Studentarbeten // Student Theses

Använd denna länk för att länka till samlingen:

https://odr.chalmers.se/handle/20.500.12380/1

Browse

Visar 1 - 20 av 394

3-D object tracking through the use of a single camera and the motion of a driverless car
(2021) Ovnell, Andreas; Chalmers tekniska högskola / Institutionen för mekanik och maritima vetenskaper; Benderius, Ola; Benderius, Ola
There has been a very large increase in interest and development of partially or fully driverless cars in recent years. For these driverless cars to function, they need to be able to navigate to their destination while avoiding nearby objects. This can be done using simultaneous localisation and mapping (SLAM). SLAM is the task of simultaneously creating a map of the surrounding objects while keeping track of the car’s position within this map. This thesis will look into the feasibility of using a single camera attached on a driverless car to perform SLAM on cones detected by the real-time object detection system You only look once (YOLO). Three different methods were tested. All of these require a calibrated camera that is capable of determining horizontal and vertical angles from the pixel positions. The first ‘triangulation’ method uses that the distance travelled and rotation between two frames is known. The second ‘plane projection’ method is an optimisation problem which consists of finding the variables which result in lowest error, and through this determine the cone distances and car speed. The map of the surrounding cones is moved according to the estimated velocity and rotation of the car such that the car is always placed at the origin, allowing for use of multiple detections to improve accuracy. The third ‘distance from cone height’ method works by using the size of the cone detections in order to determine the approximate distance of each cone, use this to determine the approximate angle of the camera and then use the median angle to make the final distance estimates. The triangulation method was shown to be completely unsuitable for mono-camera use. The plane projection method was shown to be unreliable, likely due to a relatively small number of visible cones and a too large noise amplitude of detections from YOLO. The distance from cone height method was shown to be the best out of the tested methods, as it was simple, fast and quite reliable. However, this method still had an error approximately 1.4 times larger than what is advertised by commercial stereo camera systems.
3D scenario generation using generative models
(2019) Ramazzina, Andrea; Chalmers tekniska högskola / Institutionen för elektroteknik; Kahl, Fredrik
A Bayesian machine learning approach to passive microwave precipitation retrievals
(2019) Norrestad, Teodor; Chalmers tekniska högskola / Institutionen för rymd-, geo- och miljövetenskap; Chalmers University of Technology / Department of Space, Earth and Environment
A machine learning-based approach to precipitation retrievals, using Quantile Regression Neural Networks (QRNNs), is developed for data from the Global Precipitation Measurement (GPM) mission. The retrievals are conducted within a Bayesian framework where the networks are trained to predict quantiles of the posterior distribution of rain rates, conditioned on passive microwave observations. In this way, rain rates are retrieved along with the associated retrieval uncertainties. The effects of including additional spatial information as input to the QRNNs are also investigated. Different QRNNs are trained and tested, first globally over oceans and then over the U.S Great Plains. In both cases, the performance of the QRNNs are compared to the Goddard Profiling Algorithm (GPROF), a state-of-the-art passive microwave retrieval algorithm. The primary results are those over oceans, where the QRNNs show great performance on similar levels as GPROF with respect to point estimate metrics such as the mean squared error. Furthermore, the QRNN retrievals are very fast, taking less than a millisecond per footprint on a standard computer. It turns out that extra spatial information improves the QRNNs, especially on making rain-no rain classifications with fractions of true positives and true negatives exceeding 0.67 and 0.96 respectively. Furthermore, the QRNNs manage to produce well calibrated quantiles, resulting in good confidence intervals to account for retrieval uncertainties. Over the Great Plains, the results are promising but are based on much smaller amounts of data and are thus less significant.
A Complex Systems Approach to Human Cultural Evolution
(2013) Allen, James; Chalmers tekniska högskola / Institutionen för energi och miljö; Chalmers University of Technology / Department of Energy and Environment
