TECH OFFERS

As the world continues to make strides in artificial intelligence (AI), the need for transparency in the field intensifies. Clear and understandable explanations for the predictions of AI models not only enhances user confidence but also enables effective decision-making. Such explanations are especially crucial in sectors like healthcare where predictions can have significant and sometimes life-changing consequences. A prime example is the diagnosis of cardiovascular diseases based on heart murmurs, where an incorrect or misunderstood diagnosis can have severe implications. The technology, DiagramNet, is designed to offer human-like intuitive explanations for diagnosing cardiovascular diseases from heart sounds. It leverages the human  reasoning processes of abduction and deduction to generate hypotheses of what diseases could have caused the specific heart sound, and to evaluate the hypotheses based on rules. The technology tests which murmur shapes are present in the heart sound to determine the underlying cardiac disease. This approach of abductive-deductive AI reasoning can also be applied to other diagnostic or detective tasks. DiagramNet uses deep learning AI to perform four key steps: ‘Observe event’ by observing displacement to interpret its amplitude, murmur location, and the heart phase in which the murmur occurred. ‘Generate plausible explanations’ by listing possible diagnoses, retrieving respective murmur shape functions, and initialising their corresponding shape hypotheses. ‘Evaluate plausibility’ by fitting each hypothesis to the observation, evaluating the rules in terms of shape goodness-of-fit in conjunction with matching the murmur heart phase. ‘Resolve explanation’ with the hypothesis-fitted inference and the initial inference to make a final inferred diagnosis. By offering clinically relevant explanations in an accessible format, DiagramNet bridges the gap between complex AI predictions and user understanding, fostering trust and actionable insights in critical healthcare applications. Many existing AI models struggle to provide meaningful and easily interpretable explanations—they are either too technical or too simplistic. As such, there is an opportunity for a novel AI model that can generate thorough and easily understandable explanations. In the medical field, diagrams can be particularly beneficial when it comes to illustrating complex observations and making interpretations more accessible to non-technical users and patients alike. Enhances interpretation of AI decisions through a design framework for diagrammatic reasoning. Accelerates and strengthens the adoption of AI technology by leveraging diagrams that adhere to domain conventions. Presents a diverse array of explanation types, namely, abductive, contrastive and case-based explanations. Facilitates trust and consistency in AI-based cardiac diagnosis by providing murmur diagrams which are a universally understood tool among clinicians. Explainable Artificial Intelligence, Healthcare ICT Infocomm, Artificial Intelligence

In a world where resources are diminishing and demands are rising, the value of land has significantly increased for clean energy and food production. Agrivoltaic farming represents a potential game-changing solution that can bring substantial benefits to both the energy and food sectors. The patented technology is a tubular solar photovoltaic (PV) module designed for agrivoltaic farming. The unique tubular nature of the system allows sunlight, water, and wind to reach the plants below while simultaneously harnessing solar power. Moreover, the tubular modules can provide consistent partial shading to protect the plants and reduce ambient temperature and ground moisture loss. This technology enables the dual use of land by integrating agricultural activities such as farming and gardening with solar power generation, maximising the value derived from the limited land. The combination of energy harvesting and agriculture has significant potential to improve farming productivity, increase land-use efficiency, reduce carbon emissions, and promote environmental sustainability. The technology owner is keen to collaborate with partners interested in agrivoltaic farming like farmers, gardeners, agritech companies, research centres, and ministries to test-bed and adopt their tubular solar PV technology. The technology owner is also seeking industrial partners (e.g., manufacturers, system integrators, architects, designers, etc) to co-develop a complete solar energy solution or integrate the tubular solar PV modules into specific use cases. The technology owner has developed an innovative tubular solar PV module that integrates flexible thin-film solar PV stripes into glass tubes arranged in parallel. The unique design allows for the permeation of sunlight, rain, and wind through the module. The key features of this technology are: Efficient sunlight utilisation: unique design allows it to capture more direct sunlight for electricity conversion Sunlight and rainwater permeability: increase productivity and crop yields Wind permeability: enable the usage of structures with lower load bearing, reducing the system cost Partial cooling shading: reduce moisture loss and protects the plants from excessive solar radiation Consistent protection: protect the plants below from heavy rain and hail damage Long-term reliability: monolithic PV cells continue work when partially damaged or shaded Self-cleaning capability due to cylindrical shape: reduce maintenance cost compared to conventional panels Modular design with various sizes: allow customisation for specific requirements and facility scalability Horizontal solar PV elevation: enable simple and fast installation (seamless array over large area) The potential applications include but are not limited to: Farms (agriculture, aquaculture, viticulture, horticulture, etc.) Gardens (open gardens, green roofs, etc.) Building façade and rooftop Greenhouses Natural parks, reservoirs, and lakes Other applications (EV charging stations, outdoor canopies, cabanas, pergolas, etc.) The patented technology offers the following unique features: Maximised land-use efficiency: dual use of the land High energy efficiency: constant direct sun exposure Optimised plant growth: light, water, and wind permeability High reliability and good long-term performance Low operating expense (OPEX): negligible maintenance Agrivoltaic Farming, Agrophotovoltaics, Agrisolar, Dual-Use Solar, Ultra Low Light Sensitive PV, Agrivoltaics Energy, Solar, Sustainability, Low Carbon Economy

