Search

Density Functional Theory (DFT) is extensively used in theoretical and computational chemistry to study molecular and crystal properties across diverse fields, including quantum chemistry, materials physics, catalysis, biochemistry, and surface science. Despite advances in DFT hardware and software for optimized geometries, achieving consensus in molecular structure comparisons with experimental counterparts remains a challenge. This difficulty is exacerbated by the lack of automated bond length comparison tools, resulting in labor-intensive and error-prone manual processes. To address these challenges, we propose MolGC, a Molecular Geometry Comparator algorithm that automates the comparison of optimized geometries from different theoretical levels. MolGC calculates the mean absolute error (MAE) of bond lengths by integrating data from various DFT software. It provides interactive and customizable visualization of geometries, enabling users to explore different views for enhanced analysis. In addition, it saves MAE computations for further analysis and offers a comprehensive statistical summary of the results. MolGC effectively addresses complex graph labeling challenges, ensuring accurate identification and categorization of bonds in diverse chemical structures. It achieves a 98.91% average rate in correct bond label assignments on an antibiotics dataset, showcasing its effectiveness for comparing molecular bond lengths across geometries of varying complexity and size. The executable file and software resources for running MolGC can be downloaded from https://github.com/AbimaelGP/MolGC/tree/main. [ABSTRACT FROM AUTHOR]

In recent years, vector-to-vector mapping-based raw waveform biosignal enhancement methods have gained significant attention in remote health monitoring system. In this paper, a novel end-to-end convolutional encoder–decoder (CED) model with stacked gated recurrent unit (SGRU) is proposed to learn sequential information of biosignal for signal enhancement. The proposed model CED-SGRU employs convolutional neural network to capture the spatial features and SGRU to capture temporal distributions of the biosignal layer by layer which increases the robustness of the proposed model. This work applies mean absolute error as a loss function for CED-SGRU-based vector-to-vector model. The proposed method has been evaluated on three foremost required biosignals, namely electrocardiogram, photoplethysmography and heart rate signals for diagnosing cardiovascular diseases. Experimental result shows outstanding denoising capability of the proposed CED-SGRU model on three biosignals which yields significantly higher reconstruction signal-to-noise ratio value and lower average absolute error, root mean square error and percent root mean square difference values when compared with state-of-the-art-methods. Moreover, the simple architecture of SGRU lowers the complexity of the model; thereby, reducing the inference time for denoising and restoring compressed biosignal tasks is fairly compared with baseline models, namely recurrent neural network model and long short-term memory model. [ABSTRACT FROM AUTHOR]

Cryptocurrency is a form of digital currency using cryptographic techniques in a decentralized system for secure peer-to-peer transactions. It is gaining much popularity over traditional methods of payment because it facilitates very fast, easy, and secure transactions. Social media is a significant influence, but it is also very volatile and subject to a variety of other factors. Thus, with over four billion active users on social media, we need to understand its influence on the crypto market and how it can lead to fluctuations in the values of these cryptocurrencies. In our work, we analyze the influence of activities on Twitter, in particular the sentiments of the tweets posted regarding cryptocurrencies and how they influence their prices. In addition, we also collect metadata related to tweets and users. We try to leverage these features to predict the price of cryptocurrency, for which we use some regression-based models and an LSTM-based model. [ABSTRACT FROM AUTHOR]

The threshold model is one of the most commonly used ordinal regression methods. It projects patterns onto a real axis and uses a list of thresholds to divide the real axis into consecutive intervals, one for each category. We propose using a fixed sequence of natural thresholds (i.e., 0.5 , 1.5 , ... ) to simplify the model. We prove that using fixed thresholds does not degrade the performance after minor changes in the neural network structure. The natural threshold simplifies the logical complexity and implementation complexity of the model, so that the loss function can be easily customized for any special metric. We have designed loss functions for various ordinal regression evaluation metrics and achieved the best level of results on many ordinal regression tasks. [ABSTRACT FROM AUTHOR]

