How can we make the connected home smarter and more energy efficient? Ecobeeâs research aims to address this question by making cutting-edge improvements to its smart home thermostat. There is huge potential to save energy in the residential heating and cooling space â homes with an ecobee smart thermostat can save up to 15% of their energy consumption. Ecobeeâs aim is to make use of customer-volunteered usage data in the creation of an adaptive agent which can control the comfort level in the home autonomously.
In this research project, a surcharge optimization algorithm will be developed to help the partner company to dynamically determine the premium charged for order pickup. The objective of the project is to smooth the demand curve for the order pickup timeslots: popular timeslots are congested, making it harder to deliver a positive experience, and other windows are idle, and overstaffed.
More and more companies are choosing to automate various aspects of their customer service using chatbots. While these chatbots are still in their technological infancy, they currently provide useful customer service to many people around the world. They will continue to become more desired by companies as a single chatbot system can engage millions of customers with minimal scaling costs. In these many interactions, there is a substantial amount of potential information to extract.
In this project, we propose to expand support of SOTI's MobiControl (MC) to Tizen Operating System. SOTI MobiControl has assisted numerous enterprises to overcome the management issues due to lack of security and improve business performance by monitoring the health and safety of employees, and increasing productivity, with the introduction of wearables and other IoT (Internet of Things) devices.
The pre-trained Bi-directional Encoder Representation from Transformers (BERT) model had proven to be a milestone in the field of Neural Machine Translation, achieving new state-of-the-art performances on many tasks in the field of Natural Language Processing. Despite its success, it has been noticed that there are still a lot of room for improvement, both in terms of training efficiency and structural design. The proposed research project would explore the detailed design decision of BERT on many levels, and optimize them wherever possible.
The aim is to understand how fibroblasts, the most common connective tissue in animals, and cancer cells interact with each other through image analysis. These co-culture imaging screens, containing fibroblasts and cancer cells, will help identify novel signaling mechanism involved in cancer. The objective is to apply deep learning techniques to these image-based assays to study interactions between and identify novel therapeutics that can make cancer therapies more effective.
Question Answering (QA) system automatically answer questions raised by users in natural languages, and it is a crucial component of a human-machine conversation system. A typical QA system collects human written question-answer groups and structures them in a database system. However, in order to answer questions that are semantically similar to the questions stored in the database but are worded differently, the QA system needs to be able to calculate the semantic similarity between different questions.
Based on the userâs geo-location, timestamp and other attributes (eg. time of day, past visit history and app behavior categories, etc.), a machine learning algorithm can be developed to find which cluster the users belong to. Overall, the data of geo-location and timestamp are used to roughly locate the potential clusters. This project will involve some techniques and algorithms like cloud computing i.e Google Cloud Dataproc, sliding windows, histogram and machine learning algorithms. The challenge of first phase would be coming up with a good way of estimating the number of clusters.
Health disparities arise as a result of long-standing societal disadvantage and discrimination. As machine learning models become more popular in the healthcare sector, understanding of current health disparities becomes even more critical. Without careful management of existing biases, the models can inherit and amplify health disparities, leading to highly undesirable clinical outcomes. This project focuses on health disparities in access to preventive care services. Preventive care services such as screening and preventive medicine allows for early diagnosis and timely interventions.
This work aims to explore software and hardware co-optimization for deep neural network (DNN) inference applications. Once a model is trained to sufficient accuracy, the model is used to make inference or predictions based on this trained model. With increasing performance, more people are using these models for tasks such as translation, self-driving cars and speech recognition. This has greatly increased the demand for high performance inference hardware.