AI-Powered Virtual Shopping Marketplace Platform for the Hair Integrations Industry
The average wig industry revenue over the last five years has a steady growth to $415.2 million per year. This industry caters to four distinct consumer groups: 1) individuals that purchase wigs for aesthetic purposes, 2) those that have lost their hair due to a medical condition or treatment, 3) those that follow their religious practice for specific hair restrictions, and 4) film/theatre directors who purchase wigs as part of character costumes. A wig costs from $600 to $1500 or more. In addition, with the COVID-19 outbreaks, online shopping inevitably became the leading trends.
However, shopping for a perfect wig online is not an easy task. We will build an AI-powered marketplace to solve the problem. In the AI-powered marketplace, customers get expert advice from AI as if customers are served by domain experts. AI will extract customers’ head shape, skin tone, and personality from the image and video, and make the best recommendations.
An intelligent immersive content creation platform for the non-programmer for training, maintenance and assembly using AR and VR.
OVA’s StellarX is an uncompromisingly good virtual and augmented reality software. Purpose-built for teams that want to collaborate and create in those new paradigms.
Automated Assessment of Forest Fire Hazards
The proposed project is to develop a Deep Reinforcement Learning (DRL) model capable of using Light Detection and Ranging (LiDAR) data to automatically analyze whether there is a risk of forest fire due to vegetation management around electric equipment. The model automatically classifies points in a LiDAR scan to determine whether there is direct contact between vegetation and electric equipment and outputs control actions for an Unmanned Aerial Vehicle (UAV) that can autonomously inspect infrastructure as needed. Our research will focus on the solution of two different but complementary machine learning problems that the DRL model will have to solve to allow for a UAV to autonomously acquire data with sufficient quality for fire risk assessment. Firstly, there is the problem of perception, i.e., to analyze raw LiDAR data and deduce classifications of individual objects and their shape and orientation. Secondly, there is the problem of control, i.e., to use the perceived state of the environment as determined by the first stage to adequately navigate through the environment until a complete scan has been obtained of the region that we are conducting a fire risk assessment for. Solving these two problems in a harmonious way that allows for an efficient, accurate and a complete scan of the environment is an open research problem in the domain of DRL that we aim to address.
Cloud Native Big Data Engineering and Automation
XLScout is a startup engaged in democratizing Innovation and connecting research and development with intellectual property (IP) departments across the world. The company is investing in developing proprietary algorithms, using Artificial Intelligence and Machine learning, to mimic the behaviour of an expert searcher. XLScout focus is on creating a sustainable and adaptive text mining framework that will provide natural Language Processing (NLP)based research outputs for IP in different domains. Various data points have been secured for our solution and they include patent data, litigation data, corporate data, reassignment data, examination data, and other patient-related data. XLScout hosts a data vault of about 130+ million patent documents which occupies approximately 8TB of storage. Document searching, in general ,is a cumbersome process, and specifically, searching the patent-related documents requires advanced strategies that a novice searcher might not be aware of. Therefore, this type of search requires extensive effort and time. The main objective of this project is to automate the patent and non-patent search effectively by allowing machines to understand users’ queries and thus, creating a sustainable and adaptive text mining framework that will provide NLP-based research outputs for IP search in different domains. Furthermore, this project aims to develop scalable solutions for XLScout’s data vault on which the company will run proprietary AI and ML models and generate high-value analytic solutions to help the customers make informed decisions.
Computer vision powered digital twin for tracking manual manufacturing processes
Over 70% of tasks in manufacturing are still manual; therefore, over 75% of the variation in manufacturing comes from human beings. Human errors were the primary driver behind $22.1 billion in vehicle recalls in 2016. Currently, when plant operators want to gain an understanding of their manual processes, they send out their highly paid industrial engineers to run time studies. These studies produce highly biased and inaccurate data that provides minimal value to manufacturing teams. This project aims to develop a computer vision powered digital twin prototype that is ready to test on the client’s site, which helps manufacturing plant operators gain unprecedented visibility into their manual production operations, allowing them to optimize their worker efficiency while maximizing productivity. This will be done by automated data generation using computer vision, conversion of raw data into useable information, visualization of information using standard Business Intelligence methodologies and lastly, prediction of future plant performance based on historical information, as well as information about other market drivers.
FinTech Deep Learning in Financial Modeling
The last four decades saw the development of the financial derivatives valuation technology. Only a few practical models, however, can be solved in closed form, and as most utilize numerical methods such as finite-difference partial differential equation solvers, discrete-time trees, or Monte-Carlo simulators, these traditional methods are quite slow. Running book valuation and risk processes on hundreds of CPU cores requires an overnight process to comply with regulatory and accounting standards. This creates a huge cost(~$10 million/year) and a commensurate environmental and carbon impact. Similar issues are now facing the Insurance industry due to the accounting standard IFRS 17. The key goal of the partnership is to develop deep learning, and more generally machine and reinforcement learning, models to accelerate these processes, and to provide efficient simulation engines for asset prices, volatility surfaces, derivative valuation, and hedging.
