Electromyography (EMG) signals provide critical insights into neuromuscular function, yet their analysis remains challenging due to inherent noise, inter-subject variability, and non-stationary characteristics. Bio-inspired artificial intelligence (AI) models, drawing computational principles from biological neural systems, offer promising solutions to these challenges. This mini-review synthesizes recent advances in bio-inspired AI approaches for EMG signal processing, including spiking neural networks, hierarchical deep learning, attention mechanisms, and neuromorphic computing. We evaluate state-of-the-art methods, comparing their performance across key metrics including classification ac... More >

Biomedical research is increasingly shaped by vast and diverse datasets, yet their integration is constrained by privacy concerns, regulatory barriers, and fragmented infrastructures. Federated learning (FL) has emerged as a promising paradigm that enables institutions to collaboratively train machine learning models while keeping sensitive data local. This approach has the potential to accelerate discovery in areas such as precision medicine, rare disease research, and population health by pooling knowledge without centralizing data. However, federated learning also introduces new ethical and governance challenges. Risks of information leakage, inequitable participation, algorithmic bias, u... More >

The COVID-19 pandemic irrevocably altered our perception of public health, hygiene, and personal interaction, accelerating the demand for solutions that minimize physical contact. Once, using a fingerprint scanner, pressing a PIN, or touching a shared surface felt routine. During the pandemic, these simple actions suddenly became potential vectors for contagion. Touchless biometrics — technologies that capture unique biological characteristics without physical contact — have emerged as a crucial response. From facial recognition at airports to voice authentication in banking apps, “no touch required” is becoming the new standard, combining hygiene, convenience, and security. More >

Diabetic retinopathy (DR) is a leading cause of blindness globally, requiring timely detection and classification to prevent vision loss. Deep learning techniques offer significant potential for automating DR detection by analyzing retinal fundus images with high precision. This paper proposes a RetinoNet model that consists of MobileNetV3, Convolutional Block Attention Module (CBAM), Atrous Spatial Pyramid Pooling (ASPP), and Feature Pyramid Network (FPN). MobileNetV3 provides a lightweight and efficient foundation for feature extraction, while CBAM emphasizes critical spatial and channel information, enabling the detection of subtle retinal abnormalities. ASPP captures multi-scale contextu... More >

Compared with traditional storage media, biological data storage has advanced more rapidly in capacity, diversity, and lifespan, and it also enables continuous data retention. The DNA molecule, as Nature's own archival medium, provides unparalleled density, longevity, and passive durability, making it a compelling foundation for the next generation of "cold" and "deeply cold" archives. Since 2019, progress across the stack—coding for insertion–deletion–missing channels, large-scale random access, enzyme writing, nanopore-native retrieval, and chemically robust expansion—has transformed DNA storage from provocative demonstrations into mature technologies with early end-to-end prototyp... More >