Health monitoring and fault diagnosis of rolling bearings are crucial for the continuous and effective operation of mechanical equipment. In order to improve the accuracy of BP neural network in fault diagnosis of rolling bearings, a feature model is established from the vibration signals of rolling bearings, and an improved genetic algorithm is used to optimize the initial weights, biases, and hyperparameters of the BP neural network. This overcomes the shortcomings of BP neural network, such as being prone to local minima, slow convergence speed, and sample dependence. The improved genetic algorithm fully considers the degree of concentration and dispersion of population fitness in genetic algorithms, and adaptively adjusts the crossover and mutation probabilities of genetic algorithms in a non-linear manner. At the same time, in order to accelerate the optimization efficiency of the selection operator, the elite retention strategy is combined with the hierarchical proportional selection operation. Using the rolling bearing dataset from Case Western Reserve University in the United States as experimental data, the proposed algorithm was used for simulation and prediction. The experimental results show that compared with the other seven models, the proposed IGA-BPNN exhibit superior performance in both convergence speed and predictive performance.

In the face of the escalating global energy demand, the challenge lies in enhancing the extraction of oil from low-pressure underground reservoirs. The conventional artificial gas lift method is constrained by the limited availability of high-pressure gas for injection, which is essential for reducing hydrostatic bottom hole pressure and facilitating fluid transfer to the surface. This study proposes a novel \'smart gas\' concept, which involves injecting a gas mixture with an optimized fraction of CO2 and N2 into each well. The research introduces a dual optimization strategy that not only determines the optimal gas composition but also allocates the limited available gas among wells to achieve multiple objectives. An extensive optimization process was conducted to identify the optimal gas injection rate for each well, considering the limited gas supply. The study examined the impact of reducing available gas from 20 to 10 MMSCFD and the implications of water production restrictions on oil recovery. The introduction of smart gas resulted in a 3.1% increase in overall oil production compared to using natural gas. The optimization of smart gas allocation proved effective in mitigating the decline in oil production, with a 25% reduction in gas supply leading to only a 10% decrease in oil output, and a 33% reduction resulting in a 26.8% decrease. The study demonstrates that the smart gas approach can significantly enhance oil production efficiency in low-pressure reservoirs, even with a substantial reduction in gas supply. It also shows that imposing water production limits has a minimal impact on oil production, highlighting the potential of smart gas in achieving environmentally sustainable oil extraction. Furthermore, the implementation of the smart gas approach aligns with global environmental goals by potentially reducing greenhouse gas emissions, thereby contributing to the broader objective of environmental sustainability in the energy sector.

Brain-computer interface (BCI) technology holds promise for individuals with profound motor impairments, offering the potential for communication and control. Motor imagery (MI)-based BCI systems are particularly relevant in this context. Despite their potential, achieving accurate and robust classification of MI tasks using electroencephalography (EEG) data remains a significant challenge. In this paper, we employed the Minimum Redundancy Maximum Relevance (MRMR) algorithm to optimize channel selection. Furthermore, we introduced a hybrid optimization approach that combines the War Strategy Optimization (WSO) and Chimp Optimization Algorithm (ChOA). This hybridization significantly enhances the classification model\'s overall performance and adaptability. A two-tier deep learning architecture is proposed for classification, consisting of a Convolutional Neural Network (CNN) and a modified Deep Neural Network (M-DNN). The CNN focuses on capturing temporal correlations within EEG data, while the M-DNN is designed to extract high-level spatial characteristics from selected EEG channels. Integrating optimal channel selection, hybrid optimization, and the two-tier deep learning methodology in our BCI framework presents an enhanced approach for precise and effective BCI control. Our model got 95.06% accuracy with high precision. This advancement has the potential to significantly impact neurorehabilitation and assistive technology applications, facilitating improved communication and control for individuals with motor impairments.

