Search Results (121)

Accurate detection of Jinxiu Malus fruits in unstructured orchard environments is hampered by frequent overlap, occlusion, and variable illumination. To address these challenges, we propose YOLOv8-MSP-PD (YOLOv8 with Multi-Scale Pyramid Fusion and Proportional Distance IoU), a lightweight model built on an enhanced YOLOv8 architecture. We replace the backbone with MobileNetV4, incorporating unified inverted bottleneck (UIB) modules and depth-wise separable convolutions for efficient feature extraction. We introduce a spatial pyramid pooling fast cross-stage partial connections (SPPFCSPC) module for multi-scale feature fusion and a modified proportional distance IoU (MPD-IoU) loss to optimize bounding-box regression. Finally, layer-adaptive magnitude pruning (LAMP) combined with knowledge distillation compresses the model while retaining performance. On our custom Jinxiu Malus dataset, YOLOv8-MSP-PD achieves a mean average precision (mAP) of 92.2% (1.6% gain over baseline), reduces floating-point operations (FLOPs) by 59.9%, and shrinks to 2.2 MB. Five-fold cross-validation confirms stability, and comparisons with Faster R-CNN and SSD demonstrate superior accuracy and efficiency. This work offers a practical vision solution for agricultural robots and guidance for lightweight detection in precision agriculture. Full article

The anatomical arrangement of the atrioventricular node has been likened to a riddle wrapped up in an enigma. There are several reasons for this alleged mystery, not least the marked variability in structure between different species. Lack of detailed knowledge of the location of the node relative to the atrial and ventricular septal structures has also contributed to previous misunderstandings. Recent studies comparing the findings of gross dissection with virtual dissection of living datasets, combined with access to a large number of serially sectioned human and animal hearts, have served to provide the evidence to solve the riddle. We summarise these findings in this review. We explain how the node is located within the atrial walls of the inferior pyramidal space. It becomes the non-branching component of the atrioventricular conduction axis as the axis extends through the plane of atrioventricular insulation to enter the infero-septal recess of the left ventricular outflow tract. The node itself is formed by contributions from the tricuspid and mitral vestibules, with extensive additional inputs from the base of the atrial septum. We show how knowledge of development enhances the appreciation of the arrangements and offers an explanation as to why, on occasion, there can be persisting nodoventricular connections. We discuss the findings relative to the circuits producing atrioventricular re-entry tachycardia. We conclude by emphasising the significance of the variation of the anatomical arrangements within different mammalian species. Full article

The integrity and stability of railway fasteners are of vital importance to railway safety. To address the challenges of limited anomaly samples, irregular defect geometries, and complex operational conditions in rail fastener anomaly detection, this paper proposes an unsupervised anomaly detection method using a knowledge-distilled generative adversarial network. First, the proposed method employs collaborative teacher–student learning to model normal sample distributions, where the student network reconstructs input images as normal outputs while a discriminator identifies anomalies by comparing input and reconstructed images. Second, a multi-scale attention-coupling feature-enhancement mechanism is proposed, effectively integrating hierarchical semantic information with spatial-channel attention to achieve both precise target localization and robust background suppression in the teacher network. Third, an enhanced anomaly discriminator is designed to incorporate an enhanced pyramid upsampling module, through which fine-grained details are preserved via multi-level feature map aggregation, resulting in significantly improved sensitivity for small-sized anomaly detection. Finally, the proposed method achieved an AUC of 94.0%, an ACC of 92.5%, and an F1 score of 91.6% on the MNIST dataset, and an AUC of 94.7%, an ACC of 90.1%, and an F1 score of 87.8% on the railway fastener dataset, which proves the superior anomaly detection ability of this method. Full article

The global population is experiencing a remarkable demographic shift. The population pyramid of African countries looks very different from that of the West, with a youthful population forming the base of the African population, while the population of Western countries has a larger share of an aging population. A broader understanding of the various facets of urban growth in Africa is needed, including the demographic makeup and drivers of growth. However, inadequate attention has been paid to this aspect of urban change in research, even though this knowledge can aid development planning. Demographic concerns like the interconnections between development and population are important issues of national dialogues and debates. Research from Southern Africa has also found a prevalence of female-headed households in urban areas and predicts a rise in this trend. This study thus set out to explore the primary factor behind urban population growth and the extent of prevalence of female-headed households in African cities using Port Harcourt, Nigeria, as a case study. Quantitative research was conducted. The findings revealed that natural increase was largely responsible for urban growth, given the proportion of participants in the age group 18–40 born in the city. This group currently forms the large base of the African urban population. Results also showed that male-headed households were still dominant in Port Harcourt city. This study highlights the need for expansion of similar research in other cities to enable a more holistic understanding of the wider African urban population demographics and dynamics. Full article

