In PV systems, DC-DC converters have been identified as one of the most critical and challenging sub-system in terms of failure rate. Thus, this paper proposes fault tolerant operation of a two-stage Buck/Buck-Boost converter under open-circuit switch failure. Remedial actions are efficient in any failure of one of the two switches of the converter. Here, a new unified approach is considered, for the overall fault tolerant operation of the two stages of the converter. The fault tolerant circuit we propose lies on performing redundancy by implementing the equivalent synchronous switch for the two main switches of the two stages, in offline mode. The fault tolerant circuit results from the basic two-stage Buck/Buck-Boost converter and its equivalent circuit with a synchronous switch, merged together to form the new DC-DC fault tolerant circuit. Therefore, post-fault operation at full power can also be performed. By using a switch fault management unit with reduced complexity, inserted between the control block and the switches, we have designed an unified, efficient and optimized fault tolerant control, suitable in both healthy and post-fault operations. Some selected simulation results and experimental tests, which all confirm the good performances of the proposed fault tolerant approach, are presented and discussed.

In this paper, we propose a hardware-efficient residual recurrent neural network for real-time video super-resolution (VSR) based on field programmable gate array (FPGA). Although recent learning-based VSR methods have achieved remarkable performance, the large computational complexity prohibits the deployment of the sophisticated VSR models on FPGA for real-time applications. Limited by the hardware resources, state-of-the-art FPGA-based VSR methods perform single-image super-resolution over the video sequence and suffer from temporal inconsistency. In order to exploit the inter-frame temporal correlation for real-time VSR on low-complexity hardware, we introduce a hardware-efficient recurrent neural network ERVSR. Specially, the proposed ERVSR leverages the input frame and the temporal information entailed in the hidden state to reconstruct the high-resolution counterpart. To reduce the network parameters, the low-resolution input branch and the hidden state branch are convolved individually and a channel modulation coefficient is proposed to explicitly guide the network to allocate the amount of output feature channels to each branch. Additionally, in order to reduce the memory consumption, we perform a dedicated lightweight compression of the hidden state by introducing a statistical normalization scheme followed by a fixed-point quantization. Besides, we adopt group convolution and depthwise separable convolution to further compact the network. We evaluated the proposed ERVSR on multiple public datasets from different aspects. Experimental results demonstrate that ERVSR performs better than the existing state-of-the-art FPGA-based VSR methods in both image quality and data throughput.

Increased life expectancy in most countries is a result of continuous improvements at all levels, starting from medicine and public health services, environmental and personal hygiene to the use of the most advanced technologies by healthcare providers. Despite these significant improvements, especially at the technological level in the last few decades, the overall access to healthcare services and medical facilities worldwide is not equally distributed. Indeed, the end beneficiary of these most advanced healthcare services and technologies on a daily basis are mostly residents of big cities, whereas the residents of rural areas, even in developed countries, have major difficulties accessing even basic medical services. This may lead to huge deficiencies in timely medical advice and assistance and may even cause death in some cases. Remote healthcare is considered a serious candidate for facilitating access to health services for all; thus, by using the most advanced technologies, providing at the same time high quality diagnosis and ease of implementation and use. ECG analysis and related cardiac diagnosis techniques are the basic healthcare methods providing rapid insights in potential health issues through simple visualization and interpretation by clinicians or by automatic detection of potential cardiac anomalies. In this paper, we propose a novel machine learning (ML) architecture for the ECG classification regarding five heart diseases based on temporal convolution networks (TCN). The proposed design, which implements a dilated causal one-dimensional convolution on the input heartbeat signals, seems to be outperforming all existing ML methods with an accuracy of $96.12\%$ and an F1 score of $84.13\%$, using a reduced number of parameters ($10.2$ K). Such results make the proposed TCN architecture a good candidate for low power consumption hardware platforms, and thus its potential use in low cost embedded devices for remote health monitoring.

Energy harvesting has become a promising and alternative solution to conventional energy generation patterns to overcome the problem of supplying autonomous electrical systems. More particularly, thermal energy harvesting technologies have drawn a major interest in both research and industry. Thermoelectric Generators (TEGs) can be used in two different operating conditions, under constant temperature gradient or constant heat flow. The commonly used TEG electrical model, based on a voltage source in series with an electrical resistance, shows its limitations especially under constant heat flow conditions. Here, the analytical electrical modeling, taking into consideration the internal and contact thermal resistances of a TEG under constant temperature gradient and constant heat flow conditions, is first given. To give further insight into the electrical behavior of a TEG module in different operating conditions, we propose a new and original way of emulating the above analytical expressions with usual electronics components (voltage source, resistors, diode), whose values are determined with the TEG’s parameters. Note that such a TEG emulation is particularly suited when designing the electronic circuitry commonly associated to the TEG, to realize both Maximum Power Point Tracking and output voltage regulation. First, the proposed equivalent electrical circuits are validated through simulation with a SPICE environment in static operating conditions using only one value of either temperature gradient or heat flow. Then, they are also analyzed in dynamic operating conditions where both temperature gradient and heat flow are considered as time-varying functions.