TECH OFFERS

The rise of AI adoption in a more digitalized world comes with the increasing hunger for computing power with higher performance while having lower latency. With conventional computing components not being specialized for these tasks, hardware, architecture and chips are developed and optimized to process specialized AI algorithm operations, bringing cloud computing closer to the edge. Resistive random-access memory (RRAM) is considered as the next generation of memory technology for neuromorphic computing applications due to its non-volatile, high-performance computing and ability to provide both computing and storage capabilities within a single chip. However, current RRAM technology is still heavily researched and faces challenges such as scalability limitations, high latency, and complex design largely due to its analog nature. The technology owner has developed a technology solution in the form of a neuromorphic chip. By incorporating its patent-pending optimized architecture design and proprietary peripherals, the technology solution enhances RRAM’s capabilities while eliminating its challenges. With its integration with RRAM, it is able to engage in in-memory computing within a unified architecture, lowering latency while enhancing energy efficiency (up to 30 TOPS/W). The architecture enables seamless integration with field-programmable gate arrays (FPGAs), simplifying the design process with re-programmability in mind. With its modular dual-core arrays (up to 128x128) design, it enables RRAM to be easily scaled for complex AI algorithm and large-scale data processing within devices. With these capabilities, it accelerates the adoption of neuromorphic chips for the use of edge-AI applications. The technology owner is seeking collaborative partners focusing on AI hardware and software development to further accelerate the widespread use of AI applications and industrial partners keen on exploring further integration of edge-AI capabilities into their product to unlock more sophisticated and reliable solutions. Through the integration of the optimised architecture and supporting proprietary peripherals into RRAMs, it enables the technology solution to: Engage in simultaneous computation and storage capabilities (in-memory computing) whereby conventional chip architecture separates these functions Increase system efficiency by reducing data transfer bottlenecks common in traditional systems via its simplified design Increase peak efficiency (to 30 TOPS/W) for various demanding AI inferencing processes due to the optimisation of interfacing between RRAM and digital components via its proprietary peripherals Supports modular dual-core array chip architecture (up to 128x128) for scalability to handle complex AI algorithm and large-scale data processing tasks Compatible with FPGAs which enables development of programmable software algorithms for customisation and specific application needs Resistance to radiation due to its RAD HARD robust design making it suitable for extreme environments Able to achieve the harsh standard requirement of automotive grade chips (e.g. operating temperature, error rate, lifespan) With this technology solution, it accelerates the industrial adoption of RRAMs by reducing its limitations while enhancing its capabilities. Some potential applications include: - Neuromorphic Processors: With higher energy efficiency and lower latency, it empowers edge-AI devices for more advanced AI applications such as deep learning, neural networks and real-time data processing. - Automotive: Enhancement of existing advanced driver-assistance systems (ADAS) where rapid data processing and storage and low latency are critical in its optimal operation - Consumer Electronics: The scalability and high energy efficiency enables RRAM to be deployed in smart devices, enhancing the functionality and performance of smart home devices, wearable technology and other IoT applications - Data Analytics (e.g. finance, telecommunication, data center): Due to its low latency and ability to manage and process data efficiently, it enables fast processing of large datasets to provide insightful real-time analytics for users - Extreme Environment AI Application (e.g. military operation, space exploration, nuclear facilities): Being resistant to radiation enables the use of electronics in extreme environment while providing the full functionalities of RRAM The global AI chipset market is valued at US$51.19 billion in 2023 and is estimated to be valued at US$131.78 billion by 2028, exhibiting a CAGR of 20.8% during the forecasted period. In particular, the global AI hardware processor chipset is valued at US$15.08 billion in 2023 and is estimated to be valued at US$50.66 billion by 2028, exhibiting a CAGR of 27.4% during the forecasted period. The technology solution introduces an optimized architecture design with supplementary proprietary peripherals for analog RRAM into a form of a neuromorphic chip, enabling both computational and storage into a unified architecture. With this solution being integrated into RRAM, it tackles existing RRAM challenges resulting in reduced latency, improved energy efficiency and enhancing resilience to extreme environments (e.g. radiation) while delivering high performance (up to 30 TOPS/W). With its scalable architecture supporting dual-core arrays up to 128x128 and compatibility with FPGAs, it provides adaptability, scalability and flexibility to optimize task-centric applications. With the enhancement of RRAM’s capabilities while minimizing its limitations, the technology solution accelerates the deployment and adoption of current and future edge-AI solutions. RRAM, ReRAM, Neuromorphic Computing, In-memory Computing, Non-Volatile Memory, NVM, AI Chip Electronics, Semiconductors, Infocomm, Artificial Intelligence, Smart Cities, High Performance Computing

