TECH OFFERS

Mixed plastic waste is an abundant resource containing approximately 7-12 wt.% hydrogen (H2). Traditionally, hydrogen is produced from non-sustainable fossil feedstock, such as natural gas, coal and petroleum oil. This technology offer is a thermo-catalytic process that sustainably recovers hydrogen from plastic waste instead. During hydrogen recovery process, instead of releasing carbon dioxide (CO2) that causes greenhouse gas effect, the technology converts emissions into a form of solid carbon, called carbon nanotubes (CNT). Solid carbon is easier to store and handle compared to the gaseous carbon dioxide. Furthermore, carbon can be sold as an industrial feedstock for manufacturing of polymer composites, batteries, concrete, paints, and coatings. With over 150-190 million tonnes of mixed plastic waste ending up in landfills and our environment annually, the technology offers a sustainable solution for the elimination of plastic waste and decarbonization while providing a clean hydrogen supply. Thermo-catalytic production of hydrogen. The hydrogen gas stream produce contains a purity of 60 – 70 vol% for downstream applications. Further purification can be conveniently achieved by conventional separation technologies, such as membranes and pressure swing adsorption Output of hydrogen can be from 500 – 100 kg to 2500 – 5000 kg/day Mixed and contaminated plastic waste can be used as feedstock (eg. municipal plastic waste, flexible laminate packaging waste, marine plastic litter, sorted polyethylene and propylene waste etc.) Hydrogen recovery from plastic waste is up to 70-150 kg hydrogen from 1 tonne of plastic waste, depending on composition and purity of feedstock The maximum amount of greenhouse emissions that can be captured during hydrogen recovery are 2.5-3.4 tonnes CO2 equivalent per 1 tonne of treated plastic waste (subject to plastic waste composition). Carbon is captured in a solid form (CNT), which is easier to store than gaseous greenhouse gas emissions This technology offer is applicable for industries that are keen to recycle plastic waste or looking for alternative clean generation of hydrogen. The potential applications include: Plastic material reprocessing facilities Waste management companies Hydrogen production companies Sustainable production of hydrogen using plastics Reduction of plastic waste pollution No CO2 generated (carbon captured as CNT) Non-selective feedstock (mixed and contaminated plastics can be used) Hydrogen, Hydrogen recovery, Carbon capture, Storage, Decarbonisation, Plastic waste, Sustainability, Recycling, Energy Energy, Waste-to-Energy, Waste Management & Recycling, Sustainability, Circular Economy, Low Carbon Economy

Traditionally, companies which deploy various assets in the field have to manually locate them to either service them, or just to find out where they are to collect them. Examples of these assets could be movable types like supermarket trolleys, delivery vehicles, hospital wheelchairs, etc., or non-movable types like machinery and equipment. By attaching small, IoT-based tracking devices to these assets, the asset owner will be able to track and locate them automatically. In addition, the operating status and physical parameters of the asset can be measured by additional sensors embedded into the tracking device. These location and condition data gathered by the asset tracking device can enable further downstream decisions to be made. For example, process enhancement such as predictive maintenance, real-time inventory management, or a simple track and trace operation, etc. Human-based errors can be minimised, increasing operational efficiency. This technology offer is an IoT-based asset tracking device that is fully customisable to perform various additional sensing functions. The device is also capable of monitoring its own operating conditions and associated environmental parameters. The technology owner is keen to do R&D collaboration with application developers from industries such as asset management, equipment management, logistics and the hospitality industry. The main features of the asset tracker device are: Communications range up to 10 km (within cellular coverage) Temperature range between -40 to 80 deg Celsius Battery life of 5 years Communication using NB-IoT or LTE-M Cloud-based data storage Web-based dashboard Miniature, compact size  Adaptable for all kinds of sensors Automatic alerts using email and other messaging services if the location is out of range, exceeds the boundary conditions, and weak battery power  This technology offer can be deployed in the following applications. Logistics, Last-mile delivery Fleet management Equipment management Industrial automation This technology offer can be customised further to include other sensors and different communication protocols.  The asset tracking device offers: Ultra low power operation; long battery life of more than 5 years for certain deployments Fully customisable with various sensors and different communication protocols The technology owner is keen to do R&D collaboration with application developers from industries such as asset management, equipment management, logistics and the hospitality industry.   Electronics, Sensors & Instrumentation, Embedded Systems, Infocomm, Geoinformatics & Location-based Services

