Weight Parameters Research Articles

A meta-heuristic extension of the Lagrangian heuristic framework

Lagrangian heuristics for discrete optimization work by modifying Lagrangian relaxed solutions into feasible solutions to an original problem. They are designed to identify feasible, and hopefully also near-optimal, solutions and have proven to be highly successful in many applications. Based on a primal-dual global optimality condition for non-convex optimization problems, we develop a meta-heuristic extension of the Lagrangian heuristic framework. The optimality condition characterizes (near-)optimal solutions in terms of near-optimality and near-complementarity measures for Lagrangian relaxed solutions. The meta-heuristic extension amounts to constructing a weighted combination of these measures, thus creating a parametric auxiliary objective function, which is a close relative to a Lagrangian function, and embedding a Lagrangian heuristic in a search procedure in the space of the weight parameters. We illustrate and make a first assessment of this meta-heuristic extension by applying it to the generalized assignment and set covering problems. Our computational experience show that the meta-heuristic extension of a standard Lagrangian heuristic can significantly improve upon solution quality.

Rheological analysis of network structure of raw natural rubber prepared by different processing techniques

The performance of raw natural rubber (NR) is dominated by its network structure, particular the levels of long chain branching (LCB) and entanglement. Here, three type of raw rubbers were prepared using different processing methods for commercial grade NRs. Linear and nonlinear viscoelastic behaviors, as well as stress relaxation, were analyzed to access their network structures. The third relative harmonic, phase angle, and first to second quarter-period integral ratio of stress curve were utilized as indicators for the nonlinearity of samples. By combining these values with flow activation energy and characteristic times, it can be confirmed that naturally coagulated NR showed higher elasticity than acid-coagulated NR due to high levels of LCB and entanglement, and hot air drying could lead to chain degradation. These findings correlated with molecular weight parameters, gel content and Mooney viscosity results. This research establishes a method for monitoring raw NR quality and predicting its properties.

Lightweight Detection of Train Underframe Bolts Based on SFCA-YOLOv8s

Improving the accuracy and detection speed of bolt recognition under the complex background of the train underframe is crucial for the safety of train operation. To achieve efficient detection, a lightweight detection method based on SFCA-YOLOv8s is proposed. The underframe bolt images are captured by a self-designed track-based inspection robot, and a dataset is constructed by mixing simulated platform images with real train underframe bolt images. By combining the C2f module with ScConv lightweight convolution and replacing the Bottleneck structure with the Faster_Block structure, the SFC2f module is designed for feature extraction to improve detection accuracy and speed. It is compared with FasterNet, GhostNet, and MobileNetV3. Additionally, the CA attention mechanism is introduced, and MPDIoU is used as the loss function of YOLOv8s. LAMP scores are used to rank the model weight parameters, and unimportant weight parameters are pruned to achieve model compression. The compressed SFCA-YOLOv8s model is compared with models such as YOLOv5s, YOLOv7, and YOLOX-s in comparative experiments. The results indicate that the final model achieves an average detection accuracy of 93.3% on the mixed dataset, with a detection speed of 261 FPS. Compared with other classical deep learning models, the improved model demonstrates superior performance in detection effectiveness, robustness, and generalization. Even in the absence of sufficient real underframe bolt images, the algorithm enables the trained network to better adapt to real environments, improving bolt recognition accuracy and detection speed, thus providing technical references and theoretical support for subsequent related research.

A review on model predictive control strategies for AC motor drives

AbstractIn the past decade, model predictive control (MPC) has been widely used in AC motor drives. Although a series of improved MPC strategies have been proposed, researchers are still seeking more effective solutions for different application backgrounds and application requirements to achieve the goals such as algorithm simplification, weighting factor design, parameter robustness enhancement, current/torque ripple suppression, and so on. In this paper, aiming at the above problems, the MPC strategy and its optimisation technology for AC motor drive system are comprehensively reviewed. Firstly, this paper introduces the classical MPC technology with the permanent magnet synchronous motor drive system fed by two‐level voltage source inverter as the control object. Secondly, this paper introduces and discusses the existing MPC optimisation methods from the aspects of current/torque ripple suppression, algorithm simplification, weight factor design and parameter robustness enhancement. Finally, based on the current industrial development requirements for AC motor drive systems and the research status of MPC optimisation methods in the existing literature, the current challenges and future trends of MPC technology are discussed.

