Optimal Deep Learning LSTM Model for Electric Load Forecasting using Feature Selection and Genetic Algorithm: Comparison with Machine Learning Approaches †

Optimal features selection in the high dimensional data based on robust technique: Application to different health database

Bio-informatics and gene expression analysis face major hurdles when dealing with high-dimensional data, where the number of variables or genes much outweighs the number of samples. These difficulties are exacerbated, particularly in microarray data processing, by redundant genes that do not significantly contribute to the response variable. To address this issue, gene selection emerges as a feasible method for identifying the most important genes, hence reducing the generalization error of classification algorithms. This paper introduces a new hybrid approach for gene selection by combining the Signal-to-Noise Ratio (SNR) score with the robust Mood median test. The Mood median test is beneficial for reducing the impact of outliers in non-normal or skewed data since it may successfully identify genes with significant changes across groups. The SNR score measures the significance of a gene's classification by comparing the gap between class means and within-class variability. By integrating both of these approaches, the suggested approach aims to find genes that are significant for classification tasks. The major objective of this study is to evaluate the effectiveness of this combination approach in choosing the optimal genes. A significant P-value is consistently identified for each gene using the Mood median test and the SNR score. By dividing the SNR value of each gene by its significant P-value, the Md score is calculated. Genes with a high signal-to-noise ratio (SNR) have been considered favorable due to their minimal noise influence and significant classification importance. To verify the effectiveness of the selected genes, the study utilizes two dependable classification techniques: Random Forest and K-Nearest Neighbors (KNN). These algorithms were chosen due to their track record of successfully completing categorization-related tasks. The performance of the selected genes is evaluated using two metrics: error reduction and classification accuracy. These metrics offer an in-depth assessment of how well the selected genes improve classification accuracy and consistency. According to the findings, the hybrid approach put out here outperforms conventional gene selection methods in high-dimensional datasets and has lower classification error rates. There are considerable improvements in classification accuracy and error reduction when specific genes are exposed to the Random Forest and KNN classifiers. The outcomes demonstrate how this hybrid technique might be a helpful tool to improve gene selection processes in bioinformatics.

Integration of thermal energy storage for sustainable energy hubs in the forest industry: A comprehensive analysis of cost, thermodynamic efficiency, and availability

Thermal energy storage (TES) offers a practical solution for reducing industrial operation costs by load-shifting heat demands within industrial processes. In the integrated Thermomechanical pulping process, TES systems within the Energy Hub can provide heat for the paper machine, aiming to minimize electricity costs during peak hours. This strategic use of TES technology ensures more cost-effective and efficient energy consumption management, leading to overall operational savings. This research presents a novel method for optimizing the design and operation of an Energy Hub with TES in the forest industry. The proposed approach for the optimal design involves a comprehensive analysis of the dynamic efficiency, reliability, and availability of system components. The Energy Hub comprises energy conversion technologies such as an electric boiler and a steam generator heat pump. The study examines how the reliability of the industrial Energy Hub system affects operational costs and analyzes the impact of the maximum capacities of its components on system reliability. The method identifies the optimal design point for maximizing system reliability benefits. To optimize the TES system's charging/discharging schedule, an advanced predictive method using time series prediction models, including LSTM (Long Short-Term Memory) and GRU (Gated Recurrent Unit), has been developed to forecast average daily electricity prices. The results highlight significant benefits from the optimal operation of TES integrated with Energy Hubs, demonstrating a 4.5-6 percent reduction in system operation costs depending on the reference year. Optimizing the Energy Hub design improves system availability, reducing operation costs due to unsupplied demand penalty costs. The system's peak availability can reach 98 %, with a maximum heat pump capacity of 2 MW and an electric boiler capacity of 3.4 MW. The GRU method showed superior accuracy in predicting electricity prices compared to LSTM, indicating its potential as a reliable electricity price predictor within the system.

Leveraging electrocardiography signals for deep learning-driven cardiovascular disease classification model

Electrocardiography (ECG) is the most non-invasive diagnostic tool for cardiovascular diseases (CVDs). Automatic analysis of ECG signals assists in accurately and rapidly detecting life-threatening arrhythmias like atrioventricular blockage, atrial fibrillation, ventricular tachycardia, etc. The ECG recognition models need to utilize algorithms to detect various kinds of waveforms in the ECG and identify complicated relationships over time. However, the high variability of wave morphology among patients and noise are challenging issues. Physicians frequently utilize automated ECG abnormality recognition models to classify long-term ECG signals. Recently, deep learning (DL) models can be used to achieve enhanced ECG recognition accuracy in the healthcare decision making system. In this aspect, this study introduces an automated DL enabled ECG signal recognition (ADL-ECGSR) technique for CVD detection and classification. The ADL-ECGSR technique employs three most important subprocesses: pre-processed, feature extraction, parameter tuning, and classification. Besides, the ADL-ECGSR technique involves the design of a bidirectional long short-term memory (BiLSTM) based feature extractor, and the Adamax optimizer is utilized to optimize the trained method of the BiLSTM model. Finally, the dragonfly algorithm (DFA) with a stacked sparse autoencoder (SSAE) module is applied to recognize and classify EEG signals. An extensive range of simulations occur on benchmark PTB-XL datasets to validate the enhanced ECG recognition efficiency. The comparative analysis of the ADL-ECGSR methodology showed a remarkable performance of 91.24 % on the existing methods.

Identification of Time-Series Pattern Marker in Its Application to Mortality Analysis of Pneumonia Patients in Intensive Care Unit

Electronic Health Records (EHRs) are a significant source of big data used to track health variables over time. The analysis of EHR data can uncover medical markers or risk factors, aiding in the diagnosis and monitoring of diseases. We introduce a novel method for identifying markers with various temporal trend patterns, including monotonic and fluctuating trends, using machine learning models such as Long Short-Term Memory (LSTM). By applying our method to pneumonia patients in the intensive care unit using the MIMIC-III dataset, we identified markers exhibiting both monotonic and fluctuating trends. Specifically, monotonic markers such as red cell distribution width, urea nitrogen, creatinine, calcium, morphine sulfate, bicarbonate, sodium, troponin T, albumin, and prothrombin time were more frequently observed in the mortality group compared to the recovery group throughout the 10-day period before discharge. Conversely, fluctuating trend markers such as dextrose in sterile water, polystyrene sulfonate, free calcium, and glucose were more frequently observed in the mortality group as the discharge date approached. Our study presents a method for detecting time-series pattern markers in EHR data that respond differently according to disease progression. These markers can contribute to monitoring disease progression and enable stage-specific treatment, thereby advancing precision medicine.

