant-based fluids could significantly suppress the activation and proliferation of skin myofibroblasts in patients with hypertrophic scars or keloids. These small molecules could also largely reduce the deposition of ECM. As a result, the formation of raised scar can be prevented. The prototypes of the phytonutrient-based remedial fluids have been developed and are currently undergoing product testing. They are designed to reduce raised scars and improve skin conditions. Over 50 volunteers with various types of scars and different skin conditions have tried the prototypes in the initial trial. Overall, positive feedback were received, including notable improvement in scar appearance, alleviation of itchy feeling and prevention of excessive scar tissues. This phytonutrient-based formulation can be used in scar treatment in the form of skincare products such as a general topical agent or nano-mist. They could help shrink, soften and flatten the raised scars, especially for hypertrophic scars and keloids. In addition, this technology can also be used for therapeutic purposes, such as inhibiting the development of fibrosis.  Since many scar treatment gel sheets or creams contain silicone, this natural, non-toxic product provides another option for the people who are allergic to silicone. Customers can be benefited from these herbal-based products with their non-irritating, refreshing texture. Personal Care, Cosmetics & Hair, Healthcare, Pharmaceuticals & Therapeutics

Conventional diagnostic imaging of the skin involves the use of dermatoscopes. Dermatoscopes use skin surface microscopy to examine dermal and sub-dermal tissues to diagnose skin problems. However, these devices can be costly and provide a limited view of the immediate skin surface. This limitation meant that dermatoscopes have to be used in direct contact with the patient's skin. Because of this, they can only be used to image patients in the same physical location as the clinician conducting the examination. The overall result is that only a tiny portion of the global dermatology patient-base can be reached cost-effectively and efficiently. Telemedicine and telehealth network operations are rapidly developing ways to address patients broadly and at lower costs for them and their care providers. Yet, such tools neither deliver desmatoscope-like functionality nor improved it in way that it allows patients' skins to be examined and analysed during an online medical consultation with a general practitioner. In order to facilitate remote skin disease diagnosis, the use of software is required to acquire and share images in real-time and ideally, by the patients themselves. This software enables patients to take their medical sub-skin images with their mobile, tablet or laptop cameras, and securely share it with doctors. Crucially, dermatoscopy images can also be used with the technology to improve diagnostic accuracy. This technology is intended to position itself as a technology which when scaled-up, could allow for products that can enable optical biopsy and phototherapy.  The technology, Remote Diagnostic Imaging (RDI) is available in two modes: Real-Time (RT) and Store-and-Forward (SAF): RT provides remote real-time examination of the patient’s sub-skin by a clinician. SAF enables the patient to snap and forward the sub-skin images to the clinician for assessment. A non-clinician staff member at a clinic can also help the patient to take the images and forward them to a skin specialist. This remote imaging diagnostics is intended to facilitate time and cost savings for both doctors and patients.  The RDI service consists of proprietary software that works with any smart camera device such as mobile, tablet or laptop cameras. An individual at any remote location could take photographs of suspicious skin lesions, and then forward it to the doctor. While the functionality is similar to most image-sharing software, what sets the software apart from other algorithms is the presence of a sophisticated algorithm that acquires sub-skin features of the skin (in normal light) thereby noticing skin issues prior to manifestation on the skin surface. Cosmetic and Medical Dermatology - With 3rd party software, this skin imaging software platform has the potential to facilitate more accurate diagnosis and management of a range of skin diseases, such as psoriasis, acne, vitiligo and dermatitis, to more serious and potentially fatal conditions of melanoma. Optical Biopsy - Completing initial tissue analysis in a few minutes. Phototherapy - Producing the skin and tissue pectral data needed to deliver the correct type and dosage of opticat radiation. Podiatry (diabetes) – Diabetic patients can suffer from numbness in their feet, potentially leading to foot infections which if left untreated may necessitate amputation. The RDI and proposed multispectral imaging solutions can help podiatrists gain advance notice and clarity of potential issues. The key benefit being a better patient outcome.  X-ray (radiology) – X-ray radiation continues to be a major cause for health concern despite its significant benefit in patient diagnostics. It is also not known for being able to render soft tissue visual detail in the way that MRI and ultrasound does. Both RDI service and multispectral imaging embedded technology enable the use of pre-existing X-ray images to be used to acquire visualisation of more detail. The key benefit is reduced radiation dosage which results in less risk to the health of the patient.  In the near future, it is expected that an absorbed multispectral-based imaging app or device as well as the embeddable diagnostic platform will become an integral part of a smart diagnostics platform for remote clinical diagnosis. Dermatology clinics and hospitals can use these solutions for the remote diagnosis of any type of skin disease, track the progress of a patient condition after treatment, and better engage patients in the treatment process by empowering them to take proper preemptive care of their skin health. The technology is available as an embeddable algorithm, and as a secured cloud-based service that can be embedded to a website. The embeddable version of the technology is available in a licence or co-creation form. It can be embedded in OEM devices, equipment and machines. Some of the advantages of this innovative technology are as follows: Skincare consumers and patients can self-analyse and monitor their skin's health from the comfort and privacy of their home, while having their skin analysed visually. Information can be shared in real time with their skin specialist Provides an ability to visually 'see' the skin as light sees it and interacts with it on the surface and beneath opens up new diagnosis and treatment opportunities Synergenic tool for integration into the rapidly expanding telehealth platforms out in the market Potential to enable diagnosis of skin conditions as well as setup of pre-signal detection to alert potential skin conditions before they are visibly present. Enable storing of historical sub-skin imaging data through the SAF feature, this allows for image analysis overtime. melanoma, skin, imaging, diagnostic, analysis, microbe, microorganism, bacteria, virus, spectroscopy, smartphone, non-invasive, health, telemedicine, telehealth, dermatology, oncology, phototherapy, photoanalysis, radiology, biopsy, subskin, subsurface, embeddable, camera, microbiome, dermoscopy, cosmetic, optical Infocomm, Video/Image Analysis & Computer Vision, Personal Care, Cosmetics & Hair, Healthcare, Medical Devices, Healthcare ICT

