Search Results (7,768)

Inverse Synthetic Aperture Radar (ISAR) images are extensively used in Radar Automatic Target Recognition (RATR) for non-cooperative targets. However, acquiring training samples for all target categories is challenging. Recognizing target classes without training samples is called Zero-Shot Learning (ZSL). When ZSL involves multiple modalities, it becomes Multi-modal Zero-Shot Learning (MZSL). To achieve MZSL, a framework is proposed for generating ISAR images with optical image aiding. The process begins by extracting edges from optical images to capture the structure of ship targets. These extracted edges are used to estimate the potential locations of the target’s scattering centers. Using the Geometric Theory of Diffraction (GTD)-based scattering center model, the edges’ ISAR images are generated from the scattering centers. Next, a mapping is established between the edges’ ISAR images and the actual ISAR images. Neighbor-Adapted Local Linear Embedding (NALLE) generates pseudo-ISAR images for the unseen classes by combining the edges’ ISAR images with the actual ISAR images from the seen classes. Finally, these pseudo-ISAR images serve as training samples, enabling the recognition of test samples. In contrast to the network-based approaches, this method requires only a limited number of training samples. Experiments based on simulated and measured data validate the effectiveness. Full article

Mental health assessment is typically carried out via a series of conversation sessions with medical professionals, where the overall aim is the diagnosis of mental illnesses and well-being evaluation. Despite its arguable socioeconomic significance, national health systems fail to meet the increased demand for such services that has been observed in recent years. To assist and accelerate the diagnosis process, this work proposes an AI-based tool able to provide interpretable predictions by automatically processing the recorded speech signals. An explainability-by-design approach is followed, where audio descriptors related to the problem at hand form the feature vector (Mel-scaled spectrum summarization, Teager operator and periodicity description), while modeling is based on Hidden Markov Models adapted from an ergodic universal one following a suitably designed data selection scheme. After extensive and thorough experiments adopting a standardized protocol on a publicly available dataset, we report significantly higher results with respect to the state of the art. In addition, an ablation study was carried out, providing a comprehensive analysis of the relevance of each system component. Last but not least, the proposed solution not only provides excellent performance, but its operation and predictions are transparent and interpretable, laying out the path to close the usability gap existing between such systems and medical personnel. Full article

This paper focuses on the crucial task of automatic recognition and understanding of table structures in engineering drawings and document processing. Given the importance of tables in information display and the urgent need for automated processing of tables in the digitalization process, an intelligent verification method is proposed. This method integrates multiple key techniques: YOLOv10 is used for table object recognition, achieving a precision of 0.891, a recall rate of 0.899, mAP50 of 0.922, and mAP50-95 of 0.677 in table recognition, demonstrating strong target detection capabilities; the improved LORE algorithm is adopted to extract table structures, breaking through the limitations of the original algorithm by segmenting large-sized images, with a table extraction accuracy rate reaching 91.61% and significantly improving the accuracy of handling complex tables; RapidOCR is utilized to achieve text recognition and cell correspondence, solving the problem of text-cell matching; for equipment name semantic matching, a method based on BERT is introduced and calculated using a comprehensive scoring method. Meanwhile, an improved cuckoo search algorithm is proposed to optimize the adjustment factors, avoiding local optima through sine optimization and the catfish effect. Experiments show the accuracy of equipment name matching in semantic similarity calculation approaches 100%. Finally, the paper provides a concrete system practice to prove the effectiveness of the algorithm. In conclusion, through experimental comparisons, this method exhibits excellent performance in table area location, structure recognition, and semantic matching and is of great significance and practical value in advancing table data processing technology in engineering drawings. Full article