This paper proposes a robust signal-to-noise ratio (SNR) estimation technique from continuous speech based on the non-negative frequency-weighted energy operator using the envelope of derivative of the speech signal. The proposed SNR evaluation method is implemented in two phases. The first phase of SNR estimation consists of speech region identification by glottal activity detection (GAD) along with two pre-processing and post-processing methods. Speech enhancement with background subtraction is the pre-processing and obstruent detection with duration modification is the post-processing modules to GAD, which improves the speech and non-speech region detection performance. The next stage comprises estimation of SNR from instantaneous energy contour obtained from the envelope of the derivative of the speech signal, which is based on non-negative frequency-weighted energy estimation. The ratio of instantaneous energy of speech region to non-speech region is considered as the estimated segmental SNR. The final SNR is calculated by averaging segmental SNR and compared with true SNR to get the estimation efficiency of the proposed method. The performance of the proposed method for SNR estimation from speech sample is evaluated using TIMIT, NOIZEUS, and TESDHE acoustic speech corpus. The TIMIT and NOIZEUS databases are used to evaluate the performance for a different type of noise and TESDHE database is used for analysis under a different mode of data. The result of our study shows that the proposed system provides accurate SNR estimation across different types of noise and different modes of signal for various signal levels and outperforms the other methods under observation. [ABSTRACT FROM AUTHOR]

An experimental study is carried out to evaluate the effect of temperature and composition on the variation of seven thermo physical properties (thermal conductivity, specific heat, thermal diffusivity, density, electrical resistivity, linear thermal expansion and electrical conductivity) of 32 AISI-SAE commercial steel (annealed and rolled steels), with a composition (C, Mn, P, S, Si, Ni, Cr, Mo, V), and a working temperature from 0 to 800 °C. Applying the method of progressive adjustment of functions, the experimental data obtained are generalized, developing a correlation that fits the range of validity of the experiments and that provides an adequate uncertainty value to extend its use to thermal engineering design of equipment and heat transfer applications. The validation and adjustment of the proposed models is made by comparing it with available experimental data. The weaker adjustment was achieved in the modeling of the thermal conductivity of AISI-SAE 430 steel with a mean and maximum deviation obtained of 13.1% and 16.7% respectively, while the best indices were obtained in the estimation of the density of AISI-SAE 1345 steel with a mean and maximum deviation obtained from 0.14 and 0.22%, respectively. In all cases, the agreement of the proposed model is good enough to be considered satisfactory for practical design. Regarding the elements of study presented, there is no evidence of similar expressions in the available and known literature, which is why they are considered a scientific novelty. [ABSTRACT FROM AUTHOR]

This paper presents a transfer function time series forecast model for COVID-19 deaths using reported COVID-19 case positivity counts as the input series. We have used deaths and case counts data reported by the Center for Disease Control for the USA from July 24 to December 31, 2021. To demonstrate the effectiveness of the proposed transfer function methodology, we have compared some summary results of forecast errors of the fitted transfer function model to those of an adequate autoregressive integrated moving average model and observed that the transfer function model achieved better forecast results than the autoregressive integrated moving average model. Additionally, separate autoregressive integrated moving average models for COVID-19 cases and deaths are also reported. [ABSTRACT FROM AUTHOR]

Photomosaic images are composite images composed of many small images called tiles. In its overall visual effect, a photomosaic image is similar to the target image, and photomosaics are also called “montage art”. Noisy blocks and the loss of local information are the major obstacles in most methods or programs that create photomosaic images. To solve these problems and generate a photomosaic image in this study, we propose a tile selection method based on error minimization. A photomosaic image can be generated by partitioning the target image in a rectangular pattern, selecting appropriate tile images, and then adding them with a weight coefficient. Based on the principles of montage art, the quality of the generated photomosaic image can be evaluated by both global and local error. Under the proposed framework, via an error function analysis, the results show that selecting a tile image using a global minimum distance minimizes both the global error and the local error simultaneously. Moreover, the weight coefficient of the image superposition can be used to adjust the ratio of the global and local errors. Finally, to verify the proposed method, we built a new photomosaic creation dataset during this study. The experimental results show that the proposed method achieves a low mean absolute error and that the generated photomosaic images have a more artistic effect than do the existing approaches. [ABSTRACT FROM AUTHOR]

