Selection Of Optimal Parameters Research Articles

Coexistence of 1 Tbps classical optical communication and quantum key distribution over a 100.96 km few-mode fiber.

The integration of quantum key distribution (QKD) and classical optical communication has attracted widespread attention. In this Letter, we experimentally demonstrate a real-time co-propagation of 1 Tbps for 10 classical channels with one discrete-variable QKD channel in the weakly coupled few-mode fiber (FMF). Based on the selection of optimal device parameters and wavelength assignment of classical channels, as well as the optimization of equipment performance, a secure key rate of as high as 2.7 kbps of coexistence transmission of QKD and classical optical communication can be achieved using a 100.96 km weakly coupled FMF. Therefore, this study is a step toward realizing long-distance quantum-classical coexistence transmission.

Optimizing Light Intensity with PID Control

Lighting is a fundamental cornerstone within interior design, possessing the capability to metamorphose spaces and evoke emotional responses profoundly. This principle applies to residential, industrial, and office domains, where lighting nuances are meticulously adjusted to enhance comfort and practicality. However, adequate luminance frequently intersects with energy wastage, often attributed to negligent light management practices. Mitigating this issue necessitates integrating light intensity controls adept at adapting to ambient luminosity and room-specific parameters. A prospective avenue encompasses incorporating a Proportional Integral Derivative (PID) control system synergized with light sensors. This research Implementing a closed-loop architecture, PID control utilizes feedback mechanisms to improve the precision of instrumentation systems. The PID methodology, consisting of Proportional, Integral, and Derivative control modalities, produces stable responses, accelerates system reactions, and diminishes deviations and overshooting by predetermined setpoints. The proposed Light Intensity Control System underpinned by PID methodology manifests as an exhibition of compelling outcomes drawn from empirical trials. The judicious selection of optimal parameters, specifically Kp = 0.2, Ki = 0.1, and Kd = 0.1, yielded noteworthy test outcomes: an ascent time of 0.0848, an overshoot of 6.5900, a culmination period of 0.4800, a settling period of 2.3032, and a steady-state error of 0.0300. Within this system, the PID controller assumes a pivotal role, orchestrating the regulation and meticulous calibration of light intensity to harmonize with designated criteria, thus fostering an environment of augmented energy efficiency and adaptability in illumination.Lighting is a fundamental cornerstone within interior design, possessing the capability to metamorphose spaces and evoke emotional responses profoundly. This principle applies to residential, industrial, and office domains, where lighting nuances are meticulously adjusted to enhance comfort and practicality. However, adequate luminance frequently intersects with energy wastage, often attributed to negligent light management practices. Mitigating this issue necessitates integrating light intensity controls adept at adapting to ambient luminosity and room-specific parameters. A prospective avenue encompasses incorporating a Proportional Integral Derivative (PID) control system synergized with light sensors. This research Implementing a closed-loop architecture, PID control utilizes feedback mechanisms to improve the precision of instrumentation systems. The PID methodology, consisting of Proportional, Integral, and Derivative control modalities, produces stable responses, accelerates system reactions, and diminishes deviations and overshooting by predetermined setpoints. The proposed Light Intensity Control System underpinned by PID methodology manifests as an exhibition of compelling outcomes drawn from empirical trials. The judicious selection of optimal parameters, specifically Kp = 0.2, Ki = 0.1, and Kd = 0.1, yielded noteworthy test outcomes: an ascent time of 0.0848, an overshoot of 6.5900, a culmination period of 0.4800, a settling period of 2.3032, and a steady-state error of 0.0300. Within this system, the PID controller assumes a pivotal role, orchestrating the regulation and meticulous calibration of light intensity to harmonize with designated criteria, thus fostering an environment of augmented energy efficiency and adaptability in illumination.

