Chalmers Open Digital Repository
Not a member yet
26247 research outputs found
Sort by
State-of-the-Art Bioacoustic Classification of Nordic Birds and Bats using Machine Learning
No full textMachine Learning-Based Tire Model Optimization
No full textWhen developing new vehicles, accurate tire models are crucial for simulating realworld driving behavior. However, inconsistencies in measurement and fitting methods between tire manufacturers introduce bias, leading to different models for the same physical tire.
This thesis proposes a method to correct such bias by translating biased tire models into unbiased ones using supervised learning and reinforcement learning (RL). Initially, three supervised classifiers, Artificial Neural Network, Gaussian Naive Bayes, and Random Forest, were trained to identify the origin (manufacturer) of a tire model, serving as a proxy for the unbiased data. RL models were then formulated to optimize towards this classifier proxy, where the agents aimed to reach states the classifier predicted as “unbiased”. To find a good policy, two different RL algorithms were investigated.
The Random Forest classifier demonstrated the highest accuracy, predicting the origin of a tire model with 97.0% confidence. However, the translation results, evaluated by Mean Squared Error, were mixed. While the RL agents learned to improve the classifier’s assessed probability, only some translated curves showed improvement.
Future work may improve the results through systematic hyperparameter tuning of the RL environment and agent. Additionally, access to more labeled tire model data would enable a more precise assessment of variance and bias, supporting the identification and analysis of underlying measurement errors. Despite the limitations, this thesis demonstrates the potential of combining supervised learning and RL for bias correction in tire modeling
3D Bioprinting of Soft Matter
No full text3D bioprinting is an emerging technology that has transformed various industries
with its remarkable precision and accuracy in the construction of complex structures.
It has found diverse applications across fields such as healthcare, medicine,
and chemical industries. However, identifying the optimal parameters to achieve the
best printing outcomes remains a significant challenge worldwide. This thesis addresses
one such challenge, focusing on the optimization of the printing parameters
to enhance performance.
The primary focus of this research is the 3D printing of soft matter and the essential
prerequisites for ensuring material printability. Throughout the study, various
complex materials have been explored and tested to determine the optimal process
parameters for successful printing. Additionally, this research explores the various
applications for which printed soft matter materials can be utilized. During optimization
of the parameters for 3D printing, attention is also paid to the potential
uses of these materials in various fields, highlighting their versatility and practicality
Utveckling av mätmetod för att bestämma glidfriktion vid längdskidåkning
No full textCross-country skiing is a major sport where many different parameters influence an athlete’s performance. One such parameter is the friction between the ski and the snow. Skiers have been trying to reduce this friction ever since the sport began. Today, this is primarily achieved through various surface treatment methods, including both waxing and base structuring. However, one ongoing challenge is to measure the effectiveness of these methods in a quantitative and scientific manner. The aim of this project was to develop a method for measuring the coefficient of friction in cross-country skiing in a way that is both scientifical and user-friendly. A motion equation was developed to describe the relationship governing the coefficient of friction in skiing. This was followed by a literature review of existing solutions. Based on the insights from this review, a development process was carried out to create a measurement technique and corresponding test methods to validate it.
The project resulted in a measurement system consisting of an IMU, a custom software solution, and either magnets or photocells. The method was tested through glide tests indoor in the Skidome ski facility in Gothenburg. Each test involved a 15 meter long glide phase at speeds of up to 6 m/s. The results demonstrated that the technique was capable of detecting differences in friction with a precision better than ±0.005.
The conclusion of the project is that the equipment provided useful data that could be of value to recreational skiers and in training environments. Further development of the software and an upgraded IMU could potentially provide sufficient precision to compare different types of glide wax at an elite level
The role of suppliers in the market of reused construction materials A supply chain perspective
No full textThe construction industry is the industry that is using the largest amount of natural
resources. The model of the construction industry has for decades been to “take,
make, use, dispose”, a linear model not allowing materials in properties to be reused.
Changing the construction industry to a circular model including reuse of construction
materials is a way to reduce the impact on the climate from the construction industry.
The suppliers of construction materials possess an important role in the
transformation of scaling up the market of reused materials. Thus, the purpose of this
thesis is to identify and analyze the Supply Chain role of suppliers in the market of
reused construction materials. The research is based on interviews with 29 actors in
the construction industry. First, actors involved in three projects were identified and
interviewed, to create a holistic view of how the market of reused materials function.
Thereafter, other actors, for instance suppliers, were interviewed to create an
understanding of how different stakeholders in the construction industry work with
reused materials.
The interviews resulted in information about three projects and the processes of
working with reused materials from a supplier’s and reuse hub’s point of view.
Furthermore, it contributed with information about market drivers for the reuse
market, challenges, collaboration and opinions about the future of the reuse market.
Seven actors were identified as included in the market of reused materials. These are
property owner, construction company, reuse consultant, supplier, reuse hub,
architecture firm and demolition firm. Furthermore, several resources controlled by
the actors and activities performed by them were identified.
A number of key factors influencing the reuse market is discussed in the thesis. These
factors are environmental sustainability, costs, market requirements, collaboration,
communication, procurement process, logistics, matching supply and demand, and
supplier capacity.
