Search Results (72)

Traditional farming practices are becoming increasingly inadequate to meet global food demand due to water scarcity, prolonged production cycles, climate variability, and declining arable land. In contrast, aeroponic, smart, soil-free farming technologies offer a more sustainable alternative by reducing land use and providing efficient water use, given that aeroponics intermittently delivers water in mist form rather than maintaining continuous root zone moisture. However, aeroponics faces critical challenges in irrigation management due to non-standardized structures and limited real-time control. A key limitation is the inability to dynamically respond to temperature (T), relative humidity (RH), light intensity (L_i), electrical conductivity (EC), pH, and photosynthesis rate (P_n), resulting in suboptimal crop yields and resource wastage. Despite growing interest, there remains a research gap in integrating internet of things (IoT) and machine learning technologies into aeroponic systems for adaptive control. IoT-enabled sensors provide real-time data on ambient conditions and plant health, while ML models can adaptively optimize misting intervals based on the fluctuations in P_n and environmental inputs. These technologies are particularly well suited to address the dynamic, data-intensive nature of aeroponic environments. This review purposes a novel, standardized IoT–ML framework to control irrigation by emphasizing IoT sensing and ML-based decision making in aeroponics. This integrated approach is essential for minimizing water loss, enhancing resource efficiency, and advancing the sustainability of controlled-environment agriculture. Full article

Aberrant or non-standard operations by ship drivers are a leading cause of water traffic accidents, making the development of real-time and reliable behavior detection systems critically important. However, the environment within a ship’s bridge is significantly more complex than typical scenarios, such as vehicle driving or general security monitoring, which results in poor performance when applying generic algorithms. In such settings, both the accuracy and efficiency of existing methods are notably limited. To address these challenges, this paper proposes a cross-modal behavioral intelligence framework designed specifically for a ship’s bridge, integrating multi-target tracking, behavior recognition, and feature object association. The framework employs ByteTrack, a high-performance multi-object tracker that maintains stable tracking even when subject to occlusions or motion blur through its novel association mechanism, using both high and low confidence detection boxes, for multi-driver tracking. Combined with an improved Temporal Shift Module (TSM) algorithm for behavior recognition, which effectively resolves issues concerning target association and action ambiguity in complex environments, the proposed framework achieves a Top-1 accuracy of 82.1%, based on the SCA dataset. Furthermore, the method incorporates a multi-modal decision optimization strategy, based on spatiotemporal correlation rules, leveraging YOLOv7-e6 for simultaneous personnel and small object detection, and introduces the Accuracy of Focused Anomaly Recognition (AFAR) metric to enhance the anomaly detection performance. This approach improves the anomaly detection rate, up to 81.37%, with an overall accuracy of 80.66%, significantly outperforming single-modality solutions. Full article

Background: The cargo stowage and securing plan for non-standardized cargo is vital for ensuring safety at sea, as improper placement or inadequate lashing can compromise maritime transport safety. Due to the diverse size and type of cargo, efficient planning is also essential to optimize space utilization and improve the economic performance of general cargo vessels. Methods: This paper presents a novel methodology to identify the optimal cargo securing layout using lashing lines that comply with international standards while minimizing deck space usage. A comparative analysis of two major securing guidelines was conducted to determine the stricter and safer standard. Results: The optimization approach was validated with real-world case studies, revealing the most effective securing configurations. These are defined by the optimal combination of vertical and horizontal lashing angles, which secure cargo in any stowage position by balancing longitudinal and transverse forces while minimizing occupied deck area. Additionally, novel graphs and 3D maps are introduced to illustrate the relationships between key securing parameters. Conclusions: The obtained results and the visual tools enhance understanding and provide practical support for lashing planners, facilitating safer and more efficient cargo securing decisions. Full article

We investigate an inverse problem involving source and damping term with variable-exponent nonlinearities. We establish adequate conditions on the initial data for the decay of solutions as the integral overdetermination approaches zero over time within an acceptable range of variable exponents. This class of inverse problems, where internal terms such as source and damping are to be determined from indirect measurements, has significant relevance in real-world applications—ranging from geophysical prospecting to biomedical engineering and materials science. The accurate identification of these internal mechanisms plays a crucial role in optimizing system performance, improving diagnostic accuracy, and constructing predictive models. Therefore, the results obtained in this study not only contribute to the theoretical understanding of nonlinear dynamic systems but also provide practical insights for reconstructive analysis and control in applied settings. The asymptotic behavior and decay conditions we derive are expected to be of particular interest to researchers dealing with stability, uniqueness, and identifiability in inverse problems governed by nonstandard growth conditions. Full article

