The maximum thickness for ferritic steel specimens’ residual stress measurements using neutron diffraction is known to be about 80 mm. This paper proposes a new neutron diffraction configuration of residual stress measurements for cases that are over 80 mm thick. The configuration utilizes a neutron beam with a wavelength of 1.55 Å diffracted from the (220) plane with a diffraction angle (2θ) of 99.4°. The reason for the deep penetration capability is attributed to the chosen wavelength having enough intensities due to the low cross-section near the Bragg edge and the reduced beam path length (~16 mm) reflected by the large diffraction angle. Neutron diffraction experiments with this configuration can decrease strain errors up to ±150 με, corresponding to a stress of about ±30 MPa. Full article

Approximately half of the cases of chronic kidney disease (CKD) in childhood are caused by congenital anomalies of the kidney and urinary tract (CAKUT). Specific genes were identified as having significant importance in regard to the underlying genetic factors responsible for the CAKUT phenotype, and in our research, we focused on analyzing and comparing the expression levels of ectodysplasin A2 receptor (EDA2R), protocadherin9 (PCDH9), and TNF receptor-associated factor 7 (TRAF7) proteins in the cortex and medulla of healthy control kidneys during developmental phases 2, 3, and 4. We also performed an analysis of the area percentages of the mentioned proteins in the cortical and medullary sections of healthy embryonic and fetal kidneys compared to those affected by CAKUT, including duplex kidneys (DK), horseshoe kidneys (HK), hypoplastic kidneys (HYP), and dysplastic kidneys (DYS). We found that the CAKUT candidate gene proteins EDA2R, PCDH9, and TRAF7 are all expressed during normal human kidney development stages. In DYS, the expression of EDA2R was higher than in normal kidneys, likely due to EDA2R’s role in apoptosis, which was upregulated in specific cases and could possibly contribute to the formation of DYS. The expression of PCDH9 was lower in HK, which can be attributed to the possible role of PCDH9 in cell migration suppression. Decreased PCDH9 expression is linked to increased cell migration, potentially contributing to the development of HK. The level of TRAF7 expression was reduced in all examined kidney disorders compared to normal kidneys, suggesting that this reduction might be attributed to the crucial role of TRAF7 in the formation of endothelium and ciliogenesis, both of which are essential for normal kidney development. Further research is required to ascertain the function of these proteins in both the typical development of the kidney and in CAKUT. Full article

The purpose of this paper is to automate the interpretation of data during ultrasonic diffraction using a non-destructive testing (NDT) technique to accurately size defects for assisting in decision-making. A convolutional neural network (CNN) architecture was developed to automatically measure the length of the defect. Using the architecture, the population of A-scan signals in the scanning path was classified. The defect region was extracted and its size in the scanning direction was obtained by the connected region solution algorithm based on the classification results. The arrival time of diffraction waves was accurately identified by the intelligent denoising framework proposed, combined with Hilbert transform, and then the height of defects was calculated by corresponding geometric relations. The estimation results demonstrate that the measurement method can be considered as a useful technique for crack sizing in industrial structures, even in the case of complex noise. Full article

This manuscript presents the use of three novel technologies for the implementation of wireless green battery-less sensors that can be used in agriculture. The three technologies, namely, additive manufacturing, energy harvesting, and wireless power transfer from airborne transmitters carried from UAVs, are considered for smart agriculture applications, and their combined use is demonstrated in a case study experiment. Additive manufacturing is exploited for the implementation of both RFID-based sensors and passive sensors based on humidity-sensitive materials. A number of energy-harvesting systems at UHF and ISM frequencies are presented, which are in the position to power platforms of wireless sensors, including humidity and temperature IC sensors used as agriculture sensors. Finally, in order to provide wireless energy to the soil-based sensors with energy harvesting features, wireless power transfer (WPT) from UAV carried transmitters is utilized. The use of these technologies can facilitate the extensive use and exploitation of battery-less wireless sensors, which are environmentally friendly and, thus, “green”. Additionally, it can potentially drive precision agriculture in the next era through the implementation of a vast network of wireless green sensors which can collect and communicate data to airborne readers so as to support, the Artificial Intelligence and Machine Learning-based decision-making with data. Full article

