Entropy Ratio Research Articles

Interpretability Comparison of Popular Decision Tree Algorithms

Most of the open-source decision tree algorithms are based on three splitting criteria (Entropy, Gini Index, and Gain Ratio). Therefore, the advantages and disadvantages of these three popular algorithms need to be studied more thoroughly. Comparisons of the three algorithms were mainly performed with respect to the predictive performance. In this work, we conducted a comparative experiment on the splitting criteria of three decision trees, focusing on their interpretability. Depth, homogeneity, coverage, lift, and stability were used as indicators for measuring interpretability. To measure the stability of decision trees, we present a measure of the stability of the root node and the stability of the dominating rules based on a measure of the similarity of trees. Based on 10 data collected from UCI and Kaggle, we compare the interpretability of DT (Decision Tree) algorithms based on three splitting criteria. The results show that the GR (Gain Ratio) branch-based DT algorithm performs well in terms of lift and homogeneity, while the GINI (Gini Index) and ENT (Entropy) branch-based DT algorithms performs well in terms of coverage. With respect to stability, considering both the similarity of the dominating rule or the similarity of the root node, the DT algorithm according to the ENT splitting criterion shows the best results.

Cold chain vulnerability assessment through two-stage grey comprehensive measurement of intuitionistic fuzzy entropy

PurposeThis study aims to investigate the vulnerability of cold chain logistics through a comprehensive assessment and provide targeted control measures.Design/methodology/approachThe index system of the cold chain vulnerability assessment was established with knowledge obtained from three different dimensions, namely, exposure, sensitivity and adaptability. The final index weight was determined through combination of the intuitionistic fuzzy (IF) entropy and compromise ratio approaches, followed by the comprehensive vulnerability assessment through the two-stage grey comprehensive measurement model. The feasibility and effectiveness of the proposed method were verified by evaluation with SF, HNA, China Merchants and COFCO as target examples.FindingsThe results revealed that the most influential factors in the cold chain vulnerability problem were the temperature reaching the standard, as well as the storage and preservation levels; through their analysis combined with the overall cold chain vulnerability assessment, the targeted control measures were obtained.Originality/valueBased on the research perspective of cold chain vulnerability assessment, a novel assessment model of cold chain logistics vulnerability was proposed, which is based on IF entropy two-stage grey comprehensive measurement. It provides more powerful theoretical support to improve the quality management of cold chain products.

Hall and Spin Hall Viscosity in 2d Topological Systems

We study responses to metric perturbation in topological insulator models. In this paper we introduce a novel quantity, Hall viscosity to particle density ratio, which is analogous to the viscosity to entropy ratio suggested by AdS/CFT correspondence. This quantity corresponds to the filling fraction which characterizes the quantum Hall states, and hence it could be discussed in Haldane's zero-field quantum Hall system. We also consider dissipationless viscosity in the time reversal invariant quantum spin Hall system, which is related to a spin current.

Bridge Extraction Algorithm Based on Deep Learning and High-Resolution Satellite Image

This paper proposes a novel method of extracting roads and bridges from high-resolution remote sensing images based on deep learning. Edge detection is performed on the images in the road area along with the road skeleton line, and the result of the detected binary edge is vectorized. The interference of protective belts on both sides of the road, road vehicles, road green belts, traffic signs, etc. and the shadow interference of the bridge itself are eliminated to determine the parallel sides of the road. The bridge features on the road are used to locate the detected bridge and obtain information such as the location, length, width, and direction of the bridge, verifying the experimental results of the Shaoguan Le point images. In addition, in order to learn higher-level road feature information, the algorithm in this paper introduces the hollow convolution and multicore pooling modules. Secondly, the residual refinement network further refines the output of the prediction network to improve the ambiguity of the prediction network results. In addition, in view of the small proportion of road pixels in remote sensing images, the network also integrates binary cross entropy, structural similarity, and intersection ratio loss function to reduce road information loss. The applicability of the proposed study was tested, and the results show that the algorithm is very effective for the extraction of road and bridge targets.

