Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 May 4;22(9):3491.
doi: 10.3390/s22093491.

CIM-Based Smart Pose Detection Sensors

Jyun-Jhe Chou  1 , Ting-Wei Chang  1 , Xin-You Liu  1 , Tsung-Yen Wu  2 , Yu-Kai Chen  2 , Ying-Tuan Hsu  2 , Chih-Wei Chen  3   4 , Tsung-Te Liu  2 , Chi-Sheng Shih  1   3   5
Affiliations

CIM-Based Smart Pose Detection Sensors

Jyun-Jhe Chou et al. Sensors (Basel). .

Abstract

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.

Keywords: analogy computing; non-ideality errors; smart sensors.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Color Photos and Thermal Images at Okayama Hospital, Japan: (a) Laydown, (b) Turn to the right.
Figure 2
Figure 2
The von Neumann and CIM Architecture for Thermal Image Processing.
Figure 3
Figure 3
Examples of Thermal Heat-Map Images: (a) Low-Resolution Thermal Image; (b) High-Resolution Thermal Image.
Figure 4
Figure 4
Quantization SRCNN: (a) Post-Training Quantization; (b) Quantization Aware Training.
Figure 5
Figure 5
Overall System Architecture of CIM-Based Smart Sensor.
Figure 6
Figure 6
Thermal Box Design.
Figure 7
Figure 7
Mapping on Different Input Sources.
Figure 8
Figure 8
Difference Between Bias-Voltage.
Figure 9
Figure 9
Error Distribution: (a) Expected = −6; (b) Expected = −3; (c) Expected = 0; (d) Expected = 3; (e) Expected = 6.
Figure 10
Figure 10
Example Data for Pose Detection: (a) Empty; (b) Sitting; (c) Laying.
Figure 11
Figure 11
Network Architecture for Pose Detection.
Figure 12
Figure 12
Experimental Setting for CIM SRAM and FPGA.
Figure 13
Figure 13
Input Images for Pose Detection: (a) Standing; (b) Raising hand; (c) Arms on hips; (d) Crossing hands; (e) Hands on hips.
Figure 14
Figure 14
Energy Consumption Measurement for ARM- and CIM-based platforms.
See this image and copyright information in PMC

References

    1. Studenski S., Perera S., Patel K., Rosano C., Faulkner K., Inzitari M., Brach J., Chandler J., Cawthon P., Connor E.B., et al. Gait speed and survival in older adults. JAMA. 2011;305:50–58. doi: 10.1001/jama.2010.1923. - DOI - PMC - PubMed
    1. Jang I.Y., Kim H.R., Lee E., Jung H.W., Park H., Cheon S.H., Lee Y.S., Park Y.R. Impact of a wearable device-based walking programs in rural older adults on physical activity and health outcomes: Cohort study. JMIR mHealth uHealth. 2018;6:e11335. doi: 10.2196/11335. - DOI - PMC - PubMed
    1. Zhang J., Wang Z., Verma N. In-memory computation of a machine-learning classifier in a standard 6T SRAM array. IEEE J. Solid-State Circuits. 2017;52:915–924. doi: 10.1109/JSSC.2016.2642198. - DOI
    1. Chen Z., Chen X., Gu J. 15.3 A 65nm 3T Dynamic Analog RAM-Based Computing-in-Memory Macro and CNN Accelerator with Retention Enhancement, Adaptive Analog Sparsity and 44TOPS/W System Energy Efficiency; Proceedings of the 2021 IEEE International Solid-State Circuits Conference (ISSCC); San Francisco, CA, USA. 13–22 February 2021; pp. 240–242.
    1. Si X., Chen J.J., Tu Y.N., Huang W.H., Wang J.H., Chiu Y.C., Wei W.C., Wu S.Y., Sun X., Liu R., et al. A twin-8T SRAM computation-in-memory unit-macro for multibit CNN-based AI edge processors. IEEE J. Solid-State Circuits. 2019;55:189–202. doi: 10.1109/JSSC.2019.2952773. - DOI

LinkOut - more resources