Low Error Research Articles

Mesh representation matters: investigating the influence of different mesh features on perceptual and spatial fidelity of deep 3D morphable models

BackgroundDeep 3D morphable models (deep 3DMMs) play an essential role in computer vision. They are used in facial synthesis, compression, reconstruction and animation, avatar creation, virtual try-on, facial recognition systems and medical imaging. These applications require high spatial and perceptual quality of synthesised meshes. Despite their significance, these models have not been compared with different mesh representations and evaluated jointly with point-wise distance and perceptual metrics. MethodsWe compare the influence of different mesh representation features to various deep 3DMMs on spatial and perceptual fidelity of the reconstructed meshes. This paper proves the hypothesis that building deep 3DMMs from meshes represented with global representations leads to lower spatial reconstruction error measured with L1 and L2 norm metrics and underperforms on perceptual metrics. In contrast, using differential mesh representations which describe differential surface properties yields lower perceptual FMPD and DAME and higher spatial fidelity error. The influence of mesh feature normalisation and standardisation is also compared and analysed from perceptual and spatial fidelity perspectives. ResultsThe results presented in this paper provide guidance in selecting mesh representations to build deep 3DMMs accordingly to spatial and perceptual quality objectives and propose combinations of mesh representations and deep 3DMMs which improve either perceptual or spatial fidelity of existing methods.

Unlimited sampling beyond modulo

Analog-to-digital converters (ADCs) act as a bridge between the analog and digital domains. Two important attributes of any ADC are sampling rate and its dynamic range. For bandlimited signals, the sampling should be above the Nyquist rate. It is also desired that the signals' dynamic range should be within that of the ADC's; otherwise, the signal will be clipped. Nonlinear operators such as modulo or companding can be used prior to sampling to avoid clipping. To recover the true signal from the samples of the nonlinear operator, either high sampling rates are required, or strict constraints on the nonlinear operations are imposed, both of which are not desirable in practice. In this paper, we propose a generalized flexible nonlinear operator which is sampling efficient. Moreover, by carefully choosing its parameters, clipping, modulo, and companding can be seen as special cases of it. We show that bandlimited signals are uniquely identified from the nonlinear samples of the proposed operator when sampled above the Nyquist rate. Furthermore, we propose a robust algorithm to recover the true signal from the nonlinear samples. Compared to the existing methods, our approach has a lower mean-squared error for a given sampling rate, noise level, and dynamic range. Our results lead to less constrained hardware design to address the dynamic range issues while operating at the lowest rate possible.

Accurate drift-invariant single-molecule force calibration using the Hadamard variance

Single-molecule force spectroscopy (SMFS) techniques play a pivotal role in unraveling the mechanics and conformational transitions of biological macromolecules under external forces. Among these techniques, multiplexed magnetic tweezers (MT) are particularly well suited to probe very small forces, ≤1 pN, critical for studying noncovalent interactions and regulatory conformational changes at the single-molecule level. However, to apply and measure such small forces, a reliable and accurate force-calibration procedure is crucial. Here, we introduce a new approach to calibrate MT based on thermal motion using the Hadamard variance (HV). To test our method, we perform bead-tether Brownian dynamics simulations that mimic our experimental system and compare the performance of the HV method against two established techniques: power spectral density (PSD) and Allan variance (AV) analyses. Our analysis includes an assessment of each method’s ability to mitigate common sources of additive noise, such as white and pink noise, as well as drift, which often complicate experimental data analysis. We find that the HV method exhibits overall similar or higher precision and accuracy, yielding lower force estimation errors across a wide range of signal/noise ratios (SNRs) and drift speeds compared with the PSD and AV methods. Notably, the HV method remains robust against drift, maintaining consistent uncertainty levels across the entire studied SNR and drift speed spectrum. We also explore the HV method using experimental MT data, where we find overall smaller force estimation errors compared with PSD and AV approaches. Overall, the HV method offers a robust method for achieving sub-pN resolution and precision in multiplexed MT measurements. Its potential extends to other SMFS techniques, presenting exciting opportunities for advancing our understanding of mechanosensitivity and force generation in biological systems. To make our methods widely accessible to the research community, we provide a well-documented Python implementation of the HV method as an extension to the Tweezepy package.