This thesis will use two abstract computational models to investigate a number of outstanding questions related to human cultural evolution. Using simulations explanations for a number of phenomena within the archaeological record will be put forward. These will include the discontinuous cultural evolution patterns, the broadening of human diet and the extinction of the Neanderthals. The central theme throughout these findings is that it is the delity of transfer, and by extension the increase in complexity of early hominid culture, that constrains the subsistence strategies used within the Palaeolithic era, whilst the form of the resources dictates the form that these strategies will take. Key to these dynamics is the territorial competition between groups, with a more diverse strategy leading to more efficient groups that can encroach on the less efficient, reducing the carrying capacity and causing the population to move below the minimum group size allowed, thereby becoming extinct.
A conceptual model for energy, trade and economy
(2013) Nilsson, Olof; Chalmers tekniska högskola / Institutionen för energi och miljö; Chalmers University of Technology / Department of Energy and Environment
This thesis focuses on introducing and incorporating an explicit model for energy trade into a conceptual model for economy and energy. The inclusion of an energy market into the model where countries can buy and/or sell energy to a market price is something that was not done in the model that was used as a starting point for this study. In general, energy systems models use less explicit mechanisms to determine trade, like e.g. shadow prices from optimisation. This kind of trading model is successfully developed and introduced into a more complex, dynamic model for economy and energy. The trading mechanism is analysed extensively in itself before introducing it into the more complex model. This to ensure that it exhibits the behaviours that one would expect to observe on a market. The effects of introducing energy trade into such a more complex, dynamic model for economy and energy is then explored and it is shown that when at least one country is sitting on large enough fossil fuel assets, the possibility of energy trade will inhibit the development of renewable energy for all countries. Moreover, the possibilities of avoiding definite time effects in model simulation by modifying the utility function that is subject to optimisation is studied. It is shown that it is possible to find a utility function that in many aspects avoid the definite time effects.
A coupled immunological and epidemiological model for exploration of immunization strategies
(2021) Rylander, Kevin; Chalmers tekniska högskola / Institutionen för rymd-, geo- och miljövetenskap; Andersson, Claes; Andersson, Claes
A genetic programming approach to finding discrepancies in log files
(2021) Gulliksson, Martin; Chalmers tekniska högskola / Institutionen för matematiska vetenskaper; Raum, Martin; Helgegren, Elin
An evolutionary algorithm is used to find discrepancies in log files. From a set of error-free reference logs, a set of regular expression patterns describing the logs’ general structure is generated using genetic programming. The patterns can then be checked against logs containing errors, with the goal being that added, removed and reordered lines are detected. Using a regex-oriented approach allows for grouping lines together even though the contents are not exactly the same in every instance. The approach works well so long as the log files provided do not contain too much noise.
A GPU Polyhedral Discrete Element Method
(2020) Bilock, Adam; Chalmers tekniska högskola / Institutionen för fysik; Logg, Anders; Jareteg, Klas
This thesis presents a Discrete Element Method (DEM) to simulate irregular shaped particles by a non-convex polyhedron representation. By using novel GPU techniques and an efficient HPC implementation the presented method shows a level of throughput not previously attained with polyhedron particle representations in the open literature. Further, via such a representation the exact volumetric overlaps of the particles are resolved and, as a result, the method is robust and numerically stable with respect to geometric changes. The efficient and well-behaved method allows for significant progress in the study of granular materials, where previously mainly the inadequate particle representation of spherical or clumped spherical particles have been used. The exact volumetric overlaps are resolved by a simplex representation which allows for the use of non-convex particles without any decomposition, aiding both performance and the ease of use of the method. Further, care is given to attain efficient scaling of the method with respect to particle resolution. Such a property enables studies on higher resolution particles than previously shown in relatedwork, and is result of efficient filtering of polyhedron triangles in the narrow contact phase. In addition, other novel techniques, such as a GPU BVH implementation for the broad phase contact detection, also aids the performance and the flexibility of the proposed and implemented method. The method is shown to be convergent with respect to particle resolution, both for individual particle collisions and also for laboratory scale particle systems. The HPC implementation is proven to be highly efficient, where, for instance, a one second simulation of one million non-convex particles is simulated within an hour on a single GPU. By the effective filtering of triangles in the narrow contact phase, near linear scaling can be achieved with regards to particle resolution.
A lane departure detection system based on uncertainty aware machine learning
