Search

The unduly low or high data are commonly regarded as the outliers in the classical power geometric operator. However, in many cases, these types of data may be significantly important to the aggregated results. This study aims at expanding the practical application scope of the power geometric operator and then utilizing it to develop a proportional hesitant fuzzy linguistic large-scale group decision-making (LSGDM) model. The extended power geometric (EPG) operator is first introduced, in which these outliers can be distinguished as sufficiently important or "false/biased" data in accordance with the decision-making context. Several useful properties and application characteristics of the EPG operator are investigated. Subsequently, the proportional hesitant fuzzy linguistic normalized Manhattan distance is proposed, and it forms a basic concept to the construction of the proportional hesitant fuzzy linguistic extended power geometric (PHFLEPG) operator. Combined with the clustering model for decision makers, a PHFLEPG-operator-based consensus reaching approach is provided to simplify and rationalize the decision-making process. Furthermore, the comprehensive LSGDM result is derived in the use of the PHFLEPG operator. Eventually, a case study on regulatory capacity evaluation for the Civil Aviation Safety Regulatory Authority of China (CASRAC) is performed to validate the feasibility and effectiveness of the established LSGDM model. [ABSTRACT FROM AUTHOR]

The prediction of surface settlement occupies a crucial role in achieving effective catastrophe prevention and mitigation, as well as facilitating the maintenance of airport runways. Given the challenges associated with the manual collection of settlement data and the suboptimal timeliness of the Back Propagation (BP) technique in neural networks, this study proposes an integrated prediction method that combines the Ensemble Kalman Filter (EnKF) with BP. This study focuses on the processing of Synthetic Aperture Radar (SAR) pictures obtained from the ascending orbit of the Sentinel-1A satellite. The Small Baseline Subset Interferometric synthetic aperture radar (SBAS-InSAR) technology is employed to derive the settlement time series on the runway of Kangding Airport. Moreover, three sites with high coherence within the primary settlement region are employed to assess the dependability of the model after the expansion of the data by cubic spline interpolation. The findings of the study indicate that both the BP-EnKF and BP models exhibit favorable outcomes in predicting airport runway settlement. However, following the alteration of data caused by external environmental influences, the BP-EnKF model has superior adaptability to variations in data. It has been shown that the BP-EnKF model exhibits a prediction accuracy that surpasses the BP model by 9.25%. [ABSTRACT FROM AUTHOR]

High-speed railway systems face frequent cybersecurity threats targeting their information networks. Continuous operation of protection mechanisms on wireless sensors results in persistent energy consumption, which is undesirable. To address this, we propose an optimal defense strategy selection approach for High-speed Railway Wireless Sensor Networks (HSR-WSNs) using an enhanced signaling game model. We first establish the basic elements and overall structure of the model, considering the presence of incomplete information and dynamic interactions between players. This paper provides background on signaling games, including theoretical concepts of equilibrium strategies and locations. We then develop a system to quantify payoffs for offensive and defensive tactics, incorporating distance and usage frequency weights. Finally, Long Short-Term Memory (LSTM) and the public UNSW-NB15 dataset are leveraged to augment assumptions and reduce human subjectivity in results. Experiments demonstrate the model effectively identifies energy balance points for HSR-WSNs and determines appropriate protection strategies. The work contributes to enhancing the selection of effective defense techniques against network attacks in wireless sensor systems. This has significant practical implications in enabling optimized energy usage and functionality of secured sensor nodes. [ABSTRACT FROM AUTHOR]

Fire accidents continually threaten lives and property, posing a great risk to public safety. Therefore, timely, accurate fire smoke and flame detection technology provides a technical foundation for ensuring personnel and property safety. This paper proposes a deep transfer learning model that integrates attention mechanisms and pruning techniques into the DenseNet network (P-DenseNet-A-TL) for detecting fire smoke and flame targets. To reduce the computational complexity of the fire detection model, we simplified the DenseNet network structure. To improve the recognition accuracy of the fire detection model, we incorporated attention mechanisms including a channel attention module (CAM) and spatial attention module (SAM) into the pruned dense network structure. To expedite the model training process, we also introduced a transfer learning model. Furthermore, to enhance the generalization ability and robustness of the model, we created a large-scale fire smoke and flame dataset. The experimental results show that our model (P-DenseNet-A-TL) achieved a test accuracy of 99.06%, F1 score of 99.09%, area under the curve (AUC) of 0.97, and a detection speed of 756 frames per second (FPS). The comparison experimental results and ablation experimental results indicate that our method achieves high detection accuracy and efficiency. Additionally, it possesses strong generalization capability and robustness. [ABSTRACT FROM AUTHOR]

Possibility distribution provides an alternative explanation of linguistic terms in an hesitant fuzzy linguistic term set (HFLTS). It is generated from a given HFLTS based on the assumption that all linguistic terms in an HFLTS follow a uniform distribution. In decision making contexts, linguistic terms in each HFLTS are assumed to exhibit the same possibility to represent the decision-maker(DM)’s assessment rating. However, DMs may give ratings based on different assessing attitudes because of individual differences in cognitive styles. In practice, comparative linguistic expressions are generally converted into HFLTSs through the transformation process as DMs usually use comparative linguistic expressions instead of HFLTSs when giving ratings. The transformed HFLTSs likewise exclude the DMs’ assessing attitudes. To enhance the interpretability of generated possibility distributions, this paper relaxes the original assumption of uniform distribution and incorporates an attitudinal dimension into the transformation process that converts comparative linguistic expressions to HFLTSs. With these modified conditions for possibility distribution generation, an assessing attitude-driven approach is proposed based on probability density functions (PDFs) to generate HFLTS possibility distributions. The proposed PDF-based HFLTS possibility distributions personalize individual semantics and further facilitate the process of computing with words to obtain assessing attitude-embedded accurate linguistic results that are easy for individuals to interpret and understand. [ABSTRACT FROM AUTHOR]