Search

Real-time flood forecasting is crucial for early flood warnings. It relies on real-time hydrological and meteorological data. Satellite Precipitation Products offer real-time global precipitation estimates and have emerged as a suitable option for rainfall input in flood forecasting models. This study first compared the daily Satellite Precipitation Products of Integrated Multi-Satellite Retrievals for Global Precipitation Measurement (IMERG) with observed rainfall data of India Meteorological Department from the year 2001 to 2009 using contingency tests. Rainfall data of IMERG are used to build four Real-time flood forecasting models based on machine learning: feedforward neural network (FFNN), extreme learning machine (ELM), wavelet-based feedforward neural network, and wavelet-based extreme learning machine. The models consider the IMERG gridded data at 1 h resolution as input to predict water level at Hayaghat gauging station of Bagmati River with lead times from 1 h to 10 days. These models have been trained and tested with the observed water level data. The model performance was also evaluated using various statistical criteria. Results showed good correlation between IMERG and observed data with a probability of detection of 85.42%. Overall, wavelet-based models outperformed their singular counterparts. Among the singular models, the FFNN model performed better than ELM with satisfactory predictions up to 5 days of lead time. For a 7 days lead time, only wavelet-based-FFNN performs well, whereas none of the models produced satisfactory results for 10 days lead time. [ABSTRACT FROM AUTHOR]

Glaucoma is defined as progressive optic neuropathy that damages the structural appearance of the optic nerve head and is characterized by permanent blindness. For mass fundus image-based glaucoma classification, an improved automated computer-aided diagnosis (CAD) model performing binary classification (glaucoma or healthy), allowing ophthalmologists to detect glaucoma disease correctly in less computational time. We proposed learning technique called fast discrete curvelet transform with wrapping (FDCT-WRP) to create feature set. This method is entitled extracting curve-like features and creating a feature set. The combined feature reduction techniques named as principal component analysis and linear discriminant analysis, have been applied to generate prominent features and decrease the feature vector dimension. Lastly, a newly improved learning algorithm encompasses a modified pelican optimization algorithm (MOD-POA) and an extreme learning machine (ELM) for classification tasks. In this MOD-POA+ELM algorithm, the modified pelican optimization algorithm (MOD-POA) has been utilized to optimize the parameters of ELM's hidden neurons. The effectiveness has been evaluated using two standard datasets called G1020 and ORIGA with the -fold stratified cross-validation technique to ensure reliable evaluation. Our employed scheme achieved the best results for both datasets obtaining accuracy of 93.25% (G1020 dataset) and 96.75% (ORIGA dataset), respectively. Furthermore, we have utilized seven Explainable AI methodologies: Vanilla Gradients (VG), Guided Backpropagation (GBP), Integrated Gradients (IG), Guided Integrated Gradients (GIG), SmoothGrad, Gradient-weighted Class Activation Mapping (GCAM), and Guided Grad-CAM (GGCAM) for interpretability examination, aiding in the advancement of dependable and credible automation of healthcare detection of glaucoma. [ABSTRACT FROM AUTHOR]

Improving soil strength and reducing the anticipated settlement and construction cost is a great paradox for civil as well as geotechnical engineers. In this paper, these aspects and other suitable types of ground improvement are discussed based on the principles of using geosynthetics for soil reinforcement. A series of load-settlement tests were also performed to compare strength and settlement of the silty sand reinforced with lime and one layer of geotextile. The study finds the maximum insertions of geotextile at 0.2D (3.0 cm) beneath the square footing base, and the lime percentage of 5.0% increases the UBC substantially. The UBC of lime-treated and geotextile-reinforced silty sand was to an optimum of 1,360 kN/m2 that has shown an enhancement of 258% compared to that of untreated and unreinforced silty sand that is approximately 380 kN/m2. Furthermore, comparative analysis between two ANN models was performed to provide improved estimate of the UBC, namely artificial neural network (ANN) and extreme learning machine (ELM). The developed computational models were then compared with experiment data, which proved that such models are more economical and effective than the expensive and time consuming conventional techniques. Consequently, based on the results, it was further validated that ELM possesses better generalization capability compared to ANN for predictive efficiency and thereby proves the efficiency of the model in estimating the ultimate bearing capacity of square footings incorporated with geotextile and lime-treated silty sand. This places the ELM model as a useful tool in the initial conceptual as well as the design for improvement steps of soil reinforcement. [ABSTRACT FROM AUTHOR]

This paper focuses on the distributed generation (DG) controller of a PV-based microgrid. An independent DG controller (IDGC) is designed for PV applications to improve Maximum-Power Point Tracking (MPPT). The Extreme-Learning Machine (ELM)-based MPPT method exactly estimates the controller's reference input, such as the voltage and current at the MPP. Feedback controls employ linear PI schemes or nonlinear, intricate techniques. Here, the converter controller is an IDGC that is improved by directly measuring the converter duty cycle and PWM index in a single DG PV-based MG. It introduces a fast-learning Extreme-Learning Machine (ELM) using the Moore–Penrose pseudo-inverse technique and online sequential ridge methods for robust control reference (CR) estimation. This approach ensures the stability of the microgrid during PV uncertainties and various operational conditions. The internal DG control approach improves the stability of the microgrid during a three-phase fault at the load bus, partial shading, irradiance changes, islanding operations, and load changes. The model is designed and simulated on the MATLAB/SIMULINK platform, and some of the results are validated on a hardware-in-the-loop (HIL) platform. [ABSTRACT FROM AUTHOR]

