Saved Queries

by Jianjiao Deng, Jiawei Wu, Xi Chen, Xinpeng Zhang, Shoukui Li, Yu Song, Jian Wu, Jing Xu, Shiqi Deng and Yudong Wu

Crystals 2025, 15(8), 676; https://doi.org/10.3390/cryst15080676 - 24 Jul 2025

Abstract

Automotive NVH (Noise, Vibration, and Harshness) performance significantly impacts driving comfort and traffic safety. Vehicles exhibiting superior NVH characteristics are more likely to achieve consumer acceptance and enhance their competitiveness in the marketplace. In the development of automotive NVH performance, traditional vibration reduction methods have proven to be mature and widely implemented. However, due to constraints related to size and weight, these methods typically address only high-frequency vibration control. Consequently, they struggle to effectively mitigate vehicle body and component vibration noise at frequencies below 200 Hz. In recent years, acoustic metamaterials (AMMs) have emerged as a promising solution for suppressing low-frequency vibrations. This development offers a novel approach for low-frequency vibration control. Nevertheless, conventional design methodologies for AMMs predominantly rely on empirical knowledge and necessitate continuous parameter adjustments to achieve desired bandgap characteristics—an endeavor that entails extensive calculations and considerable time investment. With advancements in machine learning technology, more efficient design strategies have become feasible. This paper presents a tandem neural network (TNN) specifically developed for the design of AMMs. The trained neural network is capable of deriving both the bandgap characteristics from the design parameters of AMMs as well as deducing requisite design parameters based on specified bandgap targets. Focusing on addressing low-frequency vibrations in the back frame of automobile seats, this method facilitates the determination of necessary AMMs design parameters. Experimental results demonstrate that this approach can effectively guide AMMs designs with both speed and accuracy, and the designed AMMs achieved an impressive vibration attenuation rate of 63.6%. Full article

(This article belongs to the Special Issue Metamaterials and Their Devices, Second Edition)

►▼ Show Figures

Figure 1

17 pages, 1066 KiB

Open AccessArticle

Comparative Study of the Microalgae-Based Wastewater Treatment, in an Oil Refining Industry Cogeneration Concept

by Ena Pritišanac, Maja Fafanđel, Ines Haberle, Sunčana Geček, Marinko Markić, Nenad Bolf, Jela Vukadin, Goranka Crnković, Tin Klanjšček, Luka Žilić and Maria Blažina

Water 2025, 17(15), 2217; https://doi.org/10.3390/w17152217 - 24 Jul 2025

Abstract

Microalage are broadly recognized as promising agents for sustainable wastewater treatment and biomass generation. However, industrial effluents such as petroleum refinery wastewater (WW) present challenges due to toxic growth inhibiting substances. Three marine microalgae species: Pseudochloris wilhelmii, Nannochloropsis gaditana and Synechococcus sp. MK568070 were examined for cultivation potential in oil refinery WW. Their performance was evaluated in terms of growth dynamics, lipid productivity, and toxicity reduction, with a focus on their suitability for largescale industrial use. N. gaditana demonstrated the highest growth rate and lipid content (37% d.w.) as well as lipid productivity (29.45 mg/(Lday)) with the N-uptake rate of 0.698 mmol/(gday). The highest specific DIN uptake rate was observed inn P. wilhelmii (0.895 mmol/(gday) along with the highest volumetric productivity (93.9 mg/L/day) and WW toxicity removal (76.5%), while Synechococcus sp. MK568070 demonstrated lower performance metrics. A simple numerical model was applied to calculate continuous operation based on empirical results of batch experiments. Sustainability of the microalgae-based WW remediation under the conditions of optimized lipid biomass production was estimated, regarding 2019–2022–2025 cost dynamics. Parameters for optimum open raceway pond cultivation were calculated, and the biomass production accumulation was estimated, with the highest biomass production noted in P. wilhelmii (171.38 t/year). Comparison of treatment costs, production costs and revenue showed that the best candidate for WW remediation is N. gaditana. Full article

