A 2.4 GHz LC-VCO Fractional-N Phase Locked Loop Open-Source Design in 130-nm BiCMOS

Radio frequency (RF) integrated circuit design using the open-source complementary Metal-Oxide semiconductor (CMOS) ecosystem, such as for phase-locked loops (PLLs), is limited by the absence of reliable passive device models, particularly on-chip spiral inductors. Consequently, prior work relies on ring-oscillator-based voltage-controlled oscillators (VCOs) with degraded phase noise performance. This work presents a 2.4 GHz type-II fractional-N PLL implemented in the IHP SG13G2 130 nm BiCMOS open-source technology. The proposed design employs a cross-coupled differential LC-VCO integrated with a custom-designed spiral inductor, developed using an open-source electromagnetic modelling workflow in OpenEMS. The optimized inductor achieves 4 nH inductance with a quality factor of 16.8 at 2.45 GHz. The LC-VCO sensitivity is approximately 120 MHz/V, while the PLL phase noise is -100.8 dBc/Hz at 1 MHz offset. The complete PLL is realized using a fully open-source electronic design automation (EDA) flow, occupying a total area of 930 um x 666 um (~0.619 mm2) and consuming 12.73 mW, demonstrating the feasibility of RF integrated circuit design in an open-source CMOS IC design ecosystem.

A Patient-Independent Neonatal Seizure Prediction Model Using Reduced Montage EEG and ECG

Neonates are highly susceptible to seizures, often leading to short or long-term neurological impairments. However, clinical manifestations of neonatal seizures are subtle and often lead to misdiagnoses. This increases the risk of prolonged, untreated seizure activity and subsequent brain injury. Continuous video electroencephalogram (cEEG) monitoring is the gold standard for seizure detection. However, this is an expensive evaluation that requires expertise and time. In this study, we propose a convolutional neural network-based model for early prediction of neonatal seizures by distinguishing between interictal and preictal states of the EEG. Our model is patient-independent, enabling generalization across multiple subjects, and utilizes mel-frequency cepstral coefficient matrices extracted from multichannel EEG and electrocardiogram (ECG) signals as input features. Trained and validated on the Helsinki neonatal EEG dataset with 10-fold cross-validation, the proposed model achieved an average accuracy of 97.52%, sensitivity of 98.31%, specificity of 96.39%, and F1-score of 97.95%, enabling accurate seizure prediction up to 30 minutes before onset. The inclusion of ECG alongside EEG improved the F1-score by 1.42%, while the incorporation of an attention mechanism yielded an additional 0.5% improvement. To enhance transparency, we incorporated SHapley Additive exPlanations (SHAP) as an explainable artificial intelligence method to interpret the model and provided localization of seizure focus using scalp plots. The overall results demonstrate the model's potential for minimally supervised deployment in neonatal intensive care units, enabling timely and reliable prediction of neonatal seizures, while demonstrating strong generalization capability across unseen subjects through transfer learning.