Chenxi Yuan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Chenxi Yuan has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
Guoyan Li
1 shared publicationHuifang Shang
1 shared publication- Jinghao Xu1 shared publication
Jinhao Duan
1 shared publicationKaidi Xu
1 shared publication- Li Geng
School of Microelectronics, Xi'an Jiaotong University 1 , Xi'an 710049
1 shared publication
Latest Publications
- 5 August 2025
- Published by Elsevier in Information Fusion
- Vol. 126
Interpretable multi-view fusion network via multi-view dual alignment and private bias filtering for Alzheimer’s disease analysis
- 5 August 2025
- Published by Elsevier in Information Fusion
- Vol. 126
Interpretable multi-view fusion network via multi-view dual alignment and private bias filtering for Alzheimer’s disease analysis
- Open Access
- 1 July 2021
- Published by Elsevier in Journal of Manufacturing Systems
- Vol. 60, 692-706
Data science skills and domain knowledge requirements in the manufacturing industry: A gap analysis
- 1 July 2021
- Published by Elsevier in Journal of Manufacturing Systems
- Vol. 60, 692-706
Open AccessData science skills and domain knowledge requirements in the manufacturing industry: A gap analysis
- 23 November 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 57-58
A 100mV Input Voltage, Multi-step Self-Startup Boost Converter Achieving 50X Voltage Step-up with Standard 0.18 μm CMOS Process for Energy Harvesting application
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.- 23 November 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 57-58
A 100mV Input Voltage, Multi-step Self-Startup Boost Converter Achieving 50X Voltage Step-up with Standard 0.18 μm CMOS Process for Energy Harvesting application
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.- Open Access
- 19 October 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 190710-190721
Attribute-Aware Generative Design With Generative Adversarial Networks
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.
- 19 October 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 190710-190721
Open AccessAttribute-Aware Generative Design With Generative Adversarial Networks
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.