Advanced convolutional neural network modeling for fuel cell system optimization and efficiency in methane, methanol, and diesel reforming

Fuel cell systems (FCSs) have been widely used for niche applications in the market. Furthermore, the research community has worked on using FCSs for different sectors, such as transportation, stationary power generation, marine and maritime, aerospace, military and defense, telecommunications, and material handling. The reformation of various fuels, such as methanol, methane, and diesel can be utilized to generate hydrogen for FCSs. This study introduces an advanced convolutional neural network (CNN) model designed to accurately forecast hydrogen yield and carbon monoxide volume percentages during the reformation processes of methane, methanol, and diesel. Moreover, the CNN model has been tailored to accurately estimate methane conversion rates in methane reforming processes. The proposed CNN models are created by combining the 3D-CNN and 2D-CNN models. The Keras Tuner approach in Python is employed in this study to find the ideal values for different hyperparameters such as batch size, learning rate, time steps, and optimization method selection. The accuracy of the proposed CNN model is evaluated by using the root mean square error (RMSE), mean absolute percentage error (MAE), mean absolute error (MAE), and R2. The results indicate that the proposed CNN model is better than other artificial intelligence (AI) techniques and standard CNN for performance estimation of reforming processes of methane, diesel, and methanol. The results also show that the suggested CNN model can be used to accurately estimate critical output parameters for reforming various fuels. The proposed method performs better in CO prediction than the support vector machine (SVM), with an R2 of 0.9989 against 0.9827. This novel methodology not only improves performance estimation for reforming processes but also provides a valuable tool for accurately estimating output parameters across various fuel types.

Predicting quantum emitter fluctuations with time-series forecasting models

2D materials have important fundamental properties allowing for their use in many potential applications, including quantum computing. Various Van der Waals materials, including Tungsten disulfide (WS2), have been employed to showcase attractive device applications such as light emitting diodes, lasers and optical modulators. To maximize the utility and value of integrated quantum photonics, the wavelength, polarization and intensity of the photons from a quantum emission (QE) must be stable. However, random variation of emission energy, caused by the inhomogeneity in the local environment, is a major challenge for all solid-state single photon emitters. In this work, we assess the random nature of the quantum fluctuations, and we present time series forecasting deep learning models to analyse and predict QE fluctuations for the first time. Our trained models can roughly follow the actual trend of the data and, under certain data processing conditions, can predict peaks and dips of the fluctuations. The ability to anticipate these fluctuations will allow physicists to harness quantum fluctuation characteristics to develop novel scientific advances in quantum computing that will greatly benefit quantum technologies.

An empirical analysis of the relationship among price, demand and CO2 emissions in the Spanish electricity market

C O 2 emissions play a crucial role in international politics. Countries enter into agreements to reduce the amount of pollution emitted into the atmosphere. Energy generation is one of the main contributors to pollution and is generally considered the main cause of climate change. Despite the interest in reducing C O 2 emissions, few studies have focused on investigating energy pricing technologies. This article analyzes the technologies used to meet the demand for electricity from 2016 to 2021. The analysis is based on data provided by the Spanish Electricity System regulator, using statistical and clustering techniques. The objective is to establish the relationship between the level of pollution of electricity generation technologies and the hourly price and demand. Overall, the results suggest that there are two distinct periods with respect to the technologies used in the studied years, with a trend toward the use of cleaner technologies and a decrease in power generation using fossil fuels. It is also surprising that in the years 2016 to 2018, the most polluting technologies offered the cheapest prices.

Identification of influential weather parameters and seasonal drought prediction in Bangladesh using machine learning algorithm

Droughts pose a severe environmental risk in countries that rely heavily on agriculture, resulting in heightened levels of concern regarding food security and livelihood enhancement. Bangladesh is highly susceptible to environmental hazards, with droughts further exacerbating the precarious situation for its 170 million inhabitants. Therefore, we are endeavouring to highlight the identification of the relative importance of climatic attributes and the estimation of the seasonal intensity and frequency of droughts in Bangladesh. With a period of forty years (1981-2020) of weather data, sophisticated machine learning (ML) methods were employed to classify 35 agroclimatic regions into dry or wet conditions using nine weather parameters, as determined by the Standardized Precipitation Evapotranspiration Index (SPEI). Out of 24 ML algorithms, the four best ML methods, ranger, bagEarth, support vector machine, and random forest (RF) have been identified for the prediction of multi-scale drought indices. The RF classifier and the Boruta algorithms shows that water balance, precipitation, maximum and minimum temperature have a higher influence on drought intensity and occurrence across Bangladesh. The trend of spatio-temporal analysis indicates, drought intensity has decreased over time, but return time has increased. There was significant variation in changing the spatial nature of drought intensity. Spatially, the drought intensity shifted from the northern to central and southern zones of Bangladesh, which had an adverse impact on crop production and the livelihood of rural and urban households. So, this precise study has important implications for the understanding of drought prediction and how to best mitigate its impacts. Additionally, the study emphasizes the need for better collaboration between relevant stakeholders, such as policymakers, researchers, communities, and local actors, to develop effective adaptation strategies and increase monitoring of weather conditions for the meticulous management of droughts in Bangladesh.

Studies on predicting soil moisture levels at Andhra Loyola College, India, using SARIMA and LSTM models

Time series modeling is a way to predict future values by examining temporal data. The present study analyzes the monthly mean soil moisture data at various depths: surface, profile, and root soil moisture, spanning from 1981 to 2022. The analysis employs two distinct approaches: the statistical seasonal autoregressive integrated moving average (SARIMA) and a deep learning long short-term memory (LSTM). The models are trained on a data set, covering the period from 1981 to 2021, acquired from the agricultural site at Andhra Loyola College in Vijayawada, Andhra Pradesh, India. Subsequently, the data from 2021 to 2022 is reserved for testing purposes. The study provides comprehensive insights into the design of both SARIMA and LSTM models, along with an evaluation of their performance using established error metrics such as the model mean absolute percentage error (MAPE), mean absolute error (MAE), and root mean squared error (RMSE). In the context of surface soil moisture prediction, the LSTM model demonstrates superior performance compared to SARIMA. Specifically, LSTM achieves a notably lower MAPE of 0.0615 in contrast to SARIMA's 0.1541, a reduced MAE of 0.0316 compared to 0.0871, and a diminished RMSE of 0.0412 as opposed to 0.1021. This pattern of enhanced accuracy persists across profile and root soil moisture predictions, further establishing LSTM's supremacy in predictive capability across diverse soil moisture levels.