Childhood stunting is a significant public health concern in Bangladesh. This study analysed the data from the Healthy Village programme, which aims to address childhood stunting in southern coastal Bangladesh. The aim was to assess childhood stunting prevalence over time and explore the risk factors in the programme areas. A cross-sectional, secondary data analysis was conducted for point-prevalence estimates of stunting from 2018 to 2021, including 132,038 anthropometric measurements of under-five children. Multivariate logistic regression analyses were conducted for risk factor analysis (n = 20,174). Stunting prevalence decreased from 51% in 2018 to 25% in 2021. The risk of stunting increased in hardcore poor (aOR: 1.46, 95% CI: 1.27, 1.68) and poor (aOR: 1.50, 95% CI: 1.33, 1.70) versus rich households, children with mothers who were illiterate (aOR: 1.25, 95% CI: 1.09, 1.44) and could read and write (aOR: 1.35, 95% CI: 1.16, 1.56) versus mothers with higher education, and children aged 1–2 years compared with children under one year (aOR: 1.32, 95% CI: 1.20, 1.45). The stunting rate was halved over three years in programme areas, which is faster than the national trend. We recommend addressing socioeconomic inequalities when tackling stunting and providing targeted interventions to mothers during the early weaning period. Full article

The autonomous vehicle is an innovative field for the application of machine learning algorithms. Controlling an agent designed to drive safely in traffic is very complex as human behavior is difficult to predict. An individual’s actions depend on a large number of factors that cannot be acquired directly by visualization. The size of the vehicle, its vulnerability, its perception of the environment and weather conditions, among others, are all parameters that profoundly modify the actions that the optimized model should take. The agent must therefore have a great capacity for adaptation and anticipation in order to drive while ensuring the safety of users, especially pedestrians, who remain the most vulnerable users on the road. Deep reinforcement learning (DRL), a sub-field that is supported by the community for its real-time learning capability and the long-term temporal aspect of its objectives looks promising for AV control. In a previous article, we were able to show the strong capabilities of a DRL model with a continuous action space to manage the speed of a vehicle when approaching a pedestrian crossing. One of the points that remains to be addressed is the notion of discrete decision-making intrinsically linked to speed control. In this paper, we will present the problems of AV control during a pedestrian crossing, starting with a modelization and a DRL model with hybrid action space adapted to the scalability of a vehicle-to-pedestrian (V2P) encounter. We will also present the difficulties raised by the scalability and the curriculum-based method. Full article

Herbal teas have attracted attention as functional beverages containing luteolin and apigenin, which exhibit antioxidant and anti-inflammatory effects. The objective of this study was to develop a sensitive online automated method to determine these flavones’ contents in herbal teas using in-tube solid-phase microextraction (IT-SPME) coupled with liquid chromatography–tandem mass spectrometry (LC–MS/MS). These compounds were extracted and concentrated by IT-SPME using a Supel Q PLOT capillary column and then separated and detected within 6 min using a CAPCELL PAK C18 MG III analytical column and a negative electrospray ionization-mode multiple-reaction monitoring system by LC–MS/MS. The detection limits (S/N = 3) for luteolin and apigenin were 0.4 and 0.8 pg mL⁻¹, respectively, and the calibration curves were linear in the range of 2–2000 pg mL⁻¹ with correlation coefficients above 0.9995, and intra-day and inter-day precisions with relative standard deviations below 2.9 and 3.6% (n = 6), respectively. The luteolin and apigenin in herbal tea were quantified using IT-SPME/LC-MS/MS following the acid hydrolysis of their glycosides. Among the 10 herbal teas tested, luteolin was detected in peppermint and sage at concentrations of 375 and 99 µg mL⁻¹, respectively, while apigenin was detected in German chamomile at 110 µg mL⁻¹, which were higher than in the other herbal teas. The method is expected to be a useful method for evaluating the efficacy of luteolin and apigenin in herbal teas as functional beverages. Full article

