Search

With the development of online real estate trading platforms, multi-modal housing trading data, including structural information, location, and interior image data, are being accumulated. The accurate appraisal of real estate makes sense for government officials, urban policymakers, real estate sellers, and personal purchasers. In this study, we propose an interpretable multi-modal stacking-based ensemble learning (IMSEL) method that deals with various modalities for real estate appraisals. We crawl the structural and image data of real estate in Chengdu city, China from the nations largest real estate transaction platform with the location information, including public services, within 2 km of the real estate using Baidu map. We then compare the predictive results from IMSEL with those from previous state-of-art methods in the literature in terms of the root mean square error, mean absolute percentage error, mean absolute error, and coefficient of determination (R2). The comparison results show that IMSEL outperformed the other methods. We verified the improvement of introducing a data transformation strategy and deep visual features through a 10-fold cross-validation. We also discuss the managerial implications of our research findings.

The rapid growth in the cloud data center needs a dynamic resource provision to maintain the Quality of Services parameters. To guarantee it, Virtual Machine Migration as part of VM Consolidation has a significant role. Efficient VM migration requires knowledge of the host’s future utilization in advance. Because of the high variation in cloud resource usage and dynamic workloads, predicting host utilization using utilization history is challenging. This paper proposes a Support Vector Regression-based methodology to predict a host‘s future utilization using multiple resource's utilization history. A Hybrid Kernel function that includes radial basis function and polynomial kernel function has been proposed and then trains the Support Vector Machine using multiple-resource utilization history. Compared to the existing approaches: multiple linear regression-based prediction, Euclidean distance, and Absolute Summation based regression, the proposed method performs better in terms of root mean square error, mean square error, mean absolute percentage error, mean absolute error, and R 2 . The result section concludes that on evaluating error percent, the prediction error is 16% for the proposed approach and predicts host utilization with 7%, 64%, and 67% more accuracy than MRHOD, MDRHU-ED, MDRHU-AS approaches, respectively.

As the increasing number of diabetic around the world and the deficiencies of invasive blood glucose detection such as prickly pain and no continuous monitoring. In this paper, an ultra-wide band microwave based technique combined with a cascaded general regression neural network (C-GRNN) was proposed for blood glucose level estimation to achieve noninvasive and intelligent monitoring. Different glucose solutions were tested by using the reported monitoring system, in which C-GRNN was used for intelligent detection and frequency choice. The proposed C-GRNN could reduce the prediction interval from 12.3858 mg/dl to 2.1375 mg/dl compared with conventional GRNN, and the root mean square error (RMSE) reached 2.20 mg/dl. These results showed good estimation performance. We also conducted a continuous-time blood glucose level (BGL) monitoring on volunteer using proposed noninvasive method. The final results showed well accuracy, where the RMSE and mean absolute percentage error (MAPE) were 13.3208 mg/dl and 9.74% respectively.

With the significant increase of e-commerce, freight transportation demand has surged significantly over the past decade. Most of the demand has been served by trucks in the United States. One major problem commonly identified across the country is the worsening truck parking availability because the increase of truck parking facilities has lagged behind the growth of trucking activities. The lack of parking spaces and real-time parking availability information greatly exacerbate the uncertainty of trips, and often results in illegal and potentially dangerous parking or overtime driving. This paper elaborates on pilot research on improving truck parking facilities cooperated with the Washington State Department of Transportation (WSDOT), building and testing the advanced Truck Parking Information and Management System (TPIMS) with the real-time user visualization and prediction function empowered by artificial intelligence. Furthermore, by analyzing the activities of truck drivers, the researchers aggregated the regularity of truck parking patterns by a customized sequential similarity methodology. A Truck Parking Occupancy Prediction (TPOP) neural network for time-variant occupancy prediction by deep learning and attributes embedding is proposed and integrated into the TPIMS. The TPOP achieves 5.82%, 5.07%, 4.84%, and 4.19% mean average percentage error (MAPE) for 16, 8, 4, and 2 minutes ahead of occupancy prediction respectively, significantly outperforms other state-of-the-art methods. Clearly, the proposed solutions can benefit both the truck drivers and government agencies by a more efficient and smart TPIMS.

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.

The purposes are to investigate the personalized situation adaptive Human-Computer Interaction (HCI) in the COVID-19 context, achieve accurate predictions for HCI in different urban transportation situations, and solve the urban intelligent transportation problems. Problems of Human-Vehicles-Interaction (HVI) in context awareness are analyzed. Historical traffic flow in three different situations, including novice user situation, mid user situation, and expert user situation, are taken as the data sources. The HVI data are preprocessed afterward. Next, Dilated Convolution (DC) and Long-Short Term Memory (LSTM) are integrated (DC-LSTM) to build an HVI model based on situation adaptive. The proposed model is simulated to analyze its performance. Simulation experiments suggest that the Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE) of the proposed model are 4.64%, 5.34%, and 7.82%, respectively. Although these three metrics increase under the mid user and expert user situations, the proposed model can still provide a higher accuracy than LTSM, Convolutional Neural Network (CNN), Simple Recurrent Network (SRN), Support Vector Regression (SVR), and Multi-Layer Perceptron (MLP). Besides, the prediction velocity can maintain about 60 Frame-Per-Second (FPS) under all three user situations. Regarding the path guidance performance, the proposed model can suppress the traffic congestion and dredge the congested sections effectively. Hence, the HVI model based on situational adaptation constructed has high prediction accuracy and traffic congestion evacuation performance, which can provide an experimental basis for the later intelligent transportation field and improving situational self-adaptability. IEEE

Cryptocurrency is a digital currency used in financial systems that utilizes blockchain technology and cryptographic functions to gain transparency and decentralization. Because cryptocurrency prices fluctuate so much, tools for monitoring and forecasting them are required. Long short-term memory (LSTM) is a deep learning model that is capable of strongly predicting data time series. LSTM has been used in previous studies to predict the common currency. In this study, we used the gate recurrent unit (GRU) and bidirectional–LSTM (Bi-LSTM) hybrid model to predict cryptocurrency prices to improve the accuracy and normalize the root mean square error (RMSE) score of previously proposed prediction Using four cryptocurrencies (Bitcoin, Ethereum, Ripple, and Binance), the LSTM model predicts the Bitcoin. The RMSE obtained based on the best experimental results was 2343, Ethereum 10 epoch 203.89, Binance 200 epoch 32.61, and Ripple 200 epoch 0.077, while the mean absolute percentage error (MAPE) obtained for Bitcoin was 4.0%, Ethereum 5.31%, Binance 5.64%, and Ripple 4.83%. The results after normalization RMSE are Bitcoin 0.0062, Ethereum 0.063, Binance 0.073, and Ripple 0.055. The GRU Bi-LSTM hybrid model obtained very good results, yielding small RMSE results. After normalization, the results get closer to 0 and MAPE scores below 10% with RMSE.

The objective of the design and operation of any water distribution network (WDN) includes meeting the desired demand at sufficient pressure at all nodes. However, this requires situational awareness; in other words, the knowledge of system state variables such as pressure and flow throughout the network. In this work, a hybrid approach is developed for sensor placement (SP) and state estimation (SE) that exploits the underlying correlation structure in the data, along with the principles governing the flow through circular pipes. The problem of SP in WDN is addressed since measuring the state variables throughout the network is not practical. The problem of SE that maps to a matrix completion problem under certain physical and logical constraints is solved later. The completed matrix represents the state of WDN at any given time. Benchmark networks used in literature were used to evaluate the proposed approach. The mean absolute percentage error (MAPE) of less than 5% was obtained while estimating the head available at nodes. The knowledge of the states in the entire network could help operate the network adaptively.

