Mohammad Alhawari

This book offers insights into hardware-software co-design of epilepsy prediction models. This comprehensive exploration is a key to unlocking the mysteries of seizure forecasting, equipped with expert guidance and visionary foresight. From theory to practice, the authors illuminate the path forward, providing researchers with the tools and knowledge needed to navigate this dynamic field with confidence. They explore the latest advancements in deep learning technology and gain invaluable perspectives on the future landscape of epilepsy research. Bridging the gap between innovation and practicality, this book is a beacon for those seeking to make a tangible impact in healthcare.

The increasing demand for high performance and energy efficiency in Artificial Neural Networks (ANNs) and Deep Learning (DL) accelerators has driven a wide range of application specific integrated circuits (ASICs). In recent years, this field has started to deviate from the conventional digital implementation of machine learning-based (ML) accelerators; instead, researchers have started to investigate implementation in the analog domain. This is due to two main reasons: better performance and lower power consumption. Analog processing has become more efficient than its digital counterparts, especially for Deep Neural Networks (DNNs), partly because emerging analog memory technologies have enabled local storage and processing known as compute in-memory (CIM), thereby reducing the amount of data movement between the memory and the processor. However, there are many challenges in the analog domain approach, such as the lack of a capable commercially available nonvolatile analog memory, and the analog domain is susceptible to variation and noise. Additionally, analog cores involve digital-to-analog converters (DACs) and analog-to-digital converters (ADCs), which consume up to 64% of total power consumption. An emerging trend has been to employ time-domain (TD) circuits to implement the multiply-accumulate (MAC) operation. TD cores require time-to-digital converters (TDCs) and digital-to-time converters (DTCs). However, DTC and TDC can be more energy and area efficient than DAC and ADC. TD accelerators leverage both digital and analog features, thereby enabling energy-efficient computing and scaling with complementary metal–oxide–semiconductor (CMOS) technology. The performance of TD accelerators can be substantially improved if custom-designed analog delay cells, DTC, and TDC are used. This monograph reviews state-of-the-art TD accelerators and discusses system considerations and hardware implementations. Additionally, the work analyzes the energy and area efficiency of the TD architectures, including spatially unrolled (SU) and recursive (REC) architectures, for varying input resolutions and network sizes to provide insight for designers into how to choose the appropriate TD approach for a particular application. The monograph also discusses an implemented scalable SU-TD accelerator synthesized in 65nm CMOS technology, and concludes with the limitations of time-domain computation and future work.

This book describes power management integrated circuits (PMIC), for power converters and voltage regulators necessary for energy efficient and small form factor systems. The authors discuss state-of-the-art PMICs not only for battery powered wearable devices, but also energy harvesting-based devices. The circuits presented support voltage scaling to reduce the overall average power consumption of a wearable device, resulting in longer device operating time. The discussion includes many designs, control techniques and approaches to distribute efficiently the power among different blocks in the device.• Demonstrates for readers how to innovate in designing power management integrated circuits (PMIC) suitable for wearable devices, powered by either battery or harvesting energy;• Introduces a dual outputs switched capacitor, using a single voltage regulator to minimize the area overhead and discusses the effect of having more than two outputs on the area and power efficiency;• Introduces a novel clock-less digital LDO regulator that eliminates the use of the clocked comparator and serial shift register in the conventional design;• Presents experimental results of energy harvesting-based power management units (PMU), using different combinations of power converters and voltage regulators, providing a guide for designers to select the appropriate option based on device requirements.

This book describes power management integrated circuits (PMIC), for power converters and voltage regulators necessary for energy efficient and small form factor systems. The authors discuss state-of-the-art PMICs not only for battery powered wearable devices, but also energy harvesting-based devices. The circuits presented support voltage scaling to reduce the overall average power consumption of a wearable device, resulting in longer device operating time. The discussion includes many designs, control techniques and approaches to distribute efficiently the power among different blocks in the device.• Demonstrates for readers how to innovate in designing power management integrated circuits (PMIC) suitable for wearable devices, powered by either battery or harvesting energy;• Introduces a dual outputs switched capacitor, using a single voltage regulator to minimize the area overhead and discusses the effect of having more than two outputs on the area and power efficiency;• Introduces a novel clock-less digital LDO regulator that eliminates the use of the clocked comparator and serial shift register in the conventional design;• Presents experimental results of energy harvesting-based power management units (PMU), using different combinations of power converters and voltage regulators, providing a guide for designers to select the appropriate option based on device requirements.

This book discusses the design and implementation of energy harvesting systems targeting wearable devices. Finally, the authors present power management circuits for using multiple energy harvesting sources at the same time to power devices and to enhance efficiency of the system.

This book discusses the design and implementation of energy harvesting systems targeting wearable devices. The authors describe in detail the different energy harvesting sources that can be utilized for powering low-power devices in general, focusing on the best candidates for wearable applications. Coverage also includes state-of-the-art interface circuits, which can be used to accept energy from harvesters and deliver it to a device in the most efficient way. Finally, the authors present power management circuits for using multiple energy harvesting sources at the same time to power devices and to enhance efficiency of the system.