Skin cancer is a type of disease in which malignant cells are formed in skin tissues. However, skin cancer is a dangerous disease, and an early detection of this disease helps the therapists to cure this disease. In the present research, an automatic computer-aided method is presented for the early diagnosis of skin cancer. After image noise reduction based on median filter in the first stage, a new image segmentation based on the convolutional neural network optimized by satin bowerbird optimization (SBO) has been adopted and its efficiency has been indicated by the confusion matrix. Then, feature extraction is performed to extract the useful information from the segmented image. An optimized feature selection based on the SBO algorithm is also applied to prune excessive information. Finally, a support vector machine classifier is used to categorize the processed image into the following two groups: cancerous and healthy cases. Simulations have been performed of the American Cancer Society database, and the results have been compared with ten different methods from the literature to investigate the performance of the system in terms of accuracy, sensitivity, negative predictive value, specificity, and positive predictive value.

https://www.degruyter.com/document/doi/10.1515/med-2020-0131/pdf

Computer-aided diagnosis of skin cancer based on soft computing techniques

Optimal parameter identification of PEMFC stacks using Adaptive Sparrow Search Algorithm

https://www.econstor.eu/bitstream/10419/244066/1/1694151980.pdf

A new technique for optimal estimation of the circuit-based PEMFCs using developed Sunflower Optimization Algorithm

This study presents a new optimal method for home energy management system based on the internet of things. The method is a multi-objective optimization method that considers two main purposes including energy consumption cost and user satisfaction. The method is designed under the environment of the smart grid. Generally, the impact of the users in the system efficiency in terms of energy cost saving is significant. This reason makes residential users participate in household appliances management. The optimization algorithm is based on a new improved version of the butterfly algorithm for increasing the convergence speed. IoT system is based on ZigBee which is known as the lowest consumption among different wireless technologies. The household employs based on a sample user scenario with different appliances. Using Multi-objective optimization gives fragmented energy consumption. The results of Multi-objective optimization are also compared with PSO-based and BOA-based algorithms to show the proposed method's effectiveness. Simulation results are compared by the normal home energy management system to declare the system efficiency.

A multi-objective home energy management system based on internet of things and optimization algorithms

Model parameter estimation of the PEMFCs using improved Barnacles Mating Optimization algorithm

In this paper, a transformer-less grid-tied single-phase inverter is proposed which is directly connected to the topology. The voltage across the leakage capacitor has the base frequency, which decreases the leakage current under the defined value in the standards. This inverter’s active switches are high- and low-frequency types. High-frequency switches control the inductor’s current. In addition, the low-frequency switches are synchronous with the grid and operate in the base frequency. Since no power electrolytic decoupled capacitor is utilized between the high- and low-frequency switches, the system’s total efficiency and lifespan are improved. The proposed inverter has the capability of stepping up/down the output voltage, making it suitable for operating in a wide range of voltages and also providing large range of powers to the grid. This topology is directly connected to the grid, without any output filter, leading to elimination of the losses caused by the filter and increased efficiency. In the proposed inverter, a digital current controller is employed to control the injected current to the grid. Furthermore, P&O algorithm is adapted to extract the maximum power from the input source. For proving the proposed converter’s performance, a 770-W prototype has been implemented and comprehensive experimental results are presented.

A Single-Phase Transformer-Less Grid-Tied Inverter Based on Switched Capacitor for PV Application

This paper presents a 12-bit 120-MS/s successive approximation register (SAR) analog-to-digital converter (ADC) with improved split capacitive DAC and low-noise dynamic comparator. A split DAC structure with parasitic capacitance depressed technique is introduced, the top-plate parasitic capacitances of MSB and LSB DAC arrays are both reduced, and the accuracy of split DAC is increased without calibration. Further, an optimized sampling method is used to provide a unit capacitance between the MSB and LSB DAC arrays, the match of DAC is improved. In addition, a high-speed dynamic comparator with input-referred noise reduction technique is proposed, an extra positive feedback loop is provided to reduce the comparison delay and the gain of the comparator is also increased to depress noise. To demonstrate the proposed techniques, a design of SAR ADC is fabricated in 65-nm CMOS technology, consuming 6 mW from 1.2 V power supply with a SNDR > 66.1 dB and SFDR > 81.5 dB. The proposed ADC core occupies an active area of 0.05 mm2, and the corresponding FoM is 30 fJ/conversion-step with Nyquist frequency.

Tian-ye Liu

Papers

A Single-Phase Transformer-Less Grid-Tied Inverter Based on Switched Capacitor for PV Application

A 12-bit 120-MS/s SAR ADC with improved split capacitive DAC and low-noise dynamic comparator