The Computer Vision-Powered Tool Chest is a cutting-edge solution designed to revolutionize inventory management across industries. Equipped with advanced cameras and computer vision algorithms, this system automates the process of tool tracking and placement verification in real time. Mounted at the top of tool chests or racks, the cameras monitor the presence, position, and organization of tools, instantly identifying missing, misplaced, or misaligned items. This technology is a game changer for industries where efficient tool management is critical, such as aerospace, automotive, and manufacturing. By eliminating manual checks and reducing human error, it improves operational efficiency, minimizes downtime, and ensures optimal tool availability. The system can be easily integrated into existing workflows and is scalable to accommodate varying tool storage configurations. Whether you're in maintenance, repair, and overhaul (MRO), or simply need better control over tool inventory, the Computer Vision-Powered Tool Chest provides a seamless and innovative solution. With its ability to connect to cloud platforms for data analysis and reporting, the system delivers a comprehensive approach to tool management that saves time, cuts costs, and enhances productivity across various sectors. The Computer Vision-Powered Tool Chest consists of several integrated components designed to automate and enhance tool tracking and inventory management. At its core, the system includes high-definition video cameras mounted above tool chests or racks to capture real-time visual data of the tools. The captured images are processed using advanced computer vision algorithms, which are capable of identifying, counting, and analyzing tool presence, placement, and organization. The system also includes an intuitive software platform for monitoring, reporting, and alerting users in case of missing or misplaced items. Data is stored on cloud-based services, allowing for seamless integration with existing inventory management platforms and real-time access to tool usage analytics. The system is designed to support a wide range of tools and storage configurations, making it highly adaptable for various operational environments. Ideal Collaboration Partners: Manufacturers: Tool manufacturers interested in integrating smart technology into their products to offer value-added services to customers. MRO Providers: Maintenance, Repair, and Overhaul companies looking for efficient, automated tool tracking and inventory solutions. Logistics Companies: To optimize tool distribution and reduce losses. Industrial Automation Providers: Companies specializing in smart factories and Industry 4.0 solutions to expand the range of automation systems. Cloud Service Providers: For seamless integration and data management. This technology offers a comprehensive solution for industries that rely on accurate tool management, reducing manual intervention and improving operational efficiency The Computer Vision-Powered Tool Chest has broad applications across multiple industries where efficient tool tracking and management are critical. Its primary deployment is within Maintenance, Repair, and Overhaul (MRO) operations, particularly in sectors like aerospace, automotive, and manufacturing, where misplaced tools can cause costly delays, safety issues, or regulatory non-compliance. In the aerospace industry, this technology ensures that specialized tools are always available and correctly placed, preventing downtime and improving workflow efficiency. Similarly, in automotive manufacturing and assembly lines, the system can track tools, reducing production stoppages due to missing equipment. Beyond MRO, warehousing and logistics companies can use this technology to streamline the organization of tools and equipment, optimizing their supply chain operations. The construction industry can also benefit from real-time monitoring of high-value tools on-site, minimizing theft and loss. This technology can be adapted into a range of products, including smart tool chests, automated tool racks, and integrated inventory systems for tool-heavy environments. By integrating it with cloud-based platforms, companies can also market remote monitoring and management systems for tool inventories, providing real-time data analytics to further enhance efficiency. This adaptable and scalable solution can revolutionize how tools are managed across industries, enhancing productivity and reducing operational risks. The Computer Vision-Powered Tool Chest offers a major improvement over traditional tool tracking systems like manual checks, barcodes, or RFID tagging. By using advanced computer vision, the system automates real-time tool detection and placement verification, eliminating the need for manual scanning and reducing errors. Its unique advantage lies in providing instant alerts for missing or misplaced tools, enhancing efficiency and reducing downtime. With cloud integration for seamless data monitoring, it offers a scalable, cost-effective, and flexible solution for industries like aerospace, automotive, and construction, ensuring accurate tool management with minimal human intervention. Infocomm, Artificial Intelligence