Intelligent financial eco-management model based on perceptron model

Abstract The intelligent financial eco-management model is studied to help enterprises realize financial information transformation and enterprise digital transformation. Starting from the perceptron model, this paper describes the basic artificial neurons that make up the perceptron and introduces the structure and construction process of the multilayer perceptron model. To realize the optimal parameter selection of the multilayer perceptron, the basic principle of the Bayesian optimization algorithm is introduced, and the parameters of the multilayer perceptron model are optimized using this algorithm, which leads to the BOA-MLP evaluation model. The intelligent financial eco-management is explained, including the connotation, construction requirements and practical significance, and the data analysis of the intelligent financial eco-management model is carried out using the BOA-MLP evaluation model. From the smart financial eco-management model perspective, the most popular among enterprises is the capital pool model, accounting for 59.91%. From the financial level, the average percentages of A, B, C and D evaluations are 46.99%, 29.45%, 14.61% and 8.95%, respectively. The overall percentage of evaluations at grade C or above at the management level was 94.04%. This indicates that the intelligent financial, and ecological management model based on the BOA-MLP evaluation model should be based on the capital pool model, which can realize the financial, and ecological management information more effectively.

Selection of Optimal Process Parameters to Obtain Defect-Free Builds in IN718 Made by Laser Powder Bed Fusion

Selection of Optimal Process Parameters to Obtain Defect-Free Builds in IN718 Made by Laser Powder Bed Fusion

ПОДБОР ОПТИМАЛЬНЫХ ПАРАМЕТРОВ ЭКСТРАГИРОВАНИЯ ФЕНОЛЬНЫХ СОЕДИНЕНИЙ ИЗ ТРАВЫ ЦИКОРИЯ ОБЫКНОВЕННОГО

Relevance. The selection of optimal parameters for the extraction of plant raw materials is one of the key tasks to ensure a high yield of biologically active substances in the resulting extract. When obtaining plant extracts, it is necessary to ensure the efficiency of ongoing technological operations, as well as to use reagents, the use of which is economically feasible. It is of interest to study and select the optimal parameters for obtaining an extract from raw materials of Cichorium intybus L. fam. Asteraceae. When studying the scientific patent literature, it was found that the existing methods for obtaining an extract of chicory involve multiple extraction and the use of mainly chicory root as a raw material. It is important to obtain a dry extract from chicory herb, which ensures a reduction in the extraction time and the use of solvents in the technological process, which can be used both in extraction and in the purification of the resulting extract - water and ethyl alcohol. The use of selected optimal extraction parameters can make it possible to obtain concentrated extracts from chicory raw materials containing high concentrations of biologically active substances (phenolic compounds). Purpose: selection of optimal parameters for the extraction of phenolic compounds from the herb Cichorium intybus L. Materials and methods. The object of the study was the dried herb of C. intybus L. The optimal parameters for the extraction of the studied herb of C. intybus L. were determined (the nature and concentration of the extractant, the fineness of the raw material, the ratio between the mass of the raw material and the volume of the extractant, the extraction temperature, the extraction time, the extraction ratio), and the quantitative content of phenolic compounds was also established. Results. It has been established that the optimal extractant for extracting phenolic compounds from the herb of C. intybus L. is 70% ethyl alcohol, the optimal grinding of the raw material is 1 mm, the optimal ratio between the mass of the raw material and the volume of the extractant is 1:10, the optimal extraction temperature is 80 ℃, the optimal extraction time – 1.5 h, the optimal multiplicity of extraction – single. The use of selected optimal parameters makes it possible to obtain an extract from the herb of C. intybus L., which is characterized by a high content of phenolic compounds. The extract from the herb of C. intybus L. subjected to thickening and drying is a dry extract of the herb of C. intybus L. The obtained dry extract of chicory herb was standardized according to the following quality indicators: organoleptic characteristics, solubility, technological parameters, content of biologically active substances. It was determined that the obtained dry extract of the herb of C. intybus L. contains high concentrations of phenolic compounds (in particular, hydroxycinnamic acids and flavonoids). Conclusion. The optimal parameters for the extraction of biologically active substances from the Cichorium intybus L. herb have been selected, which make it possible to obtain the final product – the dry extract of chicory herb, which is a source of natural antioxidants of a phenolic nature, which can later be recommended for use in the production of biologically active food supplements based on it.