Morphological and Morphometric Parameters of the Liver of Newborn Male Rabbits Alexander

Introduction. At present, the study of age-related issues of the liver structure in animals is one of the most important objectives of morphology, since liver diseases occupy one of the leading places among the nosologies causing death of newborn animals, in particular rabbits. At the same time, although the data on the micromorphological structure of the digestive tract of rabbits is extensive, the data on the age-related anatomy of the liver in the animals under study is scarce in the available literature. The aim of the paper is to determine the morphofunctional features of the liver of newborn male rabbits.Materials and Methods. The objects of the study were newborn male rabbits of the “butterfly” breed (n=9), who had no deviations in development and constitution. To establish the anatomical and topographic features and morphometric parameters of the liver of the animals under study, the standard anatomical dissection, Pirogov's cuts, macromorphometric and statistical research methods were used.Results. It has been established that the liver of newborn male rabbits of “butterfly” breed has segmental nature, the caudate process is large, distinct from the other lobes. The papillary process is oval in shape, poorly developed, adjacent to the lesser curvature of the stomach. The quadrate and right lobes of the liver are well developed, and the left lobes are less developed, which entails the horizontal position of the organ. The ligamentous attachments of the liver are well developed. A round ligament of liver (ligamentum teres hepatis) with fetal hepatic vessels can be distinguished. The linear and weight parameters of the liver are characterised by the small absolute and large relative values. The liver index is inversely proportional to the body weight of an animal and is 5.91.Discussion and Conclusion. The obtained morphological and morphometric data is aimed at establishing the standard liver parameters of the clinically healthy newborn male rabbits of the “butterfly” breed. The liver boundaries have been defined taking into account the length, width, thickness parameters of each lobe separately. The organ topography has been defined including the skeletotopy, holotopy and syntopy of the individual lobes and processes of the liver.

Correlation between Pulp Weight and Physio-Biochemical Traits of Mango (Mangifera indica L.) Germplasms

Aim: The present study was conducted to evaluate the relationship between pulp weight and various physio-biochemical attributes among 30 diverse mango (Mangifera indica L.) germplasms under the Tarai region of Uttarakhand. Place and Duration of Study: This investigation was carried out at Horticulture Research Centre, GB Pant University of Agriculture and Technology, Pantnagar, Uttarakhand, during the years 2021 and 2022. Methodology: The selected 30 germplasms included two commercially grown cultivars and 28 primary germplasms sourced from different eco-geographical locations of Uttar Pradesh and Uttarakhand states of India. Pulp weight, physical characteristics (fruit shape index, pulp/stone ratio) and biochemical parameters (Brix/Acid ratio and pH) were measured for each germplasm and statistically laid out in completely randomized design (CRD), and their relationships were analyzed using simple linear regression and Pearson’s correlation coefficients. Results: The maximum values recorded among the studied germplasms were 300.73 g for pulp weight (PMGC-19), 2.41 for fruit shape index (PMSS-31), 0.309 for pulp/stone ratio (PMGC-71), 140.87 for Brix/Acid ratio (PMGC-96) and 5.87 for pH (PMGC-96). Among the physical attributes, pulp weight exhibited a moderate positive correlation with fruit shape index (r = 0.419), indicating that fruits with a higher shape index tend to have increased pulp weight. Whereas, a moderate negative correlation was observed between pulp weight and pulp/stone ratio (r = -0.457), suggesting that as the pulp/stone ratio increases, pulp weight decreases. However, biochemical attributes such as Brix/Acid ratio and pH showed no significant correlation with pulp weight (r = 0.005 and r = 0.018, respectively), indicating an independent influence of these parameters on pulp characteristics. Conclusion: These findings provide important insights into the complex relationships between pulp weight and other physio-biochemical traits in mango, some traits for breeding programs aimed to improving fruit quality and pulp content and identified superior and promising germplasms for cultivation as well as potential parental genotypes in mango improvement programs.