Educational data mining helps the educational institutions to perform effectively and efficiently by exploiting the data related to all its stakeholders. It can help the at-risk students, develop recommendation systems and alert the students at different levels. It is beneficial to the students, educators and authorities as a whole. Deep learning has gained momentum in various domains especially image processing with a large dataset. We devise a regression model for analyzing the academic performance of the students using deep learning. We have applied regression using deep learning and linear regression on the dataset. For such models with smaller datasets, to tackle the issue of overfitting is critical. Hence, the parameters can be tuned to deal with such issues. The deep learning model records a mean absolute score (mae) of 1.61 and loss 4.7 with the value of k = 3. While the linear regression model yields a loss of 6.7 and mae score of 1.97. The deep learning model outperforms the linear regression model. The model may be successfully extended to other programmes to mine and predict the performance of the learners. [ABSTRACT FROM AUTHOR]

To predict future values based on imprecisely observed values, uncertain time series has been proposed, and the least-squares method has been presented to estimate the unknown parameters of uncertain autoregressive models. This paper considers the least absolute deviations estimation of uncertain autoregressive model, and a minimization problem is derived to calculate the unknown parameters in the uncertain autoregressive model. Finally, some numerical examples are given to illustrate the robustness of the least absolute deviations estimation compared with the least-squares estimation. [ABSTRACT FROM AUTHOR]

Biomass equations were developed for different components of oak trees (Quercus cerris L.), which have been managed in coppices at different development stages—small-diameter forest (SDF) and medium-diameter forest (MDF). In this context, four biomass regression models—two based on diameter at breast height (DBH) alone and two based on DBH and total tree height (H)—were developed for each of the crown, stem, and total aboveground biomass components. Akaike's information criterion (AIC), root mean square error percentage (RMSE (%)), mean absolute error percentage (MAE (%)), adjusted coefficient of determination (Adj.R2), and bias values were used to evaluate and compare the suitability of a total of 12 regression models developed for biomass components. As a result, in the estimation of crown biomass, only DBH-based models provided higher estimation accuracy than DBH-H-based models. For the most suitable model, estimated values were Adj.R2 = 0.60, bias = − 0.009, RMSE = 66%, and MAE = 41%. In models developed to estimate stem biomass, the estimation accuracy of DBH-H-based models was higher. In the goodness-of-fit statistics calculated for the most suitable model, Adj.R2, bias, RMSE, and MAE were 0.89, 0.010, 38%, and 23%, respectively. The models developed to estimate the total aboveground biomass were all close in terms of estimation accuracy. The biomass components (crown and stem) in the total aboveground biomass were proportionally as follows: crown at 38% and stem at 62% in the SDF stage, and crown at 35% and stem at 65% in the MDF stage, indicating lower crown and higher stem partitioning as the development stage increased. [ABSTRACT FROM AUTHOR]

Ordinal classification problems are applied in many fields. In the field of multivariate statistical analysis, these tasks are referred to as ordinal regression problems. In the field of management decision-making, they are known as multi-criteria decision analyses or sorting problems. This paper introduces the PairCode algorithm for ordinal classification with small sample sizes, which is based on a pairwise comparison strategy. In addition, this work outlines how to use pairwise comparisons to transform ordinal classifications into disordered regressions and how to transform the results of disordered regressions back to their original ordinal categories. Some effective strategies have been put forward, such as designing a class-label encoding matrix for the pairwise comparison, balancing samples, training classifiers, and predicting new samples. In numerical experiments, our algorithm (PairCode) is compared with the ordinal logistic regressions (LogisticOP) (Hu et al., IEEE Transactions on Knowledge and Data Engineering, 24(11), 2052–2064, 2012; Harrell 2015b), SVMOP (Gutiérrez et al., IEEE Transactions on Knowledge and Data Engineering, 28(1), 127–146, 2016; Leathart et al. 2016), SVORIM (Chu and Sathiya Keerthi, Neural Computation, 19(3), 792–815 2007; Gutiérrez et al., IEEE Transactions on Knowledge and Data Engineering, 28(1), 127–146, 2016), SVOREX (Chu and Sathiya Keerthi, Neural Computation, 19(3), 792–815 2007; Gutiérrez et al., IEEE Transactions on Knowledge and Data Engineering, 28(1), 127–146, 2016), and ELMOP (Deng et al., Neurocomputing, 74(1), 447–456, 2010; Gutiérrez et al., IEEE Transactions on Knowledge and Data Engineering, 28(1), 127–146, 2016). The results show that the PairCode algorithm performs better and is relatively stable as reflected by the correct classification rate (CCR), the mean absolute error (MAE), and the maximum MAE value (MMAE). However, the computing speed of the PairCode algorithm for classification is slightly slow and therefore warrants further study to improve the speed. [ABSTRACT FROM AUTHOR]

