Search Results (69)

Re-identification (ReID) has been widely applied in person and vehicle recognition tasks. This study extends its application to a novel domain: insect (silkworm) recognition. However, unlike person or vehicle ReID, silkworm ReID presents unique challenges, such as the high similarity between individuals, arbitrary poses, and significant background noise. To address these challenges, we propose a multi-view network for silkworm ReID, called WormNet, which is built upon an innovative strategy termed extraction purification extraction interaction. Specifically, we introduce a multi-order feature extraction module that captures a wide range of fine-grained features by utilizing convolutional kernels of varying sizes and parallel cardinality, effectively mitigating issues of high individual similarity and diverse poses. Next, a feature mask module (FMM) is employed to purify the features in the spatial domain, thereby reducing the impact of background interference. To further enhance the data representation capabilities of the network, we propose a channel interaction module (CIM), which combines an efficient channel attention network with global response normalization (GRN) in parallel to recalibrate features, enabling the network to learn crucial information at both the local and global scales. Additionally, we introduce a new silkworm ReID dataset for network training and evaluation. The experimental results demonstrate that WormNet achieves an mAP value of 54.8% and a rank-1 value of 91.4% on the dataset, surpassing both state-of-the-art and related networks. This study offers a valuable reference for ReID in insects and other organisms. Full article

This study proposes the use of Physics-Informed Neural Networks (PINNs) to further advance the curvature interference analysis method. The nonlinear equation system encountered in determining the curvature interference limit line is embedded into the PINN loss function, thereby enabling the solution of high-dimensional, nonlinear equations. Computational results demonstrate that the PINN model achieves a solution accuracy on the order of 10⁻¹³ when solving multidimensional nonlinear systems, which is comparable to the classical Fsolve algorithm. The curvature interference analysis reveals the presence of two curvature interference boundary lines, although they rarely extend to the worm gear tooth surface. A study on the influence of design parameters on the interference boundaries indicates that the axial installation distance has the greatest impact. Inadequate axial spacing causes the interference limit line to shift toward the inner end of the worm gear, significantly increasing the risk of interference in that region. The proposed curvature interference analysis method based on PINNs can be extended to other types of gear drives. It also lays the foundation for future work on establishing both forward and inverse mappings between design parameters and curvature interference using PINNs. Full article

The pine wood nematode, a microscopic worm-like organism, is the primary cause of Pine Wilt Disease (PWD), a serious threat to pine forests, as infected trees can die within a few months. In this study, we aim to predict the occurrence of PWD by leveraging geographical and meteorological features, with a particular focus on incorporating interpretability through explainable AI (XAI). Unlike conventional models that utilize features from a single point of location, our approach considers surrounding environmental factors (patches) and employs a channel grouping mechanism to aggregate features effectively, enhancing prediction accuracy. Experimental results demonstrate that the proposed model based on convolutional neural network (CNN) outperforms traditional point-wise models, achieving a 9.7% higher F1-score. Experimental results show that data augmentation further improved performance, while interpretability analysis identified precipitation and temperature-related features as the most significant contributors. The developed CNN model provides a robust and interpretable framework, offering valuable insights into the spatial and environmental dynamics of PWD occurrence. Full article

Human infections are greatly impacted by intestinal nematodes. These nematodes, which encompass the large roundworms, have a direct impact on human health and well-being due to their close cohabitation with the host’s microorganisms. When nematodes infect a host, the microbiome composition changes, and this can impact the host’s ability to control the parasites. We aimed to find out if the small intestinal roundworms produce substances that have antimicrobial properties and respond to their microbial environment, and if the immune and regulatory reactions to nematodes are altered in humans lacking gut microbes. There is no doubt that different nematodes living in the intestines can alter the balance of intestinal bacteria. Nonetheless, our knowledge about the parasite’s influence on the gut microbiome remains restricted. The last two decades of study have revealed that the type of iron utilized can influence the activation of unique virulence factors. However, some roundworm proteins like P43, which makes up a large portion of the worm’s excretory-secretory product, have an unknown role. This review explores how the bacterial iron regulatory network contributes to the adaptability of this opportunistic pathogen, allowing it to successfully infect nematodes in different host environments. Full article