This software platform is a revolutionary remote monitoring and control system designed to address several critical challenges faced by various industries. Problem Solved:  Centralized Monitoring: Many customers struggle with the lack of a unified platform for real-time monitoring of devices, leading to reliance on manual interventions and multiple scattered tools. The software consolidates the management of IoT devices across diverse locations into a single interface, streamlining operations.                        Data Analysis Challenges: Businesses often find it difficult to extract meaningful insights from collected data due to time-consuming manual analysis. The software automates this process, enabling users to interpret trends and identify potential issues effortlessly.  Data Visualization and Alerts: Users frequently lack intuitive interfaces for visualizing device data or receiving timely notifications. The software provides customizable dashboards and configurable alerts, allowing proactive management of potential problems. Target Market: The software platform caters to a wide range of sectors including facility management (monitoring HVAC, lighting, energy consumption), industrial operations (predictive maintenance), agriculture (environmental monitoring), and smart cities (traffic flow and air quality). Market Need: The technology addresses a significant gap in the marketplace by offering an integrated solution that enhances efficiency, reduces operational costs, and improves decision-making through advanced data visualization and automation. This software positions as a valuable asset for organizations seeking to optimize their monitoring processes and resource management. The technology owner is seeking collaboration with system integrators, facility management teams, IoT companies, and startups. The software platform boasts several key technical features that enhance its functionality and usability in remote monitoring and control applications. Cross-Platform Scalable Web Service: Built on Microsoft .NET 7, it operates seamlessly on Windows, Linux, and Raspberry Pi platforms. It has been successfully deployed in various environments, including Amazon Cloud and local servers, showcasing its flexibility and scalability for different applications. Logging and Message Relay: Efficiently manages IoT devices by collecting real-time data via HTTPS RESTful API. It performs real-time analysis and publishes results to users through secure WebSocket connections while relaying user commands to devices via MQTT. Customizable Data Analysis: Users can perform mathematical functions and time series calculations directly through a web interface, allowing tailored data analysis based on specific needs. Customizable Dashboards: Administrators can create user-specific dashboards that cater to individual or group requirements, enhancing user experience and operational efficiency. Email and Telegram Alerts: The software enables users to configure alerts based on various events, with customizable messages that can include specific device attributes and timestamps. External Interface Capability: The system integrates with higher-level software installations and Building Management Systems (BMS) via BACnet protocols, facilitating centralized monitoring across multiple sites and enabling comprehensive data analysis for optimization. These features collectively position this software platform as a versatile solution for diverse industries, enhancing monitoring capabilities while simplifying user interaction with IoT systems. The technology can be deployed across various industries, offering diverse applications that enhance monitoring and control capabilities. Industries and Applications: 1.   Facility Management: HVAC systems for optimal climate control. Lighting systems to improve energy efficiency. Energy consumption tracking to reduce costs. Fire safety and security systems for enhanced safety. 2.    Industrial Operations: Manufacturers can utilize the software for: Machine monitoring and predictive maintenance to prevent downtime. Process control and optimization for improved productivity. Real-time data analysis to ensure quality control. 3.    Agriculture: Farmers can apply the software for: Environmental monitoring (temperature, humidity, soil moisture). Irrigation control to optimize water usage. Livestock monitoring for better management. 4.    