Geohazards Susceptibility Assessment along the Upper Indus Basin Using Four Machine Learning and Statistical Models

The China–Pakistan Economic Corridor (CPEC) project passes through the Karakoram Highway in northern Pakistan, which is one of the most hazardous regions of the world. The most common hazards in this region are landslides and debris flows, which result in loss of life and severe infrastructure damage every year. This study assessed geohazards (landslides and debris flows) and developed susceptibility maps by considering four standalone machine-learning and statistical approaches, namely, Logistic Regression (LR), Shannon Entropy (SE), Weights-of-Evidence (WoE), and Frequency Ratio (FR) models. To this end, geohazard inventories were prepared using remote sensing techniques with field observations and historical hazard datasets. The spatial relationship of thirteen conditioning factors, namely, slope (degree), distance to faults, geology, elevation, distance to rivers, slope aspect, distance to road, annual mean rainfall, normalized difference vegetation index, profile curvature, stream power index, topographic wetness index, and land cover, with hazard distribution was analyzed. The results showed that faults, slope angles, elevation, lithology, land cover, and mean annual rainfall play a key role in controlling the spatial distribution of geohazards in the study area. The final susceptibility maps were validated against ground truth points and by plotting Area Under the Receiver Operating Characteristic (AUROC) curves. According to the AUROC curves, the success rates of the LR, WoE, FR, and SE models were 85.30%, 76.00, 74.60%, and 71.40%, and their prediction rates were 83.10%, 75.00%, 73.50%, and 70.10%, respectively; these values show higher performance of LR over the other three models. Furthermore, 11.19%, 9.24%, 10.18%, 39.14%, and 30.25% of the areas corresponded to classes of very-high, high, moderate, low, and very-low susceptibility, respectively. The developed geohazard susceptibility map can be used by relevant government officials for the smooth implementation of the CPEC project at the regional scale.

Shear viscosity and electric conductivity of a hot and dense QGP with a chiral phase transition

We calculate two transport coefficients -- the shear viscosity over entropy ratio $\eta/s$ and the ratio of the electric conductivity to the temperature $\sigma_0/T$ -- of strongly interacting quark matter within the extended $N_f=3$ Polyakov Nambu-Jona-Lasinio (PNJL) model along the crossover transition line for moderate values of baryon chemical potential $0 \leq \mu_B \leq 0.9$ GeV as well as in the vicinity of the critical endpoint (CEP) and at large baryon chemical potential $\mu_B=1.2$ GeV, where the first-order phase transition takes place. The evaluation of the transport coefficients is performed on the basis of the effective Boltzmann equation in the relaxation time approximation. We employ two different methods for the calculation of the quark relaxation times: i) using the averaged transition rate defined via thermal averaged quark-quark and quark-antiquark PNJL cross sections and ii) using the 'weighted' thermal averaged quark-quark and quark-antiquark PNJL cross sections. The $\eta/s$ and $\sigma_0/T$ transport coefficients have a similar temperature and chemical potential behavior when approaching the chiral phase transition for the both methods for the quark relaxation time, however, the differences grow with increasing temperature. We demonstrate the effect of the first-order phase transition and of the CEP on the transport coefficients in the deconfined QCD medium.

Impact of f(G,T) and f(R,G) on gravitational baryogenesis and observational bounds

The matter–antimatter asymmetry through baryogenesis (and generalized baryogenesis interaction) mechanism for well-known models of f(R,G) gravity (where R,G represent the Ricci scalar curvature and Gauss–Bonnet topological invariant) and f(G,T) (T denotes the trace of the energy momentum tensor) is being examined. This mechanism is based on the charge-parity (CP) violating interaction between the derivative of the Ricci scalar curvature and the baryon matter current, proposed by Davoudiasl et al. (2004). It is found that baryon to entropy ratio for f(G,T) gravity (specific models: f(G,T)=δGm+λT and f(G,T)=δGm+T+ϵT2), lies in the range 6.5−2.5+2.5×10−11 and 4−5+5×10−11. For f(R,G) (f(R,G)=k1R+k2RnGm and f(R,G)=f0R+f1G) models, we also obtain the values of baryon to entropy ratio which are very close to observational data 9×10−11. It is also mentioned here that results of general form of baryogenesis are also consistent with observational bounds for three models of modified theories of gravity.