Despite recent advances, the prognosis of acute myeloid leukemia (AML) remains unsatisfactory due to disease recurrence and the development of resistance to both conventional and novel therapies. Engineered T cells expressing chimeric antigen receptors (CARs) on their cellular surface represent one of the most promising anticancer agents. CAR-T cells are increasingly used in patients with B cell malignancies, with remarkable clinical results despite some immune-related toxicities. However, at present, the role of CAR-T cells in myeloid neoplasms, including AML, is extremely limited, as specific molecular targets for immune cells are generally lacking on AML blasts. Besides the paucity of dispensable targets, as myeloid antigens are often co-expressed on normal hematopoietic stem and progenitor cells with potentially intolerable myeloablation, the AML microenvironment is hostile to T cell proliferation due to inhibitory soluble factors. In addition, the rapidly progressive nature of the disease further complicates the use of CAR-T in AML. This review discusses the current state of CAR-T cell therapy in AML, including the still scanty clinical evidence and the potential approaches to overcome its limitations, including genetic modifications and combinatorial strategies, to make CAR-T cell therapy an effective option for AML patients. Full article

The Epstein-Barr virus (EBV) is frequently found in endomyocardial biopsies (EMBs) from patients with heart failure, but the detection of EBV-specific DNA has not been associated with progressive hemodynamic deterioration. In this paper, we investigate the use of targeted next-generation sequencing (NGS) to detect EBV transcripts and their correlation with myocardial inflammation in EBV-positive patients with heart failure with reduced ejection fraction (HFrEF). Forty-four HFrEF patients with positive EBV DNA detection and varying degrees of myocardial inflammation were selected. EBV-specific transcripts from EMBs were enriched using a custom hybridization capture-based workflow and, subsequently, sequenced by NGS. The short-read sequencing revealed the presence of EBV-specific transcripts in 17 patients, of which 11 had only latent EBV genes and 6 presented with lytic transcription. The immunohistochemical staining for CD3⁺ T lymphocytes showed a significant increase in the degree of myocardial inflammation in the presence of EBV lytic transcripts, suggesting a possible influence on the clinical course. These results imply the important role of EBV lytic transcripts in the pathogenesis of inflammatory heart disease and emphasize the applicability of targeted NGS in EMB diagnostics as a basis for specific treatment. Full article

The Côa region in inner-northern Portugal heavily relies on viticulture, which is a cornerstone of its economy and cultural identity. Understanding the intricate relationship between climatic variables and wine production (WP) is crucial for adapting management practices to changing climatic conditions. This study employs machine learning (ML), specifically random forest (RF) regression, to predict grapevine yields in the Côa region using high-resolution climate data for 2004–2020. SHAP (SHapley Additive exPlanations) values are used to potentially explain the non-linear relationships between climatic factors and WP. The results reveal a complex interplay between predictors and WP, with precipitation emerging as a key determinant. Higher precipitation levels in April positively impact WP by replenishing soil moisture ahead of flowering, while elevated precipitation and humidity levels in August have a negative effect, possibly due to late-season heavy rainfall damaging grapes or creating more favorable conditions for fungal pathogens. Moreover, warmer temperatures during the growing season and adequate solar radiation in winter months favor higher WP. However, excessive radiation during advanced growth stages can lead to negative effects, such as sunburn. This study underscores the importance of tailoring viticultural strategies to local climatic conditions and employing advanced analytical techniques such as SHAP values to interpret ML model predictions effectively. Furthermore, the research highlights the potential of ML models in climate change risk reduction associated with viticulture, specifically WP. By leveraging insights from ML and interpretability techniques, policymakers and stakeholders can develop adaptive strategies to safeguard viticultural livelihoods and stable WP in a changing climate, particularly in regions with a rich agrarian heritage, such as the Côa region. Full article

We reanalyze the phenomenon of verbal (non)agreement with the 2SG tu in a megacorpus of Brazilian Portuguese compiled from the web. Unlike previous research, which has analyzed sociolinguistic interview data and regional differences, we examine these data with a focus on the internal linguistic factors that constrain the variability. Our analysis of 4860 tokens of tu + verb reveals that non-agreement with the 3SG verb form is by far the most common pattern, 2SG agreement being relatively infrequent. Individual verb lexemes show highly distinct rates of (non)agreement. In addition, the specific tense/aspect/mood forms and main/auxiliary status are likewise significant factors affecting the variation. We conclude that future studies of this phenomenon should not ignore these internal linguistic factors. We situate our study within a group of other recent studies in Romance linguistics, which have found that individual verbal and constructional patterns can have diverse effects on morphosyntactic variation. Full article