There are 30,000 occupational drivers in Singapore, out of which 13,500 are 45 years old and above. The risk of acquiring cardiovascular disease increases with age and is potentially exacerbated by low physical activity and high emotional stress levels, which are two typical characteristics of occupational drivers arising from their work environment. Low level of physical activity and high stress levels have been shown to have significant relationship with heart rate variability, one of the indicators of cardiovascular disease. This technology is developed to help drivers to monitor their stress level, provide them with instantaneous feedback and the necessary alerts for a timely intervention. This technology offer presents a cross-platform AI system that estimates the stress levels continuously in real time, and can be easily integrated with commercially available photoplethysmography (PPG) wearables, e.g., a PPG wristwatch. In addition, this technology can be adapted for the monitoring of workplace stress with the aim of improving overall mental well-being. The current practice of using electrocardiogram (ECG) to measure the electrical activities of the heart is mainly found in the clinical settings and not easily accessible by the general population due to high costs. The need for an accurate placement of ECG electrodes does not allow the continuous monitoring of the heart condition in a non-clinical setting. It is not easy for individuals to continuously monitor their stress levels at the workplace in daily life, especially for drivers. This technology offer enables continuous, real-time monitoring and is not limited to clinical settings. It is cost-effective without the need to purchase medical grade ECG devices. The solution can be easily customised and adapted to existing and future PPG wearables. It is portable and feasible for all-day monitoring of stress levels and heart conditions in diverse workplace environments. Essentially, it is an algorithm that extracts proprietary features to predict stress levels, with an unique approach, from heart beat signals customised to a given context in the workplace. This facilitates the creation of contextualised stress profiles for specified workplace situations ranging from physical combat conditions to air-conditioned office sedentary conditions. The technology owner is interested to out-license this technology offer. Potential application areas are: Public or private hospitals, clinics, community care centers. Individual drivers and any workers who might be exposed to workplace related stress. Sports sectors including sports training, research and competition. Medical devices, equipment suppliers and manufacturers. Potential products: Existing or future wearables with PPG, e.g., wristwatch, headset, t-shirt, etc. Hardware and platform independent, easy to be incorporated into existing and future wearables. Portable and feasible for 24/7 stress monitoring. Affordable and cost-saving without the need to purchase medical grade ECG devices Real-time monitoring and timely feedback customised for users stress monitoring, ai algorithm, ai system, heart monitoring, workplace stress, wearable technology Infocomm, Artificial Intelligence, Internet of Things, Wireless Technology, Sustainability, Sustainable Living

One use of AI, including deep learning, is in prediction tasks, such as image scene understanding and medical image diagnosis. As deep learning models are complex, heatmaps are often used to help explain the AI’s prediction by highlighting pixels that were salient to the prediction. While existing heatmaps are effective on clean images, real-world images are frequently degraded or ‘biased’-such as camera blur or colour distortion under low light. Images may also be deliberately blurred for privacy reasons. As the level of image clarity decreases, the performance of the heatmaps decreases. These heatmap explanations of degraded images therefore deviate from both reality and user expectations.  This novel technology-Debiased-CAM-describes a method of training a convolutional neural network (CNN) to produce accurate and relatable heatmaps for degraded images. By pinpointing relevant targets on the images that align with user expectations, Debiased-CAMs increase transparency and user trust in the AI’s predictions. Debiased-CAMs are effective in helping users identify relevant targets even on images affected by different clarity levels and multiple issues such as camera blur, poor lighting conditions and colour distortion. The AI’s prediction also becomes more accurate. As the model is trained using self-supervised learning, no additional data is needed to train it.  The training for Debiased-CAM is generalisable, and thus applicable to other types of degraded or corrupted data and other prediction tasks such as image captioning and human activity recognition. Used to train a convolutional neural network (CNN) to produce accurate and relatable heatmaps for degraded images. By pinpointing relevant targets on the images that align with user expectations, Debiased-CAMs increase transparency and user trust in the AI’s predictions. It also increases the ability of meeting regulatory standards to deploy CNN models in the following applications, where explainable AI is required. Healthcare, eg. Radiology Autonomous Vehicles   Produces accurate, robust and interpretable heatmaps for degraded images Works on images with multiple degradation levels and types such as blurring and improper white balance Agnostic to degradation level, so that enhancement can be applied even when the level is unknown Perceived by users to be more truthful and helpful as compared to current heatmaps distorted due to image degradation Method of training can be applied to other degradation types and prediction tasks Explainable AI Infocomm, Video/Image Analysis & Computer Vision, Artificial Intelligence