Copyright of Hydrometallurgy of China is the property of Hydrometallurgy of China Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Embedded devices are used in many domains, including healthcare, industries, and home automation, all of which entail significant workloads. As a direct consequence, the embedded devices require retrieval and processing of data of large volume, which occupy large memory space in the embedded devices. Compression along with workload characterization is an effective technique for minimizing memory usage and to the improvement of endurance of memory in such devices. This paper investigates the embedded workload characterization using Extreme Learning Machine (ELM) that is particularly suitable for large-scale datasets and real-time applications. Though ELM is single-layer feedforward network, its input weight randomization has a considerable effect on the accuracy of the classification. In this paper, the authors have proposed a hybrid algorithm for the optimization of the randomization of ELM. The Particle Swarm Optimizer (PSO), the Genetic Algorithm (GA), the Ant Colony Optimizer (ACO), and the Whale Optimization Algorithm (WOA) were used in the optimization of the classification process in ELM to increase the accuracy of the results. The input data must be categorized based on the energy consumed by each workload to proceed with further processing according to the system requirements. This paper explores and analyses the performance of hybridized ELM-Genetic algorithm (ELM-GA), ELM-Particle Swarm Optimization (PSO), ELM-Ant Colony Optimizer (ELM-ACO), and ELM- Whale Optimization Algorithm (ELM-WOA) optimization algorithms. The embedded benchmarks Internet of Medical Things (IoMT), Mi Benchmark (MiBench), and Embedded Microprocessor Benchmark Consortium (EEMBC) have been used as a dataset for classification in this paper. The extensive experimental study shows that the hybridized ELM-WOA provides a 98.5 % classification accuracy, 98.1 % specificity, and 98 % sensitivity compared to the other optimization methods discussed in this paper.

Abstract Glaucoma is defined as progressive optic neuropathy that damages the structural appearance of the optic nerve head and is characterized by permanent blindness. For mass fundus image-based glaucoma classification, an improved automated computer-aided diagnosis (CAD) model performing binary classification (glaucoma or healthy), allowing ophthalmologists to detect glaucoma disease correctly in less computational time. We proposed learning technique called fast discrete curvelet transform with wrapping (FDCT-WRP) to create feature set. This method is entitled extracting curve-like features and creating a feature set. The combined feature reduction techniques named as principal component analysis and linear discriminant analysis, have been applied to generate prominent features and decrease the feature vector dimension. Lastly, a newly improved learning algorithm encompasses a modified pelican optimization algorithm (MOD-POA) and an extreme learning machine (ELM) for classification tasks. In this MOD-POA+ELM algorithm, the modified pelican optimization algorithm (MOD-POA) has been utilized to optimize the parameters of ELM’s hidden neurons. The effectiveness has been evaluated using two standard datasets called G1020 and ORIGA with the $$10 \times 5$$ -fold stratified cross-validation technique to ensure reliable evaluation. Our employed scheme achieved the best results for both datasets obtaining accuracy of 93.25% (G1020 dataset) and 96.75% (ORIGA dataset), respectively. Furthermore, we have utilized seven Explainable AI methodologies: Vanilla Gradients (VG), Guided Backpropagation (GBP ), Integrated Gradients ( IG), Guided Integrated Gradients (GIG), SmoothGrad, Gradient-weighted Class Activation Mapping (GCAM), and Guided Grad-CAM (GGCAM) for interpretability examination, aiding in the advancement of dependable and credible automation of healthcare detection of glaucoma.

Abstract Gene selection is an essential step for the classification of microarray cancer data. Gene expression cancer data (deoxyribonucleic acid microarray] facilitates in computing the robust and concurrent expression of various genes. Particle swarm optimization (PSO) requires simple operators and less number of parameters for tuning the model in gene selection. The selection of a prognostic gene with small redundancy is a great challenge for the researcher as there are a few complications in PSO based selection method. In this research, a new variant of PSO (Self-inertia weight adaptive PSO) has been proposed. In the proposed algorithm, SIW-APSO-ELM is explored to achieve gene selection prediction accuracies. This novel algorithm establishes a balance between the exploitation and exploration capabilities of the improved inertia weight adaptive particle swarm optimization. The self-inertia weight adaptive particle swarm optimization (SIW-APSO) algorithm is employed for solution explorations. Each particle in the SIW-APSO increases its position and velocity iteratively through an evolutionary process. The extreme learning machine (ELM) has been designed for the selection procedure. The proposed method has been employed to identify several genes in the cancer dataset. The classification algorithm contains ELM, K-centroid nearest neighbor, and support vector machine to attain high forecast accuracy as compared to the start-of-the-art methods on microarray cancer datasets that show the effectiveness of the proposed method.

Abstract In this work, intelligent numerical models for the prediction of debris flow susceptibility using slope stability failure factor of safety (FOS) machine learning predictions have been developed. These machine learning techniques were trained using novel metaheuristic methods. The application of these training mechanisms was necessitated by the need to enhance the robustness and performance of the three main machine learning methods. It was necessary to develop intelligent models for the prediction of the FOS of debris flow down a slope with measured geometry due to the sophisticated equipment required for regular field studies on slopes prone to debris flow and the associated high project budgets and contingencies. With the development of smart models, the design and monitoring of the behavior of the slopes can be achieved at a reduced cost and time. Furthermore, multiple performance evaluation indices were utilized to ensure the model’s accuracy was maintained. The adaptive neuro-fuzzy inference system, combined with the particle swarm optimization algorithm, outperformed other techniques. It achieved an FOS of debris flow down a slope performance of over 85%, consistently surpassing other methods.

