Search

In view of the chaotic relationship between user-transformer in the current low-voltage stations, manual identification consumes a long time period, low identification accuracy, and high input system costs. This paper proposes a method for identifying household change relations in low-voltage stations based on dual-scale similarity and spectral clustering algorithm. First, according to the different similarities of user voltage curves in different stations, consider Euclidean distance and cosine distance to establish a two-scale spectral clustering similarity matrix from the distance and shape of the voltage curve. Then based on the two-scale similarity matrix, perform spectral clustering on the voltage curves of the same station area to complete the clustering of users in the same station area. Examples show that the method proposed in the article has high recognition accuracy, low input cost, and has good application effects.

As a common lung disease, pneumonia affects millions of people worldwide each year and is often detected during physical examination using chest X-ray images (CXRs), which are usually diagnosed by radiologists. This time-consuming task often leads to fatigue-based diagnostic error and cannot be performed in countries or areas lack of radiologists. In this work, we proposed a multi-task learning model: Mt-pnet. We learn from the experience of imaging doctors in the diagnosis of pneumonia, let the network pay attention to the patient’s gender and age information in the diagnosis of pneumonia. The combined information is helpful for the network to learn robust image features for pneumonia diagnosis. At the same time, we also found that using multi-task model is helpful to improve the recall of patients with pneumonia, which has important clinical significance.

Highly crystalline and transparent CdS films are grown by utilizing the vacuum thermal evaporation (VTE) method. The structural, surface morphological, and optical properties of the films are studied and compared with those prepared by chemical bath deposition (CBD). It is found that the films deposited at a high substrate temperature (200 °C) have a preferential orientation along (002) which is consistent with CBD-grown films. Absorption spectra reveal that the films are highly transparent and the optical band gap values are found to be in a range of 2.44 eV–2.56 eV. CuIn1−xGaxSe2 (CIGS) solar cells with in-situ VTE-grown CdS films exhibit higher values of Voc together with smaller values of Jsc than those from CBD. Eventually the conversion efficiency and fill factor become slightly better than those from the CBD method. Our work suggests that the in-situ thermal evaporation method can be a competitive alternative to the CBD method, particularly in the physical- and vacuum-based CIGS technology.