Rising energy consumption and electricity costs pose significant challenges for all businesses, from light commercial to heavy industrial sectors. Moreover, sustainability has become a crucial component of corporate strategies, particularly within the framework of environmental, social, and governance (ESG). Electrical energy optimisation is not just about cost savings, but also an approach towards resource conservation, power stability, equipment protection, as well as sustainable development. The technology owner has developed a transformer-based voltage optimisation system to reduce energy consumption, optimise electrical power supply, extend equipment lifespan, and lower carbon emissions. This patented technology can control the voltage to an acceptable minimum level and keep the current within the optimum range for best efficiency, providing an immediate and practical way for energy savings. The technology owner is keen to collaborate with industrial partners such as building management, property owners, industrial facility management in manufacturing sectors, etc. The technology owner is also seeking OEM partners to integrate this technology into building management systems (BMS) or co-develop a complete energy saving solution. The core of this technology has the electronic controller regulating the direction of the current in the coil, balancing the phase voltage, and filtering the harmonics from reactive loads, to sustain the highest performance while minimising power loss. The features of this technology are: 8 – 12% reduction in power consumption and electricity bill Improve the quality of overall electrical power supply Over-voltage protection to prolong equipment lifespan Real-time remote monitoring and analysis by app Compact and modular design (easy installation and fast repair) Compatible for both indoor and outdoor installation Enable scalable and customisable adoption for property portfolios Completely self-sufficient solution with virtually unlimited lifespan The voltage optimisation system is applicable for both commercial and industrial applications, especially industrial sectors with energy intensive equipment like motors and cooling devices. The potential applications include but are not limited to: Commercial buildings (shopping malls, office buildings, markets, restaurants, hotels, etc.) Industrial facilities (factories, warehouses, chemical plants, fabrication plants, etc.) Other infrastructures (airports, hospitals, train stations, sports complexes, institutes, etc.) The patented technology offers the following unique features: 8-12% immediate energy savings High efficiency of 99.7% with low system losses Reduce maintenance cost by increasing equipment lifespan Remote monitoring for smart energy management Return on Investment (ROI) in 12-24 months Voltage Optimisation, Energy Saving, Cost Reduction Energy, Sensor, Network, Power Conversion, Power Quality & Energy Management, Electronics, Power Management, Sustainability, Low Carbon Economy

