Rikky Muller

Jade Pinkenburg, Changuk Lee, Mohammad Meraj Ghanbari et al.

Spatially distributed peripheral nerve recordings can be used to reconstruct motor intention and improve natural control of prosthetics However, many existing clinical solutions rely on percutaneous wires to access peripheral nerves; these sites are prone to infection and motion-induced electrode degradation, preventing chronic use. To address the need for fully wireless neural recording systems, this paper presents DustNet: a spatially-distributed network of ultrasonically-powered neural recording implants capable of supporting up to 8 simultaneously recording nodes over a single ultrasound link. To enable high throughput multi-implant communication, DustNet implements a time-division multiple-access (TDMA) protocol with up to 16-level amplitude modulation of the ultrasound backscatter that achieves up to 4x higher data rates than traditional on-off keying methods. Each neural implant consists of a 0.7x0.7x0.7 mm$^3$ piezoceramic transducer, a 100 nF off-chip capacitor, and an IC mounted on a flexible PCB. The implant IC was fabricated in a 28nm CMOS process and occupies an area of 0.43 mm$^2$. System functionality was verified at 90mm depth in oil, achieving a maximum measured data rate of 200 kb/s at 2 MHz ultrasound carrier frequency, with each implant transmitting uplink data at 50 kb/s and dissipating just 7 $μ$W; the system is demonstrated to support up to 400 kb/s total data rate over the same link.

Aviral Pandey, Adelson Chua, Ryan Kaveh et al.

Early prediction of seizures and timely interventions are vital for improving patients' quality of life. While seizure prediction has been shown in software-based implementations, to enable timely warnings of upcoming seizures, prediction must be done on an edge device to reduce latency. Ideally, such devices must also be low-power and track long-term drifts to minimize maintenance from the user. This work presents SPIRIT: Stochastic-gradient-descent-based Predictor with Integrated Retraining and In situ accuracy Tuning. SPIRIT is a complete system-on-a-chip (SoC) integrating an unsupervised online-learning seizure prediction classifier with eight 14.4 uW, 0.057 mm2, 90.5 dB dynamic range, Zoom Analog Frontends. SPIRIT achieves, on average, 97.5%/96.2% sensitivity/specificity respectively, predicting seizures an average of 8.4 minutes before they occur. Through its online learning algorithm, prediction accuracy improves by up to 15%, and prediction times extend by up to 7x, without any external intervention. Its classifier consumes 17.2 uW and occupies 0.14 mm2, the lowest reported for a prediction classifier by >134x in power and >5x in area. SPIRIT is also at least 5.6x more energy efficient than the state-of-the-art.

Adelson Chua, Michael I. Jordan, Rikky Muller

Implantable devices that record neural activity and detect seizures have been adopted to issue warnings or trigger neurostimulation to suppress epileptic seizures. Typical seizure detection systems rely on high-accuracy offline-trained machine learning classifiers that require manual retraining when seizure patterns change over long periods of time. For an implantable seizure detection system, a low power, at-the-edge, online learning algorithm can be employed to dynamically adapt to the neural signal drifts, thereby maintaining high accuracy without external intervention. This work proposes SOUL: Stochastic-gradient-descent-based Online Unsupervised Logistic regression classifier. After an initial offline training phase, continuous online unsupervised classifier updates are applied in situ, which improves sensitivity in patients with drifting seizure features. SOUL was tested on two human electroencephalography (EEG) datasets: the CHB-MIT scalp EEG dataset, and a long (>100 hours) NeuroVista intracranial EEG dataset. It was able to achieve an average sensitivity of 97.5% and 97.9% for the two datasets respectively, at >95% specificity. Sensitivity improved by at most 8.2% on long-term data when compared to a typical seizure detection classifier. SOUL was fabricated in TSMC's 28 nm process occupying 0.1 mm2 and achieves 1.5 nJ/classification energy efficiency, which is at least 24x more efficient than state-of-the-art.

Andy Zhou, Rikky Muller, Jan Rabaey

Electromyogram (EMG) pattern recognition can be used to classify hand gestures and movements for human-machine interface and prosthetics applications, but it often faces reliability issues resulting from limb position change. One method to address this is dual-stage classification, in which the limb position is first determined using additional sensors to select between multiple position-specific gesture classifiers. While improving performance, this also increases model complexity and memory footprint, making a dual-stage classifier difficult to implement in a wearable device with limited resources. In this paper, we present sensor fusion of accelerometer and EMG signals using a hyperdimensional computing model to emulate dual-stage classification in a memory-efficient way. We demonstrate two methods of encoding accelerometer features to act as keys for retrieval of position-specific parameters from multiple models stored in superposition. Through validation on a dataset of 13 gestures in 8 limb positions, we obtain a classification accuracy of up to 93.34%, an improvement of 17.79% over using a model trained solely on EMG. We achieve this while only marginally increasing memory footprint over a single limb position model, requiring $8\times$ less memory than a traditional dual-stage classification architecture.