Skin cancer is one of the most deadly cancer types with considerable number of patients. Image analysis has largely improved the automated diagnosis accuracy for malignant melanoma and other pigmented skin lesions, compared to unaided visual examination. Recent popular solution for automated skin lesion classification is using deep neural networks, trained from large amounts of professional annotated data, but that largely limits the model's scalability. This paper exploits transfer learning for skin lesion classification task with the help of labeled data from another domain (source), and proposes a multi-view filtered transfer learning network to strongly represent discriminative information from different image views with reasonable weighing strategy. This method also evaluates the importance for each source images, which can learn useful knowledge with neglecting negative samples from source domain. The extensive skin lesion classification experiments demonstrate our method can effectively solve Melanoma and Seborrheic Keratosis classification tasks with outstanding extensibility, and the discussion of the major components also testifies the improvements of our proposed multi-view filtered transfer learning approach.

Electrochemical discharge machining (ECDM) is an emerging special processing technology for non-conductive hard and brittle materials, but it may encounter the problem of tool wear due to its process characteristics, which affects the processing accuracy. In this study, in the non-machining state, the tungsten carbide spiral cathode with a diameter of 400 μm was selected to analyze the influencing mechanism of the process parameters on tool wear, and a suitable voltage range for the processing was obtained. The influence of the cathode’s loss behavior on the film formation time and the average current of spark discharge was discussed based on the current signal. The results show that the tool wear mainly appears from the bottom to the end and edge tip of the protrusion. Loss is mainly in the form of local material melting or gasification at high temperature. In addition, the loss may shorten the film formation time, but the effect on the average current of spark discharge is small.

Different cathode materials have different surface chemical components and machining capacities, which may finally result in different machining quality and machining efficiency of workpieces. In this paper, in order to investigate the influence of cathode materials on the electrochemical machining of thin-walled workpiece made of 304 stainless steel, five cylindrical electrodes are used as the target working cathodes of electrochemical machining to conduct experiments and research, including 45# steel, 304 stainless steel, aluminum alloy 6061, brass H62, and tungsten steel YK15. The stray current corrosion, taper, and material removal rate were used as the criteria to evaluate the drilling quality of efficiency of a thin-walled workpiece made of 304 stainless steel. The research results show that from the perspectives of stray current corrosion and taper, aluminum alloy 6061 is an optimal tool cathode, which should be used in the electrochemical machining of thin-walled workpieces made of 304 stainless steel; on the aspect of material removal rate, the 45# steel, 304 stainless steel, and aluminum alloy 6061 present close material removal rates, all of which are higher than that of brass H62 and tungsten steel YK15. Based on comprehensive consideration of both machining quality and machining efficiency, the aluminum alloy 6061 is the best option as the cathode tool in the electrochemical machining of thin-walled workpieces made of 304 stainless steel.

In this study, we comprehensively investigate the structure and operational principles of the Rotary Direct Drive Electro-Hydraulic Pressure Servo Valve (RDDPV). Our objective is to establish the dynamics equations governing the motor, slide valve, and bias mechanism of the valve. Additionally, we construct a mathematical model for the servo valve controller, while ensuring the linearization of the controller model. Furthermore, we conduct an in-depth analysis of the static characteristics of the valve, including linearity, dead zone, hysteresis loop, and zero drift. Regarding the dynamic characteristics, we establish a dynamic mathematical model for the RDDPV valve. Subsequently, we subject the servo valve to analysis with a focus on frequency response and dynamic response, using the control current as the input and the pressure as the output. To perform these analyses, we employ the software package SIMULINK of MATLAB, facilitating dynamic simulations. Remarkably, the simulation results exhibit the valve's conformity to design requirements, underscoring its suitability for subsequent research and development endeavors. Through our rigorous investigation, we offer essential technical support for the forthcoming stages of the valve's research and development, thereby laying a robust foundation for its further advancement.

This study investigates the potential of inorganic perovskite CsPbBr₃ as a photovoltaic material, highlighting its superior stability compared to that of organic–inorganic hybrid perovskite materials. Conventional methods for preparing CsPbBr₃ perovskite films, such as the two-step method and the dual-source thermal evaporation method, face challenges in obtaining high-purity films due to the decomposition of precursor films and the formation of multiple heterogeneous phases. To address this issue, we synthesized CsPbBr₃ powder material using thermal evaporation deposition, which effectively suppressed decomposition and the formation of heterogeneous phases. Consequently, we achieved uniform and dense CsPbBr₃ perovskite films. By incorporating energy-band engineering modification with CsPbBr₃ quantum dots (QDs), the all-inorganic perovskite solar cells (PSCs) attained a power conversion efficiency (PCE) of 7.01% under standard solar illumination conditions. The device PCE remained at 93% of its initial efficiency under 30% relative humidity conditions for over 100 days, showcasing its durability. The developed method produced an average grain size of 800 nm, resulting in a smooth and uniform film surface, thereby demonstrating the method’s high repeatability. Additionally, the optimized PSCs exhibited a high open-circuit voltage (V_OC) with the champion device reaching a V_OC of 1.38 V and a PCE of 7.01%. This research presents a robust, efficient, and cost-effective approach for fabricating high-quality all-inorganic PSCs.