With an ageing global population, healthcare systems confront challenges unique to the elderly. Current care models primarily manage health–illness shifts but frequently miss developmental transitions, particularly for older adults. Meleis’s transition theory offers an underutilized framework to rejuvenate our gerontogeriatric nursing approach. This article aims to articulate and advocate the value of Meleis’s transition theory as a framework for gerontogeriatric nursing, focusing on developmental transitions, thereby seeking a transformative change in the quality of elderly care. The article delves into Meleis’s transition theory’s vital components—transition types, conditions, and nursing therapeutics. It explores how these can be a multifaceted guide for gauging and overseeing ageing’s developmental shifts; adopting this theoretical perspective deepens our comprehension and bears tangible implications. Nurses versed in this theory could appreciate the benefits of a nuanced approach to the elderly, distinguishing it from the conventional biomedical stance. As the demands of an ageing populace grow, the integration of Meleis’s transition theory into nursing practices is not merely beneficial but imperative, setting a new standard for comprehensive and specialized elderly care. Full article

Malawi has the potential to explore the utilization of biogas technology. The technology has existed in the country for decades. However, the uptake has been lower than expected. Further, there has been a high rate of dis-adoption of the installed systems. To deal with the problem, this study explored the opportunities and barriers to biogas technology to enhance biogas adoption and utilization in Malawi. Qualitative research methods using key informant interviews were employed to collect the data from biogas adopters, dis-adopters, potential adopters, and experts. A total of 22 households and 6 experts were interviewed. The findings of the study show that the country has opportunities for biogas adoption and utilization. The most mentioned opportunities were livestock farming practices, constraints to access to reliable energy sources, associated benefits of biogas technology, and land holding. However, the adoption of the technology has faced several challenges. Commonly cited barriers were the high installation and maintenance costs, inadequate feedstock, inappropriate dissemination approaches, lack of training after installation services and expertise, lack of reliable water sources, absence of ownership, lack of cooperation amongst institutions involved in biogas promotion, lack of a coordinating body for institutions involved in biogas dissemination, lack of standards, and socio-cultural factors. To overcome the challenges, strategies were identified, and these include the provision of incentives, loans and subsidies, provision of technical support services, having demonstration sites, employing suitable dissemination approaches, co-digestion or diversification of raw materials, awareness campaigns, and collaboration amongst sectors involved in biogas dissemination. Full article

In modern agricultural production, where a small number of commercial cultivars dominate, the collection, evaluation, and preservation of germplasm are important tasks to reduce the erosion of genes and preserve biodiversity. The aim of this study is to characterize the morphological and fruit chemical properties of the pomegranate germplasm grown on the East Adriatic coast, including the commercial cultivars ‘Hicaznar’, ‘Granada’, and ‘Wonderful’, and to highlight the characteristics with the greatest discriminating power. The characterization of the tree, leaf, flower, arils, seed, and juice was carried out using the UPOV descriptor. The colors of the peel, arils, and juice were analyzed according to the CIEL*a*b* method, total soluble solids were measured using refractometers, and total acidity was determined by titration with 0.1 M NaOH. The research results showed significant diversity between the cultivars, which were grouped into several clusters using an unsupervised analysis technique. Factors such as plant vigor, plant growth habit, predominant number of leaves per node on young shoots, crown type, fruit shape, fruit shape in cross-section, peel weight, total aril weight, aril weight, number of arils per fruit, seed length and width, seed yield, total acidity, TSS/TA ratio, and color parameters of the peel, arils, and juice showed high variability, indicating their strong discriminating power in determining the phenotypic diversity of pomegranate. Full article

Keloids, marked by abnormal cellular proliferation and excessive extracellular matrix (ECM) accumulation, pose significant therapeutic challenges. Ethyl pyruvate (EP), an inhibitor of the high-mobility group box 1 (HMGB1) and TGF-β1 pathways, has emerged as a potential anti-fibrotic agent. Our research evaluated EP’s effects on keloid fibroblast (KF) proliferation and ECM production, employing both in vitro cell cultures and ex vivo patient-derived keloid spheroids. We also analyzed the expression levels of ECM components in keloid tissue spheroids treated with EP through immunohistochemistry. Findings revealed that EP treatment impedes the nuclear translocation of HMGB1 and diminishes KF proliferation. Additionally, EP significantly lowered mRNA and protein levels of collagen I and III by attenuating TGF-β1 and pSmad2/3 complex expression in both human dermal fibroblasts and KFs. Moreover, metalloproteinase I (MMP-1) and MMP-3 mRNA levels saw a notable increase following EP administration. In keloid spheroids, EP induced a dose-dependent reduction in ECM component expression. Immunohistochemical and western blot analyses confirmed significant declines in collagen I, collagen III, fibronectin, elastin, TGF-β, AKT, and ERK 1/2 expression levels. These outcomes underscore EP’s antifibrotic potential, suggesting its viability as a therapeutic approach for keloids. Full article

