12 September 2019 in IEEE Transactions on Circuits and Systems I: Regular Papers
In the era of Artificial Intelligence (AI), bio-inspired perceptual computing system design brings favorable opportunities, while still facing considerable challenges in the meantime. Especially for tasks of image recognition in power-limited vision-based Internet of Things (IoT) devices, energy constraints due to the end of Dennard scaling limit the performance of Neural Network (NN) algorithms on popular digital platforms, which would not reach the energy efficiency requirement for embedded AI applications. In this paper, a processing near sensor architecture in mixed-signal domain with CMOS Image Sensor (CIS) of convolutional-kernel-readout method is proposed. Visual data is collected from a smart CIS, which can realize maximum $5 x5$ kernel-readout with minimum one slide step for convolutional operations. The outputs of CIS are directly processed by analog processing units locating near CIS without the constraint of digital clock and bottleneck of Analog-to-Digital Converter (ADC). By analyzing the effects of analog noise on classification accuracy, we further evaluate the fault-tolerance of the system to circuit noise and the device imperfection, such as mismatch and process variation. A mixed-signal visual perception chip is fabricated with a 32 x 32 image sensor and a Binarized Neural Network (BNN) processing array integrated with SMIC 180nm standard CMOS mixed-signal process. Measurement results show up to 545.4 GOPS/W energy efficiency with 1.8mW power consumption taking the advantages of ADC-free processing architecture. This work provides a promising alternative for low-power vision-based IoT intelligent applications.
8 April 2020 in IEEE Transactions on Circuits and Systems I: Regular Papers
In recent years, Neural networks (NNs) present vast potential for innovative applications. However, energy efficiency continues to remain a challenge in deploying NNs on the edge. In this context, computation-in-memory (CIM) architecture becomes an emerging trend in the area of energy-efficient hardware design, because it reduces data movement of multiply-accumulate (MAC) computation significantly. However, many recent works employ massive data converters to feed input data and transform output results, which may counteract the benefits of in-memory processing. To tackle this limitation, we propose a combined architecture cooperating sensor with CIM macro to achieve local processing of sensory signals. Current-mode computing techniques are exploited to achieve high energy efficiency while eliminating data conversion overhead. Moreover, we thoroughly analyze the non-idealities of the proposed mixed-signal circuits and present a co-design scheme to mitigate these imperfections. We have fabricated a 2K-bit CIM macro in the proposed architecture with TSMC 65-nm technology. The fabricated chip achieved 60.6 TOPS/W energy efficiency while consuming 845.5 μW power and 0.3 mm² core area, presenting a promising solution for energy-constrained edge devices.
12 November 2019 in IEEE Transactions on Electron Devices
25 January 2021 in IEEE Sensors Letters
Recent years have witnessed the emerging development of flexible electronic devices in applications, such as human gait monitoring. The automatic posture identification could be achieved by sensing the feet pressure. However, the sensor data processing chip usually consumes high power. In this letter, a wearable gait recognition system integrated with an ultrahigh-energy efficiency chip is proposed. A low-power human gait pressure monitoring and recognition solution that uses artificial intelligence near-sensor chips is reported. A large-scale flexible pressure sensor array (64 × 64 pixels) was fabricated. The gait posture was recognized dynamically with a CMOS chip embedded near the sensors. The system owns a recognition rate for three different gaits of 92% with the chip power consumption of 1.45 mW. This letter paves the way for future low-power human gait monitoring.
13 September 2019 in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
The scale-invariant feature transform (SIFT) algorithm is still one of the most reliable image feature extraction methods. Despite its excellent robustness on various image transformations, SIFT's intensive computational burden has been severely preventing it from being used in real-time and energy-efficient embedded machine vision systems. To reduce processing time and energy cost while executing SIFT, an analog signal processing architecture, analog signal processing (ASP)-SIFT, is proposed in this article. In ASP-SIFT, the Gaussian pyramid construction, difference-of-Gaussian (DoG) pyramid construction and keypoint locating, which are the primary steps of the keypoint detection part of the SIFT algorithm, are done directly with analog circuit networks. Thus, by completing keypoint detection in the analog domain, the total processing time is approximately equal to the settling time of the circuit network. Besides, by adopting a current-mode circuit network operating in the subthreshold region, the power dissipation would be very low. Simulation results show that the total processing speed for a typical video graphics array (VGA)-format (640 x 480) image is up to 2.3 kframes per second, which is at least 3.26x faster than the state-of-the-art digital hardware accelerators, while the system power is 94.5 mW and the energy consumption is only 40 μJ per frame.