(This article belongs to the Special Issue Environmental Biotechnology Applied to Water and Wastewater Treatment Processes)

►▼ Show Figures

Figure 1

9 pages, 238 KiB

Open AccessArticle

An Approximation Formula of the Integral Transform on Wiener Space

by Hyun Soo Chung

Axioms 2025, 14(8), 570; https://doi.org/10.3390/axioms14080570 - 24 Jul 2025

Abstract

In this paper, we introduce an integral transform with a kernel defined on the Wiener space. We first establish the existence of the integral transform and present several illustrative examples. As the main result, we derive an approximation theorem for the integral transform. Our approach demonstrates that the integral transform can be effectively computed even in cases where direct calculation is difficult or infeasible. Full article

(This article belongs to the Special Issue Recent Advances in Special Functions and Applications, 2nd Edition)

17 pages, 1357 KiB

Open AccessArticle

A Novel Experimental Method and Setup to Quantify Evaporation-Induced Foaming Behavior of Polymer Solutions

by Xiaoyi Qiu, Zhaoqi Cui, Ming Zhao, Jie Jiang, Wenze Guo, Ling Zhao, Zhenhao Xi and Weikang Yuan

Polymers 2025, 17(15), 2025; https://doi.org/10.3390/polym17152025 - 24 Jul 2025

Abstract

This study provides a novel experimental setup and methodology for the quantitative investigation of evaporation-induced foaming behaviors in a polymer/small-molecule solution system (PSMS). In traditional dynamic test methods, it is difficult to precisely describe the evaporation-induced foaming process of a multicomponent solution because the concentration of light components in solution continuously decreases during ebullition, causing undesired changes in foaming behavior. In this study, a precisely controlled condensation reflux module was introduced into the setup to maintain pressure, temperature, and concentration of the PSMS at constant levels during the entire ebullition process, allowing dynamic test methods to quantify the evaporation-induced foamability. With this newly proposed device, experimental data of typical PSMS, polyolefin elastomer (POE)/n-hexane solution system, were obtained and modeled to illustrate the foam growth profile, thereby characterizing the dynamic foaming process based on a logistic growth function. The corresponding dimensionless number Σevap was calculated to evaluate evaporation-induced foam stability by analyzing the foam growth profile under varying pressure, concentration, and energy input levels. Furthermore, given that the PSMS represents a highly non-ideal system, the bubble nucleation rate J was modified in this work by introducing a correction coefficient δ to account for the non-ideal effects of macromolecules present in solutions. Additionally, another correction coefficient λ was incorporated into the Gibbs free energy term to adjust for supersaturation of liquid during nucleation. The experiment’s data align well with the modified bubble nucleation rate mechanism proposed herein. Full article

(This article belongs to the Special Issue Aqueous Foam of Surfactant–Polymer Composites: Properties and Applications)

16 pages, 803 KiB

Open AccessFeature PaperArticle

Temporal Decline in Intravascular Albumin Mass and Its Association with Fluid Balance and Mortality in Sepsis: A Prospective Observational Study

by Christian J. Wiedermann, Arian Zaboli, Fabrizio Lucente, Lucia Filippi, Michael Maggi, Paolo Ferretto, Alessandro Cipriano, Antonio Voza, Lorenzo Ghiadoni and Gianni Turcato