Building Automation: With BACnet integration, the software facilitates: Centralized control of building systems (HVAC, lighting, security). Real-time visualization of energy inefficiencies. Automated alerts for equipment malfunctions. 5.    Smart Manufacturing: The technology supports: Predictive maintenance of production machines. Process data analysis to enhance quality control. 6.    Additional Potential Users: Data centers for critical infrastructure monitoring. Renewable energy management for solar panels and wind turbines. Smart cities for traffic flow and air quality monitoring. Marketable Products Based on this technology, products could include integrated monitoring solutions, customizable dashboards, and automated alert systems tailored for specific industry needs, enhancing operational efficiency and decision-making capabilities. The software platform advances current remote monitoring and control systems with a UVP that addresses key limitations comprehensively. By combining ease of use with advanced features, it enhances operational efficiency across multiple industries and overcomes the shortcomings of existing solutions—such as fragmentation, limited flexibility, and high complexity—positioning itself as an effective, scalable choice. It improves upon current technologies: Unified Platform: Unlike existing solutions that require managing disparate systems for data acquisition, analysis, and alerting, the software provides a centralized platform, simplifying workflows and enhancing efficiency. Flexibility: The software supports various industrial communication protocols, allowing seamless integration with a wide range of devices and systems. This adaptability makes it suitable for diverse applications, from building automation to industrial monitoring. Scalability: The technology is designed to operate across different platforms, including Windows, Linux, and Raspberry Pi. This versatility enables deployments from small setups to extensive building automation systems without compromising performance. Customization: Users can create tailored dashboards and configure alerts based on specific requirements. This level of customization empowers users to proactively address issues and enhances overall operational efficiency. Ease of Use: With a user-friendly interface, the software is accessible to users with varying technical expertise, contrasting sharply with complex enterprise-grade IoT platforms that often require specialized knowledge. IOT, Remote Monitoring and Control Green Building, Sensor, Network, Building Control & Optimisation, Infocomm, Internet of Things, Environment, Clean Air & Water, Sensor, Network, Monitoring & Quality Control Systems

Controlling the spread of pathogens is crucial in high-traffic areas and healthcare environments. This can be achieved through environmental control methods like sanitising surfaces to prevent diseases from spreading through contaminated surfaces. However, it is labour intensive and impractical to sanitise all surfaces continuously. Antimicrobial coating is an effective way to retard the spread of pathogens on surfaces by inactivating bacteria, viruses and fungi when they contaminate a surface. Despite being commercially available, the cost and durability of the anti-microbial coating technology can still be further improved. Common commercial coatings that are available to consumers have a gradually diminishing antimicrobial strength and mostly only last a few months. It is also difficult for some coatings to adhere onto slippery surfaces like plastics. To address these challenges, the technology owner has developed a cost-effective process to fabricate more durable, high performance antimicrobial coatings on different materials, including glass and plastic. They are seeking industry partners interested to co-develop, scale up and commercialise this coating for various applications. Inorganic coating for enhanced antimicrobial performance which works through multiple pathways in the absence of UV light   Excellent antimicrobial efficacy at >99.99% against E. coli and S. aureus based on ISO 22196 and verified by third party laboratory Good durability with more lasting antimicrobial effect: In-house test with oscillating abrasion tester and zirconia balls as the abrasive media showed that this coating is more mechanically durable than other commercially available coating Possible to achieve >90% visible and NIR light transmission (400-1000 nm) and the transmission level is tunable Low temperature process using chemical bath deposition Suitable for both glass and plastic substrates This coating is a factory applied coating and on glass and plastic surfaces that require antimicrobial function and high transparency such as windows in healthcare environment, high touch surfaces, touch display panels, etc. Other products that may be developed include: Coating for built environment applications Coating for PV systems Air purifying coatings    Cost effective deposition method using chemical bath deposition More durable with better abrasive and scratch resistance than other commercial spray-on antimicrobial coatings  Multi-functional coating that is antimicrobial, anti-reflective and photocatalytic, effective through multiple pathways without UV light antimicrobial, antibacterial, antiviral, film, covid Chemicals, Coatings & Paints, Green Building, Indoor Environment Quality, Sustainability, Sustainable Living

