Chalmers Open Digital Repository

Välkommen till Chalmers öppna digitala arkiv!

Här hittar du:

Studentarbeten utgivna på lärosätet, såväl kandidatarbeten som examensarbeten på grund- och masternivå
Digitala specialsamlingar, som t ex Chalmers modellkammare
Utvalda projektrapporter

Forskningspublikationer, rapporter och avhandlingar hittar du i research.chalmers.se

Enheter i Chalmers ODR

Välj en enhet för att se alla samlingar.

Visar 1 - 2 av 2

Senast inlagda

Statistical Inference with Auxiliary Information under Block-Structured Missing Data

(2026) Holmberg, Linnéa

In medical research, a common challenge is missing data. Missing data can lead to biased findings and loss of precision if not handled appropriately. Common methods of handling missing data are complete-case analysis (CCA), multiple imputation (MI), or inverse probability weighting (IPW), but these methods have drawbacks. This thesis aims to compare these methods to the method augmented inverse probability of completecase weighting (AIPCCW), that is less established but with certain desirable theoretical properties. AIPCCW is an extension of inverse probability of complete-case weighting (IPCCW), and utilises information from both participants with fully observed data and participants with partly observed data. AIPCCW utilises two models, one for the outcome and one for missingness, where only one model is required to be correctly specified for AIPCCW to achieve unbiased inference. This thesis implement and compare AIPCCW, CCA, MI, and IPCCW in different scenarios through a simulation study and a application study on real-world data. The scenarios cover unique combinations of sample size, proportion of missing data, levels of correlation between variables with missing values and with an auxiliary variable, and different missingness mechanisms. In our experiments, the AIPCCW method demonstrate a performance in bias and eRMSE statistically significantly better than CCA, MI, and IPCCW, in certain scenarios, especially in simulated scenarios with a large proportion of missing data. AIPCCW is found to significantly improve in scenarios with a higher correlation between the variable with missing values and the auxiliary variable. On the other hand, the performance of AIPCCW is found to not outperform CCA, MI, and IPCCW in a majority of the scenarios that were implemented. AIPCCW performed comparable to CCA and IPCCW on realworld data in this study, but AIPCCW could potentially perform better on real-world data if a stronger correlation between the variable with missing data and the auxiliary variable existed. Owing to these results, the evaluation is inconclusive to whether AIPCCW is significantly better than CCA, MI, and IPCCW. This thesis concludes that AIPCCW is a stable method, but does not necessarily recommend it over more common methods. However, further research is needed.

AI Assisted matching in Mergers And Acquisitions

(2026) JOHNSON SWEGMARK, WILHELM; TVEDT, DIDRIK

Traditional buyer identification in M&A relies on manual screening and professional networks, making it resource-intensive and naturally limiting the buyer pool. This thesis investigates whether textual embedding models can support the identification of relevant potential buyers in mergers and acquisitions. The study examines how different representation methods, including TF-IDF, Doc2Vec with smooth inverse frequency weighting, and Transformer based models, capture similarity between companies when applied to standardized summaries of portfolio company descriptions. The summaries are created using a large language model with information provided on the portfolio companies websites. The performance of the embedding models is evaluated through visualization of the embedding spaces, cosine similarity search experiments, and an expert review of buyer recommendations. The results indicate that TF-IDF and the Transformer model produced relevant recommendations, with the Transformer model demonstrating the best performance in embedding space separation and alignment with expert judgment, while Doc2Vec models showed weaker differentiation between company types. Overall, the study shows that embedding based similarity search can serve as a useful first step in buyer discovery by expanding the range of potential buyers considered and improving efficiency. The work also highlights that further validation across a larger set of targets and with a more complete dataset would strengthen confidence in these results.