The performance of any speech based systems depends on the quality of input speech signals. The signal to noise ratio (SNR) is considered to be a measure of the quality of speech signal. This paper reports some analyses (based on experimental evaluations) that are focused on calculating the quality of the speech signal so as to improve the overall accuracy of the system. As compared to existing methods that are based on voice activity detection (VAD), the proposed method is based on glottal activity detection (GAD) to detect the speech and non-speech regions from the input speech signals. Literature reveals that the GAD provides better results than VAD under noisy data condition for the above mentioned task. The proposed method uses a filter with specified cut-off frequency to separate the noise components that are present in the speech activity region. After that, we calculate the SNR as the ratio of the total energy in the speech activity region to that of the non-speech regions. The comparative analyses with two state-of-the-art techniques, viz, National Institute of Standards and Technology (NIST) SNR tool and Waveform Amplitude Distribution Analysis (WADA) SNR algorithm suggest that under different data conditions the proposed method outperforms the existing ones. Since the proposed model depends on the signal processing techniques and does not require any classifier or model to be developed, therefore it is found to be computationally efficient as compared to other two methods. [ABSTRACT FROM AUTHOR]

Purpose: To compare the preoperative and postoperative measurements of optical low-coherence reflectometry (OLCR) biometry and assessment of its refractive predictability. Methods: A total of 114 eyes of 102 patients who underwent cataract treatment were prospectively examined. The axial length (AL), central corneal thickness (CCT), anterior chamber depth (ACD), lens thickness (LT), K (keratometry) 1, K2, K average (KAVE) and K astigmatic (KAST) values were recorded using Lenstar LS 900 (Haag-Streit, Koeniz, Switzerland) OLCR device. The IOL (intraocular lens) power was measured based on the SRK/T formula. The cases were divided into three subgroups according to AL (Group 1: AL < 22 mm, Group 2: 22 mm ≤ AL < 24 mm, Group 3: 24 mm ≤ AL). The mean absolute error (MAE) calculated for each eye. Results: The right eyes of 45 patients (44.1%), left eyes of 45 patients (44.1%), and both eyes of 12 patients (11.7%) were examined. The average AL in the preoperative period was 23.19 ± 1.01; it was 23.20 ± 0.99 in the postoperative period (p > 0.05). A significant deepening was detected in the postoperative ACD (preop 2.76 ± 0.38 mm, postop 3.81 ± 0.46 mm, p < 0.001). CCT was measured as 521.4 ± 36.3 µm in the preoperative period and as 530.8 ± 42.8 (p > 0.05) µm in the postoperative period. The average mean absolute error (MAE) was measured as 0.48 ± 0.41 D, whereas refractive error was − 0.081 ± 0.67 D. The MAE distribution of cases was found to be ≤ 1.5 D 109 (95.6%) eyes, and ≤ 2.0 D in 114 (100%) eyes. MAE values according to AL of the cases were calculated as 0.71 ± 0.83 D in group 1, 0.49 ± 0.43 D in group 2 and 0.41 ± 0.36 D in group 3 (p > 0.05). Conclusion: When the measurement and refractive results of the OLCR biometry were evaluated, it was observed that there was a very satisfactory result and a predictable device compatible with the current literature. The SRK/T formula, one of the new generation formulas, has shown high MAE and RE results in eyes with AL ≤ 22 mm, although not statistically significant. Other new generation formulas should be tried in these eyes. [ABSTRACT FROM AUTHOR]

This paper was aimed to address the problem of image-based human age estimation. It has the following main contributions. First, we provide a comparison of three hand-crafted image features and five deep convolutional neural networks (DCNNs). Secondly, we show that the use of pre-trained DCNNs as feature extractors can transfer the knowledge of DCNNs to new datasets and domains that were not necessarily addressed in the training phase. This is achieved by only retraining a shallow regressor over the deep features. Thirdly, we provide a cross-database evaluation involving biological and apparent ages. The paper shows that transfer learning allows the use of pre-trained DCNNs regardless of the type of ages (apparent or biological) that is adopted in DCNN training. The experiments are carried out on three public databases: MORPH, PAL, and Chalearn2016. [ABSTRACT FROM AUTHOR]