A Weighted AIMD Congestion Control Algorithm for Device-to-Device Communication in 5G Network

ABSTRACT Device-to-Device (D2D) communication offers promising benefits in 5G networks in terms of improved throughput and reduced latency. However, efficient congestion control remains a critical challenge to ensure optimal performance and resource utilization. Existing congestion control mechanisms often struggle with adapting to dynamic network conditions, leading to inefficiencies, such as underutilization of network resources or excessive packet loss. This paper addresses these challenges by proposing a novel Weighted AIMD congestion control algorithm tailored specifically for D2D communication in 5G networks (WACC-D2DC-5GN). Here, the Weighted AIMD Congestion Control Algorithm is proposed for estimating available bandwidth and Hunger Games Search Optimization to optimize the weight parameter of WACC. The proposed algorithm integrates weighted factors that dynamically adjust congestion window sizes based on real-time network feedback. Simulations are run on the NS3-mmWave module, NS3 LTE-A module. The simulation outcomes show that the proposed WACC-D2DC-5GN method attains 27.26%, 20.41%, and 23.26% higher SNR and 16.20%, 26.97%, and 30.34% higher Throughput when analysed with existing techniques like NexGen D-TCP: next generation dynamic TCP congestion control approach (NGD-TCP-CCA), user-centric channel allocation system for 5G higher-speed users by using ML to decrease handover rate (UCC-HSU-MLA), and efficient with reliable hybrid deep learning-allowed method for congestion control in 5G/6G networks (HDL-EMC-CN) respectively.

Investigation of Dynamic Characteristics of Holonomic Robot with Mecanum wheels Based on 3D Parametric Simulation Model

The paper analyzes dynamic characteristics of a four-wheeled mobile robot driven by omnidirectional mecanum wheels. To obtain information about dynamic characteristics of the robot, a computer model was developed in the MATLAB Simulink block modeling software environment. The constructed simulation model allowed to research the behavior of a holonomic mobile object with mecanum wheels in start-braking modes, based not only on its mathematical model, but also ta-king into account the weight and size parameters of the robot, introduced into the model through the integration of a three-dimensional digital prototype of the object. The investigation of the omnidirectional robot dynamics was considered within modeling the acceleration, uniform movement and deceleration of an object on a plane along a rectilinear trajectory. As a result, the dependences of kinematic, dynamic and mechanical characteristics were obtained, such as the dependence of angular velocity and torque of each wheel on time; the dependence of linear velocity of the robot's center of mass on time; the dependence of distance traveled by the robot on time; positioning errors while processing a given movement; spatial visualization of speed fluctuations. With the help of Mechanical Explorer tool, using a digital clone of the robot integrated into the model, an animation of the object’s movement along the trajectory was obtained. This approach, based on the integration of mathematical block and three-dimensional parametric models of the object with the possibility of visualization and animation of the results, allows to most fully investigate the dynamics and kinematics of nonlinear mechatronic systems. The obtained information of positioning errors and speed fluctuations in three coordinates allowed to conclude that there were random fluctuations during the robot’s movement, but their presence did not have a noticeable effect on the accuracy of the specified trajectory.

Sequence-based analysis of the rice CAMTA family: haplotype and network analyses

The calmodulin-binding transcription activator (CAMTA) family contributes to stress responses in many plant species. The Oryza sativa ssp. japonica genome harbors seven CAMTA genes; however, intraspecific variation and functional roles of this gene family have not been determined. Here, we comprehensively evaluated the structure and characteristics of the CAMTA genes in japonica rice using bioinformatics approaches and RT-qPCR. Within the CAMTA gene and promoter sequences, 527 single nucleotide polymorphisms were retrieved from 3,024 rice accessions. The CAMTA genes could be subdivided into 5–14 haplotypes. Association analyses between haplotypes and phenotypic traits, such as grain weight and salt stress parameters, identified phenotypic differences between rice subpopulations harboring different CAMTA haplotypes. Co-expression analyses and the identification of CAMTA-specific binding motifs revealed candidate genes regulated by CAMTA. A Gene Ontology functional enrichment analysis of 690 co-expressed genes revealed that CAMTA genes have key roles in defense responses. An interaction analysis identified 30 putative CAMTA interactors. Three genes were identified in co-expression and interaction network analyses, suggesting that they are potentially regulated by CAMTAs. Based on all information obtained together with the phenotypes of the CRISPR-Cas9 knockout mutant lines of three OskCAMTA genes generated, CAMTA1 likely plays important roles in the response to salt stress in rice. Overall, our findings suggest that the CAMTA gene family is involved in development and the salt stress response and reveal candidate target genes, providing a basis for further functional characterization.