Speech emotion recognition (SER) tasks are conducted to extract emotional features from speech signals. The characteristic parameters are analyzed, and the speech emotional states are judged. At present, SER is an important aspect of artificial psychology and artificial intelligence, as it is widely implemented in many applications in the human–computer interface, medical, and entertainment fields. In this work, six transforms, namely, the synchrosqueezing transform, fractional Stockwell transform (FST), K-sine transform-dependent integrated system (KSTDIS), flexible analytic wavelet transform (FAWT), chirplet transform, and superlet transform, are initially applied to speech emotion signals. Once the transforms are applied and the features are extracted, the essential features are selected using three techniques: the Overlapping Information Feature Selection (OIFS) technique followed by two biomimetic intelligence-based optimization techniques, namely, Harris Hawks Optimization (HHO) and the Chameleon Swarm Algorithm (CSA). The selected features are then classified with the help of ten basic machine learning classifiers, with special emphasis given to the extreme learning machine (ELM) and twin extreme learning machine (TELM) classifiers. An experiment is conducted on four publicly available datasets, namely, EMOVO, RAVDESS, SAVEE, and Berlin Emo-DB. The best results are obtained as follows: the Chirplet + CSA + TELM combination obtains a classification accuracy of 80.63% on the EMOVO dataset, the FAWT + HHO + TELM combination obtains a classification accuracy of 85.76% on the RAVDESS dataset, the Chirplet + OIFS + TELM combination obtains a classification accuracy of 83.94% on the SAVEE dataset, and, finally, the KSTDIS + CSA + TELM combination obtains a classification accuracy of 89.77% on the Berlin Emo-DB dataset. [ABSTRACT FROM AUTHOR]

Gene selection is an essential step for the classification of microarray cancer data. Gene expression cancer data (deoxyribonucleic acid microarray] facilitates in computing the robust and concurrent expression of various genes. Particle swarm optimization (PSO) requires simple operators and less number of parameters for tuning the model in gene selection. The selection of a prognostic gene with small redundancy is a great challenge for the researcher as there are a few complications in PSO based selection method. In this research, a new variant of PSO (Self-inertia weight adaptive PSO) has been proposed. In the proposed algorithm, SIW-APSO-ELM is explored to achieve gene selection prediction accuracies. This novel algorithm establishes a balance between the exploitation and exploration capabilities of the improved inertia weight adaptive particle swarm optimization. The self-inertia weight adaptive particle swarm optimization (SIW-APSO) algorithm is employed for solution explorations. Each particle in the SIW-APSO increases its position and velocity iteratively through an evolutionary process. The extreme learning machine (ELM) has been designed for the selection procedure. The proposed method has been employed to identify several genes in the cancer dataset. The classification algorithm contains ELM, K-centroid nearest neighbor, and support vector machine to attain high forecast accuracy as compared to the start-of-the-art methods on microarray cancer datasets that show the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

In this work, intelligent numerical models for the prediction of debris flow susceptibility using slope stability failure factor of safety (FOS) machine learning predictions have been developed. These machine learning techniques were trained using novel metaheuristic methods. The application of these training mechanisms was necessitated by the need to enhance the robustness and performance of the three main machine learning methods. It was necessary to develop intelligent models for the prediction of the FOS of debris flow down a slope with measured geometry due to the sophisticated equipment required for regular field studies on slopes prone to debris flow and the associated high project budgets and contingencies. With the development of smart models, the design and monitoring of the behavior of the slopes can be achieved at a reduced cost and time. Furthermore, multiple performance evaluation indices were utilized to ensure the model's accuracy was maintained. The adaptive neuro-fuzzy inference system, combined with the particle swarm optimization algorithm, outperformed other techniques. It achieved an FOS of debris flow down a slope performance of over 85%, consistently surpassing other methods. [ABSTRACT FROM AUTHOR]

Due to importance of cell voltage and caustic current efficiency (CCE) in chlor-alkali industry, the necessity of accurate approach for prediction these parameters has become evident. In the current work, an extreme learning machine (ELM) approach is used to this end. Determination of the statistical qualities including R2 and different types of error reveals the fact that ELM method is suitable tool for calculation of CCE and cell voltage. The determined R2 values for CCE and cell voltage are equal to 1. Furthermore, RMSE values are 0.00002 and 1.3 × 10−6 for cell voltage and CCE, respectively. On the other hand, different graphical methods confirmed this acclaim. Moreover a sensitivity analysis is used to show effect of brine concentration, current density, operating temperature, electrolyte velocity, run time and pH on cell voltage and CCE. This analysis concluded to the fact that brine concentration and current density have the most effects on CCE and Cell voltage, respectively. [ABSTRACT FROM AUTHOR]

Background: This prospective study evaluated the impact of anatomical and tomographic biomarkers on clinical outcomes of intravitreal dexamethasone implants in patients with macular edema secondary to retinal vein occlusion (RVO). Methods: The study included 46 patients (28 with branch RVO (BRVO) and 18 with central RVO (CRVO)). Best corrected visual acuity (BCVA) significantly improved from a mean baseline of 0.817 ± 0.220 logMAR to 0.663 ± 0.267 logMAR at six months and 0.639 ± 0.321 logMAR at twelve months (p < 0.05). Central retinal thickness (CRT) showed a significant reduction from 666.2 ± 212.2 µm to 471.1 ± 215.6 µm at six months and 467 ± 175.7 µm at twelve months (p < 0.05). No significant differences were found in OCT biomarkers between baseline and follow-ups. Results: The study analysed improvements in visual acuity relative to baseline biomarkers. At six months, ellipsoid zone disruption (EZD) was significant for all subgroups. Disorganization of retinal inner layers (DRIL), external limiting membrane (ELM) disruption, macular ischemia (MI), CRT, and BRVO showed significance for any improvement, while DRIL and ELM were significant for changes greater than 0.3 logMAR (p < 0.05). At twelve months, EZD remained significant for all subgroups. ELM, MI, CRT, and BRVO were significant for any improvement, while MI and BRVO were significant for changes greater than 0.3 logMAR (p < 0.05). Hyperreflective foci were not statistically significant at either time point (p > 0.05). Conclusions: The regression model suggested that MI and CRVO could be negative predictive factors for visual outcomes, while ELM and EZD were associated with BCVA improvement one-year post-treatment. [ABSTRACT FROM AUTHOR]