J. Clin. Med. 2025, 14(15), 5255; https://doi.org/10.3390/jcm14155255 - 24 Jul 2025

Abstract

Background: Intravascular albumin mass represents the total quantity of albumin circulating within the bloodstream and may serve as a physiologically relevant marker of vascular integrity and fluid distribution in sepsis. While low serum albumin levels are acknowledged as prognostic indicators, dynamic assessments based on albumin mass remain insufficiently explored in patients outside the intensive care unit. Objectives: To describe the temporal changes in intravascular albumin mass in patients with community-acquired sepsis and to examine its relationship with fluid balance and thirty-day mortality. Methods: This prospective observational study encompassed 247 adults diagnosed with community-acquired sepsis who were admitted to a high-dependency hospital ward specializing in acute medical care. The intravascular albumin mass was calculated daily for a duration of up to five days, utilizing plasma albumin concentration and estimated plasma volume derived from anthropometric and hematologic data. Net albumin leakage was defined as the variation in intravascular albumin mass between consecutive days. Fluid administration and urine output were documented to ascertain cumulative fluid balance. Repeated-measures statistical models were employed to evaluate the associations between intravascular albumin mass, fluid balance, and mortality, with adjustments made for age, comorbidity, and clinical severity scores. Results: The intravascular albumin mass exhibited a significant decrease during the initial five days of hospitalization and demonstrated an inverse correlation with the cumulative fluid balance. A greater net leakage of albumin was associated with a positive fluid balance and elevated mortality rates. Furthermore, a reduced intravascular albumin mass independently predicted an increased risk of mortality at thirty days. Conclusions: A reduction in intravascular albumin mass may suggest ineffective fluid retention and the onset of capillary leak syndrome. This parameter holds promise as a clinically valuable, non-invasive indicator for guiding fluid resuscitation in cases of sepsis. Full article

(This article belongs to the Section Intensive Care)

►▼ Show Figures

Figure 1

25 pages, 3903 KiB

Open AccessArticle

An Integrated Multi-Criteria Decision Method for Remanufacturing Design Considering Carbon Emission and Human Ergonomics

by Changping Hu, Xinfu Lv, Ruotong Wang, Chao Ke, Yingying Zuo, Jie Lu and Ruiying Kuang

Processes 2025, 13(8), 2354; https://doi.org/10.3390/pr13082354 - 24 Jul 2025

Abstract

Remanufacturing design is a green design model that considers remanufacturability during the design process to improve the reuse of components. However, traditional remanufacturing design scheme decision making focuses on the remanufacturability indicator and does not fully consider the carbon emissions of the remanufacturing process, which will take away the energy-saving and emission reduction benefits of remanufacturing. In addition, remanufacturing design schemes rarely consider the human ergonomics of the product, which leads to uncomfortable handling of the product by the customer. To reduce the remanufacturing carbon emission and improve customer comfort, it is necessary to select a reasonable design scheme to satisfy the carbon emission reduction and ergonomics demand; therefore, this paper proposes an integrated multi-criteria decision-making method for remanufacturing design that considers the carbon emission and human ergonomics. Firstly, an evaluation system of remanufacturing design schemes is constructed to consider the remanufacturability, cost, carbon emission, and human ergonomics of the product, and the evaluation indicators are quantified by the normalization method and the Kansei engineering (KE) method; meanwhile, the hierarchical analysis method (AHP) and entropy weight method (EW) are used for the calculation of the subjective and objective weights. Then, a multi-attribute decision-making method based on the combination of an assignment approximation of ideal solution ranking (TOPSIS) and gray correlation analysis (GRA) is proposed to complete the design scheme selection. Finally, the feasibility of the scheme is verified by taking a household coffee machine as an example. This method has been implemented as an application using Visual Studio 2022 and Microsoft SQL Server 2022. The research results indicate that this decision-making method can quickly and accurately generate reasonable remanufacturing design schemes. Full article

(This article belongs to the Section Manufacturing Processes and Systems)

►▼ Show Figures

Figure 1

22 pages, 16984 KiB

Open AccessArticle

Small Ship Detection Based on Improved Neural Network Algorithm and SAR Images

by Jiaqi Li, Hongyuan Huo, Li Guo, De Zhang, Wei Feng, Yi Lian and Long He

Remote Sens. 2025, 17(15), 2586; https://doi.org/10.3390/rs17152586 - 24 Jul 2025