Evaluating the Impact of Novel Incretin Therapies on Cardiovascular Outcomes in Type 2 Diabetes: An Early Systematic Review.

Background This systematic review is registered with CRD42024507397 protocol number and aims to compare the known data about retatrutide on long-term cardiovascular (CV) protection with tirzepatide, an incretin with recent proven CV benefits. Material and Methods The inclusion criteria were (i) original full-text articles that are randomized control or clinical trials; (ii) published within the last ten years; (iii) published in English; and (iv) conducted on adult human populations. The exclusion criteria were articles deruled on cell cultures or mammals. Studies were selected if they (1) included patients with type 2 diabetes mellitus (DM) and CV risk; (2) patients that received either tirzepatide or retatrutide; and (3) provided sufficient information such as the corresponding 95% confidence intervals or at least a sufficient p-value. Studies were excluded if they were a letter to the editor, expert opinions, case reports, meeting abstracts, or reviews; redundant publications; or needed more precise or complete data. Results The seven included studies were assessed for bias with the Newcastle Ottawa scale, heterogenous, and emphasized the potential CV beneficial effect of type 2 DM (T2DM) therapies (glycemia, glycated A1c hemoglobin, body weight, lipid profile, blood pressure and renal parameter). Discussions Further, longer follow-up studies are necessary to verify the long-term CV protection, standardize the specific aspects of CV risk, and compare with subjects without T2DM for a more integrative interpretation of the CV effects independent of the improvement of metabolic activity.

Monte Carlo Simülasyonu ile Yenidoğan Transportunda Fizyolojik Stabilite Risk Skor Değişiminin Tahminlemesi

Yenidoğan yoğun bakım hastalarının transportu yüksek risk ve mortaliteye sahiptir. Bu nedenle transport süreci dikkatle ele alınmalı ve değerlendirilmelidir. Bu sürecin performansının değerlendirildiği transport skorlama sistemleri bulunmaktadır. Bunlardan hastanın fizyolojik stabilite risk skoru değişimini ölçen Transport Risk Index of Physiologic Stability (TRIPS) skorlaması yaygın olarak kullanılmaktadır. TRIPS skor değeri transportun ilk 15 dakika ve sonunda olmak üzere en az iki defa ölçülür. Bu çalışmada 2011-2022 yılları arasında 1117 sayıda hastanın teslim alındığında ilk TRIPS skoru ve teslim edilmeden hemen önce ölçülen TRIPS skor değerleri ile bebeklerin kayıtlı ağırlık parametre değeri alınmıştır. Retrospektif olarak yapılan bu çalışmada hastanın ağırlığına bağlı olarak ölçülen iki TRIPS skor değeri arasındaki fark, Monte Carlo simülasyon modeli ile tahminlenmiştir. Her hasta ağırlık grubu için ayrı ayrı ortalama TRIPS skor farkı taminlenerek, farklı hasta gruplarının transport süreci birbirleri ile kıyaslanarak gruplar arası farklar tespit edilmiş ve süreç analiz edilmiştir. Bu analiz sürecin iyileştirilmesi, planlanması ve kararların alınmasına katkı sağlayacaktır.