The objective of this study is to investigate the effect of the solidification microstructure of CJ5L Recycled Stainless Steel in the cast state on its thermoplasticity. Therefore, the residual ferrite, solidification structure, and high-temperature thermoplasticity in both Recycled and Non-Recycled steel ingots are examined. The principal experimental techniques employed include SEM, OM, EPMA, and EDS. It was observed that the solidification microstructure underwent a gradual transformation from a dendritic structure with a skeletal shape to a worm-like dendrite as the thickness increased. This resulted in the formation of large equiaxed grains at the center of the steel ingots. The cooling rate decreased from 3~16 °C/s at the surface to below 0.8 °C/s at the center. The residual ferrite gradually transformed from a skeletal to granular and rod-like form with increasing depth, eventually forming a ferrite network at the center of the casting. In the Recycled steel, the composition segregation resulted in the formation of a network ferrite aggregation at the center of the steel ingots. The analysis of microstructure changes in conjunction with thermodynamic calculations revealed that the solidification mode of CJ5L stainless steel underwent a transition from the ferritic–austenitic (FA) mode to the austenitic–ferritic (AF) mode with increasing casting thickness. This resulted in an increase in the amount of residual ferrite from the surface to the center. The high-temperature thermoplasticity analysis of CJ5L stainless steel showed that at temperatures between 800 °C and 900 °C, the casting displayed optimal properties, minimizing crack formation during subsequent processing. Full article

Emulsified acid treatments present an innovative and environmentally sustainable alternative to conventional hydrochloric acid (HCl) methods in enhancing oil recovery. This study investigates the application of a stable emulsified acid formulation in matrix acidizing operations to improve injectivity in four wells within the Qusahwira Field. Compared to traditional 15% HCl treatments, the emulsified acid demonstrates deeper acid penetration and retardation effect leading to enhanced injection rate. By delivering deep worm holing effects against calcium carbonate formation, this dual-phase system enhances injectivity by 14 times while minimizing the environmental and material impacts associated with spent acid volumes. The methodology integrates advanced neural network modeling to predict stimulation outcomes based on 15 operational and reservoir factors. This model reduces the trial-and-error approach, cutting operational costs and time for carbonate reservoir. Field trials reveal significant improvements in injection pressure and a marked reduction in circulation pressure during stimulation, underscoring the treatment’s efficiency. Developed in a Superior Abu Dhabi laboratory, the emulsified acid achieves high-temperature stability (200 °F) and deep acid penetration, further reducing the ecological footprint of acid stimulation by enhancing operational precision and reducing chemical use. This paper highlights a sustainable approach to optimizing reservoir productivity, aligning with global efforts to minimize environmental impacts in oil recovery processes. Full article

Schistosomiasis is a neglected tropical disease and the second most common parasitic disease after malaria. While praziquantel remains the primary treatment, concerns about drug resistance highlight the urgent need for new drugs and effective vaccines to achieve sustainable control. Previous proteomic studies from our group revealed that the expression of Schistosoma japonicum glycosyltransferase and nicastrin as proteins was higher in single-sex males than mated males, suggesting their critical roles in parasite reproduction and their potential as vaccine candidates. In this study, bioinformatic tools were employed to analyze the structural and functional properties of these proteins, including their signal peptide regions, transmembrane domains, tertiary structures, and protein interaction networks. Recombinant forms of glycosyltransferase and nicastrin were expressed and purified, followed by immunization experiments in BALB/c mice. Immunized mice exhibited significantly elevated specific IgG antibody levels after three immunizations compared to adjuvant and PBS controls. Furthermore, immunization with recombinant glycosyltransferase and nicastrin significantly reduced the reproductive capacity of female worms and liver egg burden, though egg hatchability and adult worm survival were unaffected. These findings demonstrate that recombinant glycosyltransferase and nicastrin are immunogenic and reduce female worm fecundity, supporting their potential as vaccine candidates against schistosomiasis. Full article

