Constant current controlled flyback converter is widely used in low power applications for its simple structure and low cost. In order to further improve the output power and the efficiency, active-clamp flyback converter with soft-switching technique is always used. To avoid the nonlinearity and temperature drift of opto-coupler in the feedback circuit, a constant current digital control method is proposed for a primary-side regulation active-clamp (PSRAC) flyback converter in this article. Soft-switching technique is realized in discontinuous conduction modulation mode with a modified active-clamp technique. To compensate the nonlinearity of the secondary diode current with primary-side regulation, a new output current estimation algorithm is put forward based on the charge balance principle. The output current is predicted from primary current and the auxiliary winding voltage, and constant output current control is realized with primary peak current control method. The cost is low as only one low speed digital-to-analog converter, three comparators and a digital controller are required. The proposed control scheme was verified by a field-programmable gate array controlled 5.4-10.8 V/1.80 A PSRAC flyback converter. The output current accuracy is within in 1.2% in different input and output condition and the peak efficiency is improved by 3.6% after active-clamp technique is used.

Background: Traditional Chinese medicine (TCM) practitioners usually follow a 4-step evaluation process during patient diagnosis: observation, auscultation, olfaction, inquiry, pulse feeling, and palpation. The information gathered in this process, along with laboratory test results and other measurements such as vital signs, is recorded in the patient’s electronic health record (EHR). In fact, all the information needed to make a treatment plan is contained in the EHR; however, only a seasoned TCM physician could use this information well to make a good treatment plan as the reasoning process is very complicated, and it takes years of practice for a medical graduate to master the reasoning skill. In this digital medicine era, with a deluge of medical data, ever-increasing computing power, and more advanced artificial neural network models, it is not only desirable but also readily possible for a computerized system to mimic the decision-making process of a TCM physician. Objective: This study aims to develop an assistive tool that can predict prescriptions for inpatients in a hospital based on patients’ clinical EHRs. Methods: Clinical health records containing medical histories, as well as current symptoms and diagnosis information, were used to train a transformer-based neural network model using the corresponding physician’s prescriptions as the target. This was accomplished by extracting relevant information, such as the patient’s current illness, medicines taken, nursing care given, vital signs, examinations, and laboratory results from the patient’s EHRs. The obtained information was then sorted chronologically to produce a sequence of data for the patient. These time sequence data were then used as input to a modified transformer network, which was chosen as a prescription prediction model. The output of the model was the prescription for the patient. The ultimate goal is for this tool to generate a prescription that matches what an expert TCM physician would prescribe. To alleviate the issue of overfitting, a generative adversarial network was used to augment the training sample data set by generating noise-added samples from the original training samples. Results: In total, 21,295 copies of inpatient electronic medical records from Guang’anmen Hospital were used in this study. These records were generated between January 2017 and December 2018, covering 6352 types of medicines. These medicines were sorted into 819 types of first-category medicines based on their class relationships. As shown by the test results, the performance of a fully trained transformer model can have an average precision rate of 80.58% and an average recall rate of 68.49%. Conclusions: As shown by the preliminary test results, the transformer-based TCM prescription recommendation model outperformed the existing conventional methods. The extra training samples generated by the generative adversarial network help to overcome the overfitting issue, leading to further improved recall and precision rates.

Micro-Electro-Mechanical System (MEMS) devices have numerous advantages including small sizes, high performance and easy integration capability, and thus have been widely used in the Internet of Things. A typical MEMS device usually includes a set of performance parameters and each parameter is sensitive to the device geometries but with different regularities and weights, thus resulting in the complexity of MEMS device design. The conventional design method is mainly based on iterative finite element simulation and optimization, which is time-consuming and inefficient. To address the above issues, a bidirectional artificial neural network (ANN) based method is explored and used as the design method by using a MEMS pressure sensor as a design example. First, a forward ANN with the geometries and performance as the input and output respectively is trained and constructed, which can accurately predict the performance. Then, an inverse ANN with the performance and geometries as the input and output respectively is also investigated. By means of tandem network, the non-uniqueness issue of the inverse ANN caused by one-to-many response from the input to the output can be well addressed. This tandem network can output the corresponding geometries instantly according to the target performance. This work demonstrates the great potential of ANN as a new and facile strategy in MEMS device design.

To achieve the desired characteristics for MEMS sensors, traditional design process obtains the geometrical parameters based on complex theoretical calculations and interactive finite element (FE) simulations, which are time-consuming and data-consuming. To solve the above problems, a data-driven bidirectional design approach based on deep learning (DL) method is introduced to improve the design efficiency of MEMS sensors in this work. By using the piezoresistive acceleration sensor as a design example, the forward artificial neural network (ANN) with the sensor geometrical parameters as the input and the sensor performance as the output is trained and realized by using 1000 groups of data collected through FE simulation. This forward ANN can accurately predict the sensor performance including the measurement range, sensitivity, and resonant frequency. In addition, the inverse ANN with the sensor performance as the input and the sensor geometrical parameters as the output is also achieved by using a tandem network. This inverse ANN can provide the geometrical parameters directly and instantly according to the target performance. Both the forward and inverse networks cost only about 6 ms for each task and the mean relative errors are less than 3%. The high efficiency and low relative error indicate that DL is a promising approach to improve the design efficiency for MEMS sensors.

Primary-side regulation (PSR) flyback topology with discontinuous conduction modulation (DCM) mode has been widely used in low-power application due to its high stability, wide input voltage range, low cost, and low standby power. To improve the output power, continuous conduction modulation (CCM) mode is always introduced. However, in CCM mode, conventional PSR voltage-sampling method cannot realize high precision of output voltage or the voltage sampling method requires complex control of high cost. In this paper, a simple digital voltage sampling scheme with two reference voltages outputted from a digital-to-analog converter (DAC) is put forward to trace the “accurate-point” voltage for DCM and CCM modes. In CCM mode, the sampling voltage error of the “knee-point” voltage can be compensated just by inserting DCM switching cycle to obtain the “accurate-point” voltage. Voltage difference between DCM mode and CCM mode will be eliminated, and high precision is easily realized. The proposed method is verified in a 20V, 65W PSR flyback converter. The sampling method only requires a low speed DAC, three comparators and a digital controller. The output voltage precision is within 0.6% with universal input voltage.

The human gait features are regarded as key indicators for disease prevention, fall warning, rehabilitation training, and gait correction applications. How to achieve convenient, efficient and accurate gait recognition has become a research hotspot. In this work, a novel human gait recognition method is proposed, which effectively combines the merits of the grid-less planar flexible pressure sensors and the multi-layer heterogeneous machine-learning algorithms. The proposed system has the advantages of multi-functionality, high accuracy, low cost, easy portability, easy scalability, real-time monitoring, and self-learning improvement. In general, pressure sensors can give the information of pressure and location only, yet gait feature extraction involves a complex combination of multi-zone and time-dependent dynamic process. Therefore, the concept of “plantar patterns” are introduced to bridge the gap between pressure sensing and gait recognition. With the help of neural network algorithm, 12 typical plantar patterns were innovatively extracted from the foot pressure information, and any arbitrary gait could be divided into combination of one or several typical patterns. Applications including foot shape classification, motion status judgment, and human gait detection were testified experimentally, with an overall prediction accuracy of 97%. This gait recognition method can accurately characterize the dynamic gait features of the human body, providing visualized, accurate, and quantifiable technical support for the early intervention of movement disorders and rehabilitation treatments such.