Abstract

Synthetic aperture radar images can be used for ship target detection. However, due to the unclear ship outline in SAR images, noise and land background factors affect the difficulty and accuracy of ship (especially small target ship) detection. Therefore, based on the YOLOv5s model, this paper improves its backbone network and feature fusion network algorithm to improve the accuracy of ship detection target recognition. First, the LSKModule is used to improve the backbone network of YOLOv5s. By adaptively aggregating the features extracted by large-size convolution kernels to fully obtain context information, at the same time, key features are enhanced and noise interference is suppressed. Secondly, multiple Depthwise Separable Convolution layers are added to the SPPF (Spatial Pyramid Pooling-Fast) structure. Although a small number of parameters and calculations are introduced, features of different receptive fields can be extracted. Third, the feature fusion network of YOLOv5s is improved based on BIFPN, and the shallow feature map is used to optimize the small target detection performance. Finally, the CoordConv module is added before the detect head of YOLOv5, and two coordinate channels are added during the convolution operation to further improve the accuracy of target detection. The map50 of this method for the SSDD dataset and HRSID dataset reached 97.6% and 91.7%, respectively, and was compared with a variety of advanced target detection models. The results show that the detection accuracy of this method is higher than other similar target detection algorithms. Full article

►▼ Show Figures

Figure 1

19 pages, 4242 KiB

Open AccessArticle

Piezoelectric Effect of k-Carrageenan as a Tool for Force Sensor

by Vytautas Bučinskas, Uldis Žaimis, Dainius Udris, Jūratė Jolanta Petronienė and Andrius Dzedzickis

Sensors 2025, 25(15), 4594; https://doi.org/10.3390/s25154594 - 24 Jul 2025

Abstract

Natural polymers, polysaccharides, demonstrate piezoelectric behavior suitable for force sensor manufacturing. Carrageenan hydrogel film with α-iron oxide particles can act as a piezoelectric polysaccharide-based force sensor. The mechanical impact on the hydrogel caused by a falling ball shows the impact response time, which is measured in milliseconds. Repeating several experiments in a row shows the dynamics of fatigue, which does not reduce the speed of response to impact. Through the practical experiments, we sought to demonstrate how theoretical knowledge describes the hydrogel we elaborated, which works as a piezoelectric material. In addition to the theoretical basis, which includes the operation of the metal and metal oxide contact junction, the interaction between the metal oxide and the hydrogel surfaces, the paper presents the practical application of this knowledge to the complex hydrogel film. The simple calculations presented in this paper are intended to predict the hydrogel film’s characteristics and explain the results obtained during practical experiments. Carrageenan, as a low-cost and already widely used polysaccharide in various industries, is suitable for the production of low-cost force sensors in combination with iron oxide. Full article

(This article belongs to the Section Electronic Sensors)

16 pages, 3684 KiB

Open AccessArticle

Topography-Guided Custom Ablation Treatment for Post-Traumatic Corneal Irregularities—Case Reports

by Łukasz Drzyzga, Dorota Śpiewak, Mariola Dorecka and Dorota Wyględowska-Promieńska

Biomedicines 2025, 13(8), 1818; https://doi.org/10.3390/biomedicines13081818 - 24 Jul 2025

Abstract

Background: Post-traumatic corneal wounds that require suturing are quite common; they reduce corneal transparency and cause corneal distortion, leading to corneal astigmatism and higher-order aberrations. Excimer laser treatment can be a potentially beneficial intervention for such wounds. The observation aimed to evaluate the effectiveness of topography-guided custom ablation treatment (TCAT) in patients with corneal injuries. Methods: This observation included three patients with corneal penetrating trauma (full-thickness corneal scar) and one patient with corneal blunt trauma, i.e., a non-penetrating injury with corneal laceration (partial-thickness corneal scar). This cohort study was conducted from July 2021 to August 2023. After first-stage treatment (stabilization of the post-traumatic visual defect confirmed by refraction and topography examination, corneal healing, and improvement of the corneal scar), the patients underwent the second-stage treatment, i.e., TCAT with a 20 to 45 s application of mitomycin C solution to avoid haze induction. After TCAT, the uncorrected distance visual acuity (UDVA) and best-corrected distance visual acuity (BCVA) were measured. Refractive astigmatism was assessed using autorefractometry. Topographic astigmatism was analyzed using corneal topography and pachymetry. The root mean square (RMS) of the higher-order aberration was calculated using Zernike coefficients. The patients’ corneal healing and refractive changes were monitored. Results: All patients were monitored for corneal healing and refractive changes and underwent the same second-stage treatment, which utilized TCAT to regularize the corneal surface and reduce higher-order aberrations (HOAs). The UDVA of patients 1, 2, 3 and 4 improved by 3, 7.5, 4 and 6 rows (Snellen chart), respectively. The resultant UDVA was 1.0, 0.9, 0.7 and 1.2, while BCVA was 1.0, 1.2, 1.0, and 1.5, respectively. Conclusions: TCAT regularized the patients’ corneal surfaces and reduced HOAs. We, therefore, conclude that TCAT may be a beneficial second-stage treatment for corneal trauma-induced astigmatism. Full article

