Electricity, a fundamental commodity, must be generated as per required utilization which cannot be stored at large scales. The production cost heavily depends upon the source such as hydroelectric power plants, petroleum products, nuclear and wind energy. Besides overproduction and underproduction, electricity demand is driven by metrological parameters, economic and industrial activities. Therefore, the region specific accurate electric load forecasting can help to effectively manage, plan, and schedule appropriate low cost electricity generation units to decrease per unit cost and provision of on time energy for maximum financial benefits. Machine learning (ML) offers different supervised learning algorithms including multiple linear regression, support vector regressors with different kernels, k-nearest neighbors, Random Forest and AdaBoost to forecast the time series data, but the performance of these algorithms is data dependent. It is vitally important to consider correlated metrological parameters of the specific region for accurate prediction of electricity load demand using ML based forecasting models to minimize the price per unit. In this study, an algorithm is proposed to select least cost electric load forecasting model (lcELFM) using correlated meteorological parameters. We developed least cost forecasting models by minimizing root mean squared error, mean absolute error, and mean absolute percentage error. For simulations, the recorded electricity demand data is taken from a substation of water and power development authority Muzaffarabad city from 1st January 2014 to 31st December 2015. The meteorological time series data are obtained from the substation of Pakistan meteorological department for the same period and same region. Empirical results demonstrate the robustness of the proposed algorithm to select lcELFM. Moreover, SVR (Radial) based electric load forecasting model proves to be the robust model when built using correlated features (temperature and dew point) for the said region and in turn can save up to PKR 0.313 million daily.

Twitter sentiment analysis is a challenging problem in natural language processing. For this purpose, supervised learning techniques have mostly been employed, which require labeled data for training. However, it is very time consuming to label datasets of large size. To address this issue, unsupervised learning techniques such as clustering can be used. In this study, we explore the possibility of using hierarchical clustering for twitter sentiment analysis. Three hierarchical-clustering techniques, namely single linkage (SL), complete linkage (CL) and average linkage (AL), are examined. A cooperative framework of SL, CL and AL is built to select the optimal cluster for tweets wherein the notion of optimalcluster selection is operationalized using majority voting. The hierarchical clustering techniques are also compared with k-means and two state-of-the-art classifiers (SVM and Naïve Bayes). The performance of clustering and classification is measured in terms of accuracy and time efficiency. The experimental results indicate that cooperative clustering based on majority voting approach is robust in terms of good quality clusters with tradeoff of poor time efficiency. The results also suggest that the accuracy of the proposed clustering framework is comparable to classifiers which is encouraging.

Twitter sentiment analysis is a challenging task that involves various preprocessing steps including dimensionality reduction. Dimensionality reduction helps ensure low computational complexity and performance improvement during the classification process. In Twitter data, each tweet has feature values which may or may not reflect a person’s response. Therefore, a large number of sparse data points are generated when tweets are represented as feature matrix, eventually increasing computational overheads and error rates in Twitter sentiment analysis. This study proposes a novel preprocessing technique called class association and attribute relevancy based imputation algorithm (CAARIA) to reduce the Twitter data size. CAARIA achieves the dimensionality reduction goal by imputing those tweets that belong to the same class and also share useful information. The performance of two classifiers (Naïve Bayes and support vector machines) is evaluated on three Twitter datasets in terms of classification accuracy, measured as area under curve, and time efficiency. CAARIA is also compared against two widely used feature selection (dimensionality reduction) techniques, information gain (IG) and Pearsonb’s correlation (PC). The findings reveal that CAARIA outperforms IG and PC in terms of classification accuracy and time efficiency. These results suggest that CAARIA is a robust data preprocessing technique for the classification task.