The result from the study implies that suppliers possess an important role in the
transformation of the reuse market. There are four main activities suppliers should
implement to establish work with reused materials. First, they need to adapt
operations to enable circular flow. Secondly, they need to focus on the take back
process. Furthermore, the process at the suppliers must be updated, and finally the
selling process of reused materials needs to be implemented
Empirical Determinants of Enterprise Value in M&A Transactions A Cross-Sector Regression Analysis of U.S. Small-Cap Public Company Deals (2005–2025)
No full textExisting methods for calculating a firm’s enterprise value (EV) inherently depend
on subjective estimates and assumptions leading to variability based on the practi-
tioner’s judgment. This thesis uses a deductive, quantitative approach to investigate
which factors influence EV in mergers and acquisitions (M&A). The analysis is based
on secondary data from Capital IQ, covering U.S. small-cap public M&A transac-
tions between 2005 and 2025. Using ordinary least squares (OLS) regression , the
results show that market capitalization, net debt, and total assets are significant pre-
dictors of EV. These findings suggest that these financial variables play a key role
in determining the value of a company in M&A deals. This data-driven valuation
method offers a more objective alternative to traditional approaches
Measuring and Pricing the Value of Anti-Counterfeiting Services A Case Study in Agriculture
No full textCounterfeiting poses a significant threat across global industries, including agriculture, where it compromises food security, harms brand reputation, and leads to considerable economic losses. This thesis explores the value of anti-counterfeiting services through a case study of AGDA, a global agricultural company facing increasing counterfeit challenges. The purpose is threefold: (1) to determine how the value of anti-counterfeiting activities, specifically monitoring, detecting, and taking down counterfeits, can be measured; (2) to develop a pricing framework for offering these services to external parties; and (3) to identify the types of industries where such services can deliver the greatest value.
The study employs a mixed-methods approach, combining a comprehensive theoretical framework with empirical data from qualitative interviews and internal documents from AGDA. The theoretical portion draws from literature on customer value, brand valuation, pricing strategies, and counterfeiting typologies. Empirical findings highlight five core values driving customer preference for AGDA, quality, innovation, technical support, distribution network, and brand reputation, while also detailing regional differences in counterfeiting awareness and behavior.
Analysis reveals that the value of anti-counterfeiting services is multidimensional, incorporating not only direct cost savings from confiscated goods but also brand protection, customer loyalty, and emotional value. Moreover, in industries such as agriculture and pharmaceuticals where counterfeiting is deceptive, anti-counterfeiting services provide the highest value. When applying a pricing framework, traditional cost- and competitor-based pricing strategies are limited in capturing this full scope of value. Instead, value-based pricing, combined with service pricing theory, is identified as the most appropriate model since it supports a high degree of value appropriation. Recommendations are provided for AGDA to further develop its service offering, engage external clients, and refine its pricing model based on contextual industry characteristics
Automatic Robot Trajectory Generation for Sealing Applications
No full textAutomatic robot trajectory generation can reduce production time and material use
in automotive manufacturing. This thesis proposes a geometric approach to formulate
a nonlinear constrained optimization problem. The objective is to compute
an initial Tool Center Point (TCP) path that achieves a uniform height distribution
along two curves that define the desired sealant edges. The initial TCP path
yields sufficient trajectories for a wide range of curves. However, in scenarios involving
sharp edges, some limitations related to the physical limitations of mechanical
devices restrict the range of feasible sealants. The geometric approach does not
consider all complex sealing behaviors. To capture the complexity of the sealing
process while maintaining fast validation, a neural network was developed that predicts
sealant cross-sections along a TCP path. An obstacle course that introduces
unseen kinematic and spatial features was created to validate the network. The
network performs well on simple geometries, but more development is required for
the model to be deployable in practice. The geometric approach and the surrogate
model build a framework for further optimization of the TCP path
Shifting narratives: Stripping layers of time to reveal hidden maritime heritage
No full textTransformation is inevitable. It happens spontaneously, as well as intentionally. This thesis deals with architectural and social values associated with the many renovations and alterations of Amerikaskjulet, an industrial building of Gothenburg.
In its glory days the area was bustling with activity, as Amerikaskjulet not only was a warehouse of incoming goods but also a terminal for thousands of people travelling with, or just witnessing the greatness of, the America ships. Eventually, however, the departures ceased and in the 1980’s the building was transformed into an office building.
This transformation, and renovations of Amerikaskjulet prior to that, have been brutal.
The building is now altered into anonymity. The building has lost its prominent features and thereby its beauty. It is a collection of layers presenting an awkward pile of materials. On the facade, some details are still resembled but from the inside it looks like any other office building from the 1980’s.
For this thesis, I am imagining Amerikaskjulet as layers of time, seeing the many interventions the building has had. This thesis is an investigation and application of a method. Through the method of stripping and slow dismantling of materials, the layers and what’s beneath them is uncovered. I am illustrating Amerikaskjulet in the stripping phase with collage techniques.
During the stripping, waste material from the dismantled objects has occurred, which is then integrated in the project. Thus, this thesis also suggests concepts of adaptive reuse of materials in Amerikaskjulet.
Although the adaptive reuse is the final act of the thesis, it doesn’t stand alone as the thesis’ result. The process of uncovering and stripping is the project’s core and should also be read as the thesis’ result.
By transforming old buildings in a slow way and at the same time retrospecting to find other values that are not evident at first glance, heritage can be maintained and revived