Mango (Mangifera Indica L.), a key horticultural crop, particularly in Pakistan, has been primarily studied locally using low- to medium-resolution satellite imagery, usually focusing on a particular phenological stage. The large canopy size, complex tree structure, and unique phenology of mango trees further accentuate intrinsic challenges posed by low-spatiotemporal-resolution data. The absence of mango-specific vegetation indices compounds the problem of accurate health classification and yield estimation at the tree level. To overcome these issues, this study utilizes high-resolution multi-spectral UAV imagery collected from two mango orchards in Multan, Pakistan, throughout the annual phenological cycle. It introduces MangiSpectra, an integrated two-staged framework based on Long Short-Term Memory (LSTM) networks. In the first stage, nine conventional and three mango-specific vegetation indices derived from UAV imagery were processed through fine-tuned LSTM networks to classify the health of individual mango trees. In the second stage, associated data such as the trees’ age, variety, canopy volume, height, and weather data were combined with predicted health classes for yield estimation through a decision tree algorithm. Three mango-specific indices, namely the Mango Tree Yellowness Index (MTYI), Weighted Yellowness Index (WYI), and Normalized Automatic Flowering Detection Index (NAFDI), were developed to measure the degree of canopy covered by flowers to enhance the robustness of the framework. In addition, a Cumulative Health Index (CHI) derived from imagery analysis after every flight is also proposed for proactive orchard management. MangiSpectra outperformed the comparative benchmarks of AdaBoost and Random Forest in health classification by achieving 93% accuracy and AUC scores of 0.85, 0.96, and 0.92 for the healthy, moderate and weak classes, respectively. Yield estimation accuracy was reasonable with $R^2=0.21$, and $\mathrm{RMSE}=50.18$. Results underscore MangiSpectra’s potential as a scalable precision agriculture tool for sustainable mango orchard management, which can be improved further by fine-tuning algorithms using ground-based spectrometry, IoT-based orchard monitoring systems, computer vision-based counting of fruit on control trees, and smartphone-based data collection and insight dissemination applications. Full article

This paper establishes a physical model for the non-contact rotary screen coating process based on a spacecraft structural plate and proposes a theoretical expression for the adhesive thickness of the non-contact rotary screen coating. The thickness of the adhesive is a critical factor influencing the quality of the optical solar reflector (OSR) adhesion. The thickness of the adhesive layer depends on the equivalent fluid height and the ratio of the fluid flow rate to the squeegee speed below the squeegee. When the screen and fluid remain constant, the fluid flow rate below the squeegee depends on the pressure at the tip of the squeegee. The pressure is also a function related to the deformation characteristics and speed of the squeegee. Based on the actual geometric shape of the wedge-shaped squeegee, the analytical expression for the vertical displacement of the squeegee is obtained as the actual boundary of the flow field. The analytical expression for the deformation angle of the squeegee is used to solve the contact length between the squeegee and the rotary screen. It reduces the calculation difficulty compared with the previous method. Based on the theory of rheology and fluid mechanics, the velocity distribution of the fluid under the squeegee and the expression of the dynamic pressure at the tip of the squeegee were obtained. The dynamic pressure at the tip of the squeegee is a key factor for the adhesive to pass through the rotary screen. According to the continuity equation of the fluid, the theoretical thickness expression of the non-contact rotary screen coating is obtained. The simulation and experimental results show that the variation trend of coating thickness with the influence of variables is consistent. Experimental and simulation errors compared to theoretical values are less than 5%, which proves the rationality of the theoretical expression of the non-contact rotary screen coating thickness under the condition of considering the actual squeegee deformation. The existence of differences proves that a small part of the colloid remains on the rotary screen during the colloid transfer process. The expression parameterizes the rotary screen coating model and provides a theoretical basis for the design of automatic coating equipment. Full article

As the main working part of a combine harvester, the cleaning device affects the cleaning performance of the machine. The simulation of flow fields in a cleaning chamber has become an important part of the design. Currently, post-processing analyses of flow field simulation still rely on the researchers’ experience, so it is difficult to obtain information from post-processing automatically. The experience of researchers is difficult to describe and disseminate. This paper studied an intelligent method to analyze simulation result data which is based on the object detection algorithm and the reasoning mechanism. YOLOv8, one of the deep learning object detection algorithms, was selected to identify key-point data from the flow field in a cleaning chamber. First, the training dataset was constructed via scatter plot drawing, data enhancement, random screening, and other technologies. Then, the flow field in the cleaning chamber was divided into six key areas by identifying the key points of the flow field. And, an analysis of the reasonable wind velocity in the areas was conducted, and the cleaning results of the grain were obtained by using the reasoning mechanism based on rules and examples. Finally, a system based on the above method was established in Python 3.10 software. With the help of the method and the system in this paper, the flow field characteristics in a cleaning chamber and the effects of wind on the cleaning effect can be obtained automatically if the physical properties of the crop, the geometric parameters of the cleaning chamber, and the working parameters of the machine are given. Full article

A series of studies and research have shown the existence of a link between handwriting and a person’s personality traits. There are numerous fields that require a psychological assessment of individuals, where there is a need to determine personality traits in a faster and more efficient manner than that based on classic questionnaires or graphological analysis. The development of image processing and recognition algorithms based on machine learning and deep neural networks has led to a series of applications in the field of graphology. In the present study, a system for automatically extracting handwriting characteristics from written documents and correlating them with Myers–Briggs type indicator is implemented. The system has an architecture composed of three levels, the main level being formed by four convolutional neural networks. To train the networks, a database with different types of handwriting was created. The experimental results show an accuracy ranging between 89% and 96% for handwritten features’ recognition and results ranging between 83% and 91% in determining Myers–Briggs indicators. Full article