Deep Learning with Big Data for Innovation Acceleration
Presently, XLScout hosts data of over 130 million patents and 200+ million research publications occupying approximately 8TB of storage. Searching such a massive database using basic, mostly keyword-based search is very cumbersome and time-consuming. Moreover, it requires domain-specific knowledge about patents. With this project, XLScout aims to alleviate the pain of searching this massive system by employing machine learning (ML) and natural language processing(NL)techniques.Text autocompletion and recommendation will provide a better and smarter way for the end-users to search thismassive database. The auto-completion will be based on the corpus of patent documents and research publication to provide suggestions ofrelevant content. The MLmodel will be trained on that massive corpus taking into consideration language semantics. Techniques such as BERT and GPT 2/3 will be considered together with various pre-processing techniques. The size of the document database, document diversity, together with the subjectivity of desired results will make it challenging to evaluate such a system. We will employ both human-centric and automated evaluation approaches.Document categorization will also be based on the semantics, and it will group documents into labeled categories. Unsupervised techniques will be examined in their ability to do this categorization. However, different companies, XLScout clients, have different preferences in respect to this categorization. Therefore, an approach will be developed for the end-users to express their preferences by providing sample categories. Then, the model will learn from those preferences and carry out categorization. The challenge in this categorization is to enable unsupervised categorizationwhile supporting semi-supervision and customization. This categorization will be client-company specific and the modelwill have to learn from a limited number of example classes identified by the end-user.
Detecting and Responding to Hostile Information Activities: unsupervised methods for measuring the quality of graph embeddings
The rise in online organized disinformation campaigns presents a significant challenge to Canadian national security. State and non-state hostile actors manipulate users on social media platforms to advance their interests. Patagona Technologies is a Toronto-based software development company started by two Ryerson alumni. The project with Ryerson University is a larger initiative with the Canadian Department of National Defense to address the challenges posed by online hostile actors by analyzing the structure and content of social networks.
Developing Efficient Machine Learning Models for Price Bidding
Curate Mobile operates a demand site platform (DSP), which is an advertising platform responsible forbidding in real time ad placements from various publishers. This process is a blind auction, happeningover 50,000 times a second, and during this bidding process we have less then 100ms to determinewhich of our clients should bid for this ad placement, how much it might be worth to them, and whatprice we believe we can win this auction for. During this project, we will add machine learning modelsto our DSP to provide fast decisions in real time to maximize the return on ad spend of our clients’campaigns. The main goal for this project is to add a proof-of-concept machine learning model to CurateMobile’sDSP, with a pipeline that will continually update the models with new data as it is ingested. Wewill also design a validation module to monitor and validate the performance of the developed models.
End-to-End Machine Learning Based Demand Forecasting
This project aims to implement an end-to-end (E2E) Artificial Intelligence (AI) / Machine Learning (ML) driven demand forecasting predictive model pipeline to increase process efficiencies, help improve forecast accuracy, forecast bias and forecast value added and unlock trapped capacity in the business ensuring improved service, optimum inventory, better production scheduling and better P&L forecasting. As participants in this consortium, Unilever, Larus and SOSCIP bring unique contributions that augment the benefits of the initiative from both scientific and business perspectives. More specifically, Unilever brings unique knowledge of business and operational landscape, curated and diverse data sets and analytics expertise in story building and turning data into insights, Larus brings unique expertise in AI/ML decision making and optimization systems and SOSCIP provides the required high performance computing platforms to run ML algorithms utilizing large data sets with optimal performance.
Unilever Canada Collective Intelligence Platform
We propose to develop a demand forecasting pipeline that collects data and applies machine learning models to make accurate predictions of future demands under unstable scenarios. In particular, this project will focus on efficient forecast of Unilever’s base SKUs and involve model development based on time-series, machine learning and possibly combinations of the two, data engineering to identify critical features hinting future trends, and deployment of the models to the existing business process. Methodologies that will be used to support Collective Intelligence (CI) decision-making platform include time series methods like vector autoregression and vector error correcting model; machine learning methods like random forest and deep learning etc. The Machine learning-based demand forecasting for supply chain optimization method should be able to deliver on each component and seamlessly integrate applications to the main platform that runs in a Microsoft Azure environment.
Workplace of the Future
Ambient factors such as light, heat, and music can significantly impact physical comfort in employees. Additionally, affective states and cognitive load of workplace occupants can affect their quality of life, general happiness, and cognitive capacity. This research aims to design and develop a smart workplace capable of detecting, analyzing, and acting on the environmental ambient factors, thus optimizing both physical comfort and happiness in employees in the workplace. To achieve this goal, this project targets the development of tools and methods using artificial intelligence, machine learning, and deep learning for ubiquitous monitoring, analysis, and interpretation employee happiness, cognitive load, and physical comfort based on information obtained from a variety of different wearable and non-contact sensors. Moreover, algorithms and models will be developed for aggregation of individual preferred and perceived ambient conditions, and cognitive/affective states. Finally, the obtained information will be used to autonomously and intelligently tune ambient and organizational parameters for optimum employee happiness, comfort, and performance. With the recent COVID-19 pandemic and the necessity for organizations to adopt to new workplace models, particular attention will be paid to distributed and remote working conditions. Machine learning will be used to understand affective and cognitive factors such as happiness, stress, and cognitive load from remote audio and video calls in addition to wearable sensors where possible.