In order to solve the performance prediction and design optimization of power amplifiers (PAs), the performance parameters of Gallium Nitride high-electron-mobility transistor (GaN HEMT) PAs at different temperatures are modeled based on the particle swarm optimization–extreme learning machine (PSO-ELM) and extreme learning machine (ELM) in this paper. Then, it can be seen that the prediction accuracy of the PSO-ELM model is superior to that of ELM with a minimum mean square error (MSE) of 0.0006, which indicates the PSO-ELM model has a stronger generalization ability when dealing with the nonlinear relationship between temperature and PA performance. Therefore, this investigation can provide vital theoretical support for the performance optimization of PA design. [ABSTRACT FROM AUTHOR]

Application of massive multiple input multiple output (mMIMO) in millimeter wave (mmWave) band is a promising solution for 5G communication due to low latency and directional beamforming. Hybrid precoding is an integral part of 5G systems to fully exploit spatial information in presence of large path loss with reduction of RF chains. However, hybrid precoder design is a challenging research concern due to the involvement of large number of antennas in transmitter and receiver. Additionally, higher spectral efficiency in the presence of impulsive noise in FR2 or mmWave band also requires attention. ELM (extreme learning machine) has an efficient feed forward neural architecture with only one hidden layer which is suitable to design efficient precoding models. Therefore, this research focuses on to design hybrid precoder in millimeter wave band using ELM and variable center correntropy criterion to obtain higher spectral efficiency. Exhaustive simulation results indicate that the proposed precoder has significantly better performance than state-of-art methods in multiple test conditions. The precoder performance is tested by varying base station antennas, mobile station antennas and number of users. The bit error rate (BER) performance is also analyzed. and comparison results are presented to justify the claim. [ABSTRACT FROM AUTHOR]

Emulsion liquid membrane (ELM) stands out as an extraction process that has drawn much attention due to its promising prospects in industrial wastewater treatment technology. Nevertheless, the pivotal challenge is to reach high membrane stability to overcome the obstacle of applying ELM at the industrial scale. In this study, ELM was boosted by using nanoparticles (superparamagnetic iron oxide (Fe2O3)) in the stripping phase (W1) and ionic liquid (1-methyl-3-octyl-imidazolium-hexafluorophosphate [OMIM][PF6) in the oil phase (O) for recovering/extracting vanadium from synthetic wastewater to near completion and at the same time enhancing emulsion stability to be appropriate for industrial application. The vanadium recovery/extraction percentage has been raised significantly in 3 min to 99.6% when adding 0.01% (w/w) Fe2O3 NPs (20 to 50 nm in size) in the internal phase (W1) and 5% (v/v) [OMIM]PF6 ionic liquid in the oil phase (O). Also, the emulsion stability was considerably improved, and the leakage percentage was reduced to 16% after 3 days. The results of this study could be used in the future to remove additional heavy metal ions from industrial effluents. [ABSTRACT FROM AUTHOR]

In general, it is a worth challenging problem to build a robust classifier for data sets with noises or outliers. Establishing a robust classifier is a more difficult problem for datasets with asymmetric noise distribution. The Fisher-regularized extreme learning machine (Fisher-ELM) considers the statistical knowledge of the data, however, it ignores the impact of noises or outliers. In this paper, to reduce the negative influence of noises or outliers, we first put forward a novel asymmetric Welsch loss function named AW-loss based on asymmetric L 2 -loss function and Welsch loss function. Based on the AW-loss function, we then present a new robust Fisher-ELM called AWFisher-ELM. The proposed AWFisher-ELM not only takes into account the statistical information of the data, but also considers the impact of asymmetric distribution noises. We utilize concave-convex procedure (CCCP) and dual method to solve the non-convexity of the proposed AWFisher-ELM. Simultaneously, an algorithm for AWFisher-ELM is given and a theorem about the convergence of the algorithm is proved. To validate the effectiveness of our algorithm, we compare our AWFisher-ELM with the other state-of-the-art methods on artificial data sets, UCI data sets, NDC large data sets and image data sets by setting different ratios of noises. The experimental results are as follows, the accuracy of AWFisher-ELM is the highest in the artificial data sets, reaching 98.9%. For the large-scale NDC data sets and the image data sets, the accuracy of AWFisher-ELM is also the highest. For the ten UCI data sets, the accuracy and F 1 value of AWFisher-ELM are the highest in most data sets expect for Diabetes. In terms of training time, our AWFisher-ELM has almost the same training time with RHELM and CHELM, but it takes longer time than OPT-ELM, WCS-SVM, Fisher-SVM, Pinball-FisherSVM, and Fisher-ELM. This is because AWFisher-ELM, RHELM, and CHELM need to solve a convex quadratic subprogramming problem in each iteration. In conclusion, our method exhibits excellent generalization performance expect for the longer training time. [ABSTRACT FROM AUTHOR]