Zynq FPGA for hardware co-simulation of Takagi-Sugeno neuro-fuzzy for MPPT algorithm incorporating sensorless wind speed estimation in grid-connected wind system

This paper presents a hardware implementation on the Field Programmable Gate Array (FPGA) Zed-Board of a Maximum Power Point Tracking (MPPT) incorporating pitch angle control system and sensorless wind speed estimation using the Takagi-Sugeno (TS) Adaptive Neuro-Fuzzy Inference System (ANFIS). The described approach is applied specifically to a grid-connected Permanent Magnet Synchronous Generator-based Variable Speed Wind Turbine (VSWT). Firstly, the paper proposes an estimator-based TS-ANFIS model for real-time wind speed estimation, addressing challenges with conventional anemometers, such as precision, and susceptibility to adverse weather conditions. The estimated wind speed guides the calculation of an optimized mechanical speed for MPPT control. Secondly, an MPPT-based TS-ANFIS controller is introduced to achieve the maximum power point, integrating pitch angle control to prevent turbine failures in high wind speeds. Finally, the paper emphasizes the hardware implementation on the FPGA Zed-Board, leveraging its parallel processing capabilities to enhance control system quality by reducing sampling periods and loop delays. Validation includes simulations in Matlab/Simulink using the Xilinx system generator and hardware co-simulation on the FPGA Zed-Board. A comparative analysis highlights the contributions and advancements of the proposed models and controllers compared to recent schemes in the field. Indeed, the proposed MPPT-based TS-ANFIS approach effectively maximizes the power extracted from the VSWT, achieving an estimated average efficiency of 99.84 %. In contrast, PID methods show average efficiencies of 92.63 %. Additionally, compared to other published works, the proposed MPPT-based TS-ANFIS method demonstrates a rapid response time of 0.001 s and lower static error at 0.02 %. Furthermore, the proposed WSE-based TS-ANFIS model exhibits superior performance and effectiveness, yielding a root mean squared error (RMSE) of 0.0085381, a determination coefficient (R2) value of 0.99985, and a Pearson correlation coefficient (r) value of 0.99996. Moreover, the proposed hardware implementation of these approaches maintains lower power usage, operating at a high frequency of 80.38 MHz and achieving a high throughput of 2572.16 Mbps.

Reconsidering assumptions in the analysis of muscle fibre cross-sectional area.

Cross-sectional area (CSA) is a fundamental variable in characterizing muscle mechanical properties. Typically, the CSA of a single muscle fibre is assessed by measuring either one or two diameters, and assuming the cross-section is either circular or elliptical in shape. However, fibre cross-sections have irregular shapes. The accuracy and precision of CSAs determined using circular and elliptical shape assumptions are unclear for mammalian skinned muscle fibres. Second harmonic generation imaging of skinned rabbit soleus fibres revealed that the circular assumption overstated real CSA by 5.3±25.9% whereas the elliptical assumption overstated real CSA by 2.8±6.9%. A preferred rotational alignment can bias the circular assumption, as real CSA was overstated by 22.1±24.8% when using the larger fibre diameter and understated by 11.4±13% when using the smaller fibre diameter. With 73% lower variable error and reduced bias, the elliptical assumption is superior to the circular assumption when assessing the CSA of skinned mammalian fibres.