This technology is a 70k Axiom Single Nucleotide Polymorphism (SNP) array for two common food fish species in Singapore – Asian seabass/Barramundi and red snapper. Red Snapper This technology offers a SNP array designed for red snapper, featuring 70,774 SNPs identified through advanced bioinformatics pipelines. The array incorporates 130 monomorphic SNPs associated with 13 critical pathogens, including ‘Big Belly’ disease, Vibrio virus, Scale Drop virus, Streptococcus iniae, Megalovirus and Iridiovirus. It allows researchers and aquaculture companies to genotype red snapper and gain simultaneous insights into the presence of these pathogens. The key problem addressed is the lack of integrated tools for both genetic analysis and pathogen screening in aquaculture, which can hinder effective breeding and health management strategies. The primary users are researchers in fish genetics and aquaculture practitioners looking to enhance breeding programs and monitor fish health efficiently. Barramundi This technology provides a SNP array for barramundi with 70,182 finalized SNPs derived from a diverse set of datasets, including whole genome re-sequencing and RADseq. It features SNPs associated with growth traits, disease resistance, omega-3 content, and diagnostic markers for 10 barramundi pathogens. This array addresses the need for a comprehensive tool that supports both genetic improvement and disease monitoring in barramundi aquaculture. By offering integrated pathogen detection at no extra cost, it supports effective management of fish health and optimizes breeding strategies. The technology is targeted at researchers and aquaculture companies aiming to advance barramundi breeding programs and enhance fish health management practices. Use of these SNP chips in breeding programs by farmers and breeding centres will aid in the identification of fish which are genetically superior in terms of aquaculture traits such as faster growth, nutritional profile and disease resistance. This will thus ensure not only a good, uniform quality but also a good quantity of fingerlings. Sample collection entails simple tail fin clip and analyses would take 1-2 weeks. Aquaculture: Both the red snapper and barramundi SNP arrays are crucial for improving fish breeding programs. They would facilitate selective breeding by identifying desirable genetic traits and enhancing growth rates, disease resistance, and omega-3 content in farmed fish. The arrays also support pathogen surveillance, allowing for the detection of infections early and improving overall fish health management. It will also aid in identifying superior broodstock for producing high quality fingerlings for local production at fish farms as well as can be exported to neighbouring countries Research: These technologies are valuable tools for researchers studying fish genetics, evolutionary biology, and disease mechanisms. They can be used to explore genetic diversity, traceability of fish populations, and the impact of pathogens on aquatic species. This is an industry-applicable tools to aid future breeding processes and the continuation for genetic improvement of important fish species needed to supply high quality and uniform aquaculture produce. The unique value propositions of the red snapper and barramundi SNP arrays lie in their dual functionality and comprehensive coverage. Unlike current state-of-the-art technologies, which typically focus on either genetic selective breeding or pathogen detection, these arrays integrate both capabilities into a single tool. For the red snapper array, the inclusion of 130 pathogen-specific SNPs allows for simultaneous genotyping and pathogen screening, offering a holistic approach to fish health management. Similarly, the barramundi array not only supports genetic improvement for traits such as growth and disease resistance but also detects infections from 10 critical pathogens. This integration enhances the efficiency of aquaculture operations by streamlining genetic and health assessments, reducing the need for separate diagnostic tools. Compared to existing solutions, these arrays offer a more comprehensive and cost-effective approach, addressing both genetic and health management needs in a unified platform. This advancement simplifies workflows for researchers and aquaculture operators, ultimately leading to improved breeding outcomes, better disease control, and more sustainable fish farming practices. Aquaculture, Broodstock, Genetics, Breeding, Genotyping, SNP Arrays Life Sciences, Agriculture & Aquaculture