A first estimate of η/s in Au+Au reactions at Elab = 1.23 AGeV

The HADES experiment at GSI has recently provided data on the flow coefficients v1,...,v4 for protons in Au+Au reactions at Elab=1.23AGeV (or sNN=2.4GeV). This data allows to estimate the shear viscosity over entropy density ratio, η/s at low energies via a coarse graining analysis of the UrQMD transport simulations of the flow harmonics in comparison to the experimental data. By this we can provide for the first time an estimate of η/s≈0.65±0.15 (or (8±2)(4π)−1) at such low energies.

Flood susceptibility mapping by integrating frequency ratio and index of entropy with multilayer perceptron and classification and regression tree

Episodes of frequent flooding continue to increase, often causing serious damage and tools to identify areas affected by such disasters have become indispensable in today's society. Using the latest techniques can make very accurate flood predictions. In this study, we introduce four effective methods to evaluate the flood susceptibility of Poyang County, in China, by integrating two independent models of frequency ratio and index of entropy with multilayer perceptron and classification and regression tree models. The flood locations of the study area were identified through the flood inventory process, and 12 flood conditioning factors were used in the training and validation processes. According to the results of the linear support vector machine, elevation, slope angle, and soil have the highest predictive ability. The experimental results of the four hybrid models demonstrate that between 20% and 50% of the study area has high and very high flood susceptibility. The multilayer perceptron-probability density hybrid model is the most effective among the six comparative methods.

An Improved Hilbert–Huang Transform for Vibration-Based Damage Detection of Utility Timber Poles

In this study, vibration based non-destructive testing (NDT) technique is adopted for assessing the condition of in-service timber pole. Timber is a natural material, and hence the captured broadband signal (induced from impact using modal hammer) is greatly affected by the uncertainty on wood properties, structure, and environment. Therefore, advanced signal processing technique is essential in order to extract features associated with the health condition of timber poles. In this study, Hilbert–Huang Transform (HHT) and Wavelet Packet Transform (WPT) are implemented to conduct time-frequency analysis on the acquired signal related to three in-service poles and three unserviceable poles. Firstly, mother wavelet is selected for WPT using maximum energy to Shannon entropy ratio. Then, the raw signal is divided into different frequency bands using WPT, followed by reconstructing the signal using wavelet coefficients in the dominant frequency bands. The reconstructed signal is then further decomposed into mono-component signals by Empirical Mode Decomposition (EMD), known as Intrinsic Mode Function (IMF). Dominant IMFs are selected using correlation coefficient method and instantaneous frequencies of those dominant IMFs are generated using HHT. Finally, the anomalies in the instantaneous frequency plots are efficiently utilised to determine vital features related to pole condition. The results of the study showed that HHT with WPT as pre-processor has a great potential for the condition assessment of utility timber poles.

Comparison of Heat Demand Prediction Using Wavelet Analysis and Neural Network for a District Heating Network

Short-Term Load Prediction (STLP) is an important part of energy planning. STLP is based on the analysis of historical data such as outdoor temperature, heat load, heat consumer configuration, and the seasons. This research aims to forecast heat consumption during the winter heating season. By preprocessing and analyzing the data, we can determine the patterns in the data. The results of the data analysis make it possible to form learning algorithms for an artificial neural network (ANN). The biggest disadvantage of an ANN is the lack of precise guidelines for architectural design. Another disadvantage is the presence of false information in the analyzed training data. False information is the result of errors in measuring, collecting, and transferring data. Usually, trial error techniques are used to determine the number of hidden nodes. To compare prediction accuracy, several models have been proposed, including a conventional ANN and a wavelet ANN. In this research, the influence of different learning algorithms was also examined. The main differences were the training time and number of epochs. To improve the quality of the raw data and remove false information, the research uses the technology of normalizing raw data. The basis of normalization was the technology of the Z-score of the data and determination of the energy‒entropy ratio. The purpose of this research was to compare the accuracy of various data processing and neural network training algorithms suitable for use in data-driven (black box) modeling. For this research, we used a software application created in the MATLAB environment. The app uses wavelet transforms to compare different heat demand prediction methods. The use of several wavelet transforms for various wavelet functions in the research allowed us to determine the best algorithm and method for predicting heat production. The results of the research show the need to normalize the raw data using wavelet transforms. The sequence of steps involves following milestones: normalization of initial data, wavelet analysis employing quantitative criteria (energy, entropy, and energy‒entropy ratio), optimization of ANN training with information energy–entropy ratio, ANN training with different training algorithms, and evaluation of obtained outputs using statistical methods. The developed application can serve as a control tool for dispatchers during planning.