Improvements in the homeostasis model assessment of insulin resistance (HOMA-IR) and homeostasis model assessment of beta-cell function (HOMA-β) significantly reduce the risk of disabling diabetic pathies. Nanoparticle (AuNP-AgNP)-metformin are concentration dependent cross-interacting drugs as they may have a synergistic as well as antagonistic effect(s) on HOMA indicators when administered concurrently. We have employed a blend of machine learning: Artificial Neural Network (ANN), and evolutionary optimization: multiobjective Genetic Algorithms (GA) to discover the optimum regime of the nanoparticle-metformin combination. We demonstrated how to successfully employ a tested and validated ANN to classify the exposed drug regimen into categories of interest based on gradient information. This study also prescribed standard categories of interest for the exposure of multiple diabetic drug regimen. The application of categorization greatly reduces the time and effort involved in reaching the optimum combination of multiple drug regimen based on the category of interest. Exposure of optimum AuNP, AgNP and Metformin to Diabetic rats significantly improved HOMA β functionality (∼63 %), Insulin resistance (HOMA IR) of Diabetic animals was also reduced significantly (∼54 %). The methods explained in the study are versatile and are not limited to only diabetic drugs.

OBJECTIVE: To investigate the impact of yoga on successful aging based on the selection, optimization, and compensation model in elderly women.
METHODS: Quasi-experimental study.
METHODS: Seniors\' meeting points and parks and clubs for the old age pensioners of the ministry of education, ministry of healthcare, and the oil corporation in Shiraz, Iran. 68 elderly women within the age range of 60-86 years were divided into a yoga and a control group.
METHODS: The subjects in both groups were asked to complete the selection, optimization, and compensation model questionnaire before and after the intervention. Successful aging was measured using the selection, optimization, and compensation questionnaire.
METHODS: The yoga training program was implemented in 1-h sessions twice a week for eight weeks.
RESULTS: After eight weeks of yoga training, the results showed a significant difference between the pretest and posttest successful aging total scores of the yoga group (P = .005). However, the difference between the yoga and control groups\' posttest mean total scores was not significant (P = .601).
CONCLUSIONS: Based on the results, it seems that yoga training can improve successful aging. Thus, yoga is recommended as an inexpensive and entertaining method.

Successful pretreatments for green lentil wastewater (GLW) were developed to substitute egg. Water to lentil ratio and microwave pretreatment were found to affect foam and emulsion quality, while the addition of salt had no effect on foam and emulsion quality of GLW. The GLW obtained at optimum preconditions was used in the determination of best formulation for muffin quality. Oven type, green lentil flour ratio, GLW ratio leading to the maximum moisture content, volume index, total phenolic content, percent area of air cells, and minimum ΔE values with a constraint of control muffin\'s hardness were determined. Conventional oven baking with the formulation of 5.71% green lentil flour and 18.15% GLW produced comparable product with wheat flour and egg formulation. This study proved that discarded GLW can be used as a substitute for egg, which is an expensive ingredient in bakery.
UNASSIGNED:

The goal of this article was to review studies on distal humerus fracture plates (DHFPs) to understand the biomechanical influence of systematically changing the plate or screw variables. The problem is that DHFPs are commonly used surgically, although complications can still occur, and it is unclear if implant configurations are always optimized using biomechanical criteria. A systematic search of the PubMed database was conducted to identify English-language biomechanical optimization studies of DHFPs that parametrically altered plate and/or screw variables to analyze their influence on engineering performance. Intraarticular and extraarticular fracture (EAF) data were separated and organized under commonly used biomechanical outcome metrics. The results identified 52 eligible DHFP studies, which evaluated various plate and screw variables. The most common plate variables evaluated were geometry, hole type, number, and position. Fewer studies assessed screw variables, with number and angle being the most common. However, no studies examined nonmetallic materials for plates or screws, which may be of interest in future research. Also, articles used various combinations of biomechanical outcome metrics, such as interfragmentary fracture motion, bone, plate, or screw stress, number of loading cycles to failure, and overall stiffness (Os) or failure strength (Fs). However, no study evaluated the bone stress under the plate to examine bone \"stress shielding,\" which may impact bone health clinically. Surgeons treating intraarticular and extraarticular distal humerus fractures should seriously consider two precontoured, long, thick, locked, and parallel plates that are secured by long, thick, and plate-to-plate screws that are located at staggered levels along the proximal parts of the plates, as well as an extra transfracture plate screw. Also, research engineers could improve new studies by perusing recommendations in future work (e.g., studying alternative nonmetallic materials or \"stress shielding\"), clinical ramifications (e.g., benefits of locked plates), and study quality (e.g., experimental validation of computational studies).

