The corrosion of metals is very important, both economically and environmentally, and is a serious concern. Since the past decades, traditional (chemical) corrosion inhibitors to prevent corrosion have been and are still being used. Although these inhibitors can be said to be a good choice among other protection techniques because of their good efficiency, the toxicity of many of them causes environmental problems, and, due to the change in the laws on the use of chemicals, many of them are no longer allowed. Hence, during the past years, research on green corrosion inhibitors (GCIs) increased and very favorable results were obtained, and now they are very popular. It can be said that biodegradability and easy preparation are their most important factors. Meanwhile, the use of plants, especially their extracts, has been studied a lot. Plant extracts contain compounds that have anti-corrosion properties. In this review, the use of plants as GCIs is investigated, focusing on recent advances in their use. Also, the phenomenon of corrosion, corrosion protection (including coatings, nanoparticles, and chemical inhibitors), and other GCIs are briefly reviewed. Full article

This study innovatively assesses the Mun River flow components in Thailand, integrating artificial neural networks (ANNs) and isotopic (δ¹⁸O) end-member mixing analysis (IEMMA). It quantifies the contributions of the Upper Mun River (UMR) and Chi River (CR) to the overall flow, revealing a discrepancy in their estimated contributions. The ANN method predicts that the UMR and CR contribute approximately 70.5% and 29.5% respectively, while IEMMA indicates a more pronounced disparity with 84% from UMR and 16% from CR. This divergence highlights the distinct perspectives of ANN, focusing on hydrological data patterns, and IEMMA, emphasizing isotopic signatures. Despite discrepancies, both methods validate UMR as a significant contributor to the overall flow, highlighting their utility in hydrological research. The findings emphasize the complexity of river systems and advocate for an integrated approach of river flow analysis for a comprehensive understanding, crucial for effective water resource management and planning. Full article

One of the environmental problems worldwide is the enormous number of surgical masks used during the COVID-19 pandemic due to the measures imposed by the World Health Organization on the mandatory use of masks in public spaces. The current study is a potential circular economy approach to recycling the surgical masks discarded into the environment during the COVID-19 pandemic for use in bituminous asphalt pavement. FTIR analysis showed that the surgical masks used were made from ethylene propylene diene monomer (EPDM) rubber modified with polypropylene. The effects of the addition of surgical masks in bituminous asphalt on the performance of the base course were demonstrated in this study. The morphology and elemental composition of the bituminous asphalt pavement samples with two ratios of surgical mask composition were investigated by SEM-EDX and the performance of the modified bituminous asphalt pavement was determined by Marshall stability, flow rate, solid–liquid ratio, apparent density, and water absorption. The study refers to the technological innovation of using surgical masks in the formulation of AB 31.5 bituminous asphalt base course, which brings tremendous benefits to the environment by reducing the damage caused by the COVID-19 pandemic. Full article

Incorporation of red clover (Trifolium pratense L.) into grass pastures can reduce the need for nitrogen fertilizer applications and increase the nutritional value of the forage. However, red clover cultivars available for Kentucky producers are highly susceptible to herbicides, such as 2,4-D (2,4-dichlorophenoxy acetic acid), used for pasture broadleaf weed control. To overcome this problem, ‘UK2014’ red clover was selected for increased tolerance to 2,4-D. We employed a transcriptome analysis approach to compare the gene expression response following 2,4-D treatment of ‘UK2014’ to that of ‘Kenland’, a 2,4-D sensitive red clover and one of the parents of ‘UK2014’. The objectives were to first determine if the increased 2,4-D tolerance in ‘UK2014’ is reflected in a change of transcription response and/or a quicker recovery of a transcriptional response following 2,4-D treatment, and second, to identify genes, whether constitutively expressed or induced by 2,4-D, which could be the basis for the increased 2,4-D tolerance. Leaf tissue from the two red clovers grown in the field was collected at 4, 24, and 72 h after 2,4-D (1.12 kg 2,4-amine a.e. ha⁻¹) treatment from both untreated and treated plants. Global gene expression was determined with reads from Illumina Hiseq 2500 mapped against the red clover draft genome, Tpv2.1 (GenBank Accession GCA_900079335.1). Genes that displayed differential expression (DEGs) following 2,4-D treatment were selected for further analysis. The number of DEGs was higher for ‘Kenland’ than for ‘UK2014’, suggesting that a lower transcriptional response corresponds with the higher 2,4-D tolerance in the ‘UK2014’ line. Similarly, gene ontology enrichment analysis revealed that expression of photosynthesis-related genes was less affected by 2,4-D in the ‘UK2014’ line than ‘Kenland’. Although we were not able to identify any specific genes that are the basis for the increased 2,4-D tolerance of ‘UK2014’, we concluded that the increased 2,4-D tolerance of ‘UK2014’ correlates with a decreased transcription response to 2,4-D. Additionally, expression of several cytochrome P450 genes that had different isoforms between ‘UK2014’ and ‘Kenland’ increased significantly in both following 2,4-D treatment, one or more of these P450s could be mediators of 2,4-D metabolism and tolerance in red clover. Full article

