We present the results of applying a Fast Boosted Decision Tree (FBDT) algorithm to the task of distinguishing muons from pions in K-Long and Muon (KLM) detector of the Belle II experiment. Performance was evaluated over a momentum range of 0.6 < p < 5.0 GeV/c by plotting Receiver Operating Characteristic (ROC) curves for 0.1 GeV/c intervals. The FBDT model was worse than the benchmark likelihood ratio test model for the whole momentum range during testing on Monte Carlo (MC) simulated data. This is seen in the lower Area Under the Curve (AUC) values for the FBDT ROC curves, achieving peak AUC values around 0.82, while the likelihood ratio ROC curves achieve peak AUC values around 0.98. Performance of the FBDT model in muon identification may be improved in the future by adding a pre-processing routine for the MC data and input variables. / Master of Science / An important task of a high-energy physics experiment is taking the input information provided by detectors, such as the distance a particle travels through a detector, the momentum, and energy deposits it makes, and using that information to identify the particle's type. In this study we test a machine learning model that sorts the particles observed into two categories—muons and pions—by comparing the particle's input values to a threshold value at multiple stages, then assigns a final identity to the particle at the last stage. This is compared to a benchmark model that uses the probabilities that these input variables would be seen from a particle of each type to determine which particle type is most likely. The ability of both models to distinguish muons and pions were tested on simulated data from the Belle II detector, and the benchmark model outperformed the machine learning model.

Bioinformatics techniques to protein secondary structure prediction mostly depend on the information available in amino acid sequence. Support vector machines (SVM) have shown strong generalization ability in a number of application areas, including protein structure prediction. In this study, a new sliding window scheme is introduced with multiple windows to form the protein data for training and testing SVM. Orthogonal encoding scheme coupled with BLOSUM62 matrix is used to make the prediction. First the prediction of binary classifiers using multiple windows is compared with single window scheme, the results shows single window not to be good in all cases. Two new classifiers are introduced for effective tertiary classification. This new classifiers use neural networks and genetic algorithms to optimize the accuracy of the tertiary classifier. The accuracy level of the new architectures are determined and compared with other studies. The tertiary architecture is better than most available techniques.

<p>Simultaneous Localisation And Mapping SLAM-problemet är ett robotikproblem som består av att låta en robot kartlägga ett tidigare okänt område, och samtidigt lokalisera sig i den skapade kartan. Det här exjobbet presenterar ett försök till en lösning på SLAM-problemet som fungerar i konstant tid i en urban miljö. En sådan lösning måste hantera en datamängd som ständigt ökar, utan att beräkningskomplexiteten ökar signifikant.</p><p>Ett informationsfilter på fördröjd tillståndsform används för estimering av robotens trajektoria, och kamera och laseravståndssensorer används för att samla spatial information om omgivningarna längs färdvägen. Två olika metoder för att detektera loopslutningar föreslås. Den första är bildbaserad och använder Tree of Words för jämförelse av bilder. Den andra metoden är laserbaserad och använder en tränad klassificerare för att jämföra laserscans. När två posar, position och riktning, kopplats samman i en loopslutning beräknas den relativa posen med laserscansinriktning med hjälp av en kombination av Conditional Random Field-Match och Iterative Closest Point.</p><p>Experiment visar att både bild- och laserscansbaserad loopslutningsdetektion fungerar bra i stadsmiljö, och resulterar i good estimering av kartan såväl som robotens trajektoria.</p> / <p>In robotics, the Simultaneous Localisation And Mapping SLAM problem consists of letting a robot map a previously unknown environment, while simultaneously localising the robot in the same map. In this thesis, an attempt to solve the SLAM problem in constant time in a complex environment, such as a suburban area, is made. Such a solution must handle increasing amounts of data without significant increase in computation time.</p><p>A delayed state information filter is used to estimate the robot's trajectory, and camera and laser range sensors are used to acquire spatial information about the environment along the trajectory. Two approaches to loop closure detection are proposed. The first is image based using Tree of Words for image comparison. The second is laser based using a trained classifier for laser scan comparison. The relative pose, the difference in position and heading, of two poses matched in loop closure is calculated with laser scan alignment using a combination of Conditional Random Field-Match and Iterative Closest Point.</p><p>Experiments show that both image and laser based loop closure detection works well in a suburban area, and results in good estimation of the map as well as the robot's trajectory.</p>

