Portable automatic seizure detection system is very convenient for epilepsy patients to carry. In order to make the system on-chip trainable with high efficiency and attain high detection accuracy, this paper presents a very large scale integration (VLSI) design based on the nonlinear support vector machine (SVM). The proposed design mainly consists of a feature extraction (FE) module and an SVM module. The FE module performs the three-level Daubechies discrete wavelet transform to fit the physiological bands of the electroencephalogram (EEG) signal and extracts the time–frequency domain features reflecting the nonstationary signal properties. The SVM module integrates the modified sequential minimal optimization algorithm with the table-driven-based Gaussian kernel to enable efficient on-chip learning. The presented design is verified on an Altera Cyclone II field-programmable gate array and tested using the two publicly available EEG datasets. Experiment results show that the designed VLSI system improves the detection accuracy and training efficiency.

An automatic detection system for distinguishing healthy, ictal, and inter‐ictal EEG signals plays an important role in medical practice. This paper presents a very large scale integration (VLSI) architecture of three‐class classification for epilepsy and seizure detection. In order to find out the most efficient three‐class classification scheme for hardware implementation, several multiclass non‐linear support vector machine (NLSVM) classifiers are compared and validated using software implementation. Finally, the one‐against‐one (OAO) multiclass NLSVM is selected due to its highest accuracy. The designed system consists of a discrete wavelet transform (DWT)‐based feature extraction module, a modified sequential minimal optimization (MSMO) training module, and an OAO multiclass classification module. A lifting structure of Daubechies order 4 wavelet is introduced in three‐level DWT to save circuit area and speed up the computational time. The MSMO is used for on‐chip training. The circuit of the largest absolute value decision is designed to avoid the unclassifiable problem in the OAO multiclass classification. The designed system is implemented on a field‐programmable gate array (FPGA) platform and evaluated using the publicly available epilepsy dataset. The experimental results demonstrate that the designed system achieves high accuracy with low‐dimensional feature vectors.

A compact analytical drain current model considering the inversion layer and source depletion is developed for the gate-all-around (GAA) heterojunction tunneling FET (H-TFET) with staggered-gap alignment. Poisson's equations are solved to obtain the continuous surface potential profile for the GAA H-TFET first, then the drain current is derived based on Kane's model by using the tangent line approximation method, and finally, the model is verified by TCAD simulation using GaAs0.5Sb0.5/In0.53Ga0.47As GAA H-TFET and published data. The impacts of bias, gate oxide dielectric constant, and interface fixed charge on the surface potential, electric field, and IDS-VGS can be well predicted by the proposed model. The super-linear onset and saturation characteristics of IDS-VDS curves are also obtained.

An automatic detection system for distinguishing normal, ictal, and interictal electroencephalogram (EEG) signals is of great help in clinical practice. This paper presents a three-class classification system based on discrete wavelet transform (DWT) and the nonlinear sparse extreme learning machine (SELM) for epilepsy and epileptic seizure detection. Three-level lifting DWT using Daubechies order 4 wavelet is introduced to decompose EEG signals into delta, theta, alpha, and beta subbands. Considering classification accuracy and computational complexity, the maximum and standard deviation values of each subband are computed to create an eight-dimensional feature vector. After comparing five multiclass SELM strategies, the one-against-one strategy with the highest accuracy is chosen for the three-class classification system. The performance of the designed three-class classification system is tested with publicly available epilepsy dataset. The results show that the system achieves high enough classification accuracy by combining the SELM and DWT and reduces training and testing time by decreasing computational complexity and feature dimension. With excellent classification performance and low computation complexity, this three-class classification system can be utilized for practical epileptic EEG detection, and it offers great potentials for portable automatic epilepsy and seizure detection system in the future hardware implementation.

This study presents a survey on the existing fault diagnosis methods (FDMs) of the switch devices for the rapidly developing modular multilevel converters (MMCs). Three categories, namely mechanism‐based, signal processing‐based and artificial intelligence‐based FDMs, are evaluated and summarised depending on the operating principles. Mechanism‐based FDMs detect the faults by comparing the inner characteristics of MMC or their derived parameters with the expected values. Signal processing‐based FDMs detect the faults via comparing the processed output voltage or current with their expected values. Artificial intelligence‐based FDMs detect the faults in the way of employing a trained intelligent classifier. Methods belonging to each category are introduced in detail via comparing a lot of criteria of the FDMs. Then, a figure‐of‐merit is defined to evaluate various FDMs. Finally, the summary is given and the developing tendency is recommended for future work.

A self‐powered convertor for thermoelectric energy harvesting in body sensor nodes (BSNs) is designed to boost extremely low voltage to the typical supply voltage of BSNs. An adaptive maximum power point tracking (MPPT) based on digitally controlled oscillator (DCO) is achieved by adjusting the switching frequency according to the relation between the half open‐circuit voltage of thermoelectric generator and the equivalent voltage. DCO exhibits small line sensitivity and temperature coefficient (TC). Radio frequency (RF) kick‐start based on a self‐synchronous rectifier is introduced to achieve the no‐battery effect. A modified zero current switching based on the common‐gate comparator is utilised to decrease the power dissipation of power metal–oxide–semiconductor field‐effect transistors. In addition, the power dissipation of the main blocks is reduced by discontinuing the clocked and common‐gate comparators after comparison in each cycle, and by making most transistors of DCO and the complementary metal‐oxide‐semiconductor (CMOS) voltage reference work in the weak inversion or linear region. The zero TC principle of the CMOS voltage reference is extended to all process. The novel convertor is designed and verified in Central Semiconductor Manufacturing Corporation CMOS 0.18 µm process. The results reveal that it achieves adaptive MPPT without battery and exhibits a peak end‐to‐end efficiency of about 63%.