Accurate demand forecasting plays a critical role in most furniture businesses’ operational, tactical, and strategic decisions, as the demand in the furniture business is considered seasonal and becomes more complex in crises. In this work, a neural network model using the Long Short-Term Memory (LSTM) method was developed to forecast the demand for specific product groups. LSTM is a leading deep learning model for time series prediction, particularly seasonal, multi-item, and non-linear situations. The developed model was used to predict the demand based on old data before the Covid-19 pandemic and recent data of the first months of the pandemic as a fast response to the crisis. In addition, a comparison study was conducted between the developed model and the traditional planning inventory used by furniture businesses that provided us with the data. The results showed that the Covid-19 pandemic significantly impacted demand forecasting. Also, the fast response to Covid-19 pandemic has slightly increased the model performance. Finally, the comparison study demonstrated that our model is robust and better than the traditional demand forecasting method. Therefore, the developed model may help the business improve inventory and production planning to create a more flexible supply chain.

In this work, a novel approach is presented for the multivariate prediction of hydrological variables, employing a specialized type of recurrent neural network (RNN) known as the long-term memory network (LSTM).The central objective is to develop a flood prediction model using data collected from two hydrological stations situated along the Atrato River in the Choc´o Department, Colombia. The interconnected variables of water level, water flow, and water precipitation are analyzed in this model to enhance flood prediction accuracy. The LSTM model, integrated into an RNN structure, is designed to capture the complex dynamics and cross-correlations inherent in these hydrological variables. Validation involves a comparison with linear and nonlinear Nonlinear AutoRegressive with eXogenous input (NARX) models, considering factors such as estimation error and computational time. Additionally, the study conducts further analysis for water level prediction under two scenarios: utilizing only outflow and inflow measurements or predicting outflow alongside measuring inflow, with the objective of utilizing the proposed approach as a flood early warning system. † This article is a revised and expanded version of a paper entitled Multivariable NARX based Neural Networks Models for Short-term Water Level Forecasting, which was presented at International Conference on Time Series and Forecasting (ITISE-2023), Gran Canaria, Spain, 12th-14th July, 2023.

The influence of the secondary process of evaporation of the reaction product on the kinetics of interaction of gases (O₂, Cl₂, NH₃, H₂O and N₂H₄ vapors) with the surface of some metals (Cr, Pb, Si, Ge) and compounds (BN, SiO₂, SiC) is discussed. Also is considered the case when the growth of the scale is preceded by the process of gas etching of the metal surface. A general equation is given that describes the scale growth-evaporation kinetic (sample mass change - time) curves during the interaction of gases with the surface of metals and compounds. Special cases of parabolic, cubic and fourth degree processes are discussed.

Bio-absorbable stents are a novel tool which relieve stenosis and then resorb as the patient grows, avoiding obligatory re-intervention. This case describes the novel use of an iron bio-absorbable stent in a child with surgically repaired Tetralogy of Fallot who post-operatively developed a severely stenotic right ventricular outflow tract.

The ocean of the planet Earth, which is as thin as a cicada's wings, play a role of catalyst to the evolving of the ancient plates. The ocean and the ancient plates of the planet Earth formed a magic Whirlpool of the Cross “十” shape with double whirl arms. The central core of the Cross “十” shape Ocean-Plate Whirlpool is the Hint Black Hole (HBH) located at the Northwestern Pacific Ocean floor which is decorated with invisible geological age distribution of clam shell. The double whirl arms of ancient plates are distinguished to be left and right at Bering Strait and just formed the ring of fire of the Pacific Ocean.The Cross “十” shape Ocean-Plate Whirlpool of the planet Earth was born at the equatorial area about 66 Ma ago and is rotating anticlockwise and drifting northward by a mini footprint of spiral at s speed of as slow as a snail moves. Obviously, it would come to an end at the North Pole about 100 Ma in the future. So, the lifespan of the Cross “十” shape Ocean-Plate Whirlpool would be about 166 Ma, from birth to death on the planet Earth.What is hidden behind of the evolving of the oceans and the ancient plates is the golden law of geometrical progression of ladder pagoda of attributes evolving of them, which is “1➨2➨4➨2➨1”, including upgrading and downgrading process. It seems to hint that what is happening on the planet Earth, including the top-level species of human race, is actually unique in the Milky Way galaxy in essence.The property roles of expanding and shrinking are existing in the Cross “十” shape Ocean-Plate Whirlpool by face to face and the exchange of property roles took place tens of millions of years ago. And that situation would happen again tens of millions of years in the future. It seems a giant circle of evolving of the exchange of property roles would be drawn by the Cross “十” shape Ocean-Plate Whirlpool in her lifetime.

The Dst index is the geomagnetic storm index used to measure the energy level of geomagnetic storms, and the prediction of this index is of great significance for the geomagnetic storm study and the solar activity. In contrast to traditional numerical modelling techniques, machine learning, which has emerged in decades ago based on rapidly developing computer hardware and software and artificial intelligence methods, has been unprecedentedly developed in geophysics, especially solar-terrestrial space physics. This study chooses two machine learning models, the LSTM (Long-Short Time Memory, LSTM) and EMD-LSTM model (Empirical Mode Decomposition, EMD), to model and predict the Dst index. By building the Dst index data series from 2018-2023, two models were built to fit and predict the data. Firstly, we evaluated the influences of the learning rate and the amount of training data on the prediction accuracy of the LSTM model, and finally, 10-3 was thought as the optimal learning rate; secondly, the two models were used to predict the Dst index in the solar active and quiet periods, respectively, and the RMSE (Root Mean Square Error) of the LSTM model in the active period is 7.34 nT, the CC (correlation coefficient) is 0.96, those of the quiet period are 2.64nT and 0.97; the RMSE and r of EMD-LSTM model are 8.87nT and 0.93 in active time and 3.29nT and 0.95 in the quiet time. Finally, the prediction accuracy of the LSTM model in short time period is slightly better than the EMD-LSTM model. However, there will be a problem of prediction lag, which the EMD-LSTM model can then solve, and can better predict the geomagnetic storm.

The boosted interest in the use of rare earth elements (REEs) in modern technologies had also increase the necessity of their recovery from various sources, including raw materials and wastes. Though Hydrometallurgy plays a key role in these recovery processes, some drawbacks (apparent or not) of these processes, had led to the development of a more environmental friendship subclass named Solvometallurgy, in which non-aqueous solvents substituted to the aqueous media of the hydrometallurgical processing. The non-aqueous solvents chosen for these usages are, besides ionic liquids (ILs), the so-named Deep Eutectic Solvents (DEEs). The utilization of DEEs included the leaching of REEs from the different sources containing them, and also in the separation-purification steps necessary for the yielding of these elements, normally as oxides or salts, in the most purified form. This work reviewed the most recent literature (2023 year) about the utilization of deep eutectic solvents in the recovery of REEs from various sources, and in the coupling of these two (DESs and REEs) to derived compounds to be used in other fields.

Abstract. The remarks by the Supreme Leader of the Islamic Revolution on the toll of the famines that afflicted occupied Iran in World War I and World War II indicate a desire to incorporate these calamities in Iran’s national narrative and collective memory. His criticism of famine historiography and stated toll numbers, and the unfolding catastrophic famine in Gaza, justify and necessitate a fresh look at each famine’s historiography and toll. This article re-estimates the toll of each famine by including many overlooked and neglected primary sources and in ways not previously done. It builds a trajectory of Iran’s demographic development from 1810 to 1944, and derives the toll of each famine. The World War II famine and typhus epidemics had claimed 5.5 million victims and Ayatollah Khamenei’s criticisms concerning its stated duration and toll valid. World War I famine was also more deadly, though the 1869-73 famine was not far behind. At least 15.5 million Iranians died in the two world wars, a fact nowhere reflected in the history of the conflicts. Iran’s 1944 population of 12 million was unchanged from that of 1850 and a century of population growth obliterated

The Indorama Eleme Petrochemical Limited (IEPL) is found in the southern part of Nigeria more specifically on the Rivers State southern religion Nigeria. It consists of five distinct units, each of which generates its own unique trash at a rate of around 3115.98 tonnes per year. This study had the goal of concentrating on the management of the processing wastes in order to minimize the negative effects that they have on the environment. It is necessary to have an understanding of the number, nature, and make-up of IEPL's industrial wastes in order to effectively manage and regulate the development of waste there. As a result, we decided to collect data through the use of questionnaires. The classification of industrial wastes was accomplished by doing a comparative study and synthesis of research that were relevant to the management of petrochemical waste. Because an individual coding system is required for the integrated management of industrial waste, we gave each type of trash a code that consists of thirteen digits. The primary components of trash were catalysts (9.58 percent), metallic materials (7.62 percent), plastic barrels (35.77 percent), coke (12.66 percent), wood (4.47%), oil (4.15%), glass (0.028 percent), cooling tower packaging (6.7 percent), and other material (18.83 percent). According to the findings of the investigation into the physical qualities of the wastes, only 11.81% of these residues were liquid, while 88.19% were solid. The current handling of these wastes has been experiencing significant difficulties as of late. garbage management at IEPL was particularly challenging due to the wide variety of wastes produced there and the dangerous nature of the wastes themselves (88.19% of garbage was hazardous waste). Recycling and reuse of garbage may have been the greatest decision in some situations; yet, incineration and disposal of waste are also necessary options.

This article examines air sampling as an environmental surveillance strategy for early pathogen detection and offers a preliminary comparison of air and wastewater surveillance. Air sampling involves collecting bioaerosols to analyze the microbial composition of the air, utilizing techniques like PCR and metagenomic sequencing. Air sampling appears especially promising for detecting respiratory pathogens and highly transmissible pandemic agents, as these spread primarily via aerosols and droplets. The article details various air sampling techniques, their efficiency, and practical considerations, categorizing them into filtration, impaction, impingement, electrostatic precipitation, and condensation methods. It also explores the composition of airborne microbes, emphasizing the low concentration of viral nucleic acids and the challenges this poses for metagenomic sequencing. The selection of sampling locations, including indoor environments and airplanes, is discussed as critical for effective pathogen detection. Finally, the article contrasts air and wastewater sampling, concluding that while both methods should ideally be explored as layered defenses, air sampling does not collectively appear more promising than wastewater sampling.

Industrial process control systems commonly exhibit features of time-varying, strong coupling, and strong nonlinearity. Obtaining accurate mathematical models of these nonlinear systems and achieving satisfactory control performance is still a challenging task. In this paper, data-driven modeling techniques and deep learning methods are used to accurately capture a category of smooth nonlinear system’s spatiotemporal features. The operating point of these systems may change over time, and their nonlinear characteristics can be locally linearized. We established the LSTM-CNN-ARX model by utilizing a fusion of long short-term memory (LSTM) network and convolutional neural network (CNN) to fit the coefficients of the state-dependent exogenous variable autoregressive (SD-ARX) model. Compared to other models, the hybrid LSTM-CNN-ARX model is more effective in capturing the nonlinear system’s spatiotemporal characteristics due to its incorporating the strengths of LSTM for learning temporal characteristics and CNN for capturing spatial characteristics. The model-based predictive control (MPC) strategy, namely LSTM-CNN-ARX-MPC, is developed by utilizing the model's local linear and global nonlinear features. The control comparison experiments conducted on a water tank system (WTS) show the effectiveness of the developed models and MPC methods.

Breast Cancer diagnosis is one of the most studied problems in the medical domain. In the medical domain, cancer diagnosis has been studied extensively which instantiates the need of early prediction of cancer disease. For obtaining advance prediction, health records are exploited and given as input to an automated system. This paper focuses on constructing an automated system by employing deep learning based recurrent neural network models. A stacked GRU-LSTM-BRNN is proposed in this paper that accepts health records of a patient for determining possibility of being affected by breast cancer. Proposed model is compared against other baseline classifiers such as stacked Simple-RNN model, stacked LSTM-RNN model, stacked GRU-RNN model. Comparative results obtained in this study indicate that stacked GRU-LSTM-BRNN yield better classification performance for predictions related to breast cancer disease.

This article seeks to strengthen efforts in technological developments based on the classification of PET plastic that positively impacts sustainable development and contributes to suitable solutions in collection centers in Mexico. Three experiment designs and machine learning tools for data processing were developed. For the experimentation, three factors were considered: the bottle's size, the amount of liquids inside the bottle, and the label on the bottle. The first experiment was to identify the distance of the sensor from post-consumer PET bottles. The second experiment was to determine the detection ability of the sensor with different levels of liquids inside the bottles, and the third was to determine the detection ability on the bottle labels. A digital lux meter on a microcontroller was developed to monitor illuminance on post-consumer PET plastic when it contains liquid as it passes through a conveyor belt for processing at an average rate of three bottles per second. With the implemented methodology, liquids were satisfactorily detected inside the transparent PET bottles when they had beverages between 25% and 100% of their capacity. Finally, this paper highlights that it is possible to implement an affordable design to identify bottles with liquids for collection centers.