Improving soil strength and reducing the anticipated settlement and construction cost is a great paradox for civil as well as geotechnical engineers. In this paper, these aspects and other suitable types of ground improvement are discussed based on the principles of using geosynthetics for soil reinforcement. A series of load-settlement tests were also performed to compare strength and settlement of the silty sand reinforced with lime and one layer of geotextile. The study finds the maximum insertions of geotextile at 0.2D (3.0 cm) beneath the square footing base, and the lime percentage of 5.0% increases the UBC substantially. The UBC of lime-treated and geotextile-reinforced silty sand was to an optimum of 1,360 kN/m2 that has shown an enhancement of 258% compared to that of untreated and unreinforced silty sand that is approximately 380 kN/m2. Furthermore, comparative analysis between two ANN models was performed to provide improved estimate of the UBC, namely artificial neural network (ANN) and extreme learning machine (ELM). The developed computational models were then compared with experiment data, which proved that such models are more economical and effective than the expensive and time consuming conventional techniques. Consequently, based on the results, it was further validated that ELM possesses better generalization capability compared to ANN for predictive efficiency and thereby proves the efficiency of the model in estimating the ultimate bearing capacity of square footings incorporated with geotextile and lime-treated silty sand. This places the ELM model as a useful tool in the initial conceptual as well as the design for improvement steps of soil reinforcement.

Abstract Background Plants can retain atmospheric particulate matter (PM) through their unique foliar microstructures, which has a profound impact on the phyllosphere microbial communities. Yet, the underlying mechanisms linking atmospheric particulate matter (PM) retention by foliar microstructures to variations in the phyllosphere microbial communities remain a mystery. In this study, we conducted a field experiment with ten Ulmus lines. A series of analytical techniques, including scanning electron microscopy, atomic force microscopy, and high-throughput amplicon sequencing, were applied to examine the relationship between foliar surface microstructures, PM retention, and phyllosphere microbial diversity of Ulmus L. Results We characterized the leaf microstructures across the ten Ulmus lines. Chun exhibited a highly undulated abaxial surface and dense stomatal distribution. Langya and Xingshan possessed dense abaxial trichomes, while Lieye, Zuiweng, and Daguo had sparsely distributed, short abaxial trichomes. Duomai, Qingyun, and Lang were characterized by sparse stomata and flat abaxial surfaces, whereas Jinye had sparsely distributed but extensive stomata. The mean leaf retention values for total suspended particulate (TSP), PM2.5, PM2.5-10, PM10-100, and PM> 100 were 135.76, 6.60, 20.10, 90.98, and 13.08 µg·cm− 2, respectively. Trichomes substantially contributed to PM2.5 retention, while larger undulations enhanced PM2.5-10 retention, as evidenced by positive correlations between PM2.5 and abaxial trichome density and between PM2.5-10 and the adaxial raw microroughness values. Phyllosphere microbial diversity patterns varied among lines, with bacteria dominated by Sediminibacterium and fungi by Mycosphaerella, Alternaria, and Cladosporium. Redundancy analysis confirmed that dense leaf trichomes facilitated the capture of PM2.5-associated fungi, while bacteria were less impacted by PM and struggled to adhere to leaf microstructures. Long and dense trichomes provided ideal microhabitats for retaining PM-borne microbes, as evidenced by positive feedback loops between PM2.5, trichome characteristics, and the relative abundances of microorganisms like Trichoderma and Aspergillus. Conclusions Based on our findings, a three-factor network profile was constructed, which provides a foundation for further exploration into how different plants retain PM through foliar microstructures, thereby impacting phyllosphere microbial communities.

The elaboration likelihood model (ELM) and regression analysis were used to investigate the impact of furniture brands’ communication strategies on consumer behavior through short video platforms. The work examined a set of representative short videos, analyzing how key features—such as content theme, duration (16-60 seconds), graphics, subtitles, background music, and title style—affected communication effectiveness. The ELM model uncovered the correlation between these video characteristics and the Communication Effect Index (DCI), with statistical significance confirmed by regression. Findings indicated that live broadcasts, graphical presentations, subtitles/topics, upbeat music, and exclamatory titles significantly enhanced communication efficiency. Limitations, including time-period sampling bias, sample size, and item duplication in the ELM application, were also considered. Based on these findings, the research offers optimization suggestions and future directions for furniture enterprises in leveraging short video marketing.

Background: Plants can retain atmospheric particulate matter (PM) through their unique foliar microstructures, which has a profound impact on the phyllosphere microbial communities. Yet, the underlying mechanisms linking atmospheric particulate matter (PM) retention by foliar microstructures to variations in the phyllosphere microbial communities remain a mystery. In this study, we conducted a field experiment with ten Ulmus lines. A series of analytical techniques, including scanning electron microscopy, atomic force microscopy, and high-throughput amplicon sequencing, were applied to examine the relationship between foliar surface microstructures, PM retention, and phyllosphere microbial diversity of Ulmus L. Results: We characterized the leaf microstructures across the ten Ulmus lines. Chun exhibited a highly undulated abaxial surface and dense stomatal distribution. Langya and Xingshan possessed dense abaxial trichomes, while Lieye, Zuiweng, and Daguo had sparsely distributed, short abaxial trichomes. Duomai, Qingyun, and Lang were characterized by sparse stomata and flat abaxial surfaces, whereas Jinye had sparsely distributed but extensive stomata. The mean leaf retention values for total suspended particulate (TSP), PM2.5, PM2.5-10, PM10-100, and PM> 100 were 135.76, 6.60, 20.10, 90.98, and 13.08 µg·cm− 2, respectively. Trichomes substantially contributed to PM2.5 retention, while larger undulations enhanced PM2.5-10 retention, as evidenced by positive correlations between PM2.5 and abaxial trichome density and between PM2.5-10 and the adaxial raw microroughness values. Phyllosphere microbial diversity patterns varied among lines, with bacteria dominated by Sediminibacterium and fungi by Mycosphaerella, Alternaria, and Cladosporium. Redundancy analysis confirmed that dense leaf trichomes facilitated the capture of PM2.5-associated fungi, while bacteria were less impacted by PM and struggled to adhere to leaf microstructures. Long and dense trichomes provided ideal microhabitats for retaining PM-borne microbes, as evidenced by positive feedback loops between PM2.5, trichome characteristics, and the relative abundances of microorganisms like Trichoderma and Aspergillus. Conclusions: Based on our findings, a three-factor network profile was constructed, which provides a foundation for further exploration into how different plants retain PM through foliar microstructures, thereby impacting phyllosphere microbial communities. [ABSTRACT FROM AUTHOR]