(This article belongs to the Special Issue New Insights and Latest Advances in Corneal and Ocular Surface Diseases)

►▼ Show Figures

Figure 1

12 pages, 1099 KiB

Open AccessArticle

Data Center Temperature Control Method Based on Multi-Parameter Model-Free Adaptive Control Strategy

by Di Jiang, Shangxuan Zhang and Kaiyan Pan

Processes 2025, 13(8), 2360; https://doi.org/10.3390/pr13082360 - 24 Jul 2025

Abstract

With the continuous expansion of data center scales worldwide, the problem of energy consumption has become increasingly prominent. To address the multi-parameter control challenge in environmental temperature regulation for large data center computer rooms, achieve precise control of hot-aisle temperatures in data centers, and reduce energy waste, this paper designs a multi-parameter model-free adaptive control (MMFAC) algorithm suitable for computer room environmental temperatures. The algorithm integrates the model-free adaptive control (MFAC) algorithm with a weight matrix to perform scaling transformations. Considering the large parameter space of the MFAC controller and the dynamic complexity of data center temperature control systems, compact-form dynamic linearization (CFDL) technology and optimization mathematical methods are used to simplify the parameter identification of the pseudo-Jacobian matrices and the calculation of control quantities for the regulation devices. Simulation experiments based on measured data from a data center show that the proposed algorithm can calculate control quantities for equipment such as air conditioners according to real-time environmental parameter measurements and drive each device based on these control quantities. Meanwhile, the algorithm can reduce errors in key parameters by adjusting the weight matrix. Comparative tests with other control algorithms show that the algorithm has faster response in temperature control and smaller control errors, verifying the effectiveness and application prospects of the algorithm in data center temperature control. Full article

(This article belongs to the Section Process Control and Monitoring)

►▼ Show Figures

Figure 1

17 pages, 1134 KiB

Open AccessArticle

Application of High Efficiency and High Precision Network Algorithm in Thermal Capacity Design of Modular Permanent Magnet Fault-Tolerant Motor

by Yunlong Yi, Sheng Ma, Bo Zhang and Wei Feng

Energies 2025, 18(15), 3967; https://doi.org/10.3390/en18153967 - 24 Jul 2025

Abstract

Aiming at the problems of low thermal analysis efficiency and high computational cost of traditional computational fluid dynamics (CFD) methods for modular fault-tolerant permanent magnet synchronous motors (MFT-PMSMs) under complex working conditions, this paper proposes a fast modeling and calculation method of motor temperature field based on a high-efficiency and high-precision network algorithm. In this method, the physical structure of the motor is equivalent to a parameterized network model, and the computational efficiency is significantly improved by model partitioning and Fourth-order Runge Kutta method. The temperature change of the cooling medium is further considered, and the temperature rise change of the motor at different spatial positions is effectively considered. Based on the finite element method (FEM), the space loss distribution under rated, single-phase open circuit and overload conditions is obtained and mapped to the thermal network nodes. Through the transient thermal network solution, the rapid calculation of the temperature rise law of key components such as windings and permanent magnets is realized. The accuracy of the thermal network model was verified by using fluid-structure coupling simulation and prototype test for temperature analysis. This method provides an efficient tool for thermal safety assessment and optimization in the motor fault-tolerant design stage, especially for heat capacity check under extreme conditions and fault modes. Full article

