Youhua Shi

Youhua Shi

Waseda University

H-index: 14

Asia-Japan

About Youhua Shi

Youhua Shi, With an exceptional h-index of 14 and a recent h-index of 8 (since 2020), a distinguished researcher at Waseda University, specializes in the field of Integrated circuits and Intelligent systems.

His recent articles reflect a diverse array of research interests and contributions to the field:

A Dual-Output Rectifier-based Self-Powered Interface Circuit for Triboelectric Nanogenerators

An Area-Power-Efficient Multiplier-less Processing Element Design for CNN Accelerators

Strategy for Improving Cycle of Maximized Energy Output of Triboelectric Nanogenerators

Dataflow Optimization through Exploring Single-Layer and Inter-Layer Data Reuse in Memory-Constrained Accelerators

Power-efficient deep convolutional neural network design through zero-gating PEs and partial-sum reuse centric dataflow

A High-Performance Symmetric Hybrid Form Design for High-Order FIR Filters

Faithfully truncated adder-based area-power efficient FIR design with predefined output accuracy

Facile Construction of Troponoid Derivatives Incorporating Imidazolin-2-one Moieties

Youhua Shi Information

University

Waseda University

Position

___

Citations(all)

653

Citations(since 2020)

311

Cited By

474

hIndex(all)

14

hIndex(since 2020)

8

i10Index(all)

19

i10Index(since 2020)

7

Email

University Profile Page

Waseda University

Youhua Shi Skills & Research Interests

Integrated circuits and Intelligent systems

Top articles of Youhua Shi

A Dual-Output Rectifier-based Self-Powered Interface Circuit for Triboelectric Nanogenerators

Authors

Yirui Su,Masao Yanagisawa,Youhua Shi

Journal

IEEE Transactions on Power Electronics

Published Date

2024/3/18

Triboelectric nanogenerators (TENGs) offer a cost-effective solution for harvesting energy in Internet of Things (IoT) devices. However, their practical application is limited due to extremely high output voltage and low intrinsic capacitance, alongside the non-self-powered nature of current interface circuits and low transfer efficiency resulting from output voltage asymmetry. Addressing these issues, this letter introduces a dual-output rectifier (DOR)-based interface circuit, innovatively designed to rectify TENG output into two distinct voltage magnitudes, optimizing for energy harvesting and switching generation. The experimental results validate our approach, showing gains of 2.75 and 2.34 times in terms of maximum output power over a full-wave rectifier (FWR)-based design at 2 Hz and 3 Hz, respectively. Furthermore, under identical frequency and load conditions (1MΩ at 2 and 3Hz), the output gains reached 152 …

An Area-Power-Efficient Multiplier-less Processing Element Design for CNN Accelerators

Authors

Jiaxiang Li,Masao Yanagisawa,Youhua Shi

Published Date

2023/10/24

Machine learning has achieved remarkable success in various domains. However, the computational demands and memory requirements of these models pose challenges for deployment on privacy-secured or wearable edge devices. To address this issue, we propose an area-power-efficient multiplier-less processing element (PE) in this paper. Prior to implementing the proposed PE, we apply a power-of-2 dictionary-based quantization to the model. We analyze the effectiveness of this quantization method in preserving the accuracy of the original model and present the standard and a specialized diagram illustrating the schematics of the proposed PE. Our evaluation results demonstrate that our design achieves approximately 30% lower power consumption and 35% smaller core area compared to a conventional multiplication-and-accumulation (MAC) PE. Moreover, the applied quantization reduces the model …

Strategy for Improving Cycle of Maximized Energy Output of Triboelectric Nanogenerators

Authors

Yirui Su,Masao Yanagisawa,Youhua Shi

Published Date

2023/9/25

Triboelectric nanogenerator (TENG) is a new energy harvesting technology proposed in recent years. However, the output energy per cycle from TENG to a load has been proven to be confined within Cycle of Maximized Energy Output (CMEO) which is always used as a common standard to evaluate the performance of a TENG. In this work, a new energy extraction strategy is proposed that utilizes the energy of TENG’s negative half cycle to complete the pre-biasing for TENG’s positive half cycle, which realizes the output of TENG per cycle beyond the CMEO limit. The simulation results show that the output energy per cycle of this strategy is 1.74 times that of CMEO.

Dataflow Optimization through Exploring Single-Layer and Inter-Layer Data Reuse in Memory-Constrained Accelerators

Authors

Jinghao Ye,Masao Yanagisawa,Youhua Shi

Journal

Electronics

Published Date

2022/7/28

Off-chip memory access has become the performance and energy bottleneck in memory-constrained neural network accelerators. To provide a solution for the energy efficient processing of various neural network models, this paper proposes a dataflow optimization method for modern neural networks by exploring the opportunity of single-layer and inter-layer data reuse to minimize the amount of off-chip memory access in memory-constrained accelerators. A mathematical analysis of three inter-layer data reuse methods is first presented. Then, a comprehensive exploration to determine the optimal data reuse strategy from single-layer and inter-layer data reuse approaches is proposed. The result shows that when compared to the existing single-layer-based exploration method, SmartShuttle, the proposed approach can achieve up to 20.5% and 32.5% of off-chip memory access reduction for ResNeXt-50 and DenseNet-121, respectively.