Daily flow prediction of the Huayuankou hydrometeorological station based on the coupled CEEMDAN-SE-BiLSTM model

Enhancing flood forecasting accuracy, promoting rational water resource utilization and management, and mitigating river disasters all hinge on the crucial role of improving the accuracy of daily flow prediction. The coupled model of Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN), Sample Entropy (SE), and Bidirectional Long Short-Term Memory (BiLSTM) demonstrates higher stability when faced with nonlinear and non-stationary data, stronger adaptability to various types and lengths of time series data by utilizing sample entropy, and significant advantages in processing sequential data through the BiLSTM network. In this study, in the context of predicting daily flow at the Huayuankou Hydrological Station in the lower reaches of the Yellow River, a coupled CEEMDAN-SE-BiLSTM model was developed and utilized. The results showed that the CEEMDAN-SE-BiLSTM coupled model achieved the utmost accuracy in prediction and optimal fitting performance. Compared with the CEEMDAN-SE-LSTM, CEEMDAN-BiLSTM, and BiLSTM coupled models, the root mean square error (RMSE) of this model is reduced by 42.77, 182.02, and 193.71, respectively; the mean absolute error (MAE) is reduced by 37.62, 118.60, and 126.67, respectively; and the coefficient of determination (R2) is increased by 0.0208, 0.1265, 0.1381.

Surface Roughness Prediction in Ultra-Precision Milling: An Extreme Learning Machine Method with Data Fusion

This paper pioneers the use of the extreme learning machine (ELM) approach for surface roughness prediction in ultra-precision milling, leveraging the excellent fitting ability with small datasets and the fast learning speed of the extreme learning machine method. By providing abundant machining information, the machining parameters and force signal data are fused on the feature level to further improve ELM prediction accuracy. An ultra-precision milling experiment was designed and conducted to verify our proposed data-fusion-based ELM method. The results show that the ELM with data fusion outperforms other state-of-art methods in surface roughness prediction. It achieves an impressively low mean absolute percentage error of 1.6% while requiring a mere 18 s for model training.

Utilizing convolutional neural networks to classify monkeypox skin lesions

Monkeypox is a rare viral disease that can cause severe illness in humans, presenting with skin lesions and rashes. However, accurately diagnosing monkeypox based on visual inspection of the lesions can be challenging and time-consuming, especially in resource-limited settings where laboratory tests may not be available. In recent years, deep learning methods, particularly Convolutional Neural Networks (CNNs), have shown great potential in image recognition and classification tasks. To this end, this study proposes an approach using CNNs to classify monkeypox skin lesions. Additionally, the study optimized the CNN model using the Grey Wolf Optimizer (GWO) algorithm, resulting in a significant improvement in accuracy, precision, recall, F1-score, and AUC compared to the non-optimized model. The GWO optimization strategy can enhance the performance of CNN models on similar tasks. The optimized model achieved an impressive accuracy of 95.3%, indicating that the GWO optimizer has improved the model's ability to discriminate between positive and negative classes. The proposed approach has several potential benefits for improving the accuracy and efficiency of monkeypox diagnosis and surveillance. It could enable faster and more accurate diagnosis of monkeypox skin lesions, leading to earlier detection and better patient outcomes. Furthermore, the approach could have crucial public health implications for controlling and preventing monkeypox outbreaks. Overall, this study offers a novel and highly effective approach for diagnosing monkeypox, which could have significant real-world applications.

Diabetes Detection Models in Mexican Patients by Combining Machine Learning Algorithms and Feature Selection Techniques for Clinical and Paraclinical Attributes: A Comparative Evaluation

The development of medical diagnostic models to support healthcare professionals has witnessed remarkable growth in recent years. Among the prevalent health conditions affecting the global population, diabetes stands out as a significant concern. In the domain of diabetes diagnosis, machine learning algorithms have been widely explored for generating disease detection models, leveraging diverse datasets primarily derived from clinical studies. The performance of these models heavily relies on the selection of the classifier algorithm and the quality of the dataset. Therefore, optimizing the input data by selecting relevant features becomes essential for accurate classification. This research presents a comprehensive investigation into diabetes detection models by integrating two feature selection techniques: the Akaike information criterion and genetic algorithms. These techniques are combined with six prominent classifier algorithms, including support vector machine, random forest, k-nearest neighbor, gradient boosting, extra trees, and naive Bayes. By leveraging clinical and paraclinical features, the generated models are evaluated and compared to existing approaches. The results demonstrate superior performance, surpassing accuracies of 94%. Furthermore, the use of feature selection techniques allows for working with a reduced dataset. The significance of feature selection is underscored in this study, showcasing its pivotal role in enhancing the performance of diabetes detection models. By judiciously selecting relevant features, this approach contributes to the advancement of medical diagnostic capabilities and empowers healthcare professionals in making informed decisions regarding diabetes diagnosis and treatment.

A Novel LSTM-Based Machine Learning Model for Predicting the Activity of Food Protein-Derived Antihypertensive Peptides

Food protein-derived antihypertensive peptides are a representative type of bioactive peptides. Several models based on partial least squares regression have been constructed to delineate the relationship between the structure and activity of the peptides. Machine-learning-based models have been applied in broad areas, which also indicates their potential to be incorporated into the field of bioactive peptides. In this study, a long short-term memory (LSTM) algorithm-based deep learning model was constructed, which could predict the IC₅₀ value of the peptide in inhibiting ACE activity. In addition to the test dataset, the model was also validated using randomly synthesized peptides. The LSTM-based model constructed in this study provides an efficient and simplified method for screening antihypertensive peptides from food proteins.

Artificial intelligence for waste management in smart cities: a review

The rising amount of waste generated worldwide is inducing issues of pollution, waste management, and recycling, calling for new strategies to improve the waste ecosystem, such as the use of artificial intelligence. Here, we review the application of artificial intelligence in waste-to-energy, smart bins, waste-sorting robots, waste generation models, waste monitoring and tracking, plastic pyrolysis, distinguishing fossil and modern materials, logistics, disposal, illegal dumping, resource recovery, smart cities, process efficiency, cost savings, and improving public health. Using artificial intelligence in waste logistics can reduce transportation distance by up to 36.8%, cost savings by up to 13.35%, and time savings by up to 28.22%. Artificial intelligence allows for identifying and sorting waste with an accuracy ranging from 72.8 to 99.95%. Artificial intelligence combined with chemical analysis improves waste pyrolysis, carbon emission estimation, and energy conversion. We also explain how efficiency can be increased and costs can be reduced by artificial intelligence in waste management systems for smart cities.