Groundwater recharge potential zonation using an ensemble of machine learning and bivariate statistical models

Many regions in Iran are currently experience water crisis, largely driven by frequent droughts and expanding agricultural land combined with over abstraction of groundwater. Therefore, it is extremely important to identify potential groundwater recharge (GWR) zones to help in prevent water scarcity. The key objective of this research is to applying different scenarios for GWR potential mapping by means of a classifier ensemble approach, namely a combination of Maximum Entropy (ME) and Frequency Ratio (FR) models in a semi-arid mountainous, Marboreh Watershed of Iran. To consider the ensemble effect of these models, 15 input layers were generated and used in two models and then the models were combined in seven scenarios. According to marginal response curves (MRCs) and the Jackknife technique, quaternary formations (Qft1 and Qft2) of lithology, sandy-clay-loam (Sa. Cl. L) class of soil, 0–4% class of slope, and agriculture & rangeland classes of land use, offered the highest percolation potential. Results of the FR model showed that the highest weight belonged to Qft1 rocks and Sa. Cl. L textures. Seven scenarios were used for GWR potential maps by different ensembles based on basic mathematical operations. Correctly Classified Instances (CCI), and the AUC indices were applied to validate model predictions. The validation indices showed that scenarios 5 had the best performance. The combination of models by different ensemble scenarios enhances the efficiency of these models. This study serves as a basis for future investigations and provides useful information for prediction of sites with groundwater recharge potential through combination of state-of-the-art statistical and machine learning models. The proposed ensemble model reduced the machine learning and statistical models’ limitations gaps and promoted the accuracy of the model where combining, especially for data-scarce areas. The results of present study can be used for the GWR potential mapping, land use planning, and groundwater development plans.

Experimental study on heat transfer, friction factor, entropy and exergy efficiency analyses of a corrugated plate heat exchanger using Ni/water nanofluids

In the present study, the heat transfer, entropy, friction factor, exergy efficiency, pumping power, and performance index ratio of nickel/water nanofluids flow in a corrugated plate heat exchanger are investigated experimentally. The nickel nanoparticles were synthesized using the chemical precipitation method and characterized by various techniques. The stable water based nickel nanofluids were prepared with particle volume concentrations of 0.1%, 0.3%, and 0.6%. The experiments were conducted at nanofluids Reynolds numbers ranged from 300 to 1000. The properties of nickel nanofluid are evaluated experimentally as well. The thermal conductivity and viscosity enhancements are 33.92%, and 67.45% at a temperature of 60 °C compared to the base fluid data. The increase of nanoparticle loadings and Reynolds number leads to an augmentation of the overall heat transfer coefficient, heat transfer coefficient, and Nusselt number. The overall heat transfer coefficient, convective heat transfer, and Nusselt number enhanced by 38.60%, 57.35%, and 42.68% at 0.6 vol % of nanofluid and a Reynolds number of 707, respectively compared to water data. The thermal entropy generation is decreased by 15.70%, while frictional entropy generation and pumping power are increased by 68.29% and 61.77%, respectively at 0.6 vol % of nanofluid and a Reynolds number of 707 against water data. The exergy efficiency was enhanced by 42.27% at 0.6 vol % of nanofluid and a Reynolds number of 303 compared to water data. The performance index ratio is decreased with the use of nanofluids due to the increase of viscosity, friction factor, pressure drop, and pumping power.

Late-gadolinium enhancement properties associated with atrial fibrillation rotors in patients with persistent atrial fibrillation.