Accelerometer-assisted computer vision data fusion framework for structural dynamic displacement reconstruction

Accurate displacement measurement provides crucial information for evaluating the structural health condition. It is important to note that both direct and indirect displacement measurement methods have their own limitations, which can be remedied by leveraging each other’s strengths. In this study, a novel accelerometer-assisted computer vision data fusion framework is developed for accurately reconstructing structural dynamic displacement. The framework does not require a specific mathematical model or prior knowledge about the data’s characteristics, allowing it to be applied more broadly across different applications without the constraints of model assumptions. The core of this framework is to integrate successive variational mode decomposition (SVMD) and Bayesian optimization approaches to adaptively determine the weight factors of the fusion components. Importantly, an enhanced optical flow approach is presented for converting pixel movement to structural displacement from natural targets. This approach can effectively reduce the selection of mis-matched points within the ROI (Region of Interest), thereby reducing drift errors. The developed framework is verified via shaking table tests of a reinforced concrete frame structure under seismic excitation. Results indicate that the developed framework excels in accurately estimating structural dynamic displacement. Compared to single-vision displacement identification results, the proposed framework demonstrates lower peak error (< 1.65 mm) and normalized root mean square error (< 0.30). Meanwhile, the reconstructed displacement, by introducing dynamic displacement component from acceleration measurement, presents a wider frequency range than the vision-based displacement.

Comparative studies of Taguchi dynamic analysis, statistical, and artificial neural networks for low-carbon steel corrosion inhibition in acidic media

The aim of the present work is to optimize the corrosion inhibition process of low-carbon steel in 2.5 M phosphoric acid at different temperatures and inhibitor concentrations. The weight loss method is used to evaluate the corrosion rate in the absence or presence of a corrosion inhibitor. Taguchi dynamic (L16), mathematical regression, and artificial neural networks (ANN) are used during the data processing. The outcomes showed that the %IE increased with inhibitor concentration and temperature up to 50 oC. The Taguchi method showed that the optimum conditions for the corrosion inhibition temperature were found to be 50 oC and a 0.05 M KI concentration. Two mathematical models are proposed to construct a relationship between %IE and independent variables: the exponent model (EM) and the polynomial model (PM). PM was more accurate than EM, with a significant correlation coefficient approaching 0.9851. Temperature had a greater effect on the %IE than inhibitor concentration, which was consistent with Taguchi's findings. In ANN analyses, five networks were suggested: linear, a generalized regression neural network (GRNN), radial basis functions (RBF), and two multi-layer perceptron (MLP) networks. The highest correlation coefficient (0.996) and lower absolute error (0.126) were achieved by MLP 2:2-9-4-1:1.

A study for geometrical error in micro-geometries using VAT photopolymerization

A set of specimens was manufactured using VAT photopolymerization to study the relative error caused between different CAD geometries (i.e., Hexagonal, Pentagonal, Quadrangular, Circular, and Triangular) and manufactured workpieces. VAT photopolymerization was studied to understand the causes of errors in processing using ABS Flex White as resin. To accomplish the study of the geometry’s characterization, three replicates were measured and characterized. The manufacturing area was divided into four regions for the characterization, and the test probes were measured dimensionally by comparing the CAD design with the manufactured pieces. According to the results, triangular and circular geometries resulted in a lower relative error for solid and hollow samples, which might be attributed to the over-cured voxels and the angle in these geometries. For geometries produced at the microscale, there must be a match between the variation of the internal angle and, the voxel size and the lamp power density along the platform.

Validation of OceanSat-3 sea surface winds for their utilization in the NCMRWF NWP assimilation systems