Dynamic Viscosity of Polyethylene Glycol (PEG): Data Assessment, Sensitivity Analysis and Robust Modeling via Artificial Intelligence Methods

ABSTRACTAccurate determination of physio‐chemical properties of polyethylene glycol as a green non‐toxic solvent is vital for any chemical and energy process involving polyethylene glycol. Machine learning algorithms are known as robust methods for prediction purposes. This study put forward least squares support vector machine scheme optimized with either particle swarm optimization, genetic algorithm and coupled simulated annealing optimization methods to precisely carry out the prediction task of polyethylene glycol viscosity in terms of its influencing parameters of pressure, temperature and polyethylene glycol molecular weight using a dataset containing experimental pertinent values. An outlier detection algorithm is made use of to confirm the data reliability for model development. In addition, sensitivity study is done to ascertain the relative impacts of each input factor on polyethylene glycol viscosity. The results showed that least squares support vector machine optimized with coupled simulated annealing is the most accurate model for the PEG viscosity prediction task with coefficient of determination of 0.997, average absolute relative error percent of 0.653 and mean square error of 8.005 for all datapoints. In addition, it was found that unlike temperature, we observe an indirect correlation of pressure and polyethylene glycol molecular weight with the pertinent viscosity data. The robustness of the developed least squares support vector machine optimized with coupled simulated annealing is further approved as it outperforms a renowned correlation that is often used for general viscosity prediction.

Tolvaptan and the role of kidney aquaporin-2 abundance in managing volume overload in patients with CKD

ABSTRACT Objective This retrospective study evaluated tolvaptan's efficacy, safety, and predictive indicators in managing volume overload in chronic kidney disease (CKD) patients. Methods CKD patients with volume overload, treated with loop diuretics alone or with tolvaptan at Zhongda Hospital, Southeast University, from 1 March 2022 to 31 December 2023, were included. Patients were divided into loop diuretic (Group C) and loop diuretic combined with tolvaptan (Group T) cohorts. Primary outcomes included volume control, changes in weight, urine output, and laboratory parameters within 1 week post-medication. Adverse events such as hypernatremia and hyperkalemia, etc., were recorded. We further conducted immunohistochemical staining of renal biopsy tissues to investigate the roles of aquaporin-2 (AQP2) in the collecting duct and plasma albumin in predicting the efficacy of tolvaptan. Results Of 174 CKD patients with volume overload, 108 (67.07%) were male. Group C and Group T each comprised 87 patients. At baseline, no significant differences in urine output and weight were noted. By day 3, Group T exhibited a greater increase in urine output (P < .001) and weight reduction (P < .001). At day 7, Group T maintained more significant diuretic effects (P < .001). More Group C patients required ultrafiltration therapy (P = .040). Adverse event rates did not significantly differ. Notably, AQP2 expression in the collecting duct may predict tolvaptan responsiveness, while plasma albumin did not affect efficacy. Conclusion Tolvaptan showed efficacy and safety in managing volume overload in CKD patients. The expression of AQP2 in the collecting duct could predict tolvaptan's efficacy. This study protocol was approved by the Ethics Committee of Zhongda Hospital Affiliated to Southeast University (Approval No. 2023ZDSYLL180-P01, Clinical Trial Registration No. ChiCTR2300075274, Trial Registration Link: https://www.chictr.org.cn/guide.html).

Next-generation monitoring in obstetrics: Assessing the accuracy of non-piezo portable ultrasound technology.

The emergence of handheld ultrasound devices capable of connecting to cell phones or tablets heralds a significant advancement in medical technology, particularly within the field of obstetrics. These devices offer the promise of immediate bedside ultrasound examinations, potentially revolutionizing patient care by enabling fetal assessments in diverse settings. This prospective study aimed to validate the reliability of non-piezo, chip-based handheld ultrasound devices in clinical obstetric practice. Conducted in a university hospital obstetric ward, the study included 100 pregnant women between 17 and 41 weeks of gestation. Participants underwent ultrasound examinations using both conventional and portable point-of-care ultrasound (POCUS) devices to compare the accuracy in estimating fetal weight and other parameters, such as cardiac activity, fetal presentation, placental location, and amniotic fluid volume. The reliability and agreement between the devices were assessed using intraclass correlation coefficients, Bland-Altman plots, and Pearson correlation coefficients. The results show a near-perfect agreement (0.98) and correlation (r = 0.98, p < 0.001) for estimated fetal weight and most biometry measurements between the two types of ultrasound devices, with slight deviations in head circumference and amniotic fluid index measurements. Subgroup analysis revealed variations in agreement and correlation rates with higher BMI and advanced gestational age, indicating areas for further refinement. These findings affirm the high reliability of handheld ultrasound devices for basic obstetric ultrasound evaluations, supporting their integration into daily clinical practice. This technology improves the flexibility and immediacy of prenatal care, although further research is needed to optimize its application across patient populations and treatment settings.