Abstract Background Curve fitting has been intensively used to model artery pressure waveform (APW). The modelling accuracy can greatly influence the calculation of APWs parameters that serve as quantitative measures for assessing the morphological characteristics of APWs. However, it is unclear which fitting function is more suitable for APW. In this paper, we compared the fitting accuracies of four types of fitting functions, including Raleigh function, double-exponential function, Gaussian function, and logarithmic normal function, in modeling radial artery pressure waveform (RAPW). Methods RAPWs were recorded from 24 healthy subjects in resting supine position. To perform curve fitting, 10 consecutive stable RAPWs for each subject were randomly selected and each waveform was fitted using three instances of the same fitting function. Results The mean absolute percentage errors (MAPE) of the fitting results were 5.89% ± 0.46% (standard deviation), 3.31% ± 0.22%, 2.25% ± 0.31%, and 1.49% ± 0.28% for Raleigh function, double-exponential function, Gaussian function, and logarithmic normal function, respectively. Their corresponding mean maximum residual errors were 23.71%, 17.83%, 6.11%, and 5.49%. Conclusions The performance of using Gaussian function and logarithmic normal function to model RAPW is comparable, and is better than that of using Raleigh function and double-exponential function. Graphical abstract Image 1 Highlights • The performances of four fitting functions were compared. • Two-Stage particle swarm optimizer (TSPSO) was used in this work. • Gaussian function and logarithmic normal function resulted in ideal accuracies. [ABSTRACT FROM AUTHOR]

Chamfering, a mask-driven technique, refers to a process of propagating local distances over an image to estimate a reference metric. Performance of the technique depends on the design of chamfer masks using cost functions. To date, most scholars have been using a mean absolute error and a mean squared error to formulate optimization problems for estimating weights in the chamfer masks. However, studies have shown that these optimization functions endure some potential weaknesses, including biasedness and sensitivity to outliers. Motivated by the weaknesses, the present work proposes an alternative difference function, RLog, that is unbiased, symmetrical, and robust. RLog takes the absolute logarithm of the relative accuracy of the estimated distance to compute optimal chamfer weights. Also, we have proposed an algorithm to map entries of the designed real-valued chamfer masks into integers. Analytical and experimental results demonstrate that chamfering based on our weights generate polygons and distance maps with lower errors. Methods and results of our work may be useful in robotics to address the matching problem. [ABSTRACT FROM AUTHOR]

Precipitation is the most discontinuous atmospheric parameter because of its temporal and spatial variability. Precipitation observations at automatic weather stations (AWSs) show different patterns over different time periods. This paper aims to reconstruct missing data by finding the time periods when precipitation patterns are similar, with a method called the intermittent sliding window period (ISWP) technique-a novel approach to reconstructing the majority of non-continuous missing real-time precipitation data. The ISWP technique is applied to a 1-yr precipitation dataset (January 2015 to January 2016), with a temporal resolution of 1 h, collected at 11 AWSs run by the Indian Meteorological Department in the capital region of Delhi. The acquired dataset has missing precipitation data amounting to 13.66%, of which 90.6% are reconstructed successfully. Furthermore, some traditional estimation algorithms are applied to the reconstructed dataset to estimate the remaining missing values on an hourly basis. The results show that the interpolation of the reconstructed dataset using the ISWP technique exhibits high quality compared with interpolation of the raw dataset. By adopting the ISWP technique, the root-mean-square errors (RMSEs) in the estimation of missing rainfall data-based on the arithmetic mean, multiple linear regression, linear regression, and moving average methods-are reduced by 4.2%, 55.47%, 19.44%, and 9.64%, respectively. However, adopting the ISWP technique with the inverse distance weighted method increases the RMSE by 0.07%, due to the fact that the reconstructed data add a more diverse relation to its neighboring AWSs. [ABSTRACT FROM AUTHOR]

Some supervised tasks are presented with a numerical output but decisions have to be made in a discrete, binarised, way, according to a particular cutoff. This binarised regression task is a very common situation that requires its own analysis, different from regression and classification-and ordinal regression. We first investigate the application cases in terms of the information about the distribution and range of the cutoffs and distinguish six possible scenarios, some of which are more common than others. Next, we study two basic approaches: the retraining approach, which discretises the training set whenever the cutoff is available and learns a new classifier from it, and the reframing approach, which learns a regression model and sets the cutoff when this is available during deployment. In order to assess the binarised regression task, we introduce context plots featuring error against cutoff. Two special cases are of interest, the $$ UCE $$ and $$ OCE $$ curves, showing that the area under the former is the mean absolute error and the latter is a new metric that is in between a ranking measure and a residual-based measure. A comprehensive evaluation of the retraining and reframing approaches is performed using a repository of binarised regression problems created on purpose, concluding that no method is clearly better than the other, except when the size of the training data is small. [ABSTRACT FROM AUTHOR]