Aquatic biodiversity includes a variety of unique species, their habitats, and their interactions with each other. Albania has a large hydrographic network including rivers, lakes, wetlands and coastal marine areas, contributing to a high level of aquatic biodiversity. Currently, evaluating aquatic biodiversity relies on morphological species identification methods, but DNA-based taxonomic identification could improve the monitoring and assessment of aquatic ecosystems. This study aims to evaluate the coverage of COI DNA barcodes in the reference libraries for the known aquatic animal species present in the coastal lagoons of Albania. In this study, the six most studied coastal lagoons of Albania were selected. Species data were gathered from the scientific literature and publicly available sites and studies. The collected species lists were taxonomically standardised using global public taxonomic databases like WORMS. The standardised lists were used to analyse the barcode gap of COI based on two public DNA barcode libraries: Barcode of Life Data Systems (BOLD) and NCBI GenBank. The results show that the COI DNA barcode gap in the coastal lagoons of Albania ranges from 7% (Lagoon of Patok) to 33% (Karavasta Lagoon). Fishes and Amphibia represent the groups with the lowest barcode gap (8% each), while Annelida shows the highest (47%). In conclusion, the COI gene marker for DNA-based biodiversity assessments is reliable for the coastal lagoons of Albania. Full article

Malware remains a major threat to computer systems, with a vast number of new samples being identified and documented regularly. Windows systems are particularly vulnerable to malicious programs like viruses, worms, and trojans. Dynamic analysis, which involves observing malware behavior during execution in a controlled environment, has emerged as a powerful technique for detection. This approach often focuses on analyzing Application Programming Interface (API) calls, which represent the interactions between the malware and the operating system. Recent advances in deep learning have shown promise in improving malware detection accuracy using API call sequence data. However, the potential of Generative Adversarial Networks (GANs) for this purpose remains largely unexplored. This paper proposes a novel hybrid deep learning model combining Gated Recurrent Units (GRUs) and GANs to enhance malware detection based on API call sequences from Windows portable executable files. We evaluate our GRU–GAN model against other approaches like Bidirectional Long Short-Term Memory (BiLSTM) and Bidirectional Gated Recurrent Unit (BiGRU) on multiple datasets. Results demonstrated the superior performance of our hybrid model, achieving 98.9% accuracy on the most challenging dataset. It outperformed existing models in resource utilization, with faster training and testing times and low memory usage. Full article

This paper presents a novel three-dimensional (3D) minimally actuated serial robot (MASR) and its unique kinematic analysis. Unlike traditional robots, the 3D MASR features a passive arm devoid of wires or motors, comprising passive rotational and prismatic joints. A single mobile actuator (MA) traverses the arm, engages designated joints for operation, and locks them in place with a worm gear setup. A gripper is attached to the MA, enabling object transportation along the arm, reducing joint actuation, and optimizing task completion time. Our key contributions include the mechanical design, and in particular the robot’s passive joints with their automated actuation mechanism, and a novel optimization algorithm leveraging neural networks (NNs) to minimize task completion time through advanced kinematic analysis. Experiments with a physical prototype of the 3D MASR demonstrate its major advantages: it is remarkably lightweight (2.3 kg for a 1 m long arm and a 1 kg payload) compared to similar robots; it is highly modular (five joints R and P actuated by a single MA); and part replacement is effortless due to the absence of wiring along the arm. These features are visually depicted in the accompanying video. Full article

Dual networks formed by entangled polymer chains and wormlike surfactant micelles have attracted increasing interest in their application as thickeners in various fields since they combine the advantages of both polymer- and surfactant-based fluids. In particular, such polymer-surfactant mixtures are of great interest as novel hydraulic fracturing fluids with enhanced properties. In this study, we demonstrated the effect of the chemical composition of an uncharged polymer poly(vinyl alcohol) (PVA) and pH on the rheological properties and structure of its mixtures with a cationic surfactant erucyl bis(hydroxyethyl)methylammonium chloride already exploited in fracturing operations. Using a combination of several complementary techniques (rheometry, cryo-transmission electron microscopy, small-angle neutron scattering, and nuclear magnetic resonance spectroscopy), we showed that a small number of residual acetate groups (2–12.7 mol%) in PVA could significantly reduce the viscosity of the mixed system. This result was attributed to the incorporation of acetate groups in the corona of the micellar aggregates, decreasing the molecular packing parameter and thereby inducing the shortening of worm-like micelles. When these groups are removed by hydrolysis at a pH higher than 7, viscosity increases by five orders of magnitude due to the growth of worm-like micelles in length. The findings of this study create pathways for the development of dual semi-interpenetrating polymer-micellar networks, which are highly desired by the petroleum industry. Full article

