Abstract Accurately forecasting traffic in telecommunication networks is essential for operators to efficiently allocate resources, provide better services, and save energy. We propose Circle Attention, a novel spatial attention mechanism for telecom traffic forecasting, which directly models the area of effect of neighboring cell towers. Cell towers typically point in three different geographical directions, called sectors. Circle Attention models the relationships between sectors of neighboring cell towers by assigning a circle with learnable parameters to each sector, which are: the azimuth of the sector, the distance from the cell tower to the center of the circle, and the radius of the circle.
Abstract Time series forecasting is an important problem, with many real world applications. Transformer models have been successfully applied to natural language processing tasks, but have received relatively little attention for time series forecasting. Motivated by the differences between classification tasks and forecasting, we propose PI-Transformer, an adaptation of the Transformer architecture designed for time series forecasting, consisting of three parts: First, we propose a novel initialization method called Persistence Initialization, with the goal of increasing training stability of forecasting models by ensuring that the initial outputs of an untrained model are identical to the outputs of a simple baseline model.
Abstract A thorough regulation of building energy systems translates in relevant energy savings and in a better comfort for the occupants. Algorithms to predict the thermal state of a building on a certain time horizon with a good confidence are essential for the implementation of effective control systems. This work presents a global Transformer architecture for indoor temperature forecasting in multi-room buildings, aiming at optimizing energy consumption and reducing greenhouse gas emissions associated with HVAC systems.
Abstract Prostate cancer is the most common malignancy affecting men and thesecond-leading cause of cancer death in the US. To detect and classify the risk of prostate cancer, doctors perform screening of prostate-specific antigen (PSA) levels. In this Thesis we want to improve thisrisk classification with unsupervised machine learning methods, as thelabels of cancer or no cancer may not reflect the truth; given that canceris only considered as such after confirmation by biopsy and thus possi-bly leaving some patients with cancer with the wrong label.
Abstract Cancer detection is one of the leading research topics in medical science. Whetherit is breast, lung, brain, or prostate cancer, progress is being made to improve theaccuracy and timing of detection. Prostate cancer is the second most commoncancer in men and the sixth leading cause of cancer death among men in the world.Many prostate cancers are indolent and do not result in cancer mortality, evenwithout treatment. However, a significant percentage of prostate cancer patientshave aggressive cancers that rapidly progress to metastatic disease and are oftendangerous.
Abstract Modelling the behaviour and performance of cyclists during competition ahead of time has several useful applications to professional cycling teams. Although existing physics-based approaches perform reasonably well in this regard, they generally require several assumed parameters. Performance is also dependant on several variables which may be hard to quantify, such as a rider’s cornering ability and pacing strategy. The work presented in this thesis is a fully data-driven approach to speed pre- diction in time trials performed by elite cyclists.
Abstract The aim of this thesis was to predict the wind power production volume of a large geographical region given the Numerical Weather Prediction data (NWP) over the region using deep learning. Accurate production volume predictions is important for power grid balancing, production planning, and price estimation. Having an accurate forecast for the upcoming wind power production volume has become more and more important in the past years due to the fast increasing number of installed wind turbines and installed total production capacity.
Abstract With the growing inclusion of renewable energy sources, developing price models for intraday trading has become an essential task for many market participants in order to optimize the decision-making process. Yet the available literature on the topic has not been keeping up with the pace of increased intraday trading activity. We predict prices in the final hour prior to delivery on the German intraday market, utilizing Deep Learning techniques. This thesis looks into the usage of feed-forward neural networks and recurrent neural networks (LSTM and GRU).