The malposition of nasogastric tube (NGT) is when the tip is lying in the lungs or the pleural space, leading to pneumothorax, pneumonia and feed empyema and can be fatal. This happens in blind placements and has a 1 - 3% occurrence. Current clinical NGT placement are typically performed blindly without any visual aids. Misplacement is a preventable issue that can delay treatment, increase healthcare costs and put patient safety at risk. This system enhances the accuracy of NGT placement by integrating a flexible guiding stylet with a removable permanent magnet (PM). The magnet allows for easy retrieval and re-insertion, enabling periodic confirmation of the tube's position during feeding. It leverages an external network of magnetic sensors to detect the magnetic field produced by the PM. These sensors, integrated into a smart fabric affixed to the patient, provide real-time feedback through LED indicators that display the exact location of the NGT tip. This technology ensures immediate detection and correction of any misplacement during the insertion process, significantly reducing risks and eliminating the need for repeated imaging or testing, unlike traditional methods that rely on pH tests or radiological imaging to verify the tube’s position. The technology owner is looking for partners to collaborate and further the commercialization of the technology.  The solution uses passive magnetic tracking technology to provide proven, real-time, robust, safe and cost-effective localisation of the NGT during the insertion process as well as subsequent re-confirmation. High accuracy in complex environments with real-time localization: NGT can be located real-time with computational algorithms and a network of sensors allow precise tracking of the NGT’s position, even in the presence of nearby metallic objects, ensuring reliability in diverse clinical environments. Direct and definitive: Quantify the actual position of the NGT unlike the pH method which is indirectly inferring the location of the NGT tip. An integrated sensing display unit contains  Cost-effective and easy integration: Minimal changes to the NGT design and clinical workflow, ensures the solution to be cost effective. Non-invasive detection: External sensors accurately locate the PM through human tissue (e.g., skin, muscle, and bone) due to its low magnetic susceptibility, allowing non-invasive tracking. Technology can be used for real-time localization of medical devices such as nasogastric tubes, catheters, within the body. Its ability to function without line of sight and through non-ferromagnetic mediums like tissue ensures accurate device placement in critical procedures, significantly improving safety in minimally invasive surgeries. The system can overcome the limitations of traditional tracking by providing non-invasive, highly accurate localization without the need for continuous X-rays exposure, offering safer alternatives for real-time feedback. Tracking starts from the critical oesophagus-trachea juncture, all the way to the target gastric-intestinal site, with real time feedback on the actual location.  Easy to use and intuitive: Does not require bulky sensing and electronic systems that is placed on the patient Does not change workflow: The insertion procedure and NGT are fundamentally unmodified Less cumbersome system: System consists of a fully wireless system requiring no auxiliary power and smaller footprint Able to use in home-care setting: Available to be used in home-care setting unlike traditional X-ray methods  Able to handle both initial and subsequent tube confirmations without requiring the NGT to be fully retrieved from the body. Using the novel stylet approach, the NGT can be left inside the body for subsequent re-confirmations. Following confirmation, the stylet can be retrieved so that only the NG tube is left inside the body (exactly the same as it is presently done). Nasogastric Tube (NGT), Localization, Real-time, Permanent Magnet, Tracking Healthcare, Medical Devices, Telehealth, Medical Software & Imaging

Side stream valorisation in sectors such as food and beverage manufacturing has gained substantial interest over the years. The waste streams, in particularly the liquid has high amount of nutrients and organics, in which suitable bioprocesses can be deployed to convert them into value-added products. One product of interest is the purple phototrophic bacteria (PPB), a metabolically diverse group of proteobacteria that contains pigments bacteriochlorophyll a and b. Attributed to its unique versatile metabolic pathways, PPB can be used as powerful pollutant removal in different types of wastewater treatments, under stressful conditions. Its light utilization process and hormone secreting properties also made PPB a good bio-fertilizer and bio-stimulant for plant growth.  This proposed PPB cultivation technology in photobioreactor (PBR) system has greater treatment efficiency and higher biomass conversion rate than conventional open pond systems. Biomass generated from this cultivation technology demonstrated its ability to enhance essential nutrients in soil and supply key plant hormones that aid in plant growth. This novel application of PPB can be adopted in the agriculture industry, in the effort to develop more eco-friendly agricultural inputs.  