Search

To ensure the stability of the communication architecture in the power monitoring system, we propose an intelligent grid cyber-physical communication architecture modelling method based on the correlation characteristic matrix model. The article connects the physical entity layer, the information physical coupling layer, and the information system layer through an incidence matrix to form a complete power information physical system unit model. Through this system, we call the link and each node on the call link as the monitoring object, collect the relevant index data, and establish the business alarm mapping model of the communication network failure. The experimental results verify the reliability of the system and algorithm.

The advancement of Chinese education informatisation construction has injected new vitality into the development of Chinese educational technology in the new era and brought new challenges to the development of Chinese educational technology. Nonlinear dissipative structure theory has been a necessary enlightenment for the development of education informatisation. Based on the theory of nonlinear dissipative structure, the paper explores the relationship between the theory and education and teaching. It constructs a diversified regression calculation model of the information-based teaching ecology. Finally, it points out the strategies and ways to apply the dissipative structure theory to improve information-based teaching.

This article takes the nonlinear differential equation model as an example and uses information technology to create a new course teaching model. The computing software Maple is effectively applied to the precise solution of nonlinear differential equations through the analysis of examples. The overall goal and specific implementation of the teaching plan to integrate ordinary differential equations and information technology have been completed. The study found that the teaching plan proposed in the article is assisted by information technology, with teachers and students participating in an interactive and exploratory teaching method. This method is worthy of further promotion.

The dichotomy model of education informatisation is essential, which means the measurement of education informatisation construction and development. Finite element differential equations play an essential role in signal and information teaching. To improve teaching information, the paper applies the dichotomy model of finite element differential equations to the reform of physics education information teaching. This article fully introduces the basic principles of the dichotomy model in finite element differential equations and introduces several analysis methods of the inverse Laplace transform of differential equations. At last, the method is applied to the informatisation of physics education to improve the quality of teaching.

The digital and physical methods of establishing minimal curved surfaces are the basis for realizing the design of the minimal curved surface modeling structure. Based on this research background, the paper showed an artistic surface modeling method based on nonlinear over-limit difference equations. The article combines parameter optimization and 3D modeling methods to model the constructed surface modeling. The research found that the nonlinear out-of-limit difference equation proposed in the paper is more accurate than the standard fractional differential equation algorithm. For this reason, the method can be extended and applied to the design of artistic surface modeling.

Machine Learning (ML) has become a potent predictive analytics tool in several fields, including the study of social media data. Social media sites have developed into massive repositories of user-generated information, providing insightful data about user trends, interests, and behavior. This abstract emphasizes the use of machine learning methods for predictive analytics in social media data and examines the potential and problems unique to this field. Utilizing the capabilities of machine learning algorithms to identify significant trends and forecast user behavior from social media data is the goal of this study. The study makes use of a sizable dataset made up of user profiles, blog posts, comments, and engagement metrics gathered from well-known social networking sites. Predictive models are created using a variety of machine learning algorithms, such as ensemble methods, neural networks, decision trees, and support vector machines. As a result, this study emphasizes how important machine learning is for doing predictive analytics on social media data. The employment of diverse algorithms and preprocessing methods yields insightful information about user behavior and enables precise prediction of user behaviors. To improve the prediction powers of machine learning in this area, future research should concentrate on tackling the obstacles related to social media data, such as privacy concerns and data quality issues.

Contemporarily numerous analysts labored in the field of Vehicle detection which improves Intelligent Transport System (ITS) and reduces road accidents. The major obstacles in automatic detection of tiny vehicles are due to occlusion, environmental conditions, illumination, view angles and variation in size of objects. This research centers on tiny and partially occluded vehicle detection and identification in challenging scene specifically in crowed area. In this paper we present comprehensive methodology of tiny vehicle detection using Deep Neural Networks (DNN) namely CenterNet. Substantially DNN disregards objects that are small in size 5 pixels and more false positives likely to happen in crowded area. Primarily there are two categories of deep learning models single-step and two-step. A single forward pass model is the one in which detection is performed directly to possible location over dense sampling, wherein two-step models incorporated by Region proposals followed by object detection. We in this research scrutinize one-step State of the art (SOTA) model CenteNet as proposed recently with three different feature extractor ResNet-50, HourGlass-104 and ResNet-101 one by one. We train our model on challenging KITTI dataset which outperforms in comparison with SOTA single-step technique MSSD300* which depicts performance improvement by 20.2%mAPandSMOKEby with 13.2% mAP respectively. Effectiveness of CenterNet can be justified through the huge improved performance. The performance of our model is evaluated on KITTI (Karlsruhe Institute of Technology and Toyota Technological Institute) benchmark dataset with different backbones such as ResNet-50 gives 62.3% mAP ResNet-101 82.5% mAP, last but not the least HourGlass-104 outperforms with 98.2% mAP CenterNet-HourGlass-104 achieved high mAP among above mentioned feature extractors. We also compare our model with other SOTA techniques. [ABSTRACT FROM AUTHOR]