Background: Foundational research on the gamma distribution and inventory control highlighted its flexibility and practicality for managing fast-moving finished goods. Nonetheless, concerns remain about conventional statistical approximations of lead-time demand (LTD) distributions. Real-world lead times often result in nonstandard LTD forms, and traditional methods may introduce parameter mismatches under nonclassical conditions. Despite these challenges, this research demonstrates that a gamma LTD approximation is an effective method for managing these goods. Methods: This study employs numerical experiments to assess accuracy at high service levels, focusing on errors in system cost and product availability. Three propositions are validated: (1) a standard distribution generally characterizes the demands of fast-moving items; (2) demand variability systematically modifies the form of nonstandard LTD distributions, enhancing accuracy; (3) nonclassical conditions generally improve the accuracy of properly parameterized gamma approximations. A purposive sample of disruptive lead-time distributions found in global maritime supply chains drives numerical experiments. Results: Externally validated evidence provides the following findings within our study context: (1) a nonstandard lead-time distribution does not necessarily result in a similar LTD distribution, as it also depends on demand variability; (2) demand variability positively affects the form of a nonstandard LTD distribution under conventional conditions, with nonclassical conditions enhancing this effect; (3) the shape transformations almost always improve the accuracy of a gamma approximation. Conclusions: A gamma LTD approximation can manage inventory for fast-moving finished goods effectively, even with disruptive lead times under both conventional and nonclassical conditions. Full article

Background/Objectives: This systematic review presents how neural and emotional networks are integrated into EEG-based emotion recognition, bridging the gap between cognitive neuroscience and practical applications. Methods: Following PRISMA, 64 studies were reviewed that outlined the latest feature extraction and classification developments using deep learning models such as CNNs and RNNs. Results: Indeed, the findings showed that the multimodal approaches were practical, especially the combinations involving EEG with physiological signals, thus improving the accuracy of classification, even surpassing 90% in some studies. Key signal processing techniques used during this process include spectral features, connectivity analysis, and frontal asymmetry detection, which helped enhance the performance of recognition. Despite these advances, challenges remain more significant in real-time EEG processing, where a trade-off between accuracy and computational efficiency limits practical implementation. High computational cost is prohibitive to the use of deep learning models in real-world applications, therefore indicating a need for the development and application of optimization techniques. Aside from this, the significant obstacles are inconsistency in labeling emotions, variation in experimental protocols, and the use of non-standardized datasets regarding the generalizability of EEG-based emotion recognition systems. Discussion: These challenges include developing adaptive, real-time processing algorithms, integrating EEG with other inputs like facial expressions and physiological sensors, and a need for standardized protocols for emotion elicitation and classification. Further, related ethical issues with respect to privacy, data security, and machine learning model biases need to be much more proclaimed to responsibly apply research on emotions to areas such as healthcare, human–computer interaction, and marketing. Conclusions: This review provides critical insight into and suggestions for further development in the field of EEG-based emotion recognition toward more robust, scalable, and ethical applications by consolidating current methodologies and identifying their key limitations. Full article

In protected agriculture, accurately identifying the key growth stages of tomatoes plays a significant role in achieving efficient management and high-precision production. However, traditional approaches often face challenges like non-standardized data collection, unbalanced datasets, low recognition efficiency, and limited accuracy. This paper proposes an innovative solution combining generative adversarial networks (GANs) and deep learning techniques to address these challenges. Specifically, the StyleGAN3 model is employed to generate high-quality images of tomato growth stages, effectively augmenting the original dataset with a broader range of images. This augmented dataset is then processed using a Vision Transformer (ViT) model for intelligent recognition of tomato growth stages within a protected agricultural environment. The proposed method was tested on 2723 images, demonstrating that the generated images are nearly indistinguishable from real images. The combined training approach incorporating both generated and original images produced superior recognition results compared to training with only the original images. The validation set achieved an accuracy of 99.6%, while the test set achieved 98.39%, marking improvements of 22.85%, 3.57%, and 3.21% over AlexNet, DenseNet50, and VGG16, respectively. The average detection speed was 9.5 ms. This method provides a highly effective means of identifying tomato growth stages in protected environments and offers valuable insights for improving the efficiency and quality of protected crop production. Full article