The Indian Space Research Organization (ISRO) launched OceanSat-3, the third-generation satellite in the OceanSat series, carrying a Ku-band scatterometer in November 2022. The novelty of the OceanSat-3 scatterometer (OSCAT-3) is its high-resolution sea surface wind products generated at 12.5 km in addition to 25 km. This study aims to check the quality of OSCAT-3 winds for their possible assimilation in the National Centre for Medium Range Weather Forecasting (NCMRWF) operational Numerical Weather Prediction (NWP) models. The newly available high-resolution OSCAT-3 wind products are validated against in-situ buoy winds and NCMRWF NWP model equivalents for six months from July to December 2023. The validation results of OSCAT-3 winds are also compared with those of the Advanced Scatterometer (ASCAT) onboard the Meteorological Operational Satellite-C (MetOp-C) using the same method. Validation of OSCAT-3 winds against buoy winds shows that the Root Mean Square Errors (RMSEs) in wind speed (direction) is less than 2 m/s (15°) over the Tropics (20° N − 20° S) and slightly higher than 2 m/s (20°) over the Northern Hemisphere (20° N − 90° N), which is closer to the satellite’s mission specifications of 1.8 m/s and 20°. The RMSE in the wind speed/direction in both the scatterometer winds are less than 2 m/s (20°) over the three different geographical regions: the Tropics, Northern Hemisphere, and Southern Hemisphere, but with lower errors for ASCAT winds. The better agreement of ASCAT winds with the NWP equivalents can be attributed partially to the routine assimilation of ASCAT winds in the NCMRWF operational NWP models and also due to the frequency of operation, C-band compared to the OSCAT-3 operated in the Ku band. Since there are three distinct datasets, scatterometer winds, buoy winds, and the NWP equivalents, triple collocation is also carried out in this study. Triple collocation also shows that the errors in OSCAT-3 winds are within the mission goal. The findings from this study indicate that the OSCAT-3 vector winds are of similar quality as its predecessors (OSCAT-2 and SCATSAT-1) and can be assimilated operationally in the NCMRWF NWP models as well as in other global operational NWP models.

A New Stochastic Controller for Efficient Power Extraction from Small-Scale Wind Energy Conversion Systems under Random Load Consumption

This paper presents an innovative scheme to enhance the efficiency of power extraction from wind energy conversion systems (WECSs) under random loads. The study investigates how stochastic load consumption, modeled and predicted using a Markov chain process, impacts WECS efficiency. The suggested approach regulates the rectifier voltage rather than the rotor speed, making it a sensorless and reliable method for small-scale WECSs. Nonlinear WECS dynamics are represented using Takagi–Sugeno (TS) fuzzy modeling. Furthermore, the closed-loop system’s stochastic stability and recursive feasibility are guaranteed regardless of random load changes. The performance of the suggested controller is compared with the traditional perturb-and-observe (P&amp;O) algorithm under varying wind speeds and random load variations. Simulation results show that the proposed approach outperforms the traditional P&amp;O algorithm, demonstrating higher tracking efficiency, rapid convergence to the maximum power point (MPP), reduced steady-state oscillations, and lower error indices. Enhancing WECS efficiency under unpredictable load conditions is the primary contribution, with simulation results indicating that the tracking efficiency increases to 99.93%.

Non-contact Structural Displacement Measurement using UAV and DIC with Non-coplanar Fixed Region of Interest

The use of unmanned aerial vehicles (UAV) for displacement measurement using Digital Image Correlation (DIC) has been popular. A fixed region of interest (FROI) is often used to calibrate the UAV camera. Existing techniques require the FROI to be coplanar with the target plane, such that a corner of the FROI can be taken directly as the origin of the global coordinates. However, this condition does not exist when the target plane is in motion, and this has been a significant challenge in the correction of the UAV images. This paper proposed an algorithm to estimate the posture of the UAV camera for solving this issue. Numerical simulation shows that the proposed algorithm has high computation accuracy and stability, and it is robust to the amplitude of motion of the target image or camera. Field experiments confirm the feasibility of the proposed algorithm for images with non-coplanar conditions with a maximum error of less than 2.3 mm and a peak error below 5 %. In comparison to the traditional coplanar correction method, the CPS method demonstrates lower errors, making it better suited for cases where the FROI and the target plane are not coplanar.

