Machine learning prediction on embedded systems

Machine learning (ML) applications have shown remarkable performance in vanous intelligent tasks but high computational intensity and large memory requirements have hindered its widespread ubhzation in embedded and Internet of things devices due to resource constraints.
Many optimization techniques have been proposed previously for domain specific architectures. These optimizations will affect an embedded device differently. and each of them have their own trade-offs and Impact speed, accuracy and energy efficiency differently.

The importance and multi-dimensional approach of marketing strategy in the data security industry

As a customer you expect your personal and sensitive data to be kept safe in the company’s storage and to be handled confidentially. But that is exactly among others one of the biggest challenge for businesses nowadays. Therefore, they need the best partner in IT and data protection by their side. Data security and protection solutions are offered by several software companies to address the issue. But how can businesses find the best suitable solution? That is when marketing strategy of the software companies comes into play.

Eye Gazing Enabled Driving Behavior Monitoring and Prediction

Automobiles have become one of the necessities of modern life, but also introduced numerous traffic accidents that threaten drivers and other road users. Most state-of-the-art safety systems are passively triggered, reacting to dangerous road conditions or driving behaviors only after they happen and are observed, which greatly limits the last chances for collision avoidances. Timely tracking and predicting the driving behaviors calls for a more direct interface beyond the traditional steering wheel/brake/gas pedal.

Improving Human-centric Facility Management through Machine Learning Analysis and Visualization

Buildings represent up to 40% of primary energy consumption. To optimize that energy cost vs. the comfort of its occupants, Facility Management (FM) relies on data from sensors, and on automation, to increase efficiency. The majority of existing buildings however have limited automation, so it is up to Facility Managers to interpret and act upon the information resulting from the various building sensors. This is often difficult without the appropriate contextual information to guide and support decisions.

Characterization of back-illuminated complimentary metal-oxide semiconductor detector arrays for CASTOR

We seek to test the behaviour of candidate detectors for the proposed CASTOR space telescope. We are focused on the response to dim images, the behaviour when resetting portions of an image during exposure, and the behaviour when using multiple reads throughout an exposure to reduce the effect of random noise generated when reading the detector. We will do this by performing these readouts on the detectors when they are illuminated by a known light source under laboratory conditions in a cold vacuum chamber.

NOVA (Network Optimized Video Analytics)

Project NOVA will build on the University of Ottawa and Ciena’s advanced analytics capabilities to allow networks around the world to understand where video flows run over their network.  This will allow the network operators to improve video Qualify of Experience for their end customers, more quickly and cost effectively fix video impacting network problems, plan their networks to better support video, and provide greater customer service awareness of end customer over the top video quality. Ciena anticipates this capability will propel it into be the world leader in network video analytic

Intelligent Vision Based Navigation Systems

Utilizing geomatics sensors such as laser scanners, GNSS, Inertial Navigation Systems (INS), and photogrammetry cameras to provide mobile mapping solutions has been studied and utilized extensively in the past three decades. The data fusion between high-end mobile mapping systems such as laser scanning and imagery-based systems, and low-cost camera systems are still a fertile field in digital transformation. The anticipated outcome of this project is a software development kit (SDK) that enables data fusion between high-end mobile mapping systems and low-cost camera systems.

RLCapture: A deep reinforcement learning based control strategy forswitching between motion capture inspired controllers.

Making robots walk and balance as well as humans is extremely difficult. New techniques involving machine learning have shown promise in getting robots to mimic the movements of humans recorded using motion capture
technology widely used for videogames and movies. While these techniques show promise, they are still in development, and have difficulty switching between behaviours. It’s still very difficult for robots to go from standing still to running. They also fall over very easily when pushed or tripped, since they don't have a concept of reacting to pushes in the same way that people do.

Comprehensive study of VCSEL-MMF coupling techniques

Vertical cavity surface emitting lasers (VCSELs) are in high demand in short-reach optical interconnects. Reflex Photonics is a leading company in developing VCSEL-based optical transceivers for the harsh environments. So far, the speeds up to 12.5 Gb/s for a reach of 100 m have been achieved. One of the key bottleneck in developing rugged transceivers is the loss associated with the coupling light from the VCSEL to the multimode fiber (MMF). By analyzing the overlapping modes from the VCSEL to the MMF, the optimum launching condition can be determined.

Materials Selection & Design Strategies for Impact Resistance in Hand Protection

The needs for protective equipment are many, and range from use at home to many industrial sectors, such as: construction, mechanics, forestry, oil and gas, health, and manufacturing. There are many reasons to wear protective equipment: to provide improved grip and resistance to chemical exposure, pathogens, heat, cold, abrasion, punctures, cuts, crushing, and impact. In this research, we will focus on gaining detailed scientific and ergonomic understanding of how to design materials and structures to be used on the back of the hand to improve protection from mechanical impacts.