In this work, ZnO thick films were synthesized via two simple and easy methods, mechanochemical synthesis and screen-printing deposition. The ZnO powders were obtained through milling at low temperature with milling times of 20, 40, and 60 min. The ZnO thick films were fabricated by depositing 10 cycles of ZnO inks onto glass substrates. The characterization of ZnO thick films revealed a thickness ranging from 4.9 to 5.4 µm with a surface roughness between 85 and 88 nm. The structural analysis confirmed a hexagonal wurtzite crystalline structure of ZnO, both in powders and in thick films, with a preferred orientation on the (002) and (101) planes. Nanostructures with sizes ranging from 36 to 46 nm were observed, exhibiting irregular agglomerated shapes, with an energy band found between 2.77 and 3.02 eV. A static experimental set up was fabricated for gas sensing tests with continuous UV-LED illumination. The ZnO thick films, well adhered to the glass substrate, demonstrated high sensitivity and selectivity to H₂S gas under continuous UV-LED illumination at low operating temperatures ranging from 35 to 80 °C. The sensitivity was directly proportional, ranging from 3.93% to 22.40%, when detecting H₂S gas concentrations from 25 to 600 ppm. Full article

Hydrogen−rich water (HRW) is widely recognized for its growth promoting, antioxidant, and anti−inflammatory properties. However, little is known about the role of HRW in aquaculture. This study aims to investigate how different concentrations of HRW affect the growth performance, digestive ability, antioxidant capacity, mTOR signaling pathway, and gut microbiota of juvenile largemouth bass. We randomly assigned 360 fish (13.73 ± 0.1 g) to three treatments. The control group was maintained in regular water, while the treatment groups were treated with different concentrations of H₂ dissolved in water, which were H1 (179.65 ± 31.95 ppb) and H2 (280.65 ± 64.43 ppb), respectively. Through an analysis of the three treatments, it was found that H1 significantly increased the final body weight, weight gain rate, specific growth rate, and survival rate, and reduced the feed conversion ratio (p < 0.05). In addition, the trypsin activity was significantly increased in the intestine (p < 0.05), and the expression of genes related to the glucose metabolism (pk and pepck) and mTOR (tor, akt, s6k1, 4ebp1, and ampka) signaling pathways were significantly increased in the liver in H1 (p < 0.05). The relative abundance of Blautia in the gut microbiota (p < 0.05) was significantly increased in H1. Therefore, these results indicated that H1 can significantly improve growth performance, promote intestinal digestion, activate the glucose metabolism pathway and mTOR signaling pathway, and increase the abundance of beneficial bacteria in the gut of largemouth bass. These findings provided valuable support for the application of HRW to support the healthy aquaculture of largemouth bass. Full article

Chitin is a structural polysaccharide abundant in the biosphere. Chitin possesses a highly ordered crystalline structure that makes its processing a challenge. In this study, chitin hydrogels and methanogels, prepared by dissolution in calcium chloride/methanol, were subjected to supercritical carbon dioxide (scCO₂) to produce porous materials for use as scaffolds for osteoblasts. The control of the morphology, porosity, and physicochemical properties of the produced materials was performed according to the operational conditions, as well as the co-solvent addition. The dissolution of CO₂ in methanol co-solvent improved the sorption of the compressed fluid into the hydrogel, rendering highly porous chitin scaffolds. The chitin crystallinity index significantly decreased after processing the hydrogel in supercritical conditions, with a significant effect on its swelling capacity. The use of scCO₂ with methanol co-solvent resulted in chitin scaffolds with characteristics adequate to the adhesion and proliferation of osteoblasts. Full article

