Browsing by Author "Chang, Kuo-Wei"

Now showing 1 - 5 of 5

EMBRYO LAB CHIP TAKING ADVANTAGE OF MICROFLUIDICS AND CELL CO-CULTURING
(2015)
Liu, Cheng-Hsien
;
Chang, Kuo-Wei
;
Chang, Pei-Yu
;
Sung, Yi-Jung
;
Huang, Hong-Yuan
This research serves as an in vitro platform for fertilization and embryonic development. Thin polydimethylsiloxane ( PDMS) membrane was etched to create an array of through-holes, and sandwiched between two PDMS channels to form an upper chamber and lower chamber. This device integrates the concentration gradient design and perfusion system for proposed embryo coculture with stromal cells.
Fabrication of 3D Microfluidic Chip integrating Concentration gradient design and Perfusion system for Embryo coculture with Stromal cells
(2012-01-01)
Chang, Pei-Yu
;
Chang, Kuo-Wei
;
Lin, Ciou-Wen
;
Shih, Po-Chen
;
Liu, Cheng-Hsien
Fabrication of 3D chip that enables cell culture under continuous flow perfusion and repeated in situ observation by light microscopy is described. Thin polydimethylsiloxane PDMS) membrane was etched to create an array of through-holes, and sandwiched between two PDMS channels to form an upper chamber and lower chamber. Thus we fabricated a 3D microfluidic chip which integrates the concentration gradient design and perfusion system for proposed embryo coculture with stromal cells.
VSCNN: Convolution Neural Network Accelerator With Vector Sparsity
(2019-01-01)
Chang, Kuo-Wei
;
Chang, Tian-Sheuan
;
電子工程學系及電子研究所
;
Department of Electronics Engineering and Institute of Electronics
Hardware accelerator for convolution neural network (CNNs) enables real time applications of artificial intelligence technology. However, most of the accelerators only support dense CNN computations or suffers complex control to support fine grained sparse networks. To solve above problem, this paper presents an efficient CNN accelerator with 1-D vector broadcasted input to support both dense network as well as vector sparse network with the same hardware and low overhead. The presented design achieves 1.93X speedup over the dense CNN computations.
VWA: Hardware Efficient Vectorwise Accelerator for Convolutional Neural Network
(2020-01-01)
Chang, Kuo-Wei
;
Chang, Tian-Sheuan
;
電子工程學系及電子研究所
;
Department of Electronics Engineering and Institute of Electronics
Hardware accelerators for convolution neural networks (CNNs) enable real-time applications of artificial intelligence technology. However, most of the existing designs suffer from low hardware utilization or high area cost due to complex data flow. This paper proposes a hardware efficient vectorwise CNN accelerator that adopts a $3\times 3$ filter optimized systolic array using 1-D broadcast data flow to generate partial sum. This enables easy reconfiguration for different kinds of kernels with interleaved input or elementwise input data flow. This simple and regular data flow results in low area cost while attains high hardware utilization. The presented design achieves 99, 97, 93.7, and 94 hardware utilization for VGG-16, ResNet-34, GoogLeNet, and Mobilenet, respectively. Hardware implementation with TSMC 40nm technology takes 266.9K NAND gate count and 191KB SRAM to support 168GOPS throughput while consumes only 154.98mW when running at 500MHz operating frequency, which has superior area and power efficiency than other designs.
Womb-on-a-chip biomimetic system for improved embryo culture and development
(2016-04-01)
Chang, Kuo-Wei
;
Chang, Pei-Yu
;
Huang, Hong-Yuan
;
Li, Chin-Jung
;
Tien, Chang-Hung
The 3D biomimetic microsystem described in this research integrates various functions of the fallopian tube to serve as an in vitro platform for fertilization and embryonic development. This device mimics the in vivo embryo-endometrial stromal cell monolayer coculture to enhance the group culture of embryos and mechanically culture the embryos in a dynamic manner to enhance their development. The microdevice presented here is compared with static culture for embryonic development rate in the presence and absence of epithelial cells. The results suggest that the dynamic biomimetic microsystem enhances the rate of embryo development, providing a culture environment that closely mimics the in vivo microenvironment. This all-in-one biomimetic microsystem has the potential to replace the present embryo culture platforms used for assisting in vitro fertilization. (C) 2015 Elsevier B.V. All rights reserved.