Current soil mixing sampling surveys face several challenges. These challenges include significant variations in the size and shape of farmland plots, which complicate the sampling process. Additionally, the procedures for establishing mixing points are often cumbersome and non-standardized. Furthermore, when the number of mixing points is large and the plot area is extensive, sampling efficiency is significantly reduced. In this study, an automated method for establishing the layout of sampling points and a threshold-based mixed path planning algorithm are proposed. These approaches are designed to automatically arrange sampling points within delineated sampling units according to various sampling methods. Additionally, real-time path planning is conducted on the basis of the initial position of the sampling vehicle. The experimental results indicate that the maximum relative error in estimating farmland area is 0.22%, which is less than 666.67 m². The average deviation between the locations of the sampling points generated by the sampling point layout algorithm and those established via related software is 0.0336 m. Furthermore, the threshold-based hybrid algorithm consistently yields optimal or near-optimal paths while reducing the path planning time, with an average duration of 1.0783 s for path planning. This study provides reliable technical support for standardizing the sampling point layout and enhancing the soil sampling efficiency. Full article

Candida auris, an emerging multidrug-resistant fungal pathogen, poses significant challenges in healthcare settings due to its high misidentification rate and resilience to treatments. Despite advancements in diagnostic tools, a gap remains in rapid, cost-effective identification methods that can differentiate C. auris from other Candida species, particularly on non-standard culture media. We used Raman spectroscopy to characterize C. auris grown on modified Dixon’s agar (mDixon) and differentiated it from Candida albicans and Candida parapsilosis. Key Raman spectral markers at 1171 cm⁻¹ and 1452 cm⁻¹, linked to mannan and β-glucan composition, differentiated C. auris into two subgroups, A and B. Despite the spectral similarities of groups A and B with C. albicans and C. parapsilosis, respectively, all Candida species were distinguishable through principal component analysis (PCA). Additionally, this study is the first to demonstrate the distinct spectral signature of mDixon agar, achieved through spatially offset Raman spectroscopy (SORS), which enables accurate discrimination between the culture medium and fungal samples. The observed inter-individual variability within C. auris, coupled with the spectral overlap between C. auris subgroups and other Candida species, highlights a major challenge in differentiating closely related fungi due to their similar molecular composition. Enhancements in spectral resolution and further fluorescence minimization from the culture medium are needed to reliably detect the subtle biochemical differences within these species. Despite these challenges, the results underscore the potential of Raman spectroscopy as a real-time, non-destructive, and complementary tool for fungal pathogen identification. Full article

The limit behaviour of I-shaped welded steel cross-sections subjected to axial force, shear, and bending moment is a crucial matter to ascertain the reliability of framed structures constituted by non-standard beam elements. International standards provide an approximate solution to the problem, and other studies have proposed improved approximate formulations to ascertain the real features of the relevant cross-sections. The present paper is devoted to enhancing the problem of the limit behaviour of plane I-shaped welded steel cross-sections subjected to axial force $\left(N\right)$, shear $\left(T\right)$ and bending moment $\left(M\right)$; therefore, new appropriate formulations are proposed in order to define suitable new domains, both in planes $\left(N,T\right)$, $\left(N,M\right)$, and $\left(M,T\right)$ and in the space $\left(N,T,M\right)$. The material is assumed as elastic–perfectly plastic and the Von Mises limit condition is adopted as the resistance criterion. The elastic stresses are described by the Navier formula and the Jourawski formula. The limit stress condition related to the contemporaneous presence of the acting forces is defined as the one that, at each point of the cross-section, fulfils the Von Mises limit condition as equality. The formulation is rigorously devoted to factory-made welded I-shaped steel cross-sections. Some numerical examples are reported in the application stage and useful comparison are carried out, with the results being obtainable by the application of the classical known standard formulae, proving the reliability and effectiveness of the determined domains. Full article

Two novel crossover models for breast cancer that incorporate $\Psi$-Caputo fractal variable-order fractional derivatives, fractal fractional-order derivatives, and variable-order fractional stochastic derivatives driven by variable-order fractional Brownian motion and the crossover model for breast cancer that incorporates Atangana–Baleanu Caputo fractal variable-order fractional derivatives, fractal fractional-order derivatives, and variable-order fractional stochastic derivatives driven by variable-order fractional Brownian motion are presented here, where we used a simple nonstandard kernel function $\Psi \left(t\right)$ in the first model and a non-singular kernel in the second model. Moreover, we evaluated our models using actual statistics from Saudi Arabia. To ensure consistency with the physical model problem, the symmetry parameter $\zeta$ is introduced. We can obtain the fractal variable-order fractional Caputo and Caputo–Katugampola derivatives as special cases from the proposed $\Psi$-Caputo derivative. The crossover dynamics models define three alternative models: fractal variable-order fractional model, fractal fractional-order model, and variable-order fractional stochastic model over three-time intervals. The stability of the proposed model is analyzed. The $\Psi$-nonstandard finite-difference method is designed to solve fractal variable-order fractional and fractal fractional models, and the Toufik–Atangana method is used to solve the second crossover model with the non-singular kernel. Also, the nonstandard modified Euler–Maruyama method is used to study the variable-order fractional stochastic model. Numerous numerical tests and comparisons with real data were conducted to validate the methods’ efficacy and support the theoretical conclusions. Full article

