TECH OFFERS

Computer vision models are used in a suite of prediction tasks such as Object Detection and Instance Segmentation that have 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. However, to accomplish this, teams have to navigate between Data Ingestion, Image Labelling, Transfer Learning, Model Validation, Deployment, and Model Tuning. This can take upwards of 8-12 different tools that teams have to use, making a swift, collaborative approach to model building a difficult task. This technology offer presents an end-to-end MLOps platform that alleviates such issues and allows teams to build robust computer vision models step-by- step with enterprise-standard practices internally while maintaining a collaborative approach. This platform is industry agnostic, which provides an adaptive model that allows the teams and researchers to convert their datasets into working models.

Separation of oil/water mixture using wetting materials has been extensively investigated. However, the wastes released in industrial processes such as multi-phase liquids extraction, food industries or chemical reaction contain more complicated liquids components. The technology presents a novel strategy to prepare a broad range of superlyophobic materials based on polydopamine (PDA) mediated coating. The results demonstrate that the deposition of PDA nanoparticles enhances the growth of silicone microsheets (SMS), which increases trapped air fraction and results in superlyophobicity towards high surface tension liquids and superlyophilicity to liquids with surface tension smaller than 30 mN/m. Superlyophobic sorbents generated from melamine foam and polyurethane foam can absorb various oils with capacity from 53 g/g to 120 g/g (melamine foam) and from 26.5 g/g to 52.5 g/g (polyurethane foam), depending on the oil type and density. High absorption capacity of porous foams towards oils makes them possible to remove low surface tension liquids from a batch of high surface tension immiscible organic liquids such as formamide or diethylene glycol. On the other hand, superlyophobic membranes fabricated from stainless steel mesh, cotton fabric and filter papers can filter chloroform and carbon tetrachloride from water and formamide with efficiency higher than 96%. All as-prepared superlyphobic materials show excellent regeneration. The preparation of superlyophobic materials introduced in this work opens a general strategy for separation of immicible liquids by both static and continuous methods. The technology provider is seeking partner for research collaboration, scale-up testing/test-bedding, product co-development, technology licencing or manufacturing.    

This technology relates to a reinvention of the structure of spiral wound membrane module to increase productivity and to simplify the membrane fabrication process. Despite undergoing a long history of development, the structure of the spiral wound membrane modules remained the same. Each module is made up of several leaf sets, with each leaf set consisting of feed spacers, flat sheet membranes and a permeate carrier wrapped around the permeate collecting tube. The technology here involves combining the 3 layers in a leaf set into 2 layers on an industrial-scale casting line such that more membrane can fit into a standard specific volume. By combining the permeate carrier and the membrane into a single sheet, we were able to eliminate the need for the typical non-woven backing for the membrane. As such, the leaf set thickness can be significantly reduced by approximately 10-20%, and hence the theoretical surface area and productivity of the membrane modules can be increased by 30-50%. The material cost can potentially be reduced by 10-20% and the internal ion concentration polarization (ICP) is expected to be reduced due to less bulky structure. This design also lessen the work required to roll an element due to less sheets per leaf-set. The technology provider is currently seeking joint-venture partners for technology evaluation licensing with research collaboration agreement (RCA) to scale-up and commercialize the technology.

Bots are supposed to understand what humans want, guiding them to their desired outcome. However open-text chatbots tend to do poorly because they are unable to detect intents (what the customers are actually asking) accurately. Our technology puts intelligence into our clients' chat or voice bots, to know what their end-users want.  Our proprietary rules-based models predict user intentions by (1) automatically analysing human-bot conversations and (2) using this to train bots faster, better and in a more cost-efficient manner.  Using our platform takes 20x less human intervention. Consequently, bots become smarter much faster than if clients relied on manual training, typically reducing errors by 68% in as little as 3 weeks. This brings the current  average chatbot accuracy rates from 30-40% to 90+% within several training iterations. The platform also provides tools to help clients identify customer trends and their emotions towards the bot. We are looking for corporate clients and bot developers who want to differentiate themselves in the marketplace by offering chatbots that actually meet their customer metrics using our proprietary training platform.