Forecasting of stage-discharge in a non-perennial river using machine learning with gamma test

Knowledge of the stage-discharge rating curve is useful in designing and planning flood warnings; thus, developing a reliable stage-discharge rating curve is a fundamental and crucial component of water resource system engineering. Since the continuous measurement is often impossible, the stage-discharge relationship is generally used in natural streams to estimate discharge. This paper aims to optimize the rating curve using a generalized reduced gradient (GRG) solver and the test the accuracy and applicability of the hybridized linear regression (LR) with other machine learning techniques, namely, linear regression-random subspace (LR-RSS), linear regression-reduced error pruning tree (LR-REPTree), linear regression-support vector machine (LR-SVM) and linear regression-M5 pruned (LR-M5P) models. An application of these hybrid models was performed and test to modeling the Gaula Barrage stage-discharge problem. For this, 12-year historical stage-discharge data were collected and analyzed. The 12-year historical daily flow data (m³/s) and stage (m) from during the monsoon season, i.e., June to October only from 03/06/2007 to 31/10/2018, were used for discharge simulation. The best suitable combination of input variables for LR, LR-RSS, LR-REPTree, LR-SVM, and LR-M5P models was identified and decided using the gamma test. GRG-based rating curve equations were found to be as effective and more accurate as conventional rating curve equations. The outcomes from GRG, LR, LR-RSS, LR-REPTree, LR-SVM, and LR-M5P models were compared to observed values of daily discharge based on Nash Sutcliffe model efficiency coefficient (NSE), Willmott Index of Agreement (d), Kling-Gupta efficiency (KGE), mean absolute error (MAE), mean bias error (MBE), relative bias in percent (RE), root mean square error (RMSE) Pearson correlation coefficient (PCC) and coefficient of determination (R²). The LR-REPTree model (combination 1: NSE = 0.993, d = 0.998, KGE = 0.987, PCC(r) = 0.997, and R² = 0.994 and minimum value of RMSE = 0.109, MAE = 0.041, MBE = -0.010 and RE = -0.1%; combination 2; NSE = 0.941, d = 0.984, KGE = 0. 923, PCC(r) = 0. 973, and R² = 0. 947 and minimum value of RMSE = 0. 331, MAE = 0.143, MBE = -0.089 and RE = -0.9%) performed superior to the GRG, LR, LR-RSS, LR-SVM, and LR-M5P models in all input combinations during the testing period. It was also noticed that the performance of the alone LR and its hybrid models (i.e., LR-RSS, LR-REPTree, LR-SVM, and LR-M5P) was better than the conventional stage-discharge rating curve, including the GRG method.

Interrelationships between urban travel demand and electricity consumption: a deep learning approach

The analysis of infrastructure use data in relation to other components of the infrastructure can help better understand the interrelationships between infrastructures to eventually enhance their sustainability and resilience. In this study, we focus on electricity consumption and travel demand. In short, the premise is that when people are in buildings consuming electricity, they are not generating traffic on roads, and vice versa, hence the presence of interrelationships. We use Long Short Term Memory (LSTM) networks to model electricity consumption patterns of zip codes based on the traffic volume of the same zip code and nearby zip codes. For this, we merge two datasets for November 2017 in Chicago: (1) aggregated electricity use data in 30-min intervals within the city of Chicago and (2) traffic volume data captured on the Chicago expressway network. Four analyses are conducted to identify interrelationships: (a) correlation between two time series, (b) temporal relationships, (c) spatial relationships, and (d) prediction of electricity consumption based on the total traffic volume. Overall, from over 250 models, we identify and discuss complex interrelationships between travel demand and electricity consumption. We also analyze and discuss how and why model performance varies across Chicago.

An efficient and robust Phonocardiography (PCG)-based Valvular Heart Diseases (VHD) detection framework using Vision Transformer (ViT)

BACKGROUND AND OBJECTIVES

Valvular heart diseases (VHDs) are one of the dominant causes of cardiovascular abnormalities that have been associated with high mortality rates globally. Rapid and accurate diagnosis of the early stage of VHD based on cardiac phonocardiogram (PCG) signal is critical that allows for optimum medication and reduction of mortality rate.

METHODS

To this end, the current study proposes novel deep learning (DL)-based high-performance VHD detection frameworks that are relatively simpler in terms of network structures, yet effective for accurately detecting multiple VHDs. We present three different frameworks considering both 1D and 2D PCG raw signals. For 1D PCG, Mel frequency cepstral coefficients (MFCC) and linear prediction cepstral coefficients (LPCC) features, whereas, for 2D PCG, various deep convolutional neural networks (D-CNNs) features are extracted. Additionally, nature/bio-inspired algorithms (NIA/BIA) including particle swarm optimization (PSO) and genetic algorithm (GA) have been utilized for automatic and efficient feature selection directly from the raw PCG signal. To further improve the performance of the classifier, vision transformer (ViT) has been implemented levering the self-attention mechanism on the time frequency representation (TFR) of 2D PCG signal. Our extensive study presents a comparative performance analysis and the scope of enhancement for the combination of different descriptors, classifiers, and feature selection algorithms.

MAIN RESULTS

Among all classifiers, ViT provides the best performance by achieving mean average accuracy A_cc of 99.90 % and F1-score of 99.95 % outperforming current state-of-the-art VHD classification models.

CONCLUSIONS

The present research provides a robust and efficient DL-based end-to-end PCG signal classification framework for designing a automated high-performance VHD diagnosis system.

An Application of Machine Learning to Logistics Performance Prediction: An Economics Attribute-Based of Collective Instance

In this work, a machine learning application was constructed to predict the logistics performance index based on economic attributes. The prediction procedure employs both linear and non-linear machine learning algorithms. The macroeconomic panel dataset is used in this investigation. Furthermore, it was combined with the microeconomic panel dataset obtained through the data envelopment analysis method for evaluating financial efficiency. The procedure was implemented in six ASEAN member countries. The non-linear algorithm of an artificial neural network performed best on the complex pattern of a collective instance of these six countries, followed by the penalized linear of the Ridge regression method. Due to the limited amount of training data for each country, the artificial neural network prediction procedure is only applicable to the datasets of Singapore, Malaysia, and the Philippines. Ridge regression fits the Indonesia, Thailand and Vietnam datasets. The results provide precise trend forecasting. Macroeconomic factors are driving up the logistics performance index in Vietnam in 2020. Malaysia logistics performance is influenced by the logistics business's financial efficiency. The results at the country level can be used to track, improve, and reform the country's short-term logistics and supply chain policies. This can bring significant gains in national logistics and supply chain capabilities, as well as support for global trade collaboration, all for the long-term development of the region.