Simultaneous Localisation And Mapping SLAM-problemet är ett robotikproblem som består av att låta en robot kartlägga ett tidigare okänt område, och samtidigt lokalisera sig i den skapade kartan. Det här exjobbet presenterar ett försök till en lösning på SLAM-problemet som fungerar i konstant tid i en urban miljö. En sådan lösning måste hantera en datamängd som ständigt ökar, utan att beräkningskomplexiteten ökar signifikant. Ett informationsfilter på fördröjd tillståndsform används för estimering av robotens trajektoria, och kamera och laseravståndssensorer används för att samla spatial information om omgivningarna längs färdvägen. Två olika metoder för att detektera loopslutningar föreslås. Den första är bildbaserad och använder Tree of Words för jämförelse av bilder. Den andra metoden är laserbaserad och använder en tränad klassificerare för att jämföra laserscans. När två posar, position och riktning, kopplats samman i en loopslutning beräknas den relativa posen med laserscansinriktning med hjälp av en kombination av Conditional Random Field-Match och Iterative Closest Point. Experiment visar att både bild- och laserscansbaserad loopslutningsdetektion fungerar bra i stadsmiljö, och resulterar i good estimering av kartan såväl som robotens trajektoria. / In robotics, the Simultaneous Localisation And Mapping SLAM problem consists of letting a robot map a previously unknown environment, while simultaneously localising the robot in the same map. In this thesis, an attempt to solve the SLAM problem in constant time in a complex environment, such as a suburban area, is made. Such a solution must handle increasing amounts of data without significant increase in computation time. A delayed state information filter is used to estimate the robot's trajectory, and camera and laser range sensors are used to acquire spatial information about the environment along the trajectory. Two approaches to loop closure detection are proposed. The first is image based using Tree of Words for image comparison. The second is laser based using a trained classifier for laser scan comparison. The relative pose, the difference in position and heading, of two poses matched in loop closure is calculated with laser scan alignment using a combination of Conditional Random Field-Match and Iterative Closest Point. Experiments show that both image and laser based loop closure detection works well in a suburban area, and results in good estimation of the map as well as the robot's trajectory.

Vehicle Action Intention Prediction plays a more and more crucial role in automated driving and traffic safety. It allows automated vehicles to comprehend the other road participants’ current actions, and foresee the upcoming actions, which can significantly reduce the likelihood of traffic accidents, so as to enhance overall road safety. Meanwhile, by anticipating other vehicles’ movements on the road, the ego vehicle can plan its velocity and trajectory in advance, and make more smooth and finer adjustments during the whole driving process, contributing to a more safe and efficient traffic. Furthermore, the intention prediction enables vehicles to respond proactively rather than reactively in traditional ADAS (Advanced Driver Assistance Systems), such as AEB (Automatic Emergency Braking), which facilitates a more preventive and early intervention approach to traffic safety. In normal conditions, traffic behavior is controlled by traffic rules. This thesis explores vehicle behavior using intention prediction models in scenarios where there are no traffic rules. At hand, we have a unique dataset containing vehicle trajectories, collected from 2 cameras installed overhead on a 1-lane narrowing street, where the vehicles need to negotiate their right of way. After pre-processing these data to form specific input structures, we use different classifier models including both traditional methods and deep learning methods to make vehicle action intention predictions. The data was organized in 3-second windows and contained vehicle position and distance to the center of the intersection along with the speed of both vehicles. We compared and evaluated the model performances and found that MLPs (Multi-Layer Perceptrons) and LSTM (Long Short Term Memory) yield the best performance. Furthermore, a feature selection method and features’ importance analysis are also applied to explore which variables influence the model most in order to explain the internal principle of the prediction model. It was found that close to the narrowing street the first and last samples of the position and distance in the time window and the last sample of the speed of both vehicles were found to influence the model performance the most. Further away from the narrowing street, the first and last samples of the position of the vehicle have a higher influence on the model.

Fluid inclusion and mineralogical features indicative of boiling have been characterized in 855 samples from epithermal precious metals deposits along the Veta Madre at Guanajuato, Mexico. Features associated with boiling that have been identified at Guanajuato include colloform texture silica, plumose texture silica, moss texture silica, ghost-sphere texture silica, lattice-bladed calcite, lattice-bladed calcite replaced by quartz and pseudo-acicular quartz after calcite and coexisting liquid-rich and vapor-rich fluid inclusions. Most samples were assayed for Au, Ag, Cu, Pb, Zn, As and Sb, and were divided into high-grade and low-grade samples based on the gold and silver concentrations. For silver, the cutoff for high grade was 100 ppm Ag, and for gold the cutoff was 1 ppm Au. The feature that is most closely associated with high grades of both gold and silver is colloform texture silica, and this feature also shows the largest difference in grade between the presence or absence of that feature (178.8 ppm Ag versus 17.2 ppm Ag, and 1.1 ppm Au versus 0.2 ppm Au). For both Ag and Au, there is no significant difference in average grade as a function of whether or not coexisting liquid-rich and vapor-rich fluid inclusions are present. The textural and fluid inclusion data obtained in this study were analyzed using the binary classifier within SPSS Clementine. The models that correctly predicted high versus low grade samples most consistently (~70-75% of the tests) for both Ag and Au were the neural network, the C5 decision tree and Quest decision tree models. For both Au and Ag, the presence of colloform silica texture was the variable with the greatest importance, i.e., the variable that has the greatest predictive power. Boiling features are absent or rare in samples collected along a traverse perpendicular to the Veta Madre. This suggests that if an explorationist observes these features in samples collected during exploration that an environment favorable to precious metal mineralization is nearby. Similarly, good evidence for boiling is observed in the deepest levels of the Veta Madre that have been sampled in the mines and drill cores, suggesting that additional precious metal reserves are likely beneath the deepest levels sampled. / Master of Science