This paper discusses the time-fractional nonlinear Schrödinger model with optical soliton solutions. We employ the $\left(f+\left(\frac{G^{\prime }}{G}\right)\right)$-expansion method to attain the optical solution solutions. An important tool for explaining the particular explosion of brief pulses in optical fibers is the nonlinear Schrödinger model. It can also be utilized in a telecommunications system. The suggested method yields trigonometric solutions such as dark, bright, kink, and anti-kink-type optical soliton solutions. Mathematica 11 software creates 2D and 3D graphs for many physically important parameters. The computational method is effective and generally appropriate for solving analytical problems related to complicated nonlinear issues that have emerged in the recent history of nonlinear optics and mathematical physics. Furthermore, we venture into uncharted territory by subjecting our model to chaotic and sensitivity analysis, shedding light on its robustness and responsiveness to perturbations. The proposed technique is being applied to this model for the first time. Full article

Prion diseases are fatal neurodegenerative disorders characterized by an accumulation of misfolded prion protein (PrP^Sc) in brain tissues. The shadow of prion protein (Sho) encoded by the shadow of prion protein gene (SPRN) is involved in prion disease progress. The interaction between Sho and PrP accelerates the PrP^Sc conversion rate while the SPRN gene polymorphisms have been associated with prion disease susceptibility in several species. Until now, the SPRN gene has not been investigated in ducks. We identified the duck SPRN gene sequence and investigated the genetic polymorphisms of 184 Pekin ducks. We compared the duck SPRN nucleotide sequence and the duck Sho protein amino acid sequence with those of several other species. Finally, we predicted the duck Sho protein structure and the effects of non-synonymous single nucleotide polymorphisms (SNPs) using computational programs. We were the first to report the Pekin duck SPRN gene sequence. The duck Sho protein sequence showed 100% identity compared with the chicken Sho protein sequence. We found 27 novel SNPs in the duck SPRN gene. Four amino acid substitutions were predicted to affect the hydrogen bond distribution in the duck Sho protein structure. Although MutPred2 and SNPs&GO predicted that all non-synonymous polymorphisms were neutral or benign, SIFT predicted that four variants, A22T, G49D, A68T, and M105I, were deleterious. To the best of our knowledge, this is the first report about the genetic and structural characteristics of the duck SPRN gene. Full article

An intelligent optimization technology was proposed to mitigate prevalent multi-defects, particularly failure, wrinkling, and springback in sheet metal forming. This method combined deep neural networks (DNNs), genetic algorithms (GAs), and Monte Carlo simulation (MCS), collectively as DNN-GA-MCS. Our primary aim was to determine intricate process parameters while elucidating the intricate relationship between processing methodologies and material properties. To achieve this goal, variable blank holder force (VBHF) trajectories were implemented into five sub-stroke steps, facilitating adjustments to the blank holder force via numerical simulations with an oil pan model. The Forming Limit Diagram (FLD) predicted by machine learning algorithms based on the Generalized Incremental Stress State Dependent Damage (GISSMO) model provided a robust framework for evaluating sheet failure dynamics during the stamping process. Numerical results confirmed significant improvements in formed quality: compared with the average value of training sets, the improvements of 18.89%, 13.59%, and 14.26% are achieved in failure, wrinkling, and springback; in the purposed two-segmented mode VBHF case application, the average value of three defects is improved by 12.62%, and the total summation of VBHF is reduced by 14.07%. Statistical methodologies grounded in material flow analysis were applied, accompanied by the proposal of distinctive optimization strategies for the die structure aimed at enhancing material flow efficiency. In conclusion, our advanced methodology exhibits considerable potential to improve sheet metal forming processes, highlighting its significant effect on defect reduction. Full article