Recently, the rising adoption of Internet of Things (IoT) devices and portable electronics has made electronic waste (e-waste) pollution worse, especially when small and low-power IoT devices are single-use only. As such, low-cost and environmentally friendly power sources are in high demand. The technology owner has developed an eco-friendly liquid-activated primary battery for single-use and disposable electronic devices. The battery can be activated by any aqueous liquid and is highly customisable to specific requirements (i.e., shape, size, voltage, power) of each application. This thin and flexible battery can be easily integrated into IoT devices, smart sensors, and medical devices, providing a sustainable energy solution for low-power and single-use applications. The technology owner is keen to do R&D collaboration and IP licensing to industrial partners who intend to use liquid-activated batteries to power the devices. The technology is a single-use and non-rechargeable battery that can be instantly activated by any aqueous liquid (e.g., water, fruit juice, soft drink, etc.) as well as all types of body fluids (e.g., blood, saliva, urine, sweat, bile, etc.). The features of this technology are: Customisable shape, size, and power (1.5 to 6.0 V at 4 to 50 mW) Ultra-thin and flexible (<1 mm in thickness) Lightweight (when dry) High energy density (less than 5 mm2 for low-power application: 1.5 V, 2 mAh) Indefinite pre-activation shelf-life (no self-discharge) Non-toxic and biocompatible (safe for human beings) Environmentally friendly (no disposal pollution) This inherently safe and non-toxic battery can be widely applied in MedTech applications, disposable IoT, smart sensors, and low-power electronics. The potential applications include but are not limited to: Medical devices: digital pills, ingestible sensors, smart bandages, wearable biosensors, in-vitro diagnostics (IVDs), body fluid testing, etc. Disposable IoT: Bluetooth Low Energy (BLE) chips, microprocessors, wireless sensors (pH, temperature, humidity), micromotors, LEDs, heaters, etc. Other low-power electronics: smart labels, electronic skin patches, cold chain monitoring, smart packaging, etc. The technology offers the following unique features: Highly customisable for different applications Thin and flexible (adaptable to various designs) Long shelf-life (can be sealed for a very long time) Biocompatible (can be safely consumed) Environmentally friendly and non-toxic The technology owner is keen to do R&D collaboration and IP licensing to industrial partners who intend to use liquid-activated batteries to power the devices.  Primary Battery, Environmentally Friendly, Non-Toxic, MedTech, Disposable IoT Energy, Battery & SuperCapacitor, Healthcare, Medical Devices, Infocomm, Internet of Things

Despite the increasing prevalence of obesity, all FDA-approved medications, which act indirectly on the central nervous system to suppress appetite or on the gastrointestinal tract to inhibit fat absorption, suffer from poor effectiveness and side effects. Most of these medications have been withdrawn from the market. Although liposuction performed in clinics can effectively remove targeted subcutaneous fat, it suffers from invasiveness, high costs, associated risks, induction of compensatory increase of visceral fat. Although thermal lipolysis induced by high-power laser energy is a non-invasive way to reduce subcutaneous fat, its effectiveness is limited and it often causes skin burning. Both liposuction and laser lipolysis cannot improve whole-body metabolism. The technology owner has developed a transdermal mild photothermal therapy directly acting on the root of evil, i.e. subcutaneous fat, to induce its ameliorating remodelling (browning, lipolysis, angiogenesis, and apoptosis), based on the injectable hydrogel encapsulated with photothermal agent. Browning refers to the conversion of energy-storage white fats into energy-burning brown fats. Further, combining with pharmaceutical therapy by codelivery of pharmacological agent leads to a strong therapeutic synergy. This method not only ensures high effectiveness and low side effects due to localized and targeted application but also remotely creates significant improvements in whole-body metabolism (e.g., reduction of visceral fat, relief of diabetic symptoms). In addition, this technology is applicable for cosmetic purposes, e.g., body contouring and reduction of double chin. The technology owner is seeking potential biotechnology companies, clinicians, and other partners to clinically translate and commercialize this technology. Possible modes of collaboration include R&D, process, and product development. Photothermal agents and pharmacological agents are encapsulated in biocompatible and biodegradable hydrogel which retains the therapeutics to ensure sustained effects. After being injected into subcutaneous fat depots (e.g., belly fat) using an insulin needle or an automated injection device with minimal pain, NIR irradiation at each injection site will be applied for only five minutes using a portable laser source, one to three times a day for several days without the need of another injection. This described procedure (injection + laser treatment) can be applied once or several times. Obvious mass reduction of the treated fat and other beneficial effects on the whole-body should be resulted. In contrast to laser lipolysis, this procedure shall be much more effective, pain free without causing skin burning, and profoundly beneficial. It can be conducted in clinics by professionals or be self-administered at home for long-term care. The primary application area of our technology is for treating obesity and associated metabolic diseases (e.g., type 2 diabetes). This technology can also be used for non-therapeutic or cosmetic purposes, including contouring, sculpting, or slimming one or more regions of the subject’s body for a desirable appearance. To be specific, this technology can locally remove stubborn fat below the chin, or in thigh, abdomen, thorax, flank, upper limb, upper body, lower limb, back, etc.   As highlighted by Mordor Intelligence, the anti-obesity drugs market was valued at about US$ 1,690 million in 2020, and it is expected to reach US$ 4,250 million in 2026, registering a CAGR (compound annual growth rate) of 15% over the forecast period, 2021-2026. And according to IMARC Group, the global body contouring market reached a value of US$ 7.3 billion in 2021, and is expected to reach US$ 11.1 billion by 2027, exhibiting at a CAGR of 6.9% during 2022-2027. This technology provides an unprecedented solution with high effectiveness and low risks. Non-invasive targeted treatment on subcutaneous fat Drastic reduction of subcutaneous fat and visceral fat Relief of obesity-associated metabolic diseases (e.g., diabetes) Low risks and low side-effects High effectiveness Self-administrable Obesity, Diabetes, Metabolic Diseases, Transdermal Therapy, Personal Care, Slimming Healthcare, Medical Devices, Pharmaceuticals & Therapeutics