The purpose of this study was to demonstrate the series of processes involved in designing, manufacturing, installing, and operating a practical Surface Image Flowmeter (SIF) system, complete with suitable hardware and software. By ‘practical’, we mean a system capable of automatically measuring discharges in a river 24 h a day, 365 days a year, at 2 min intervals. The equipment required for this practical SIF includes a CCTV camera, a water level gauge, a Linux-based PC for analysis, and lighting for night-time measurements. We also developed software to operate the system. Furthermore, we applied a coordinate transformation method using projective transformation to calculate the area of the measurement cross-section according to changes in water level and to adjust the positions of velocity analysis points within the image. The CCTV captured 20 s video clips every 2 min, which were then analyzed using the Spatio-Temporal Image Velocimetry (STIV) method. For the STIV method, measurement points were set at appropriate intervals on the measurement cross-section, and spatio-temporal images (STIs) were constructed at these points for analysis. The STIs were captured parallel to the main flow direction (perpendicular to the cross-section), and the resulting STIs were analyzed using the hybrid STIV method to calculate the discharge. When the constructed SIF system was tested in a steep-sloped channel at the Andong River Experiment Center, the velocity distribution showed a difference of less than 9% compared to measurements from a traditional current meter, and the discharge showed a difference of around 10% compared to measurements from an Acoustic Doppler Current Profiler (ADCP). Full article

Interferometric synthetic aperture radar (InSAR) technology plays a crucial role in monitoring surface deformation and has become widely used in volcanic and earthquake research. With the rapid advancement of satellite technology, InSAR now generates vast volumes of deformation data. Deep learning has revolutionized data analysis, offering exceptional capabilities for processing large datasets. Leveraging these advancements, automatic detection of volcanic and earthquake deformation from extensive InSAR datasets has emerged as a major research focus. In this paper, we first introduce several representative deep learning architectures commonly used in InSAR data analysis, including convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and Transformer networks. Each architecture offers unique advantages for addressing the challenges of InSAR data. We then systematically review recent progress in the automatic detection and identification of volcanic and earthquake deformation signals from InSAR images using deep learning techniques. This review highlights two key aspects: the design of network architectures and the methodologies for constructing datasets. Finally, we discuss the challenges in automatic detection and propose potential solutions. This study aims to provide a comprehensive overview of the current applications of deep learning for extracting InSAR deformation features, with a particular focus on earthquake and volcanic monitoring. Full article

Background: Machine learning methods for clinical assistance require a large number of annotations from trained experts to achieve optimal performance. Previous work in natural language processing has shown that it is possible to automatically extract annotations from the free-text reports associated with chest X-rays. Methods: This study investigated techniques to extract 49 labels in a hierarchical tree structure from chest X-ray reports written in Danish. The labels were extracted from approximately 550,000 reports by performing multi-class, multi-label classification using a method based on pattern-matching rules, a classic approach in the literature for solving this task. The performance of this method was compared to that of open-source large language models that were pre-trained on Danish data and fine-tuned for classification. Results: Methods developed for English were also applicable to Danish and achieved similar performance (a weighted F1 score of 0.778 on 49 findings). A small set of expert annotations was sufficient to achieve competitive results, even with an unbalanced dataset. Conclusions: Natural language processing techniques provide a promising alternative to human expert annotation when annotations of chest X-ray reports are needed. Large language models can outperform traditional pattern-matching methods. Full article

Radio Frequency Identification (RFID) is a key component in automatic systems that address challenges in environment monitoring. However, tag collision continues to be an essential challenge in such applications due to high-density RFID deployments. This paper addresses the issue of RFID tag collision in large-scale intensive tags, particularly in industrial membrane contamination monitoring systems, and improves the system performance by minimizing collision rates through an innovative collision-avoiding algorithm. This research improved the Predictive Framed Slotted ALOHA–Collision Tracking Tree (PRFSCT) algorithm by cooperating probabilistic and deterministic methods through dynamic frame length adjustment and multi-branch tree processes. After simulation and validation in MATLAB R2023a, we performed a hardware test with the RFM3200 and UHFReader18 passive tags. The method’s efficiency is evaluated through collision slot reduction, delay minimization, and enhanced throughput. PRFSCT significantly reduces collision slots when the number of tags to identify is the same for PRFSCT, Framed Slotted ALOHA (FSA), and Collision Tracking Tree (CTT); the PRFSCT method needs the fewest time slots. When identifying more than 200 tags, PRFSCT has 225 collision slots for 500 tags compared to FSA and CTT, which have approximately 715 and 883 for 500 tags, respectively. It demonstrates exceptional stability and adaptability under increased density needs while improving tag reading at distances. Full article