A novel hybrid model based on evolving multi-quantile long and short-term memory neural network for ultra-short-term probabilistic forecasting of photovoltaic power

Probabilistic forecasting is extremely crucial in eliminating uncertainty in photovoltaic (PV) power generation. Quantile regression long and short-term memory neural network (QRLSTM) is widely recognized as promising methods for PV power probabilistic forecasting due to their strong generalization ability. However, these models train the model for each quantile individually, which lacks consideration of the correlation and monotonicity between quantiles, and multiple training leads to excessive computational complexity. Furthermore, the non-differentiable pinball loss function generated by QR places significant demands on the optimization algorithms. To address these issues, this paper proposes an evolutive distributed chaotic particle swarm optimization (EDCPSO)-optimized multi-quantile LSTM (MQLSTM) to achieve high-quality probabilistic PV power prediction. MQLSTM is a multi-output network structure that simultaneously outputs all quantile estimates and adopts a loss function with all quantile scores and non-crossing constraints to guide the training of the model. This approach not only improves the quality and reasonableness of quantile estimations, but also reduces computational difficulty. Then, from the perspective of evolutionary computation, considering the weight parameters of each connection layer in MQLSTM as decision variables, we convert the probabilistic forecasting into an optimization problem and propose a EDCPSO to solve the training difficulty. It implements a targeted distributed chaos strategy based on the evolutionary state to improve convergence speed and search capability. The proposed model is tested to be superior in real cases.

Sustainable urban water management index for developing countries. A case study in Puebla City, Mexico

Several indicator and index frameworks have been reported to assess management efficiency and promote transparency, facilitating decision-making and innovation. However, they cannot be applied in cities with limited information, making them impractical. This study proposes a Sustainable Urban Water Management Index (SUWMI) for such cities, selecting six AquaRating indicators plus two indexes recommended in the Sustainable Development Goal 6, yielding a simplified and practical version for diagnosing the management performance rate of the Water Operating Systems (WOS) in cities. Conceptual and mathematical models were defined for SUWMI, and the eight selected terms were hierarchized based on a decision tree with the participation of an expert panel and further multicriteria decision-making methodology by the Analytic Hierarchy Process (AHP) to calculate the weighting parameters. The selected indicators represent five categories on a percentage scale. The highly populated Puebla City Metropolitan Zone in Mexico was the case study. Information was gathered from five Water Operation Systems (WOS) from 2002 to 2020. The tap water area's coverage and physical efficiency improved despite the population growth due to an adequate political strategy after 2014. The SUWMI values of each WOS diagnoses its performance, highlighting their differences and providing a valuable tool for guiding urban water public policy programs. The paper proposes a simple, fast, and easy-to-calculate index that can be helpful for a broader cluster of cities and urban settlements with deficient available information, which is common in developing countries.

Which to select?: Analysis of speaker representation with graph attention networks.

Although the recent state-of-the-art systems show almost perfect performance, analysis of speaker embeddings has been lacking thus far. An in-depth analysis of speaker representation will be performed by looking into which features are selected. To this end, various intermediate representations of the trained model are observed using graph attentive feature aggregation, which includes a graph attention layer and graph pooling layer followed by a readout operation. To do so, the TIMIT dataset, which has comparably restricted conditions (e.g., the region and phoneme) is used after pre-training the model on the VoxCeleb dataset and then freezing the weight parameters. Through extensive experiments, there is a consistent trend in speaker representation in that the models learn to exploit sequence and phoneme information despite no supervision in that direction. The results shed light to help understand speaker embedding, which is yet considered to be a black box.

