This paper presents a new protograph-based LDPC code design framework that simultaneously achieves full diversity over block-fading channels (BFCs) and near-capacity performance over additive white Gaussian noise channels. By leveraging a Boolean approximation-based analysis-Diversity Evolution-we derive structural constraints with generalized rootchecks that guarantee full diversity. Building on these constraints, we propose a diversity-aligned protograph template tailored for the two-block BFC (M=2) that ensures full diversity under iterative belief propagation decoding. Furthermore, a genetic algorithm guided by density evolution is employed to optimize the protograph edges within this family for improved coding gain. The resulting codes, termed DA-GRP-LDPC codes, simultaneously achieve full diversity and enhanced coding gain, reaching a 0.8 dB gap to the outage limit for the two-block BFC at a block length of 16,896. This demonstrates that the proposed framework effectively bridges the gap between diversity optimality in non-ergodic channels and high coding gain in ergodic channels.

Inspired by human visual attention, we propose a novel inverse reinforcement learning formulation using Maximum Entropy Deep Inverse Reinforcement Learning (MEDIRL) for predicting the visual attention of drivers in accident-prone situations. MEDIRL predicts fixation locations that lead to maximal rewards by learning a task-sensitive reward function from eye fixation patterns recorded from attentive drivers. Additionally, we introduce EyeCar, a new driver attention dataset in accident-prone situations. We conduct comprehensive experiments to evaluate our proposed model on three common benchmarks: (DR(eye)VE, BDD-A, DADA-2000), and our EyeCar dataset. Results indicate that MEDIRL outperforms existing models for predicting attention and achieves state-of-the-art performance. We present extensive ablation studies to provide more insights into different features of our proposed model.1

The potential benefits of thumb-based touch interaction have not been fully exploited due to its usability problems and performance deterioration. Despite the well-known problems, mobile phone users often prefer thumb-based input method in their daily context of use. Without understanding input performance under realistic variability, design solutions may not address the problems adequately. This research aims to evaluate performance of one-handed thumb-based input compared to cradled finger-based input for the large number of users and varying task conditions. By investigating performance under a range of user- and task-variability, common patterns can be identified to help infer realistic performance in context of use. For this experiment, 259 participants were recruited balanced on gender and age. They performed user testing of moving an icon on a mobile touch-screen. Overall, the one-handed thumb input showed a 30% reduction in throughput compared to the cradled finger-based input, with significant reduction in speed and accuracy. Reduced throughput is attributed to inaccuracy rather than speed. In addition, the partial effects of touch position, dragging direction, and target size were investigated and quantified. In conclusion, performance could maintain constant throughput only for the finger-based input of limited task conditions, when realistic variability was introduced. Also, high variance of throughput for the thumb-based input led to poor conformity to Fitts’s law. The findings have implications for design of thumb-based touch interface to offset performance reduction and characterizing performance measure for thumb-based input method.