Application of machine learning and complex network measures to an EEG dataset from ayahuasca experiments

Ayahuasca is a blend of Amazonian plants that has been used for traditional medicine by the inhabitants of this region for hundreds of years. Furthermore, this plant has been demonstrated to be a viable therapy for a variety of neurological and mental diseases. EEG experiments have found specific brain regions that changed significantly due to ayahuasca. Here, we used an EEG dataset to investigate the ability to automatically detect changes in brain activity using machine learning and complex networks. Machine learning was applied at three different levels of data abstraction: (A) the raw EEG time series, (B) the correlation of the EEG time series, and (C) the complex network measures calculated from (B). Further, at the abstraction level of (C), we developed new measures of complex networks relating to community detection. As a result, the machine learning method was able to automatically detect changes in brain activity, with case (B) showing the highest accuracy (92%), followed by (A) (88%) and (C) (83%), indicating that connectivity changes between brain regions are more important for the detection of ayahuasca. The most activated areas were the frontal and temporal lobe, which is consistent with the literature. F3 and PO4 were the most important brain connections, a significant new discovery for psychedelic literature. This connection may point to a cognitive process akin to face recognition in individuals during ayahuasca-mediated visual hallucinations. Furthermore, closeness centrality and assortativity were the most important complex network measures. These two measures are also associated with diseases such as Alzheimer's disease, indicating a possible therapeutic mechanism. Moreover, the new measures were crucial to the predictive model and suggested larger brain communities associated with the use of ayahuasca. This suggests that the dissemination of information in functional brain networks is slower when this drug is present. Overall, our methodology was able to automatically detect changes in brain activity during ayahuasca consumption and interpret how these psychedelics alter brain networks, as well as provide insights into their mechanisms of action.

Economic modelling of electricity generation: long short-term memory and Q-rung orthopair fuzzy sets

The main goal of this study is to evaluate the impact of population mobility on electricity generation in Russian cities in the conditions of the spread of COVID-19, and identify hotspots. Furthermore, the evaluation is also conducted using hybrid fuzzy decision-making modelling. In this context, q-ROF DEMATEL and TOPSIS methods are taken into consideration. Additionally, a comparative evaluation is also performed with the help of Intuitionistic and Pythagorean fuzzy sets. The results are quite similar that allows to conclude that the findings are reliable and coherent. The study proves the hypothesis that human behavior changed during the COVID-19 pandemic, and electricity consumption is declining in major cities around the world. The biggest fall in energy generation was in Moscow and Yekaterinburg. In St. Petersburg and Nizhny Novgorod, the fall in energy generation is no so crucial because these cities have low building density. The study uses Long Short-Term Memory models with many different parameters. The Q-Rung Orthopair Fuzzy Sets model forecasts new COVID-19 using ten parameters. This study identifies factors influencing the spread of COVID-19 based on the theory of "broken windows" and outlines directions in limiting population mobility, which can form the basis of state policy. According to the analysis the air temperature is the variable that most affects this process.

An HGA-LSTM-Based Intelligent Model for Ore Pulp Density in the Hydrometallurgical Process

This study focused on the intelligent model for ore pulp density in the hydrometallurgical process. However, owing to the limitations of existing instruments and devices, the feed ore pulp density of thickener, a key hydrometallurgical equipment, cannot be accurately measured online. Therefore, aiming at the problem of accurately measuring the feed ore pulp density, we proposed a new intelligent model based on the long short-term memory (LSTM) and hybrid genetic algorithm (HGA). Specifically, the HGA refers to a novel optimization search algorithm model that can optimize the hyperparameters and improve the modeling performance of the LSTM. Finally, the proposed intelligent model was successfully applied to an actual thickener case in China. The intelligent model prediction results demonstrated that the hybrid model outperformed other models and satisfied the measurement accuracy requirements in the factory well.

Prediction of Outlet Pressure for the Sulfur Dioxide Blower Based on Conv1D-BiGRU Model and Genetic Algorithm

The sulfur dioxide blower is a centrifugal blower that transports various gases in the process of acid production with flue gas. Accurate prediction of the outlet pressure of the sulfur dioxide blower is quite significant for the process of acid production with flue gas. Due to the internal structure of the sulfur dioxide blower being complex, its mechanism model is difficult to establish. A novel method combining one-dimensional convolution (Conv1D) and bidirectional gated recurrent unit (BiGRU) is proposed for short-term prediction of the outlet pressure of sulfur dioxide blower. Considering the external factors such as inlet pressure and inlet flow rate of the blower, the proposed method first uses Conv1D to extract periodic and local correlation features of these external factors and the blower's outlet pressure data. Then, BiGRU is used to overcome the complexity and nonlinearity in prediction. More importantly, genetic algorithm (GA) is used to optimize the important hyperparameters of the model. Experimental results show that the combined model of Conv1D and BiGRU optimized by GA can predict the outlet pressure of sulfur dioxide blower accurately in the short term, in which the root mean square error (RMSE) is 0.504, the mean absolute error (MAE) is 0.406, and R-square (R 2) is 0.993. Also, the proposed method is superior to LSTM, GRU, BiLSTM, BiGRU, and Conv1D-BiLSTM.

Temporal patterns selection for All-Cause Mortality prediction in T2D with ANNs

Mortality prevention in T2D elderly population having Chronic Kidney Disease (CKD) may be possible thorough risk assessment and predictive modeling. In this study we investigate the ability to predict mortality using heterogeneous Electronic Health Records data. Temporal abstraction is employed to transform the heterogeneous multivariate temporal data into a uniform representation of symbolic time intervals, from which then frequent Time Intervals Related Patterns (TIRPs) are discovered. However, in this study a novel representation of the TIRPs is introduced, which enables to incorporate them in Deep Learning Networks. We describe here the use of iTirps and bTirps, in which the TIRPs are represented by a integer and binary vector representing the time respectively. While bTirp represents whether a TIRP's instance was present, iTirp represents whether multiple instances were present. While the framework showed encouraging results, a major challenge is often the large number of TIRPs, which may cause the models to under-perform. We introduce a novel method for TIRPs' selection method, called TIRP Ranking Criteria (TRC), which is consists on the TIRP's metrics, such as the differences in its recurrences, its frequencies, and the average duration difference between the classes. Additionally, we introduce an advanced version, called TRC Redundant TIRP Removal (TRC-RTR), TIRPs that highly correlate are candidates for removal. Then the selected subset of iTirp/bTirps is fed into a Deep Learning architecture like a Recurrent Neural Network or a Convolutional Neural Network. Furthermore, a predictive committee is utilized in which raw data and iTirp data are both used as input. Our results show that iTirps-based models that use a subset of iTirps based on the TRC-RTR method outperform models that use raw data or models that use full set of discovered iTirps.