A computational model demonstrated that atrial fibrillation (AF) rotors could be distributed in patchy late-gadolinium enhancement (LGE) areas and play an important role in AF drivers. However, this was not validated in humans. The purpose of this study was to evaluate the LGE properties of AF rotors in patients with persistent AF. A total of 287 segments in 15 patients with persistent AF (long-standing persistent AF in 9 patients) that underwent AF ablation were assessed. Non-passively activated areas (NPAs), where rotational activation (AF rotor) was frequently observed, were detected by the novel real-time phase mapping (ExTRa Mapping). The properties of the LGE areas were assessed using the LGE heterogeneity and the density which was evaluated by the entropy (LGE-entropy) and the volume ratio of the enhancement voxel (LGE-volume ratio), respectively. NPAs were found in 61 (21%) of 287 segments and were mostly found around the pulmonary vein antrum. A receiver operating characteristic curve analysis yielded an optimal cutoff value of 5.7% and 10% for the LGE-entropy and LGE-volume ratio, respectively. The incidence of NPAs was significantly higher at segments with an LGE-entropy of >5.7 and LGE-volume ratio of >10% than at the other segments (38 [30%] of 126 vs. 23 [14%] of 161 segments; p = .001). No NPAs were found at segments with an LGE-volume ratio of >50% regardless of the LGE-entropy. Of five patients with AF recurrence, NPAs outside the PV antrum were not ablated in three patients and the remaining NPAs were ablated, but their LGE-entropy and LGE-volume ratio were low. AF rotors are mostly distributed in relatively weak and much more heterogenous LGE areas.

Residual Current Detection Method Based on Variational Modal Decomposition and Dynamic Fuzzy Neural Network

To further improve the detection ability of residual current in low-voltage distribution networks, an adaptive residual current detection method based on variational mode decomposition (VMD) and dynamic fuzzy neural network (DFNN) is proposed. First, using the general <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$K$ </tex-math></inline-formula> -value selection method of VMD proposed in this study, the residual current signal is decomposed into <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$K$ </tex-math></inline-formula> intrinsic mode functions (IMFs). By introducing the cross-correlation coefficient <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$R$ </tex-math></inline-formula> and the time-domain energy entropy ratio <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$E$ </tex-math></inline-formula> as two classification indexes, IMFs are divided into three categories: effective IMFs, noise IMFs and aliasing IMFs. Then, the aliasing IMFs are denoised by recursive least squares (RLS), and the denoised IMFs are superimposed with the effective IMFs to obtain the reconstructed signal. Finally, the dynamic fuzzy neural network (DFNN) is adjusted by the minimum output method to achieve the detection of the reconstructed residual current signal, and the network is used to predict the residual current according to the detection results. The detection results of the simulation and measured data show that the proposed algorithm has high detection accuracy and is superior to the wavelet neural network, empirical mode decomposition-thresholding, and wavelet entropy-auto encoder-back propagation neural network methods in terms of mean square error, goodness of fit and running time. This method provides a reference for further research on new adaptive residual current protection devices.

Advanced Encryption Standard (AES) 128 Bit untuk Keamanan Data Internet of Things (IoT) Tanaman Hidroponik

One method of growing vegetables is to use hydroponics by utilizing water as the medium used. In this era of rapidly developing technology, one of which is Internet of Things (IoT) is a system between computers or objects that can connect and exchange data without requiring interaction, because the data sent is public data, a security system is needed to secure the data sent. Advanced Encryption Standard (AES) 128 bits are used to secure data sent by users or data received by users, using a private key so that data security is maintained. The process of encryption and decryption was carried out through the website using an Arduino Uno microcontroller, SoC version ESP 8266. To adjust the rules for controlling plant needs such as Total Dissolve Solid (TDS), Potential Hydrogen (PH), temperature, and distance, this study uses Sensor2. Database in the research used to facilitate computerized access to assist the process of caring for IoT-based hydroponic plants. The final results have been tested in the encryption decryption process, Avalanche Effect (AE), entropy and Bit Error Ratio (BER). The AE yield 58.01% as highest score, the highest entropy was 6.3566 while all data resulted in BER = 0.

