Journal of Intelligent & Fuzzy Systems - Volume 45, issue 6

Authors: Kong, Decai | Tang, Yi | Zhang, Hao | Bi, Aorui

Article Type: Research Article

Abstract: Technology trading matching facilitates quicker solution-finding for technology demanders and expedites the transformation of scientific and technological achievements. Yet, unstable matchings often lead traders to renounce existing contracts, sidestep trading intermediaries, and resort to private transactions. This results in inefficient trading mechanisms and market disarray. To ensure a stable and mutually satisfactory match for both suppliers and demanders, we propose a stable two-sided matching decision-making method that incorporates intuitionistic fuzzy multi-attribute information. Initially, we introduce an intuitionistic fuzzy TOPSIS approach to compute the comprehensive satisfaction of both suppliers and demanders by aggregating intuitionistic fuzzy information across various attributes. Subsequently, we …design a multi-objective optimization model that weighs both stability and satisfaction to determine the ideal technology trading pairs. We conclude with a real-world example that demonstrates the proposed method’s application, and its effectiveness is corroborated through sensitivity and comparative analyses. Show more

Keywords: Technology trading, two-sided matching, stable matching, intuitionistic fuzzy sets

DOI: 10.3233/JIFS-232275

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 12395-12409, 2023

Authors: Wang, Hao | Xu, Yanyan | Han, Yue | Zhang, Kejia

Article Type: Research Article

Abstract: With the rapid growth of the global population and the increasing urbanization, the urban landscape in China is gradually enriched, and the scale of the landscape that plays a healing role is expanding. However, curing the problem of landscape ecological security is an important part of Homeland security, economic and social sustainable development. We must deal with the relationship between high-quality social development and ecological environment protection on the basis of scientific evaluation. To address this issue, research has provided better data support for feature extraction through image preprocessing. Then the Convolutional neural network in deep learning is trained through …a large number of collected measured data. Finally, the pressure state response model is used to evaluate the ecological security of the healing landscape. The results show that the average error of the ground class in 2010 was 13.65%, and the fitting accuracy reached 86.35%, indicating that this method has high accuracy and can be effectively applied in evaluation. Meanwhile, in 2010 and 2019, the average landscape ecological security levels of City A were 7.27 and 6.65, both at a “safe” level, but the overall security level showed a downward trend. It is recommended to optimize the land use pattern in future urban planning and construction, improve the urban landscape ecological security index value, and maintain consistency with the actual situation of the city. This can provide reference for the evaluation model of urban landscape ecological security, and further provide scientific basis and guidance for the ecological civilization construction of urban agglomerations. In subsequent research, the evolution trend of urban landscape ecological security can be taken as the research goal, and finally, guidance on optimizing urban landscape ecological security can be provided. Show more

Keywords: Deep learning, PSR model, ecological security assessment

DOI: 10.3233/JIFS-233040

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 12411-12424, 2023

Authors: Huang, Shuaina | Zhang, Zhiyong | Song, Bin | Mao, Yueheng

Article Type: Research Article

Abstract: Social network attackers leverage images and text to disseminate sensitive information associated with pornography, politics, and terrorism,causing adverse effects on society.The current sensitive information classification model does not focus on feature fusion between images and text, greatly reducing recognition accuracy.To address this problem, we propose an attentive cross-modal fusion model (ACMF), which utilizes mixed attention mechanism and the Contrastive Language-Image Pre-training model.Specifically, we employ a deep neural network with a mixed attention mechanism as a visual feature extractor. This allows us to progressively extract features at different levels. We combine these visual features with those obtained from a text feature …extractor and incorporate image-text frequency domain information at various levels to enable fine-grained modeling. Additionally, we introduce a cyclic attention mechanism and integrate the Contrastive Language-Image Pre-training model to establish stronger connections between modalities, thereby enhancing classification performance.Experimental evaluations conducted on sensitive information datasets collected demonstrate the superiority of our method over other baseline models. The model achieves an accuracy rate of 91.4% and an F1-score of 0.9145. These results validate the effectiveness of the mixed attention mechanism in enhancing the utilization of important features. Furthermore, the effective fusion of text and image features significantly improves the classification ability of the deep neural network. Show more

Keywords: Multi-modal, sensitive information, spatial attention mechanism, channel attention mechanism, deep learning

DOI: 10.3233/JIFS-233508

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 12425-12437, 2023

Authors: Nalini Joseph, L. | Anand, R.

Article Type: Retraction

DOI: 10.3233/JIFS-219330

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 12439-12439, 2023