The human nose has 400 different types of odour receptors yet has the ability to recognise about 10000 different smells. Currently, there are different artificial methods that can be used to sense various odours by detecting volatile organic compounds (VOCs). However, many of these methods detect a single type of VOC at any one time or detect the whole VOCs without identification, are often expensive, time-consuming, or require skilled laboratory personnel to perform the procedure. This technology offer is a novel Artificial Olfactory Sensor (AOS) system with pattern recognition using artificial intelligence (AI). This system can simultaneously detect multiple VOCs, and is able to classify the odours through AI techniques. The sensor can detect at concentration as low as 1ppb (parts per billion) and provides a fast sensing speed at 10 second/cycle.  The patented technology can be used in food quality evaluation, air quality evaluation or human healthcare diagnostics. The sensor consists of 16 elements and each of them have different receptors that response to various odour molecules. This will allow the sensor system to classify and identify more than 100 VOCs through machine learning. The system is customisable to include more sensor elements for further application development.   The sensors can be placed in multiple areas. The high sensitivity allows it to detect odours accurately even in wide spaces. Hence, it can be used to monitor and detect odours in public spaces, hotel rooms, public transportation, etc. The high-speed detection system allows it to operate in real time, and in a non-destruction manner; sample pre-treatment is not required. The technology offer can be implemented in the following applications: Healthcare diagnostics by detection of VOCs from the body  Health/ well-being monitoring by detection of VOCs from the body  Non-invasive food quality control during manufacturing or distribution Real-time alcoholic fermentation monitoring Air quality control e.g., in restaurants, schools or offices Ripeness/maturity check for fruits (e.g., avocado, strawberry) Detection of meat spoilage Reactor monitoring in chemical industry This AOS has broad applications. It can be further developed for specific applications through sensor customisation and machine learning techniques High speed and sensitive detection No sample pre-treatment required Real time, non-invasive and cost effective method, which can be used to classify large groups of VOCs The technology owner is interested to do R&D collaboration with companies working in odour detection from various industries, e.g., food industry, smart buildings, healthcare, energy and environment, etc. Electronics, Sensors & Instrumentation, Infocomm, Artificial Intelligence, Healthcare, Diagnostics, Foods, Quality & Safety, Environment, Clean Air & Water, Sensor, Network, Monitoring & Quality Control Systems

With the increasing global prevalence of gastrointestinal disorders, the rise in the geriatric population, and the preference for minimally invasive techniques by patients for diagnosis, the demand for capsule endoscopy is expected to grow to $1.2 billion by 2026. But the process of detecting lesions or abnormalities from the images taken by the capsule endoscope is very tedious, time-consuming and error-prone. It takes about two hours for a doctor to read an image due to which the missed diagnosis rate could be high. This technology offer is an AI platform that assists with the clinical diagnosis of endoscopy images and it comprises three deep learning networks that can be used to classify vascular lesions/inflammation, improve the image quality of the area of interest, and upscale the image resolution. This technology comprises three deep learning networks: A lesion classification network that can be used to classify vascular lesion images, inflammatory images, and normal images with more than 95% accuracy A segmentation network that can be used to clarify the location and area of the lesions with an Intersection-of-Union (IOU) of more than 85% A super-resolution network that enlarges the resolution to twice its original resolution, resulting in clearer images This technology comprises several neural networks that assist doctors/clinicians in hospitals and clinics which use capsule endoscopy techniques to capture images of the gastrointestinal track. It augments the clinician's workflow by reducing the cognitive load of locating lesions, it therefore reduces the time taken for diagnosis and improves the overall accuracy of diagnosis. Supports clinicians by pre-classifying large volumes of images captured by capsule endoscopes Aids clinicians in rapidly localising potentially problematic areas within captured images Improves the quality of images to facilitate accurate diagnosis The technology owner is interested in collaboration/co-development/customisation of the technology into a new product or service. Infocomm, Video/Image Processing, Artificial Intelligence