Ensuring the security of vertical applications in fifth-generation (5G) mobile communication systems and previous generations is crucial. These systems must prioritize maintaining the confidentiality, integrity, and availability of services and data. Examples of vertical applications include smart cities, smart transportation, public services, Industry 4.0, smart grids, smart health, and smart agriculture. Each vertical application has specific security requirements and faces unique threats within the mobile network environment. Thus, it is essential to implement comprehensive and robust security measures. This approach helps minimize the attack surface and effectively manage risks. This survey thoroughly examines mobile networks and their security challenges in vertical applications, shedding light on associated threats and potential solutions. Our study considers the interplay between security considerations in 5G, legacy networks, and vertical applications. We emphasize the challenges, opportunities, and promising directions for future research in this field and the importance of securing vertical applications in the evolving landscape of mobile technology.

This document serves as supplemental information to Shapero et al. (2023), which is itself a comment on Nowell et al. (2022). Environmental Health Perspective’s publishing standards for article comments have strict word counts and do not allow the addition of new primary data analyses; therefore, this document provides an additional level of detail and supporting analyses that serve as an important backup to and expansion of Shapero et al. (2023) and that also respond to some comments within the author’s reply to our comments (Holmes and Nowell, 2023). Nowell et al. (2022) evaluated potential PM_2.5 community impacts from sugarcane harvesting. However, their analysis is flawed by erroneous assumptions and misapplied technical approaches, as discussed in Shapero et al. (2023) and as detailed in this supplemental information document. Additionally, the authors ended their analysis with 2018 data, but later data shows no marginal increase in PM_2.5 during sugarcane harvest following 2019 even using the authors’ approach (Holmes and Nowell, 2023). Therefore, the authors’ evaluations have no relevance to current conditions. Nonetheless, even their evaluation and conclusions regarding PM_2.5 concentrations purportedly attributable to sugarcane harvesting prior to 2019 are unsupported and technically unsound as detailed below.

Cities are complex systems requiring urban design models that balance order and disorder. Collective creativity initiatives engage citizens in these processes, empowering bottom-up approaches that prioritize people and social well-being within urban development. This paper investigates an 'Urban Laboratory' as a case study, examining the potential of collective creativity to address urban complexity. The successful and ongoing project 'El Campo de Cebada' in Madrid, Spain, demonstrates how a community transformed a vacant lot into a vibrant social hub. The phases of this study include case selection, data collection, data analysis, and presentation of the results. This study identifies key enabling factors, including agents, management, social dynamics, infrastructure, and actions. These insights offer a methodological framework for designing future collaborative, resilient, and inclusive urban spaces, addressing the complex needs of communities within our cities.

Raru’s plants bark has long been used as traditional medicine in Batak’s tribe. Raru’s bark is derived from several trees that are usually used in a mixture in Batak traditional beverages. This bark is generally used as antidiabetic remedies. This study aims to combine the rarus’s bark extract and mocaf activated-carbon (MAC) in order to study antidiabetics in rats. The combination of raru’s bark extract and MAC were tested on male rats as of Sprague Dawley strain for testing antidiabetic bioactivity. The result showed that antidiabetic activity of raru’s extract and MAC exposed the antidiabetic level declines in rat’s blood. The various treatments of different concentration ratios of raru’s extract and MAC useful in the experiments showed that the levels of blood level reduction were slightly different (14-21%). The raru’s extract pure was observed more effective in decreasing the blood glucose level in rat’s blood, in comparison the positive control. The mixture of raru’s extract and MAC with 75:25 ratio is better than 50:50 ratio. The involvement of MAC in the alleged antidiabetic agent did little in improving the blood glucose level decrease in rat’s blood. Raru’s extract and MAC indicate its potential utilization as an antidiabetic agent.

Objectives: Few studies have evaluated and compared artificial intelligence (AI) models for breast cancer detection on the same database. The purpose is to compare the performances of 3 artificial intelligence algorithms on the same dataset at a free operative threshold and to evaluate how the performance is impacted by the chosen threshold. Materials: In this retrospective single-center study, a dataset of 314 2D screening mammograms performed between 2012 and 2020 was established with a prevalence of 19.6% of histologically proven cancer. Three AI constructors using CE (European conformity) marking algorithms have agreed to take part in the study by submitting the cancer-enriched cohort to their algorithm. They chose a free operative threshold to distinguish benign and malignant mammograms. The most suspicious lesion was marked and correctly located by the AI algorithm. Statistical parameters were analyzed and compared between the algorithms. Results: Regarding both sensitivity and specificity, at the chosen threshold, AI 1 had the best compromise between sensitivity (74%) and specificity (79%). AI 2 had a statistically lower sensitivity (52%; p<0.05) with a higher specificity (98.4%) than the other AI algorithms. AI 3 had a nonsignificant sensitivity difference (69.9%) but a significantly lower specificity (45.3%; p<0.001) than the other two. The performances varied depending on the chosen threshold; when the AI 2 threshold was lowered, the sensitivity increased (69.9%), while a higher specificity (86.1%) was maintained. Conclusion: Two AI algorithms stood out in terms of performance when the threshold was optimized, resulting in an acceptable sensitivity and specificity.

The diagnosis of a chronic disease, such as multiple sclerosis, has both psychological and physical effects. Living with the disease and its uncertain consequences requires a great deal of psychological resilience in order to employ more comprehensive coping strategies in stressful situations. This study investigated the effect of a four-week online self-directed resilience training on the perception of psychological resilience among multiple sclerosis patients. A total of 64 MS patients were recruited for a randomized controlled trial. The experimental group underwent a 28-day online self-directed training program consisting of daily exercises aimed at strengthening a resilient mindset. Psychological resilience was measured through self-assessment immediately before, immediately after, and three months after the training. A repeated measures ANOVA revealed a statistically significant improvement in the perception of four factors related to stress: perceived worries, tension, joy and demands. Two resilience coping strategies were measured, of which one, a resilient orientation, improved significantly in the short and long term. The study suggests that online self-directed resilience training might provide an easily accessible, low-cost option for patients with MS to improve their psychological resilience. The transferability to other patient groups should be examined.

The removable partial denture, despite new technologies and new materials, continues to play a significant role in clinical dental practice. The purpose of the following study was to evaluate the design of new retention devices in Kennedy's second grade classrooms. For the study of "lamellar" retentive devices, 4 prosthetists were chosen and selected, according to inclusion and exclusion criteria, 16 patients, 8 women and 8 men, whose upper arch had to be rehabilitated with a removable partial prosthesis. The results showed that the parameters taken into consideration such as satisfaction, stability, aesthetics and retention had an average score higher than 3.30 (range 1-4), with an average standard deviation of 0.6225 in the 4 indicative parameters that the data they are relatively homogeneous and coherent. In conclusion we can state that the skeletonized prosthesis with lamellar retentions, designed in Kennedy's second grade classes, has shown good acceptance in selected patients

Predicting the prices of cryptocurrency owing to its volatility, instability, and other factors has been challenging; investors and traders especially in Nigeria have been on a constant look for a more reliable way of knowing market trends and prices and while there has been so many research conducted using deep learning, the results for which has fall short of what investors could called a strong predictor. This research reviewed the results of many works that had been done and proposed two types of recurrent neural network (RNNs) namely Long Short-Term Memory and Gated Recurrent Unit (GRU) for predicting the future prices of two of the most common crypto assets namely Bitcoin (BTC) and Ethereum (ETH), these two were selected based on their popularity, the volume traded and their market capitalization. The experiment was conducted in a GPU Jupyter Notebook environment and the performance of our experiment was evaluated on a test set using root mean square error (RMSE) and based on its values, the LSTM presented a better performance with rsme scores of 654.66, and 80.30 respectively for BTC and ETH as compared to GRU. The paper proceeds further to compare the results of this experiment with other related works and we discovered that its performance is a great improvement.

Soil moisture is an important factor affecting the plant growth. For a long time, the convenience, timeliness and accuracy of soil moisture monitoring have been limited due to the backward of observation methods and equipment. Therefore, the quantitative prediction of soil moisture has become a difficult problem. Aiming at the problems of high erection cost, easily damaged sensors and low measurement accuracy of the existing fixed sensor soil moisture monitoring system, a soil moisture prediction model based on the long short term memory neural network (LSTM) integrating the particle swarm optimization (PSO) (PSO-LSTM) is designed and implemented. The hyperparameters of the LSTM network can be obtained based on the excellent global search ability of the PSO algorithm. According to the meteorological data and soil moisture data of Haidian Park in 2019, the long short term memory(LSTM) neural network based prediction model is constructed with input vectors of surface temperature, average temperature, evaporation, sunshine hours, precipitation and average wind speed, and the output vector of soil relative humidity. The results show that compared with the back propagation(BP) neural network, the Elman neural network and the LSTM neural network, the proposed PSO-LSTM model has higher prediction performance.

Many studies in the current literature annotate patterns in stock prices and use computer vision models to learn and recognize these patterns from stock price-action chart images. Additionally, current literature also use Long Short-Term Memory Networks to predict prices from continuous dollar amount data. In this study, we combine the two techniques. We annotate the consolidation breakouts for a given stock price data, and we use continuous stock price data to predict consolidation breakouts. Unlike computer vision models that look at the image of a stock price action, we explore using the convolution operation on raw dollar values to predict consolidation breakouts under a supervised learning problem setting. Unlike LSTMs that predict stock prices given continuous stock data, we use the continuous stock data to classify a given price window as breakout or not. Finally, we do a regularization study to see the effect of L₁, L₂, and Elastic Net regularization. We hope that combining regression and classification shed more light on stock market prediction studies.

Actually, the study aimed to manage and to analyse the results of the laboratory methods, using liver samples, preparing and analizing in pathology service. This mentioned, are known as routinally practice for hepatitis C diagnosis, which conduct to hepatic cirrhosis. In this study direction, chronic liver diseases stimulate a degree of hepatocyte injury. So previously mentioned modifications, alters thet affect the liver architecture and finally ends in cirrhosis are well analyse on microscopic preparates. Folowing morphological steps, it is possible to analyse normal and alterate liver structure, on colored preparates.

Per- and polyfluoroalkyl substances (PFAS) are arguably the most common water contaminants in the world today. While several research experiments have been done to understand and remove PFAS from the environment, there is still a lot of unknown. Little has been known about the use of Machine learning (ML) to understand PFAS. This work hence reviews some leading ML approaches and applications in PFAS studies in the distribution, transport, removal, and occurrence predictions of PFAS. Several evaluation matrices were examined and used to perform this function. There are still a lot of areas whereby ML can be used to improve our PFAS knowledge base, some of these were briefly stated in this review.

Antiphospholipid antibody syndrome (APS) is an autoimmune disorder characterised by thrombosis and the presence of antiphospholipid antibodies (aPL): lupus anticoagulant and/or IgG/IgM anti-β2-glycoprotein I and anticardiolipin antibodies. APS carries significant morbidity for a relatively young patient population from recurrent thrombosis in any vascular bed (arterial, venous or microvascular), often despite current standard of care, which is anticoagulation with vitamin K antagonists (VKA). Platelets have established roles in thrombosis at any site, and platelet hyperreactivity is clearly demonstrated in the pathophysiology of APS. Together with excess thrombin generation, platelet activation and aggregation are the common end result of all the pathophysiological pathways leading to thrombosis in APS. However, antiplatelet therapies play little role in APS, reserved as a possible option of low dose aspirin in addition to VKA in arterial or refractory thrombosis. This review outlines the current evidence and mechanisms for excessive platelet activation in APS, how it plays a central role in APS-related thrombosis, what evidence for antiplatelets is available in clinical outcomes studies and potential future avenues to define how to target platelet hyperreactivity better with minimal impact on haemostasis.

Presenting a case report about a 14-year-old female patient presenting with a history of weakness in all four limbs since the age of 5. The patient has a history of difficulty in walking, wearing footwear, climbing stairs, and performing fine motor tasks. During the neurological examination showed mild spasticity, muscle weakness, areflexia, ill-sustained clonus, and sensory deficits. Radiological examination, including a contrast-enhanced MRI of the brain was done which showed findings that are consistent with Megalencephalic leukoencephalopathy with subcortical cysts, also known as Van der Knaap disease.