Tree-Structured Parzan Estimator–Machine Learning–Ordinary Kriging: An Integration Method for Soil Ammonia Spatial Prediction in the Typical Cropland of Chinese Yellow River Delta with Sentinel-2 Remote Sensing Image and Air Quality Data

Spatial prediction of soil ammonia (NH3) plays an important role in monitoring climate warming and soil ecological health. However, traditional machine learning (ML) models do not consider optimal parameter selection and spatial autocorrelation. Here, we present an integration method (tree-structured Parzen estimator–machine learning–ordinary kriging (TPE–ML–OK)) to predict spatial variability of soil NH3 from Sentinel-2 remote sensing image and air quality data. In TPE–ML–OK, we designed the TPE search algorithm, which encourages gradient boosting decision tree (GBDT), random forest (RF), and extreme gradient boosting (XGB) models to pay more attention to the optimal hyperparameters’ high-possibility range, and then the residual ordinary kriging model is used to further improve the prediction accuracy of soil NH3 flux. We found a weak linear correlation between soil NH3 flux and environmental variables using scatter matrix correlation analysis. The optimal hyperparameters from the TPE search algorithm existed in the densest iteration region, and the TPE–XGB–OK method exhibited the highest predicted accuracy (R2 = 85.97%) for soil NH3 flux in comparison with other models. The spatial mapping results based on TPE–ML–OK methods showed that the high fluxes of soil NH3 were concentrated in the central and northeast areas, which may be influenced by rivers or soil water. The analysis result of the SHapley additive explanation (SHAP) algorithm found that the variables with the highest contribution to soil NH3 were O3, SO2, PM10, CO, and NDWI. The above results demonstrate the powerful linear–nonlinear interpretation ability between soil NH3 and environmental variables using the integration method, which can reduce the impact on agricultural nitrogen deposition and regional air quality.

Mechanism to form nanosized oxides when burning aqueous carbohydrate salt solutions

This paper describes a method for the synthesis of nanosized oxide powders exemplified by Al2O3, MgO, and SiO2, which includes combustion of a saturated aqueous solution of salts and carbohydrates with multi-stage thermal treatment. A new approach to the synthesis of dispersed oxides with controlled properties has been developed. Particular attention is paid to the selection of optimal synthesis parameters (ratio of components, temperature, processing time) and analysis of phase transformations in the process of formation of nanosized powders with low bulk density. The stages of structural transformations of nanosized oxide particles during multistage heat treatment of an element-containing polymer matrix have been established. The synthesized Al2O3, MgO, and SiO2 nanoparticles are highly reactive due to their disordered defect structure.

Design and industrial implementation of a multi-functional part produced by powder bed fusion

The use of robot end-effectors programmed to perform handling tasks in industrial environments has expanded in several sectors as a consequence of the rapid digital transformation seen in recent years. With such growing demands, additive manufacturing is evolving in the robotics field with more efficient, innovative, and customer-specific solutions owing to its design flexibility. Thus, this work presents a robot end-effector developed and produced by powder bed fusion (PBF) to execute palletizing operations in the automotive electronics industry, where electrostatic discharge interference is a critical concern. To guarantee the functionality of the developed robot end-effector under real conditions of implementation, prototypes of polyamide 12 (PA12) and PA12 incorporating graphene nanoplatelets were fabricated and characterized. This included the assessment of the mass, electrical surface resistance, and mechanical properties under tensile and compressive loads using biaxial strain gauges coupled to the prototypes for local strain monitoring. The experimental data were then used to define multilinear isotropic hardening models needed to numerically characterize the robotic system. At last, the final product was validated in an industrial environment at Bosch Car Multimedia S.A. Through the applied methodology, valuable insights in guiding process parameters optimization and materials selection for functional PBF parts depending on the technical requirements demanded by industrials are provided.