This technology offer is an Intelligent IoT Vertical Farming system, which is designed to be 4-tiered and mobile, for either indoor or outdoor farming. It uses a hydroponic system that grows plants by enhancing the photosynthetic process.  Since the system does not use soil, it is cleaner and more hygienic. FDA-approved and organic mineral nutrients are used for the hydroponic growing.  Compared to traditional agriculture, the vertical farming implementation saves more than 90 percent land area needed, while harvesting 80 percent more per unit area. Furthermore, with the water recycling design, the system achieves a reduction of 70 to 85 percent water usage.  The set-up therefore, promotes the “Go Green” initiative and contributes towards Singapore’s effort to reduce our carbon footprint.  In summary, the following is achieved: More than 90% land savings with more than 80% physical spaces unlocked. 70-85% water savings. Reduced wastages of fertilizers and nutrients. The main features are: The system automatically monitors temperature, humidity, CO2 level in the environment and maintains optimal conditions for the growth of vegetables. The system reduces maintenance costs by automatically controlling lighting and watering, and reducing water usage by recycling. The system incorporates a mobile-enabled dashboard that enables owners to monitor the growth of their crops and receive alerts when anomalies occur. The technology owner is keen to customise, out-license or test-bed this technology with the following potential collaborators: Food and Agricultural Industries Institutions (such as secondary schools, IHLs) Offices and shopping mall owners with spare land/space HDB roof-top carparks and gardens Warehouses with spare spaces Private Estate Owners The technology owner has been working closely with various partners to bring this affordable and IoT-enabled vertical farming solution to consumers, such as public housing owners and private estate owners, as well as urban farming industries. The system has also been deployed at a few Ministry of Education secondary schools.   System is suitable for: Urban Farming Industry companies HDB Owners Private Estate Owners Resizable to satisfy the requirements of consumers Portable and compact size system Bespoke large sized system Cost will vary based on system size IoT-Enabled automated system Environment control Monitor & Alert system Cleaner environment (No pests) Increase yield of crops Less land/space required Less water, fertilizers & nutrients required Crops grown are organic The system is suitable for: Urban Farming Industry companies HDB Owners Private Estate Owners The system is resizable to satisfy the requirements of consumers, and the cost will vary based on system size, which can be: Portable and compact size system Bespoke large sized system Urban farming, Vertical Farming, Go Green, hydroponic Infocomm, Internet of Things, Smart Cities, Sustainability, Food Security

Transparent conductive films have the function of transmitting both electricity and visible light. Indium tin oxide (ITO) has been widely used as a transparent electrode, but it is not able to meet the demand for lower resistance required in recent years. Metal mesh has been developed as an alternative, but there is a trade-off between lower resistance and finer wiring lines. When a large size is required, transmissivity has to be sacrificed by the increased line width to lower the resistance. The technology owner has developed a double-sided metal mesh-based transparent conductive film using a unique roll-to-roll manufacturing process to achieve a high wiring aspect ratio, low electrical resistance, and high transmissivity at the same time. It also has a very high planarity of the film surface, ensuring stable performance and quality when used as a transparent electrode for thin film applications. This technology is a unique manufacturing process for making metal mesh-based transparent conductive films with high light transmissivity and low electrical resistance. The technical features and specifications are listed as follows: Super-fine line width of 2 µm or less Low sheet resistance of 2 Ω or less (when transmissivity is 89%) Unique wire forming method (embedded in substrate film) High aspect ratio wiring to achieve low resistance maintaining high transmissivity Various base film materials (Polyethylene terephthalate (PET), polycarbonates (PC), cyclic olefin polymer (COP)) Single side and double side patterning available Supply form: roll form and sheet form available (max size 580 x 700 mm) Transparent conductive films have a wide range of potential applications in various industries, where the combination of transparency and conductivity is required. The potential applications include but are not limited to: Transparent touch sensor for electronics, automotive and medical devices Transparent display for AR headsets, smart glasses, and digital signage Transparent heater for sensing camera, LiDAR, and surveillance camera High frequency tele-communication: Transparent antenna for 5G/6G communication Meta-surface radio wave reflector Transparent electrodes: Flexible photovoltaics (PV) solar cell Light control panel and window Transparent electromagnetic interference (EMI) shield Transparent biochip for in-vitro diagnostic and monitoring Combine low electrical resistance and high light transmissivity Unique wire forming method and roll-to-roll manufacturing process Wide choices of base film materials (PET, PC, COP) Adaptable to various applications: touch screen, large-size and flexible display, defogging heater, high frequency tele-communication, high efficiency solar cell, quick response light control panel, etc. The technology owner is keen on R&D collaborations with partners who are interested in adopting the transparent conductive film in their products and applications. Transparent Conductive Film, Transparent Electrode, Metal Mesh, High Transmittance, High Transmissivity, Low Resistance, High Aspect Ratio, Flat Surface, Touch sensor, Photovoltaics Electronics, Display, Infocomm, Mobility, Energy, Solar, Radio Frequency, Sustainability, Low Carbon Economy