The diagnosis of leukemia is a serious matter that requires immediate and accurate attention. This research presents a revolutionary method for diagnosing leukemia using a Capsule Neural Network (CapsNet) with an optimized design. CapsNet is a cutting-edge neural network that effectively captures complex features and spatial relationships within images. To improve the CapsNet\'s performance, a Modified Version of Osprey Optimization Algorithm (MOA) has been utilized. Thesuggested approach has been tested on the ALL-IDB database, a widely recognized dataset for leukemia image classification. Comparative analysis with various machine learning techniques, including Combined combine MobilenetV2 and ResNet18 (MBV2/Res) network, Depth-wise convolution model, a hybrid model that combines a genetic algorithm with ResNet-50V2 (ResNet/GA), and SVM/JAYA demonstrated the superiority of our method in different terms. As a result, the proposed method is a robust and powerful tool for diagnosing leukemia from medical images.

This research was designed to isolate the predominant L-asparaginase-producing fungus from rhizosphere soil of tapioca field and assess the suitable growth conditions required to produce maximum L-asparaginase activity. The Aspergillus tubingensis was identified as a predominant L-asparaginase producing fungal isolate from 15 isolates, and it was characterized by 18S rRNA sequencing. The L-asparaginase-producing activity was confirmed by pink color zone formation around the colonies in modified Czapek Dox agar plate supplemented with 1% L-asparagine. The optimal growth conditions required for the L-asparaginase production by A. tubingensis were optimized as pH 6.0, temperature 30°C, glucose as carbon source, 1.5% of L-asparagine, ammonium sulphate as nitrogen source, rice husk as natural L-asparagine enriched source, and 8 days of the incubation period. The L-asparaginase activity from A. tubingensis was excellent under these optimal growth conditions. It significantly used rice husk as an alternative to synthetic L-asparagine. As a result, this may be considered a sustainable method of converting organic waste into valuable raw material for microbial enzyme production.

Image registration is an essential step in many medical image analysis tasks. Traditional methods for image registration are primarily optimization-driven, finding the optimal deformations that maximize the similarity between two images. Recent learning-based methods, trained to directly predict transformations between two images, run much faster, but suffer from performance deficiencies due to domain shift. Here we present a new neural network based image registration framework, called NIR (Neural Image Registration), which is based on optimization but utilizes deep neural networks to model deformations between image pairs. NIR represents the transformation between two images with a continuous function implemented via neural fields, receiving a 3D coordinate as input and outputting the corresponding deformation vector. NIR provides two ways of generating deformation field: directly output a displacement vector field for general deformable registration, or output a velocity vector field and integrate the velocity field to derive the deformation field for diffeomorphic image registration. The optimal registration is discovered by updating the parameters of the neural field via stochastic mini-batch gradient descent. We describe several design choices that facilitate model optimization, including coordinate encoding, sinusoidal activation, coordinate sampling, and intensity sampling. NIR is evaluated on two 3D MR brain scan datasets, demonstrating highly competitive performance in terms of both registration accuracy and regularity. Compared to traditional optimization-based methods, our approach achieves better results in shorter computation times. In addition, our methods exhibit performance on a cross-dataset registration task, compared to the pre-trained learning-based methods.