Performance evaluation of abrasive water jet machining on spent garnet reinforced hybrid composite

In recent years, garnet from abrasive water jet machining has been used for cutting-edge technologies. Specifically, spent garnet abrasive particles posses significant strength in nature and have been used for strengthening polymer composites for new applications such as aero blade rotors and the construction industry. The spent garnet received from the abrasive water jet machine (AWJM) has been fed to 30 mesh size using a sieve shaker, which is used to reinforce the glass fiber polymer composite. The hybrid polymer composite was fabricated using a wet hand lay-up technique, and AWJM was used to cut the polymer composite. The machining output responses of surface roughness (Ra) was measured using an SJ-210 m, and kerf was measured using a video measurement system (VMS). Kerf taper (KT) and surface roughness (Ra) were measured by changing the machining inputs of AWJM. The KT and Ra were controlled by varying the input parameters. Moreover, it was found that the kerf was influenced by the amount of spent garnet reinforced in the glass fiber, which ranged from the range of 5% to 15%. Subsequently, cut surface smoothness was predominantly affected by the addition of spent garnet more than 10%. Increasing water jet pressure mainly improves the surface quality and reduces the kerf width. The abrasive flow rate mainly affects the Ra and is just the reverse of water jet pressure. The selection of optimal AWJM parameters is desirable for hybrid composite machining.

DDoS attack detection in smart home applications

AbstractIn smart applications, edge nodes are deployed to perform faster computations. Due to the limited computational capability of edge nodes, collaborative computing is used in which multiple edge nodes collaborate for request processing. For faster processing, these edge nodes are used in many applications namely, smart homes, smart farming, healthcare and so forth. In this paper, we have discussed the use of edge nodes in smart home applications. The smart home application contains different types of sensors and these sensors generate various types of data. Edge nodes are used in these applications for the immediate processing of data. A data classifier is used to classify the data and to reduce delay in data processing. However, the data classifier is more susceptible to DDoS attacks. Hence, an efficient attack detection mechanism is required to detect DDoS attacks. We have used a Feature Selection SVM (FSSVM) algorithm to select optimal parameters for attack recognition. In this algorithm, the information gain ratio is used for optimal parameter selection, and SVM is used for classification. The FSSVM algorithm has been compared with KPCA‐SVM, SVM, and Naive Bayes. Simulation results show that the FSSVM algorithm provides better accuracy compared to KPCA‐SVM, SVM, and Naive Bayes algorithms.

Enhancing the drilling efficiency through the application of machine learning and optimization algorithm

This article presents a novel Artificial Intelligence (AI) workflow to enhance drilling performance by mitigating the adverse impact of drill-string vibrations on drilling efficiency. The study employs three supervised machine learning (ML) algorithms, namely the Multi-Layer Perceptron (MLP), Support Vector Regression (SVR), and Regression Decision Tree (DTR), to train models for bit rotation (Bit RPM), rate of penetration (ROP), and torque. These models combine to form a digital twin for a drilling system and are validated through extensive cross-validation procedures against actual drilling parameters using field data.The combined SVR - Bit RPM model is then used to categorize torsional vibrations and constrain optimized parameter selection using the Particle Swarm Optimization block (PSO). The SVR-ROP model is integrated with a PSO under two constraints: Stick Slip Index (SSI<0.05) and Depth of Cut (DOC<5 mm) to further improve torsional stability. Simulations predict a 43% increase in ROP and torsional stability on average when the optimized parameters WOB and RPM are applied. This would avoid the need to trip in/out to change the bit, and the drilling time can be reduced from 66 to 31 h.The findings of this study illustrate the system's competency in determining optimal drilling parameters and boosting drilling efficiency. Integrating AI techniques offers valuable insights and practical solutions for drilling optimization, particularly in terms of saving drilling time and improving the ROP, which increases potential savings.