An Adaptive Optimized TVF-EMD Based on a Sparsity-Impact Measure Index for Bearing Incipient Fault Diagnosis

Bearing incipient fault diagnosis is very crucial to the timely condition-based maintenance (CBM), but it is also relatively difficult because of the faint feature and environmental interference. In this article, an adaptive optimized time-varying filtering-based empirical mode decomposition (TVF-EMD) (AO-TVF-EMD) is put forward to extract more explicit and abundant incipient fault features by optimizing the parameter combination in conventional TVF-EMD. First, a novel integrated indicator termed sparsity-impact measure index (SIMI) constructed from dispersion entropy (DE) and envelope characteristic frequency ratio (ECFR) is designed as the parameter selection criterion. This index fully guarantees the optimal sparsity and impact properties of the obtained modes simultaneously, considering both time- and frequency-domain characteristics. Simulation verified that SIMI can not only sensitively characterize the variation of fault feature but also is robust to the environmental disturbance. Subsequently, we employ the Salp swarm algorithm (SSA) to realize the accurate search of parameter combinations where the minimum SIMI is defined as the fitness function. Moreover, comparative analysis in two runs to failure tests of bearings demonstrate that AO-TVF-EMD is more effective to extract incipient fault features than the maximum weighted Kurtosis (MWK) optimized TVF-EMD, the conventional TVF-EMD with fixed parameter, and some other advanced signal processing methods, which highlights the superiority of the proposed method.

Predict high-frequency trading marker via manifold learning

High-frequency trading (HFT) has continuously evolved and dominated trading in the past decades. However, HFT trading marker prediction is a rarely investigated problem in Fintech literature. In this study, we first propose a novel manifold learning based HFT trading marker prediction model: M-SCAN to handle this challenge. Our study takes advantage of manifold embeddings of HFT data and seeks potential markers among the outliers in density-based clustering. We further propose HFT trading marker evaluation algorithms to validate the prediction effectiveness besides unveiling trading marker discovery via visualization. Our results demonstrate locally linear embedding (LLE) outperforms its peers in capturing trading markers in terms of accuracy and complexity for its local data structure keeping mechanism in embedding though different stocks may demonstrate their model preference under M-SCAN. Our studies also propose novel entropy and variance concentration ratios (VCR) to quantify HFT data and show that a high-entropy dataset is more likely to have better trading marker prediction than a low-entropy one. To the best of our knowledge, it is the first study in HFT trading marker prediction and will inspire coming studies in this area.

Measurement of long-range two- and multi-particle correlations by ALICE

Measurements of long-range particle correlations provide critical insights into the properties of the strongly coupled matter created in heavy-ion collisions and even in small collision systems, such as pp and p–Pb collisions. New results on long-range two-particle correlations for different multiplicity classes and ν2(η) in p–Pb collisions at 5.02 TeV are presented. These measurements utilize the Forward Multiplicity Detector (FMD), which allows for unprecedented Δη ranges to be explored (up to |Δη| ∼ 8) and to extract the pseudo-rapidity dependence of flow with wide pseudo-rapidity range (−3.4 <η < 5). The first measurement of the pseudo-rapidity dependence of two- and multi-particle cumulants in Pb–Pb collisions at 5.02 TeV is also presented. With the future hydrodynamic calculations, the presented results will provide key constraints on the temperature dependence of the shear viscosity over entropy density ratio. In addition, by comparing to AMPT model calculations, the ALICE data provide precise information on the 3D evolution of the hot and dense matter created in heavy-ion collisions and small collision systems.

Linear and non-linear flow modes of charged and identified particles in Pb–Pb collisions at [formula omitted] with ALICE

The higher order harmonic flow observables νn (n > 3) and their non-linear responses to the initial state anisotropy have the strong potential to constrain shear and bulk viscosity to entropy ratios because of different sensitivities for various stages of heavy-ion collisions. The measurements of the flow coefficients and the non-linear coefficients up to the ninth and fifth harmonic, respectively, are presented in Pb–Pb collisions at sNN=5.02TeV for charged hadrons. In addition, the results of pT-differential non-linear flow modes for π±, K±, p+p¯, K0s, Λ+Λ¯s0 and ϕ are presented. The results are compared to the same measurements at 2.76 TeV and calculations from state of the art hydrodynamic models.