The prediction of atmospheric particulate matter (APM) concentration is essential to reduce adverse effects on human health and to enforce emission restrictions. The dynamics of APM are inherently nonlinear and chaotic. Phase space reconstruction (PSR) is one of the widely used methods for chaotic time series analysis. The APM mass concentrations are an outcome of complex anthropogenic contributors evolving with time, which may operate on multiple time scales. Thus, the traditional single-variable PSR-based prediction algorithm in which data points of last embedding dimension are used as a target set may fail to account for multiple time scales inherent in APM concentrations. To address this issue, we propose a novel PSR-based scientific solution that accounts for the information contained at multiple time scales. Different machine learning algorithms are used to evaluate the performance of the proposed and traditional PSR techniques for predicting mass concentrations of particulate matter up to 2.5 micron (PM_2.5), up to 10 micron (PM_10.0), and ratio of PM_2.5/PM_10.0. Hourly time series data of PM_2.5 and PM_10.0 mass concentrations are collected from January 2014 to September 2015 at the Masfalah air quality monitoring station (couple of kilometers from the Holy Mosque in Makkah, Saudi Arabia). The performances of various learning algorithms are evaluated using RMSE and MAE. The results demonstrated that prediction error of all the machine learning techniques is smaller for the proposed PSR approach compared to traditional approach. For PM_2.5, FFNN leads to best results (both RMSE and MAE 0.04 μgm⁻³), followed by SVR-L (RMSE 0.01 μgm⁻³ and MAE 0.09 μgm⁻³) and RF (RMSE 1.27 μgm⁻³ and MAE 0.86 μgm⁻³). For PM_10.0, SVR-L leads to best results (both RMSE and MAE 0.06 μgm⁻³), followed by FFNN (RMSE 0.13 μgm⁻³ and MAE 0.09 μgm⁻³) and RF (RMSE 1.60 μgm⁻³ and MAE 1.16 μgm⁻³). For PM_2.5/PM_10.0, FFNN is the best and accurate method for prediction (0.001 for both RMSE and MAE), followed by RF (0.02 for both RMSE and MAE) and SVR-L (RMSE 0.05 μgm⁻³ and MAE 0.04).

Machine learning (ML) offers several supervised learning algorithms to build classifiers for developing accurate decision support systems. However, the selection of robust classifier for reliable decision making in healthcare domain is three-fold: accuracy, refraining for low confidence decisions, and the cost of decisions. In the field of medical science, there are costs associated with the incorrect and the refraining from decisions, which can have negative implications in devising adequate therapeutic interventions. For example, it may be life threating if a cancer patient is declared as healthy one (misclassification cost) or decision remains pending for some time (rejection cost). In this work we proposed the concept of Accuracy Rejection Normalized-Cost Curves (ARNCCs), which is an extension of Accuracy Rejection Curves (ARCs); a three-dimensional visualization technique to demonstrate the strengths and weaknesses of classification algorithms over different rejection regions and normalized-cost (NC) to select the robust classifier. ARNCCs method holds ARCs plot on two dimensions, in addition it computes NC at third dimension against ratio of false positive costs and ratio of rejection costs obtained at different rejection rates. The proposed three-dimensional graphs have the potential to answer a variety of questions regarding accuracy, rejection rate and NC of a classifier. Six publicly available cancer datasets (four breast cancer and two lung cancer) having clinical parameters obtained from ML repository of University of California, Irvine (UCI) were used to assess the performance of proposed ARNCCs in this study. Empirical results show that ARNCCs provide broad range of decisions to choose the desired parameters (accuracy, rejection rate and NC) for further necessary actions as compared to traditional ARCs method. ARNCCs framework has the ability to more logically compare the performances of classification algorithms in terms of accuracy, rejection rate and NC based scenarios.

Computer-aided decision support systems (DSSs) are becoming popular in a variety of professions. Notably, medical DSSs assist healthcare professionals (decision makers) choose the optimal course of action (decisions) while treating patients. Such systems help decision-makers in situations when there is uncertainty in manual decisions due to lack of information or expertise. Choosing a suitable learning algorithm in a DSS is essential and affects its performance. Among machine learning (ML) algorithms, artificial neural networks (ANNs) are considered the most suitable framework for many classification tasks. In healthcare, an ML-based prediction system/DSS employs data (genetic profile or clinical characteristics) and learning algorithms to forecast target values, which may give promising results. However, improving prediction accuracy is a crucial step in making informed decisions. One can apply various preprocessing methods (cross validation, feature selection, bagging, boosting, etc.) to achieve this. For complex classification tasks like cancer, decision-makers can utilize the hybridization of classifiers to increase prediction accuracy. The presented study investigates the possibilities of improvements in the design of hybridized systems for DSSs to assist healthcare professionals in robust decision-making before, during, and after cancer diagnosis. Since the network weights and the activation functions are the two crucial elements in the learning process of an ANN, this study is organized to investigates the improvement in the hybrid system by selecting suitable features from gene expression microarray data and using these features to compute the more realistic initial weights instead of using random guesses as initial weights for ANN. The use of the proposed framework gives promising results (upto 6.67% gain in accuracy when compared to previous study [19] (Table-V) while 10.43% increase in accuracy when compared to conventional ML classifiers (Table-IV)).