Exergy-based methodology to develop design guidelines for performance optimization of a coupled co-axial thermoacoustic refrigerator

Performance of thermoacoustic (TA) systems are very complex, and their performance optimization is a difficult task, and most TA systems have relatively very low efficiencies. The main objective of this study was to develop an exergy analysis to introduce a guide for a designer, how to optimize the performance of a TA system. We have applied this methodology to a coupled thermoacoustic engine and refrigerator with a standing wave in the engine and a traveling wave in the refrigerator. In an optimization procedure, a lumped systems numerical analysis was performed to predict the main parameters of the thermoacoustic system. The numerical method was validated by comparison with numerical and experimental results in the literature. The cost function was the total system coefficient of performance, and design parameters include the refrigerator regenerator length, location, and hydraulic radius. The performance index was decomposed into three main subsystem indices, i.e., the efficiency of the engine, the efficiency of the resonator, and the coefficient of performance of the refrigerator. The optimum point for each component was found, and the total system optimal point which is a result of thermoacoustic interaction of all segments were analyzed. It was illustrated how a change in design parameters could affect the pressure and velocity amplitude and phase distribution in different subsystems, which help the designer deal with the challenge of the optimal parameter selection to enhance the system performance. Finally, an exergy analysis was introduced to assess loss mechanism's contribution to each refrigerator's component. This result in a roadmap for optimization of the system. A new parameter called non-dimensional exergy loss portion (NELP) was introduced, which may significantly show the improvement potential in each system component.

Diabetes risk prediction model based on community follow-up data using machine learning

Diabetes is a chronic metabolic disease characterized by hyperglycemia, the follow-up management of diabetes patients is mostly in the community, but the relationship between key lifestyle indicators in community follow-up and the risk of diabetes is unclear. In order to explore the association between key life characteristic indicators of community follow-up and the risk of diabetes, 252,176 follow-up records of people with diabetes patients from 2016 to 2023 were obtained from Haizhu District, Guangzhou. According to the follow-up data, the key life characteristic indicators that affect diabetes are determined, and the optimal feature subset is obtained through feature selection technology to accurately assess the risk of diabetes. A diabetes risk assessment model based on a random forest classifier was designed, which used optimal feature parameter selection and algorithm model comparison, with an accuracy of 91.24% and an AUC corresponding to the ROC curve of 97%. In order to improve the applicability of the model in clinical and real life, a diabetes risk score card was designed and tested using the original data, the accuracy was 95.15%, and the model reliability was high. The diabetes risk prediction model based on community follow-up big data mining can be used for large-scale risk screening and early warning by community doctors based on patient follow-up data, further promoting diabetes prevention and control strategies, and can also be used for wearable devices or intelligent biosensors for individual patient self examination, in order to improve lifestyle and reduce risk factor levels.

Influencing parameters of recharge efficiency and well types optimization in middle-deep sandstone geothermal reservoir

ABSTRACT Recharge efficiency is of importance to ensure the sustainable utilization of geothermal resources. However, there are still challenges for reinjection work of porous sandstone in North China. The present work aims at optimizing reinjection parameters and well types based on the high recharge efficiency, and it was studied by establishing a numerical model of geothermal production-reinjection and designing an indoor reinjection experiment. It is observed that the effects of skin coefficient, daily reinjection amount, well diameter, well inclination angle, and water layer thickness ratio on the recharge efficiency are decreased in turn. In order to ensure the high efficiency of reinjection work, the mode of two reinjectors and one producer should be selected, preferentially considering around 60° directional well or horizontal well. The skin coefficient should be controlled about 1, the well diameter is greater than 81/2 in, the daily reinjection amount is greater than 2320 m3, and the water layer thickness ratio is about 1:3. The present results can provide helpful references for optimal selection of reinjection parameters and well types of Sandstone Geothermal Reservoir.

FSO-Based Space-Air-Ground Integrated Vehicular Networks: Cooperative HARQ With Rate Adaptation

