A 65nm Silicon-on-Thin-Box (SOTB) Embedded 2T-MONOS Flash Achieving 0.22 pJ/bit Read Energy with 64 MHz Access for IoT Applications

Matsubara, Ken; Nagasawa, Tsutomu; Kaneda, Yoshinobu; Mitani, Hiroki; Sato, Hiroshi; Iwase, Takashi; Aoki, Yasunobu; Maekawa, Kazuyuki; Yamakoshi, Hideaki; Ito, Takashi; Kondo, Hiroyuki; Kimura, Takashi

doi:10.23919/vlsic.2019.8778078

Cited by 4 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By integrating Deep Learning Accelerator (DLA), NVIDIA DRIVE AGX Xavier can deliver an incredible 30 TOPS for automated driving [137]. To enable real-time sensing with limited energy generated by energy harvesting, Renesas embedded AI (e-AI) [138] demonstrated power efficiency of 8.8 TOPS/W [139]. The Renesas accelerator developed a processing-inmemory (PIM) architecture, an increasingly popular approach for AI technology, in which multiply-and-accumulate operations are performed in the memory circuit as data is read out from that memory.…”

Section: B Hardware-assisted ML In Iot Devicesmentioning

confidence: 99%

Hardware-Assisted Machine Learning in Resource-Constrained IoT Environments for Security: Review and Future Prospective

Kornaros¹

2022

IEEE Access

View full text Add to dashboard Cite

As the Internet of Things (IoT) technology advances, billions of multidisciplinary smart devices act in concert, rarely requiring human intervention, posing significant challenges in supporting trusted computing and user privacy, as well as protecting against attacks such as spoofing, denial of service (DoS), jamming, and eavesdropping. To tackle attacks on the IoT and cyber-physical ecosystem, many intrusion detection and security approaches have been presented in the literature. Machine learning (ML) based intrusion and anomaly detection has lately gained traction due to its capacity to cope with encrypted and rapidly developing threat techniques. This work investigates into machine learning (ML) and deep learning (DL) methodologies for IoT device security and examine the benefits, drawbacks, and potential. To protect an IoT infrastructure, various solutions look into hardware-based methods for ML-based IoT authentication, access control, secure offloading, and malware detection schemes. This review aims to illuminate the value of various approaches for addressing IoT security in a truly effective, flexible, and seamless manner, as well as to provide answers to questions about tradeoffs in integrating accelerators and customizing embedded device architectures for effective use of ML-based methods. INDEX TERMSAI-based IoT security, Hardware-based machine learning, IoT intrusion detection, Trusted embedded devices I. INTRODUCTION

show abstract

Section: B Hardware-assisted ML In Iot Devicesmentioning

confidence: 99%

Hardware-Assisted Machine Learning in Resource-Constrained IoT Environments for Security: Review and Future Prospective

Kornaros¹

2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…To prevent the case that the recharge period is longer than Tsi, additional design effort for eFlash is needed. Figure 15 (a) presents the MCU developed based on the combination of SOTB process, intermittent operation and 2T-MONOS eFlash with intrinsic advantages of low energy operations and less mask adder [29]. SOTB SRAM with very low standby power [30] is utilized as a write buffer to store analyzed data in place of eFlash, removing the energy consumption by write operations to eFlash.…”

Section: Extremely Low Energy Solution With Sotb (Silicon On Thin Burmentioning

confidence: 99%

Essential Roles, Challenges and Development of Embedded MCU Micro-Systems to Innovate Edge Computing for the IoT/AI Age

Kimura

Taito

Hidaka

2020

IEICE Trans. Electron.

Self Cite

View full text Add to dashboard Cite

Embedded system approaches to edge computing in IoT implementations are proposed and discussed. Rationales of edge computing and essential core capabilities for IoT data supply innovation are identified. Then, innovative roles and development of MCU and embedded flash memory are illustrated by technology and applications, expanding from CPS to big-data and nomadic/autonomous elements of IoT requirements. Conclusively, a technology roadmap construction specific to IoT is proposed.

show abstract

“…Energy-harvesting technology that derives energy from the surrounding environment, such as from solar radiation [1], pressure [2,3], friction [4], radio frequency (RF) energy [5,6], vibration [1,7], temperature [1,8], and light [9], is one of the core technologies of Internet-of-Things (IoT) sensors that operate without the need for power or batteries [10][11][12][13]. Since the power available for energy harvesting is quite limited, power consumption of less than a few microwatts is required in energy-harvesting circuits [14,15].…”

Section: Introductionmentioning

confidence: 99%

An Energy-Efficient UWB Transmitter with Wireless Injection Locking for RF Energy-Harvesting Sensors

Kim

Heo

Kwon

2021

Sensors

View full text Add to dashboard Cite

An ultralow-power ultrawideband (UWB) transmitter with an energy-efficient injection-locked radio frequency (RF) clock harvester that generates a carrier from an RF signal is proposed for RF energy-harvesting Internet-of-Things (IoT) sensor applications. The energy-efficient RF clock harvester based on the injection-locked ring oscillator (ILRO) is proposed to achieve optimal locking range and minimum input sensitivity to obtain an injection-locked 450 MHz clock in ultralow-power operation. A current-starved inverter-based delay stage is adopted that allows delay adjustment by bias voltage to minimize dynamic current consumption while maintaining a constant delay regardless of changes in process, supply voltage, and temperature (PVT). To minimize static current consumption, a UWB transmitter based on a digital-based UWB pulse generator and a pulse-driven switching drive amplifier is proposed. The proposed injection-locked RF clock harvester achieves the best RF input sensitivity of −34 dBm at a power consumption of 2.03 μW, enabling energy-efficient clock harvesting from low RF input power. In ultralow-power operation, a 23.8% locking range is achieved at the RF injection power of –15 dBm to cope with frequency changes due to PVT variations. The proposed UWB transmitter with RF clock harvester achieves the lowest energy consumption per pulse with an average power consumption of 97.03 μW and an energy consumption of 19.41 pJ/pulse, enabling operation with the energy available in RF energy-harvesting applications.

show abstract

A 65nm Silicon-on-Thin-Box (SOTB) Embedded 2T-MONOS Flash Achieving 0.22 pJ/bit Read Energy with 64 MHz Access for IoT Applications

Cited by 4 publications

References 0 publications

Hardware-Assisted Machine Learning in Resource-Constrained IoT Environments for Security: Review and Future Prospective

Hardware-Assisted Machine Learning in Resource-Constrained IoT Environments for Security: Review and Future Prospective

Essential Roles, Challenges and Development of Embedded MCU Micro-Systems to Innovate Edge Computing for the IoT/AI Age

An Energy-Efficient UWB Transmitter with Wireless Injection Locking for RF Energy-Harvesting Sensors

Contact Info

Product

Resources

About