The latest Singapore National Population Health Survey has reported a concerning diabetes trend. From 2019-2020, 9.5% of the adults had diabetes, slightly dropping to 8.5% from 2021-2022. About 1 in 12 (8.5%) of residents aged 18 to 74 were diagnosed, with an age-standardised prevalence of 6.8% after accounting for population ageing. Among the diabetes patients, close to 1 in every 5 (18.8%) had undiagnosed diabetes, and 61.3% did not meet glucose control targets. Prediabetes is also prevalent, with 35% progressing to type 2 diabetes within eight years without lifestyle changes. Untreated Type 2 diabetes can lead to severe health issues. Tackling this challenge requires a holistic approach, focusing on awareness, early diagnosis, and lifestyle adjustments for diabetes and prediabetes. Recognising the need for innovation to address this, the technology owner develops a cost-effective and non-invasive AI-powered solution, Blood Glucose Evaluation And Monitoring (BGEM), that detects glucose dysregulation in individuals to monitor and evaluate diabetic risks. BGEM allows users to track their blood glucose levels regularly, identify any adverse trends and patterns, and adopt early intervention and lifestyle changes to prevent or delay the onset of diabetes. Clinically validated in 2022, with a research paper published in October 2023, the technology is open for licensing to senior care/home care providers, telehealth platforms, health wearables companies, and more. The BGEM technology is an end-to-end managed AI platform that leverages Photoplethysmography (PPG) enabled wearable sensors to monitor various heart rate variability (HRV) features associated with blood glucose fluctuation. The solution comprises the following features: Optimised and validated AI algorithm Mobile Demo App Including UI/UX design guideline User-friendly visualisations SaaS Scalability Security API Integration The BGEM technology offers a cost-effective, non-invasive approach to predicting an individual's diabetes risk. The applications include: Population Health Perspective: The technology leverages the high growth rate of smart wearables and hearables, presenting an opportunity to identify undiagnosed diabetes individuals within the population. Preventive Health Monitoring: With the ability to monitor blood glucose changes regularly at minimal cost, the technology empowers high-risk users to adopt a healthier lifestyle and, therefore, prevent or delay the onset of diabetes. Diabetes around the world in 2021: 537 million adults (20-79 years) are living with diabetes, 1 in 10. This number is predicted to rise to 643 million by 2030 and 783 million by 2045. Over 3 in 4 adults with diabetes live in low- and middle-income countries. Diabetes is responsible for 6.7 million deaths in 2021 - 1 every 5 seconds. Diabetes caused at least USD 966 billion dollars in health expenditure – a 316% increase over the last 15 years. 541 million adults have Impaired Glucose Tolerance (IGT), which places them at high risk of type 2 diabetes. Overview of the wearable technology market: The market is projected to expand at a compound annual growth rate (CAGR) of approximately 12.5% between 2023 to 2030. Estimated to be worth USD 55.5 billion in 2022, with a projected revenue of USD 142.4 billion by 2030. Current blood glucose monitoring technologies either require finger pricking for blood extraction or the insertion of sensors into the skin and discomfort through wearing patches for extended periods. Instead, the technology uses external sensors and algorithms to detect and predict diabetes risk. No object needs to be inserted into the user's body or continuously worn throughout the day, resulting in minimal pain and discomfort. Additionally, the only equipment required for testing is the wearable device. No additional disposable equipment needles or test strips are needed, which makes blood glucose monitoring much more convenient and cost-effective than other "State-of-the-Art" solutions. The Unique Value Proposition of BGEM include: Market-ready: It is a market-ready non-invasive diabetes risk detection and prediction AI solution that leverages consumer-grade wearables to detect blood glucose dysregulation. Performance: Demonstrates outstanding prediction and detection capabilities. Cloud-based: Operates on a cloud-based platform for seamless integration. Third-party compatibility: Easily implemented with third-party devices and apps. Sustainability: Reduction in bio-medical waste such as needles, test strips etc User-friendly: Non-invasive, convenient and allows frequent measurement. Non-invasive measurement, blood glucose, diabetes mellitus, preventive healthcare, AI, ML, Wearables, PPG, Blood Glucose Monitoring, Diabetes Monitoring, Diabetes Evaluation, Non-Invasive Diabetes Monitoring, Diabetic Risk Assessment Infocomm, Artificial Intelligence, Healthcare, Diagnostics

