Convolutional Neural Network (CNN) has attained high accuracy and it has been widely employed in image recognition tasks. In recent times, deep learning-based modern applications are evolving and it poses a challenge in research and development of hardware implementation. Therefore, hardware optimization for efficient accelerator design of CNN remains a challenging task. A key component of the accelerator design is a processing element (PE) that implements the convolution operation. To reduce the amount of hardware resources and power consumption, this article provides a new processing element design as an alternate solution for hardware implementation. Modified BOOTH encoding (MBE) multiplier and WALLACE tree-based adders are proposed to replace bulky MAC units and typical adder tree respectively. The proposed CNN accelerator design is tested on Zynq-706 FPGA board which achieves a throughput of 87.03 GOP/s for Tiny-YOLO-v2 architecture. The proposed design allows to reduce hardware costs by 24.5% achieving a power efficiency of 61.64 GOP/s/W that outperforms the previous designs.

This paper presents a novel maximum efficiency point (MEP) tracking method for wireless power transfer (WPT) systems. It is proved that at the MEP for a typical system containing a boost converter on the receiving end, the derivative dD/dV _in (V _in being the inverter's dc input and D being the duty cycle of the converter) is equal to or smaller than a constant β that is determined by system parameters. By tuning V _in and comparing dD/dV _in with β, the MEP can be tracked without a power or current sensor, hence reducing the tracking cost. A WPT system is demonstrated experimentally to verify the method. When the diameters of and the vertical distance between the transmitting and receiving coils are 4.3 and 2.35 cm, respectively, without horizontal misalignment, high efficiency is maintained even when the load ranges from 5 to 100 Ω, and the efficiency improvement reaches 41.2% when compared to the measured efficiencies without the proposed method. The differences between the maximum efficiencies tracked by the proposed method and the manually searched maximum values are at most 1.8%. Extension of the proposed method to WPT systems employing other popular forms of inverter, dc/dc converter, and coil topology is also presented.

This paper presents a four-level pulse amplitude modulation (PAM-4) receiver that incorporates a continuous time linear equalizer, a variable gain amplifier, a phase interpolator-based clock and data recovery, and a 4-tap direct decision feedback equalizer (DFE) for moderate channel loss applications in wireline communication. A dynamic current-mode logic comparator (DCMLC) is proposed and employed in the DFE. The DCMLC, which adopts dynamic logic, breaks the trade-off between the bandwidth and the clock to Q delay in the traditional current-mode logic comparator (CMLC). Compared with the traditional CMLC, the DCMLC reduces the clock to Q delay by 36%, which allows the implementation of a 4-tap direct DFE. Moreover, the first tap feedback signals are directly tapped from the output of the DCMLC, allowing the first tap feedback current to initiate 0.5UI before the decision clock. The PAM-4 receiver prototype is fabricated in a 65nm CMOS process. At a data rate of 56-Gbps, it can compensate for up to 20.17dB loss and achieve a bit error rate $< 1\text{E}$ -10 with a power efficiency of 4.75 pJ/bit.

A wireless intracranial pressure (ICP) monitoring system based on the air pressure sensing is proposed in this work. The proposed system is composed of an implantable ICP sensing device and a portable wireless data recorder. The ICP sensing device consists of an air pressure sensor, an ultra-thin air pouch for pressure sensing, and a low-power dedicated system-on-a-chip (SoC) for the data acquisition control and wireless transmission. The SoC consists of a power management unit, a wake-up controller, the sensor interface, a wireless transmitter, and the workflow control logic. The SoC is fabricated in 0.18 μm CMOS technology with a die area of 3.04 mm × 2 mm. Experimental results show that the prototype implantable ICP device has achieved a resolution of 0.2 mmHg and a battery lifetime of 1 week with a 3 V 50 mAh battery. The ICP device has been tested in the liquid environment. The nonlinearity error is less than ±0.4 mmHg for the full measurement range of -20 to +150 mmHg. Compared to the other implantable wireless ICP solutions in the literature, the proposed system alleviates the biocompatibility issue and increases the measurement accuracy.

Wi-Fi-based indoor position sensing solutions have the advantages of easy integration in mobile phones and low cost by using existing Wi-Fi access points. The mainstream methods are commonly based on the received signal strength indicator (RSSI), which suffers from multipath interference in complicated indoor environments. Through the in-depth analysis of the multipath interference, an RSSI-assisted time difference of arrival (TDoA) method is proposed for Wi-Fi-based indoor position sensing in this work. The key idea is to compensate for the multipath interference in the received signals based on the coarse estimation using RSSI and TDoA calculation. A prototype system has been implemented to validate the proposed method. Experimental results have demonstrated the effectiveness of the proposed method, especially for handling the multipath interference with small propagation delay difference. Experimental results show that the indoor position sensing system can achieve a 90th percentile error of 0.3 m. The proposed method can also achieve moderate computational complexity and moderate real-time performance compared to other methods.

In this paper, we set up a novel audio dataset named Gastrointestinal (GI) Sound Set which includes 6 kinds of body sounds Bowel sound, Speech, Snore, Cough, Groan, and Rub. We do sound event detection (SED) based on it, and can accurately detect 6 types of sound events. First, the GI Sound Set is collected by wearable auscultation devices. To ensure generalization, patients from five different hospital departments are recruited for data collection, along with a group of healthy subjects. GI Sound Set refers to Google AudioSet in data format but varies in audio length and sampling rate. Second, we extract Mel-filter features from the recordings and investigate the performance of different activation functions and neural network architectures for detecting sound events. We use data augmentation, class balance to deal with the problem of quantitative imbalance between classes on the dataset. We apply multiple instances learning(MIL) to give out not only bag-level results but also frame-level results. In this work, GI Sound Set is the largest body sound dataset to date, and our approach shows state-of-the-art performance with an average score of F1=81.06% evaluated on the test set. Due to its simple network and conventional processing method, our CRNN system has high universality, which can be used in other audio datasets, such as respiratory sound and heart sound.