Dynamically adaptive streaming over HTTP requires a large-scale server to transcode various bitrate versions in which different preset parameters can be used to provide different video qualities at each resolution. When transcoding servers contain a heterogeneous mix of CPUs and GPUs, the task scheduler must choose a processor and preset parameter for each transcoding task to meet the transcoding deadlines while achieving the best possible video quality. We apply regression analysis to sample variable-bit-rate videos to provide accurate (mean absolute percentage error values from 1.3% to 13.9%) model for predicting bitrate, transcoding time and video quality at each resolution on different processors. We build this into a greedy allocation and scheduling algorithm which first satisfies deadlines with low video quality, and then redistributes the workload to improve that quality while continuing to meet the deadlines. This scheme was both simulated and implemented on a testbed server. It satisfies all deadlines while outperforming standard algorithms by between 3.12% and 15.59% in terms of popularity-weighted video quality divided by bitrate.

High frequency Bitcoin price series are often non-linear and non-stationary and hence forecasting the price of Bitcoin directly or by transformation using statistical models is subject to large errors. This paper presents an ensemble model using variational mode decomposition (VMD) and Generalized additive model (GAM) to forecast intraday Bitcoin price. To evaluate the performance of the constructed model, it is compared with an ensemble of empirical mode decomposition (EMD) and GAM. The results showed that VMD-GAM model performed better than the EMD-GAM ensemble model in terms of three evaluation metrics (root mean square error, mean absolute percentage error, and bias) used.

Customized path-based speed prediction is an eventful tool for congestion avoidance, route optimization and travel time prediction for navigation apps, cab-hailing companies and autonomous vehicles. Traditionally, the speed prediction algorithms are based on road segments and can only support several main roads. Path-based speed prediction is very challenging since the speed is always changing in different path locations and is jointly affected by lots of complicated factors. This article presents a novel deep learning framework for customized path-based speed prediction. A Path-based Speed Prediction Neural Network (PSPNN) is designed to achieve speed predictions for a given path and attributes information. A hierarchical Convolutional Neural Network (CNN) and deep Bidirectional Long Short-Term Memory (Bi-LSTM) structure for different kinds of feature extraction are applied for multiple levels: the path cell, sub-path and the whole path. The method narrows down the prediction unit from road segments to customized path cells (mean length: 59.52m) and achieves a mean absolute error (MAE) of 1.94 m/s and Mean Absolute Percentage Error (MAPE) of 18.14%, showing the potential of serving rigorous data-driven applications. So far, PSPNN is the first made-to-order path-based speed prediction algorithm and can help both travelers and managers to obtain large-scale bespoke paths speed information in advance.

The purpose is to explore the spatial-temporal dynamic prediction performance of urban road network traffic flow based on convolutional neural networks (CNN) of deep learning. A dynamic prediction model of road network traffic flow based on STGCN-BiLSTM (spatial-temporal graph convolution network Bi-directional Long Short-Term Memory) is designed in view of the complex and highly nonlinear traffic data in the actual environment. Finally, the simulation experiment is conducted on the constructed model to verify its performance which is compared with that of the LSTM (Long Short-Term Memory) model, CNN model, RNN (Recurrent Neural Network) model, AlexNet model and STGCN model. The results show that the root mean square error, mean absolute error and mean absolute percentage error of the proposed algorithm model are 4.60%, 5.46% and 7.73%, respectively. The training time is stable at about 45s, the test time is stable at about 33s, and the delay is close to 1.86x10⁻⁴s. Additionally, the traffic flow of the test section in the next 15 min, 30 min, 1 h and 2 h is further predicted. Compared with other algorithms, the predicted value of the proposed algorithm is the closest to the actual value, along with the best prediction effect. Therefore, the constructed dynamic prediction model of road network traffic flow can achieve high accuracy and better robustness under the premise of low error, which can provide experimental basis for the spatial-temporal dynamic digital development of transportation in smart cities.

This study focuses on the development and analysis of a real-time updated operations strategy of a distributed energy system (DES). Owing to the relevant Chinese policy of electrical transmission and distribution, combined cooling, heating, and power system (CCHP) and photovoltaic (PV) systems are not currently allowed. However, with the Chinese supply-side power grid reform, the permissions for connections between DESs and utilities are gradually evolving. By performing building simulation and using mixed integer linear programming (MILP), a real-time updated operation strategy of a DES is established. Then, considering the DES from Tianjin Eco-city as a case study, a comparative analysis between this updated strategy and the current operation strategy is performed by evaluating three factors: economic efficiency, energy consumption, and CO2 emission. The results show that the updated strategy can reduce 29.12% of electricity time-of-use cost, 10.11% of total fuel consumption, and 18.40% of CO2 emission during the cooling season. Besides, a method of “rolling load forecasting” for DES by using Support vector regression machine (SVR) is proposed and discussed. The testing shows that the Mean Absolute Percentage Error (MAPE) is below 7.5%. And when the training sample is large, the particle swarm optimization algorithm can be used to shorten the modeling time of the air conditioning load forecasting model.

The torrefaction process enhances the quality of raw biomass and has gained widespread attention as an effective technique in energy production. Therefore, the estimation of torrefied biomass characteristics at certain operating conditions is critical to obtain desired solid products. In this study, the carbon, hydrogen, oxygen content and higher heating value (HHV) of torrefied biomass were estimated based on the results of proximate analysis (the fixed-carbon, volatile matter and ash values) of raw biomass and experimental conditions (torrefaction temperature and time). A total of 448 input and output sets belonging to lignocellulosic biomass were collected from 61 different works in the literature. Subsequently, the feedforward backpropagation algorithm based artificial neural network (ANN) model and adaptive neuro-fuzzy inference system (ANFIS) were developed as a machine learning approach for modeling the torrefaction process. The estimation capability of the developed models was examined with evaluation indicators such as mean squared error, mean absolute percentage error, and coefficient of determination. The method developed in this study provided acceptable accuracies for both elemental composition and heating value estimates. Moreover, the ANN model provided slightly better performance than ANFIS. The results show that the developed ANN model is a useful tool to obtain the desired torrefied biomass.

COVID-19 pandemic has questioned the way healthcare operations take place globally as the healthcare professionals face an unprecedented task of controlling and treating the COVID-19 infected patients with a highly straining and draining facility due to the erratic admissions of infected patients. However, COVID-19 is considered as a white swan event. Yet, the impact of the COVID-19 pandemic on healthcare operations is highly uncertain and disruptive making it as a black swan event. Therefore, the study explores the impact of the COVID-19 outbreak on healthcare operations and develops machine learning-based forecasting models using time series data to foresee the progression of COVID-19 and further using predictive analytics to better manage healthcare operations. The prediction error of the proposed model is found to be 0.039 for new cases and 0.006 for active COVID-19 cases with respect to mean absolute percentage error. The proposed simulated model further could generate predictive analytics and yielded future recovery rate, resource management ratios, and average cycle time of a patient tested COVID-19 positive. Further, the study will help healthcare professionals to devise better resilience and decision-making for managing uncertainty and disruption in healthcare operations.