Image annotation is a critical step in developing computer vision and image recognition systems. Image annotation can be used in applications in a spectrum of deep-tech pillars such as Healthcare/Medical (detecting and diagnosing diseases from radiology or pathology images), Manufacturing (defect detection from image scans), Agritech (plant/crop health check via images and photos), and more. As a result, image annotation is critical in developing Artificial Intelligence/ Machine Learning (AI/ML) models in a variety of fields. The role of image annotation in deep learning has changed over time. Today, image annotation has become more important for object recognition with new characteristics and capabilities in real-world settings. However, manual labeling of complex objects continues to be time-consuming, tedious, and error-prone - additionally, outsourcing these labeling tasks might not always be the best way due to domain-expertise required in labeling complex image data e.g. radiography images or surface defects on semiconductors. This technology offer is an AI-assisted image labelling tool that enables technical teams to collaboratively, quickly, and easily label large image datasets with pixel-level accuracy masks. As the tool is industry agnostic, it can be used by any industry with a minimal learning curve. The technology owner is keen to work with companies who are looking to build out datasets / ground-truths / and labels for building deep-learning experiments and capabilities, through R&D collaboration and licensing opportunities. The features of this technology are as follows: AI-Assisted Labelling Most datasets are huge with complex geometries. The AI-Assisted labelling feature within the tool uses a mixture of contour analysis methods and deep-learning to label these datasets within a few clicks per image with pixel-level accuracy. Users just need to click on the area of interest and the corresponding masks around the object of interest will be automatically generated. Industry Agnostic The image labelling process is industry agnostic and works with most 2-dimensional (2D) RGB image types (JPG, PNG, etc) - the tool has already been used in computational pathology, manufacturing, and inspection use-cases. General Specifications Works on 2D RGB Images (or converted from other spectrums) Supports Polygon, Bounding Box, Mask labels Exportable to major annotation formats e.g. COCO JSON, LabelMe, PascalVOC, COCO MASK, CSV Width-Height, etc Supports immediate model training with MaskRCNN, DeepLabV3 with "One-Click Train" feature One of the issues faced by researchers, machine learning, and data scientists is that labeling data can be tedious and time-consuming. The tool seeks to help them label data much faster - using only a few clicks to generate near pixel-perfect masks for your data.  Teams have been able to label thousands of medical images within a week using our automated segmentation algorithm and fully-online tool to improve collaboration amongst the labeling team and supervisors.  Computational Pathology and Medical Imaging Disease Detection and Identification (Tumour Lesion, Fracture, Foreign Objects) from X-Ray / MRI Machines Anomaly Detection in Blood Cell Scans / Pathology Scans Manufacturing  Multi-Class Materials Defect Detection (Semiconductors, Materials, Fabrication Quality Assurance, etc) Assembly Parts Identification and Counting Material Defects Labeling  Cracks / Rust / Anomaly Labelling from X-Ray / RGB Images Agriculture and Food Technology Crops and Food Grading Crops / Trees Labeling Food Inspection Data Labeling Others Construction Site Management Smart City Use Cases (Human Monitoring, Crowd Controls, Carpark Capacity Scanning System) The global data annotation tools market size was valued at USD 629.5 million in 2021 and is anticipated to expand at a compound annual growth rate (CAGR) of 26.6% from 2022 to 2030. The growth is majorly driven by the increasing adoption of image data annotation tools in the automotive, retail, and healthcare sectors - the demand for annotation tools is soaring because of the need to reinforce the value of data in these industries. Additionally, the global data collection and labeling market size was valued at USD 1.67 billion in 2021 and is expected to expand at a compound annual growth rate (CAGR) of 25.1% from 2022 to 2030. The market is expected to witness a surge in the adoption of the technology owing to benefits such as extracting business insights from socially shared pictures and auto-organizing untagged photo collections. It also contributes to developing enhanced safety features in autonomous vehicles, such as condition monitoring, terrain detection, wear detection, and emergency vehicle detection. Machine Learning has been incorporated in various industries, including facial recognition on social networking websites, automated picture arrangement on visual websites, and robotics and drones. Helps teams label data much faster - an AI-enabled segmentation tool that uses only a few clicks to generate pixel-perfect masks for your data. Completely online, no additional plug-ins are required - labelling is done in a web browser, and can be performed collaboratively within the team or with an offshore workforce Medical data for example, require years of expertise to label correctly - this tool allows professionals such as doctors, and researchers to label data 10 times faster. Does not require learning any proprietary software (minimal learning curve) Allows teams to quickly train powerful AI models after data-labeling for an end-to-end workflow as images are taken as inputs, and trained deep-learning models are generated as outputs (FasterRCNN, MaskRCNN, DeepLabV3, YOLO etc) Supports the generation of labeled files for multiple popular frameworks Artificial Intelligence, Deep-Learning, Data Labeling, Machine Learning, Computer Vision, Instance Segmentation, Medical Imaging, Defect Detection Infocomm, Video/Image Analysis & Computer Vision, Artificial Intelligence

