Automatic vehicle-type classification plays an imperative role in the development of efficient Intelligent Transportation Systems (ITS). In this paper, a super-learner ensemble is proposed for the vehicle-type classification problem. A densely connected single-split super learner is utilized to exploit the strengths and diminish the weaknesses of the individual base learners ResNet50, Xception, and DenseNet. The super learner aims to learn fusion weights in a data-adaptive manner to obtain the optimal combination of the base learners. The proposed method is simple, robust, and enhances the discrimination capabilities among the similarly-looking classes without requiring any hand-crafted features or logical reasoning. The proposed method is evaluated using two of the most challenging publicly available traffic surveillance datasets: the MIOvision Traffic Camera Dataset (MIO-TCD) and the Beijing Institute of Technology’s (BIT) vehicle classification dataset. Three variants of the super learner ensemble: RXD-CV-CW, RXD-CV-CW-NCW and Augmented-RXD, were examined on the MIO-TCD dataset with variations in applying class weights and data augmentation during training. RXD-CV-CW-NCW and Augmented-RXD share the third place among the published state-of-the-art methods reported in the MIO-TCD classification challenge. Augmented-RXD generalizes to the classes in common between the two datasets without degrading its performance on the MIO-TCD dataset. Both variants achieved an overall accuracy of 97.94%, and a Cohen Kappa score of 96.78%. In addition, the super-learner variants that we trained on the BIT-Vehicle dataset images achieved overall accuracies of up to 97.62%.
This paper presents a new framework for a systematic and thorough generalization of the most well-known instantaneous transformations used in electrical engineering for power systems analysis and computing through geometric principles based on the language of Geometric Algebra. By introducing the concepts of Kirchhoff Vector and Kirchhoff Subspace, a new generalized transformation is presented. Thus, it is shown how the Clarke, Park or Hyper-Space vector transformations (widely used in electrical engineering) are particular cases of this unifying framework. Moreover, a generalization to an arbitrary number of phases is achieved. In order to be as close as possible to the geometrical intuition, all the underlying ideas are presented by means of spatial-like conceptualizations, substantiated by their corresponding algebraic formulation. This proposal has potential uses in a wide range of power system applications such as electrical machines, current compensation, power quality, electronic converters or transmission lines. Preliminary results show the superior efficiency of the method compared to matrix methods. Some real-world examples have been included to highlight the potential use of the method.
7 February 2018 in Advances in Applied Clifford Algebras
This paper introduces a novel method for solving the resection problem in two and three dimensions based on conformal geometric algebra (CGA). Advantage is taken because of the characteristics of CGA, which enables the representation of points, lines, planes, and volumes in a unified mathematical framework and offers a more intuitive and geometric understanding of the problem, in contrast to existing purely algebraic methods. Several numerical examples are presented to demonstrate the efficacy of the proposed method and to compare its validity with established techniques in the field. Numerical simulations indicate that our vector geometric algebra implementation is faster than the best-known algorithms to date, suggesting that the proposed GA-based methods can provide a more efficient and comprehensible solution to the two- and three-dimensional resection problem, paving the way for further applications and advances in geodesy research. Furthermore, the method’s emphasis on graphical and geometric representation makes it particularly suitable for educational purposes, allowing the reader to grasp the concepts and principles of resection more effectively. The proposed method has potential applications in a wide range of other fields, including surveying, robotics, computer vision, or navigation.
Ray-tracing is an efficient asymptotic computational electromagnetic method for studying wave propagation. The major bottleneck of ray-tracing algorithms is the computational complexity of the geometric-processing steps. There is a clear need for designing efficient ray-tracing algorithms and implementations in computational electromagnetics applications. We use Geometric algebra for the formulation of the pre-processing of electromagnetic ray tracing. Geometric algebra provides unified mathematical representations of geometric primitives and transformations. Various kinds of geometric algebras are currently used in many practical applications. We develop a unified 2D/3D ray-tracing procedure based on the homogeneous geometric algebra. The procedure is implemented using generative programming for optimizing code compilation. Results show that combining the powerful mathematical modeling capabilities of geometric algebra with efficient automatic code generation resulted in better performance of the ray-tracing implementation compared to typical approaches.