(2020) Larsson, Jesper; Sjöstedt, Mattias; Chalmers tekniska högskola / Institutionen för elektroteknik; Svensson, Lennart
A machine learning algorithm to detect fog from space
(2024) Svensson, Kevin; Johansson, Nils; Chalmers tekniska högskola / Institutionen för rymd-, geo- och miljövetenskap; Chalmers University of Technology / Department of Space, Earth and Environment; Eriksson, Patrick; Ceccobello, Chiara
Fog detection is important for traffic safety. Detecting fog using machine learning on satellite data has been researched before, but not on a global scale using syn thetic data. The aim of the thesis is to use a synthetic dataset of simulated MODIS satellite data to determine the viability of machine learning algorithms for detecting fog in satellite images. The synthetic dataset we use is simulated using a fast ra diative transfer model called RTTOV by inputting various atmospheric information for different conditions. The dataset is tabular and no spatial or temporal relation ship exists between the data points meaning each pixel is treated independently. We use the synthetic data to train and evaluate numerous machine learning models including various implementations of XGBoost and feed forward deep neural net works. We also apply a model trained on synthetic data to a real MODIS image. We demonstrate that classification models can achieve good recall values on synthetic data when oversampling fog in the training data, the best being 0.87 recall with a deep neural network. However, we find that this comes at the cost of a large amount of false positives evident by the low precision value of 0.27. It is concluded that no model performed satisfactory results for replacing existing methods of fog detection. We identify the acquisition of supplemental labeled real satellite images as a possi bility for future improvement, allowing for spatial analysis which is impossible with the independent pixels of the synthetic dataset alone. However, this is a non-trivial task due to the challenges in obtaining and labeling a sufficiently large and diverse dataset of real satellite images.
A model for the evolution of local adaptation of a subdivided population
(2014) emanuelsson, anna; Chalmers tekniska högskola / Institutionen för teknisk fysik; Chalmers University of Technology / Department of Applied Physics
The ecotypes of Littorina saxatalis are believed to be intermediate steps in an ongoing speciation process. L. saxatalis is therefore of scientific interest as a model organism for speciation by local adaptation. In order to understand the genetic patterns that arise from the local adaptation, temporal and spatial adaptation dynamics in a model with two partly isolated subpopulations are analysed. The model is implemented by means of individualbased stochastic simulations and deterministic approximations. We obtain qualitative understanding of the mechanisms underlying local adaptation by investigating how a mutant allele (beneficial in one sub-population) is accepted in a system already containing two alleles (each adapted to opposite sub-populations) with frequencies in steady state. The sizes of the original alleles describe the level of local adaptation before the mutation event. We find the parameter regions where the mutant allele replaces one original allele and investigate the dynamics further within this region. We investigate the replacement probability of the mutant allele. We show that the replacement probability increases with increasing mutation effect size, decreases with increasing degree of local adaptation and decreases with increasing value of the migration rate. We investigate the improvement in average phenotype that results from a replacement of one of the original alleles by the mutant allele, and we investigate the amount of deleterious alleles within each sub-population (the gene flow). We find that the gene flow between the sub populations decrease with increased level of adaptation. By allowing for recombination between two loci, we derive results that implies that a concentrated genetic architecture is preferred by the system in certain parameter regions.
A network analysis of a company’s internal email communications
(2021) Mur, Klaudia; Chalmers tekniska högskola / Institutionen för rymd-, geo- och miljövetenskap; Andersson, Claes; Andersson, Claes
A new generation humanoid robot platform
(2011) Magnus, Wahlstrand; Chalmers tekniska högskola / Institutionen för tillämpad mekanik; Chalmers University of Technology / Department of Applied Mechanics