The utilization of second-generation biofuel has been known as one of the sustainable solutions for energy challenges worldwide. Jatropha curcas L. (JCL), as a non-edible feedstock with high oil content fruits, has a promising potential for biodiesel production. JCL can grow in semi-arid and wasteland areas and has attracted many interests in recent years. Making efficient decisions for the production of JCL biofuels requires accurate forecasting of JCL cultivation areas. The present study develops an artificial neural network (ANN) model to predict the cultivation areas for JCL cultivation in China and India. Different structures of the ANN model are investigated for the ANN model, and the most appropriate one is determined. Eight input parameters were selected according to their impact on JCL development, including CO2 emission, Gross Domestic Product (GDP), oil price, fossil fuel energy consumption, renewable energy consumption, total energy use, population, and value-added agriculture. The mean absolute percentage error (MAPE) was used to validate the ANN models. The acquired results illustrate that the precision accuracy of the applied ANN model is 99.8%. Also, the results show that the JCL cultivation areas have increased by about 20% in China and have decreased by about 5% in India from 2010 to 2015. Finally, the achieved results from the ANN model are compared with different regression models to show the advantages of the ANN model.

Remote sensing derived datasets (e.g. Leaf Area Index (LAI)) are increasingly being used in process based cropping system models to improve the prediction skill of the simulations when implementing operationally at regional scale. However, challenges such as inadequate quality of the available remote sensing data products and high reliance of models on climate variables and their uncertainties still exist. To address these challenges, we developed Geo-CropSim, a spatial modeling framework to use high quality remote sensing products in the Environmental Policy Integrated Climate (EPIC) agroecosystem model to regulate simulated processes and improve predictions of crop yield and evapotranspiration. Geo-CropSim comprises three main features 1) pixel level model initialization using crop emergence dates; 2) ability of the EPIC model to read in the PROSAIL (i.e. combined PROSPECT leaf optical properties model and SAIL canopy bidirectional reflectance model) inversion-based crop type LAI; and 3) a stress adjustment function to regulate simulated stress using LAI anomalies. To understand its performance, we implemented it over the State of Nebraska to estimate corn (Zea mays L.) and soybean (Glycine max [Merr.]) yields and evapotranspiration (ET) for 2012 (drought year) and 2015 (normal year) at 500-m resolution. Results showed that emergence dates and seasonal LAI captured spatial and temporal differences in crop progression (e.g. delayed planting in 2015) and growth (e.g. declined LAI in 2012) driven by regional differences in crop management and weather conditions very well. These differences were reflected in Geo-CropSim yield estimates, and showed improved spatial and temporal details compared over those from EPIC simulations obtained without using remote sensing derived emergence and LAI. Results revealed that Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE) of Geo-CropSim yield estimates, computed based on USDA-NASS reported yields, were 18.85% and 1.22 Mg ha−1 for corn, and 17.90% and 0.46 Mg ha−1 for soybeans, respectively, which are substantially lower than those of original EPIC estimates (MAPE = 33.74% and RMSE = 2.18 Mg ha−1 for corn; and MAPE = 40.71% and RMSE = 0.98 Mg ha−1 for soybeans). Further, Geo-CropSim was able to capture ET and transpiration dynamics reasonably well (e.g. 10–12 % lower values for soybeans compared to corn values), and showed good agreement with flux measurements (i.e. R2 values of 0.63 and 0.72, RMSE values of 29.88 and 33.41 mm, and MAPE values of 5.0% and 6.8% for corn and soybean, respectively). Overall, this study demonstrated that Geo-CropSim has considerable potential to serve as a reliable operational tool to assess crop yields and water use under various cropping systems and to help in regional yield monitoring and water resource management.

Many data mining workloads are being analyzed in large-scale distributed cloud computing environments which provide nearly infinite resources with diverse hardware configurations. To maintain cost-efficiency in such environments, understanding the characteristics and estimating the overheads of a distributed matrix multiplication task that is a core computation kernel in many machine learning algorithms are essential. This study aims to propose a Matrix Multiplication Performance Estimator on Cloud (MPEC) algorithm. The proposed algorithm predicts the latency incurred when executing distributed matrix multiplication tasks of various input sizes and shapes with diverse instance types and a different number of worker nodes on cloud computing environments. To achieve this goal, we first analyze the characteristics of distributed matrix multiplication tasks. With characteristics generated from qualitative analysis, we propose to apply an ensemble of non-linear regression algorithm to predict the execution time of arbitrary matrix multiplication tasks. Thorough experimental results reveal that the proposed algorithm demonstrates higher accuracy than a state-of-the-art machine learning task performance estimation engine, Ernest, by decreasing the Mean Absolute Percentage Error (MAPE) in half.

Using the regression model, a method that accommodates variables related to each other is called the simultaneous equation method. The study aims to determine the factors affecting inflation and rupiah exchange rate and model simultaneous equations towards the factors affecting inflation and rupiah exchange rate in Indonesia using Two-Stage Least Square. Data used in this study are secondary data obtained from the website of Statistics of Indonesia. Findings on the simultaneous equation model with two-stage least squares reveal that variables that significantly affect inflation are the Indonesia rupiah exchange rate and money supply. At the same time, variables that significantly affect the Indonesian rupiah exchange rate are inflation and money supply. The predictive value using the inflation and rupiah exchange rate equation indicates that the obtained MAPE (Mean Absolute Percentage Error) value does not exceed 50%. In conclusion, the prediction result using the inflation and Indonesia rupiah exchange rate equation is accurate.

Time series forecasting has attracted wide attention in recent decades. However, some time series are imbalanced and show different patterns between special and normal periods, leading to the prediction accuracy degradation of special periods. In this paper, we aim to develop a unified model to alleviate the imbalance and thus improving the prediction accuracy for special periods. This task is challenging because of two reasons: (1) the temporal dependency of series, and (2) the tradeoff between mining similar patterns and distinguishing different distributions between different periods. To tackle these issues, we propose a self-attention-based time-varying prediction model with a two-stage training strategy. First, we use an encoder-decoder module with the multi-head self-attention mechanism to extract common patterns of time series. Then, we propose a time-varying optimization module to optimize the results of special periods and eliminate the imbalance. Moreover, we propose reverse distance attention in place of traditional dot attention to highlight the importance of similar historical values to forecast results. Finally, extensive experiments show that our model performs better than other baselines in terms of mean absolute error and mean absolute percentage error.

Dissolved oxygen (DO) is an important indicator of aquaculture, and its accurate forecasting can effectively improve the quality of aquatic products. In this paper, a new DO hybrid forecasting model is proposed that includes three stages: multi-factor analysis, adaptive decomposition, and an optimization-based ensemble. First, considering the complex factors affecting DO, the grey relational (GR) degree method is used to screen out the environmental factors most closely related to DO. The consideration of multiple factors makes model fusion more effective. Second, the series of DO, water temperature, salinity, and oxygen saturation are decomposed adaptively into sub-series by means of the empirical wavelet transform (EWT) method. Then, five benchmark models are utilized to forecast the sub-series of EWT decomposition. The ensemble weights of these five sub-forecasting models are calculated by particle swarm optimization and gravitational search algorithm (PSOGSA). Finally, a multi-factor ensemble model for DO is obtained by weighted allocation. The performance of the proposed model is verified by time-series data collected by the pacific islands ocean observing system (PacIOOS) from the WQB04 station at Hilo. The evaluation indicators involved in the experiment include the nash-sutcliffe efficiency (NSE), kling-gupta efficiency (KGE), mean absolute percent error (MAPE), standard deviation of error (SDE), and coefficient of determination (R2). Example analysis demonstrates that: ① the proposed model can obtain excellent DO forecasting results; ② the proposed model is superior to other comparison models; and ③ the forecasting model can be used to analyze the trend of DO and enable managers to make better management decisions.