Point feature cartographic label placement is a key problem in the automatic configuration of map labeling. Prior research on it only addresses label conflict or overlap issues; it does not fully take into account and resolve both types of issues. In this study, we attempt to apply machine learning techniques to the automatic placement of point feature labels since label placement is a task that heavily relies on expert expertise, which is very congruent with neural networks’ ability to mimic the human brain’s thought process. We trained ResNet using large amounts of well-labeled picture data. The label’s proper location for a given unlabeled point feature was then predicted by the trained model. We assessed the outcomes both quantitatively and qualitatively, contrasting the ResNet model’s output with that of the expert manual placement approach and the conventional Maplex automatic placement method. According to the evaluation, the ResNet model’s test set accuracy was 97.08%, demonstrating its ability to locate the point feature label in the right place. This study offers a workable solution to the label overlap and conflict issue. Simultaneously, it has significantly enhanced the map’s esthetic appeal and the information’s clarity. Full article

The rapid growth of the human population, the increase in consumer needs regarding food authenticity, and the sub-par synchronization between agricultural and food industry production necessitate the development of reliable track and tracing solutions for food commodities. The present research proposes a simple and affordable digital system that could be implemented in most production processes to improve transparency and productivity. The system combines non-destructive, rapid quality assessment methods, such as near infrared spectroscopy (NIRS) and computer/machine vision (CV/MV), with track and tracing functionalities revolving around the Internet of Things (IoT) and radio frequency identification (RFID). Meanwhile, authenticity is provided by a self-developed blockchain-based solution that validates all data and documentation “from farm to fork”. The system is introduced by taking certified Hungarian sweet potato production as a model scenario. Each element of the proposed system is discussed in detail individually and as a part of an integrated system, capable of automatizing most production flows while maintaining complete transparency and compliance with authority requirements. The results include the data and trust model of the system with sequence diagrams simulating the interactions between participants. The study lays the groundwork for future research and industrial applications combining digital tools to improve the productivity and authenticity of the agri-food industry, potentially increasing the level of trust between participants, most importantly for the consumers. Full article

Studying particle discharge rates in fluidized bed technology is important for optimizing continuous processes and improving product quality. This study investigates particle discharge, specifically the mass outflow rate, from a pilot-scale fluidized bed by means of experimental methods and mathematical modeling. The modeling uses various algebraic equations to predict the mass outflow rate and the time evolution of bed mass. Experiments in which these quantities were measured were conducted under different conditions, including varying mass inflow rates and process modes such as continuous and semi-batch. The results indicate that the mass outflow rate can be effectively modeled using existing equations from the literature, as well as a newly introduced equation, providing a comprehensive understanding of the holdup and discharge behavior of the fluidized bed. The newly introduced equation seems to perform better under transient conditions, being most appropriate for automatic control. Full article

Recent research has explored combining large language models (LLMs) with speech recognition for various services, but such applications require a strong network environment for quality service delivery. For on-device services, which do not rely on networks, resource limitations must be considered. This study proposes HYLR-FO, an efficient model that integrates a smaller language model (LM) and a rule-based system (RBS) to enable fast and reliable voice-based order processing in resource-constrained environments, approximating the performance of LLMs. By considering potential error scenarios and leveraging flexible natural language processing (NLP) and inference validation, this approach ensures both efficiency and robustness in order execution. Smaller LMs are used instead of LLMs to reduce resource usage. The LM transforms speech input, received via automatic speech recognition (ASR), into a consistent form that can be processed by the RBS. The RBS then extracts the order and validates the extracted information. The experimental results show that HYLR-FO, trained and tested on 5000 order data samples, achieves up to 86% accuracy, comparable to the 90% accuracy of LLMs. Additionally, HYLR-FO achieves a processing speed of up to 55 orders per second, significantly outperforming LLM-based approaches, which handle only 1.14 orders per second. This results in a 48.25-fold improvement in processing speed in resource-constrained environments. This study demonstrates that HYLR-FO provides faster processing and achieves accuracy similar to LLMs in resource-constrained on-device environments. This finding has theoretical implications for optimizing LM efficiency in constrained settings and practical implications for real-time low-resource AI applications. Specifically, the design of HYLR-FO suggests its potential for efficient deployment in various commercial environments, achieving fast response times and low resource consumption with smaller models. Full article