(This article belongs to the Special Issue Linear/Planar Motors and Other Special Motors)

13 pages, 1401 KiB

Open AccessArticle

Cost-Effectiveness of Endoscopic Stricturotomy Versus Resection Surgery for Crohn’s Disease Strictures

by Kate Lee Karlin, Grace Kim, Francesca Lim, Adam S. Faye, Chin Hur and Bo Shen

Healthcare 2025, 13(15), 1801; https://doi.org/10.3390/healthcare13151801 - 24 Jul 2025

Abstract

Background: Endoscopic therapies for Crohn’s disease (CD) strictures, including endoscopic balloon dilation (EBD) and endoscopic stricturotomy (ESt), are less invasive interventions compared to surgery. ESt is advantageous for strictures that are longer, more fibrotic, or adjacent to anatomic structures requiring precision, and it has shown a high rate of surgery-free survival. Methods: We designed a microsimulation state-transition model comparing ESt to surgical resection for CD strictures. We calculated quality-adjusted life years (QALYs) over a 10-year time horizon; secondary outcomes included costs (in 2022 USD) and incremental cost-effectiveness ratios (ICERs). We used a societal perspective to compare our strategies at a willingness-to-pay (WTP) threshold of 100,000 USD/QALY. Sensitivity analyses, both deterministic and probabilistic, were performed. Results: The surgery strategy cost more than 2.5 times the ESt strategy, but resulted in nine more QALYs per 100 persons. The ICER for the surgery strategy was 308,787 USD/QALY; thus, the ESt strategy was determined more cost-effective. One-way sensitivity analyses showed that quality of life after ESt as compared to that after surgery, the likelihood of repeat intervention, and surgical mortality and cost were the most influential parameters shifting cost-effectiveness. Probabilistic sensitivity analyses favored ESt in most (65.5%) iterations. Conclusions: Our study finds endoscopic stricturotomy to be a cost-effective strategy to manage primary or anastomotic Crohn’s disease strictures. Post-intervention quality of life and probabilities of requiring repeated interventions exert most influence on cost-effectiveness. The decision between ESt and surgery should be made considering patient and stricture characteristics, preferences, and cost-effectiveness. Full article

(This article belongs to the Section Healthcare Quality and Patient Safety)

23 pages, 5464 KiB

Open AccessArticle

A Coffee-Based Bioadsorbent for CO₂ Capture from Flue Gas Using VSA: TG-Vacuum Tests

by Marcelina Sołtysik, Izabela Majchrzak-Kucęba and Dariusz Wawrzyńczak

Energies 2025, 18(15), 3965; https://doi.org/10.3390/en18153965 - 24 Jul 2025

Abstract

In the energy sector and in other types of industries (cement, iron/steel, chemical and petrochemical), highly roasted coffee ground residue can be used as a source material for producing bioadsorbents suitable for CO₂ capture. In this study, a bioadsorbent was produced in a two-step process involving biowaste carbonization and biocarbon activation within a KOH solution. The physicochemical properties of the bioadsorbent were assessed using LECO, TG, SEM, BET and FT-IR methods. Investigating the CO₂, O₂ and N₂ equilibrium adsorption capacity using an IGA analyzer allowed us to calculate CO₂ selectivity factors. We assessed the influence of exhaust gas carbon dioxide concentration (16%, 30%, 81.5% and 100% vol.) and adsorption step temperature (25 °C, 50 °C and 75 °C) on the CO₂ adsorption capacity of the bioadsorbent. We also investigated its stability and regenerability in multi-step adsorption–desorption using a TG-Vacuum system, simulating the VSA process and applying different pressures in the regeneration step (30, 60 and 100 mbar_abs). The tests conducted assessed the possibility of using a produced bioadsorbent for capturing CO₂ using the VSA technique. Full article

(This article belongs to the Section B3: Carbon Emission and Utilization)

