Robots performing human-scale manipulation tasks require an extensive amount of knowledge about their surroundings in order to perform their actions competently and human-like. In this work, we investigate the use of virtual reality technology as an implementation for robot environment modeling, and present a technique for translating scene graphs into knowledge bases. To this end, we take advantage of the Universal Scene Description (USD) format which is an emerging standard for the authoring, visualization and simulation of complex environments. We investigate the conversion of USD-based environment models into Knowledge Graph (KG) representations that facilitate semantic querying and integration with additional knowledge sources. The contributions of the paper are validated through an application scenario in the service robotics domain.

Networks evolve continuously over time with the addition, deletion, and changing of links and nodes. Although many networks contain this type of temporal information, the majority of research in network representation learning has focused on static snapshots of the graph and has largely ignored the temporal dynamics of the network. In this work, we describe a general framework for incorporating temporal information into network embedding methods. The framework gives rise to methods for learning time-respecting embeddings from continuous-time dynamic networks. Overall, the experiments demonstrate the effectiveness of the proposed framework and dynamic network embedding approach as it achieves an average gain of 11.9% across all methods and graphs. The results indicate that modeling temporal dependencies in graphs is important for learning appropriate and meaningful network representations.

This paper presents an efficient training approach for support vector machines that will improve their ability to learn from a large or imbalanced data set. Given an original training set, the proposed approach applies unsupervised learning to extract a smaller set of salient training exemplars, which are represented by weighted cluster centers and the target outputs. In subsequent supervised learning, the objective function is modified by introducing a weight for each new training sample and the corresponding penalty term. In this paper, we investigate two methods of defining the weight based on cluster vectors. The proposed SVM training is implemented and tested on two problems: (i) gender classification of facial images using the FERET data set; (ii) income prediction using the UCI Adult Census data set. Experiment results show that compared to standard SVM training, the proposed approach leads to much faster SVM training, produces a more compact classifier while maintaining generalization ability.

We have demonstrated two techniques for all optical frequency up-conversion of Multi-Band Orthogonal Frequency Division Multiplexing (MB-OFDM) signal with 400 Mbps bit rate in the 60 GHz band. The first technique is based on direct modulation of Laser Diode (LD) associated with an electro-optic modulator (EOM) and the second one is based on two cascaded EOMs. For both techniques, a fiber Bragg grating (FBG) is inserted to suppress undesired signal around 60 GHz band. Direct modulation of LD with an EOM is cost effective compared to two cascaded EOMs, and exhibits a gain of 5 dB in the received optical power. A minimum error vector magnitude (EVM) of 18% and 20% are measured for direct modulation of LD with an EOM and two cascaded EOMs techniques, respectively which complies with MB-OFDM standard.

This paper presents a new learning approach for pattern classification applications involving imbalanced data sets. In this approach, a clustering technique is employed to resample the original training set into a smaller set of representative training exemplars, represented by weighted cluster centers and their target outputs. Based on the proposed learning approach, four training algorithms are derived for feed-forward neural networks. These algorithms are implemented and tested on three benchmark data sets. Experimental results show that with the proposed learning approach, it is possible to design networks to tackle the class imbalance problem, without compromising the overall classification performance.

In this article, we propose a new supervised learning approach for pattern classification applications involving large or imbalanced data sets. In this approach, a clustering technique is employed to reduce the original training set into a smaller set of representative training exemplars, represented by weighted cluster centers and their target outputs. Based on the proposed learning approach, two training algorithms are derived for feed-forward neural networks. These algorithms are implemented and tested on two pattern classification applications - skin detection and image classification. Experimental results show that with the proposed learning approach, it is possible to design networks in a fraction of time taken by the standard learning approach, without compromising the generalization ability and overall classification performance.