The inferior mechanical performance and freeze–thaw (FT) resistance of recycled concrete are mostly due to the significant water absorption and porosity of recycled coarse particles. In this study, different dosages of zeolite powder were used in recycled concrete. A series of macroscopic tests were used to evaluate the workability and FT durability of zeolite powder-modified recycled concrete (ZPRC). X-ray diffraction (XRD) and scanning electron microscopy (SEM) were used to reveal the micro-mechanisms of FT resistance in ZPRC. The results show that the increase in zeolite powder content leads to a decrease in the slump and water absorption of ZPRC. Additionally, ZPRC with 10% zeolite powder has superior mechanical characteristics and tolerance to FT conditions. The higher strength and FT resistance of the ZPRC can be attributed to the particle-filling effect, water storage function, and pozzolanic reaction of zeolite powder, which results in a denser microstructure. The particle-filling effect of zeolite powder promotes the reduction of surface pores in recycled coarse aggregates (RCAs). The water storage function of zeolite powder can provide water for the secondary hydration of cement particles while reducing the free water content in ZPRC. The pozzolanic reaction of zeolite powder can also promote the generation of hydrated calcium silicate and anorthite, thereby making the microstructure of ZPRC more compact. These results provide theoretical guidance for the engineering application of recycled concrete in cold regions. Full article

This study evaluates the viability of n-octanol as an alternative fuel in a direct-injection diesel engine, aiming to enhance sustainability and efficiency. Experiments fueled by different blends of n-octanol with pure diesel were conducted to analyze their impacts on engine performance and emissions. The methodology involved testing each blend in a single-cylinder engine, measuring engine performance parameters such as brake torque and brake power under full-load conditions across a range of engine speeds. Comparative assessments of performance and emission characteristics at a constant engine speed were also conducted with varying loads. The results indicated that while n-octanol blends consistently improved brake thermal efficiency, they also increased brake-specific fuel consumption due to the lower energy content of n-octanol. Consequently, while all n-octanol blends reduced nitrogen oxide emissions compared to pure diesel, they also significantly decreased carbon monoxide, hydrocarbons, and smoke opacity, presenting a comprehensive reduction in harmful emissions. However, the benefits came with complex trade-offs: notably, higher concentrations of n-octanol led to a relative increase in nitrogen oxide emissions as the n-octanol ratio increased. The study concludes that n-octanol significantly improves engine efficiency and reduces diesel dependence, but optimizing the blend ratio is crucial to balance performance improvements with comprehensive emission reductions. Full article

This paper proposed a novel, precast double-skin composite (DSC) shear wall, which was composed of two precast parts at the factory and welding and pouring grouting material on site. One monolithic cast-in-place DSC shear wall specimen and two precast DSC shear wall specimens with different axial compression ratios were subjected to reverse cyclic loading tests. The results indicated that the failure mode of both the cast-in-place and precast DSC shear wall shear walls were compression-bending failures, and the damage range of specimens within a height range of 100 mm to 200 mm from the bottom of the DSC shear wall. The load-bearing capacity of the precast specimen was 6.3% higher than that of the monolithic counterpart, but its ductility was reduced by 16%. The precast DSC shear wall with better casting quality and easier site installation exhibited a satisfactory seismic performance on a par with that of the monolithic cast-in-place DSC shear wall. Under higher axial compression ratios, the bearing capacity and energy dissipation of the precast DSC shear wall specimen significantly improved due to the enhanced confinement effect. Finite element (FE) models clarified the stress and deformation mechanisms between the exterior steel plate and the infill concrete. Finally, the key parameters affecting the seismic bearing capacity of the precast DSC shear wall were identified through FE parameter analysis. Full article

Obtaining mathematical models of nonlinear cyber–physical systems for use in controller design is both difficult and time consuming. In this paper, an ANN-based method is proposed to design a controller for a nonlinear system that does not require a mathematical model. The developed ANN-based control algorithm is implemented directly on a real-time field controller, and its performance is evaluated without the use of auxiliary devices, such as PCs or workstations. By executing machine learning algorithms on local devices or embedded systems, edge artificial intelligence (Edge AI) with transfer learning gives priority to processing data at the source, minimizing the necessity for continuous connectivity to remote servers. The control algorithm was developed using the Matlab Simulink environment. The first and second ANNs were cascaded, wherein the first ANN computes the appropriate pressure signal for the given displacement, while the second predicts the force based on the pressure value from the first ANN. Subsequently, the ANN-based control algorithm was converted to SCL code using the Simulink PLC Coder and deployed on the PLC for operation. The algorithm was tested using two different scenarios. The conducted tests demonstrated the successful prediction of pressure signals corresponding to the targeted displacement values and accurate estimation of force values. Experimental work was carried out on PAM manipulators as a nonlinear model application, and the obtained results were discussed. Full article