A wireless instrumentation system was successfully developed and tested to overcome the constraints associated in collection of torque data of PTO-driven agricultural machinery with benefits such as no disturbance in telescopic action or vertical inclination of Cardan shaft. The system ensured no alterations in standard length of PTO driveline shaft. Further, telemetry system enabled remote acquisition of signals without inducing any risk of damaging the associated electronic components. It offered sensitivity of 1.6 mV/V per kN-m of applied torque with good linearity during static calibration. The performance was assessed based on accuracy, non-linearity, hysteresis, and non-repeatability and their values were 97.06%, 2.57%, 3.44%, and 0.26%, respectively. The data obtained for torque were validated with the torque computed from axial and radial load data of PTO ball bearing acquired simultaneously during rotary tillage. The low values of mean absolute percentage error (7.78% and 6.58%), maximum absolute variation (15.17% and 15.39%), and root mean square error (21.24 and 22.16 N-m), indicated good accuracy of the system. The experiments were designed with active tillage tools having two different numbers of blades, transmission gear ratios, engine speeds, tyre sizes, and four working depths as treatments. Results revealed that considered variables other than tire size, significantly affected the PTO torque and power. The decrease in PTO torque and power was found to be levelled off beyond velocity ratio 7.92. The developed instrumentation technique is simple, reliable and could be useful for database generation, implement design, and matching for effective utilization of tractor engine power.

In mining or construction projects, for exploitation of hard rock with high strength properties, blasting is frequently applied to breaking or moving them using high explosive energy. However, use of explosives may lead to the flyrock phenomenon. Flyrock can damage structures or nearby equipment in the surrounding areas and inflict harm to humans, especially workers in the working sites. Thus, prediction of flyrock is of high importance. In this investigation, examination and estimation/forecast of flyrock distance induced by blasting through the application of five artificial intelligent algorithms were carried out. One hundred and fifty-two blasting events in three open-pit granite mines in Johor, Malaysia, were monitored to collect field data. The collected data include blasting parameters and rock mass properties. Site-specific weathering index (WI), geological strength index (GSI) and rock quality designation (RQD) are rock mass properties. Multi-layer perceptron (MLP), random forest (RF), support vector machine (SVM), and hybrid models including Harris Hawks optimization-based MLP (known as HHO-MLP) and whale optimization algorithm-based MLP (known as WOA-MLP) were developed. The performance of various models was assessed through various performance indices, including a10-index, coefficient of determination (R2), root mean squared error (RMSE), mean absolute percentage error (MAPE), variance accounted for (VAF), and root squared error (RSE). The a10-index values for MLP, RF, SVM, HHO-MLP and WOA-MLP are 0.953, 0.933, 0.937, 0.991 and 0.972, respectively. R2 of HHO-MLP is 0.998, which achieved the best performance among all five machine learning (ML) models.

Uncertainty about how process factors affect output might lead to waste of resources in laboratory experiments. To address this constraint, a data-driven method might be used to describe the non-linear connection between process parameters and desired output. A Multi-Layer Perceptron-Artificial Neural Network (MLP-ANN) and non-linear response surface method are used to predict hydrogen generation by catalytic steam methane reforming. The impact of training methods (scaled conjugate and gradient descent), hidden layer variation, artificial neuron variation, and activation functions were studied in 80 MLP-ANN combinations (hyperbolic tangent function and sigmoid function). The performance of MLP-ANN models was affected by the training techniques, activation functions, layer count, and number of artificial neurons. The model with the sigmoid function and 3 input layers, 17 artificial neurons in the first layer, 15 artificial neurons in the second layer, and 2 output nodes had the greatest performance among the 40 configurations of scaled conjugate trained ANNs. It projected an 89.55% maximal hydrogen yield with a coefficient of determination (R2) of 0.997 and reduced errors with Mean absolute percentage error (MAPE) and mean squared error (MSE) of 0.199 and 0.121, respectively. Similarly, the gradient descent ANN model with hyperbolic tangent activation function had the greatest performance among the 40 gradient descent trained-ANN configurations. The 3–15–7–2 gradient descent trained ANN model projected a maximum hydrogen output of 89.73% compared to the experimental results of 89.51%. The MLP-ANN models outperformed nonlinear response surface methods, with R2, MAPE, and MSE of 0.231, 0.191, and 0.988, respectively. The updated Garson algorithm indicated that the input parameters impacted the hydrogen production in the sequence reaction temperature>methane partial pressure>steam partial pressure. The sensitivity analysis might assist identify how resources should be spent.

Power transformers are an important asset of power companies. To improve the economic benefits of power companies, it is of great significance to accurately predict the lifecycle cost of each power transformer. Based on the historical operating data on 83 110 kV power transformers, this paper estimates the lifecycle costs of different transformers, and then creates a dataset containing the estimated lifecycle costs and multiple features of the transformers, namely, bid price, transformer capacity, no-load loss, load loss, silicon steel cost, copper wire cost, annual failure frequency (AFF) of major repair, and AFF of minor repair. Based on the dataset, a lifecycle cost prediction model was established for power transformers, which couples grey wolf optimization (GWO) with support vector regression (SVR). The GWO-SVR model was simulated on the prepared dataset. The results show that the mean absolute percentage error (MAPE) of the model was merely 5.20% on the test set. The proposed model provides a new method for power companies to accurately predict and evaluate the lifecycle cost of power transformers.

Site suitability is highly essential for utility-scale solar-PV exploration, however, beyond this phase, the need to investigate solar resource variability in suitable site is very vital to strategic planning and grid-integration. This study investigates solar resource variability in a suitable site obtained from geographical information system (GIS)-based site suitability analysis using soft computing techniques. The Western Cape Province, South Africa was used as a case study and climatological, topographic, and location factors were considered for the site suitability analysis for solar-PV in the province. Five soft computing techniques were applied on a candidate site chosen from the final suitability map. These are: gradient descent with adaptive learning rate neural network (GDALRNN), resilient backpropagation neural network (RBNN), adaptive neurofuzzy inference system (ANFIS), genetic algorithm-based ANFIS (GA-ANFIS) and particle swarm optimization based ANFIS (PSO-ANFIS). Each model was trained and tested with 70% and 30% of the data obtained from the representative site respectively. The GDALRNN model outperforms all other models with a root mean square error (RMSE) of 0.0316, coefficient of variation of RMSE (CV(RMSE)) of 4.7590%, relative mean bias error of −0.2951%, mean absolute percentage error of 4.0998, robust coefficient of variation of 0.0403, skill score of 10.7345 and computational time of 9.71 s. Finally, the possibility of integrating resource variability investigation into site suitability and the relevance of simple intelligent models over complex hybrid ones in solar resource variability modelling were established.

The present study aims at bioengineering of medium components using data and process centric approaches for enhanced production of L-asparaginase, an important biological molecule, by halotolerant Bacillus licheniformis PPD37 strain. To achieve this, first significant medium components were screened followed by optimisation of a combination of media components and culture conditions such as L-asparagine, MgSO4, NaCl, pH, and temperature. Optimisation study was carried out using statistical models such as response surface methodology (RSM) - process centric and artificial neural network (ANN) - data centric approaches. The production improved from 2.86 U/mL to 17.089 U/mL, an increase of approximately 6-times of the unoptimised L-asparaginase production. On comparing RSM and ANN models for optimised L-asparaginase production based on R2 value, mean absolute percentage error (MAPE), root mean square error (RMSE), and mean absolute deviation (MAD) values, the ANN model emerged as the superior one. As this is the first report to the authors best knowledge on development of inference system using RSM and ANN models for enhanced L-asparaginase production using a halotolerant bacteria, this study could lead to more in-depth and large-scale L-asparaginase production.