To date, the development of unmanned technologies using autonomous underwater vehicles (AUVs) has become an urgent demand for solving the problem of inspecting industrial subsea structures. A key issue here is the precise localization of AUVs relative to underwater objects. However, the impossibility of using GPS and the presence of various interferences associated with the dynamics of the underwater environment do not allow high-precision navigation based solely on a standard suite of AUV navigation tools (sonars, etc.). An alternative technology involves the processing of optical images that, at short distances, can provide higher accuracy of AUV navigation compared to the technology of acoustic measurement processing. Although there have been results in this direction, further development of methods for extracting spatial information about objects from images recorded by a camera is necessary in the task of calculating the exact mutual position of the AUV and the object. In this study, in the context of the problem of subsea production system inspection, we propose a technology to recognize underwater objects and provide coordinate references to the AUV based on stereo-image processing. Its distinctive features are the use of a non-standard technique to generate a geometric model of an object from its views (foreshortening) taken from positions of a pre-made overview trajectory, the use of various characteristic geometric elements when recognizing objects, and the original algorithms for comparing visual data of the inspection trajectory with an a priori model of the object. The results of experiments on virtual scenes and with real data showed the effectiveness of the proposed technology. Full article

Many studies have shown successful applications of the Dirichlet process mixture model (DPMM) for clustering continuous data. Beyond continuous data, in practice, one can expect to see different data types, including ordinal and nominal data. Existing DPMMs for clustering mixed-type data assume a strict covariance matrix structure, resulting in an overfit model. This article explores a DPMM for mixed-type data that allows the covariance matrix to differ from one cluster to another. We assume an underlying latent variable framework for ordinal and nominal data, which is then modeled jointly with the continuous data. The identifiability issue on the covariance matrix poses computational challenges, thus requiring a nonstandard inferential algorithm. The applicability and flexibility of the proposed model are illustrated through simulation examples and real data applications. Full article

Corrosion and scaling in metal pipelines are the major issues in the exploitation of geothermal sources. Geothermal fluids are complex mixtures consisting of dissolved gases and high-salinity solutions. This creates very aggressive environments primarily due to the high concentrations of carbon dioxide (CO₂), hydrogen sulfide (H₂S), chlorides, and other chemical species. Besides, the high temperature of the brines also increases corrosion rates, which can lead to failures related to stress and fatigue corrosion. On the other hand, reinjection of cooled brine exiting the heat exchanger favors the onset of scaling, since the chemicals dissolved in geothermal waters may tend to precipitate promoting inorganic depositions on the casing. Corrosion and scaling phenomena are difficult to detect visually or monitor continuously. Standard techniques based on pH, temperature pressure, electrical resistance measurements, chemistry composition, and physical properties are habitually applied as indirect methods for corrosion rate control. These methods, however, lack enough robustness for accurate and reliable measuring of the corrosion behavior of materials. To address this issue, a novel system has been proposed for the continuous monitoring of corrosion degradation caused by the effect of the geothermal brines. The present work aims to design, develop, and validate a dedicated electrochemical-based test system for online and onsite monitoring of the corrosion rate and scaling growth occurring on different materials exposed to real operating conditions. This system uses non-standard methods based on electrochemical impedance spectroscopy (EIS) to obtain quantitative data related to the material quality. It can be used to track the condition of the pipeline, reducing the operation and maintenance (O&M) costs and shutdown times. By providing early corrosion rate data, this system allows the prediction of failures in critical units of the plant. Full article

The metallurgical sector is one of the important sectors of the Slovak economy. Its integral part is the storage of metallurgical waste, which is accompanied by noise that bothers the inhabitants of the surrounding urban areas. This paper focuses on the analysis of the problem of noise propagation into protected areas located in the vicinity of the metallurgical plant. The paper describes a number of measurements that have been carried out at the slag landfill. Based on these measurements, simulations were performed using a mathematical model, and predictions of noise propagation in the exterior were made. Subsequently, noise reduction measures were proposed. The results obtained by the authors form a methodological basis for addressing such situations, since, during the solution, it was often necessary to deal with non-standard situations that were specific to the area of the technology addressed. This solution was then applied in real practice. Full article