Predicting the Optimal Treatment for Diseases Using Whale Optimization Algorithm

Recently, there has been a significant research focus on addressing disease prevalence, especially in dealing with the complexities of big data associated with disease data. The challenge is achieving high accuracy due to missing value problems in big data. This study aims to use AI techniques to develop a system that predicates the optimal solutions for disease, regardless of the type of disease, i.e. the system can be applied to any type of disease. The approach involves handling missing values and normalizing disease datasets. The Whale Optimization Algorithm (WOA) will be used to improve predictions for effective disease treatments. We obtained good results for predicting the appropriate treatment for the disease in the proposed research, compared to the results obtained when applying the PSO algorithm before development in state of earlier, where the results obtained in the proposed research had higher accuracy than the results in in state of earlier at high iterations starting from 200 iterations and also had a lower error rate.:

Average Wind Speed Prediction in Giresun-Kümbet Plateau Region with Artificial Neural Networks

In order to estimate the electricity generation capacity and schedule the supply for vendor needs, wind speed prediction is crucial for wind power plant frameworks. Prior to the installation of the wind power plants, a reliable wind behaviour model is neccesary. To have such a model, wind data is recorded periodically. In this study, hourly recorded meteorological data of actual pressure, relative humidity, temperature, wind direction and average wind speed for the year 2023 were obtained from the General Directorate of Meteorology for the Kümbet plateau region of Giresun province. The data is used to accurately predict the future wind speed for the region. Matlab Artificial Neural Networks (ANN) is utilized. Actual pressure, relative humidity, temperature and wind direction parameters are defined as input in the prediction process. 85% of the data set is used as training data and remainin 15% data set is used for testing data. An optimization process is applied to determine the number of hidden layers to have the prediction value with the smallest error. Bayesian Regularization training process was performed by seeing that the hidden layer has the lowest error at 90 neurons. Performance evaluations are performed with Mean Square Error (MSE), Mean Absolute Error (MAE), Root Mean Square Error (RMSE) and Pearson Correlation Coefficient (R) metrics. The values of the metrics for the test data are 26.7137, 5.1685, 3.5055 and 0.7457 respectively. The results show that, ANN based model is useful for the wind speed prediction over the region.

Assessing the Recreational Fishers and their Catches based on Social Media Platforms: Privacy and Ethical Data Analysis Considerations

Social Media (SM) can offer insights to track recreational Fishing (Rf); Many Limitations Hinder Its Practical Application. The proportion and characteristics of RFs that share their catches remain unidentified. The objective was to enhance the surveillance abilities of RF by utilizing SM information. This study focuses on the sharing economy information transmission, network optimization of SM platforms, and privacy protection issues during data transmission. The study starts with the data transmission characteristics in SM platforms, analyzes the data ethics in SM information transmission from the perspectives of natural and economic data attributes, and then focuses on the privacy protection principles in network information transmission. Then, a privacy protection scheme based on a locally sensitive hash algorithm is constructed, and finally, an information transmission scheme and method optimization based on a network optimization module are proposed. The research gathered data using physical (face-to-face) surveys and digital (email) surveys to define marine RF that post catches on online platforms (“sharers”), together with additional demographic and fishing data. A comparative analysis was conducted on the computational convergence and accuracy of different privacy protection methods, and the optimal rule framework for data privacy protection was discussed. The observation results show that the efficiency of information transmission using the Minhash-SSNR method is slightly inferior to that using the OSNR-SSNR method. Minhash technology is based on a similarity comparison of dimensionality-reduced data. This leads to data causing the initially highly similar two sets of lists to be misjudged as not having enough similarity, thereby reducing some potential information dissemination opportunities and affecting the efficacy of information transmission. It can be seen that the Minhash-SSNR strategy can effectively send information to nodes with high similarity, preventing excessive information duplication within the system. Although the Minhash-SSNR strategy has a certain degree of decline in information transmission efficiency, it accounts for only about 5% compared to the OSNR-SSNR strategy, ensuring the essential operational stability of SM opportunity networks without significant impact. With few learning and training times, the network information transmission optimization module proposed in this study quickly achieved a lower exponential error. As the number of training sessions gradually increases, the exponential error of the network information transmission optimization module in this study is small, and the prediction accuracy of the method is high. RFs who captured a prize, iconic, or symbolic species tended to discuss their catches more. This research signifies significant progress in incorporating SM information to oversee RFs.