In Singapore, more than 30,000kg of okara are generated from soya milk and tofu production. Due to the high amount of insoluble dietary fiber and a unique, poignant smell of okara, it is often discarded as a waste product. Despite okara's low palatability, it is rich in nutrients. Therefore, the technology owner has developed a cost-effective formulation to include okara in feed for abalone. The formulation can potentially be adapted and customised for other aquatic species. The technology owner is seeking potential partners to license and commercialise the technology. The technology allows for an alternative nutrient source for animal feed allowing for the sustainability of food supply and reduction of food waste. The formulation consists of a cost-effective plant-based functional ingredient, lowering the costs of feed for aquaculture farms. The nutritional composition can be tailored for different species to increase growth rates and survivability. Okara is used as a cost-effective feed for high-value abalone, a commonly cultured species of mollusc. Okara-based feed results in the beautiful purple colouration of the shell and increased growth and survivability of abalone. In comparison, the okara-based feed costs ~30% less than commercial feed used in the industry. There is potential for okara to be included in feed for other aquatic species such as shrimp and fish. The success of this method will valorise okara, transferring them into a nutrient-dense aquatic feed while promoting a more environmentally sustainable food production chain.       okara, aquatic feed Foods, Ingredients

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

Lists are an indispensable part of the online experience, often used to show many results, such as products, web pages, and food dishes. These items can be neatly sorted by a desired attribute like price, relevance, or healthiness. Listed items often have multiple attributes. However, instead of being able to sort multiple attributes simultaneously, consumers are currently limited to sorting only one attribute at a time. This makes searching for the desired item tedious and confusing. Imma Sort supports interpretable and multi-attribute sorting. Sorting for two or more attributes is possible. In contrast to existing search technology, Imma Sort trades off the smoothness of the sorted trend for the main attribute to increase ease of prediction for other attributes, by sorting them more approximately. Results for specific attributes can be made smoother by setting higher importance weights. Provides intuitively sorted results sorted by two or more attributes to improve decision-making and user experience Results can be customised by allocating higher weightage for selected attributes Enables users to perform multi-attribute sorting in any existing list interface without requiring sophisticated spreadsheets or data visualisations Can be integrated into search and recommendation systems across a wide range of applications Can also be incorporated into various search and recommendation systems for more effective search results. Examples of possible applications: Food dishes can be sorted by healthiness and tastiness Hotels can be sorted by price and distance Sorting by price and rating would generate results that generally trend in one direction for both attributes. This makes it easy for users to anticipate the values of multiple attributes as they move down the list, without having to construct a mental list for the secondary attribute. By decreasing users’ mental effort, this will improve decision-making and increase satisfaction. Multi-Attribute Sorting, e-commerce, algorithm Infocomm, eCommerce & ePayment, Enterprise & Productivity