This paper compares four prediction methods, namely random forest regressor (RFR), SARIMAX, Holt-Winters (H-W), and the support vector regression (SVR), to forecast the total CO2 emission from the paddy crop in India. The major objective of this study is to compare these four models and suggest an effective model for the prediction of total CO2 emission. Data from 1961 to 2018 has been categorised into two parts: training and test data. The study forecasts total CO2 emission from paddy crops in India from 2019 to 2025. A comparison of mean absolute percentage error (MAPE) and the mean square error (MSE) highlights the differences in accuracy among the four models. The mean absolute percentage eror (MAPE) and the mean square error (MSE) for the four methods are RFR (MAPE: 5.67; MSE: 549,900.02), SARIMAX (MAPE: 1.67; MSE:70,422.35), H-W (MAPE:0.75; MSE:16,648.58), and SVR (MAPE: 0.91; MSE: 17,832.4). The values of MAPE and MSE with the Holt-Winters (H-W) and the support vector regression (SVR) are relatively low as compared to SARIMAX and RFR. Based on these results, it can be inferred that H-W and SVR were found suitable models to forecast the total CO2 emission from paddy crops. Holt-Winters model predicted 14,364.97 for the year 2025, and SVR predicted 13,696.67 for the year 2025. The decision-maker can use these predictions to build a suitable policy for the future. This approach can be contrasted with other forecasting methods, such as the neural network, and train the model to achieve better forecast accuracy.

In recent years, the penetration of solar power at residential and utility levels has progressed exponentially. However, due to its stochastic nature, the prediction of solar global horizontal irradiance (GHI) with higher accuracy is a challenging task; but, vital for grid management: planning, scheduling & balancing. Therefore, this paper proposes an ensemble model using the extended scope of wavelet transform (WT) and bidirectional long short term memory (BiLSTM) deep learning network to forecast 24-h ahead solar GHI. The WT decomposes the input time series data into different finite intrinsic model functions (IMF) to extract the statistical features of input time series. Further, the study reduces the number of IMF series by combining the wavelet decomposed components (D1-D6) series on the basis of comprehensive experimental analysis with an aim to improve the forecasting accuracy. Next, the trained standalone BiLSTM networks are allocated to each IMF sub-series to execute the forecasting. Finally, the forecasted values of each sub-series from BiLSTM networks are reconstructed to deliver the final solar GHI forecast. The study performed monthly solar GHI forecasting for one year dataset using one month moving window mechanism for the location of Ahmedabad, Gujarat, India. For the performance comparison, the naïve predictor as a benchmark model, standalone long short term memory (LSTM), gated recurrent unit (GRU), BiLSTM and two other wavelet-based BiLSTM models are also simulated. From the results, it is observed that the proposed model outperforms other models in terms of root mean square error (RMSE) & mean absolute percentage error (MAPE), coefficient of determination (R2) and forecast skill (FS). The proposed model reduces the monthly average RMSE by range from 26.04–58.89%, 5.17–31.35%, 23.26–56.06% & 21.08–57% in comparison with benchmark, standalone BiLSTM, GRU & LSTM networks respectively. On the other hand, the monthly average MAPE is reduced by range from 9 to 51.18%, 12.59–28.14%, 30.43–59.19% & 26.54–58.92% in comparison to benchmark, standalone BiLSTM, GRU & LSTM respectively. Further, the proposed model obtained the value of R2 equal to 0.94 and forecast skill (%) of 47% with reference to the benchmark model.

Nutrient assessment of plants, a key aspect of agricultural crop management and varietal development programs, traditionally is time demanding and labor-intensive. This study proposes a novel methodology to determine leaf nutrient concentrations of citrus trees by using unmanned aerial vehicle (UAV) multispectral imagery and artificial intelligence (AI). The study was conducted in four different citrus field trials, located in Highlands County and in Polk County, Florida, USA. In each location, trials contained either ‘Hamlin’ or ‘Valencia’ sweet orange scion grafted on more than 30 different rootstocks. Leaves were collected and analyzed in the laboratory to determine macro- and micronutrient concentration using traditional chemical methods. Spectral data from tree canopies were obtained in five different bands (red, green, blue, red edge and near-infrared wavelengths) using a UAV equipped with a multispectral camera. The estimation model was developed using a gradient boosting regression tree and evaluated using several metrics including mean absolute percentage error (MAPE), root mean square error, MAPE-coefficient of variance (CV) ratio and difference plot. This novel model determined macronutrients (nitrogen, phosphorus, potassium, magnesium, calcium and sulfur) with high precision (less than 9% and 17% average error for the ‘Hamlin’ and ‘Valencia’ trials, respectively) and micro-nutrients with moderate precision (less than 16% and 30% average error for ‘Hamlin’ and ‘Valencia’ trials, respectively). Overall, this UAV- and AI-based methodology was efficient to determine nutrient concentrations and generate nutrient maps in commercial citrus orchards and could be applied to other crop species.

Air pollution is a severe problem growing over time. A dense air-quality monitoring network is needed to update the people regarding the air pollution status in cities. A low-cost sensor device (LCSD) based dense air-quality monitoring network is more viable than continuous ambient air quality monitoring stations (CAAQMS). An in-field calibration approach is needed to improve agreements of the LCSDs to CAAQMS. The present work aims to propose a calibration method for PM2.5 using domain adaptation technique to reduce the collocation duration of LCSDs and CAAQMS. A novel calibration approach is proposed in this work for the measured PM2.5 levels of LCSDs. The dataset used for the experimentation consists of PM2.5 values and other parameters (PM10, temperature, and humidity) at hourly duration over a period of three months data. We propose new features, by combining PM2.5, PM10, temperature, and humidity, that significantly improved the performance of calibration. Further, the calibration model is adapted to the target location for a new LCSD with a collocation time of two days. The proposed model shows high correlation coefficient values (R2) and significantly low mean absolute percentage error (MAPE) than that of other baseline models. Thus, the proposed model helps in reducing the collocation time while maintaining high calibration performance.

Agricultural price forecasting is one of the research hotspots in time series forecasting due to its unique characteristics. In this paper, we developed a deep long short-term memory (DLSTM) based model for the accurate forecasting of a nonstationary and nonlinear agricultural prices series. DLSTM model is a type of deep neural network which is advantageous in capturing the nonlinear and volatile patterns by utilizing both the recurrent architecture and deep learning methodologies together. The study further compares the price forecasting ability of the developed DLSTM model with conventional time-delay neural network (TDNN) and ARIMA models using international monthly price series of maize and palm oil. The empirical results demonstrate the superiority of the developed DLSTM model over other models in terms of various forecasting evaluation criteria like root mean square error, mean absolute percentage error and mean absolute deviation. The DLSTM model also showed dominance over other models in predicting the directional change of those monthly price series. Moreover, the accuracy of the forecasts obtained by all the models is also evaluated using the Diebold–Mariano test and the Friedman test whose results validate that the DLSTM based model has a clear advantage over the other two models.

