Charles Hughes

Dongjie Wang, Pengyang Wang, Kunpeng Liu et al.

In this paper, we study the problem of mobile user profiling, which is a critical component for quantifying users' characteristics in the human mobility modeling pipeline. Human mobility is a sequential decision-making process dependent on the users' dynamic interests. With accurate user profiles, the predictive model can perfectly reproduce users' mobility trajectories. In the reverse direction, once the predictive model can imitate users' mobility patterns, the learned user profiles are also optimal. Such intuition motivates us to propose an imitation-based mobile user profiling framework by exploiting reinforcement learning, in which the agent is trained to precisely imitate users' mobility patterns for optimal user profiles. Specifically, the proposed framework includes two modules: (1) representation module, which produces state combining user profiles and spatio-temporal context in real-time; (2) imitation module, where Deep Q-network (DQN) imitates the user behavior (action) based on the state that is produced by the representation module. However, there are two challenges in running the framework effectively. First, epsilon-greedy strategy in DQN makes use of the exploration-exploitation trade-off by randomly pick actions with the epsilon probability. Such randomness feeds back to the representation module, causing the learned user profiles unstable. To solve the problem, we propose an adversarial training strategy to guarantee the robustness of the representation module. Second, the representation module updates users' profiles in an incremental manner, requiring integrating the temporal effects of user profiles. Inspired by Long-short Term Memory (LSTM), we introduce a gated mechanism to incorporate new and old user characteristics into the user profile.

Kamran Ali, Ilkin Isler, Charles Hughes

Facial expression recognition is a challenging task due to two major problems: the presence of inter-subject variations in facial expression recognition dataset and impure expressions posed by human subjects. In this paper we present a novel Human-to-Animation conditional Generative Adversarial Network (HA-GAN) to overcome these two problems by using many (human faces) to one (animated face) mapping. Specifically, for any given input human expression image, our HA-GAN transfers the expression information from the input image to a fixed animated identity. Stylized animated characters from the Facial Expression Research Group-Database (FERGDB) are used for the generation of fixed identity. By learning this many-to-one identity mapping function using our proposed HA-GAN, the effect of inter-subject variations can be reduced in Facial Expression Recognition(FER). We also argue that the expressions in the generated animated images are pure expressions and since FER is performed on these generated images, the performance of facial expression recognition is improved. Our initial experimental results on the state-of-the-art datasets show that facial expression recognition carried out on the generated animated images using our HA-GAN framework outperforms the baseline deep neural network and produces comparable or even better results than the state-of-the-art methods for facial expression recognition.

Felix G. Hamza-Lup, Jannick P. Rolland, Charles Hughes

Augmented Reality (AR) systems describe the class of systems that use computers to overlay virtual information on the real world. AR environments allow the development of promising tools in several application domains. In medical training and simulation the learning potential of AR is significantly amplified by the capability of the system to present 3D medical models in real-time at remote locations. Furthermore the simulation applicability is broadened by the use of real-time deformable medical models. This work presents a distributed medical training prototype designed to train medical practitioners' hand-eye coordination when performing endotracheal intubations. The system we present accomplishes this task with the help of AR paradigms. An extension of this prototype to medical simulations by employing deformable medical models is possible. The shared state maintenance of the collaborative AR environment is assured through a novel adaptive synchronization algorithm (ASA) that increases the sense of presence among participants and facilitates their interactivity in spite of infrastructure delays. The system will allow paramedics, pre-hospital personnel, and students to practice their skills without touching a real patient and will provide them with the visual feedback they could not otherwise obtain. Such a distributed AR training tool has the potential to: allow an instructor to simultaneously train local and remotely located students and, allow students to actually "see" the internal anatomy and therefore better understand their actions on a human patient simulator (HPS).