This thesis presents a framework for automatic recognition of human actions in uncontrolled, realistic video data such as movies, internet and surveillance videos. In this thesis, the human action recognition problem is solved from the perspective of local spatio-temporal feature and bag-of-features representation. The bag-of-features model only contains statistics of unordered low-level primitives, and any information concerning temporal ordering and spatial structure is lost. To address this issue, we proposed a novel multiscale local part model on the purpose of maintaining both structure information and ordering of local events for action recognition. The method includes both a coarse primitive level root feature covering event-content statistics and higher resolution overlapping part features incorporating local structure and temporal relationships. To extract the local spatio-temporal features, we investigated a random sampling strategy for efficient action recognition. We also introduced the idea of using very high sampling density for efficient and accurate classification. We further explored the potential of the method with the joint optimization of two constraints: the classification accuracy and its efficiency. On the performance side, we proposed a new local descriptor, called GBH, based on spatial and temporal gradients. It significantly improved the performance of the pure spatial gradient-based HOG descriptor on action recognition while preserving high computational efficiency. We have also shown that the performance of the state-of-the-art MBH descriptor can be improved with a discontinuity-preserving optical flow algorithm. In addition, a new method based on histogram intersection kernel was introduced to combine multiple channels of different descriptors. This method has the advantages of improving recognition accuracy with multiple descriptors and speeding up the classification process. On the efficiency side, we applied PCA to reduce the feature dimension which resulted in fast bag-of-features matching. We also evaluated the FLANN method on real-time action recognition. We conducted extensive experiments on real-world videos from challenging public action datasets. We showed that our methods achieved the state-of-the-art with real-time computational potential, thus highlighting the effectiveness and efficiency of the proposed methods.

This thesis investigates if support vector machine classification is a suitable approach when performing automatic segmentation of knee cartilage using quantitative magnetic resonance imaging data. The data sets used are part of a clinical project that investigates if patients that have suffered recent knee damage will develop cartilage damage. Therefore the thesis also investigates if the segmentation results can be used to predict the clinical outcome of the patients. Two methods that perform the segmentation using support vector machine classification are implemented and evaluated. The evaluation indicates that it is a good approach for the task, but the implemented methods needs to be further improved and tested on more data sets before clinical use. It was not possible to relate the cartilage properties to clinical outcome using the segmentation results. However, the investigation demonstrated good promise of how the segmentation results, if they are improved, can be used in combination with quantitative magnetic resonance imaging data to analyze how the cartilage properties change over time or vary between knees.

For autonomous mine vehicles that perform the ”load-haul-dump” (LHD) cycle to operate properly, calibration of the sensors they rely on is crucial. The LHD cycle refers to a vehicle that loads material, hauls the material along a route and dumps it in an extraction point. Many of these vehicles are waist-actuated, meaning that the front and rear part of the machines are fixated at an articulation point.   The focus of this thesis is about developing and implementing two differ- ent frameworks to distinguish patterns from routes where calibration of the hinge-angle sensor was needed before and try to predict when calibrating the sensor is needed. We present comparative results of one method using ma- chine learning, specifically supervised learning with support vector machine and one optimization-based method using scan matching by implementing a two-dimensional NDT (Normal Distributions Transform) algorithm.   Comparative results based on evaluation metrics used in this thesis show that detecting incorrect behaviour of the hinge-angle sensor is possible. Evaluation show that the machine learning classifier performs better on the data used for this thesis than the optimization-based classifier.