This paper addresses the evolving landscape of communication technology, emphasizing the pivotal role of 5G and the emerging 6G networks in accommodating the increasing demand for high-speed and accurate data transmission. We delve into the advancements in 5G technology, particularly the implementation of millimeter wave (mmWave) frequencies ranging from 30 to 300 GHz. These advancements are instrumental in enhancing applications requiring massive data transmission and reception, facilitated by massive MIMO (multiple input multiple output) systems. Looking towards the future, this paper forecasts the necessity for faster data transmission technologies, shifting the focus toward the development of 6G networks. These future networks are projected to employ ultra-massive MIMO systems in the terahertz band, operating within 0.1–10 THz frequency ranges. A significant part of our research is dedicated to exploring advanced signal detection techniques, helping to mitigate the impact of interference and improve accuracy in data transmission and enabling more efficient communication, even in environments with high levels of noise, and including zero forcing (ZF) and minimum mean square error (MMSE) methods, which form the cornerstone of our proposed approach. Additionally, signal detection contributes to the development of new communication technologies such as 5G and 6G, which require a high data transmission efficiency and rapid response speeds. The core contribution of this study lies in the application of deep learning to signal detection in ultra-massive MIMO systems, a critical component of 6G technology. We compare this approach with existing ELMx-based machine learning methods, focusing on algorithmic efficiency and computational performance. Our comparative analysis included the regularized extreme learning machine (RELM) and the outlier robust extreme learning machine (ORELM), juxtaposed with ZF and MMSE methods. Simulation results indicated the superiority of our convolutional neural network for signal detection (CNN-SD) over the traditional ELMx-based, ZF, and MMSE methods, particularly in terms of channel capacity and bit error rate. Furthermore, we demonstrate the computational efficiency and reduced complexity of the CNN-SD method, underscoring its suitability for future expansive MIMO systems. [ABSTRACT FROM AUTHOR]

Research indicates that auditors have an impoverished understanding of trial preparation factors that, independent of audit quality, can significantly elevate audit litigation risk. As the scholarly literature sheds little insight about the nature and implications of these factors, we identify what factors audit litigators consider in trial preparation, how they expect these factors to affect litigation outcomes, and how they attempt to leverage these factors. To do so, we interview 39 audit litigators, who identify factors germane to trial venues, jury pools, and case arguments. Guided by the elaboration likelihood model, we construct a framework that predicts these factors influence litigation outcomes by changing jurors' motivation and/or capability to elaborate. Importantly, we find that litigators who defend (sue) auditors strategically maneuver these factors to increase (decrease) the likelihood of higher juror elaboration, because higher elaboration is favorable to auditors. We discuss implications of our results for practice and research. JEL Classifications: K22; K40; K41; M4; M41; M42. [ABSTRACT FROM AUTHOR]

The management of water resources must be based on accurate models of the river discharge in the context of the water flow alteration due to anthropic influences and climate change. Therefore, this article addresses the challenge of detecting the best model among three artificial intelligence techniques (AI)—backpropagation neural networks (BPNN), long short-term memory (LSTM), and extreme learning machine (ELM)—for the monthly data series discharge of the Buzău River, in Romania. The models were built for three periods: January 1955–September 2006 (S1 series), January 1955–December 1983 (S2 series), and January 1984–December 2010 (S series). In terms of mean absolute error (MAE), the best performances were those of ELM on both Training and Test sets on S2, with MAETraining = 5.02 and MAETest = 4.01. With respect to MSE, the best was LSTM on the Training set of S2 (MSE = 60.07) and ELM on the Test set of S2 (MSE = 32.21). Accounting for the R2 value, the best model was LSTM on S2 (R2Training = 99.92%, and R2Test = 99.97%). ELM was the fastest, with 0.6996 s, 0.7449 s, and 0.6467 s, on S, S1, and S2, respectively. [ABSTRACT FROM AUTHOR]

Conditioned steak is easily contaminated by foreign bodies, such as iron sheets, glass, and crush bones in the manufacturing processes, posing hidden safety hazards to consumers. In this study, the feasibility of using ultrasonic imaging to detect and identify foreign bodies in conditioned steaks was investigated. Firstly, the ultrasonic imaging data of foreign bodies was collected. Four discriminant models among them linear discriminant analysis (LDA), and extreme learning machine (ELM) were established, and based on the texture values of the smallest circumscribed rectangular area of the foreign bodies, the type was identified. The foreign bodies were then extracted by gray-level co-occurrence matrix (GLCM). The detection rate of foreign bodies was 97.78 %, meanwhile ELM showed the highest accuracy of recognition rate of 76.67 %. The results showed that ultrasound imaging technology could be used to detect foreign bodies in the conditioned steak and to identify the type of foreign body via pattern recognition. [ABSTRACT FROM AUTHOR]

