Open Access. Powered by Scholars. Published by Universities.®
- Institution
Articles 1 - 4 of 4
Full-Text Articles in Engineering
Pixel-Level Deep Multi-Dimensional Embeddings For Homogeneous Multiple Object Tracking, Mateusz Mittek
Pixel-Level Deep Multi-Dimensional Embeddings For Homogeneous Multiple Object Tracking, Mateusz Mittek
Department of Electrical and Computer Engineering: Dissertations, Theses, and Student Research
The goal of Multiple Object Tracking (MOT) is to locate multiple objects and keep track of their individual identities and trajectories given a sequence of (video) frames. A popular approach to MOT is tracking by detection consisting of two processing components: detection (identification of objects of interest in individual frames) and data association (connecting data from multiple frames). This work addresses the detection component by introducing a method based on semantic instance segmentation, i.e., assigning labels to all visible pixels such that they are unique among different instances. Modern tracking methods often built around Convolutional Neural Networks (CNNs) and additional, …
Cure: Flexible Categorical Data Representation By Hierarchical Coupling Learning, Songlei Jian, Guansong Pang, Longbing Cao, Kai Lu, Hang Gao
Cure: Flexible Categorical Data Representation By Hierarchical Coupling Learning, Songlei Jian, Guansong Pang, Longbing Cao, Kai Lu, Hang Gao
Research Collection School Of Computing and Information Systems
The representation of categorical data with hierarchical value coupling relationships (i.e., various value-to-value cluster interactions) is very critical yet challenging for capturing complex data characteristics in learning tasks. This paper proposes a novel and flexible coupled unsupervised categorical data representation (CURE) framework, which not only captures the hierarchical couplings but is also flexible enough to be instantiated for contrastive learning tasks. CURE first learns the value clusters of different granularities based on multiple value coupling functions and then learns the value representation from the couplings between the obtained value clusters. With two complementary value coupling functions, CURE is instantiated into …
Smart Control Of Buck Converters Using A Switching-Based Clustering Algorithm, Brook Abegaz, M. Cmiel
Smart Control Of Buck Converters Using A Switching-Based Clustering Algorithm, Brook Abegaz, M. Cmiel
Engineering Science Faculty Publications
This paper proposes a new approach to the control of switching voltage regulators (buck converters). The method is performed using a switching-based clustering algorithm. The implementations of competing approaches such as a fuzzy-logic controller, proportional integral derivative controller and a neural network based controller are presented in order to compare and evaluate the performance of the switching-based clustering algorithm. The results of the approach show that the proposed method could improve the stability and the performance of the buck converter system by 2.7% in terms of settling time and by 0.6% in terms of the overshoot value as compared to …
Smart Control Of Automatic Voltage Regulators Using K-Means Clustering, Brook Abegaz, J. Kueber
Smart Control Of Automatic Voltage Regulators Using K-Means Clustering, Brook Abegaz, J. Kueber
Engineering Science Faculty Publications
The future cyber physical systems consist of voltage regulators distributed across wide geographical areas. In this paper, a smart control approach of voltage regulators is presented for cyber physical system applications. The approach is implemented using K-means clustering algorithms that use data from voltage and current sensors, compute the correlation of changes across the regulators and generate a proportional feedback. Advanced estimation methods are used in cases where the data from the sensors was not available. The results show that the approach could be used to improve the performance of networked, power dependent systems by 94.5% in terms of overshoot …