Because of the complexity, nonlinearity, and volatility, stock market forecasting is either highly difficult or yields very unsatisfactory outcomes when utilizing traditional time series or machine learning techniques. To cope with this problem and improve the complex stock market’s prediction accuracy, we propose a new hybrid novel method that is based on a new version of EMD and a deep learning technique known as long-short memory (LSTM) network. The forecasting precision of the proposed hybrid ensemble method is evaluated using the KSE-100 index of the Pakistan Stock Exchange. Using a new version of EMD that uses the Akima spline interpolation technique instead of cubic spline interpolation, the noisy stock data are first divided into multiple components technically known as intrinsic mode functions (IMFs) varying from high to low frequency and a single monotone residue. The highly correlated sub-components are then used to build the LSTM network. By comparing the proposed hybrid model with a single LSTM and other ensemble models such as the support vector machine (SVM), Random Forest, and Decision Tree, its prediction performance is thoroughly evaluated. Three alternative statistical metrics, namely root means square error (RMSE), mean absolute error (MAE) and mean absolute percentage error (MAPE), are used to compare the aforementioned techniques. The empirical results show that the suggested hybrid Akima-EMD-LSTM model beats all other models taken into consideration for this study and is therefore recommended as an effective model for the prediction of non-stationary and nonlinear complex financial time series data.

The pore system in carbonates is complicated because of the associated biological and chemical activity. Secondary porosity, on the other hand, is the result of chemical reactions that occur during diagenetic processes. A thorough understanding of the carbonate pore system is essential to hydrocarbon prospecting. Porosity classification schemes are currently limited to accurately forecast the petrophysical parameters of different reservoirs with various origins and depositional environments. Although rock classification offers a way to describe lithofacies, it has no impact on the application of the poro-perm correlation. An outstanding example of pore complexity (both in terms of type and origin) may be found in the Central Luconia carbonate system (Malaysia), which has been altered by diagenetic processes. Using transmitted light microscopy, 32 high-resolution pictures were collected of each thin segment for quantitative examination. An FESEM picture and a petrographic study of thin sections were used to quantify the grains, matrix, cement, and macroporosity (pore types). Microporosity was determined by subtracting macroporosity from total porosity using a point-counting technique. Moldic porosity (macroporosity) was shown to be the predominant type of porosity in thin sections, whereas microporosity seems to account for 40 to 50% of the overall porosity. Carbonates from the Miocene have been shown to possess a substantial quantity of microporosity, making hydrocarbon estimate and production much more difficult. It might lead to a higher level of uncertainty in the estimation of hydrocarbon reserves if ignored. Existing porosity classifications cannot be used to better understand the poro-perm correlation because of the wide range of geological characteristics. However, by considering pore types and pore structures, which may be separated into macro- and microporosity, the classification can be enhanced. Microporosity identification and classification investigations have become a key problem in limestone reservoirs across the globe.

With recent advancement in computational biology, high throughput next generation sequencing technology has become a de facto standard technology for genes expression studies including DNAs, RNAs and proteins. As a promising technology, it has significant impact on medical sciences and genomic research. However, it generates several millions of short DNA and RNA sequences with several petabytes size in single run. In addition, the raw sequencing datasets such as RNAs are increasing exponentially leading to a big data analytics issue in computational biology. Due to the explosive growth of RNA sequences, the timely classification of RNAs sequence into piRNAs and non-piRNAs have become a challenging issue for traditional technology and conventional machine learning algorithms. Parallel and distributed computing models along with deep neural network have become a major computing platform for big data analytics now required in the field of computational biology. This paper presents a computational model based on parallel deep neural network for timely classification of large number of RNAs sequence into piRNAs and non-piRNAs, taking advantages of parallel and distributed computing platform. The performance of the proposed model was extensively evaluated using two-fold performance metrics. In the first fold, the performance of the proposed model was assessed using accuracy-based metrics such as accuracy, specificity, sensitivity and Matthew’s correlation coefficient. In the second fold, computational-based metrics such as computation times, speedup and scalability were observed. Moreover, initially the performance of the proposed model was assessed using real benchmark dataset and subsequently the performance was assessed using replicated benchmark dataset. The evaluation results in both cases showed that the proposed model improved computation speedup in order of magnitude in comparison with sequential approach without affected accuracy level.

This research provides the instructional exploration of analytic geometry pattern based on van Hiele thinking pattern, and the potential of GeoGebra effect on experimental group along with its nested group (high and low achievers) in comparison with control group in analytic geometry. To...

The importance of unsupervised clustering methods is well established in the statistics and machine learning literature. Many sophisticated unsupervised classification techniques have been made available to deal with a growing number of datasets. Due to its simplicity and efficiency in clustering a large dataset, the k-means clustering algorithm is still popular and widely used in the machine learning community. However, as with other clustering methods, it requires one to choose the balanced number of clusters in advance. This paper’s primary emphasis is to develop a novel method for finding the optimum number of clusters, k, using a data-driven approach. Taking into account the cluster symmetry property, the k-means algorithm is applied multiple times to a range of k values within which the balanced optimum k value is expected. This is based on the uniqueness and symmetrical nature among the centroid values for the clusters produced, and we chose the final k value as the one for which symmetry is observed. We evaluated the proposed algorithm’s performance on different simulated datasets with controlled parameters and also on real datasets taken from the UCI machine learning repository. We also evaluated the performance of the proposed method with the aim of remote sensing, such as in deforestation and urbanization, using satellite images of the Islamabad region in Pakistan, taken from the Sentinel-2B satellite of the United States Geological Survey. From the experimental results and real data analysis, it is concluded that the proposed algorithm has better accuracy and minimum root mean square error than the existing methods.

Ensemble methods based on $k$ -NN models minimise the effect of outliers in a training dataset by searching groups of the $k$ closest data points to estimate the response of an unseen observation. However, traditional $k$ -NN based ensemble methods use the arithmetic mean of the training points’ responses for estimation which has several weaknesses. Traditional $k$ -NN based models are also adversely affected by the presence of non-informative features in the data. This paper suggests a novel ensemble procedure consisting of a class of base $k$ -NN models each constructed on a bootstrap sample drawn from the training dataset with a random subset of features. In the $k$ nearest neighbours determined by each $k$ -NN model, stepwise regression is fitted to predict the test point. The final estimate of the target observation is then obtained by averaging the estimates from all the models in the ensemble. The proposed method is compared with some other state-of-the-art procedures on 16 benchmark datasets in terms of coefficient of determination ( $R^{2}$ ), Pearson’s product-moment correlation coefficient ( $r$ ), mean square predicted error ( $MSPE$ ), root mean squared error ( $RMSE$ ) and mean absolute error ( $MAE$ ) as performance metrics. Furthermore, boxplots of the results are also constructed. The suggested ensemble procedure has outperformed the other procedures on almost all the datasets. The efficacy of the method has also been verified by assessing the proposed method in comparison with the other methods by adding non-informative features to the datasets considered. The results reveal that the proposed method is more robust to the issue of non-informative features in the data as compared to the rest of the methods.