We propose a deep learning model to reconstruct physical designs of complex coupled photonic systems, such as waveguide Bragg gratings, from their spectral responses for inverse design and fabrication diagnosis. Traditional reconstructing algorithms demand considerable computing resources at every query. Conversely, machine learning algorithms use most of the computing resources during the training process and provide effortless and orders-of-magnitude faster analysis in response to queries. This approach is demonstrated using silicon photonic grating-assisted, contra-directional couplers consisting of thousands of Bragg periods. The contra-directional couplers are modeled as coupled cavities, for which a transfer matrix model is used to generate a synthetic dataset comprising a strategic design parameter space. The free-form, architecture-independent model allows to include any geometries to the design parameter space. Upon proper training, the model achieves 1.4% mean absolute percentage error on device reconstruction and thus proves suitable for inverse design applications. To further show its potential for assessment of fabricated devices, another dataset is generated to emulate the fabrication conditions of a nominal design hindered by fabrication imperfections. The model is shown to reconstruct devices from experimental measurements with greater than 600-fold improvement in speed compared to the classical layer-peeling algorithm. This proves promising for data-driven processes required by Industry 4.0.

In this brief, concurrent learning (CL)-based full- and reduced-order observers for a perspective dynamical system (PDS) are developed. The PDS is a widely used model for estimating the depth of a feature point from a sequence of camera images. Building on the current progress of CL for parameter estimation in adaptive control, state observers are developed for the PDS model where the inverse depth appears as a time-varying parameter in the dynamics. The data recorded over a sliding time window in the near past are used in the CL term to design the full- and reduced-order state observers. A Lyapunov-based stability analysis is carried out to prove the uniformly ultimately bounded (UUB) stability of the developed observers. Simulation results are presented to validate the accuracy and convergence of the developed observers in terms of convergence time, root mean square error (RMSE), and mean absolute percentage error (MAPE) metrics. Real-world depth estimation experiments are performed to demonstrate the performance of the observers using the aforementioned metrics on a 7-DoF manipulator with an eye-in-hand configuration.

Bawang merah adalah komoditas strategis negara yang dapat mempengaruhi ekonomi nasional. Setiap tahun, produksi bawang merah meningkat beriringan dengan konsumsi rumah tangga. Tiap-tiap provinsi memiliki pola produksi berbeda-beda pada siklus dan nilai panen. Penggerombolan provinsi-provinsi yang memiliki kesamaan pola produksi dapat membantu penyusunan kebijakan oleh pemerintah. Penelitian ini bertujuan untuk menentukan gerombol-gerombol deret waktu dan memberi evaluasi terhadap peramalan produksi bawang merah di beberapa provinsi di Indonesia. Deret-deret waktu dikelompokkan secara hierarki terhadap kedekatan jarak Euclidean dengan meninjau grafik Elbow. Sebanyak tiga gerombol optimal terbentuk yang memiliki karakteristik terkait pola deret waktu dan produksinya. Deret-deret waktu pada tingkat provinsi dan gerombol kemudian dimodelkan menurut Autoregressive Integrated Moving Average (ARIMA) dan Seasonal ARIMA (SARIMA). Evaluasi peramalan tingkat gerombol selanjutnya dibandingkan dengan tingkat provinsi dan disimpulkan bahwa penggerombolan membuat peramalan menjadi lebih efisien. Hal ini berdasarkan rata-rata Mean Absolute Percentage Error (MAPE) yang lebih kecil daripada tingkat provinsi.

In recent years, ultra-fine-grained Fe–C alloy have received widespread attention because of their high levels of strength, hardness, and wear resistance. However, these alloy have strict requirements on control of the process parameters during production to meet product specifications. This study was aimed at designing a prediction model for their mechanical properties, which could ultimately promote the industrial development of ultra-fine-grained Fe–C alloy. The effect of process parameters on the mechanical properties of ultra-fine-grained Fe–C alloy was analyzed by electron backscatter diffraction (EBSD) and scanning electron microscope (SEM). By fusing experimental combinations of alloy composition, rolling process, annealing process, and resultant mechanical properties into a dataset for training and verification, a machine-learning-based prediction model of mechanical properties of ultra-fine-grained Fe–C alloy was constructed and tested. When choosing the machine learning algorithm, the best network model was obtained for this application by optimizing a conventional backpropagation (BP) network structure: a three-layer network structure, with a learning rate of 0.5, 18 hidden layer neurons, and activation functions of the hidden and output layers, namely Tansig and Purelin (MATLAB functions), respectively. Finally, the sample data was divided into training set and verification set, and the prediction accuracy, efficiency and generalization ability of BP neural network (BPNN), genetic neural network (GA-BP) and support vector machine (SVM) were compared and analyzed. The superiority of BPNN in the prediction of mechanical properties of ultrafine grained Fe–C alloy was determined, and the mean absolute percentage error (MAPE) of the BPNN for tensile strength, yield strength and uniform elongation are 3.02%, 4.47% and 6.47% respectively, and the number of training steps is 412, which are less than the other two models. The result lays a foundation for the production of high stability and high performance steel products.

Regression analysis is a statistical technique that is most commonly used for forecasting. Data sets are becoming very large due to continuous transactions in today's high-paced world. The data is difficult to manage and interpret. All the independent variables can’t be considered for the prediction because it costs high for maintenance of the data set. A novel algorithm for prediction has been implemented in this paper. Its emphasis is on extraction of efficient independent variables from various variables of the data set. The selection of variables is based on Mean Square Errors (MSE) as well as on the coefficient of determination r2p, after that the final prediction equation for the algorithm is framed on the basis of deviation of actual mean. This is a statistical based prediction algorithm which is used to evaluate the prediction based on four parameters: Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE) and residuals. This algorithm has been implemented for a multivariate data set with low maintenance costs, preprocessing costs, lower root mean square error and residuals. For one dimensional, two-dimensional, frequent stream data, time series data and continuous data, the proposed prediction algorithm can also be used. The impact of this algorithm is to enhance the accuracy rate of forecasting and minimized average error rate.

Peak particle velocity (PPV) is an important criterion for assessing the risk level of ground vibration induced by mine blasting. Based on this criterion, many efforts to predict accurately and mitigate PPV have been studied. In this paper, a novel integration approach based on the extreme learning machine (ELM) and multi-verse optimization (MVO), named the MVO–ELM model, was proposed to predict PPV. MVO was applied to initialize the number of populations and optimize the weights of the ELM model. For this, 137 blasting events in a copper mine in China with blasting parameters and rock properties were collected to test the proposed model. They were then divided into training and testing subsets for developing and testing the model, respectively. Different training/testing ratios of data subsets (e.g., 80/20 and 70/30), different topology networks (e.g., 22 neurons and 25 neurons), and various activation functions (e.g., elu, relu, tanh, and sigmoid) were considered to determine the best data subset ratio and topology network of the proposed model. To evaluate the enhanced accuracy of the proposed MVO–ELM, the traditional ELM, multi-perceptron (MLP) neural network, and the USBM (United States Bureau of Mines) models were applied to predict PPV for comparison with the optimized MVO–ELM model. The results revealed that the MVO–ELM model was the best one, with data subset ratio of 80/20, topology network with 25 hidden neurons, and “elu” activation function. The performance metrics also indicated that the optimized MVO–ELM model provided high-caliber performance compared with the ELM, MLP, and USBM models, i.e., RMSE (root-mean-squared error) = 0.196 and 0.374, R2 (determination coefficient) = 0.980 and 0.943, MAPE (mean absolute percentage error) = 0.206 and 0.670, VAF (variance accounted for) = 98.048 and 94.350, on the training and testing data subsets, respectively. Moreover, the accuracy of the optimized MVO–ELM model was improved by approximately 36% compared to the traditional ELM model. In contrast, the ELM, MLP, and USBM yielded lower performances, i.e., RMSE = 0.846, 0.657, 1.008, R2 = 0.638, 0.782, 0.558, MAPE = 1.242, 0.653, 0.691, and VAF = 63.787, 78.126, 53.406, on the training dataset; RMSE = 1.020, 0.718, 0.834, R2 = 0.619, 0.827, 0.815, MAPE = 1.219, 1.090, 0.868, and VAF = 58.284, 79.191, 75.565, on the testing data subset. The results also revealed that the maximum explosive charged per delay, monitoring horizontal distance, and rock mass integrity coefficient significantly affected PPV predictions.

