Browse

You are looking at 1 - 10 of 13,812 items for :

  • Engineering x
Clear All
Open access

M. Javaid, M. Abbas, Jia-Bao Liu, W. C. Teh and Jinde Cao

Abstract

A topological property or index of a network is a numeric number which characterises the whole structure of the underlying network. It is used to predict the certain changes in the bio, chemical and physical activities of the networks. The 4-layered probabilistic neural networks are more general than the 3-layered probabilistic neural networks. Javaid and Cao [Neural Comput. and Applic., DOI 10.1007/s00521-017-2972-1] and Liu et al. [Journal of Artificial Intelligence and Soft Computing Research, 8(2018), 225-266] studied the certain degree and distance based topological indices (TI’s) of the 3-layered probabilistic neural networks. In this paper, we extend this study to the 4-layered probabilistic neural networks and compute the certain degree-based TI’s. In the end, a comparison between all the computed indices is included and it is also proved that the TI’s of the 4-layered probabilistic neural networks are better being strictly greater than the 3-layered probabilistic neural networks.

Open access

Ryotaro Kamimura

Abstract

The present paper1 aims to propose a new type of information-theoretic method to maximize mutual information between inputs and outputs. The importance of mutual information in neural networks is well known, but the actual implementation of mutual information maximization has been quite difficult to undertake. In addition, mutual information has not extensively been used in neural networks, meaning that its applicability is very limited. To overcome the shortcoming of mutual information maximization, we present it here in a very simplified manner by supposing that mutual information is already maximized before learning, or at least at the beginning of learning. The method was applied to three data sets (crab data set, wholesale data set, and human resources data set) and examined in terms of generalization performance and connection weights. The results showed that by disentangling connection weights, maximizing mutual information made it possible to explicitly interpret the relations between inputs and outputs.

Open access

Parisa Rastin, Basarab Matei, Guénaël Cabanes, Nistor Grozavu and Younès Bennani

Abstract

Collaborative Clustering is a data mining task the aim of which is to use several clustering algorithms to analyze different aspects of the same data. The aim of collaborative clustering is to reveal the common underlying structure of data spread across multiple data sites by applying clustering techniques. The idea of collaborative clustering is that each collaborator shares some information about the segmentation (structure) of its local data and improve its own clustering with the information provided by the other learners. This paper analyses the impact of the quality and the diversity of the potential learners to the quality of the collaboration for topological collaborative clustering algorithms based on the learning of a Self-Organizing Map (SOM). Experimental analysis on real data-sets showed that the diversity between learners impact the quality of the collaboration. We also showed that some internal indexes of quality are a good estimator of the increase of quality due to the collaboration.

Open access

Michal Mizera, Pawel Nowotarski, Aleksander Byrski and Marek Kisiel-Dorohinicki

Abstract

Evolutionary Multi-agent System introduced by late Krzysztof Cetnarowicz and developed further at the AGH University of Science and Technology became a reliable optimization system, both proven experimentally and theoretically. This paper follows a work of Byrski further testing and analyzing the efficacy of this metaheuristic based on popular, high-dimensional benchmark functions. The contents of this paper will be useful for anybody willing to apply this computing algorithm to continuous and not only optimization.

Open access

Md Meftahul Ferdaus, Sreenatha G. Anavatti, Matthew A. Garratt and Mahardhika Pratama

Abstract

Advanced and accurate modelling of a Flapping Wing Micro Air Vehicle (FW MAV) and its control is one of the recent research topics related to the field of autonomous MAVs. Some desiring features of the FW MAV are quick flight, vertical take-off and landing, hovering, and fast turn, and enhanced manoeuvrability contrasted with similar-sized fixed and rotary wing MAVs. Inspired by the FW MAV’s advanced features, a four-wing Nature-inspired (NI) FW MAV is modelled and controlled in this work. The Fuzzy C-Means (FCM) clustering algorithm is utilized to construct the data-driven NIFW MAV model. Being model free, it does not depend on the system dynamics and can incorporate various uncertainties like sensor error, wind gust etc. Furthermore, a Takagi-Sugeno (T-S) fuzzy structure based adaptive fuzzy controller is proposed. The proposed adaptive controller can tune its antecedent and consequent parameters using FCM clustering technique. This controller is employed to control the altitude of the NIFW MAV, and compared with a standalone Proportional Integral Derivative (PID) controller, and a Sliding Mode Control (SMC) theory based advanced controller. Parameter adaptation of the proposed controller helps to outperform it static PID counterpart. Performance of our controller is also comparable with its advanced and complex counterpart namely SMC-Fuzzy controller.