Impact of COVID-19 on electricity energy consumption: A quantitative analysis on electricity

In addition to the tremendous loss of life due to coronavirus disease 2019 (COVID-19), the pandemic created challenges for the energy system, as strict confinement measures such as lockdown and social distancing compelled by governments worldwide resulted in a significant reduction in energy demand. In this study, a novel, quantitative and uncomplex method for estimating the energy consumption loss due to the pandemic, which was derived from epidemiological data in the beginning stages, is provided; the method bonds a data-driven prediction (LSTM network) of energy consumption due to COVID-19 to an econometric model (ARDL) so that the long- and short-term impact can be synthesized with adequate statistical validation. The results show that energy loss is statistically correlated with the time-changing effective reproductive number (R_t) of the disease, which can be viewed as quantifying confinement intensity and the severity of the earlier stages of the pandemic. We detected a 1.62% decrease in electricity consumption loss caused by each percent decrease in R_t on average. We verify our method by applying it to Germany and 5 U.S. states with various social features and discuss implications and universality. Our results bridge the knowledge gap between key energy and epidemiological parameters and provide policymakers with a more precise estimate of the pandemic’s impact on electricity demand so that strategies can be formulated to minimize losses caused by similar crises.

Prediction of arabica coffee production using artificial neural network and multiple linear regression techniques

Crop yield and its prediction are crucial in agricultural production planning. This study investigates and predicts arabica coffee yield in order to match the market demand, using artificial neural networks (ANN) and multiple linear regression (MLR). Data of six variables, including areas, productivity zones, rainfalls, relative humidity, and minimum and maximum temperature, were collected for the recent 180 months between 2004 and 2018. The predicted yield of the cherry coffee crop continuously increases each year. From the dataset, it was found that the prediction accuracy of the R2 and RMSE from ANN was 0.9524 and 0.0784 tons, respectively. The ANN model showed potential in determining the cherry coffee yields.

Forecasting the Risk Factor of Frontier Markets: A Novel Stacking Ensemble of Neural Network Approach

Forecasting the risk factor of the financial frontier markets has always been a very challenging task. Unlike an emerging market, a frontier market has a missing parameter named “volatility”, which indicates the market’s risk and as a result of the absence of this missing parameter and the lack of proper prediction, it has almost become difficult for direct customers to invest money in frontier markets. However, the noises, seasonality, random spikes and trends of the time-series datasets make it even more complicated to predict stock prices with high accuracy. In this work, we have developed a novel stacking ensemble of the neural network model that performs best on multiple data patterns. We have compared our model’s performance with the performance results obtained by using some traditional machine learning ensemble models such as Random Forest, AdaBoost, Gradient Boosting Machine and Stacking Ensemble, along with some traditional deep learning models such as Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM) and Bidirectional Long Short-Term (BiLSTM). We have calculated the missing parameter named “volatility” using stock price (Close price) for 20 different companies of the frontier market and then made predictions using the aforementioned machine learning ensemble models, deep learning models and our proposed stacking ensemble of the neural network model. The statistical evaluation metrics RMSE and MAE have been used to evaluate the performance of the models. It has been found that our proposed stacking ensemble neural network model outperforms all other traditional machine learning and deep learning models which have been used for comparison in this paper. The lowest RMSE and MAE values we have received using our proposed model are 0.3626 and 0.3682 percent, respectively, and the highest RMSE and MAE values are 2.5696 and 2.444 percent, respectively. The traditional ensemble learning models give the highest RMSE and MAE error rate of 20.4852 and 20.4260 percent, while the deep learning models give 15.2332 and 15.1668 percent, respectively, which clearly states that our proposed model provides a very low error value compared with the traditional models.

Ultrahigh-resolution PM2.5 estimation from top-of-atmosphere reflectance with machine learning: Theories, methods, and applications

Intra-urban pollution monitoring requires fine particulate (PM_2.5) concentration mapping at ultrahigh-resolution (dozens to hundreds of meters). However, current PM_2.5 concentration estimation, which is mainly based on aerosol optical depth (AOD) and meteorological data, usually had a low spatial resolution (kilometers) and severe spatial missing problem, cannot be applied to intra-urban pollution monitoring. To solve these problems, top-of-atmosphere reflectance (TOAR), which contains both the information about land and atmosphere and has high resolution and large spatial coverage, may be efficiently used for PM_2.5 estimation. This study aims to systematically evaluate the feasibility of retrieving ultrahigh-resolution PM_2.5 concentration at a large scale (national level) from TOAR. Firstly, we make a detailed discussion about several important but unsolved theoretic problems on TOAR-based PM_2.5 retrieval, including the band selection, scale effect, cloud impact, and mapping quality evaluation. Secondly, four types and eight retrieval models are compared in terms of quantitative accuracy, mapping quality, model generalization, and model efficiency, with the pros and cons of each type summarized. Deep neural network (DNN) model shows the highest retrieval accuracy, and linear models were the best in efficiency and generalization. As a compromise, ensemble learning shows the best overall performance. Thirdly, using the highly accurate DNN model (cross-validated R² equals 0.93) and through combining Landsat 8 and Sentinel 2 images, a 90 m and ∼4-day resolution PM_2.5 product was generated. The retrieved maps were used for analyzing the fine-scale interannual pollution change inner the city and the pollution variations during novel coronavirus disease 2019 (COVID-19). Results of this study proves that ultrahigh resolution can bring new findings of intra-urban pollution change, which cannot be observed at previous coarse resolution. Lastly, some suggestions for future ultrahigh-resolution PM_2.5 mapping research were given.