Residual multiscale attention based modulated convolutional neural network for radio link failure prediction in 5G

In the realm of the 5 G environment, Radio Access Networks (RANs) are integral components, comprising radio base stations communicating through wireless radio links. However, this communication is susceptible to environmental variations, particularly weather conditions, leading to potential radio link failures that disrupt services. Addressing this, proactive failure prediction and resource allocation adjustments become crucial. Existing approaches neglect the relationship between weather changes and radio communication, lacking a holistic view despite their effectiveness in predicting radio link failures for one day. Therefore, the Dynamic Arithmetic Residual Multiscale attention-based Modulated Convolutional Neural Network (DARMMCNN) is proposed. This innovative model considers radio link data and weather changes as key metrics for predicting link failures. Notably, the proposed approach extends the prediction span to 5 days, surpassing the limitations of existing one-day prediction methods. In this, input data is collected from the Radio Link Failure (RLF) prediction dataset. Then, the distance correlation and noise elimination are used to improve the quality and relevance of the data. Following that, the sooty tern optimization algorithm is used for feature selection, which contributes to link failures. Next, a multiscale residual attention modulated convolutional neural network is applied for RLF prediction, and a dynamic arithmetic optimization algorithm is accomplished to tune the weight parameter of the network. The proposed work obtains 79.03 %, 65.93 %, and 67.51 % of precision, recall, and F1-score, which are better than existing techniques. The analysis shows that the proposed scheme is appropriate for RLF prediction.

An efficient water quality index forecasting and categorization using optimized Deep Capsule Crystal Edge Graph neural network.

The world's freshwater supply, predominantly sourced from rivers, faces significant contamination from various economic activities, confirming that the quality of river water is critical for public health, environmental sustainability, and effective pollution control. This research addresses the urgent need for accurate and reliable water quality monitoring by introducing a novel method for estimating the water quality index (WQI). The proposed approach combines cutting-edge optimization techniques with Deep Capsule Crystal Edge Graph neural networks, marking a significant advancement in the field. The innovation lies in the integration of a Hybrid Crested Porcupine Genghis Khan Shark Optimization Algorithm for precise feature selection, ensuring that the most relevant indicators of water quality (WQ) are utilized. Furthermore, the use of the Greylag Goose Optimization Algorithm to fine-tune the neural network's weight parameters enhances the model's predictive accuracy. This dual optimization framework significantly improves WQI prediction, achieving a remarkable mean squared error (MSE) of 6.7 and an accuracy of 99%. By providing a robust and highly accurate method for WQ assessment, this research offers a powerful tool for environmental authorities to proactively manage river WQ, prevent pollution, and evaluate the success of restoration efforts. PRACTITIONER POINTS: Novel method combines optimization and Deep Capsule Crystal Edge Graph for WQI estimation. Preprocessing includes data cleanup and feature selection using advanced algorithms. Deep Capsule Crystal Edge Graph neural network predicts WQI with high accuracy. Greylag Goose Optimization fine-tunes network parameters for precise forecasts. Proposed method achieves low MSE of 6.7 and high accuracy of 99%.

Measurement method of flexible component pose based on discrete motion actuators

Abstract In order to address the limitations of traditional large discrete motion actuator mechanisms in realizing high-precision inter-axis relationship calibration in manufacturing environments, this paper proposes a new convolutional neural network-based attitude mapping estimation method, component pose using convolutional neural network (CPCNN). The method implicitly encodes the inter-axis relation matrix into the weight parameters of the training neural network, which results in a high degree of integration with existing large discrete motion actuator mechanisms. The CPCNN-based method directly obtains the attitude change of the adjustment cabin by reading the change of each axis of the current motion actuator mechanism in its own coordinate system. This method can overcome the limitations of the experimental process in the traditional calibration methods and improve the accuracy of attitude mapping under the influence of self-weight by selecting better motion parameters through redundant degrees of freedom. The application of this new method will provide an effective solution for the high-precision inter-axis relationship calibration of large discrete motion actuator mechanisms in manufacturing environments, offering new possibilities for improving production efficiency and product quality.