A high-resolution catalog for the 2014 Ms6.5 Ludian aftershocks was constructed based on the deep learning phase-picking model (CERP) and the seismic-phase association technology (PALM). A specific training strategy, which combines the advantages of the conventional short-long window average energy ratio algorithm (STA/LTA) and AI algorithm, is employed to retrain the CERP model. The P & S phases were accurately detected and picked on continuous seismic waveforms by the retained AI model. Hypoinverse and HypoDD were utilized for precise location of 3286 events. Compared to the previous results, our new catalog exhibits superior performances in terms of location accuracy and the number of aftershock events, thereby enabling a more de-tailed depiction of the deep-seated tectonic features. According to the distribution of aftershocks, it can be inferred that, (1) the seismogenic fault of Ludian earthquake is the NW-trending Baogunao-Xiaohe Fault. (2) the Ludian aftershocks interconnected the discontinuous NW-trending Baogunao-Xiaohe Fault, and intersected with the Zhaotong-Ludian Fault. (3) It suggests that the NE-trending Zhaotong-Ludian Fault may have been intersected by the NW-trending Baogunao -Xiaohe Fault, indicating that the Baogunao-Xiaohe Fault is likely a rela-tively young Neogene fault.

This study used Dutch potatoes at the end of dormancy as the material to explore the impact of menthol (0.2 and 0.5 g/kg based on potato mass) treatment on sprouting inhibition and potato quality. The findings revealed that a menthol concentration of 0.5 g/kg effectively inhibited potato tuber sprouting and significantly reduced glucoside alkaloids production. After a storage period of 15 days, the sprouting percentage and glucoside alkaloids content of potatoes treated with 0.5 g/kg menthol were observed to be significantly lower at 4.17% and 68.63 mg/kg, respectively, compared to the control group which exhibited values of 100% and 282.01 mg/kg, respectively (P < 0.05). Throughout the storage period, 0.5 g/kg of menthol promoted respiration, reduced malondialdehyde production in potatoes, inhibited polyphenol oxidase activity, and slowed down tissue browning. Additionally, it mitigated the decline in starch and soluble protein content, inhibiting the accumulation of reducing sugars.

Breast cancer brain metastasis (BCBM) is a challenging condition with limited treatment options and poor prognosis. Understanding the interactions between tumor cells and the blood-brain barrier (BBB) is critical for developing novel therapeutic strategies. One promising target is estrogen receptor β (ERβ), which promotes the expression of key tight junction proteins, sealing the BBB and reducing its permeability. In this study, we investigated the effects of 17β-estradiol (E2) and the selective ERβ agonist diarylpropionitrile (DPN) on endothelial and cancer cells. Western blot analysis revealed the expression patterns of ERs in these cell lines, and estrogen treatment upregulated claudin-5 expression in brain endothelial cells. Using in vitro models of the BBB, we found that DPN treatment significantly increased BBB tightness about suppressed BBB transmigration activity of representative HER2-positive (BT-474) and triple-negative (MDA-MB-231) breast cancer cell lines. However, the efficacy of DPN treatment decreased when cancer cells were pre-differentiated in the presence of E2. Our results support ERβ as a potential target for the prevention and treatment of BCBM and suggest that targeted vector-based approaches may be effective for future preventive and therapeutic implications.

This study focused on evaluating the potential of natural fermentation of pea flour (F) to improve the release of antioxidant compounds. Two fermentation conditions of F were performed: 1: 36.4% w/w, 24 h, 30°C (FF1); 2: 14.3% w/w, 24 h, 37°C (FF2); pH values decreased to 4.4-4.7, with a predominance of lactic acid bacteria. An increment of the proteolysis degree (TNBS method) (greater for FF2), polypeptides aggregation and decrease of solubility, increase of &lt; 2 kDa peptides, and increase in the ORAC potency of PBS-soluble fractions after fermentation was demonstrated. After simulated gastrointestinal digestion (SGID, COST-INFOGEST), FF1D and FF2D showed greater proteolysis degrees (63 and 53%) than F1D and F2D (45%), with differences in the molecular composition of the different digests. ORAC and HORAC potencies increased in all cases. FF2D presented the greater ORAC value, with higher activities for &gt; 4 kDa, some in the range 2 to 0.3 kDa. and &lt; 0.10 kDa fractions. Fermentation also increased the 60 % ethanol extracted phenolic compounds, mainly flavonoids, and the ORAC activity. After SGID, the flavan-3-ols disappeared but some phenolic acids increased respect to F. Fermentation in condition 2 was considered the most appropriate to obtain a functional antioxidant ingredient.

Flood forecasting helps anticipate floods and evacuate people, but due to the access of a large number of iot data acquisition devices, the explosive growth of multidimensional data and the increasingly demanding prediction accuracy, classical parameter models and traditional machine learning algorithms are unable to meet the high efficiency and high precision requirements of prediction tasks. In recent years, deep learning algorithms represented by convolutional neural networks, recurrent neural networks and Informer models have achieved fruitful results in time series prediction tasks. The Informer model is used to predict the flood flow of the reservoir. At the same time, the prediction results are compared with the prediction results of the traditional method and the LSTM model, and how to apply the Informer model in the field of flood prediction to improve the accuracy of flood prediction is studied. The data of 28 floods in the Wan 'an Reservoir control basin from May 2014 to June 2020 were used, with areal rainfall in five subzones and outflow from two reservoirs as inputs and flood processes with different sequence lengths as outputs. The results show that the Informer model has good accuracy and applicability in flood forecasting. In the flood forecasting with sequence length of 4, 5 and 6, Informer has higher prediction accuracy, and the prediction accuracy is better than other models under the same sequence length, but the prediction accuracy will decline to a certain extent with the increase of sequence length. The Informer model stably predicts the flood peak better, and its average flood peak difference and average maximum flood peak difference are the smallest. As the length of the sequence increases, the number of fields with a maximum flood peak difference less than 15% increases, and the maximum flood peak difference decreases. Therefore, the Informer model can be used as one of the better flood forecasting methods, and it provides a new forecasting method and scientific decision-making basis for reservoir flood control.

In the quest for sustainable energy solutions, predicting electricity prices for renewable energy sources plays a pivotal role in efficient resource allocation and decision-making. This article presents a novel approach to forecasting electricity prices for renewable energy sources using deep learning models, leveraging historical data from the Power System Operator (PSE). The proposed methodology encompasses data collection, preprocessing, feature engineering, model selection, training, and evaluation. By harnessing the power of recurrent neural networks (RNNs) and other advanced deep learning architectures, the model captures intricate temporal relationships, weather patterns, and demand fluctuations that impact renewable energy prices. The study demonstrates the applicability of this approach through empirical analysis, showcasing its potential to enhance energy market predictions and aid in the transition to more sustainable energy systems. The outcomes underscore the importance of accurate renewable energy price predictions in fostering informed decision-making and facilitating the integration of renewable sources into the energy landscape. As governments worldwide prioritize renewable energy adoption, this research contributes to the arsenal of tools driving the evolution towards a cleaner and more resilient energy future.

Recent SDN advances address traditional network management challenges through centralized control and plane separation. SDN prevents breaches using a centralized controller but introduces risks. The controller can be a single point of failure. Thus, an OpenFlow Controller's flow-based anomaly detection enhances SDN security. Our research explored two OpenFlow intrusion detection methods. The first employed machine learning, NSL-KDD dataset, and feature selection, yielding 82% accuracy with random forest. The second combined deep neural networks with GRU-LSTM, achieving 88% accuracy using ANOVA F-Test and feature elimination. Experiments highlighted deep learning as superior for OpenFlow intrusion detection.

Chatbots are extensively needed in customer services to handle customer inquiries, such as tracking orders or providing information about products and services. One of the most reliable implementations of chatbots is using the common architectures of LSTM networks named Seq2Seq networks. The networks are using an encoder and a decoder. Seq2Seq chatbot is a type of chat system that is professional enough to pass the Turing test. The Turing test is a way of deciding the accuracy of the machine by examining its response, it should appear like a human response. In this research, we will introduce a novel architecture that can pass the Turing test. The seq2seq Accuracy is improved by making incremental training to the chatbot. The new proposal provides higher accuracy and high similarity to human chat responses.

The article considers an approach to the problem of assessing the quality of speech during speech rehabilitation as a classification problem. For this, a classifier is built on the basis of an LSTM neural network for dividing speech signals into two classes: before the operation and immediately after. At the same time, speech before the operation is the standard to which it is necessary to approach in the process of rehabilitation. The metric of belonging of the evaluated signal to the reference class acts as an assessment of speech. An experimental assessment of rehabilitation sessions and a comparison of the resulting assessments with expert assessments of phrasal intelligibility were carried out.

This work addresses the intricate task of predicting the prices of diverse financial assets, including stocks, indices, and cryptocurrencies, each exhibiting distinct characteristics and behaviors under varied market conditions. To tackle the challenge effectively, a novel hybridized architecture, AE-GRU, integrating the encoder-decoder principle with GRU is designed. The experimentation involves multiple activation functions and hyperparameter tuning. With extensive experimentation and enhancements applied to AE-LSTM, the proposed AE-GRU architecture still demonstrates significant superiority in forecasting the annual prices of volatile financial assets from multiple sectors mentioned above. Thus, the novel AE-GRU architecture emerges as a superior choice for price prediction across diverse sectors and fluctuating market scenarios by extracting important non-linear features of financial data and retaining the long-term context from past observations.

Air pollution has been a major environmental issue worldwide from the last few decades. It is a man-made issue that has a serious harmful impact on the environment and the health of humans. There are different sources of emission, but industrial processes and motor vehicles contribute to a chief part of air pollution. It has acute as well as chronic effects on the health of humans and affects different organs. It is thought the main environmental risk factor in the incidence and progression of several diseases such as lung cancer, asthma, Alzheimer's and Parkinson's diseases. Long-term exposure to air pollution has different toxicological impacts on humans such as respiratory and cardiovascular diseases, neuropsychiatric complications, eye irritation and skin diseases. As per the study by the World Health Organization (WHO), nitrogen oxides (NOx), carbon monoxide (CO), ozone (O₃), sulfur dioxide (SO₂), volatile organic compounds (VOCs) and heavy metals are the major air contaminants. These pollutants are different in their properties, composition and time of disintegration. The aim of this study is to review the different sources, types, impacts, challenges and mitigation of air pollution in detail.

Enhancing the Efficiency of Natural Gas Liquid (NGL) Extraction and Fractionation Trains: An Integrated Approach of Simulation Analysis, Advanced Modifications, and Technological Advancements. Through comprehensive research, innovative solutions such as the heat pump aided distillation (HPAD) system and self-heat recuperation technology (SHRT) have been developed to significantly reduce the energy consumption associated with conventional distillation systems. To identify a practical system for NGL fractionation trains, this study extensively examined and compared various HPAD and SHRT options to retrofit a single column. The objective was to find the most suitable and efficient solution for the fractionation process of natural gas liquids (NGLs). The retrofit options analyzed in this study encompassed a range of techniques, including vapor compression (VC), mechanical vapor re-compression (MVR), thermal vapor re-compression (TVR), bottom flashing (BF), side heat exchanger (SHE), intermediate heating and cooling (IHC), self-heat recuperative (SHR), and modified self-heat recuperative (MSHR) distillation. These methods were carefully examined to determine their suitability and effectiveness in improving the performance of NGL fractionation trains.In this study, a depropanizer column, typically employed in conventional NGL plants, was selected as a case study. The simulation software Aspen HYSYS V7.3 was employed to model and analyze eight retrofit designs based on predefined criteria. The simulation data was carefully evaluated to identify the most efficient design for minimizing energy consumption. Among the retrofit options, the mechanical vapor re-compression (MVR) technique demonstrated the most significant energy cost reduction, with a remarkable 68.11 percent improvement compared to the base case conventional column. These findings highlight the potential of MVR as an effective solution for lowering energy costs in NGL fractionation trains.Following the MVR retrofit option, the study found that vapor compression (VC) achieved a considerable energy cost reduction of 66.65 percent, closely followed by modified self-heat recuperative (MSHR) at 64.02 percent, bottom flashing (BF) at 62.88 percent, self-heat recuperative (SHR) at 55.85 percent, side heat exchanger (SHE) at 54.23 percent, intermediate heating and cooling (IHC) at 39.54 percent, and thermal vapor re-compression (TVR) also at 39.54 percent. These findings highlight the significant potential for energy savings offered by these retrofit options, with VC being the most popular choice, closely followed by MSHR, BF, SHR, SHE, IHC, and TVR.