Space-air-ground integrated vehicular networks (SAGIVN) have been widely envisioned as a promising network architecture for 6 G to support the Internet of Vehicles (IoV). In SAGIVN, free-space optics (FSO)-based, high altitude platform (HAP) relay-assisted low Earth orbit (LEO) satellite systems have recently attracted research efforts worldwide. Critical challenges in designing and implementing FSO-based SAGIVN include atmospheric turbulence, weather conditions, and pointing misalignment. This paper offers a comprehensive cross-layer design framework of error-control protocols with rate adaptation for FSO burst transmissions in HAP-aided SAGIVN. Remarkably, we propose a design of link-layer cooperative incremental redundancy (IR) hybrid automatic repeat request (HARQ)-based sliding window mechanism. An analytical channel model for HAP-aided LEO satellite to emerging unmanned aerial vehicles (UAVs) FSO links is provided. At the same time, the analysis can also be applied to other kinds of vehicles. The queuing behavior induced by both the cooperative IR-HARQ protocol and the rate adaptation scheme is analyzed with a Markov model. Several performance metrics are analytically obtained, including the average round-trip frame delay, throughput, and energy efficiency. The results quantitatively demonstrate the impact of atmospheric turbulence and weather conditions on the system performance and support the optimal selection of system parameters. Additionally, the effectiveness of the proposed system is numerically confirmed. Monte Carlo simulations are also performed to validate the accuracy of theoretical derivations.

Ingenious integration of Fe0 and multiphased MoS2 to activate peroxymonosulfate for carbamazepine removal at high salinity condition

To tackle high salinity challenge, differently from singlet oxygen-governed systems, extremely abundant and highly reactive sulfate radicals (SO4•─)-dominated systems might be also feasible. Ingenious integration of two active popular catalysts, and optimal selection of reaction parameters could sufficiently activate the added peroxymonosulfate (PMS) to efficiently degrade complicated pollutants within a short time so as to overlook the negative effects of inorganic anions. Herein, zero-valent iron decorated metallic 1T/semiconducting 2H hybrid phased molybdenum disulfide with different Mo/S feeding ratio (Fe0/Nx-MoS2) were constructed and compared to activate PMS for carbamazepine (CBZ) removal, where Fe0/N2-MoS2 (M(Mo):M(S) = 7:30) with ultrathin sheet morphology presented most charming decontamination performance. Optimal Fe0/N2-MoS2 dosage and PMS amount was respectively selected as 75 and 50 mg·L-1 in treating 10 mg·L-1 CBZ at pH = 3.00 via tailoring reaction parameters. CBZ could be completely removed in a short time of 10 min with a high pseudo-first-order kinetic rate constant of 0.939 ± 0.016 min−1. The system exhibits the promising anti-interference capacity toward Cl─, NO3─ and SO42─ of high concentration (even up to 3000 mg·L-1). Electron paramagnetic resonance and scavenging experiments of reactive species suggested that SO4•─ played a dominant function. Furthermore, Mo and Fe bimetallic cycles could efficiently promote PMS activation to produce rich reactive radicals. Degradation pathways and toxicity evolutions for CBZ in the (Fe0/N2-MoS2 + PMS) system were proposed via liquid chromatography time-of-flight mass spectrometer and Toxicity Estimation Software Tool, and we hope that the system would be applied in high salinity wastewater treatment in future.

IMPACT OF GEOMETRIC PARAMETERS ON THE CHOICE OF A CUSTOM FEMORAL IMPLANT

In this paper, the effects of both geometric parameters and mineral density on the evolution of stresses generated in a cementless hip implant are investigated to enable orthopedic surgeons to make an appropriate selection. A design of experiment was used, followed by the analysis of variance (ANOVA) to identify the effects of geometric and physical parameters in terms of bone density on a femoral implant. Twenty-seven implants of different geometric dimensions were considered, without modification of the topology. Multiple regression analysis was chosen to replace the finite element method to predict the level of stresses generated in the stem, in terms of life expectancy, allowing for optimal geometric parameter selection. Three parameters of the stem were selected, namely, stem length (SL), neck length (NL), and neck shaft angle (NSA), where each parameter is apprehended by three levels. Based on a design (3[Formula: see text], 27 femur–implant CAD models were created, to analyze the effect of three limiting densities (low, medium, and high) for the estimation of maximum stresses by finite elements. The results obtained by ANOVA for the three densities, respectively, for the low density the SL had an impact of the order of 58.5% on the level of von Mises constraints followed by the NL and NSA. For the medium density, it was observed that the SL remains the most influential parameter, with a rate of 41.2%, while for the high density the NL becomes the most influential (37.5%) followed by the SL and the NSA. The regression model used showed very good accuracy in terms of predicting the level of von Mises stress, compared to the results obtained by the finite element method.

