• Journal of applied mathematics & informatics
• /
• v.42 no.4
• /
• pp.879-897
• /
• 2024

The emergence of generalized square metrics in Finsler geometry can be attributed to various classification concerning (𝛼, 𝛽)-metrics. They have excellent geometric properties in Finsler geometry. Within the scope of this research paper, we have conducted an investigation into the generalized square metric denoted as $F(x,y)=\frac{[{\alpha}(x,y)+{\beta}(x,y)]^{n+1}}{[{\alpha}(x,y)]^n}$, focusing specifically on its application to the Finslerian hypersurface. Furthermore, the classification and existence of first, second, and third kind of hyperplanes of the Finsler manifold has been established.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.2
• /
• pp.907-923
• /
• 2020

For the severe haze situation in the Beijing-Tianjin-Hebei region, conventional fine particulate matter (PM2.5) concentration prediction methods based on pollutant data face problems such as incomplete data, which may lead to poor prediction performance. Therefore, this paper proposes a method of predicting the PM2.5 concentration based on image analysis technology that combines image data, which can reflect the original weather conditions, with currently popular machine learning methods. First, based on local parameter estimation, autoregressive (AR) model analysis and local estimation of the increase in image blur, we extract features from the weather images using an approach inspired by free energy and a no-reference robust metric model. Next, we compare the coefficient energy and contrast difference of each pixel in the AR model and then use the percentages to calculate the image sharpness to derive the overall mass fraction. Furthermore, the results are compared. The relationship between residual value and PM2.5 concentration is fitted by generalized Gauss distribution (GGD) model. Finally, nonlinear mapping is performed via the wavelet neural network (WNN) method to obtain the PM2.5 concentration. Experimental results obtained on real data show that the proposed method offers an improved prediction accuracy and lower root mean square error (RMSE).

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.14 no.6
• /
• pp.171-178
• /
• 2010

Pipeline structure is one of core underground infrastructure which transports primary sources. Since the almost pipeline structures are placed underground and connected each other complexly, it is difficult to monitor their structural health condition continuously. In order to overcome this limitation of recent monitoring technique, recently, a Ubiquitous Sensor Network (USN) system based on on-line and real-time monitoring system is being developed by the authors' research group. In this study, real-time pipeline health monitoring (PHM) methodology is presented based on electromechanical impedance methods using USN. Two types of damages including loosened bolts and notches are artificially inflicted on the pipeline structures, PZT and MFC sensors that have piezoelectric characteristics are employed to detect these damages. For objective evaluation of pipeline conditions, Damage metric such as Root Mean Square Deviation (RMSD) value was computed from the impedance signals to quantify the level of the damage. Optimal threshold levels for decision making are estimated by generalized extreme value(GEV) based statistical method. Throughout a series of experimental studies, it was reviewed the effectiveness and robustness of proposed PHM system.