Naturally fermented dairy products are an important component of the human diet. They are a valuable source of nutrients as well as vitamins and minerals. Their importance as a source of probiotic bacterial strains should not be overlooked. A number of studies highlights the positive effects of species of the Lactobacillacea on the intestinal microbiota, the overall homeostasis of the body, as well as a complementary treatment for some diseases. However, data on the effects on intestinal epithelial cells of postmetabolites released by bacteria are incomplete. This is likely due to the fact that these effects are species and strain specific. In the present study, we investigated the effects of postmetabolites produced by a pre-selected candidate probiotic strain Limosilactobacillus fermentum on HT-29 intestinal epithelial cells. Our data showed a pronounced proliferative effect, evaluated by flow cytometry, quantification of cell population, and determination of mitotic index. This was accompanied by stabilization of the cell monolayer, measured by increase of TEER (trans epithelial electric resistance) and reorganization of actin filaments. The data obtained are a clear indication of the positive effects, that the products secreted by L. fermentum strain 53 have on the intestinal epithelial cells.

(1) Background: Until December 2021, French Guiana (FG), located in South America, faced four consecutive COVID-19 epidemic waves. This study sought to analyze the mortality trend of severe COVID-19 patients admitted to the referral ICU of FG. (2) Methods: We conducted a prospective, observational, and non-interventional study in ICU at Cayenne Hospital. We included 383 patients older than 18 admitted with SARS-CoV-2-related pneumonia hospitalized from May 2020 to December 2021. The study covers three periods. Period 1 (Waves 1 and 2, original variant), period 2 (Wave 3, gamma variant), and period 3 (Wave 4, delta variant). (3) Results: The median age was 63 years (52-70). Frailty was diagnosed in 36 patients over 70 (32.4%). Only 4.8% of patients were vaccinated. The median ICU LOS was 10 days (6-19). Hospital mortality was 37.3%. It was 30.9% in period 1, 36.6% in period 2 (p=0.329 vs. period 1), and 47.1% in period 3 (0.015 vs. period 1). In multivariate analysis, independent factors associated with hospital mortality were age more than 40 years (]40-60 years] OR=5.2, 95%CI: 1.4-19.5; (]60-70 years] OR=8.5 95%CI: 2.2-32; (]70+ years] OR=17.9, 95%CI: 4.5-70.9), frailty (OR=5.6, 95%CI: 2.2-17.2), immunosuppression (OR=2.6, 95%CI: 1.05-6.7), and MV use (OR=11, 95%CI: 6.1-19.9). This model had an overall sensitivity of 72%, a specificity of 80.4%, a positive predictive value of 68.7%, and a negative predictive value of 82.8%. (4) Conclusions: The mortality of severe COVID-19 patients in French Amazonia was higher during the delta variant wave. This over-death is explained by the virulence of the responsible SARS-CoV-2 variant and the under-vaccination coverage of the studied population.

Culture signifies the customs, language, ceremonies, Indigenous Medical Knowledge (IMK) and other material objects of a tribe. These and many other features are a representation of identity for many Zambian communities. IMK practices are skills inherent by certain individuals in a tribal grouping who are chosen by the spirits (gods) or trained by those who practice. This intrinsic skill is in danger of diminishing as a result of modern medication. This article attempts to understand the role of traditional healers (also known as asing’anga in local language) in preservation of IMK in Chibombo District of Zambia. In so doing, the paper examined methods of preservation used by asing’anga and the challenges faced. Using hermeneutic phenomenology and linear snowball sampling, findings revealed that preservation was done through training. The study found unwillingness, expiration, and spirituality as challenges in the process of preserving IMK. The study recommended that the Lenje Cultural Association consider documenting and disseminating information to the local people by showcasing what is available in the Mukuni Culture Village Museum and Library. This was seen as a way through which many youths would be encouraged to appreciate the indigenous values in their culture.

: In today’s rapidly expanding era of the Internet of Things (IoT) and the Industrial Internet of Things (IIoT), the emphasis on robust data security and insightful data interpreta- tion is more pronounced than ever. This research introduces a comprehensive approach to both data protection and predictive analytics, leveraging the diverse dataset TON IoT.csv, sourced from a myriad of IoT and IIoT environments. For data security, a dual-encryption technique incorporating both AES and RSA algorithms is established. Its efficacy is evidenced by a perfect match between the original and decrypted datasets, underscoring the integrity of our encryption process. Concurrently, the study ventures into predictive modeling using a modified Snake Optimization Algorithm (SOA) to streamline hyperparameter selection. This subsequently aids in the development and fine-tuning of an LSTM network, which exhibits remarkable predictive accuracy. Additionally, the paper provides an in-depth examination of various encryption methodologies like elliptic curve cryptography (ECC), Lightweight Cryptography for Cloud computing, and homomorphic encryption, while also emphasizing the nuances of encryption in cloud setups, particularly contrasting server-side with client-side encryption and efficient key management. The insights presented serve as a cornerstone for ensuing research, promising a bright future for advancements in IoT and IIoT data protection and analysis

With an explosion of data in the nearly every domain, from physical and environmental sciences to econometrics and even social science, we have entered a golden era of time-domain data science. In addition to ever increasing data volumes and varieties of time-series, there's a plethora of techniques available to analyses them. Unsurprisingly, machine learning approaches are very popular. In environmental sciences (ranging from climate studies to space weather/solar physics), machine learning (ML )and deep learning (DL) approaches complement the traditional data assimilation approaches. In solar and astrophysics, multiwavelength time-series or lightcurves along with observations of other messengers like gravitational waves provide a treasure trove of time-domain data for ML/DL approaches for modeling and forecasting. In this regard, deep learning algorithms such as recurrent neural networks (RNNs) should prove extremely powerful for forecasting as it has in several other domains. Such methods agnostic of the physics can only predict transient flares that are represented in the original distribution trained on (eg. coloured noise fluctuations) and not special, isolated episodes (eg. a one-off outburst like a major coronal mass ejection) potentially distinguishing them. Therefore it is vital to test robustness of these techniques ; here we attempt to make a small contribution to this by exploring sensitivity of RNNs with some rudimentary experiments. We test the performance of a very successful class of RNNs, the Long Short Term Memory (LSTM) algorithms with simulated lightcurves. As an example, we focus on univariate forecasting of time-series (or lightcurves) characteristic certain variable astrophysical objects (eg. active galactic nuclei or AGN). Specifically, we explore the sensitivity of training and test losses to key parameters of the LSTM network and data characteristics namely gaps and complexity measured in terms of number of Fourier components. We find that typically, the performances of LSTMs are better for pink or flicker noise type sources. The key parameters on which performance is dependent are batch size for LSTM and the gap percentage of the lightcurves. While a batch size of $10-30$ seems optimal, the most optimal test and train losses are under $10 \%$ of missing data for both periodic and random gaps in pink noise. The performance is far worse for red noise. This compromises detectability of transients. Thus, we show that generative models (time-series simulations) are excellent guides for use of RNN-LSTMs in building forecasting systems

The deployment of a Static Synchronous Compensator within a microgrid can facilitate voltage and reactive power regulation, leading to enhanced stability and reliability. Within a microgrid setting, a STATCOM can effectively balance power supply and demand, and mitigate voltage fluctuations caused by the intermittent nature of renewable energy sources. To ensure the successful integration of a STATCOM within a microgrid, coordinating the control system with other Distributed Energy Resources, especially when multiple control strategies are employed, can be a challenging task. Therefore, a meticulously designed control system is indispensable to guarantee the microgrid’s efficient and effective operation. The use of GA in LSTM tuning can accelerate the process of finding optimal hyperparameters for a specific task, obviating the necessity for time-consuming and computationally expensive grid search or manual tuning. This method can be particularly advantageous when handling large data sets and complex models. In this paper, an attempt has been made to model the STATCOM to communicate with the microgrid tuned using LSTM-GA for effective calculation of real and reactive power support during grid disturbances.

Cognitive neuroscience is the study of how the human brain functions on tasks like decision making, language, perception and reasoning. Deep learning is a class of machine learning algorithms that use neural networks. They are designed to model the responses of neurons in the human brain. Learning can be supervised or unsupervised. Ngram token models are used extensively in language prediction. Ngrams are probabilistic models that are used in predicting the next word or token. They are a statistical model of word sequences or tokens and are called Language Models or Lms. Ngrams are essential in creating language prediction models. We are exploring a broader sandbox ecosystems enabling for AI. Specifically, around Deep learning applications on unstructured content form on the web.

This study provides a comprehensive comparison of the Peter Chew Sum method and Newton's Sum in Quadratic Root Function Computations. Both methods offer significant advancements by alleviating the need for memorization of multiple formulas. However, when confronted with higher-order quadratic root functions such as the calculation of power 33. Newton's Sum method proves cumbersome due to its requirement of all previous answers for final computation, leading to increased steps and error risks. In contrast, the Peter Chew Sum method simplifies the computational process by requiring only a few previous answers, resulting in a more straightforward series of operations. We contextualize our analysis within the historical progression of mathematical techniques, highlighting the transformative leap represented by the Peter Chew Sum method in quadratic root function computations. Peter Chew Sum addressing the limitations of Newton's Sum , especially concerning higher-order functions such as the calculation of power 256. Furthermore, study demonstrates that the innovative approach of the Peter Chew Sum method not only simplifies complex computations but also fosters enhanced conceptual understanding among students. In conclusion, study findings underscore the profound impact of the Peter Chew Sum method on quadratic root function computations.

This research follows the publication of recent scoping and systematic reviews of existing literature on vaccine literacy (VL), its relationship to vaccine hesitancy (VH), and associated variables, such as vaccination beliefs, attitudes, and behaviors towards immunization. In this review, 17 articles were selected, published between December 2022 and November 2023, in which VL tools were used, most of which support the notion of a negative association between VL and VH, although not confirmed by others. Moreover, the definitions of the variables under consideration were not homogeneous between studies, some aimed to evaluate the association of VL with vaccine confidence, while others were more focused on outcomes such as willingness to be vaccinated or vaccine uptake. The complexity of the factors underlying VL, and the heterogeneity of the methods applied in the studies, in particular the limitations of cross-sectional surveys, still make it difficult to have a comprehensive understanding of the role of VL. Therefore, it is important to develop future assessment tools that consider not just the measurement of psychological factors connected to the motivational aspect of VL, but also those related to knowledge and competencies. For this purpose, a theoretical framework is proposed, where the positioning of VL at the intersection between antecedents and beliefs/attitudes leading to behaviors explains why and how VL serves as a tool and a critical, direct, or mediating driver of vaccination choices, overcoming VH and increasing vaccination rates, operating at personal, as well as at organizational and community level.

The Yellow-legged Hornet (Vespa velutina nigrithorax) (YLH) is an invasive insect that arrived in Europe in 2004 and is now spread across nine countries. It is a threat to the native entomofauna and harmful to beekeeping and agriculture, as it is a ravenous predator of the European Honey Bee (Apis mellifera) and other pollinating species. Its expansion has been unstoppable and all resources are needed to fight against it, including native vertebrate predators. Among these, the European Bee-eater (Merops apiaster) (EBE) is a potential one, but little is known about its predation on YLH. In a study carried out in Portugal, remains of YHL were detected in EBE nesting sites, which to the best of our knowledge is the first such report. This means that this bird could be one more agent in the biological control of this pest (although research on predation intensity is still needed), in conjunction with other natural predators and other strategies. In the Iberian Peninsula both species are allopatric in vast regions, so the role of EBE may be more limited. However, in the rest of Europe, at a country or continent scale, the scenario may be different and sympatry may occur to a greater extent.

This study uses the social impact theory to analyse consumer behaviour amidst Covid-19. Fear of scarcity has changed consumer buying behaviour in crisis times such as the now abating global health crisis – i.e., Covid-19. The study asserts that the existing five-stage model of consumer purchasing decisions does not fit neatly in turbulent times. It proposes a shortened four-stage process of need recognition, purchase, ownership and satisfaction as a better and more adaptable fit. Cutting out information search and evaluation of alternatives in the old model, and replacing these with ownership, is where the main contribution of the study lies. The study has implications for managing the marketing mix as we know it. It asserts that not all the 4Ps of the marketing mix are important in crisis times.