The technology provider is seeking for collaborators to test bed the technology to license the technology. The biomass conversion process boasts high efficiency, achieving up to 0.8 grams of biomass for every gram of chemical oxygen demand (COD) removed. Its versatility allows it to work with various types of feed, adaptable to different loads and conditions. High efficiency and robustness of the technology also contribute to more compact system design and lower operating cost. This sustainable approach in PPB production utilizes waste streams from food manufacturing sectors, transforming waste into valuable products. Additionally, biomass generated from the technology offers a novel application in stimulating and supporting plant growth. The PPB technology can be deployed in wastewater treatment processes, to remove organics and pollutants efficiently. PPB can enhance essential nutrients in the soil and support plant growth. It can be used as alternative agricultural inputs such as bio-fertilizer and bio-stimulant, promoting crop yield in a sustainable manner. Value-added product derived from the technology also has high level of protein content, which can be utilised as alternative in animal feed formulation for aquaculture or livestock breeding. This novel compact PPB cultivation technology offers higher treatment efficiency and wider product applications than the conventional open ponds systems. Purple phototrophic bacteria, bio-fertilizer, agriculture, valorisation, microbes, PPB Foods, Quality & Safety, Waste Management & Recycling, Food & Agriculture Waste Management, Sustainability, Food Security

Antioxidants (ATOs) such as tocopherol and synthetic ATOs such as Butylated Hydroxytoluene (BHT), Butylated Hydroxyanisole (BHA), and Tertiary-Butyl Hydroquinone (TBHQ) are used in the food and supplement industry to extend shelf life and protect products from oxidation.  Due to concerns over long-term exposure to synthetic ATOs, there is a search for natural alternatives like rosemary and green tea, which have shown efficacy in preserving oils and other products.  However, natural ATOs exhibit significant chemical variations due to diverse cultivation and extraction processes, making it challenging and costly to identify the optimal combination for maximum efficacy.  Machine learning, capable of extracting patterns from input data for predictive analysis, can offer a solution by predicting the peroxide value (PV) in peanut oil using chemical parameters and storage duration. Six machine learning classifiers (logistic regression, multilayer perceptron, radial basis function, Gaussian Naïve Bayes classifier, support vector machine, and decision tree) were employed, with the multilayer perceptron demonstrating the highest predictive performance, achieving an accuracy of at least 89.8% in determining whether PV remains within acceptable limits post-storage in peanut oil.  Edible oil manufacturers, food and beverage companies, natural antioxidant suppliers, food quality testing laboratories and agricultural processors can use this technology to improve the quality and stability of their output. The technology consists of a predictive model based on machine learning algorithms that utilises key chemical parameters to forecast the PV in peanut oil during storage.  Specifically, the model employs six machine learning classifiers: logistic regression, multilayer perceptron, radial basis function, Gaussian Naïve Bayes classifier, support vector machine, and decision tree.  The model uses input parameters such as total phenolic content, total antioxidant content, total carotenoid content, partition coefficient, and storage duration to predict PV, which is crucial for assessing the stability and safety of peanut oil. This technology can be deployed in the food and beverage industry, particularly within sectors focused on edible oil production, food preservation, and food safety testing. It also has applications in the agriculture industry, particularly for oilseed processors, and in the health and wellness industry where natural antioxidants are of interest. This technology can be applied in: 1. Edible Oil Production: To monitor and predict the stability and shelf life of various edible oils during production and storage. 2. Food Preservation: To ensure that food products containing oils remain safe and of high quality throughout their shelf life. 3. Quality Control: As a quality assurance tool to validate the effectiveness of natural antioxidants in preserving food products.   This technology could be marketed in following products/services: 1. Predictive Software for Oil Stability: A software tool designed for oil producers to predict the PV and shelf life of their products. 2. Enhanced Edible Oils: Oils treated with specific formulations of natural antioxidants optimized using the predictive model. 3. Food Quality Monitoring Kits: Integrated solutions combining chemical analysis with the machine learning model for real-time monitoring of oil stability in food products. 4. Consulting Services: Offering expertise in applying this predictive model to optimize food preservation processes. This technology offers significant improvements in the following areas: 1. Predictive Accuracy: Unlike traditional methods that rely solely on periodic testing of PV, this technology leverages machine learning to predict PV with high accuracy, allowing for proactive management of oil stability. 