An Ultralow-Power Sleep Spindle Detection System on Chip

Iot-based power detection equipment management and control system

The development and application scope of the Internet of Things is also becoming more and more extensive. Especially in the application of power testing improved systems, great progress has been made. This article aims to study how to analyze the system detection equipment based on the Internet of Things. This article describes the basic theoretical knowledge of the Internet of Things and power detection improved systems. A clustering analysis algorithm and a support vector machine algorithm based on the Internet of Things are proposed. In the experiment of this article, the scoring items of the expert’s traditional detection system include complex technology, inconvenient use, and incomplete intelligence. Among them, the highest score for complex technology is 8.6 points, the lowest score is 7 points; the highest score for inconvenience is 8.6 points, and the lowest is 8.3 points. It can be seen that related experts believe that the traditional power detection improved system is not only very complicated in technology, very inconvenient to use but also incompletely intelligent. Therefore, it is very necessary to study the system detection equipment based on the Internet of Things.

When the Whole Is Less Than the Sum of Its Parts: Maximum Object Category Information and Behavioral Prediction in Multiscale Activation Patterns

Neural codes are reflected in complex neural activation patterns. Conventional electroencephalography (EEG) decoding analyses summarize activations by averaging/down-sampling signals within the analysis window. This diminishes informative fine-grained patterns. While previous studies have proposed distinct statistical features capable of capturing variability-dependent neural codes, it has been suggested that the brain could use a combination of encoding protocols not reflected in any one mathematical feature alone. To check, we combined 30 features using state-of-the-art supervised and unsupervised feature selection procedures (n = 17). Across three datasets, we compared decoding of visual object category between these 17 sets of combined features, and between combined and individual features. Object category could be robustly decoded using the combined features from all of the 17 algorithms. However, the combination of features, which were equalized in dimension to the individual features, were outperformed across most of the time points by the multiscale feature of Wavelet coefficients. Moreover, the Wavelet coefficients also explained the behavioral performance more accurately than the combined features. These results suggest that a single but multiscale encoding protocol may capture the EEG neural codes better than any combination of protocols. Our findings put new constraints on the models of neural information encoding in EEG.

Quantitative electroencephalogram analysis of frontal cortex functional changes in patients with migraine

The functional abnormality of brain areas accounting for the migraine remains to be elucidated. Most related studies have used functional magnetic resonance imaging to investigate brain areas involved in migraine. However, the results are heterogeneous. In this study, we used a convenient tool to explore the brain regions involved in migraine. In this study, 40 children with migraine and 40 sex- and age-matched health controls were enrolled, and electroencephalogram was used to explore the functional abnormal areas of migraine through electroencephalogram bands and low-resolution electromagnetic tomography analysis. The results revealed that spectrum edge frequency 50 in all electroencephalogram channels in patients with migraine were lower than those in controls. Significant differences were discovered over frontal areas. In addition, significantly higher current density over the frontopolar prefrontal cortex and orbitofrontal cortex and higher connectivity over the left prefrontal cortex were observed in patients with migraine. We suggest that functional disturbance of the prefrontal cortex may play a potential role in children with migraine, and that low-resolution electromagnetic tomography is a reliable and convenient tool for studying the functional disturbance of migraine.

A 41.2 nJ/class, 32-Channel On-Chip Classifier for Epileptic Seizure Detection

A 41.2 nJ/class, 32-channel, patient-specific onchip classification architecture for epileptic seizure detection is presented. The proposed system-on-chip (SoC) breaks the strict energy-area-delay trade-off by employing area and memoryefficient techniques. An ensemble of eight gradient-boosted decision trees, each with a fully programmable Feature Extraction Engine (FEE) and FIR filters are continuously processing the input channels. In a closed-loop architecture, the FEE reuses a single filter structure to execute the top-down flow of the decision tree. FIR filter coefficients are multiplexed from a shared memory. The 540 × 1850 μm² prototype with a 1kB register-type memory is fabricated in a TSMC 65nm CMOS process. The proposed on-chip classifier is verified on 2253 hours of intracranial EEG (iEEG) data from 20 patients including 361 seizures, and achieves specificity of 88.1% and sensitivity of 83.7%. Compared to the state-of-the-art, the proposed classifier achieves 27 × improvement in Energy-AreaLatency product.