Objective To investigate nailfold capillary parameters in community-dwelling individuals aged over 60 years who have hypertension and do not exercise regularly. Furthermore, the study examined the correlations between capillary function and other health-related indicators. Design A single- center pilot trial Setting Faculty of Health, Tsukuba University of Technology, Japan Participants hypertensive community-dwelling elderly people Intervention Microcirculation was observed before and 1 min after arm-curl exercise by means microscopy of capillary with non-exercised limb. Additionally, we examined other health-related indicators. Outcome measures: Acute effects of reperfusion on nailfold density, flow, and diameters. Secondary outcomes included the correlations between microvascular parameters and other health-related indicators. We hypothesized that brief exercise could enhance microcirculation reperfusion and correlate with other health-related parameters.　 Results: There were 20 participants with a mean (SD) age of 67.1 (5.8) years. The capillary flow rate changed from 2.3±6.7 to 2.7±0.2 log µm/s (P

Text-based CAPTCHA remains the most widely adopted security scheme, which is the first barrier to securing websites. Deep learning methods, especially Convolutional Neural Networks (CNNs) are the mainstream approach for text-CAPTCHA recognition, which are widely used in CAPTCHA vulnerability assessment and data collection. However, verification code recognizers are mostly deployed on the CPU platform as part of a web crawler and security assessment, they are required to have both low complexity and high recognition accuracy. Due to the specifically designed anti-attack mechanisms like noise, interference, geometric deformation, twisting, rotation, and character adhesion in text CAPTCHAs, some characters are difficult to efficiently identify with high accuracy in these complex CAPTCHA images. This paper proposed a recognition model named Adaptive-CAPTCHA with a CRNN module and trainable and configurable filtering networks, which effectively handle the interference and learn the correlation between characters in CAPTCHAs to enhance recognition accuracy. Experimental results on two datasets of different complexity show that compared with the baseline model Deep-CAPTCHA, the number of parameters of our proposed model is reduced by about 70% and the recognition accuracy is improved by more than 10 percentage points in the two datasets. In addition, the proposed model has a faster training convergence speed.

In cutting processes tool condition affects the quality of the manufactured parts. As such an essential component to prevent unplanned downtime and to assure machining quality is having information about the state of the cutting tool. The primary function of it is to alert the operator that the tool has reached or is reaching a level of ware beyond which behavior is unreliable. In this paper the tool condition is being monitored by analyzing the electric current on the main spindle via an artificial intelligence model utilizing a LSTM neural network. In the current study the tool is monitored while working on a cylindrical raw piece made of AA6013 aluminum alloy with a custom polycrystalline diamond tool, for the purposes of monitoring the ware of these tools. Spindle current characteristics were obtained using external measuring equipment to not influence the operation of the machine included in a larger production line. As a novel approach, an artificial intelligence model based on a LSTM neural network is utilized for the analysis of the spindle current obtained during a manufacturing cycle and assessing the tool ware range in real time. The neural network was designed and trained to notice significant char-acteristics of the captured current signal. The conducted research serves as a proof of concept for use of a LSTM neural network-based model as a method of monitoring the condition of cutting tools.

This paper investigates nonverbal communication in human interactions, with a specific focus on facial expressions. Employing a Long Short-Term Memory (LSTM) architecture and a custom-ized facial expression framework, our approach aims to improve virtual agent interactions by incorporating subtle nonverbal cues. The paper contributes to the emerging field of facial expres-sion generation, addressing gaps in current research and presenting a novel framework within Unreal Engine 5. The model's architecture, trained on the CANDOR corpus, captures temporal dynamics, and refines hyperparameters for optimal performance. During testing, the trained model showed a cosine similarity of -0.95. This enables the algorithm to accurately respond to non-verbal cues and interact with humans in a way that is comparable to human-human interac-tion. Unlike other approaches in the field of facial expression generation, the presented method is more comprehensive and enables the integration of a multi-modal approach for generating facial expressions. Future work involves integrating blendshape generation, real-world testing, and the inclusion of additional modalities to create a comprehensive framework for seamless hu-man-agent interactions beyond facial expressions.

This study proposes a short- and medium-term electricity consumption prediction algorithm by combining the GRU model suitable for long-term forecasting and the Prophet model suitable for seasonality and event handling. (1) Manufacturing Company B's Electricity consumption data and meteorological data in Naju, Jeollanam-do, South Korea are collected and preprocessed. (2) The preprocessed data proposes the Prophet model in the first step for seasonality and event handling prediction. (3) In the second step, seven multivariate data are experimented with GRU. Specifically, the seven multivariate data consist of six meteorological data and the residuals between the predicted data from the proposed Prophet model in Step 1 and the observed data. These are utilized to predict electricity consumption at 15-minute intervals. (4) Electricity consumption is predicted for short-term (2 days and 7 days) and medium-term (15 days and 30 days) scenarios. The experimental results demonstrate that the proposed method outperforms the conventional Prophet model by more than 23 times and the modified GRU model by more than 2 times in terms of MAPE.

: Innovative solutions are now being researched to manage the ever-increasing amount of data required to optimize the performance of internal combustion engines. Machine Learning ap-proaches have shown to be a valuable tool for signal prediction due to their real-time and cost-effective deployment. Among them, the architecture consisting of Long Short-Term Memory (LSTM) and one-dimensional Convolutional Neural Networks (1DCNN) has emerged as a highly promising and effective option for replacing the role of physical sensors. The architecture com-bines the capacity of LSTM to detect patterns and relationships in smaller segments of the signal with the ability of 1DCNN to detect patterns and relationships in larger segments of the signal. The purpose of this work is to assess the feasibility of substituting a physical device dedicated to calculating the torque supplied by a spark-ignition engine. The suggested architecture was trained and tested using signals from the field during a test campaign conducted under transient operating conditions. The results reveal that LSTM+1DCNN is particularly well suited for signal prediction with considerable variability. It constantly outperforms other architectures used for comparison, with average error percentages of less than 2%, proving the architecture's ability to replace physical sensors.

Nowadays people express their opinions on social media. Also provides product reviews on eCommerce websites and responds to various news as comments. It is necessary to know the polarity and aspect of various posts and comments for business, education and security. Aspect-based sentiment analysis (ABSA) predicts text category and polarity. In this paper, we proposed a deep learning framework Deep-ABSA for aspect-based sentiment analysis from Bangla texts. Our proposed framework is a multi-channel architecture. We implemented the word embedding, Bi-LSTM with the attention mechanism for one channel. And for another channel, we adopted the character-embedded convolutional neural network. Finally, we concatenated both channels for adjoining the features of each channel. We obtained an adequate performance from our proposed framework for aspect term analysis from Bangla sentences.

GNSS time series prediction plays a significant role in monitoring crustal plate motion, landslide detection, and maintenance of the global coordinate framework. Long Short-Term Memory (LSTM), a deep learning model has been widely applied in the field of high-precision time series prediction especially when combined with Variational Mode Decomposition (VMD) to form the VMD-LSTM hybrid model. To further improve the prediction accuracy of the VMD-LSTM model, this paper proposes a dual variational modal decomposition long short-term memory (DVMD-LSTM) model to effectively handle the noise in GNSS time series prediction. This model extracts fluctuation features from the residual terms obtained after VMD decomposition to reduce the prediction errors associated with residual terms in the VMD-LSTM model. Daily E, N, and U coordinate data recorded at multiple GNSS stations between 2000 and 2022 are used to validate the performance of the proposed DVMD-LSTM model. The experimental results demonstrate that compared to the VMD-LSTM model, the DVMD-LSTM model achieves significant improvements in prediction performance across all measurement stations. The average RMSE is reduced by 9.86%, and the average MAE is reduced by 9.44%. Furthermore, the average accuracy of the optimal noise model for the predicted results is improved by 36.50%, and the average speed accuracy of the predicted results is enhanced by 33.02%. These findings collectively attest to the superior predictive capabilities of the DVMD-LSTM model, thereby enhancing the reliability of the predicted results.

Time series (TS)-based predictions are made by examining the behaviour of historical data to forecast future values. Multiple industries; such as stock market trading, power load forecasting, medical monitoring, and intrusion detection; frequently use it. Several variables; such as the performance of other markets as well as the economic situation of a country which affect its market performance; significantly affect the prediction of stock market prices. Therefore, this present study uses numerous variables; such as the opening, lowest, highest, and closing prices; to predict the indices of the stock market of the Kingdom of Saudi Arabia (KSA). Successfully accomplishing an investment goal largely depends on choosing the right stocks to buy, sell, or maintain. The project's output is the projected closing prices (regression) over the next seven days, which helps investors make the best decisions. This present study used exponential smoothing (ES) to remove noise from the input data obtained from the Saudi Stock Exchange, or Tadawul, before using a multivariate long short-term memory (LSTM) deep learning (DL) algorithm to forecast stock market prices. The proposed multivariate LSTMDL model had satisfactory prediction rates of 97.49% and 92.19% for the univariate model. Therefore, it can be used to effectively predict stock market prices. The results also indicate that DL as well as multiple sources of information can be used to accurately predict stock markets.

A full connected world is expected to gain in the 6th generation mobile network (6G). As a typi-cal fully connected scenario, the internet of vehicle (IoV) enables intelligent vehicle operations via artificial intelligence (AI) and edge computing technologies. In the future of vehicular net-works, wide variety of services need powerful computing resources and higher quality of ser-vice (QoS). Existing resources are insufficient to match these requirements. Aim to this problem, An intelligent service offloading framework is provided. Based on the framework, an Algorithm of Improved Gradient Descent (AIGD) is created to accelerate the speed of iteration. So, the con-vergence of convolutional neural network (CNN) based on AIGD is able to be accelerated too. Then, an Algorithm of convolutional long short-term memory (CN_LSTM) Based Traffic Predic-tion (ACLBTP) is designed to gain the predicted number of vehicles belonged to the edge node. At last, an Algorithm of Service Offloading Based on CN_LSTM (ASOBCL) is conducted to of-fload these services to the vehicles belonged to the edge node. In ASOBCL, sorting technique is adopted to speed up the offloading work. Simulation results demonstrate the fact that the pre-diction strategy designed in this paper has high accuracy. The low offloading time and main-taining stable load balance is gained via running ASOBCL. Low offloading time means short response time. And, the QoS is guaranteed. So, these strategies designed in this paper are effec-tive and valuable.

Photovoltaic(PV) power generation is highly nonlinear and stochastic. Accurate prediction of PV power generation plays a crucial role in grid connection as well as the operation and scheduling of power plants. To predict the PV power combination model, this paper suggests a method based on Empirical Mode Decomposition (EMD), Ensemble Empirical Mode Decomposition (EEMD), Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN), Nonlinear Auto-Regressive Neural Networks with Exogenous Input (NARXNN), Long Short Term Memory (LSTM) Neural Network, and Light Gradient Boosting Machine (LightGBM) algorithms. To attempt to reduce the non-smoothness of PV power, the weather variable features with the greatest effect on PV power are first identified by correlation analysis. Following this, the PV power modal decomposition is split and reorganized into a new feature matrix. Finally， a NARX is used to obtain preliminary PV power components and residual vector features， and the PV power is predicted by combining three models of LightGBM， LSTM, and NARX and then the final prediction results are obtained by combining the PV power prediction results using error inverse method weighted optimization. The prediction results demonstrate that the model put forth in this paper outperforms those of other models and validate the model's validity by utilizing real measurement data from Andre Agassi College in the United States.

Computer systems that operate in remote locations such as satellites, remote weather stations and autonomous robots are highly limited in the availability of energy for their operation. This work aims to employ artificial intelligence algorithms in energy management in order to obtain the maximum energy yield and the prediction of energy availability to the system. The work presents the main types of algorithms used in artificial intelligence and presents the creation of a prototype that will operate as a low power system powered by batteries and a small solar plate, the prototype will perform inferences on the LSTM neural network algorithm in order to predict the future availability of energy, consequently the management system will carry out the energy distribution in order to obtain the maximum operation of the prototype without total discharge of the batteries. So that the artificial intelligence system could be embedded in the prototype, the TensorFlow Lite framework was used, which allows the inference to be carried out in devices with low consumption and limited processing power.

Speech signals are degraded in real-life environments, product of background noise or other factors. The processing of such signals for voice recognition and voice analysis systems presents important challenges. One of the conditions that make adverse quality difficult to handle in those systems is reverberation, produced by sound wave reflections that travel from the source to the microphone in multiple directions.To enhance signals in such adverse conditions, several deep learning-based methods have been proposed and proven to be effective. Recently, recurrent neural networks, especially those with long and short-term memory (LSTM), have presented surprising results in tasks related to time-dependent processing of signals, such as speech. One of the most challenging aspects of LSTM networks is the high computational cost of the training procedure, which has limited extended experimentation in several cases. In this work, we present a proposal to evaluate the hybrid models of neural networks to learn different reverberation conditions without any previous information. The results show that some combination of LSTM and perceptron layers produce good results in comparison to those from pure LSTM networks, given a fixed number of layers. The evaluation has been made based on quality measurements of the signal's spectrum, training time of the networks and statistical validation of results. Results help to affirm the fact that hybrid networks represent an important solution for speech signal enhancement, with advantages in efficiency, but without a significan drop in quality.

Accurate and fast traffic flow forecasting is vital in intelligent transportation system because many of the advanced features in intelligent transportation systems are based on it. However, existing methods have poor performance regarding accuracy and computational efficiency in long-term traffic flow forecasting under big data. Hence, we propose an improved Long short-term memory (LSTM) Network and its cluster computing implementation in this paper to address the above challenge. We propose a singular point probability LSTM (SDLSTM) algorithm. The method discards the units of the network according to the singular point probability during the training process and amends the SDLSTM by Autoregressive Integrated Moving Average Model (ARIMA) to achieve the accurate prediction of 24-hour traffic flow data. Furthermore, the paper designs a scheme for implementing this method through cluster computing to shorten the calculation time and improve the system's operating speed. Theoretical analysis and experimental results show that SDLSTM gains a higher accuracy rate and better stability in the long-term traffic flow forecasting compared with previous methods.