Energy Optimization Approach in Wireless Sensor Network

In recent years, the importance of routing protocols in wireless sensor networks and the Internet of Things has been demonstrated by the numerous studies that have been presented in this area. because it is crucial to the network's functionality and effectiveness. Among routing's main goals are lowering latency, enhancing reliability, and averting network collisions. Additionally, it can be claimed that the type of network routing affects service quality, network longevity, and network traffic load control. Thus, in order to lower routing error and boost network performance and efficiency, the firefly is employed in this study to identify the best information transmission path within the network. It is also employed to reduce energy consumption. Taking into account the ability of evolutionary algorithms to optimize specified objective functions, we attempted to lower the network's energy consumption. The network can enhance the number of sending packets with the beginning energy of 3 joules from 1480 rounds to 1798 rounds, based on the proposed algorithm's results. Additionally, by contrasting the approaches described in the same article, it was discovered that the suggested approach can send roughly 40.11% more packets than the RM-LB algorithm and 1.9573% more than the OMS-LB technique. Additionally, it was discovered that by raising the starting energy to 150 joules, the suggested technique outperformed the other two algorithms by 51.23% and 45.17%, respectively, and was able to lengthen the longevity. This was in comparison to the RM-LB method and the OMS-LB method.

A Method for Fingerprint Edge Enhancement Based on Radial Hilbert Transform

Fingerprints play a significant role in various fields due to their uniqueness. In order to effectively utilize fingerprint information, it is necessary to enhance image quality. This paper introduces a method based on Radial Hilbert transform (RHLT), which simulates the vortex filter using the point spread function (PSF) of spiral phase plate (SPP) with a topological charge l=1, for fingerprint edge enhancement. The experimental results show that the processed fingerprint image has more distinct edges, with an increase in information entropy and average gradient. Unlike classical edge detection operators, the fingerprint edge image obtained by the RHLT method exhibits a lower mean square error (MSE) and a higher peak signal-to-noise ratio (PSNR). This indicates that the RHLT method provides more accurate edge detection and demonstrates higher noise-resistance capabilities. Due to its ability to highlight edge information while preserving more original features, this method has great application potential in fingerprint image processing.

Predicting specific wear rate of laser powder bed fusion AlSi10Mg parts at elevated temperatures using machine learning regression algorithm: Unveiling of microstructural morphology analysis

Precisely predicting the Specific Wear Rate (SWR) of AlSi10Mg components produced using Laser Powder Bed Fusion (LPBF) at high temperatures, which is an essential concern in additive manufacturing. This study aims to address the gap in literature by developing accurate predictive models for SWR via machine learning regression techniques. Experiments using a dry sliding wear rig shown that wear loss in AlSi10Mg print specimens increased with temperature and load, reaching a maximum wear rate of 1.5444E-06 mm3/Nm at 200 °C, 10 N, and 1.2 m/s, compared to the minimum wear rate of 6.4672E-07 mm3/Nm seen at 100 °C, 20 N, and 1.4 m/s. However, to accurately predict the wear rate at high temperatures, six different machine learning regression algorithms were used, namely Support Vector Machine (SVM), Linear Regression (LR), Random Forest Regression (RFR), Gaussian Process Regression (GPR), XGBoost regression (XGB) and Decision Tree (DT). R-squared values and various error functions were employed to validate these strategies against the anticipated outcomes. Within this set of models, GPR model has a lower Mean Absolute Error of 0.3177, Root Mean Square Error of 0.6704 and higher R2 value of 0.9686, resulting a prediction accuracy of 96.86%. From these findings, it is suggested that GPR is a very useful model for predicting the rate at which LPBFed AlSi10Mg printed parts wear under high temperature conditions in comparison with other developed models. These machine learning methods are anticipated to be beneficial for additive manufacturing enterprises.