Plastic is a very versatile material as it is lightweight, cheap, and durable. However, plastics take hundreds of years to decompose in nature, leading to the problem of plastic pollution. Furthermore, most commercially available biodegradable plastics are unable to be used as complete replacements for single-use plastics as they have weaker mechanical properties such as strength and temperature resistance. Therefore, a new biodegradable alternative is necessary to mitigate the serious environmental pollution problem brought about by conventional single-use plastics. This technology is a renewable, bio-based, and degradable resin that meets both international industrial and home composting standards. Produced through a propietary compounding process, the material can meet the standards for food contact grade. The polymer also has excellent fluidity, toughness and good moulding performance that meet the production requirements in injection moulding, extrusion, thermoforming, and other moulding processes. It does not require strict conditions to degrade and will achieve 100% self-degradation when placed in a natural environment together with ordinary waste, leaving no harmful substances. This material aims to be a viable replacement to replace conventional plastics in disposable tableware, food packaging, and sanitary ware.

In conventional electrolysis, water molecules first dissociate into intermediate ions, namely, negative hydroxyl ions (OH-), positive hydrogen ions (H+) and positive hydronium ions (H3O+), before further decomposition into oxygen and hydrogen. This process of generating hydrogen is inefficient due to the high probability of hydroxyl ions recombining with either hydrogen ions or hydronium ions to form back water molecules. The technology described herein is related to a hybridised process which enhances hydrogen production rate of a conventional electrolysis system through combining the hybridised process with photocatalytic decomposition reaction. By combining the hybridised process with photo-catalytic decomposition, the probability of intermediate radical/ion recombination is reduced. This results in an increase in hydrogen and oxygen production of up to 25%. A prototype has been developed to demonstrate the feasibility and effectiveness of producing hydrogen and oxygen based on the hybrid photocatalyst-electrolysis method. With a strong knowledge in optimisation of the operating parameters in a hybrid photocatalyst-electrolysis reaction, the technology owner would like to seek partnership from the industry to commercialise the technology.   

A tactile sensing glove embedded with multiple tactile sensors can measure each sensing point’s applied pressure and its corresponding position. Its pressure sensing layer is constructed with multiple rows and columns of piezoresistive sensing points. The piezoresistive sensor’s electrical resistance decreases when a pressure is applied on it. The tactile sensing glove can be put on a robotic gripper or prosthetic device to receive haptic feedback during manipulation tasks.

This technology offer is a small, secure, low power and cost-effective hardware module with a dedicated convolutional neural network (CNN) accelerator. The hardware accelerator supports many pre-trained artificial intelligence (AI) models, allowing edge processing at the IoT sensor node itself. As such, real time AI inference can be done without the need for high bandwidth communications to the cloud. Simple API calls through one of many communication interfaces makes adding AI capability to IoT nodes an easy task.

The production of shrimp roe is dependent on the age, weight, and size of the adult females. There is a concurrent specific nutritional requirement prior to roe development. Consequently, roe production is random and inconsistent within any shrimp batches. Traditional methods to increase spawning frequency and egg production involve the unsustainable method of eyestalk ablation whereby one eyestalk of the shrimps is removed to stimulate yolk formation (vitellogenesis). In addition to the anatomical stress on the shrimps, eyestalk ablation can only be performed on shrimp with a minimum weight of 70 - 90 g which requires 12 months to grow out. The proprietary epigenetic activated fermentation (EpAF) technology stimulates vitellogenesis naturally in female shrimps within 4 - 5 months, reaching 30 - 35 g. This greatly increases the quality and quantity of shrimp egg production. In addition, the taste of shrimp eggs can be altered subtly to suit the taste of the target market. The technology provider is looking for joint venture partners or licensing the technology to interested parties from the aquaculture and/or food industry.