Most cluster identification studies regarding consumer electricity load is faced with problems of erroneous clustering method similarity, low clustering quality and poor identification accuracy. To solve these problems, this paper utilizes the elbow method, k-Means++, entropy weight method and a graph convolutional neural network to provide a means for cluster identification based on electrical appliance power data collected via smart sockets. In this article, elbow and entropy weight methods were used to achieve the adaptive clustering algorithm. To obtain the electrical appliance load curves, Euclidean and dynamic time warping (DTW) distances were integrated and the similarity measurement method was used to improve the k-means++ algorithm, which was then applied to data collected via smart socket clustering. Next, clustering results were input into the graph convolutional neural network (GCN) for identification purposes and appliance type information was obtained. Finally, experiments were conducted using electrical load data from 20 commercial users. The method used was a combination of the k-means algorithm and long short-term memory network (LSTM). The results show that under optimal K value conditions (as determined by the elbow score), the methods used in this paper have improved clustering quality and recognition accuracy, when compared to LSTM.
Background. Wristband identification (wristband for short) is an accurate and reliable tool for patients, and it is the basic requirement of the whole medical activity of the hospital. Wearing wristband correctly can help clinical medical staff to identify patients quickly and accurately and effectively prevent medical errors and medical accidents. According to the survey, the wristband wearing rate of clinical patients is still low, mainly because the wristband is tight and improper and the medical staff education is not in place. Therefore, how to scientifically and effectively improve the wearing rate and accuracy of patients’ wristbands is an urgent nursing safety problem to be solved. Accurate identification of children is the key to ensure the safety of clinical drug use and carry out diagnosis and treatment, and wearing wristbands is the main way to identify children. Objective. A case-control study was conducted to explore the suitability and treatment compliance of an enhanced wristband wearing method compared with the traditional method. Methods. 260 hospitalized children admitted to our hospital from March 2019 to June 2021 were randomly divided into control group and study group. The control group used a traditional wristband, while the study group used a modified wristband. The existence of wristbands, the recognition speed of medical staff, the clarity of wristband handwriting, and the incidence of skin depression were observed in the two groups. The local skin reaction, wearing rate, incidence of wristband-related adverse events, identity compliance, and family satisfaction of patients with wristband were compared. Results. In terms of authentication compliance, the normal authentication frequency of the observation group was higher than that of the control group, but the difference was not statistically significant ( P > 0.05 ). The score of local skin reaction in the test group was lower than that in the control group, and the skin condition in the test group was better than that in the control group ( P < 0.05 ). The incidence of adverse events in the observation group was significantly lower than that in the control group ( P < 0.05 ). The proportion of wristband position, immediate recognition, and clear handwriting in the observation group was significantly higher than that in the control group in terms of wristband position, recognition speed, clear handwriting, and sunken skin ( P < 0.05 ). There was no significant difference in the incidence of skin depression ( P > 0.05 ). Parents’ ratings of satisfaction with treatment and child wearing rates were compared. After the intervention, the parents’ satisfaction with diagnosis and treatment in the observation group was 89.23%, which was significantly higher than that in the control group (79.23%) ( P < 0.05 ). The score of wearing rate in the observation group was significantly higher than that in the control group ( P < 0.05 ). Conclusion. On the basis of ensuring children’s compliance, the improved wristband wearing method can reduce the incidence of wristband shedding and ligature marks, reduce the diagnosis and treatment error rate, enhance the suitability of wearing, enhance the work efficiency of doctors and treaters, and improve the satisfaction of diagnosis and treatment.
The traces of bullets' rifling are not easy to destroy, difficult to disguise, and unique. It is of great significance for the batch filing of standard guns. Aiming at the problems of traditional binocular microscope comparison, segmented photo stitching, and other methods, namely, timeconsuming, low efficiency, and inability to carry out quantitative analysis, a batch filing system of bullets' rifling traces based on point laser detection was studied. Firstly, the translation, swing, and rotation of the test piece are controlled by the movement of five-stage stepper motors until the cylindrical centerline of the tested bullet coincides with the rotation centerline of the electric rotating table. Secondly, laser displacement sensing technology is used to detect rifling marks on the bullet surface in a 360-degree circle along the circumference direction, the superposition of multiple detection data is used to remove the influence item, and the generalized morphological filtering is used for the noise reduction of detection data. After that, the Pearson correlation coefficient is used to compare and calculate the similarity of traces, and finally achieve the rapid matching of bullet traces. With this system, a total of 321 bullets fired by 69 different guns were matched with rifling traces, and an excellent matching rate of more than 80% and a relatively high matching speed were obtained. The actual bullet matching experiments show that this system can be effectively applied to the batch filing of guns.
Traditional gun archiving methods are mostly carried out through bullets’ physics or photography, which are inefficient and difficult to trace, and cannot meet the needs of large-scale archiving. Aiming at such problems, a rapid archival technology of bullets based on graph convolutional neural network has been studied and developed. First, the spot laser is used to take the circle points of the bullet rifling traces. The obtained data is filtered and noise-reduced to make the corresponding line graph, and then the dynamic time warping (DTW) algorithm convolutional neural network model is used to perform the processing on the processed data. Not only is similarity matched, the rapid matching of the rifling of the bullet is also accomplished. Comparison of experimental results shows that this technology has the advantages of rapid archiving and high accuracy. Furthermore, it can be carried out in large numbers at the same time, and is more suitable for practical promotion and application.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.