2. Comprehensive Parameter Integration: Integrating multiple chemical parameters, providing a more holistic and precise assessment of oil stability compared to conventional methods that might focus on fewer variables. 3. Reduction in Testing Time and Costs: By accurately predicting PV, this technology can reduce the need for time-consuming stability tests, lowering operational costs and speeding up the decision-making process for product release. 4. Adaptability to Natural Antioxidants: This technology is particularly effective in assessing the stability of oils preserved with natural antioxidants, addressing a growing industry demand for clean-label and natural food preservation methods.   The Unique Value Proposition in comparison to the current “State-of-the-Art”: 1. Machine Learning-Driven Precision: Advanced machine learning algorithms that significantly enhance the precision and reliability of PV predictions are used, setting it apart from conventional approaches. 2. Enhanced Safety Profile: By focusing on natural antioxidants and accurately predicting their efficacy, this technology supports safer food products, meeting consumer for natural preservation methods over synthetic alternatives. 3. Scalability Across Various Oils and Food Products: The technology’s ability to be tailored to different types of oils and food products provides a competitive edge, making it a versatile tool for the industry. Infocomm, Artificial Intelligence

The use of plastic waste is severely restricted due to high levels of contamination, expensive sorting processes, and the non-homogeneous nature of the materials. These challenges contribute to low recycling rates both locally and globally, with most plastic waste being disposed of through landfilling or incineration, leading to further environmental concerns.  This technology aims to create sustainable products and processes for infrastructural applications by transforming mixed plastics from municipal solid waste (MSW) into raw materials like fibres, aggregates, and polymer modifiers, which can be incorporated into bituminous mixtures. It is the first of its kind to enable the direct use of MSW mixed plastics without the need for extensive sorting. The as-received mixed plastic waste is processed into standardized forms commonly used in the construction industry. Given the large scale of infrastructure projects, this technology can absorb significant volumes of plastic waste, reducing the demand for landfill space and eliminating greenhouse gas emissions (such as CO2) and toxic pollutants (like dioxins) from incineration.   The technology owner is looking for collaborations (R&D, test-bedding and/or licensing) with oil industry companies, road paving companies, building and construction industry players, waste management centres, institutes of higher learning (IHLs), and government agencies.  The technology incorporates several proprietary systems designed to efficiently process mixed plastic waste. These include:  Sink-float vessels: Provide high separation efficiency, allowing for the effective separation of mixed plastic waste based on density.  Calibration library: Offers accurate real-time measurement of the composition of as-received mixed plastic waste, ensuring precise processing.  Compositional adjustment/standardization unit: Standardizes the composition of mixed plastics to meet industry requirements for infrastructure applications.  Advanced Mechanical Recycling (aMR) process line: A cutting-edge process line that converts mixed plastics into usable raw materials, such as polymer modifiers, for incorporation into bituminous mixtures. These technical features enable the transformation of contaminated, mixed plastic waste into standardized, valuable products for the construction industry.  Substitute for commercial polymer-modified bitumen in asphalt road pavements.  Substitute for commercial polymer modifiers in waterproofing materials.   Coatings and paints for marine, floating, coastal protection, and underground structures.  First-of-its-Kind Technology: Allows direct use of as-received mixed plastics from MSW without the need for costly and complex sorting processes.  Standardized Materials for Infrastructure: Processes mixed, contaminated plastics into standardized materials used in construction, such as polymer-modified asphalt. Consistency Through NIR Calibration Model: Uses a Near Infra-Red (NIR) calibration model and machine learning based on NEA’s plastic composition data to ensure consistent quality of mixed plastic waste.  Enhanced Bituminous Mixtures: Improves technical properties of bituminous mixtures by creating a 3D cross-linked polymer structure within the matrix, enhancing durability.  Cost Savings: Offers 15%-25% cost savings compared to conventional polymer-modified bitumen.  Environmental Impact: Reduces waste going to landfills and incineration, providing a sustainable solution for the construction sector. recycled mixed plastics, polymer modified bitumen, asphalt wearing course, binder testing, environment testing, microplastics, ground water Waste Management & Recycling, Industrial Waste Management, Sustainability, Sustainable Living