Open access

Massimiliano Zappa, Ladislav Holko, Martin Šanda, Tomáš Vitvar and Juraj Parajka

Open access

Anton Yu. Komarov, Yury G. Seliverstov, Pavel B. Grebennikov and Sergey A. Sokratov

Abstract

The aim of the investigation was assessment of spatial variability of the characteristics of snowpack, including the snow water equivalent (SWE) as the main hydrological characteristic of a seasonal snow cover. The study was performed in Khibiny Mountains (Russia), where snow density and snow cover stratigraphy were documented with the help of the SnowMicropen measurements, allowing to determine the exact position of the snow layers’ boundaries with accuracy of 0.1 cm. The study site was located at the geomorphologically and topographically uniform area with uniform vegetation cover. The measurement was conducted at maximum seasonal SWE on 27 March 2016. Twenty vertical profiles were measured along the 10 m long transect. Vertical resolution depended on the thickness of individual layers and was not less than 10 cm. The spatial variation of the measured snowpack characteristics was substantial even within such a homogeneous landscape. Bulk snow density variability was similar to the variability in snow height. The total variation of the snowpack SWE values along the transect was about 20%, which is more than the variability in snow height or snow density, and should be taken into account in analysis of the results of normally performed in operational hydrology snow course SWE estimations by snow tubes.

Open access

Kerstin Hürkamp, Nadine Zentner, Anne Reckerth, Stefan Weishaupt, Karl-Friedrich Wetzel, Jochen Tschiersch and Christine Stumpp

Abstract

High amounts of precipitation are temporarily stored in high-alpine snow covers and play an important role for the hydrological balance. Stable isotopes of hydrogen (δ2H) and oxygen (δ18O) in water samples have been proven to be useful for tracing transport processes in snow and meltwater since their isotopic ratio alters due to fractionation. In 18 snow profiles of two snowfall seasons, the temporal and spatial variation of isotopic composition was analysed on Mt. Zugspitze. The δ18O and δ2H ranged between -26.7‰ to -9.3‰ and -193.4‰ to -62.5‰ in 2014/2015 and between -26.5‰ to -10.5‰ and -205.0‰ to -68.0‰ in 2015/2016, respectively. Depth-integrated samples of entire 10 cm layers and point measurements in the same layers showed comparable isotopic compositions. Isotopic composition of the snowpack at the same sampling time in spatially distributed snow profiles was isotopically more similar than that analysed at the same place at different times. Melting and refreezing were clearly identified as processes causing isotope fractionation in surficial, initial base or refrozen snow layers. For the future, a higher sampling frequency with detailed isotopic composition measurements during melt periods are recommended to improve the understanding of mass transport associated with snowmelt.

Open access

Martin Šanda, Tomáš Vitvar and Jakub Jankovec

Abstract

Nine years of seasonal δ18O values in precipitation, soilwater and groundwater were evaluated in the Uhlířská catchment between 2008 and 2016 and recharge winter/summer ratios were calculated using δ18O values. The longterm average 18O content in groundwater is lower than the mean weighted 18O content in precipitation. This is explained by more than 50% of winter- and snowmelt- induced groundwater recharge that occurs in all years except of 2010 and 2013. The recharge of the peat organic soil water is balanced between summer and winter, whereas the mineral hillslope soil is dominantly recharged by summer precipitation. The 67% portion of baseflow, dominantly generated in the winter season, is composed of groundwater and peat organic soil water, according to the hydrochemical distribution of runoff components. Isotopic mass balance of individual winters shows that precipitation in warmer winters is entirely transformed into outflow until the end of the winter season, generating no significant water storage for potential drought periods

Open access

Philippe Riboust, Guillaume Thirel, Nicolas Le Moine and Pierre Ribstein

Abstract

Conceptual degree-day snow models are often calibrated using runoff observations. This makes the snow models dependent on the rainfall-runoff model they are coupled with. Numerous studies have shown that using Snow Cover Area (SCA) remote sensing observation from MODIS satellites helps to better constrain parameters. The objective of this study was to calibrate the CemaNeige degree-day snow model with SCA and runoff observations. In order to calibrate the snow model with SCA observations, the original CemaNeige SCA formulation was revisited to take into account the hysteresis that exists between SCA and the snow water equivalent (SWE) during the accumulation and melt phases. Several parametrizations of the hysteresis between SWE and SCA were taken from land surface model literature. We showed that they improve the performances of SCA simulation without degrading the river runoff simulation. With this improvement, a new calibration method of the snow model was developed using jointly SCA and runoff observations. Further analysis showed that the CemaNeige calibrated parameter sets are more robust for simulating independent periods than parameter sets obtained from discharge calibration only. Calibrating the snow model using only SCA data gave mixed results, with similar performances as using median parameters from all watersheds calibration.