Personalized Recommendation System Based on Collaborative Filtering for IoT Scenarios

Summary Historic landscape islands are a unique landscape phenomenon in the urbanization and modernization process in Shanghai. Shanghai has been fragmented and isolated at the landscape space level because of islanding, and its historic and cultural values have been broken and weakened. Therefore, it is urgent to implement fusion protection planning. Considering the islanding of urban historic landscape, cellular automata (CA) and neural network intelligent method were used to establish the intelligent CA model of Shanghai historic landscape islands and carry out computer simulation, expecting to provide a basis for studying urban historic landscapes in China via the intelligent evaluation of urban historic landscape islands and the establishment of an intelligent planning model. A technical path to alleviate landscape fragmentation and cultural value fracture of isolated islands was explored, so as to provide the latest theoretical basis for decision makers to manage historic landscape islands in Shanghai and offer reference for more scientific, intelligent, and efficient decision‐making.

Section: Resultsmentioning

confidence: 99%

Construction of an intelligent cellular automata model for historic landscape islands in Shanghai and fusion simulation

Wei

Zhang

2020

“…In the absence of local information and models, complex problems can still be solved. At present, intelligent algorithms have been successfully applied in various fields, such as medical, 25 Blockchain technology, 26,27 software defect prediction, 28 image processing, 29 recommendation systems, 30,31 and wireless sensor. [32][33][34][35] Researchers have proposed a series of swarm intelligence optimization algorithms, 36,37 such as genetic algorithm, 38 particle swarm algorithm, 39 cuckoo algorithm.…”

Section: Introductionmentioning

confidence: 99%

A many‐objective integrated evolutionary algorithm for feature selection in anomaly detection

Zhang

Xie

2020

At present, irrelevant or redundant features in network traffic data occupy a lot of storage and computing resources, reducing the accuracy of network anomaly detection. Aiming at this problem, a many-objective feature selection model is proposed in this article. The model takes the number of selected feature, false alarm rate, detection rate, precision and accuracy as the optimization objectives, and characterizes the performance of the feature selection method from different perspectives. At the same time, a many-objective integration optimization algorithm (IN-MaOEA) is designed to solve this model. First, the algorithm will build the evolution strategy pool and the dominance strategy pool, then a random probability strategy selection mechanism is designed to improve the algorithm's convergence and diversity. At the same time, an anomaly detection simulation was performed using the NSL-KDD dataset. Experimental results show that the IN-MaOEA algorithm can effectively improve the performance of detection.

“…With the further propagation of the news, netizens' attitudes toward the events have gradually deepened, two or more opposite remarks on the Internet have appeared, that is to say, bipolarization or multidimensional polarization phenomenon has formed. The emergence of the polarization of network groups will often result in a series of network malicious attack and network violence events, causing great harm to the subject of the event and the network environment. In addition, network incidents may be further extended to the real world, which will easily lead to a series of demonstrations affecting social stability.…”

Section: Introductionmentioning

confidence: 99%

Modeling and simulation analysis of public opinion polarization in a dynamic network environment

Yuan

Shi

Che

et al. 2020

Summary At present, there are many group incidents on the Internet, which has caused a high level of public opinion. Hot issues on the Internet can often trigger intense discussions among netizens and finally evolve toward bipolarization or multipolarization. This article focuses on the phenomenon of public opinion polarization under the dynamic network. First, the single‐dimensional evaluation system for the JA model was expanded to multidimensional and analyzes the main factors that cause the polarization of public opinion of network groups from multiple dimensions of hot events. Second, the strength of the relationship between individuals and its dynamic changes were taken into account in the model. The strength of the relationship between individuals and its changes will affect the interaction of opinions, and thus affect the degree and speed of group polarization. Third, combining the changing process of the strength of relationship, the dynamic connection mechanism of network nodes was set to make the network structure more consistent with the social network in real life. Finally, we verify the reliability and scientificity of the model by combining practical cases.