We describe a multi-resolution approach for audio classification and illustrate its application to the open data set for environmental sound classification. The proposed approach utilizes a multi-resolution based ensemble consisting of targeted feature extraction of approximation (coarse scale) and detail (fine scale) portions of the signal under the action of multiple transforms. This is paired with an automatic machine learning engine for algorithm and parameter selection and the LSTM algorithm, capable of mapping several sequences of features to a predicted class membership probability distribution. Initial results show an improvement in multi-class classification accuracy.

The rise of the Internet has enabled people to express their opinions on various subjects through social media, blogs, and website comments. As a result, there has been a significant increase in research on sentiment analysis. However, most of the research efforts have focused on analyzing sentiment in English-language data, neglecting the wealth of information available in other languages. In this paper, we provide a comprehensive review of the current state-of-the-art in multilingual sentiment analysis. The survey investigates techniques for data preprocessing, representation learning, and feature extraction in multilingual sentiment analysis. It explores cross-lingual transfer learning, domain adaptation, and data augmentation methods that enhance the performance of sentiment analysis models, particularly in low-resource languages and domains. It provides insights into the state-of-the-art approaches, challenges, and opportunities in this evolving field and encourages further advancements in multilingual sentiment analysis research.

The paper presents the observational, remote sensing and model simulation to analyze Southern Brazil Antarctic Ozone Hole influence (SBAOHI) events occurred between 2005 and 2014. To an-alyze it we use Total Ozone Column (TOC) data provide by Brewer Spectrophotometer (BS) and OMI (Ozone Monitoring Instrument) instrument satellite, besides the AURA/MLS (Microwave Limb Sounder) instrument satellite ozone profiles was utilized with DYBAL (Dynamical Barrier Localization) code in MIMOSA (Modélisation Isentrope du transport Mésoéchelle de l’Ozone Stratosphérique par Advection) model Potential Vorticity (PV) fields. TOC has 7.0 ± 2.9 DU re-ductions average in 62 events. October have more events (30.7%). Polar Tongue events are 19.3% of total, being in October more frequently observed (50% of cases), with medium intensity (58.2%) and in stratosphere medium levels (55.0%). Already Polar Filament events (80.7%) are more frequent in September (32.0%), medium intensity (42.0%) and in stratosphere medium lev-els (40.7%). ENSO index positive phase influenced 61.3% of events, having dominance in all in-tensity categories (minor 57.9%, medium 51.6%, major 58.3%), while the equilibrium dominate the QBO influence with 50% of total cases in positive phase and 50 % in negative phase.

Physical exercise is the greatest stress on the cardiovascular system, not only in humans but also in all vertebrates. Consequently, the cardiovascular response cannot be thought of as having only one "anthropocentric" interpretation. The modulation of cardiac output (Q) in response to exercise in the five major groups of vertebrates exhibits considerable variability. Moreover, the response of the heart rate (HR) and the stroke volume (SV), the fundamental factors that cause the rise in Q, is also highly variable. The difference in the range of HR is difficult to determine in many vertebrates, both at rest and at maximal effort. Additionally, the increase in SV varies among vertebrates. For example, while rainbow trout and leopards increase their SV by increasing end diastolic volume (EDV), humans do so at the expense of both increasing EDV and reducing end systolic volume (ESV). The variation in arterial pressure that arises during exercise varies notably among vertebrates, such as amphibians, whose blood pressure values do not increase as significantly as in mammals. Such differences in cardiovascular response among vertebrates may be linked to their habitat or living environment. This review aims to analyze the cardiovascular response of vertebrates to physical exercise as the most common stressor.

HIV incidence remains alarmingly high among female sex workers (FSWs) in low- and middle-income countries, with Uganda being no exception. The elevated risk of HIV transmission among this vulnerable population can be attributed to a complex interplay of factors, including engaging in sexual activities with multiple partners, inconsistent condom usage, substance use, and structural barriers, such as legal criminalization and pervasive stigmatization by healthcare providers. To combat this epidemic, various HIV prevention interventions have been devised, targeting these multi-faceted challenges. This study involved conducting focus groups among FSWs and healthcare providers in Uganda, with the overarching objective of informing the development of a tailored HIV prevention intervention aimed squarely at FSWs. Through these discussions, valuable insights were gained into FSWs’ perceptions of their HIV risk, their attitudes regarding HIV prevention strategies, and their recommendations regarding the content and delivery of future interventions.

The sustainability of the planet and its inhabitants is in dire danger and is among the highest priorities on global agendas such as the Sustainable Development Goals (SDGs) of the United Nations (UN). Solar energy -- among other clean, renewable, and sustainable energies -- is seen as essential for environmental, social, and economic sustainability. Predicting solar energy accurately is critical to increasing reliability and stability, and reducing the risks and costs of the energy systems and markets. Researchers have come a long way in developing cutting-edge solar energy forecasting methods. However, these methods are far from optimal in terms of their accuracies, generalizability, benchmarking, and other requirements. Particularly, no single method performs well across all climates and weathers due to the large variations in meteorological data. This paper proposes SENERGY (an acronym for Sustainable Energy), a novel deep learning-based auto-selective approach and tool that, instead of generalising a specific model for all climates, predicts the best performing deep learning model for GHI forecasting in terms of forecasting error. The approach is based on carefully devised deep learning methods and feature sets through an extensive analysis of deep learning forecasting and classification methods using ten meteorological datasets from three continents. We analyse the tool in great detail through a range of metrics and methods for performance analysis, visualization, and comparison of solar forecasting methods. SENERGY outperforms existing methods in all performance metrics including Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Forecast Skills (FS), Relative Forecasting Error, and the normalised versions of these metrics. The proposed auto-selective approach can be extended to other research problems such as wind energy forecasting and predict forecasting models based on different criteria (in addition to the minimum forecasting error used in this paper) such as the energy required or speed of model execution, different input features, different optimisations of the same models, or other user preferences.

A hypothesis that the generally accepted value of the LiPON conductivity should be attributed to the absorption and displacement currents is substantiated. The reason is a small contribution of the drift current due to field screening by the electric double layer. The basis for this assumption is the measurement of the LiPON absorption capacitance, according to which its dielectric constant is about 106. An alternative equivalent circuit containing a non-ideal absorption element is proposed and its impedance is calculated. It is shown that the Bode diagrams of the alternative circuit well approximate the experimental curves. Parameters and the magnitude of electric field screening are calculated basing on proposed model of a double electric layer. Considering the screening effect, the drift conductivity of LiPON is obtained, which value is in good agreement with the data on lithium concentration and mobility.

Per- and polyfluoroalkyl substances (PFAS), a large group of developing contaminants, have recently become the subject of increased concern due to their potentially hazardous effects. They are classified as poisonous substances that can be found in a variety of aquatic situations. The widespread usage of PFAS across numerous industries has resulted in a high environmental and biological accumulation of the substance. Identification and elimination of PFAS from the environment is crucial since they are tenacious and have the potential to cause cancer. Traditional methods of PFAS content assessment, while useful in some cases, are often inadequate for continuing environmental control and monitoring. Within academia, there is a noticeable desire for rapid, cost-effective, durable, and readily transportable techniques targeted at detecting PFAS compounds in field settings. As a result, environmental labs and other governmental and non-governmental bodies may start testing more often as mandated by legislation. PFAS-detecting sensors, which offer an innovative solution that can be applied in situ and is affordable and simple to use, have emerged as a promising method for assessment based on the existing research. In addition, it may give administrators and users of water worldwide useful information they can use. This article provides a thorough summary of recent developments, limitations, and performance considerations in PFAS detection sensors. The Surface-enhanced Raman scattering (SERS) method has also been covered because of its excellent sensitivity and specificity for detecting pollutants, making it a potential solution for sensing PFAS. Intelligent sensing systems for PFAS detection should benefit from this research.

Salmonella causes various type of disease worldwide with a remarkable pace. Salmonella enteric serotype typhi (S. typhi), a gram-negative bacterium (only cause disease in man) is the mainly causative agent of Typhoid fever. Typhoid fever is most common in poor and unprivileged developing countries of Asia and Africa. One of the major components of virulence factors produced during salmonella infection is Lipid A, which acts as a potent human immuno-modulator bacterial endotoxin. Regulation of Lipid A biosynthetic pathway occurs at second step, catalyzed by LpxC, a Zn2+ dependent metalloamidase. Systematic Screening of a pool of drug datasets like natural products library from Zinc database, Asinex database, Thiophene analogues fruitfully provided us 3 potent lead molecules s1_dl_mseq2, s1_ll_mseq2, and s2_ll_mseq8 which actively binds with LpxC enzyme and could be developed into sound inhibitors of LpxC enzyme after the application of drug development and processing strategies. Wet lab experimentation is required to validate these results for further use.

Physical properties like shape, volume and size affect the dynamics of biological systems. Along these lines, we focus on the topological properties of biological fluids and their biochemical and physiological outcomes. We take as a paradigmatic example the salivary fluid and describe how its topological features may affect the physiopathology of the oral cavity. Topological approaches assess the general properties of saliva, ignoring small-scale physical details such as density, flow rate, stiffness, viscosity. Specifically, the mucin aggregates scattered in the salivary fluid can be tackled in terms of topological holes, i.e., vortical clusters that modify the direction, flow, impulse, local rate-of-change and velocity of saliva. While the current methodological approaches are inclined to remove the effects of impurities assessing systems as homogeneous structures, we argue that the occurrence of mucins breaks up the salivary fluid’s homogeneity, leading to unexpected biophysical modifications. We suggest that every collected salivary sample is not reliable for accurate clinical and experimental investigation, since it displays highly local as well as variable chemical, physical and biological features, not reflecting the current physiological state of the oral cavity. Therefore, the assessment of a single salivary sample is not fully reproducible and cannot provide information about the biophysical, enzymatic and microbiological content of the whole saliva. In sum, the very topological features of the saliva - such as volume, shape, antipodal cells, vortex area, whirling fluid mass, segmentation, discretization, triangulation, node numbering - produce unnoticed biological consequences and network connectivity features with intriguing operational implications.

The effects of the coolant pulsation and the film cooling with the plasma aerodynamic actuation (PAA) could be herein explored via large eddy simulations. The electrohydrodynamic force derived from the PAA was solved through the phenomenological plasma model. The Strouhal number of the sinusoidal coolant pulsation and the averaged pulsation blowing ratio were 0.25 and 1.0, respectively. Comprehensive analyses were carried out on the time-averaged flow fields, and the results revealed that the pulsed cooling jet might cause a deeper penetration into the crossflow, and this phenomenon could be remarkably mitigated by the downward force of the PAA. Furthermore, because of the coolant pulsation, the counter rotating vortex pair (CRVP) expanded to lifted off the wall less well, and the PAA lessened the negative lift-off impact and entrapment from the CRVP. Then, the spatial-temporal development of the coherent structures was figured out by the alterations of the centerline temperature, reflecting formation of the intermittent coherent structures rather than hairpin vortices due to the coolant pulsation, and their size and upcast behaviors were reduced by the PAA. Consequently, there was a basic suppression of the turbulent mixing of the cooling fluid with the crossflow. Finally, the three-dimensional streamlines confirmed that the coherent structure dynamic behaviors were significantly regulated by the PAA for alleviating the adverse influences of the coolant pulsation. In summary, through controlling how the dominating coherent structures evolve throughout time and space, the PAA can effectively increase the pulsed film cooling efficiency.

Reasonable allocation of production plans and saving the overall electricity cost are crucial for large manufacturing conglomerates, which is an effective way for conglomerates to realize open-source and cost-saving. This paper develops an optimization model of off-site industrial production scheduling for enterprises in response to the problems of high electricity costs due to the irrational allocation of production schedules on the demand side of China's electric power and the difficulty of promoting industrial and commercial distributed photovoltaic (PV) projects in China. The model makes full use of the conditions of different PV resources and different electricity prices in different places to optimize the scheduling of industrial production in different places. The model is embedded with two sub-models of the electricity price prediction model and distributed photovoltaic kWh cost model to complete the model parameters, in which the electricity price prediction model utilizes the LSTM neural network. The integrated model is then solved by the particle swarm algorithm. To verify the effectiveness of the model in solving the problem of off-site production scheduling on the demand side of electricity, the research team researched two off-site pharmaceutical factories belonging to the same large pharmaceutical company. Finally, the research data were substituted into the model for solving, and it was concluded that the optimization model could significantly reduce the cost of electricity consumption of the enterprise by about 7.9 %.

