International Journal of Youth Science and Technology Innovation https://ijysti.org/index.php/main <p>The International Journal of Youth Science and Technology Innovation is an open-access journal for the display and publication of outstanding achievements of youth science and technology innovation. All articles published in the journal are reviewed by well-known scholars from various fields to ensure that these articles are innovative and enlightening. Its focus is to get articles reflecting the scientific and technological innovation achievements of outstanding young people worldwide published. The main purpose is to promote and accelerate the exploration of scientific and technological innovation achievements and ideas from outstanding young people worldwide, and thereby provide a platform for this.<br />IJYSTI covers a wide range of topics related to scientific and technological innovation of young people worldwide, including the application and innovation of artificial intelligence technology, big data technology, mathematics, physics, chemistry, biology, statistics, sociology, philosophy and art, etc. IJYSTI has no restrictions on the topic selection of articles. All original articles with the efforts of young people themselves are welcome.<br />IJYSTI is published and managed by American Youth Association of Scientific and Technological Innovation.</p> <p>American Youth Science and Technology Innovation Association (AYSTI) was founded in Denver in 2018. The association is committed to promoting youth science and innovation education philosophy about equality and sustainability as well as educational resources to every corner of the world, especially underdeveloped countries and regions with relatively backward education. Scientific and technological innovation is the most important driving force for human progress, and we hope that through our efforts, as many teenagers around the world as possible could come to their scientific and technological innovation consciousness. So they could learn to apply their scientific knowledge to daily life and career development, and popularize scientific and technological innovation concept to the whole world with consciousness of scientific and technological innovation in mind.</p> en-US Charlie.w@aysti.us (Charlie) contact@aysti.us (William) Fri, 20 Dec 2024 18:22:06 -0600 OJS 3.3.0.6 http://blogs.law.harvard.edu/tech/rss 60 A Study on Regional Power Load Forecasting Using an ARIMA-CNN-LSTM Residual Correction Model https://ijysti.org/index.php/main/article/view/9 <p>This paper presents a hybrid ARIMA-CNN-LSTM model for accurate regional power load forecasting. The model leverages the ARIMA model’s ability to capture linear trends and the CNN-LSTM network’s strength in modeling nonlinear dependencies and temporal patterns. Experimental results demonstrate that the hybrid model outperforms the standalone ARIMA model, achieving significant improvements in forecasting accuracy. With an RMSE of 3504.08, an MAE of 1466.66, and an R-squared value of 0.9902, the hybrid model proves to be an effective tool for energy management and grid planning. Its balance between accuracy and computational efficiency makes it suitable for real-time forecasting applications.</p> Chaozheng Wang Copyright (c) 2024 Chaozheng Wang https://creativecommons.org/licenses/by-nc-sa/4.0 https://ijysti.org/index.php/main/article/view/9 Mon, 02 Sep 2024 00:00:00 -0500 Multi-functional image Stylization and portrait dispose based on traditional image dispose and deep learning https://ijysti.org/index.php/main/article/view/10 <p>This paper studies the multi-function image based on traditional image processing and deep learning stylized processing method with the portrait, aims to develop the most efficient and convenient image processing system. The content of the research includes two core modules: image stylization and portrait dispose, which combines traditional image dispose techniques with deep learning method. Image stylization module adopts VGG19 network to realize image style transfer, and combines OpenCV technology to realize image cartoonization dispose. Portrait processing module through deep learning algorithms for detecting like cutting and exposed skin. System USES Qt GUI interface technology integration, and through the multithreaded processing efficiency. Results show that a system in the processing efficiency and quality of output achieves the expected effect, provides users with efficient and diversified image processing solutions.</p> Ye Han Copyright (c) 2024 Ye Han https://creativecommons.org/licenses/by-nc-sa/4.0 https://ijysti.org/index.php/main/article/view/10 Fri, 20 Dec 2024 00:00:00 -0600