Power-efficient deep convolutional neural network design through zero-gating PEs and partial-sum reuse centric dataflow

Authors

Lin Ye,Jinghao Ye,Masao Yanagisawa,Youhua Shi

Journal

IEEE Access

Published Date

2021/1/21

Convolution neural networks (CNNs) have shown great success in many areas such as object detection and pattern recognition at the cost of extreme high computation complexity and significant external memory access, which makes state-of-the-art deep CNNs difficult to be implemented on resource-constrained portable/wearable devices with limited capacity of battery. To address this design challenge, a power-efficient CNN design through zero-gating processing elements (PEs) and partial-sum reuse centric dataflow is proposed in this paper. Unlike the existing works which either only consider the zeros in activation maps or use off-chip training process for on-chip computation reduction, a zero-gating PE design is proposed to avoid unnecessary on-chip computation by taking advantages of the large number of zeros in both the filter’s weights of pre-trained models and the activation maps. Furthermore, a partial …

A High-Performance Symmetric Hybrid Form Design for High-Order FIR Filters

Authors

Jinghao Ye,Masao Yanagisawa,Youhua Shi

Published Date

2020/12/8

In this paper, a symmetric hybrid form for high performance finite impulse response (FIR) filters with symmetric coefficients is proposed, which can be utilized in both fixed and reconfigurable FIR implementations to solve the driving capacity problem caused by the high fanout signals in the existing symmetric transposed form based FIR architecture. The evaluation results show that, when compared with the existing high speed FIR designs such as the symmetric systolic form in [13] and the hybrid form in [1], the proposed form can achieve significant area and power savings with great ADP and PDP reduction. Moreover, when compared with the symmetric systolic form in [13] the required latency can be approximately reduced by 33.3%, which clearly shows the performance improvement of the proposed method.

Faithfully truncated adder-based area-power efficient FIR design with predefined output accuracy

Authors

Jinghao Ye,Masao Yanagisawa,Youhua Shi

Journal

IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

Published Date

2020/9/1

To solve the area and power problems in Finite Impulse Response (FIR) implementations, a faithfully truncated adder-based FIR design is presented in this paper for significant area and power savings while the predefined output accuracy can still be obtained. As a solution to the accuracy loss caused by truncated adders, a static error analysis on the utilization of truncated adders in FIRs was performed. According to the mathematical analysis, we show that, with a given accuracy constraint, the optimal truncated adder configuration for an area-power efficient FIR design can be effortlessly determined. Evaluation results on various FIR implementations by using the proposed faithfully truncated adder designs showed that up to 35.4% and 27.9% savings in area and power consumption can be achieved with less than 1 ulp accuracy loss for uniformly distributed random inputs. Moreover, as a case study for normally …

Facile Construction of Troponoid Derivatives Incorporating Imidazolin-2-one Moieties

Authors

Jing Yu,Xiaobei Chen,Ye Liu,Bing Wu,Haiyan Li,Yanwei Hu,Liang Wang,Shilei Zhang

Journal

Synthesis

Published Date

2020/6

Troponoid derivatives incorporating imidazolin-2-one moieties were efficiently constructed via a cascade process, under simple thermal conditions, which features a novel nitrogen source, is catalyst- and oxidant-free, and has high atom- and step-economy.

See List of Professors in Youhua Shi University(Waseda University)

Youhua Shi FAQs

What is Youhua Shi's h-index at Waseda University?

The h-index of Youhua Shi has been 8 since 2020 and 14 in total.

What are Youhua Shi's top articles?

The articles with the titles of

A Dual-Output Rectifier-based Self-Powered Interface Circuit for Triboelectric Nanogenerators

An Area-Power-Efficient Multiplier-less Processing Element Design for CNN Accelerators

Strategy for Improving Cycle of Maximized Energy Output of Triboelectric Nanogenerators

Dataflow Optimization through Exploring Single-Layer and Inter-Layer Data Reuse in Memory-Constrained Accelerators

Power-efficient deep convolutional neural network design through zero-gating PEs and partial-sum reuse centric dataflow

A High-Performance Symmetric Hybrid Form Design for High-Order FIR Filters

Faithfully truncated adder-based area-power efficient FIR design with predefined output accuracy

Facile Construction of Troponoid Derivatives Incorporating Imidazolin-2-one Moieties

are the top articles of Youhua Shi at Waseda University.

What are Youhua Shi's research interests?

The research interests of Youhua Shi are: Integrated circuits and Intelligent systems

What is Youhua Shi's total number of citations?

Youhua Shi has 653 citations in total.

    academic-engine

    Useful Links