https://scholars.lib.ntu.edu.tw/handle/123456789/632309
標題: | CIM-Based Smart Pose Detection Sensors | 作者: | Chou J.-J Chang T.-W Liu X.-Y Wu T.-Y Chen Y.-K Hsu Y.-T Chen C.-W TSUNG-TE LIU CHI-SHENG SHIH |
關鍵字: | analogy computing; non-ideality errors; smart sensors | 公開日期: | 2022 | 卷: | 22 | 期: | 9 | 來源出版物: | Sensors | 摘要: | The majority of digital sensors rely on von Neumann architecture microprocessors to process sampled data. When the sampled data require complex computation for 24 × 7, the processing element will a consume significant amount of energy and computation resources. Several new sensing algorithms use deep neural network algorithms and consume even more computation resources. High resource consumption prevents such systems for 24 × 7 deployment although they can deliver impressive results. This work adopts a Computing-In-Memory (CIM) device, which integrates a storage and analog processing unit to eliminate data movement, to process sampled data. This work designs and evaluates the CIM-based sensing framework for human pose recognition. The framework consists of uncertainty-aware training, activation function design, and CIM error model collection. The evaluation results show that the framework can improve the detection accuracy of three poses classification on CIM devices using binary weights from 33.3% to 91.5% while that on ideal CIM is 92.1%. Although on digital systems the accuracy is 98.7% with binary weight and 99.5% with floating weight, the energy consumption of executing 1 convolution layer on a CIM device is only 30,000 to 50,000 times less than the digital sensing system. Such a design can significantly reduce power consumption and enables battery-powered always-on sensors. © 2022 by the authors. Licensee MDPI, Basel, Switzerland. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85129406696&doi=10.3390%2fs22093491&partnerID=40&md5=b69ee52cf511e6ed91b7a6f6bd91c25f https://scholars.lib.ntu.edu.tw/handle/123456789/632309 |
ISSN: | 14248220 | DOI: | 10.3390/s22093491 | SDG/關鍵字: | Deep neural networks; Digital storage; Gesture recognition; Analogy computing; Complex computation; Computation resources; Detection sensors; Digital sensors; Neumann architecture; Non-ideality error; Nonideality; Pose detection; Sampled data; Energy utilization |
顯示於: | 資訊工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。