Transfer learning (TL) techniques have proven useful in a wide variety of applications traditionally dominated by machine learning (ML), such as natural language processing, computer vision, and computer-aided design. Recent extrapolations of TL to the radio frequency (RF) domain are being used to increase the potential applicability of RFML algorithms, seeking to improve the portability of models for spectrum situational awareness and transmission source identification. Unlike most of the computer vision and natural language processing applications of TL, applications within the RF modality must contend with inherent hardware distortions and channel condition variations. This paper seeks to evaluate the feasibility and performance trade-offs when transferring learned behaviors from functional RFML classification algorithms, specifically those designed for automatic modulation classification (AMC) and specific emitter identification (SEI), between homogeneous radios of similar construction and quality and heterogeneous radios of different construction and quality. Results derived from both synthetic data and over-the-air experimental collection show promising performance benefits from the application of TL to the RFML algorithms of SEI and AMC. Full article

Light-induced phase segregation, particularly when incorporating bromine to widen the bandgap, presents significant challenges to the stability and commercialization of perovskite solar cells. This study explores the influence of hole transport layers, specifically poly[bis(4-phenyl)(2,4,6-trimethylphenyl)amine (PTAA) and [4-(3,6-dimethyl-9H-carbazol-9-yl)butyl]phosphonic acid (Me-4PACz), on the dynamics of phase segregation. Through detailed characterization of the buried interface, we demonstrate that Me-4PACz enhances perovskite photostability, surpassing the performance of PTAA. Nanoscale analyses using in situ Kelvin probe force microscopy and quantitative nanomechanical mapping techniques elucidate defect distribution at the buried interface during phase segregation, highlighting the critical role of substrate wettability in perovskite growth and interface integrity. The integration of these characterization techniques provides a thorough understanding of the impact of the buried bottom interface on perovskite growth and phase segregation. Full article

Four complexes of essential metal ions, Cu(II) and Ni(II), with the new sulfonamide ligand N-(pyridin-2-ylmethyl)quinoline-8-sulfonamide (HQSMP) were synthesized and physicochemically and structurally characterized. Complex [Cu(QSMP)Cl]_n (2) consists of a polymeric chain formed by distorted square pyramidal units. In two, the sulfonamide ligand acts as a bridge coordinating to one Cu(II) through its three N atoms and to another metal ion via one O atom in the sulfonamido group, while the pentacoordinate complex [Cu(QSMP)(C₆H₅COO)] (3) presents a highly distorted square pyramidal geometry. Complex [Ni(QSMP)(C₆H₅COO)(CH₃OH)][Ni(QSMP)(CH₃COO)(CH₃OH)] (4) consists of two mononuclear entities containing different anion coligands, either a benzoate or an acetate group. Both units exhibit a distorted octahedral geometry. The interaction of the complexes with CT-DNA was studied by means of UV-Vis and fluorescence spectroscopy, interestingly revealing that the Ni(II) complex presents the highest affinity towards the nucleic acid. Complexes 1 and 2 are able to cleave DNA. Both compounds show promising nuclease activity at relatively low concentrations by mediating the production of a reactive oxygen species (ROS). The interaction of the four complexes with bovine serum albumin (BSA) was also investigated, showing that the compounds can bind to serum proteins. The antitumor potential of complexes 1 and 2 was evaluated against the A549 lung adenocarcinoma cell line, revealing cytotoxic properties that were both dose- and time-dependent. Full article

