Machine Learning and Vision for Waste Management System

Project Description Using Machine Learning and Machine Vision tools, detect and report events of interest recorded by cameras installed on trucks in the waste management industry. The objective is to identify in real-time key events and generate alerts for a vehicle operations monitoring system. Examples of interesting events are people or animals in front of the vehicle, bins being picked up and lifted, and unexpected scenarios. As the vehicles operate outdoor under all weather conditions, external factors such as lighting and precipitation can influence outcomes. The objective is to solve real world problems currently encountered in the waste management industry using advanced ML and MV algorithms. Data sets and programming tools will be provided. Key Project Activities 1) Select two widely-used ML libraries/SDKs for Microsoft Windows with good Machine Vision capabilities. 2) Design test data set and choose appropriate algorithms to train for event detections. Code must be written in one of C# or Python. 3) Optimise for real-time data processing. 4) Write report summarising findings, challenges, and notable details. Ideal Roles and Responsibilities This project is ideal for students with a strong background in computer science, engineering, or mathematics. Programming experience, especially with .Net framework, C#, Python, and Machine Learning/AI tools would be highly desirable. Ideal candidates are those in their final year of study and have completed a number of advanced computing and math courses. Familiarity with image processing, cameras, optics, image file and video formats (.png, .jpg) are also important. Final Project Deliverables 1) Two complete solutions (code and data) using different Machine Learning tools that are capable of detecting with high accuracy Events of Interest. 2) Comprehensive final report describing how the solutions work, how they compare to each other, what their relative strengths and weaknesses are, performance data, etc. Requirements Programming using Visual Studio or Visual Studio Code, object oriented language such as C++ or C#, good understanding of relational databases, data structure concepts, Machine Learning/AI, Machine Vision, Python. Strong math and statistics background advantageous. Ideally 2 to 3 students will work cooperatively on this project remotely within Canada. Our offices are in Alberta and BC.

Machine Learning Modelling of Personality Traits

Positions available: one to two students The project’s goal is to create an initial framework for a Machine Learning project which will be used in finding patterns and making predictions about personality traits of people who apply for certain types of jobs. The question we want to ask: are there relationships between personality traits and people who apply for certain types of occupations? For example, do extroverted people gravitate towards people-facing occupations more often than introverts? Do anxious people gravitate towards certain types of jobs? In this project the student will help Maxus lay the foundations for a ML application which will be used in answering these questions. STUDENT TASKS Setup project on GitHub Work with mentor to design a ASP.Netcore/C# webpage to use in evaluating Machine Learning algorithms with respect to our project goals. Enhance existing webpages to help users visualize data from a graph database. Written report on the pros and cons of the selected ML toolsets and especially the challenges within the early stages of the learning curve. The ideal candidate will have basic understanding and interest in relational databases, Visual Studio, C#, SQL, .Net, Machine Learning/AI concepts, webpage design using ASP.Net. COMMUNICATION We will communicate with the student using emails, phone, video, and instant messaging.

Machine Learning Product Evaluation

Positions available: one individual student This is a market research and technical evaluation project into various commercial Machine Learning (ML) products. The main objective is to give Maxus a birds-eye view of the pros and cons and capabilities of selected ML systems in relation to the application of personality assessments for the hiring process. For the chosen set of Machine Learning packages, determine how each one stacks up against the others along key metrics: pricing, hardware platforms supported, developer community size, connectivity, software language support, performance, algorithm library, product maturity, strengths and weaknesses, market share, etc. The ideal student for this project is interested in Artificial Intelligence/Machine Learning, Big Data, market research, databases, and a passion for technology. Creativity, good communication skills, and resourcefulness are especially important for project success. STUDENT TASKS Work with mentor to design a ASP.Netcore/C# webpage to use in evaluating Machine Learning algorithms with respect to our project goals. The ideal candidate will have basic understanding and is familiar with relational and/or graph databases, Machine Learning/AI concepts, social media, market research. Knowledge of software development languages would be useful: C#, Python, Javascript, Java, Html, Json, Xml. Key deliverable: Create a written report on the pros and cons of the selected ML toolsets and especially the challenges within the early stages of the learning curve for using each one. COMMUNICATION We will communicate with the student using emails, phone, video, and instant messaging.

Machine Learning Research with Neo4j

Positions available: one individual student The project’s goal is to create an initial framework for a Neo4j-based Machine Learning project which will be used in finding patterns and making predictions based on a broad set of training data related to consumer and individual behaviour. Some of the things we will create: Standalone Neo4j database populated with a test dataset. ML models for pattern recognition and prediction. Configuration and testing webpage as user interface. The intent is to quickly climb the learning curve for Neo4j to understand the pros and cons of using this tool in a real-world application. In this project the student will help Maxus lay the foundations for an ML framework to be adopted for use in our clients’ respective industries at a later date. STUDENT TASKS Work with a mentor to create a Neo4j graph database to store training data that will be used for ML modelling and predictions. Create a webpage and using GraphQL build a simple querying and testing tool for the database. Participate in data modelling, coding, and web design. The ideal candidate will have basic understanding and interest in relational databases, Visual Studio, C#, SQL, .NetCore, Machine Learning/AI concepts, webpage design using ASP.Net. COMMUNICATION We will communicate with the student using emails, phone, video, and instant messaging.