Fast robust enhanced trend filter: A promising tool for automatically extracting high precision friction coefficient under unknown noise

Friction coefficient is the core parameter of material friction performance test. However, it often suffers from complex unknown noise, which frequently follows non-Gaussian distribution, such as outliers during the test phase. Moreover, the amount of test data is often very large that lead to the heavy computational burden. Thus, how to efficiently and accurately extract the friction coefficient is becoming a challenging task. To address this challenge, this paper proposes a fast trend filtering method based on Robust Enhanced Trend Filtering (RobustETF) which combines mix of Gaussian (MoG) and non-convex sparsity-inducing functions to extend l1 trend filtering, called Fast RobustETF. First, the sliding window strategy is used to segment the original data, and the wear stage is distinguished via judging the data margin factor inside the window. Then the window data with the largest and smallest margins is selected as the characteristic data segment of the stable and severe wear stage, and we consider the trend kurtosis and variance into the selection of optimal regularization parameters for different wear stages. Then, RobustETF is used in each window for extracting high precision friction coefficient under unknown noise. Finally, the trend signals in all windows are integrated and reconstructed to complete the precise extraction of the friction coefficient. Finally, simulation signals and real friction coefficient signals are used to verify the performance of Fast RobustETF by the comparison with other filtering methods.

Evolutionary Algorithm with Graph Neural Network Driven Cyberbullying Detection on Low Resource Asian Languages

ICT is widely adopted by Asian youth and is utilized by people of all ages across the continent. Despite its many advantages, unethical ICT usage can lead to many complications. A harmful application of ICT for social communication and engagement is cyberbullying. Simply adhering to the generally accepted norms and guidelines for cybersecurity will not protect you from cybercrime. Even well-known social media stages like Twitter are safe from this attack. Natural language processing (NLP) research on cyberbullying detection has become popular recently. Even though old-style NLP procedures have become highly cyberbullying, there are still hurdles to overcome. These include the limited character count allowed by social media platforms, an imbalance among comments, ambiguity, and unnecessary use of slang. Models based on (CNNs), Multilayer Perceptrons (MLPs), and (RNNs), have recently shown encouraging results in a variety of NLP tasks. With this motivation, this research develops an African vulture optimization algorithm with a graph neural network-based cyberbullying detection and classification (AVOAGNN-CBDC) model. The proposed AVOAGNN-CBDC technique mainly intends to detect and classify cyberbullying. The AVOAGNN-CBDC technique undergoes data preprocessing in different stages and a FastText-based word embedding process to achieve this. Besides, the AVOAGNN-CBDC technique employs the GNN model for cyberbullying detection and classification. Finally, the AVOA is used for the optimal parameter selection of the GNN model, which helps achieve improved classification performance. The experimental result investigation of the AVOAGNN-CBDC technique is tested on the cyberbullying dataset, and the outcomes highlighted the supremacy of the AVOAGNN-CBDC technique in terms of several measures.

An optimal parameters estimation for the proton exchange membrane fuel cells based on amended deer hunting optimization algorithm

The present research proposes a new optimal dynamic modeling of proton exchange membrane fuel cells (PEMFCs). The main idea is on the optimal selection of the uncertain parameters in the PEMFC dynamic model. To do so, the main objective is considered to minimize the sum of the square error between the model voltage and the experimental voltage data. The minimization technique is based on using an amended version of the Deer Hunting Optimization Algorithm (ADHO) algorithm. For authentication of the presented method, two different case studies including 250 W PEMFC and Nexa PEMFC stacks have been utilized and the results have been compared with the experimental data and some other state-of--of-the--the-art methods, including (N + λ) - ES algorithm, Improved Grass Fibrous Root Optimization (IGFRO) Algorithm, and Adaptive Sparrow Search Algorithm (ASSA) to specify the advantage of the suggested method toward the other comparative methods. Simulation results indicate a promising confirmation between the suggested ADHO algorithm and the empirical data.