Cardiovascular diseases remain a leading global health threat, with arrhythmia being a key early indicator of cardiac abnormalities. The need for continuous cardiac monitoring has driven demand for portable, low-power arrhythmia detection systems. This paper presents a low-power mixed-precision System-on-Chip (SoC) solution designed for arrhythmia detection using 12-lead electrocardiogram (ECG) signals. The proposed approach employs a dynamically reconfigurable convolutional neural network (CNN) architecture with flexible hyperparameters, enhancing hardware adaptability while reducing resource overhead and power consumption. At the computation level, an 8-bit and 16-bit mixed-precision floating-point multiplier is introduced to effectively balance arithmetic accuracy and energy efficiency. Furthermore, clock gating and multi-threshold voltage techniques are employed at the digital back-end to further reduce the power consumption of the chip. Through system-level and module-level optimization, the proposed chip design is of great significance for enabling low-power arrhythmia detection in power-constrained portable medical devices.

Addressing security threats faced by high efficiency video coding (HEVC) video devices in open deployment environments, this article proposes a HEVC Transform and Quantization (TQ)-based Software Physical Unclonable Function (TQ-SPUF). By overclocking the HEVC TQ module, this function induces clock violations on the critical path, thereby generating a stable and unique device fingerprint. Meanwhile, a two-stage postprocessing scheme combining majority voting and butterfly-xoroperations is employed to generate stable and uniform device fingerprints. Based on the proposed TQ-SPUF, a lightweight challenge-response authentication protocol was designed to achieve device identity binding. Furthermore, the PUF-gated session key is utilized to drive a dual-perturbation selective encryption scheme, which introduces both fixed- and random-position perturbations into the I-frame network abstraction layer units. In this way, semantic information exploitable was effectively disrupted, thereby preventing content recovery or tampering. Experimental results show that the proposed TQ-SPUF achieves 98.84% randomness and 49.15% uniqueness, passing part of the NIST test. Moreover, the encrypted videos exhibit an average peak signal-to-noise ratio (PSNR) of 10.4313dB and an average structural similarity index measure (SSIM) of 0.2935. This indicates that the encrypted content is visually incomprehensible, thereby achieving video anti-tampering protection.

The novel nonvolatile computing-in-memory (nvCIM) technology enables data to be stored and processed in situ, providing a feasible solution for the widespread deployment of machine learning algorithms in edge AI devices. However, current nvCIM approaches based on weighted current summation face challenges such as device nonidealities and substantial time, storage, and energy overheads when handling high-precision analog signals. To address these issues, we propose a resistive random access memory (RRAM)-based binary convolution macro for constructing a complete binary convolutional neural network (BCNN) hardware circuit, accelerating edge AI applications with low-weight precision. This macro performs error compensation at the circuit level and provides stable rail-to-rail output, eliminating the need for any ADCs or processor to perform auxiliary computations. Experimental results demonstrate that the proposed BCNN full-hardware computing system achieves on-chip recognition accuracy of 90.7% (98.64%) on the CIFAR10 (MNIST) dataset, which represents a decrease of 0.98% (0.59%) compared to software recognition accuracy. In addition, this binary convolution macro achieves a maximum throughput of 320 GOPS and a peak energy efficiency of 578 TOPS/W at 136 MHz.

Security and cost efficiency are of utmost importance for embedded processors when it comes to limiting hardware resources in IoT applications. This brief presents a security reduced instruction set computer-five (RISC-V) specific instruction set extension (ISE) designed based on hardware-assisted orthogonal obfuscation for hardware security. The orthogonal obfuscation defines an architecture geared toward high-security processors that supports a Pay-Per-ISE function using a key management unit (KMU), thus capable of supporting the customization of the key for a user’s partially authorized ISE and controlling the unlocking of the specific ISE. The proposed security RISC-V test chip is fabricated in a 65-nm CMOS technology with a core area occupying about 0.739 mm2. The measured results demonstrate that our processor realizes the instruction set authorization function. The results show an average power of 52.8 mW at 1.2 V, a hardware overhead of <3% at 50 MHz, and a 30% improvement in security.

The choroid provides oxygen and nourishment to the outer retina thus is related to the pathology of various ocular diseases. Optical coherence tomography (OCT) is advantageous in visualizing and quantifying the choroid in vivo. However, its application in the study of the choroid is still limited for two reasons. (1) The lower boundary of the choroid (choroid-sclera interface) in OCT is fuzzy, which makes the automatic segmentation difficult and inaccurate. (2) The visualization of the choroid is hindered by the vessel shadows from the superficial layers of the inner retina. In this paper, we propose to incorporate medical and imaging prior knowledge with deep learning to address these two problems. We propose a biomarker-infused global-to-local network (Bio-Net) for the choroid segmentation, which not only regularizes the segmentation via predicted choroid thickness, but also leverages a global-to-local segmentation strategy to provide global structure information and suppress overfitting. For eliminating the retinal vessel shadows, we propose a deep-learning pipeline, which firstly locate the shadows using their projection on the retinal pigment epithelium layer, then the contents of the choroidal vasculature at the shadow locations are predicted with an edge-to-texture generative adversarial inpainting network. The results show our method outperforms the existing methods on both tasks. We further apply the proposed method in a clinical prospective study for understanding the pathology of glaucoma, which demonstrates its capacity in detecting the structure and vascular changes of the choroid related to the elevation of intra-ocular pressure.