Novel double-layer bidirectional LSTM network with improved attention mechanism for predicting energy consumption

For power generation management and power system dispatching, it is of big significance to predict the consumption of electric energy accurately. For the sake of improving the prediction accuracy of power consumption, taking the complex features of time series data into consideration, a novel neural network sandwich structure with an improved attention mechanism is inserted into the double-layer bidirectional long short-term memory network shortened as A-DBLSTM is put forward in this article. In A-DBLSTM, compared with traditional attention mechanism, the presented attention mechanism focuses on different features in each time unit and the A-DBLLSTM network extracts time information in sequence. The parameter optimization of A-DBLSTM is based on the method of particle swarm optimization (PSO). For confirming the effectiveness and feasibility of A-DBLSTM, case studies using two datasets of the hourly temperature values and power loads between 2012 and 2014 and the electric energy consumption are carried out. The experimental results indicate that the presented A-DBLSTM with the novel sandwich network structure achieves superior performance in the aspects of the mean square error, root mean square, the average absolute error and the mean absolute percentage error to other advanced methods. What is more, the factors that have the greatest impact on the prediction performance can be found through analyzing the heatmap of the attention layer.

Hybrid Deep Learning Applied on Saudi Smart Grids for Short-Term Load Forecasting

Despite advancements in smart grid (SG) technology, effective load forecasting utilizing big data or large-scale datasets remains a complex task for energy management, planning, and control. The Saudi SGs, in alignment with the Saudi Vision 2030, have been envisioned as future electrical grids with a bidirectional flow of power and data. To that end, data analysis and predictive models can enhance Saudi SG planning and control via artificial intelligence (AI). Recently, many AI methods including deep learning (DL) algorithms for SG applications have been published in the literature and have shown superior time series predictions compared with conventional prediction models. Current load-prediction research for the Saudi grid focuses on identifying anticipated loads and consumptions, on utilizing limited historical data and the behavior of the load’s consumption, and on conducting shallow forecasting models. However, little scientific proof on complex DL models or real-life application has been conducted by researchers; few articles have studied sophisticated large-scale prediction models for Saudi grids. This paper proposes hybrid DL methods to enhance the outcomes in Saudi SG load forecasting, to improve problem-relevant features, and to accurately predict complicated power consumption, with the goal of developing reliable forecasting models and of obtaining knowledge of the relationships between the various features and attributes in the Saudi SGs. The model in this paper utilizes a real dataset from the Jeddah and Medinah grids in Saudi Arabia for a full year, 2021, with a one-hour time resolution. A benchmark strategy using different conventional DL methods including artificial neural network, recurrent neural network (RNN), conventional neural networks (CNN), long short-term memory (LSTM), gated recurrent unit (GRU), and different real datasets is used to verify the proposed models. The prediction results demonstrate the effectiveness of the proposed hybrid DL models, with CNN–GRU and CNN–RNN with NRMSE obtaining 1.4673% and 1.222% improvements, respectively, in load forecasting accuracy.

A Pilot Study of the Efficiency of LSTM-Based Motion Classification Algorithms Using a Single Accelerometer

Inertial sensors are widely used for classifying the motions of daily activities. Although hierarchical classification algorithms were commonly used for defined motions, deep-learning models have been used recently to classify a greater diversity of motions. In addition, ongoing studies are actively investigating algorithm efficiency (e.g., training time and accuracy). Thus, a deep-learning model was constructed in this study for the classification of a given motion based on the raw data of inertial sensors. Furthermore, the number of epochs (150, 300, 500, 750, and 900) and hidden units (100, 150, and 200) were varied in the model to determine its efficiency based on training time and accuracy, and the optimum accuracy and training time was determined. Using a basic long short-term memory (LSTM), which is a neural network known to be suitable for sequential data, the data classification training was conducted on a common desktop PC with typical specifications. The results show that the accuracy was the highest (99.82%) with 150 hidden units and 300 epochs, while the training time was also relatively short (78.15 min). In addition, the model accuracy did not always increase even when the model complexity was increased (by increasing the number of epochs and hidden units) and the training time increased as a consequence. Hence, through suitable combinations of the two factors that constitute deep-learning models according to the data, the potential development and use of efficient models have been verified. From the perspective of training optimization, this study is significant in having determined the importance of the conditions for hidden units and epochs that are suitable for the given data and the adverse effects of overtraining.

A Novel Learning Algorithm Based on Bayesian Statistics: Modelling Thermostat Adjustments for Heating and Cooling in Buildings

The temperature of indoor spaces is at the core of highly relevant topics such as comfort, productivity and health. In conditioned spaces, this temperature is determined by thermostat preferences, but there is a lack of understanding of this phenomenon as a time-dependent magnitude. In addition to this, there is scientific evidence that the mental models of how users understand the operation of the billions of air-conditioning machines around the world are incorrect, which causes systems to ‘compensate’ for temperatures outside by adjusting the thermostat, which leads to erratic changes on set-points over the day. This paper presents the first model of set-point temperature as a time-dependent variable. Additionally, a new mathematical algorithm was developed to complement these models and make possible their identification on the go, called the life Bayesian inference of transition matrices. Data from a total of 75 + 35 real thermostats in two buildings for more than a year were used to validate the model. The method was shown to be highly accurate, fast, and computationally trivial in terms of time and memory, representing a change in the paradigm for smart thermostats.

Deterioration of Electrical Load Forecasting Models in a Smart Grid Environment

Smart Grid (S.G.) is a digitally enabled power grid with an automatic capability to control electricity and information between utility and consumer. S.G. data streams are heterogenous and possess a dynamic environment, whereas the existing machine learning methods are static and stand obsolete in such environments. Since these models cannot handle variations posed by S.G. and utilities with different generation modalities (D.G.M.), a model with adaptive features must comply with the requirements and fulfill the demand for new data, features, and modality. In this study, we considered two open sources and one real-world dataset and observed the behavior of ARIMA, ANN, and LSTM concerning changes in input parameters. It was found that no model observed the change in input parameters until it was manually introduced. It was observed that considered models experienced performance degradation and deterioration from 5 to 15% in terms of accuracy relating to parameter change. Therefore, to improve the model accuracy and adapt the parametric variations, which are dynamic in nature and evident in S.G. and D.G.M. environments. The study has proposed a novel adaptive framework to overcome the existing limitations in electrical load forecasting models.

Estimation of Unmeasured Room Temperature, Relative Humidity, and CO2 Concentrations for a Smart Building Using Machine Learning and Exploratory Data Analysis

Smart buildings that utilize innovative technologies such as artificial intelligence (AI), the internet of things (IoT), and cloud computing to improve comfort and reduce energy waste are gaining popularity. Smart buildings comprise a range of sensors to measure real-time indoor environment variables essential for the heating, ventilation, and air conditioning (HVAC) system control strategies. For accuracy and smooth operation, current HVAC system control strategies require multiple sensors to capture the indoor environment variables. However, using too many sensors creates an extensive network that is costly and complex to maintain. Our proposed research solves the mentioned problem by implementing a machine-learning algorithm to estimate unmeasured variables utilizing a limited number of sensors. Using a six-month data set collected from a three-story smart building in Japan, several extreme gradient boosting (XGBoost) models were designed and trained to estimate unmeasured room temperature, relative humidity, and CO2 concentrations. Our models accurately estimated temperature, humidity, and CO2 concentration under various case studies with an average root mean squared error (RMSE) of 0.3 degrees, 2.6%, and 26.25 ppm, respectively. Obtained results show an accurate estimation of indoor environment measurements that is applicable for optimal HVAC system control in smart buildings with a reduced number of required sensors.

