The designers’ tendency to adhere to a specific mental set and heavy emotional investment in their initial ideas often limit their ability to innovate during the design ideation process. The shrinking time-to-market and the growing diversity of users’ needs further exacerbate this gap. Recent advances in deep generative models have created new possibilities to overcome the cognitive obstacles of designers through automated generation or editing of design concepts. This paper explores the capabilities of generative adversarial networks (GAN) for automated, attribute-aware generative design of the visual attributes of a product. Specifically, a design attribute GAN (DA-GAN) model is developed for automated generation of fashion product images with the desired visual attributes. Experiments on a large fashion dataset signify the potentials of GAN for attribute-aware generative design, verify the ability of editing attributes with relatively higher accuracy and uncover several key challenges and research questions for future work.
15 November 2024 in Engineering Applications of Artificial Intelligence
In this paper, a multi-step self-startup boost converter is proposed for energy harvesting application. To decrease the minimum startup voltage, novel body-effect control method of MOSFETs is applied to self-startup circuit. Besides, dual-phase charge pump is adopted to reduce the output ripple. In addition, multi-step startup strategy is proposed to realize self-startup process of the boost converter. The boost converter is fabricated with standard 0. $1S\mu m$ CMOS process. The active area of the boost converter is nearly 3 mm 2 , which guarantees high power conversion efficiency (PCE) at as high as 2 A load current. Simulated results demonstrate that the boost converter can kick start with 400 mV input voltage, and the output voltage can be maintained up to 5 V with minimum of 100 mV input voltage, where 50X voltage step-up is achieved.