Navigation and Localization for Railway Inspection Drone in GPS-denied Environments: An Investigative Study of Modular SLAM Baselines and End-to-End Learning-based Approaches

(2026) Wang, Guanfei

Autonomous navigation in GPS-denied environments remains a critical challenge for unmanned aerial vehicles performing infrastructure inspection. This thesis investigates the feasibility of learning-based navigation for railway-inspection drones by first constructing and analyzing a state-of-the-art modular baseline and then evaluating emerging end-to-end paradigms. A high-performance navigation system combining FasterLIO SLAM with Fast-Planner trajectory generation is implemented in high-fidelity simulation and used as an analytical baseline. While the system successfully navigates dense forest environments, controlled experiments reveal three structural failure modes—SLAM localization drift, flight-controller tracking limitations, and planner-induced trajectory constraints—highlighting deeper challenges such as cumulative error propagation and real-time sensor–compute bottlenecks. Building on these insights, the thesis conducts an experimentally grounded feasibility study of three dominant end-to-end learning directions: predictive worldmodel architectures, self-supervised representation learning pipelines, and visionreinforcement- learning approaches. By implementing prototype models and stresstesting their stability and data requirements, the study identifies several infeasible or unstable directions—such as feature-forecasting models and self-distillation objectives— and reveals simulator limitations that currently block scalable vision-RL for UAVs. Rather than delivering a complete end-to-end navigation system, this work provides a systematic evaluation of the landscape, clarifies the fundamental obstacles facing learning-based navigation in GPS-denied environments, and establishes concrete design requirements and a research roadmap for future PhD-level research.

Adaptive Cabin Climate Control for Battery Electric Vehicles Using TD3 Reinforcement Learning

(2025) ABUKAR, ABUBAKAR

The transition from combustion engine vehicles to Battery Electric Vehicles (BEVs) has increased the importance of efficient thermal management in trucks. Conventional cabin climate control methods prioritize transparency and safety but lack adaptability, limiting potential energy savings. This thesis addresses this challenge using the Twin-Delayed Deep Deterministic Policy Gradient (TD3) combined with a novel surrogate model, the Twin Fourier Neural Operator (Twin FNO), designed to capture cabin thermodynamics through partially enforced physics and dual output heads for improved accuracy. The Twin FNO predicts average cabin temperature with a mean absolute error of 0.55 °C while being 180 times faster than numerical solvers. Integrated into the TD3 framework, the agent effectively balances energy efficiency and thermal comfort. It maintains the setpoint temperature when energy is abundant and deliberately creates an offset when energy is limited, achieving up to 40% reduction in Heating Ventilation and Air Conditioning (HVAC) energy consumption with a 6 °C temperature deviation. These results highlight the potential of reinforcement learning and surrogate modeling to enable energy-adaptive thermal control strategies in BEVs while raising questions on acceptable thermal comfort trade-offs.

A study on gap acceptance in roundabouts in Sweden

(2025) Hansson, Victor

Traffic levels and congestion is rising both globally and in Sweden and is causing issues related to time loss, health problems and pollution. Traffic analysis software is a powerful tool to help planning and optimization of the road network to tackle these issues and the accuracy of their predictions is of a vital importance. This thesis aims to examine the use of a new method to collect data regarding gap acceptance parameters. The method consisted of recording video footage of three different roundabouts in the Greater Gothenburg area and implementing the AI-based video analysis software GoodVision to extract data from the recordings to then analyze the gap acceptance parameters. Raff’s method was used to calculate critical gap values at all roundabouts at 3.68 seconds, 3.81 seconds and 3.86 seconds respectively. Making up a combined critical gap value of 3.73 seconds. Comparative analysis was performed by using the traffic analysis software SIDRA Intersection and measuring the results of using the critical gap value based on the data collected at the location and the standardized critical gap value in the program. The results showed substantial differences, one scenario displayed an increased capacity reaching up to 25% when using critical gap values calculated from local data. Differences in results of this magnitude greatly affects the decision making in traffic planning and could ultimately be the difference maker between investing in new infrastructure or not. Parameters affecting why a gap is accepted or rejected were analyzed by implementing machine learning classification algorithms. The results showed that the individual driving behavior of each driver had a higher impact on the decision of accepting or rejecting a gap than roundabout geometry or vehicle type in this thesis.