There are many tasks that humans for different reasons are unwilling or unfit to do. Examples are, for instance, dangerous tasks such as handling toxic waste or monotonous tasks, like working in assembly lines. The hope is that robots one day can do tasks like these for us. Even though a lot of progress has been made in robotics in the last few decades, it is clear that a lot of work and research remains for this goal to be fulfilled. This master thesis describes a process of upgrading Kondo, a small humanoid robot, from a basic robot with no sensory capabilities to a more advanced robotic platform. The hope is that the improved platform can be used to facilitate further research in several fields of robotics such as human-robot interaction, adaptive control and evolutionary robotics. In order to perform this upgrade, the servo controller of existing platform was replaced by a new programmable servo controller. Furthermore, a sensor module with an accelerometer and distance sensors was designed and added to the platform, giving Kondo sensory capabilities. To complete the system, a two part software interface was created. This included a graphical user interface to directly control the robot and create motion sequences and a Python class interface for prototyping and more advanced programs. The resulting platform was tested in order to ensure that it fulfilled the objectives stipulated in the project. The tests included hardware testing, i.e. testing the actual motion of the robot and the communication between to and from the electronic modules. The platform’s configurability was also tested by implementing three common robotic features, including automated fall recovery and wall avoidance. The results of these tests indicate that the basic functionality of the new platform, such as walking and standing, is rather robust. The speed of the developed gait however, can be improved. The platform is relatively easy to extend and modify therefore can be used in education or in robotic research. A weakness of the current platform is the number of connections needed to power and communicate with the electronic boards. Decreasing this number is something that could be worked on in future projects in order to increase the robot’s autonomy.
A probabilistic model for genetic regulation of metabolic networks
(2013) Kallus, Jonatan; Wilsson, Joel; Chalmers tekniska högskola / Institutionen för data- och informationsteknik (Chalmers); Chalmers University of Technology / Department of Computer Science and Engineering (Chalmers)
Recent advancements in gene expression pro ling and measurement of metabolic reaction rates have led to increased interest in predicting metabolic reaction rates. In this thesis we present a principled approach for using gene expression pro les to improve predictions of metabolic reaction rates. A probabilistic graphical model is presented, which addresses inherent weaknesses in the current state of the art method for data-driven reconstruction of regulatory-metabolic networks. Our model combines methods from systems biology and machine learning, and is shown to outperform the current state of the art on synthetic data. Results on real data from S. cerevisiae and M. tuberculosis are also presented.
A question of aggregation A comparative study of objective function creation methods applied to missile defense for helicopters
(2014) djurfeldt, hanna; Chalmers tekniska högskola / Institutionen för teknisk fysik; Chalmers University of Technology / Department of Applied Physics
This report describes an investigation done about method one can use when creating a target function for optimization and the e ects of those choices. Three simple and four advanced target function creation methods are described in detail and the results from optimizing with these target functions are analyzed. Lastly suggestions into possible continuations of this investigation is made.
A Simplified Agent Based Model of a Sinks and Faucets Resource Economy, Using a blind commitment market
(2014) Dalsmo, Anton; Chalmers tekniska högskola / Institutionen för energi och miljö; Chalmers University of Technology / Department of Energy and Environment
This masters thesis seeks to model a simple financial system by using an agent based model. It seeks to do this by constructing an as simple as possible market and agent dynamic. To do this the blind commitment market is introduced and the general model constructed around this. For this model a number of questions are then posed concerning the model's stability and effectiveness at modelling the core market dynamics. Further- more an analytical analog is created in order to analyse the equilibrium dynamics. From the analytical representation parallels are drawn to the agent based model. The agent based model is constructed in such a way that agents are encouraged to interact in order to meet all demands. The arising dependancy network of agents is then analysed using a graphical representation, which shows how much the different agents depend on each other. The general dynamics are also examined as the three main parameters of the model are varied. It is shown that the bind commitment market upholds supply and demand char- acteristics, and that the agent based model functions as an economy with cooperating agents, however these agents are not making any profit. Furtheromre it is shown that the analytical model is stable for all possible parameters of the allowed parameter space in the sense that feedback processes steer the supply and demand dynamics to a stable fix point, an equilibrium price. The agent based model also gravitates towards an equi- librium price, however minority game dynamics prevent the system from reaching, or staying, at the equilibrium price for long. The minority game dynamics ing the system away from the stable point, causing the system to restart its trajectory towards the equilibrium price, aided by the feedback processes. Lastly the three main parameters of the model are examined with respect to how much they influence the stability of prices inside the model.
