scholarly journals Deep Learning for Photonic Design and Analysis: Principles and Applications

2022 ◽  
Vol 8 ◽  
Author(s):  
Bing Duan ◽  
Bei Wu ◽  
Jin-hui Chen ◽  
Huanyang Chen ◽  
Da-Quan Yang
Keyword(s):  
Deep Learning ◽  
Data Analysis ◽  
Research Field ◽  
Structure Design ◽  
Low Energy ◽  
Optical Data ◽  
Photonic Structure ◽  
Optical Neural Networks ◽  
Energy Consuming ◽  
Innovative Techniques

Innovative techniques play important roles in photonic structure design and complex optical data analysis. As a branch of machine learning, deep learning can automatically reveal the inherent connections behind the data by using hierarchically structured layers, which has found broad applications in photonics. In this paper, we review the recent advances of deep learning for the photonic structure design and optical data analysis, which is based on the two major learning paradigms of supervised learning and unsupervised learning. In addition, the optical neural networks with high parallelism and low energy consuming are also highlighted as novel computing architectures. The challenges and perspectives of this flourishing research field are discussed.

scholarly journals Design and exploration of neural network microsystem based on SiP

2021 ◽  
Vol 3 (9) ◽  
Author(s):  
Hao Lv ◽  
Shengbing Zhang ◽  
Bao Deng ◽  
Jia Wang ◽  
Desheng Jing ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Power Consumption ◽  
Convolutional Neural Network ◽  
Research Field ◽  
Structure Design ◽  
Learning Technology ◽  
Balance Performance ◽  
Fpga Design ◽  
Data Set

AbstractIn recent years, microelectronics technology has entered the era of nanoelectronics/integrated microsystems. System in package (SiP) and system on chip (SoC) are two important technical approaches for the realization of microsystems. Deep learning technology based on neural networks is used in graphics and images. Computer vision and target recognition are widely used. The deep learning technology of convolutional neural network is an important research field in the miniaturization and miniaturization of embedded platforms. How to combine the lightweight neural network with the microsystem to achieve the optimal balance of performance, size, and power consumption is a difficult point. This article introduces a micro-system implementation scheme that combines SiP technology and FPGA-based convolutional neural network. It uses Zynq SoC and FLASH and DDR3 memory as the main components, and uses SiP high-density system packaging technology to integrate. PL end (FPGA) design Convolutional Neural Network, convolutional neural network accelerator, adopt the method of convolution multi-dimensional division and cyclic block to design the accelerator structure, design multiple multiplication and addition parallel computing units to provide the computing power of the system. Improving and accelerating perform on the YOLOv2_Tiny model. The test uses the COCO data set as the training and test samples. The microsystem can accurately identify the target. The volume is only 30 × 30 × 1.2 mm. The performance reaches 22.09GOPs and the power consumption is only 0.81 W under the working frequency of 150 MHz. Multi-objective balance (performance, size and power consumption) of lightweight neural network Microsystems has realized.

Towards Hardware-driven Design of Low-energy Algorithms for Data Analysis

2015 ◽  
Vol 43 (4) ◽  
pp. 15-20 ◽  
Author(s):  
Indre Zliobaite ◽  
Jaakko Hollmen ◽  
Lauri Koskinen ◽  
Jukka Teittinen
Keyword(s):  
Data Analysis ◽  
Low Energy

scholarly journals Optical Data Analysis: Decoding Optical Data with Machine Learning (Laser Photonics Rev. 15(2)/2021)

2021 ◽  
Vol 15 (2) ◽  
pp. 2170017
Author(s):  
Jie Fang ◽  
Anand Swain ◽  
Rohit Unni ◽  
Yuebing Zheng
Keyword(s):  
Machine Learning ◽  
Data Analysis ◽  
Optical Data

Novel Trapezoidal-Loop Piezoelectric Energy Harvester

2014 ◽  
Vol 672-674 ◽  
pp. 402-406
Author(s):  
Bing Jiang ◽  
Shuai Yuan ◽  
Xiao Hui Xu ◽  
Mao Sheng Ding ◽  
Ye Yuan ◽  
...  
Keyword(s):  
Output Voltage ◽  
Energy Harvester ◽  
Research Field ◽  
Structure Design ◽  
Loop Structure ◽  
Element Analysis ◽  
Resonant Frequencies ◽  
First Order ◽  
Microelectronic Devices ◽  
Piezoelectric Energy

In recent years, piezoelectric energy harvester which can replace the traditional battery supply has become a hot topic in global research field of microelectronic devices. Characteristics of a trapezoidal-loop piezoelectric energy harvester (TLPEH) were analyzed through finite-element analysis. The output voltage density is 4.251V/cm2 when 0.1N force is applied to the free end of ten-arm energy harvester. Comparisons of the resonant frequencies and output voltages were made. The first order resonant frequency could reach 15Hz by increasing the number of arms. Meanwhile, the output voltage is improved greatly when excited at first-order resonant frequencies. The trapezoidal-loop structure of TLPEH could enhance frequency response, which means scavenging energy more efficiently in vibration environment. The TLPEH mentioned here might be useful for the future structure design of piezoelectric energy harvester with low resonance frequency.

scholarly journals Rapid mapping of landslides in the Western Ghats (India) triggered by 2018 extreme monsoon rainfall using a deep learning approach

Landslides ◽  
2021 ◽  
Author(s):  
Sansar Raj Meena ◽  
Omid Ghorbanzadeh ◽  
Cees J. van Westen ◽  
Thimmaiah Gudiyangada Nachappa ◽  
Thomas Blaschke ◽  
...  
Keyword(s):  
Deep Learning ◽  
Western Ghats ◽  
Auxiliary Information ◽  
Optical Data ◽  
Spectral Information ◽  
Topographic Slope ◽  
Western Ghats Of India ◽  
Landslide Inventory Map ◽  
Inventory Map ◽  
The Western Ghats

AbstractRainfall-induced landslide inventories can be compiled using remote sensing and topographical data, gathered using either traditional or semi-automatic supervised methods. In this study, we used the PlanetScope imagery and deep learning convolution neural networks (CNNs) to map the 2018 rainfall-induced landslides in the Kodagu district of Karnataka state in the Western Ghats of India. We used a fourfold cross-validation (CV) to select the training and testing data to remove any random results of the model. Topographic slope data was used as auxiliary information to increase the performance of the model. The resulting landslide inventory map, created using the slope data with the spectral information, reduces the false positives, which helps to distinguish the landslide areas from other similar features such as barren lands and riverbeds. However, while including the slope data did not increase the true positives, the overall accuracy was higher compared to using only spectral information to train the model. The mean accuracies of correctly classified landslide values were 65.5% when using only optical data, which increased to 78% with the use of slope data. The methodology presented in this research can be applied in other landslide-prone regions, and the results can be used to support hazard mitigation in landslide-prone regions.

Sign in / Sign up

Export Citation Format

Share Document