Few-shot object detection is a challenging task aimed at recognizing novel classes and localizing with limited labeled data. Although substantial achievements have been obtained, existing methods mostly struggle with forgetting and lack stability across various few-shot training samples. In this paper, we reveal two gaps affecting meta-knowledge transfer, leading to unstable performance and forgetting in meta-learning-based frameworks. To this end, we propose sample normalization, a simple yet effective method that enhances performance stability and decreases forgetting. Additionally, we apply Z-score normalization to mitigate the hubness problem in high-dimensional feature space. Experimental results on the PASCAL VOC data set demonstrate that our approach outperforms existing methods in both accuracy and stability, achieving up to +4.4 [email protected] and +5.3 mAR in a single run, with +4.8 [email protected] and +5.1 mAR over 10 random experiments on average. Furthermore, our method alleviates the drop in performance of base classes. The code will be released to facilitate future research. Full article

Land formation seriously disturbs coastal salt marsh wetland ecosystems, while its influences on soil organic carbon (SOC) under chronosequences remain unclear. In this study, the impacts of the land formation time (from one to fourteen years) and soil properties on the chronosequences changes of SOC in the nascent wetland of Hengsha Island were investigated. The study results showed the following. (1) As the land-formation time extended, the SOC experienced a significant increase, tripling after a period of 14 years. The changes in SOC occurred mainly in the surface layer but not in the deep soil layer. Specifically, the surface layer’s average SOC reached 5.52 g·kg⁻¹, markedly higher than 3.17 g·kg⁻¹ in the deeper layer. (2) Spearman correlation analysis revealed that the ammonium nitrogen (${\mathrm{NH}}_4^{+}$-N), aboveground biomass (AGB), and soil water content (SWC) were positively correlated with the SOC. Methane emissions (CH₄) and SOC exhibited a negative correlation. (3) The structural equation model (SEM) illustrated that the duration of soil deformation directly impacted the vegetation growth and affected the distribution characteristics of the SOC by modifying the soil environmental conditions. Changes in SOC following land formation influenced the rapid succession of soil properties and vegetation, with the modification of carbon sinks in the ecosystems. Full article

Lacticaseibacillus rhamnosus is applied as a probiotic to alleviate various metabolic, gastrointestinal, and psychological symptoms and diseases, and its probiotic effectiveness is strain-specific. In this study, we obtained 21 strains of Ls. rhamnosus, and their genomes were sequenced. We defined the pan- and core-genomes of Ls. rhamnosus. Phenotypes such as the assimilation of carbohydrates and antibiotic resistance were experimentally characterized and associated with genome annotations. Nine strains were selected and tested for growth rates, tolerance to acidity/alkalinity and bile acids, the production of short-chain fatty acids, and competition with pathogenic microbes. Strains WL11 and WL17 were targeted as potential probiotics and were applied in mouse model tests for the alleviation of chronic fatigue syndrome (CFS) and irritable bowel syndrome (IBS). The results showed that WL11 and WL17 effectively alleviated slow body weight gain, anxiety, poor memory, and cognitive impairment in CFS mouse models. They also reduced the expression of pro-inflammatory factors, such as TNF-α and IL-6, and alleviated intestinal peristalsis, visceral hypersensitivity, and anxiety-like behavior in IBS mouse models. This study reports new Ls. rhamnosus strain resources and their effect on alleviation of both IBS and CFS symptoms with mouse models; the probiotic functions of those strains in human patients remain to be further tested. Full article

Existing methods for inverse synthetic aperture radar (ISAR) target recognition typically rely on a single high-resolution radar signal type, such as ISAR images or high-resolution range profiles (HRRPs). However, ISAR images and HRRP data offer representations of targets across different aspects, each containing valuable information crucial for radar target recognition. Moreover, the process of generating ISAR images inherently facilitates the acquisition of HRRP data, ensuring timely data collection. Therefore, to fully leverage the different information from both HRRP data and ISAR images and enhance ISAR ship target recognition performance, we propose a novel deep fusion network named the Separation-Decision Recognition network (SDRnet). First, our approach employs a convolutional neural network (CNN) to extract initial feature vectors from ISAR images and HRRP data. Subsequently, a feature separation module is employed to derive a more robust target representation. Finally, we introduce a weighted decision module to enhance overall predictive performance. We validate our method using simulated and measured data containing ten categories of ship targets. The experimental results confirm the effectiveness of our approach in improving ISAR ship target recognition. Full article