A software toolkit for generating ice and snow particle sharp data
(2016) Rathsman, Torbjörn; Chalmers tekniska högskola / Institutionen för rymd- och geovetenskap; Chalmers University of Technology / Department of Earth and Space Sciences
Abstract Ice and snow particle shape data are important for understanding the scattering of microwave radiation from a cloud. This thesis presents a software toolkit that can be used to generate such data, for use with Discrete Dipole Approximation calculations. The toolkit has been used to implement a Gillespie-based algorithm with overlap rejection. This algorithm, when used with hexagonal columns, has reproduced some of the properties of real snowflakes, namely their fractal dimension, and their size distribution. The toolkit uses ice crystal prototypes to construct aggregates. Ice crystal prototypes can be modeled in 3D modelling software. This makes it is easy to construct exotic shapes, as opposed to a system based on different classes for different prototypes. In order to keep the possibility of arbitrary parameterisation, the ice crystal prototypes specifies transformation rules that are used if the ice crystal prototype should be deformed. Aggregates and ice crystal prototypes can be merged in different ways to form larger aggregates. To feed a DDA calculation program, the toolkit also provides a rasterisation system, which fills geometry with voxels by using a 6-directional floodfill algorithm. A large part of the thesis discusses various ways of measuring particles. This has lead to a unit neutral way of testing whether or not a model simulates reality. The idea is to compare an averaged spherical volume fill ratio, which according to measurements should follow a particular equation, derived within this thesis. Besides giving an overview of the toolkit, and presenting simulation results, this thesis also serves as a reference manual on how to use the toolkit.
A study of periodic and quasi-periodicorientational motion of microrods in a shear flow using optical tweezers
(2014) Laas, Alexander; Chalmers tekniska högskola / Institutionen för teknisk fysik; Chalmers University of Technology / Department of Applied Physics
The orientational motions of single isolated inertialess microrods are studied in a reversible creeping shear ow. In previous work [12, 24, 30] it was observed that rodlike particles could experience both periodic and quasi-periodic behavior. This work studies how the orientational motion, including periodic and quasi-periodic motion, depends upon the orientational initial conditions, for a single microrod. For the purpose of changing the initial conditions, optical tweezers are installed in the experimental setup. In order to demonstrate that the microdrods and uid are inertialess the ow is reversed and the trajectories before and after the reversal are analyzed. If both the microrod and the ow are inertialess, the orientational motion of the rod is expected to retrace itself when the ow is reversed. The experimental results show that if the ow is reversed smoothly, particles can show this retraceibility. The experimental results also demonstrate that a single rod may exhibit either periodic or quasi-periodic motion, depending solely on its orientational initial condition. The observable dynamics show good agreement with Je ery's equations of motion for an inertialess ellipsoid in a creeping shear flow.
A telegraph model for extension fluctuations of nano-confined DNA molecules
(2018) Ödman, Daniel; Chalmers tekniska högskola / Institutionen för energi och miljö; Chalmers University of Technology / Department of Energy and Environment
Accelerating Proximity Queries Accelerating Proximity Queries for Non-convex Geometries in a Robot Cell Context
(2018) Thorén, Joakim; Chalmers tekniska högskola / Institutionen för data- och informationsteknik (Chalmers); Chalmers University of Technology / Department of Computer Science and Engineering (Chalmers)
Sampling-based motion-planners, for example rapidly exploring dense tree (RRT) based planners, depend on fast proximity queries. Regrettably, bounding volume tests are significant bottlenecks of proximity queries. Sampling-based motion-planners are therefore accelerated by reducing the number of bounding volume tests. To this end, a novel algorithm called Forest Proximity Query (FPQ) is developed. Contrary to previous research, FPQ traverses several pairs of BVHs simultaneously, effectively exploiting an actuality that only a single minimal separation distance — out of several possible separation distances — is required during sampling-based motion-planning. An implementation of FPQ show that FPQ performs up to 67% fewer BV tests in comparison to the well-known Proximity Query Package, increasing proximity querying performance by up to 46%. In conclusion, FPQ is successful in its attempt at improving performance of sampling-based motion-planners.

Browse

Browsar Studentarbeten // Student Theses efter Program "Complex adaptive systems (MPCAS), MSc"

Sökresultat per sida

Sortera efter