As the population increases so does the waste that is generated. Manually recycling waste is expensive and slow. Computer Vision (CV) solutions aim to make this less expensive and faster. Lots of data of this waste (thousands of images) is needed to train these CV solutions. This project, called Synthetic Waste Generator (SWaG) can create synthetic waste data through the use of Blender and Python. Moreover, this project makes a contribution to the current state of research by having developed an automated synthetic data generation pipeline. This synthetic data can be used to train CV solutions to enable automated recycling procedures. With the help of adjustable parameters, the synthetic data can be customized, such that different unique images of waste can be created deterministically based on a seed. Furthermore, SWaG is fully portable as it has been containerized using Docker which makes it extremely easy to obtain even faster results by running SWaG on an NVIDIA GPU enabled system as a single local container, on the cloud as a farm or incorporate it in a container-orchestration system such as Kubernetes. SWaG also crushes 3D models, to mimic real waste using soft body dynamics. The pipeline has also been suited to automatically generate COCO datasets by using masking and image segmentation techniques. SWaG can also add textures and different colors to the waste objects in the synthetically created image. Furthermore, with SWaG different conveyor belt setups at recycling plants can be simulated with the help of variable camera heights, conveyor belts, backgrounds and lighting conditions. SWaG is currently deployable and is being used and built upon by our client. After conducting empirical research experiments with SWaG, it is noted that its performance speed is linear as the amount of objects that are in a given scene increases. In fact, with between roughly 40 and 80 objects SWaG performs sub-linearly. This is an important performance criteria as images of trash on the conveyor belt often have tonnes of objects pilled up on top of one another. ... Read more

The most crucial choices a student will make is about which college and major they decide to join. Accord- ing to a statistical analysis performed by Koenig (2018) in the U.S. News World Report, majors such as Computer and information science, Engineering and Engineering technology yield the highest employment rates and salaries compared to other majors. In an article they wrote about the factors that influence youths career choices, Akosah-Twumasi (2018) argued that the knowledge of issues related to ’job security’ and ’salaries’ may pressure youth to choose a career path based on the benefits associated with a particular profession. This causes an influence in the decision making of a student who will not necessarily apply for a major they would enjoy doing, but instead their choice is going to shift to a more reliable major. Thus, many students will apply for studies such as Computer Science even though it might not be well-suited for them. Our team has been asked by the Delft University of Technology’s communication department to develop a Chatbot in order to help students with their decision making, and specifically students interested in the master program Embedded Systems. The communication department gave our team a set of requirements that needed to be fulfilled. The final product needed to be a chatbot with which it is possible to have a conversation on the Embedded Systems study program. It should coach the student into making a decision as well as be able to answer frequently asked questions. The chatbot needed to be accompanied by a content management system which should allow the communication department to modify some of the content of the chatbot as well as provide them with useful statistics about the interactions with the chatbot. Our team was also required to use the Rasa (2019) open source machine learning tool for conversational artificial intelligence as back-end of our chatbot system in order to provide feedback about this framework which might be used in future projects at TU Delft. ... Read more

Artificial Intelligence (AI) is increasingly affecting people’s lives. AI is even employed in fields where human lives depend on the AI’s decisions. However, these algorithms lack transparency, i.e. it is unclear how they determine the outcome. If, for instance, the AI’s purpose is to classify an image, the AI will learn this from examples provided to it (e.g. an image of a cow in a meadow). The algorithm can focus on the wrong part of the image. Instead of focusing on the foreground (cow), it could focus on the background (meadow). This way, by focusing on the background, it could produce a false output (e.g. a horse instead of a cow). To show this, an explanation is needed. For this reason, a variety of methods have been created to explain the reasoning behind these algorithms, called explainability methods. In this paper, six local explainability methods are discussed and compared. These methods were chosen as they were the most prominently used approaches for explainability methods for Convolutional Neural Networks (CNN). By comparing methods with analogous characteristics, this paper is going to show what methods exceed others in terms of performance. Furthermore, their advantages and limitations are being discussed. The comparison shows that Local Interpretable Model-agnostic Explanations, Layer-wise Relevance Propagation and Gradient-weighted Class Activation Mapping perform better than Sensitivity Analysis, Deep Taylor Decomposition and Deconvolutional Network, respectively. ... Read more