Because of the insufficient stability and high time cost of single data-driven models, Genetic Algorithm-Back Propagation Neural Network (GA-BPNN), Genetic Algorithm-Support Vector Machine (GA-SVM) and Extreme Learning Machine (ELM), a fusion modeling method of information entropy Stacking is proposed to establish linear fusion models of information entropy. Actual production data, the gasifier load, feed pressure and flow rate, and cooling water flow rate were used as inputs, while the gasifier outlet temperature, syngas flow temperature and rate, and syngas composition at the outlet of the washing tower were used as outputs. An information entropy Stacking fusion model of the gasifier was established. The Mean Relative Errors (MRE) of the predictions of the information entropy Stacking fusion model on the gasifier outlet temperature, syngas outlet temperature and flow rate, syngas CO content, and H² content were determined to be 1.89.%, 0.17%, 0.78%, 0.95%, and 0.71%, respectively. These results are more stable than those obtained by the single data driven model. The fitting speed was about 19% higher than that of the linear information entropy fusion model. Combined with the optimization algorithm, our model can be applied to the online optimization of operating conditions such as oxygen coal ratio in the gasification process, the gasification temperature of the gasifier, and the effective gas yield during the process. [ABSTRACT FROM AUTHOR]

This study integrates the Theory of Planned Behavior (TPB) and the Elaboration Likelihood Model (ELM) to assess and explain taxpayers' compliance with the Twitter account @DitjenPajakRI. This is a quantitative study with an explanatory approach. A purposive sample strategy was used with a questionnaire to collect data for this research. A total of 200 people filled out the research questionnaire. According to the study’s findings, Source Credibility influences Attitudes, and the two TPB components, Attitudes and Perceived Behavioral Control, influence Taxpayer Compliance. As for the relationship between Argument Quality and Source Credibility on Attitudes, there is no moderating effect of Involvement; instead, the relationship between Source Credibility and Taxpayer Compliance through Attitudes is a full mediation relationship. The findings of this study can assist the tax authority in developing strategies and policies for efficiently and effectively communicating tax information to taxpayers as they make decisions about how to fulfill their tax rights and obligations through messages from central route, peripheral route, normative, and non-volitional processes.

Potato plants have an important role in providing a source of carbohydrates for society. However, potato production is often threatened by various plant diseases, such as leaf disease, which can cause a decrease in yields. Identification of diseases on potato leaves is currently mostly done by farmers manually, so it is not always efficient and accurate. So the aim of this research is to identify diseases on potato leaves with artificial neural networks using the ELM (Extreme Learning Machine) approach and the GLCM (Gray Level Co-Occurrence Matrix) method for feature extraction. The GLCM approach functions to obtain texture features on objects by measuring how often certain pairs of pixel intensities appear together at various distances and directions in the image. Meanwhile, the ELM algorithm is used for image identification by adopting a one-time training method without iteration, which involves randomly determining weights and biases in hidden layers, thus allowing training to be carried out quickly and efficiently. Evaluation of the model by looking for the level of accuracy produces a value of 84.667%. The results show that the model developed is capable of accurate identification.

This paper addresses the evolving landscape of communication technology, emphasizing the pivotal role of 5G and the emerging 6G networks in accommodating the increasing demand for high-speed and accurate data transmission. We delve into the advancements in 5G technology, particularly the implementation of millimeter wave (mmWave) frequencies ranging from 30 to 300 GHz. These advancements are instrumental in enhancing applications requiring massive data transmission and reception, facilitated by massive MIMO (multiple input multiple output) systems. Looking towards the future, this paper forecasts the necessity for faster data transmission technologies, shifting the focus toward the development of 6G networks. These future networks are projected to employ ultra-massive MIMO systems in the terahertz band, operating within 0.1–10 THz frequency ranges. A significant part of our research is dedicated to exploring advanced signal detection techniques, helping to mitigate the impact of interference and improve accuracy in data transmission and enabling more efficient communication, even in environments with high levels of noise, and including zero forcing (ZF) and minimum mean square error (MMSE) methods, which form the cornerstone of our proposed approach. Additionally, signal detection contributes to the development of new communication technologies such as 5G and 6G, which require a high data transmission efficiency and rapid response speeds. The core contribution of this study lies in the application of deep learning to signal detection in ultra-massive MIMO systems, a critical component of 6G technology. We compare this approach with existing ELMx-based machine learning methods, focusing on algorithmic efficiency and computational performance. Our comparative analysis included the regularized extreme learning machine (RELM) and the outlier robust extreme learning machine (ORELM), juxtaposed with ZF and MMSE methods. Simulation results indicated the superiority of our convolutional neural network for signal detection (CNN-SD) over the traditional ELMx-based, ZF, and MMSE methods, particularly in terms of channel capacity and bit error rate. Furthermore, we demonstrate the computational efficiency and reduced complexity of the CNN-SD method, underscoring its suitability for future expansive MIMO systems.