Internet traffic classification is an important field which several stakeholders are dependent on for a number of different reasons. Internet Service Providers (ISPs) and network operators benefit from knowing what type of traffic that propagates over their network in order to correctly treat different applications. Today Deep Packet Inspection (DPI) and port based classification are two of the more commonly used methods in order to classify Internet traffic. However, both of these techniques fail when the traffic is encrypted. This study explores a third method, classifying Internet traffic by machine learning in which the classification is realized by looking at Internet traffic flow characteristics instead of actual payloads. Machine learning can solve the inherent limitations that DPI and port based classification suffers from. In this study the Internet traffic is divided into two classes of interest: Video and Other. There exist several machine learning methods for classification, and this study focuses on Support Vector Machine (SVM) to classify traffic. Several traffic characteristics are extracted, such as individual payload sizes and the longest consecutive run of payload packets in the downward direction. Several experiments using different approaches are conducted and the achieved results show that overall accuracies above 90% are achievable. / HITS, 4707

A common impairment after a traumatic brain injury (TBI) is a deficit in emotional recognition, such as inferences of others’ intentions. Some researchers have found these impairments in 39\% of the TBI population. Our research information needed to make inferences about emotions and mental states comes from visually presented, nonverbal cues (e.g., facial expressions or gestures). Theory of mind (ToM) deficits after TBI are partially explained by impaired visual attention and the processing of these important cues. This research found that patients with deficits in visual processing differ from healthy controls (HCs). Furthermore, we found visual processing problems can be determined by looking at the eye tracking data developed from industry standard eye tracking hardware and software. We predicted that the eye tracking data of the overall population is correlated to the TASIT test. The visual processing of impaired (who got at least one answer wrong from TASIT questions) and unimpaired (who got all answer correctly from TASIT questions) differs significantly. We have divided the eye-tracking data into 3 second time blocks of time series data to detect the most salient individual blocks to the TASIT score. Our preliminary results suggest that we can predict the whole population's impairment using eye-tracking data with an improved f1 score from 0.54 to 0.73. For this, we developed optimized support vector machine (SVM) and random forest (RF) classifier.

The Global Positioning System (GPS) and other satellite-based positioning systems are often a key component in applications requiring localization. However, accurate positioning in areas with poor GPS coverage, such as inside buildings and in dense cities, is in increasing demand for many modern applications. Fortunately, recent developments in ultra-wideband (UWB) radio technology have enabled precise positioning in places where it was not previously possible by utilizing multipath-resistant wide band pulses. Although ultra-wideband signals are less prone to multipath interference, it is still a bottleneck as increasingly ambitious projects continue to demand higher precision. Some UWB radios include on-board detection of multipath conditions, however the implementations are usually limited to basic condition checks. In order to address these shortcomings, We propose an application of machine learning to reliably detect non-line-of-sight conditions when the on-board radio classifier fails to recognize these conditions. Our solution includes a neural network classifier that is 99.98% accurate in a variety of environments.

No description available.

his thesis deals with detection of the road adjacent to an autonomous vehicle. The road is recognition is based on the Velodyne LiDAR laser radar data. An existing solution is used and extended by machine learning - a Support Vector Machine with online learning. The thesis evaluates the existing solution and the new one using a KITTI dataset. The reliability of the road recognition is then computed using F-measure.

This Master thesis deals with usage of radar signal for vehicle classification. The thesis uses radar modules with continuous wave based on Doppler effect. Radar signal is processed by a series of signal processing method finished by Fourier transform. Data produced by FFT is used to create SVM and AdaBoost classifier which can be used to classify vehicles into groups.

This thesis deals with the failure mode detection of aircraft engines. The main approach to the detection is searching for anomalies in the sensor data. In order to get a comprehensive idea of the system and the particular sensors, the description of the whole system, namely the aircraft engine HTF7000 as well as the description of the sensors, are dealt with at the beginning of the thesis. A proposal of the anomaly detection algorithm based on three different detection methods is discussed in the second chapter. The above-mentioned methods are SVM (Support Vector Machine), K-means a ARIMA (Autoregressive Integrated Moving Average). The implementation of the algorithm including graphical user interface proposal are elaborated on in the next part of the thesis. Finally, statistical analysis of the results,the comparison of efficiency particular models and the discussion of outputs of the proposed algorithm can be found at the end of the thesis.