Solar energy adoption worldwide has expanded exponentially due to a surge in international interest in producing clean energy and the declining cost of solar power plants and their technology. It is anticipated that by 2050, solar will have surpassed fossil fuels to become the primary source of energy. However, one of the main challenges associated with solar energy production is the instability of photovoltaic (PV) power generation because of weather changes. Short-term forecasting of the power output of photovoltaic systems is essential for efficient management of the power grid and energy markets. This paper aims to evaluate the ability of deep learning (DL) models to provide accurate forecasting of hourly global horizontal irradiance (GHI) using different sets of features, including weather and aerosol variables along with solar radiation components. The results show that the best forecast skills are achieved by the long short-term memory autoencoder (LSTM-AE) model.

This paper introduces an innovative approach to lipreading, leveraging a web application designed to generate subtitles for videos where the speaker's mouth is visible and a comprehensive literature review that precedes the discussion, encompassing a thorough examination of various lipreading methods employed over the past decade. Our method employs a powerful deep learning model, featuring a 3D-convolution network and bidirectional LSTM, enabling accurate sentence-level predictions based solely on visual lip movements. With an impressive accuracy of 97%, our model is trained using pre-segmented lips regions, transformed into animated GIFs for effective pre-training. This work stands as a significant contribution to the evolving landscape of lipreading research, offering a practical and accurate solution for real-world applications.

Background: Novel technologies like continuous glucose monitor (CGM) systems are improving diabetes management by means of real-time sensor glucose levels, retrospective course of glucose and trend arrows. Continuous Glucose Monitoring (CGM) offers real-time alerts for (prognostic) hypo- and hyperglycemia, fast dropping or increasing glucose, and hence improving glycaemia under unstable conditions like during meals, physical activity and exercise management. Complex CGM systems challenge people with diabetes and health care professionals in interpreting rapid changes, sensor delay (~10-minute difference between interstitial and plasma glucose), and malfunctions. Enhanced prediction models are necessary for optimal insulin dosing, daily activities, and especially for future fully closed-loop systems. Methods: The aim of this study was to investigate the efficacy of three different predictive models for glucose responses: 1) an autoregressive integrated moving average model (ARIMA), 2) logistic regression, 3)and long short-term memory networks (LSTM), in predicting glucose levels after 15 minutes and one hour. We compared and evaluated the performance of these models in predicting hypoglycemia (<70 mg/dL), euglycemia (70-180 mg/dL), and hyperglycemia (>180 mg/dL). In more detail, by assessing metrics such as precision, recall, F1-score, and accuracy, we specifically assessed which model provided the most accurate and reliable predictions for glucose levels Results: As expected, ARIMA showed the worst accuracy especially predicting hypoglycaemia withing 1-hour (7.3%). The accuracy of the logistic regression model, predicting hypoglycemia during the first 15 min was higher (98%), comparing to LSTM (88%). However, the LSTM model (87%) exceeded the accuracy of hypoglycemia prediction of the logistic regression (83%) during an hour prognosis. The same pattern observed in hyperglycemia - ARIMA model (60%, 1 hour), logistic regression (96%, 15 minutes) and LSTM (85%, 1 hour) Conclusions: These findings suggest that different models may have varying strengths and weaknesses in predicting glucose levels, and the choice of model should be carefully considered based on the specific requirements and context of the clinical application. The logistic regression model was more accurate for the next 15 minutes, especially predicting hypoglycemia. However, the LSTM model exceeded logistic regression for the next one hour prediction. Future research could explore hybrid models or ensemble approaches that combine the strengths of multiple models to further improve the accuracy and reliability of glucose predictions.

With the advancement of urbanization in China, effective control of pollutant emissions and air quality have become important goals in current environmental management. Nitrogen dioxide (NO2), as a precursor of tropospheric ozone and fine particulate matter, plays a significant role in atmospheric chemistry research and air pollution control. However, the uneven ground monitoring stations and low temporal resolution of polar-orbiting satellites set challenges for accurately assessing near-surface NO2. To address this issue, a spatiotemporal refined NO2 retrieval model was established for China using the geostationary satellite Himawari-8. The spatiotemporal characteristics of NO2 were analyzed and its contribution factors were explored. Firstly, seven Himawari-8 channels sensitive to NO2 were selected by using the forward feature selection based on information entropy. Subsequently, a 2DCNN-LSTM network model was constructed, incorporating the selected channels and meteorological variables as retrieval factors to estimate hourly NO2 in China from March 2018 to February 2020 (with a resolution of 0.05°, per hour). The performance evaluation demonstrated that the full-channel 2DCNN-LSTM model had good fitting capability and robustness (R2=0.74, RMSE=10.93), and further improvements were achieved after channel selection (R2=0.87, RMSE=6.84). The 10-fold cross-validation results indicated that the R2 between retrieval and measured values was above 0.85, the MAE was within 5.60, and the RMSE was within 7.90. R2 varied between 0.85 and 0.90, showing better validation at mid-day (R2=0.89) and in spring and fall transition seasons (R2 =0.88 and R2 =0.90). To investigate the cooperative effect of meteorological factors and other air pollutants on NO2, statistical methods (Beta coefficients) were used to test the factor interpretability. Meteorological factors as well as other pollutants were analyzed. From a statistical perspective, PM2.5, Boundary Layer Height, and O3 were found to have the largest impacts on near-surface NO2, with each standard deviation change in these factors leading to 0.28, 0.24, and 0.23 in standard deviations of near-surface NO2, respectively. Findings of the study contribute to a comprehensive understanding of the spatiotemporal distribution of NO2 and provide a scientific basis for formulating targeted air pollution policies.

The intrinsic non-linearity and complexity of suspended sediment dynamics, which are impacted by the geographical variability of basin parameters and temporal climatic patterns, make it difficult to estimate suspended sediment concentration (SSC) accurately in hydrological processes. Deep neural networks (DNNs), a cutting-edge modeling method that can capture the innate non-linearity in hydrological systems, have emerged as a solution to this problem. Using primary data on discharge, SSC, and turbidity, the long short-term memory method of DNNs was employed in this study to simulate the discharge-suspended sediment connection for the Esopus Creek, NY, USA as the first objective. To develop effective modeling strategies, multiple scenarios of feature selection, including combinations of discharge, turbidity and SSC for preceding days, were considered. Secondly, the variations in SSC and discharge between the three USGS gages along Esopus Creek that were upper stream, lower stream, and downstream, adjacent to the pourpoint were analyzed. Statistical metrics and scenarios of feature importance were used to evaluate the effectiveness of the DNN-based models. The study shows that among 24 DNN approaches feature selection is crucial in simulating the daily SSC, and discharge and presenting novel research directions for utilizing machine learning algorithms in water quality.

Activated sludge process is a well known method to treat municipal and industrial waste water. In this complex process, the oxygen concentration in the reactors plays a critical role in the plant efficiency. This paper proposes the use of a Long Short-Term Memory (LSTM) network to identify an input-output model suitable for the design of an oxygen concentration controller. The model is identified from easy-accessible measures collected from a real plant. This dataset covers almost a month. The performances achieved with the proposed LSTM model are compared with the ones obtained with a standard AutoRegressive model with eXogenous input (ARX). Both models catch the oscillation and the overall behaviour (ARX ρ=0.833 , LSTM ρ=0.921), but, while the ARX model fails in reaching the correct amplitude (FIT=41.20%), the LSTM presents satisfactory performance (FIT=60.56%).

Objective: The aim of this study was to provide a new machine learning method to determine temporal events and inner-cycle parameters (e.g., cycle, poles and skis contact and swing time) in cross-country roller ski skating on the field, using a single deported inertial measurement unit (IMU). Methods: The developed method is based on long short-term memory neural networks to detect poles and skis initial and final contact with the ground during the cyclic movements. Eleven athletes skied four laps of 2.5 km at low and high intensity using skis with two different rolling coefficients. They were equipped with IMUs attached to the upper back, lower back and to the sternum. Data from force insoles and force poles were used as reference system. Results: The IMU placed on the upper back provided the best results, as the LSTM network was able to determine the temporal events with an accuracy ranging from 49 to 55 ms and the corresponding inner-cycles parameters were calculated with a precision of 63 to 68 ms. The method detected 95% of the events for the poles and 87% of the events for the skis. Conclusion: The proposed LSTM method provides a promising tool for assessing temporal events and inner-cycle phases in roller ski skating showing the potential of using a deported IMU to estimate different spatio-temporal parameters of human locomotion.

The choice of holiday destinations is highly depended on climate considerations. Nowadays, since the effects of climate crisis are being increasingly felt, the need of accurate weather and climate services for hotels is crucial. Such a service could be beneficial for both the future planning of tourists’ activities and destinations and for hotel managers as it could help in decision making about the planning and expansion of the touristic season, due to a prediction of higher temperatures for a longer time span, thus causing increased revenue for companies in the local touristic sector. The aim of this work is to calculate predictions on climatic variables using statistical techniques as well as Artificial Intelligence (AI) for a specific area of interest utilising data from in situ meteorological station, and produce valuable and reliable localised predictions with the most cost-effective method possible. This investigation will answer the question of the most suitable prediction method for time series data from a single meteorological station that is deployed in a specific location. As a result, an accurate representation of the microclimate in a specific are is achieved. To achieve this high accuracy in situ measurements and prediction techniques are used. As prediction techniques, Seasonal Auto Regressive Integrated Moving Average (SARIMA), AI techniques like the Long-Short-Term-Memory (LSTM) Neural Network and hybrid combinations of the two are used. Variables of interest are divided in the easier to predict temperature and humidity that are more periodic and less chaotic, and the wind speed as an example of a more stochastic variable with no known seasonality and patterns. Our results show that the examined Hybrid methodology performs the best at temperature and wind speed forecasts, closely followed by the SARIMA whereas LSTM perform better overall at the humidity forecast, even after the correction of the Hybrid to the SARIMA model.

Dissolved Oxygen (DO) concentration is a vital parameter that indicates water quality. DO short term forecasting using time series analysis on data collected from an aquaculture pond is presented here. This can provide data support for an early warning system for an improved management of the aquaculture farm. The conventional forecasting approaches are commonly characterized by low accuracy and poor generalization problems. In this article, we present a novel hybrid DO concentration forecasting method with ensemble empirical mode decomposition (EEMD) based LSTM (Long short-term memory) neural network (NN). With this method, first, the sensor data integrity is improved through linear interpolation and moving average filtering methods of data preprocessing. Next, the EEMD algorithm is applied to decompose the original sensor data into multiple intrinsic mode functions (IMFs). Finally, the feature selection is used to carefully select IMFs that are strongly correlated with the original sensor data and integrate both into inputs for the NN. The hybrid EEMD-based LSTM forecasting model is then constructed. Performance of this proposed model in training and validation sets was compared with the observed real sensor data. To obtain the exact evaluation accuracy of the forecasted results of the hybrid EEMD-based LSTM forecasting model, three statistical performance indices were adopted: MAE, MSE, and RMSE. Results presented for short term (12-hour period) and long term (1-month period) give a strong indication of suitability of this method for forecasting DO values.

We present contrast information, a novel application of some specific cases of relative entropy measures, designed to be useful for cognitive modelling of sequential perception of continuous signals. We explain the relevance of entropy in cognitive modelling of music and language. Then, as a first step to demonstrating the utility of constrast information for that purpose, we show empirically that its discrete case correlates well with existing successful cognitive models in the literature. We explain some interesting properties of constrast information. Finally we propose future work towards a cognitive architecture that uses it.

Immune checkpoint inhibitors (ICI) are a promising form of immunotherapy that has significantly changed the therapeutic landscape for many advanced cancers. They have shown unique clinical benefit against a broad range of tumour types and a strong overall impact on survival in studied patient populations. However, there are still many limitations holding back this immunotherapy from reaching its full potential as a possible curative option for advanced cancer patients. A great deal of research is being undertaken in the hope of driving advancements in this area, building a better understanding of the mechanisms behind immune checkpoint inhibition and ultimately developing more effective, safer, and wider-reaching agents. Taking into account the current literature on this topic, this review aims to explore in depth the basis of the use of ICIs in the treatment of advanced cancers, evaluate its efficacy and safety, consider its current limitations, and finally reflect on what the future holds for this very promising form of cancer immunotherapy.