Asako Tanaka, Masayuki Hata, Memiri Tsuchikawa, Naoko Ueda-Arakawa Ueda-Arakawa, Hiroshi Tamura, Manabu Miyata, Ayako Takahashi, Ai Kido, Yuki Muraoka, Masahiro Miyake, Sotaro Ooto, Akitaka Tsujikawa Department of Ophthalmology and Visual Sciences, Kyoto University Graduate School of Medicine, Kyoto, JapanCorrespondence: Masayuki Hata, Department of Ophthalmology and Visual Sciences Kyoto University Graduate School of Medicine, Sakyo-ku, Kyoto, 606-8507, Japan, Tel +81-75-751-3248, Fax +81-75-752-0933, Email trj74h6@kuhp.kyoto-u.ac.jpPurpose: To evaluate the efficacy and safety of faricimab injections for treatment-naïve neovascular age-related macular degeneration (nvAMD) patients, including subtypes and pachychoroid phenotypes, and identify predictive factors for visual outcomes.Methods: nvAMD patients were prospectively recruited, receiving three monthly faricimab (6 mg) injections. Best-corrected visual acuity (BCVA) two months after the last injection (month 4) was compared between subtypes, and between pachychoroid neovasculopathy (PNV) and non-PNV eyes. Regression analysis determined factors influencing month 4 BCVA.Results: The study involved 23 patients (12 typical AMD [tAMD], 10 polypoidal choroidal vasculopathy [PCV], 1 retinal angiomatous proliferation [RAP]). Eleven exhibited PNV phenotype. Significant BCVA (P = 4.9 × 10− 4) and central retinal thickness (CRT) (P = 1.3 × 10− 5) improvements were observed post-faricimab treatment. The therapy demonstrated favourable results for both tAMD and PCV eyes, and non-PNV and PNV eyes. Faricimab achieved dry macula in 77.3% of eyes, with subretinal fluid resolution in most cases, although intraretinal fluid (IRF) often persisted. Multivariable analysis identified external limiting membrane (ELM) presence and IRF as BCVA contributors at month 4.Conclusion: Faricimab demonstrated significant effectiveness and safety in treatment-naïve nvAMD patients, particularly for PCV and PNV eyes. ELM presence and IRF is predictive of visual outcomes.Keywords: anti-VEGF, anti-vascular endothelial growth factor, CRT, central retinal thickness, ELM, external limiting membrane, faricimab, IRF, intraretinal fluid, MNV, macular neovascularization, nvAMD, neovascular age-related macular degeneration, PCV, polypoidal choroidal vasculopathy, PNV, pachychoroid neovasculopathy, RAP, retinal angiomatous proliferation

Ensuring the dependability of software before its public release is of utmost importance. Many software issues arise due to human errors made throughout the development process, highlighting the importance of addressing these errors early. It is crucial to incorporate testing resources at the beginning of development to minimize potential issues. Utilizing an approach that identifies modules susceptible to errors helps potential problems. With an understanding of the significance of precisely anticipating module failures, multiple automated solutions are already emerging. This work presents a refined software defect prediction model that utilizes a meta-heuristic optimization technique. The methodology integrates NASA’s data collection procedure, which involves data cleansing, reducing the dimensionality of features, and predicting defects. Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) are used to decrease the feature dimensionality, while an Extreme Learning Machine (ELM) is utilized for forecasting defects. The ELM parameters, such as weight and biases, are ideally chosen using the suggested improved JAYA optimization (IMJAYA) method. The model’s validation involves assessing its accuracy, sensitivity, specificity, F1 score, and MCC metrics using a $10\times 5$ cross-validation. The model is verified using NASA datasets that consist of several classes, such as CM1, KC2, KC3, MC1, PC1, and JM1. The PCA-LDA+ IMJAYA-ELM model yields defect prediction accuracies of 95.73%, 98.08%, 94.87%, 96.23%, 97.10%, and 97.46% for the CM1, KC2, KC3, MC1, PC1, and JM1 datasets, respectively. The research outcomes show encouraging outcomes when using a meta-heuristic optimization technique with smaller feature sets for studies on predicting software defects.

This paper focuses on the distributed generation (DG) controller of a PV-based microgrid. An independent DG controller (IDGC) is designed for PV applications to improve Maximum-Power Point Tracking (MPPT). The Extreme-Learning Machine (ELM)-based MPPT method exactly estimates the controller’s reference input, such as the voltage and current at the MPP. Feedback controls employ linear PI schemes or nonlinear, intricate techniques. Here, the converter controller is an IDGC that is improved by directly measuring the converter duty cycle and PWM index in a single DG PV-based MG. It introduces a fast-learning Extreme-Learning Machine (ELM) using the Moore–Penrose pseudo-inverse technique and online sequential ridge methods for robust control reference (CR) estimation. This approach ensures the stability of the microgrid during PV uncertainties and various operational conditions. The internal DG control approach improves the stability of the microgrid during a three-phase fault at the load bus, partial shading, irradiance changes, islanding operations, and load changes. The model is designed and simulated on the MATLAB/SIMULINK platform, and some of the results are validated on a hardware-in-the-loop (HIL) platform.

The usage of geosynthetics can be employed widely in the field and geotechnical engineering. The ground improvement approaches using geosynthetics as reinforcing materials are widely used to overcome the limitations of other methods. Considering these aspects, a sequence of model load versus settlement experiments with variance in the position of geotextile and percentage of lime was executed to observe the toughness as well as settlement properties of the silty sand with single layer of geotextile. There are several aspects of this paper like the computational techniques such as artificial neural network (ANN) and extreme learning machine (ELM). The implementation of computational models gives an advanced resolution for forecasting the load sustaining capability of the rectangular footing in a simple and economic way. These computational models could be judged by employing several well-approved statistical indices. It could also be verified through the experimental results achieved from the studies. The upshot shows that the developed ELM model has a remarkable potential to evaluate the ultimate bearing capacity (UBC) of the rectangular footing. It can be set forth as a predictive tool for the initial designing process. [ABSTRACT FROM AUTHOR]

This paper introduces a fault diagnosis and prediction framework for petroleum machinery production systems, addressing the need for more efficient and reliable fault handling in the face of complex signals. Utilizing the Complete Ensemble Empirical Mode Decomposition (CEEMD) and permutation entropy, it extracts signal features to analyse system dynamics. An Adaptive Variational Mode Decomposition (VMD) and optimized Extreme Learning Machine (ELM) simulation model enhances diagnostic accuracy through signal processing and fast learning capabilities. This approach not only elevates fault diagnosis precision but also supports the maintenance and health management of petroleum machinery systems, offering significant theoretical and practical benefits. [ABSTRACT FROM AUTHOR]