Despite all the literature on building energy management, building-stock-scale models depicting its impact for energy-market-scale optimisation models are lacking. To address this shortcoming, an open-source tool called ArchetypeBuildingModel.jl has been developed for aggregating building-stock-level data into simplified lumped-capacitance thermal models compatible with existing open-source energy-system modelling frameworks. This paper aims to demonstrate the feasibility of these simplified thermal models by comparing their performance against dedicated building simulation software, as well as examining their sensitivity to key modelling and parameter assumptions. Modelling and parameter assumptions comparable to the existing literature achieved an acceptable performance according to ASHRAE Guideline 14 across all tested buildings and nodal configurations. The most robust performance was achieved with a period of variations above 13 days and interior node depth between 0.1 and 0.2 for structural thermal mass calibrations, and with external shading coefficients between 0.6 and 1.0 and solar heat gain convective fractions between 0.4 and 0.6 for solar heat gain calibrations. Furthermore, three-plus-node lumped-capacitance thermal models are recommended when modelling buildings with structures varying in terms of thermal mass. Nevertheless, the ArchetypeBuildingModel.jl performance was found to be robust against uncertain key parameter assumptions, making it plausible for energy-market-scale applications. Full article

The development of specific antiviral therapies targeting SARS-CoV-2 remains fundamental because of the continued high incidence of COVID-19 and limited accessibility to antivirals in some countries. In this context, dark chemical matter (DCM), a set of drug-like compounds with outstanding selectivity profiles that have never shown bioactivity despite being extensively assayed, appears to be an excellent starting point for drug development. Accordingly, in this study, we performed a high-throughput screening to identify inhibitors of the SARS-CoV-2 main protease (M^pro) using DCM compounds as ligands. Multiple receptors and two different docking scoring functions were employed to identify the best molecular docking poses. The selected structures were subjected to extensive conventional and Gaussian accelerated molecular dynamics. From the results, four compounds with the best molecular behavior and binding energy were selected for experimental testing, one of which presented inhibitory activity with a K_i value of 48 ± 5 μM. Through virtual screening, we identified a significant starting point for drug development, shedding new light on DCM compounds. Full article

Improving fracture toughness, electrical conductivity, and biocompatibility has consistently presented challenges in the development of artificial bone replacement materials. This paper presents a new strategy for creating high-performance, multifunctional composite ceramic materials by doping graphene oxide (GO), which is known to induce osteoblast differentiation and enhance cell adhesion and proliferation into barium calcium zirconate titanate (BCZT) ceramics that already exhibit good mechanical properties, piezoelectric effects, and low cytotoxicity. Using fast hot-pressed sintering under vacuum conditions, (1 − x)(Ba_0.85Ca_0.15Zr_0.1Ti_0.9)O₃₋xGO (0.2 mol% ≤ x ≤ 0.5 mol%) composite piezoelectric ceramics were successfully synthesized. Experimental results revealed that these composite ceramics exhibited high piezoelectric properties (d₃₃ = 18 pC/N, k_p = 62%) and microhardness (173.76 HV_0.5), meeting the standards for artificial bone substitutes. Furthermore, the incorporation of graphene oxide significantly reduced the water contact angle and enhanced their wettability. Cell viability tests using Cell Counting Kit-8, alkaline phosphatase staining, and DAPI staining demonstrated that the GO/BCZT composite ceramics were non-cytotoxic and effectively promoted cell proliferation and growth, indicating excellent biocompatibility. Consequently, with their superior mechanical properties, piezoelectric performance, and biocompatibility, GO/BCZT composite ceramics show extensive potential for application in bone defect repair. Full article

We aimed to characterize SARS-CoV-2 infection in companion animals living in households with COVID-19-positive people and understand the dynamics surrounding how these animals become infected. Public health investigators contacted households with at least one confirmed, symptomatic person with COVID-19 for study recruitment. Blood, nasal, and rectal swab specimens were collected from pet dogs and cats and a questionnaire was completed. Specimens were tested for SARS-CoV-2 by RT-PCR, and for neutralizing antibodies; genomic sequencing was performed on viral-positive samples. A total of 36.4% of 110 pets enrolled had evidence of infection with SARS-CoV-2. Pets were more likely to test positive if the pet was immunocompromised, and if more than one person in the home was positive for COVID-19. Among 12 multi-pet households where at least one pet was positive, 10 had at least one other pet test positive. Whole-genome sequencing revealed the genomes of viral lineages circulating in the community during the time of sample collection. Our findings suggest a high likelihood of viral transmission in households with multiple pets and when pets had very close interactions with symptomatic humans. Further surveillance studies are needed to characterize how new variants impact animals and to understand opportunities for infection and spillover in susceptible species. Full article