►▼ Show Figures

Figure 1

36 pages, 1566 KiB

Open AccessArticle

The Impact of Geopolitical Risk on the Connectedness Dynamics Among Sovereign Bonds

by Mustafa Almabrouk Abdalla Alfughi and Asil Azimli

Mathematics 2025, 13(15), 2379; https://doi.org/10.3390/math13152379 - 24 Jul 2025

Abstract

This study examines the impact of geopolitical risk (GPR) on the connectedness dynamics among the sovereign bonds of the emerging seven (E7) and the Group of Seven (G7) countries. Initially, a quantile-based vector-autoregressive (Q-VAR) connectedness approach is used to calculate the total connectedness index (TCI) among sovereign bonds under different market states. Then, the impact of GPR on the TCI at the median and tails is estimated to examine if GPR affects the TCI among sovereign bonds. Using daily yields from 30 January 2012, to 17 June 2024, the findings show that the GPR is one of the significant determinants of the TCI among sovereign bonds during normal and extreme market conditions. Other determinants of the TCI include yields on Treasury bills (T-bills), the exchange rate, and the financial market volatility index. The impact of GPR on the TCI varies significantly during different GPR episodes and bond market conditions. The effect of GPR on the TCI among sovereign bonds yields is higher during war times and when bond yields are average. These findings can be utilized by investors seeking to achieve international diversification and policymakers aiming to mitigate the effects of heightened geopolitical risk on financial stability. Furthermore, GPR can be used as an early signal tool for systematic tail risk spillovers among sovereign bonds. Full article

(This article belongs to the Special Issue Modeling Multivariate Financial Time Series and Computing)

►▼ Show Figures

Figure 1

25 pages, 7623 KiB

Open AccessArticle

ASHM-YOLOv9: A Detection Model for Strawberry in Greenhouses at Multiple Stages

by Yan Mo, Shaowei Bai and Wei Chen

Appl. Sci. 2025, 15(15), 8244; https://doi.org/10.3390/app15158244 - 24 Jul 2025

Abstract

Strawberry planting requires different amounts of soil water-holding capacity and fertilizer at different growth stages. Determining the stages of strawberry growth has important guiding significance for irrigation, fertilization, and picking. Quick and accurate identification of strawberry plants at different stages can provide important information for automated strawberry planting management. We propose an improved multistage identification model for strawberry based on the YOLOv9 algorithm—the ASHM-YOLOv9 model. The original YOLOv9 showed limitations in detecting strawberries at different growth stages, particularly lower precision in identifying occluded fruits and immature stages. We enhanced the YOLOv9 model by introducing the Alterable Kernel Convolution (AKConv) to improve the recognition efficiency while ensuring precision. The squeeze-and-excitation (SE) network was added to increase the network’s capacity for characteristic derivation and its ability to fuse features. Haar wavelet downsampling (HWD) was applied to optimize the Adaptive Downsampling module (Adown) of the initial model, thereby increasing the precision of object detection. Finally, the CIoU function was replaced by the Minimum Point Distance based IoU (MPDIoU) loss function to effectively solve the problem of low precision in identifying bounding boxes. The experimental results demonstrate that, under identical conditions, the improved model achieves a precision of 97.7%, a recall of 97.2%, mAP50 of 99.1%, and mAP50-95 of 90.7%, which are 0.6%, 3.0%, 0.7%, and 7.4% greater than those of the original model, respectively. The parameters, model size, and floating-point calculations were reduced by 3.7%, 5.6% and 3.8%, respectively, which significantly boosted the performance of the original model and outperformed that of the other models. Experiments revealed that the model could provide technical support for the multistage identification of strawberry planting. Full article

►▼ Show Figures

Figure 1

Show export options Show export options

Select all

Export citation of selected articles as:

Error

Oops... you haven't selected anything for export.

Displaying article 1-50 on page 1 of 2000.

Go to page 1 2 3 4 5

Search Results (105,360)

Further Information

Guidelines

MDPI Initiatives

Follow MDPI