Singapore is currently only producing 13% of its vegetable consumption. With little farming land available, Singapore relies heavily on imports from other countries. Due to increasing focus on food security, the alternative to solve land scarcity problem is to build greenhouses on concrete rooftop. Although concrete rooftop greenhouse are able to keep pests out, there is a signifcant heating problem which severely inhibits the growth of the vegetables. Therefore, there is a need for a rooftop greenhouse that is able to actively cool itself to avoid such problem. This technology offer is a modular rooftop greenhouse farming system (hydroponics) capable of producing vegetables on concrete roofs to meet the local demand while reducing over-reliance on imports. The design of the greenhouse farming system enables cooling and does not heat up, thus allowing the growth of pest-free vegetables. The system is approximately the size of a typical carpark lot (2.5 x 5 m). The production rate is 30 kg per month (2.5 x 5 m size) and requires minimal human intervention. The technology offer comprises both the farming system and its operation know-how. The modular rooftop greenhouse farming system can be set-up within 3 days or scaled-up when required with guaranteed vegetable growth. The break-even cost of one greenhouse is about 3 years. The technology owner is seeking to out-license their technology. This technology offer is a temperature regulated and modular farming system (hydroponics) for rooftop farming. The features and specifications are as follows: Modular and scalable Flexible sizes (as small as 2.5 x 5 m) 30 kg/month (2.5 x 5 m size) Active cooling design (20% reduction in temperature) Passive system operation (minimal manpower) Anti-pest  Quick setup (3 days) Applicable for wide range of crops The main application for this technology is for those that are interested in rooftop farming. The potential applications are: Conversion of barren and unused concrete space into temporary/permanent arable land (eg. Carpark rooftops, schools, apartments, factories and floating platforms etc.) Can be applied to high-value crops Minimal human intervention is needed as the modular greenhouse farming system encompasses Internet of Thing (IoT) and automation Ability to scale-up immediately greenhouse, vegetable, urban farming, rooftop farming, bak choy, deep water culture hydroponics system, hydroponics, pesticide-free, farming IoT, farming automation Life Sciences, Agriculture & Aquaculture, Sustainability, Food Security

In recent years, there has been an increasing demand for carbon dioxide (CO2) adsorbents due to climate change. These materials can be used for CO2 capture in both flue gas and directly from the air which can mitigate and reduce greenhouse gas (GHG) emissions. The current conventional CO2 adsorbents includes alkaline salts, aqueous amine solution and metal organic frameworks (MOF). However, these materials are expensive (MOF) and suffers from problems such as heat generation (alkaline salt) to energy intensive post-adsorption recovery (aqueous amine solution) which severely limits its wide scale adoption. This technology offer is an amino-based resin adsorbent for low concentration and ambient temperature CO2 adsorption and desorption. This adsorbent is capable of adsorbing low concentrations of CO2 in air at room temperature and generates little heat when adsorbing CO2. It is also possible to capture CO2 from flue gas in the same manner as well. In addition, the regeneration (release of CO2) of the adsorbent can be performed at low temperature with significantly less energy consumption than existing materials. This technology offer is an amino-based resin adsorbent for low concentration and room temperature capture of CO2. The technical features and specifications are as follows: Porous amino-based resin Easy to handle granules High affinity CO2 chemisorption Low concentration and temperature CO2 adsorption (as low as 400 ppm and at room temperature) Desorption is possible at lower temperatures than existing materials (30 oC or higher) Environmentally friendly (non-toxic, non-volatile) Flexible implementation design (filter parts, filing columns etc.) The use of this technology is for industries who are interested in CO2 capture and/or utilisation. The potential applications are: - Scenarios for CO2 Capture Air conditioners (passive CO2 capture and indoor CO2 concentration control) Manufacturing and other CO2 emitting industries (removal of CO2 from pre-combustion or flue gas) - Scenarios for CO2 Utilisation Beauty applications (promotion of blood circulation by use of CO2) Agriculture application (promotion of growth by use of CO2)  Low concentration and room temperature CO2 capture Desorption is possible at lower temperatures than existing materials (30 oC or higher) Environmentally friendly adsorbent (non-toxic, non-volatile) Flexible use case (direct air capture, flue gas capture) This technology owner is keen to out-license this patented technology, or to do R&D collaboration utilising the adsorbent material with partners who are interested in CO2 capture and/or utilisation. Direct air capture, Flue gas capture, CO2, Adsorbent, Amine, Resin Materials, Plastics & Elastomers, Environment, Clean Air & Water, Filter Membrane & Absorption Material, Green Building, Heating, Ventilation & Air-conditioning