Some global difficulties in the modern period include energy storage conversion. Researchers have looked to renewable energy resources to discover long-term answers to this dilemma. Fuel cells are one example of prospective energy producing technology. Although these technologies appear to be very enticing, they are known to be expensive due to high expenses. Catalyst costs, as well as concerns concerning energy density. Pt based Electrocatalysts have traditionally been used to drive ORR and offer efficient power outputs. However, cost constraints have limited the use of these electrocatalysts, rendering them inefficient. Apart from the high price, Pt-based Electrodes are prone to time-dependent drift and CO deactivation, both of which occur gradually. Electrocatalysts deteriorate over time, reducing the efficiency of fuel cells. This is why alternative electrocatalysts are in high demand for future energy applications. This review covers the comparative study of Platinium and Non-Platinium based electrocatalyst in fuel cells, their shortcomings and recent advancement for efficient and optimized electrocatalyst.

The Diophantine equation for which p is prime 2^n = p^2 + 7 and n is integers with p > 0, is examined in this work. It is demonstrated by examining the characteristics of the equation that the only solutions meeting these requirements are p = 3 with n = 5 and p = 5 with n = 7. In order to analyze the above equation, it is necessary to look at the properties of primes and how they relate to powers of two. These results advance our knowledge of prime numbers and how they behave in certain mathematical problems.

Many studies have addressed sex differences in patients with psoriatic arthritis, although these are aimed more at describing the phenotype than at investigating the causes underlying the differences. Cross-sectional study of 203 patients. The clinical and demographic variables included age, years of education, time since onset, smoking, type of treatment, clinical presentation, number of entheses affected, dactylitis, fatigue, and cutaneous involvement. Disease activity,functioning and disease was measured. The comorbid conditions evaluated included obesity (and leptin as an associated parameter), anxiety and depression, and sleep quality. Mean age was 54.6, and 46.8% of patients were women. Women less frequently presented axial involvement and more frequently presented enthesitis. They also presented greater disease activity, greater disease impact, and poorer functioning, as well as greater fatigue. As for comorbid conditions, women presented a higher leptin/BMI ratio, higher levels of anxiety and depression, and poorer sleep quality. By sex, pain affecting women was associated with the leptin/BMI ratio and sleep quality. The leptin/BMI ratio was not associated with any component of disease activity in men. Sex was associated with several clinical manifestations, disease activity, functioning, and disease impact. Leptin was associated with intensity of pain in women.

This exploration delves into the intricacies of decision-making in business management. It covers decision-making models, influencing factors, real-world case studies, and strategies for effectiveness. Emphasizing the role of data-driven approaches, the exploration highlights the transformative impact of effective decisions on organizational success. Challenges and pitfalls are addressed, providing insights for overcoming obstacles. The importance of mastering decision-making is underlined as a strategic advantage in the competitive landscape of business management. In summary, this exploration offers a nuanced understanding, empowering leaders to make informed choices that shape organizational destinies.

Previous studies have revealed the microbial metabolism of dietary choline in the gut, leading to its conversion into trimethylamine (TMA), a precursor of the cardiovascular inflammatory marker trimethylamine N-oxide (TMAO). Polymethoxyflavones (PMFs), exemplified by tangeretin, demonstrate efficacy in mitigating TMAO-induced cardiovascular inflammation. However, the specific mechanism by which these compounds exert their effects, particularly in modulating the gut microbiota, remains uncertain. This investigation focused on tangeretin, a representative PMFs, exploring its influence on the gut microbiota and the choline-TMA conversion process. Experimental results showed that tangeretin treatment attenuated the population of CutC-active bacteria, specifically Clostridiaceae and Lactobacillus, induced by choline chloride in rat models. This inhibition resulted in reduced efficiency in choline conversion to TMA, thereby ameliorating cardiovascular inflammation resulting from prolonged choline consumption. In conclusion, tangeretin's preventive action against cardiovascular inflammation is intricately linked to its targeted modulation of TMA-producing bacterial activity.

Abstract: this study aimed to evaluate the benefits of applying 5 cmH2O of CPAP using a pediatric helmet during the recovery phase from general anesthesia in brachycephalic dogs. Brachycephalic dogs undergoing various surgical procedures were included in the study, and a total of 64 subjects were randomly assigned to receive either standard oxygen supplementation (NO-CPAP group) or oxygen supplementation combined with CPAP (CPAP group). The study evaluated arterial blood pH, blood gas partial pressures of O2 and CO2, arterial blood O2 saturation, and related parameters during recovery. The dogs were monitored, and helmet tolerance was assessed using predefined criteria. Of the initially assessed 69 dogs, 64 were enrolled, 32 in the CPAP group and 32 in the NO-CPAP group. Fifteen dogs in the NO-CPAP group were excluded based on predetermined criteria. The CPAP group showed significant improvements in PaO2, PaO2/FiO2, P(A-a)O2, F-Shunt, and respiratory rate compared to the NO-CPAP group (p < 0.001). The incidence of reintubation and helmet intolerance was higher in the NO-CPAP group (18% and 15.6%, respectively) than in the CPAP group (0%). This study highlights the potential benefits of incorporating CPAP, delivered through a pediatric helmet, in the perioperative management of brachycephalic dogs. Keywords: Brachycephalic; dog; CPAP; oxygenation; anesthesia

Traditional aquaculture systems appear to be confronted with the high total ammonia nitrogen (TAN) produced during production, which can be harmful to aquatic life. As the demand for global fish production continues to increase, farmers should adopt Recirculating Aquaculture Systems (RAS) to improve production. The biofilter plays a vital role in ammonia removal. However, the drawback of the biofilter operation is needed an automatic and controlled system with a water quality monitoring system to guarantee optimal performance. RAS utilize a monitoring and control system to maintain the water quality and control the biofilm growth in the biofilter to reduce the ammonia. Therefore, this study focuses on developing a water quality monitoring and control system to achieve optimum biofilm performance. From 35 days of the experiment, the water quality was controlled at a level save for the aquatic environment, such as dissolved oxygen, pH, temperature, and TDS. Thus, the highest TAN removal efficiency is 50% when biofilm thickness reaches 119.88 µm.

Accurate estimation of chlorophyll content in wheat leaves can not only reflect its growth and nutritional status, but also provide a scientific basis for field management. In order to evaluate the potential of hyperspectral data to estimate the chlorophyll content of wheat leaves, this study focused on the leaves of wheat at the flag-picking stage, flowering stage, grain filling stage and maturity stage. Based on the framework of five vegetation indexes, the spectral index was con-structed by using the combination of 400-1000nm bands, and the correlation between the con-structed spectral index and the measured chlorophyll value was analyzed, and the optimal spectral index was screened by the correlation coefficient. Based on the optimal spectral index, polynomial regression, random forest, decision tree and artificial neural network were used to establish the estimation model of chlorophyll value, and the optimal model for estimating the chlorophyll value of wheat leaves was selected through model evaluation. The results showed that the five optimal spectral indices at the four growth stages were mainly composed of red band, red edge band and near-infrared band, and the five optimal spectral indices at the grain filling stage had the highest correlation with the chlorophyll value, and the absolute value of the cor-relation coefficient was greater than 0.73, the accuracy of the estimation model established in the four growth stages was different, and the estimation accuracy of the flag stage was the best, with R² and RMSE of 0.79 and 2.63, respectively. The above results show that hyperspectral data is suitable for estimating the chlorophyll value of wheat leaves, and the PR model of flag picking period can be used as the optimal model for estimating the chlorophyll value of wheat leaves.

Transition to renewable energy has been recognized as a crucial step to addressing climate change and achieving greenhouse gas reduction targets, but it can also cause energy sprawl if not planned properly. Clean renewable energy communities (CREC) are emerging globally as an approach for decentralized energy systems and an alternative to traditional centralized energy systems. CREC aims to lower the energy carbon footprint, enhance local energy resilience, and improve the quality of life of residents. Through a comprehensive literature review, this study reviews metrics that can assess the impact of energy transition plans and support decision-making to select technologies that create efficient, reliable, and accessible energy systems. It classifies these metrics into a five-dimensional sustainability approach: environmental, technical, social, economic, political and institutional. The paper proposes a conceptual framework to guide decision-makers in recognizing the role of sustainable land development, sustainable energy planning, and resiliency as an integrated approach to energy transition planning. This framework stresses mapping the place-based potential for clean renewable energy at various scales, highlights the importance of resilience in energy planning, and addresses challenges associated with energy source selection, built environment efficiency, and energy trade. While the framework can serve as a starting point for evaluating energy transition plans, further work is needed to address the limitations of existing metrics and identify additional evaluations for energy mixed land use that are critical to managing energy sprawl on ecosystem services and other land uses.

Epithelial barrier damage plays a central role in the development and maintenance of allergic inflammation. The rise in airways epithelial barrier permeability alters the tissue homeostasis and allows the allergen and other external agents penetration. Different factors contribute to barrier impairment, such as eosinophilic infiltrate and allergens proteases action: the eosinophilic cationic proteins and the allergens' proteolytic activity have a central role in contributing to epithelial damage. In the airways, the allergens proteases degrade the epithelial junctional proteins allowing the allergen penetration and the uptake by dendritic cells. The increase in allergen-immune system interactions induce the release of the alarmins and the activation of type 2 inflammatory pathways causing, or worsening, the main symptoms at skin, bowel and respiratory levels. We aim to highlight the molecular mechanisms underlying allergenic proteases-induced epithelial barrier damage and the role of immune response in allergic asthma onset, maintenance and progression. We further will explore clinical and radiological potential biomarkers of airways remodeling in allergic asthma patients.

Caring for dolphins is a delicate process that requires experienced caretakers to pay close attention to their behavioral characteristics. However, caretakers may sometimes lack experience or not be able to give their full attention, which can lead to misjudgment or oversight. To address these issues, a dolphin behavior analysis system has been designed to assist caretakers in making accurate assessments. The study utilized image preprocessing techniques to reduce sunlight reflection in the pool and enhance the outline of dolphins, making it easier to analyze their movements. The dolphins were divided into 11 keypoints using an open-source tool called DeepLabCut, which helped accurately mark various body parts for skeletal detection. The AquaAI Dolphin Decoder (ADD) was then used to analyze six dolphin behaviors. To improve behavior recognition accuracy, the Long Short-Term Memory (LSTM) neural network was introduced. The ADD and LSTM models were integrated to form the ADD-LSTM system. Several classification models, including unidirectional and bidirectional LSTM, GRU, and SVM, were compared. The results showed that the ADD module combined with a double-layer bidirectional LSTM method achieved high accuracy in dolphin behavior analysis. The accuracy rates for each behavior were over 90%.

The escalating reliance on revolutionary online web services has introduced heightened security risks, with persistent challenges posed by phishing despite extensive security measures. Traditional phishing systems, reliant on machine learning and manual features, struggle with evolving tactics. Recent advances in deep learning offer promising avenues for tackling novel phishing challenges and malicious URLs. This paper introduces a two-phase stack generalized model named AntiPhishStack, designed to detect phishing sites. The model leverages the learning of URLs and character-level TF-IDF features symmetrically, enhancing its ability to combat emerging phishing threats. In Phase I, features are trained on a base machine learning classifier, employing K-fold cross-validation for robust mean prediction. Phase II employs a two-layered stacked-based LSTM network with five adaptive optimizers for dynamic compilation, ensuring premier prediction on these features. Additionally, the symmetrical predictions from both phases are optimized and integrated to train a meta-XGBoost classifier, contributing to a final robust prediction. This work's significance lies in advancing phishing detection with AntiPhishStack, operating without prior phishing-specific feature knowledge. Experimental validation on two benchmark datasets, comprising benign and phishing or malicious URLs, demonstrates the model's exceptional performance, achieving a notable 96.04% accuracy. This research adds value to the ongoing discourse on symmetry and asymmetry in information security and provides a forward-thinking solution for enhancing network security in the face of evolving cyber threats.

Peanut leaf spot is a worldwide disease whose prevalence poses a major threat to peanut yield and quality, and accurate prediction models are urgently needed for timely disease management. In this study, we proposed a novel peanut leaf spot prediction method based on an improved long short-term memory (LSTM) model and multi-year meteorological data combined with disease survey records. Our method employed a combination of convolutional neural network (CNN) and LSTM to capture spatial-temporal patterns from the data and improve the model ability to recognize dynamic features of the disease. In addition, we introduced an attention mechanism module to enhance model performance by focusing on key features. Through several hyper-parameter optimization adjustments, we identified a peanut leaf spot disease condition index prediction model with a learning rate of 0.001, a number of cycles (Epochs) of 800, and an optimizer of Adma. The results showed that the integrated model demonstrated excellent prediction ability, obtaining an RMSE of 0.063 and an R2 of 0.951, which reduced the RMSE by 0.253 and 0.204, and raised the R2 by 0.155 and 0.122, respectively, compared to the single CNN and LSTM. Predicting the incidence and severity of peanut leaf spot disease based on the meteorological conditions and neural networks is feasible and valuable to help growers made accurate management decisions and reduced disease impacts through optimal fungicide application timing.