Design of an AI-based egg fertility detection system for incubators

The conventional approach to determine the fertility of chicken eggs, called candling, is subjective, time-consuming, and ineffective and thereby results in low hatching rates and financial losses. As a result, a more reliable, accurate, and sustainable system that uses artificial intelligence and automated systems to improve the process of assessing egg fertility for incubation. The system proposes capturing of images of eggs at the early stages of incubation by a camera and sent to a cloud server, where a Convolutional Neural Network (CNN) analyses and classifies the data to determine the fertility status of the eggs. The system aims to increase the quality and hatching rate of chicken eggs, lower labour expenses and human error, and boost the poultry industry's sustainability and profitability. The framework of the system is based on the current poultry egg fertility assessment methods in Zimbabwe, which include candling, infrared thermography, ultrasound, heart rate detection, oxygen flux detection, visible or near-infrared transmittance spectroscopy, and thermal imaging. The system is expected to perform better than existing systems in terms of accuracy, speed, and cost-effectiveness. The experimental results show that, the method's average identification time is 0.210 seconds, and its identification accuracy is 98.40 percent. These results demonstrate the viability of the suggested AI-based method for automatically determining an egg's fertility without human intervention, greatly increasing hatcheries' and related businesses' productivity.

Solar energy prediction with synergistic adversarial energy forecasting system (Solar-SAFS): Harnessing advanced hybrid techniques

An effective solar forecasting is an important part of managing and enhancing the effectiveness of solar power systems. The purpose of this paper is to develop a distinct and smart energy prediction system for solar PV systems. An efficient Solar Synergistic Adversarial Energy Forecasting System (Solar-SAFS) has been developed, which greatly enhances the precision and reliability of solar power predictions. It combines various deep learning methods including Graph Convolutional Networks (GCNs), Variational Autoencoders (VAEs), Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks to effectively understand spatial and time-related patterns in solar data. The strength and accuracy of this model are increased by using adversarial training, which makes sure it gives reliable predictions in different situations. For making the hyper parameters better and to increase model's effectiveness and efficiency, we are using Grey-Oystercatcher Hybrid Optimization (GOHO) technique. The Solar-SAFS is validated and tested with different data sets including Fingrid and DSK solar. It shows that this method gives better results compared to current deep learning models. Our findings suggest that Solar-SAFS improves the accuracy and stability of solar energy prediction by a large margin, offering an advanced solution for managing renewable energy resources. Moreover, it significantly helps to obtain better predictions for solar energy production, which is a crucial need in this sector. It also encourages more efficient and dependable forecasting methods for renewable energy sources like sunlight. Compared to existing deep learning models, the Solar-SAFS demonstrates significantly lower error rates across multiple performance metrics, including Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Mean Bias Error (MBE).

Efficient and Accurate PageRank Approximation on Large Graphs

PageRank is a commonly used measurement in a wide range of applications, including search engines, recommendation systems, and social networks. However, this measurement suffers from huge computational overhead, which cannot be scaled to large graphs. Although many approximate algorithms have been proposed for computing PageRank values, these algorithms are either (i) not efficient or (ii) not accurate. Worse still, some of them cannot provide estimated PageRank values for all the vertices. In this paper, we first propose the CUR-Trans algorithm, which can reduce the time complexity for computing PageRank values and has lower error bound than existing matrix approximation-based PageRank algorithms. Then, we develop the T 2 -Approx algorithm to further reduce the time complexity for computing this measurement. Experiment results on three large-scale graphs show that both the CUR-Trans algorithm and the T 2 -Approx algorithm achieve the lowest response time for computing PageRank values with the best accuracy (for the CUR-Trans algorithm) or the competitive accuracy (for the T 2 -Approx algorithm). Besides, the two proposed algorithms are able to provide estimated PageRank values for all the vertices.