In this paper, an attempt has been made to predict the rate of penetration (ROP) of rocks by incorporating thrust, revolutions per minute (rpm), flushing media and compressive strength of rocks using artificial neural network (ANN) technique. A three-layer feed-forward back-propagation neural network with 4-7-1 architecture was trained using 472 experimental data sets of sandstone, limestone, rock phosphate, dolomite, marble and quartz-chlorite-schist rocks. A total of 146 new data sets were used for the testing and comparison of the ROP by ANN. Multivariate regression analysis (MVRA) has also been done with same data sets of ANN. ANN and MVRA results were compared based on coefficient of determination (CoD) and mean absolute error (MAE) between experimental and predicted values of ROP. The coefficient of determination by ANN was 0.985, while coefficient of determination was 0.629 for rate of penetration. The mean absolute error (MAE) for rate of penetration by ANN was 0.3547, whereas MAE by MVRA was 1.7499. [ABSTRACT FROM AUTHOR]

Ground vibrations induced by blasting are one of the fundamental problems in the mining industry and may cause severe damage to structures and plants nearby. Therefore, a vibration control study plays an important role in the minimization of environmental effects of blasting in mines. In this paper, an attempt has been made to predict the peak particle velocity using support vector machine (SVM) by taking into consideration of maximum charge per delay and distance between blast face to monitoring point. To investigate the suitability of this approach, the predictions by SVM have been compared with conventional vibration predictor equations. Coefficient of determination (CoD) and mean absolute error were taken as a performance measure. [ABSTRACT FROM AUTHOR]

Three estimators of the proportion in a tail of the normal distribution are compared using the criteria of mean squared error and mean absolute error. The estimators that we compare are the maximum likelihood estimator, the minimum variance unbiased estimator, and an intuitive estimator that is frequently used in practice. The intuitive estimator is similar to the MLE but uses the usual unbiased estimator of σ rather than the MLE of σ. We show that the intuitive estimator has low efficiency, and for this reason it is not recommended. For very small p and for large p the MVUE has the highest efficiency. The MLE is best for moderate values of p. [ABSTRACT FROM AUTHOR]

This paper presents both estimation and simulation as optimization problems that differ in the optimization criteria, minimization of a local expected loss for estimation and reproduction of global statistics (semivariogram, histogram) for simulation. An intermediate approach is proposed whereby an initial random image is gradually modified using simulated annealing so as to better match both local and global constraints. The relative weights of the different constraints in the objective function allow the user to strike a balance between smoothness of the estimated map and reproduction of spatial variability by simulated maps. The procedure is illustrated using a synthetic dataset. The proposed approach is shown to enhance the influence of observations on neighboring simulated values, hence the final realizations appear to be “better conditioned” to the sample information. It also produces maps that are more accurate (smaller prediction error) than stochastic simulation ignoring local constraints, but not as accurate as E-type estimation. Flow simulation results show that accounting for local constraints yields, on average, smaller errors in production forecast than a smooth estimated map or a simulated map that reproduces only the histogram and semivariogram. The approach thus reduces the risk associated with the use of a single realization for forecasting and planning. [ABSTRACT FROM AUTHOR]

Multi-label sorting learning has been successful in many fields. It can not only express the complex semantic information of learning objects, but also present good generalization ability in dealing with complex things. This paper proposes age estimation algorithm of facial images based on multi-label sorting. This estimation algorithm is for the lack of facial age dataset, and it changes the traditional multi-valued classification method, simplified the problem of tedious steps to estimate age and shortened the time for model training. A series of experiments on two age datasets shows that the algorithm has achieved very good results in evaluating indicators, and these indicators include MAE (mean absolute error), CS (cumulative score), and convergence rate. When compared with some classic algorithms of age estimation, the efficiency and accuracy of the algorithm are verified. [ABSTRACT FROM AUTHOR]