This study addresses the current lack of research on the effectiveness assessment of Artificial Intelligence (AI) technology in architectural education. Our aim is to evaluate the impact of AI-assisted architectural teaching on student learning. To achieve this, we developed an AI-embedded teaching model. A total of 24 students from different countries participated in this 9-week course, completing a comprehensive analysis of architectural programming and design using AI technologies. This study conducted questionnaire surveys with students at both midterm and final stages of the course, followed by structured interviews after the course completion, to explore the effectiveness and application status of the teaching model. The results indicate that the AI-embedded teaching model positively and effectively influenced student learning. The “innovative capability” and “work efficiency” of AI technologies were identified as key factors affecting the effectiveness of the teaching model. Furthermore, the study revealed a close integration of AI technologies with architectural programming but identified challenges in the uncontrollable expression of architectural design outcomes. Student utilization of AI technologies appeared fragmented, lacking a systematic approach. Lastly, the study provides targeted optimization suggestions based on the current application status of AI technologies among students. This research offers theoretical and practical support for the further integration of AI technologies in architectural education. Full article

To understand the spatial temporal distribution characteristics of Illex argentinus caught by trawl fishing vessels in the Southwestern Atlantic Ocean and their relationship with key marine environmental factors, this study analyzed the temporal and spatial changes in the fishing ground center of trawl vessels at the ten-day scale from December 2019 to May 2022, combining Chinese trawl fishing log data marine environmental data with satellite remote sensing marine environmental data. Utilizing the Maxent model, ten-day intervals were used as the temporal scale, and ten marine environmental factors, including sea surface temperature, sea surface height, sea surface salinity, chlorophyll concentration, temperature at 50 m and 100 m depth, and the meridional and zonal velocities of ocean currents were quantitatively analyzed to explore the correlation between the spatial distribution of catch and environmental factors. The study reveals that the trawl fishing grounds for Illex argentinus are divided into southern and northern grounds. The southern grounds first appear near 45°20′ S in December, gradually moving southeastward in February and March. The northern grounds do not appear until April, near 42° S in the high seas. On the ten-day time scale, the central fishing grounds of Illex argentinus show significant spatial variability but minor interannual differences. The Maxent model results indicate that sea surface temperature and chlorophyll a concentration are the key environmental factors influencing the spatial and temporal variability of the high seas trawl fishing grounds for most of the time, with high environmental contribution rates during the fishing season. While the range of suitable habitats with an HSI > 0.6 identified by the Maxent model varies significantly between years, a pattern is observed where the range expands at the start and end of the fishing season and contracts during the peak fishing season. This suggests that a more concentrated range of suitable habitats is conducive to accurate predictions of trawl fishing grounds, enabling efficient fishing operations. Full article

Glioblastoma is a highly aggressive neoplasm and the most common primary malignant brain tumor. Endothelial tissue plays a critical role in glioblastoma growth and progression, facilitating angiogenesis, cellular communication, and tumorigenesis. In this review, we present an up-to-date and comprehensive summary of the role of endothelial cells in glioblastomas, along with an overview of recent developments in glioblastoma therapies and tumor endothelial marker identification. Full article

Time-series forecasting is crucial in the efficient operation and decision-making processes of various industrial systems. Accurately predicting future trends is essential for optimizing resources, production scheduling, and overall system performance. This comprehensive review examines time-series forecasting models and their applications across diverse industries. We discuss the fundamental principles, strengths, and weaknesses of traditional statistical methods such as Autoregressive Integrated Moving Average (ARIMA) and Exponential Smoothing (ES), which are widely used due to their simplicity and interpretability. However, these models often struggle with the complex, non-linear, and high-dimensional data commonly found in industrial systems. To address these challenges, we explore Machine Learning techniques, including Support Vector Machine (SVM) and Artificial Neural Network (ANN). These models offer more flexibility and adaptability, often outperforming traditional statistical methods. Furthermore, we investigate the potential of hybrid models, which combine the strengths of different methods to achieve improved prediction performance. These hybrid models result in more accurate and robust forecasts. Finally, we discuss the potential of newly developed generative models such as Generative Adversarial Network (GAN) for time-series forecasting. This review emphasizes the importance of carefully selecting the appropriate model based on specific industry requirements, data characteristics, and forecasting objectives. Full article