A hybridized method that relies on using the support vector regression (SVR) method with equilibrium optimizer (EO) is proposed to foresee the closing prices of Egyptian Exchange (EGX). Three indices are modeled and employed: EGX 30, EGX 30 capped, and EGX 50 EWI. The efficiency of using the technical indicators and statistical measures in the forecasting process is evaluated. The proposed EO-SVR-based forecasting model is adopted and evaluated using mean absolute percentage error, average, standard deviation, best fit, worst fit, and CPU time. Also, it is compared with recently developed metaheuristic optimization algorithms published in the literature such as whale optimization algorithm, salp swarm algorithm, Harris Hawks optimization, gray wolf optimizer, Henry gas solubility optimization, Barnacles mating optimizer, Manta ray foraging optimization, and slime mold algorithm. The proposed EO-SVR model got better results than other the counterparts, and EO-SVR is considered the optimal model according to its superior outcomes. Moreover, there is no need to use technical indicators and statistical measures as their effect is not noticeable.

This paper presents an innovative data-integration that uses an iterative-learning method, a deep neural network (DNN) coupled with a stacked autoencoder (SAE) to solve issues encountered with many-objective history matching. The proposed method consists of a DNN-based inverse model with SAE-encoded static data and iterative updates of supervised-learning data are based on distance-based clustering schemes. DNN functions as an inverse model and results in encoded flattened data, while SAE, as a pre-trained neural network, successfully reduces dimensionality and reliably reconstructs geo-models. The iterative-learning method can improve the training data for DNN by showing the error reduction achieved with each iteration step. The proposed workflow shows the small mean absolute percentage error below 4% for all objective functions, while a typical multi-objective evolutionary algorithm fails to significantly reduce the initial population uncertainty. Iterative learning-based many-objective history matching estimates the trends in water cuts that are not reliably included in dynamic-data matching. This confirms the proposed workflow constructs more plausible geo-models. The workflow would be a reliable alternative to overcome the less-convergent Pareto-based multi-objective evolutionary algorithm in the presence of geological uncertainty and varying objective functions.

Seemingly unrelated mixed-effects models were used to model biomass models for Larix olgensis, Pinus koraiensis, and Pinus sylvestris, and the developed models considered multiple variables to enhance the practicality of the models. Korean larch (Larix olgensis), Korean pine (Pinus koraiensis), and Mongolian pine (Pinus sylvestris) are important coniferous species in the northeastern area of the P.R. China; hence, accurate biomass estimates of these species are meaningful for evaluating forest health and calculating carbon storage. Based on the tree variables of diameter at breast height ( $$DBH$$ ), tree height ( $$H$$ ), age, live crown length and crown width, three log-transformed species-specific biomass functions were developed using linear seemingly unrelated regression (SUR) since the error structures of the component biomass model (stem, branches, foliage and roots) were proven to be multiplicative. Furthermore, the plot-level random effect was introduced into the SUR model, namely the SURM model, to achieve more accurate biomass estimates. The results showed that the SURM model has a better fitting performance than the SUR models for three species and model types. The determination coefficient, $${R}^{2}$$ , was always larger for the SURM models than for the corresponding SUR models, while the root mean square error, $${\text{RMSE}}$$ , was always smaller for the SURM models. By leave-one-out validation, the SURM models were proven to provide more accurate predictions because the mean prediction percent error ( $${\text{MPE}}$$ ) was close to 0 and the mean absolute percentage error ( $${\text{MAPE}}$$ ) was smaller than that of the corresponding SUR models across species and model types. In addition, the size and design of the sample used to calibrate for random effects were assessed using the $${\text{MAPE}}$$ statistical index, $${\text{MAPE}}$$ . The calibration of the SURM showed a decreasing pattern of bias as the sample size increased, indicating that more available sampled trees improved the prediction accuracy of SURM models, while only slight differences existed across sampling designs. Overall, the newly developed biomass models have advantages in various data structures, and will be meaningful and useful in terms of accurately predicting the biomass of three important species in Northeast China.

This study aims to determine an automatic forecasting method of univariate time series, using the nonlinear autoregressive neural network model with exogenous input (NARX). In this automatic setting, users only need to supply the input of time series. Then, an automatic forecasting algorithm sets up the appropriate features, estimate the parameters in the model, and calculate forecasts, without the users’ intervention. The algorithm method used include preprocessing, tests for trends, and the application of first differences. The time series were tested for seasonality, and seasonal differences were obtained from a successful analysis. These series were also linearly scaled to [−1, +1]. The autoregressive lags and hidden neurons were further selected through the stepwise and optimization algorithms, respectively. The 20 NARX models were fitted with different random starting weights, and the forecasts were combined using the ensemble operator, in order to obtain the final product. This proposed method was applied to real data, and its performance was compared with several available automatic models in the literature. The forecasting accuracy was also measured by mean squared error (MSE) and mean absolute percent error (MAPE), and the results showed that the proposed method outperformed the other automatic models.

The solar power generation (SPG) prediction is indispensable to establish a reliable and secure power grid. The intelligent and knowledgeable techniques are required to forecast the most nonlinear and volatile SPG due to its dependency on fluctuating weather conditions (solar irradiance and temperature). In this work, an optimized Extreme Learning Machine (ELM) is employed to forecast real-time SPG of Chhattisgarh state of India by conceding weather conditions. The performance of ELM approach is enhanced by exploring relevant parameters such as weights, biases, and numbers of hidden layers. It requires computational techniques which are proficient enough to deal with high dimensional and complex problems. Teaching Learning Based Optimization (TLBO) technique is modified with two novel approaches to enhance the exploration and exploitation proficiency of TLBO algorithm. The collaboration of modified TLBO (MTLBO) and optimizable ELM technique is implemented to forecast SPG for four different case studies such as an hour ahead, a day ahead, a month ahead and three months ahead forecasting. The performance measures such as mean absolute error (MAE), mean squared error (MSE), mean absolute percentage error (MAPE), mean arctangent absolute percentage error (MAAPE), and correlation of determination (R2) are used to demonstrate the performance of proposed approach. Diebold-Mariano (DM) test and forecasting effectiveness are employed to hypothetically corroborate the capability of MTLBO based ELM model to outperform different optimization based ELM, ELM (with randomly fixed weights and biases) and ANN models. The simulation results contribute the evidence of excel performance of proposed approach for SPG forecasting.

In the process of riveting-welding hybrid bonding for magnesium and the carbon fiber reinforced polymer (CFRP), the weld morphology including weld penetration and weld width makes an important influence on the property of welded joint. In order to understand the optimal weld morphology, the relationship between the morphology coefficient Φ (the ratio of penetration depth to width) and the joint strength was established under a series groups of welding parameters. In addition, in order to obtain ideal appearance and optimized welding parameters, a BP neural network model optimized by genetic algorithm is established, in which the weld penetration and weld width are taken as the input units of neural network, and the welding process parameters such as welding speed, laser power, and laser defocused amount are regarded as the output units of the neural network. The results show that the mean absolute percentage error (MAPE) of each group of data did not exceed 3% while minimum mean square error (MSE) reached 0.0097, which can ensure the production of welded joints with ideal uniform appearance and mechanical properties. This research provides a new method for control of welding quality in the process of riveting-welding hybrid bonding for magnesium and CFRP.

