Environmental factors like weather and road conditions significantly impact object recognition in autonomous vehicles. While cameras provide rich semantic information, their reliance on electromagnetic waves makes them vulnerable to performance degradation in adverse conditions such as low light and rain. In contrast, ultrasonic sensors offer reliable short-range detection, unaffected by such conditions. We introduce Bat-VUFN, a bio-inspired multi-sensory system that merges camera and ultrasonic data using an Input Quality Score (IQS)-based fusion technique to enhance near-field perception in challenging environments. Bat-VUFN dynamically adjusts sensor contributions based on prevailing conditions, achieving impressive results on the K-Bat dataset (average precision: 0.95, MAE: 0.52m, RMSE: 0.55m), demonstrating its robustness in adverse scenarios.

In convolutional neural network (CNN) accelerators, the dominant power consumption is caused by the access of external data memory. In addition, power and area occupied by I/O interfaces maintaining low bit-error-rate, e.g., 1e-15, grow as the data rate increases. Considering the inherent error resilience of the inference process in machine learning applications, the requirement of error-free communication in the data-path is controversial. In this paper, a custom CNN accelerator integrating a channel emulator is designed by using an FPGA to analyze the effect of the BER of an I/O transceiver on the image classification accuracy. In order to implement a channel emulator, a digital-domain look-up-table (LUT)-based 12-tap FIR filter is employed to create inter-symbol interference (ISI), and a PRBS31 generator is used as a noise source. The implementation was evaluated by running the ImageNet dataset on the FPGA-based custom accelerator (Virtex Ultrascale+) implementing VGG-16. The results show that the BER up to 1e-4 in the memory access has a negligible impact on the inference accuracy.

In this paper, a bat-inspired high-resolution ultrasound 3D imaging system is presented. Live bats demonstrate that the properly used ultrasound can be used to perceive 3D space. With this in mind, a neural network referred to as a Bat-G network is implemented to reconstruct the 3D representation of target objects from the hyperbolic FM (HFM) chirped ultrasonic echoes. The Bat-G network consists of an encoder emulating a bat's central auditory pathway, and a 3D graphical visualization decoder. For the acquisition of the ultrasound data, a custom-made Bat-I sensor module is used. The Bat-G network shows the uniform 3D reconstruction results and achieves precision, recall, and F1-score of 0.896, 0.899 and 0.895, respectively. The experimental results demonstrate the implementation feasibility of a high-resolution non-optical sound-based imaging system being used by live bats. The project web page (https://sites.google.com/view/batgnet) contains additional content summarizing our research.

This brief presents a new frequency acquisition method using a semirotational frequency detection (SRFD) algorithm for referenceless clock and data recovery (CDR) in a serial-link receiver. The proposed SRFD algorithm classifies the bang-bang phase detector (BBPD) outputs to estimate the current phase state and detects the frequency mismatch between the input data and the sampling clock. The voltage-controlled oscillator (VCO)-track path in a digital loop filter (DLF) enables online calibration of a drifted frequency of the VCO caused by temperature or voltage variation after a frequency acquisition. The proposed algorithm can be implemented as a digitally synthesized circuit, lowering design efforts for referenceless CDRs. A 10-Gb/s transceiver IC with the proposed algorithm, fabricated in a 65-nm CMOS process, demonstrates successful recovery of the input phase without any reference clock.

A four-parallel 10-Gb/s referenceless-and-masterless phase rotator-based transceiver is presented. Entire lanes operate independently just like the conventional voltage-controlled-oscillator-based parallel referenceless designs while saving power and area. The measured recovered-clock jitter in each lane is 1.24 psrms and the transceiver surpasses the OC-192 jitter-tolerance specification. The power efficiency of the proposed parallel transceiver fabricated in a 90-nm CMOS process is 6.325 mW/(Gb/s).

A 0.6-2.7-Gb/s phase-rotator-based four-channel digital clock and data recovery (CDR) IC featuring a low-power dispersion-tolerant referenceless frequency acquisition technique is presented. A quasi-periodic reference clock signal extracted directly from a dispersed input signal is distributed to digitally controlled phase rotators in the CDR ICs for phase acquisition. A multiphase frequency acquisition scheme is employed for the reduction of the clock jitter. The measurement results show that the proposed design offers a lower frequency offset and clock noise floor under channel dispersion, as compared with conventional designs. The proposed four-channel digital CDR IC is fabricated in a 90-nm CMOS process. The figure of merit for a single channel is 8 mW/Gb/s such as a feedforward equalizer, a decision-feedback equalizer, and a referenceless CDR.

An efficient method for the extraction of hemodynamic response in near-infrared spectroscopy (NIRS) systems is proposed to increase the spatial and temporal resolution without hardware overhead. The performance improvement is attributed to high-signal-to-noise-ratio (SNR) receivers, a modulation scheme, and a multi input multi output (MIMO) based data extraction algorithm. The proposed systems shows a 72% increment in the figure of merit (FOM) compared to conventional designs. Experimental results support the validity of the proposed system.