Class imbalanced datasets are common in real-world applications ranging from credit card fraud detection to rare disease diagnosis. Recently, deep generative models have proved successful for an array of machine learning problems such as semi-supervised learning, transfer learning, and recommender systems. However their application to class imbalance situations is limited. In this paper, we consider class conditional variants of generative adversarial networks and variational autoencoders and apply them to the imbalance problem. The main question we seek to answer is whether or not deep conditional generative models can effectively learn the distributions of minority classes so as to produce synthetic observations that ultimately lead to improvements in the performance of a downstream classifier. The numerical results show that this is indeed true and that deep generative models outperform traditional oversampling methods in many circumstances, especially in cases of severe imbalance.

This paper addresses a brand new way of thinking that distinguishes itself by integrating two entities, namely, dynamic spectrum management on the one hand and cognitive dynamic system (CDS) on the other. To be more precise, the CDS performs the role of a cognitive engine centered at the heart of wireless communications, wherein licensed bands rooted in network providers responsible for primary users and unlicensed bands rooted in other networks responsible for secondary users. Thus, these two worlds embody primary users and secondary users, which collectively function within a single complex wireless communication network empowered by the CDS for the first time ever.

This paper is concerned with the mechanical design of a mobile manipulating unmanned ground vehicle (MM-UGV) coupled with an existing commercial unmanned aerial vehicle (UAV) to create a novel hybrid aerial/ground mobile manipulator. A novel systematic optimization-based approach is presented for making important design choices, such as the selection of gearboxes and electric DC motors in the drive-train, manipulator link lengths, and UGV base length. The objective is to minimize the overall mass of the MM-UGV. Constraints related to workspace, dynamic tip-over stability, actuator torque/force limits in static and dynamic motions, executed in the air or on the ground, and battery properties are incorporated into the problem formulation. The system operating conditions in the form of the range of end-effector forces, operating surface grade, and various position, velocity and acceleration variables are provided by the designer. The resulting problem is a robust bilevel nonlinear optimization, in which some of the constraints are derived from maximization/minimization over the operational variables to ensure constraint satisfaction in all possible operation scenarios. The problem is solved using a genetic algorithm. Numerical simulations demonstrate that the proposed strategy produces a design that meets the user-specified requirements.