Designing an optimal neural network architecture: an application to property valuation

Purpose

The success of a neural network depends on, among others, an architecture that is appropriate for the task at hand. This study attempts to identify an optimal architecture of a neural network in the context of property valuation, and aims to test the ability of connecting related neural networks to reduce the property valuation error.

Design/methodology/approach

This study explores efficient network architectures to estimate land and house prices in Seoul, South Korea. The input is structured data, and the embedding technique is used to process high-cardinality categorical variables.

Findings

The shared architecture of a network for simultaneous estimation of both land and houses was revealed to be the best performing network. Through weight sharing between relevant layers in networks, the root-mean-square error (RMSE) for land price estimation was reduced significantly, from 0.55–0.68 using the baseline architecture, to 0.44–0.47 using the shared architecture.

Originality/value

The study results are expected to encourage active investigation of efficient architectures by using domain knowledge, and to promote interest in using structured data, which is still the dominant type in most industries.

Study on a Discharge Circuit Prediction Model of High-Voltage Electro-Pulse Boring Based on Bayesian Fusion

It is necessary to develop new drilling and breaking technology for hard rock construction. However, the process of high-voltage electro-pulse (HVEP) rock-breaking is complex, and the selection of electro-pulse boring (EPB) process parameters lacks a theoretical basis. Firstly, the RLC model, TV-RLC model, and TV-CRLC model are established based on the characteristics of the HVEP circuit to predict the EPB dynamic discharge curve. Secondly, the parameters are identified by the Particle Swarm Optimization Genetic Algorithm (PSO-GA). Finally, due to the nonlinear and complex time-varying characteristics of the discharge circuit, the discharge circuit prediction models based on Bayesian fusion and current residual normalization fusion method are proposed, and the optimal weight of these three models is determined. Compared with the single models for EPB current prediction, the average relative error reduction rates based on Bayesian fusion and current residual normalization fusion methods are 25.5% and 9.5%, respectively. In this paper, the discharge circuit prediction model based on Bayesian fusion is established, which improves the prediction accuracy and reliability of the model, and it guides the selection of process parameters and the design of pulse power supply and electrode bits.

Multi-Step Hourly Power Consumption Forecasting in a Healthcare Building with Recurrent Neural Networks and Empirical Mode Decomposition

Short-term forecasting of electric energy consumption has become a critical issue for companies selling and buying electricity because of the fluctuating and rising trend of its price. Forecasting tools based on Artificial Intelligence have proved to provide accurate and reliable prediction, especially Neural Networks, which have been widely used and have become one of the preferred ones. In this work, two of them, Long Short-Term Memories and Gated Recurrent Units, have been used along with a preprocessing algorithm, the Empirical Mode Decomposition, to make up a hybrid model to predict the following 24 hourly consumptions (a whole day ahead) of a hospital. Two different datasets have been used to forecast them: a univariate one in which only consumptions are used and a multivariate one in which other three variables (reactive consumption, temperature, and humidity) have been also used. The results achieved show that the best performances were obtained with the multivariate dataset. In this scenario, the hybrid models (neural network with preprocessing) clearly outperformed the simple ones (only the neural network). Both neural models provided similar performances in all cases. The best results (Mean Absolute Percentage Error: 3.51% and Root Mean Square Error: 55.06) were obtained with the Long Short-Term Memory with preprocessing with the multivariate dataset.

Advanced ML-Based Ensemble and Deep Learning Models for Short-Term Load Forecasting: Comparative Analysis Using Feature Engineering

Short-term load forecasting (STLF) plays a pivotal role in the electricity industry because it helps reduce, generate, and operate costs by balancing supply and demand. Recently, the challenge in STLF has been the load variation that occurs in each period, day, and seasonality. This work proposes the bagging ensemble combining two machine learning (ML) models—linear regression (LR) and support vector regression (SVR). For comparative analysis, the performance of the proposed model is evaluated and compared with three advanced deep learning (DL) models, namely, the deep neural network (DNN), long short-term memory (LSTM), and hybrid convolutional neural network (CNN)+LSTM models. These models are trained and tested on the data collected from the Electricity Generating Authority of Thailand (EGAT) with four different input features. The forecasting performance is measured considering mean absolute percentage error (MAPE), mean absolute error (MAE), and mean squared error (MSE) parameters. Using several input features, experimental results show that the integrated model provides better accuracy than others. Therefore, it can be revealed that our approach could improve accuracy using different data in different forecasting fields.

Bayesian Optimization Algorithm-Based Statistical and Machine Learning Approaches for Forecasting Short-Term Electricity Demand

This article focuses on developing both statistical and machine learning approaches for forecasting hourly electricity demand in Ontario. The novelties of this study include (i) identifying essential factors that have a significant effect on electricity consumption, (ii) the execution of a Bayesian optimization algorithm (BOA) to optimize the model hyperparameters, (iii) hybridizing the BOA with the seasonal autoregressive integrated moving average with exogenous inputs (SARIMAX) and nonlinear autoregressive networks with exogenous input (NARX) for modeling separately short-term electricity demand for the first time, (iv) comparing the model’s performance using several performance indicators and computing efficiency, and (v) validation of the model performance using unseen data. Six features (viz., snow depth, cloud cover, precipitation, temperature, irradiance toa, and irradiance surface) were found to be significant. The Mean Absolute Percentage Error (MAPE) of five consecutive weekdays for all seasons in the hybrid BOA-NARX is obtained at about 3%, while a remarkable variation is observed in the hybrid BOA-SARIMAX. BOA-NARX provides an overall steady Relative Error (RE) in all seasons (1~6.56%), while BOA-SARIMAX provides unstable results (Fall: 0.73~2.98%; Summer: 8.41~14.44%). The coefficient of determination (R2) values for both models are >0.96. Overall results indicate that both models perform well; however, the hybrid BOA-NARX reveals a stable ability to handle the day-ahead electricity load forecasts.