Low-Power MCU With Embedded ReRAM Buffers as Sensor Hub for IoT Applications

Chien, Tsai-Kan; Chiou, Lih-Yih; Sheu, Shyh-Shyuan; Lin, Jing-Cian; Lee, Chang-Chia; Ku, Tzu–Kun; Tsai, Ming-Jinn; Wu, Chih-I

doi:10.1109/jetcas.2016.2547778

Cited by 31 publications

(23 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, the microcontrollers are also used to interconnect devices from different vendors. The frequently used microcontrollers include Arduino [22], Raspberry Pi microcontroller board [23], and an 8-bit microcontroller to power lightweight sensors [24]. In industrial applications, the microcontrollers should be well incorporated into the IoT systems.…”

Section: Related Workmentioning

confidence: 99%

A Smart Microcontroller Architecture for the Internet of Things

Qiu

Zhang

2020

Sensors

View full text Add to dashboard Cite

The interoperations of endpoint devices are generally achieved by gateways in Internet of Things (IoT) systems. However, the gateways mainly focus on networking communication, which is lack of data logic control capabilities. The microcontrollers with embedded intelligence could work as an intermediate device to help the interconnections of the endpoint devices. Moreover, they could help control the endpoint devices. In this paper, a microcontroller architecture with intelligent and scalable characteristics is proposed. The intelligence means that the microcontroller could control the target endpoint devices by its logical circuits, and the scalability means that the microcontroller architecture could be easily extended to deal with more complex problems. Two real world industrial implementations of the proposed architecture are introduced. The implementations show that the microcontroller is important to provide the intelligent services to users in IoT systems. Furthermore, a simulation experiment based on the cloud model is designed to evaluate the proposed method. The experimental results demonstrate the effectiveness of the proposed architecture.

show abstract

Section: Related Workmentioning

confidence: 99%

A Smart Microcontroller Architecture for the Internet of Things

Qiu

Zhang

2020

Sensors

View full text Add to dashboard Cite

show abstract

“…Currently, FLASH is the widely used technology for wearable and mobile devices [23]. However, emerging non-volatile memory technologies, such as FeRAM [24,25] and RRAM [26][27][28], are expected to replace conventional memories [29,30].…”

Section: Iot Applicationsmentioning

confidence: 99%

MB-CNN: Memristive Binary Convolutional Neural Networks for Embedded Mobile Devices

Chowdhury

Kulkarni

Bojnordi

2018

JLPEA

View full text Add to dashboard Cite

Applications of neural networks have gained significant importance in embedded mobile devices and Internet of Things (IoT) nodes. In particular, convolutional neural networks have emerged as one of the most powerful techniques in computer vision, speech recognition, and AI applications that can improve the mobile user experience. However, satisfying all power and performance requirements of such low power devices is a significant challenge. Recent work has shown that binarizing a neural network can significantly improve the memory requirements of mobile devices at the cost of minor loss in accuracy. This paper proposes MB-CNN, a memristive accelerator for binary convolutional neural networks that perform XNOR convolution in-situ novel 2R memristive data blocks to improve power, performance, and memory requirements of embedded mobile devices. The proposed accelerator achieves at least 13.26 × , 5.91 × , and 3.18 × improvements in the system energy efficiency (computed by energy × delay) over the state-of-the-art software, GPU, and PIM architectures, respectively. The solution architecture which integrates CPU, GPU and MB-CNN outperforms every other configuration in terms of system energy and execution time.

show abstract

“…Typically, there are several sensing devices connected to a sensor hub. In the sensor hub, data from the sensors is firstly buffered and waiting for further processing by the Microcontroller unit (MCU) until a certain amount of data has been accumulated in the buffer [3] . The sensing data can be processed in batch by the sensor hub or uploaded to the servers connected to the sensor hub.…”

Section: Introductionmentioning

confidence: 99%