This article presents the operation of an automatic pine sawn timber inspection system, which was developed at the Woodinspector company and is offered commercially. The vision inspection system is used to detect various wood defects, including knots, blue stain, and mechanical damage caused by worms. A blue stain is a defect that is difficult to detect based on the color of the wood, because it can be easily confused with wood defects or dirt that do not impair its strength properties. In particular, the issues of detecting blue stain in wood, the use of artificial neural networks, and improving the operation of the system in production conditions are discussed in this article. While training the network, 400 boards, 4 m long, and their cross-sections of 100 × 25 [mm] were used and photographed using special scanners with laser illuminators from four sides. The test stages were carried out during an 8-hour workday at a sawmill (8224 m of material was scanned) on material with an average of 10% blue stain (every 10th board has more than 30% of its length stained blue). The final learning error was assessed based on defective boards detected by humans after the automatic selection stage. The system error for 5387 boards, 550 m long, which had blue staining that was not detected by the scanner (clean) was 0.4% (25 pieces from 5387), and 0.1 % in the case of 3412 boards, 610 mm long, on which there were no blue stains, but were wrongly classified (blue stain). For 6491 finger-joint boards (180–400 mm), 48 pieces were classified as class 1 (clean), but had a blue stain (48/6491 = 0.7%), and 28 pieces did not have a blue stain, but were classified as class 2 (28/3561 = 0.7%). Full article

The Internet of Things (IoT) is becoming increasingly important due to the ability to collect data in real time and monitor the performance of systems. In this sense, the objective of the project is to create an IoT system to monitor and enhance red boll worm farming conditions in California as part of a strategy to diversify annelid-based goods. Therefore, the goal is to expand this animal’s productivity so that additional items can be made from California red worms. Furthermore, the method used implies a research design that uses an experimental approach to obtain data based on the variable conditions identified in the literature review. The analysis of the data will allow determination of the factors that result in optimization of production, and at the same time creation of a production estimation in the network platform. Finally, this project proposes to facilitate the monitoring and control of the variables that interfere in the earthworm reproduction process to increase the production of annelids in pursuit of product diversification. In addition, we put it into practice in real life to demonstrate its applicability and efficacy. In this mode, the results indicate potential findings about IoT application in agriculture situations. Full article

Drug–target interactions (DTIs) are considered a crucial component of drug design and drug discovery. To date, many computational methods were developed for drug–target interactions, but they are insufficiently informative for accurately predicting DTIs due to the lack of experimentally verified negative datasets, inaccurate molecular feature representation, and ineffective DTI classifiers. Therefore, we address the limitations of randomly selecting negative DTI data from unknown drug–target pairs by establishing two experimentally validated datasets and propose a capsule network-based framework called CapBM-DTI to capture hierarchical relationships of drugs and targets, which adopts pre-trained bidirectional encoder representations from transformers (BERT) for contextual sequence feature extraction from target proteins through transfer learning and the message-passing neural network (MPNN) for the 2-D graph feature extraction of compounds to accurately and robustly identify drug–target interactions. We compared the performance of CapBM-DTI with state-of-the-art methods using four experimentally validated DTI datasets of different sizes, including human (Homo sapiens) and worm (Caenorhabditis elegans) species datasets, as well as three subsets (new compounds, new proteins, and new pairs). Our results demonstrate that the proposed model achieved robust performance and powerful generalization ability in all experiments. The case study on treating COVID-19 demonstrates the applicability of the model in virtual screening. Full article

Industry 4.0 has been an impactful and much-needed revolution that has not only influenced different aspects of life but has also changed the course of manufacturing processes. The main purpose of the manufacturing industry is to increase productivity, reduce manufacturing costs, and improve the quality of the product. This has helped to drive economic growth and improve people’s standards. The gear-hobbing industry, being the most efficient one, has not received much attention in terms of Industry 4.0. In prior works, simulation-based approaches with individual parameters, e.g., temperature, current, and vibration, or a few of these parameters, were considered with different approaches, This work presents a real-time experimental approach that involves raw data collection on three different parameters together, i.e., temperature, current, and vibration, using sensors placed on an industrial machine during gear hobbing process manufacturing. The data are preprocessed and then utilised for training an artificial neural network (ANN) to predict the remaininguseful life (RUL) of a tool. It is demonstrated that an ANN with multiple hidden layers can predict the RUL of the tool with high accuracy. The compared results show that tool wear prediction using an ANN with multiple layers has better prediction accuracy during worm gear hobbing. Full article