The complex and process-critical conditions of machineries are needed to be continuously monitored in order for incipient breakdown to detect and ensure its high performance and operating safety. The change in the resonant frequency is focused by the spectrum analysis which is caused by the structural degradation and for health monitoring, useful information is produced. A test signal is required by the spectral analysis for health monitoring of structural condition. A test signal is the easiest way for structural spectral characteristics measurement but during every measurement, a structure vibration is impractical. Several techniques are presented for the condition of a machine depending on the application monitoring. The structure health would be able to be monitored if structural vibrations are utilized for spectral characteristics measurement due to wind and ground motion. The vision-based monitoring with the sources of errors are detailed and presented in this paper. Different parameters are observed for the different signals, unify the scale and can also be used to signals errors as compared with different levels of amplitudes. The PSNR and Structural Similarity are analyzed, the PSNR value is obtained in the range of 40 dB to 50 dB and the SSIM values are nearby to the 1 for all the signals. The MAPE and MAE values obtained by the presented technique are less for all the signal samples. The presented method outperforms the existed technique by 3.21 % to 44.02 % in form of MAPE. The presented method is 3.21 % to 44.02 % better than the previously existed technique in form of MAPE. The percentage improvement of the presented method outperforms by 33.93 % and 42.43 % in terms of MAE.

Central Java province is one of the provinces with the highest number of poor people on the island of Java, with the number of poor people in 2020 increasing by 0.44 million people from the previous year. Poverty is caused by several factors, one of which is the Human Development Index (HDI) and the Total Population level. Each region has different characteristics from other regions. These differences in characteristics cause more specific spatial effects, namely spatial heterogeneity. Geographically Weighted Regression (GWR) is a statistical method that can analyze spatial heterogeneity by assigning different weights and models to each observation location. This study aims to determine whether the HDI variable and percentage of total population significantly impact the number of poor people in Central Java Province in 2020 without eliminating the spatial effect. There are three groupings of variables that affect the Number of Poor People for GWR with the Adaptive Kernel Bisquare weighting function and four groups for the Adaptive Kernel Tricube weighting function. The Key Performance Indicators (KPI) used are Mean , Akaike Information Criterion (AIC), Absolute Error (MAE), Mean Square Error (MSE), and Mean Absolute Percentage Error (MAPE). Based on these KPIs, the GWR model with the Adaptive Kernel Bisquare weighting function provides better results when compared to the OLS model.

Research background: Tax evasion is an urgent challenge for governments, as reaching sufficient level of tax revenues enable adequate sustainable economic development. The motivation for the research was thus the identification of the situation in the EU countries. Purpose of the article: The main research objective was to identify the extent of tax evasion in the EU countries, with a subsequent specific focus on the econometric predictive models and a forecast of their future development in the case of Slovakia as the poorest performing country of the V4 in this area. Methods: The research was primarily based on testing selected statistical indicators in the field of tax evasions expressed on the basis of the VAT gap. The data for the research was obtained from the EUROSTAT database and the international system VIES for the period between 2000 and 2017. In addition to panel graphs, the research hypotheses were tested primarily using a cluster analysis, t-test, time series analysis, and an analysis of the time series trend with 4 basic models: linear trend, quadratic trend, growth curve model, and S-curve model. On the basis of the Mean Absolute Percentage Error (MAPE), the S-Curve model was selected as the determining model of predicting tax evasion. Findings & value added: Based on the results of the cluster analysis, the EU countries were divided into five reference groups by the VAT gap value, using the VAT gap percentage share on the overall GDP value. The research also provides a unique methodological framework and a unique econometric model for predicting the future VAT gap in Slovakia as the poorest performing country of the V4 in this area, which is applicable to other V4 and EU countries. The research results also enable policy-makers in the EU countries and specifically also in Slovakia and other V4 countries to compare themselves explicitly with the reference countries of the EU in terms of tax evasion and subsequently adopt adequate measures to improve the effectiveness and performance in this field.

Honeysuckle is widely known for its effective chemical components and extensive pharmacological effects as a traditional medicinal material in China. Echo State Network (ESN) combined with excitation-emission fluorescence spectroscopy was proposed to detect multiple pesticides in honeysuckle and perform quantitative analysis accurately. Three different models including ESN, RNN, and BPNN were validated by comparing root mean square error, mean absolute error, and mean absolute percentage error. Results revealed that ESN outperformed other two models. For quantitative analysis, the results of three models in terms of recovery rate and average recovery rate were relatively better by ESN training, which were closer to 100% for each pesticide. Therefore, ESN model was considered as the optimal training method for detecting pesticides in honeysuckle and performing better quantitative analysis on account of its effective and accuracy predicting performance, which could provide scientific basis and theoretical reference in future research.

Accurate house price estimation is of great importance not only to various real estates stakeholders such as house owners, buyers, investors, and agents but also to banking and insurance sectors among others. This estimation is a very challenging and complex task as it involves a variety of attributes. Among all attributes, location is one of the most influential attributes affecting house price. The present study has incorporated selected structural attributes and relative location through spatial attributes (geographical, infrastructural, and neighborhood) for modeling the influence of location on house prices. The hedonic model, a traditional method for estimating house price has been criticized due to nonlinearity, multicollinearity, and heteroskedasticity problems. Unlike the hedonic model, the Artificial Neural Network (ANN) permits nonlinear relationships and also tries to solve the problem of multicollinearity. The present study aims to examine the application of ANN in estimating accurate house prices and comparing the results with the Ordinary Least Squares (OLS) based hedonic model. The Gotri area located in the western part of Vadodara city, India is considered as a case study. TensorFlow (a python environment) of Google is used to implement the ANN model. In ANN model building, a three-layer network with a single hidden layer and RELU (REctified Linear Unit) activation function is adopted. The estimation performance has been evaluated by employing Root Mean Squared Error and Mean Absolute Percentage Error. According to results, ANN was found better when compared to OLS in terms of both the performance measures. This paper suggests that the ANN estimator could be a complement to the OLS based linear regression method.

There has been significant growth in both utility-scale and residential-scale solar installations in recent years, driven by rapid technology improvements and falling prices. Unlike utility-scale solar farms that are professionally managed and maintained, smaller residential-scale installations often lack sensing and instrumentation for performance monitoring and fault detection. As a result, faults may go undetected for long periods of time, resulting in generation and revenue losses for the homeowner. In this article, we present SunDown, a sensorless approach designed to detect per-panel faults in residential solar arrays. SunDown does not require any new sensors for its fault detection and instead uses a model-driven approach that leverages correlations between the power produced by adjacent panels to detect deviations from expected behavior. SunDown can handle concurrent faults in multiple panels and perform anomaly classification to determine probable causes. Using two years of solar generation data from a real home and a manually generated dataset of multiple solar faults, we show that SunDown has a Mean Absolute Percentage Error of 2.98% when predicting per-panel output. Our results show that SunDown is able to detect and classify faults, including from snow cover, leaves and debris, and electrical failures with 99.13% accuracy, and can detect multiple concurrent faults with 97.2% accuracy.