In this study, the ordered flow shop scheduling problem, which is in the class of NP-hard optimization problems, is considered. This problem is used especially to increase the efficiency and prevent delays in the production process. The problem was first identified in the literature during the 1970s. The main objective of this study is to develop an efficient and fast method to overcome the complexity of this problem. For this purpose, the ordered flow shop scheduling problem is explained in detail and a robust meta-heuristic method is proposed. First of all, a genetic algorithm is developed by considering Smith’s convexity criterion. While performing operations such as crossover and mutation in the genetic algorithm, the pyramid structure is integrated to ensure that the solution has certain symmetry. The developed method is compared with other methods, such as the Nawaz–Enscore–Ham (NEH), pair insert, and iterated local search (ILS) methods. In order to increase the reliability of the results, the Pyramid Structure Adapted Tabu Search (PSA-TS) algorithm is also developed. The results are validated by statistical analysis using the Wilcoxon signed-rank test and Friedman test. The proposed genetic algorithm outperforms the methods with which it is compared. To the best of the authors’ knowledge, there is no other method in the literature that preserves the pyramid structure in the ordered flow shop scheduling problem. Therefore, this study is expected to make a significant contribution to the literature in this respect. Full article

The strength and conditioning literature examining neuromuscular physiology, bioenergetics, neuroendocrine factors, nutrition and metabolic factors, and the use of ergogenic aids, as well as physical and physiological responses and adaptations, have clearly identified the benefits of participating in regular resistance training programs for athletic populations, especially as it relates to improving muscular strength. Beyond evidence-based research, models for resistance training program implementation are of considerable value for optimizing athletic performance. In fact, several have been provided that address general to specific characteristics of athleticism (i.e., strength endurance, muscular strength, and muscular power) through resistance training over the decades. For instance, a published model known as the strength–endurance continuum that enhances dynamic correspondence (i.e., training specificity) in athletic populations by developing structural, metabolic, and neural capacities across a high-load, low-repetition and low-load, high-repetition range. Further models have been developed to enhance performance approaches (i.e., optimum performance training model) and outcomes (i.e., performance pyramid), even within specific populations, such as youth (i.e., youth physical development model). The ten, five, three, or 10-5-3 (TFT) model for strength and conditioning professionals synthesizes currently available information and provides a framework for the effective implementation of resistance training approaches to suit the needs of athletes at each stage of development. The model includes three key components to consider when designing strength and conditioning programs, denoted by the acronym TFT (ten, five, three). Over recent years, the model has gained much support from teams, coaches, and athletes, mainly due to the ability to streamline common knowledge within the field into an efficient and effective resistance training system. Furthermore, this model is distinctly unique from others as it prioritizes the development of strength–endurance, muscular strength, and muscular power concurrently. This paper explains the model itself and begins to provide recommendations for those interested in implementing TFT-based approaches, including a summary of points as a brief take-home guide to implementing TFT interventions. It is the author’s hope that this paper encourages other performance professionals to share their models to appreciate human ingenuity and advance our understanding of individualized approaches and systems towards the physical development of the modern-day athlete. Full article

Background: Adherence to nutritional recommendations in groups of adolescents practicing various sports, including esthetic disciplines, is insufficient. Hence, the authors of this study attempted to design, implement and evaluate a nutritional education program for girls aged 10–12 attending a ballet school and artistic gymnastics classes. Methods: The study was conducted with 60 female students at the state ballet school and artistic gymnastics classes (professionally practicing ballet and artistic gymnastics). The nutritional education program was implemented by all students for a period of 4 weeks. The program consisted of three parts: group sharing and discussing the educational brochure, group nutritional workshops, and providing and discussing individual nutritional recommendations. Information provided to students during the nutritional education program concerned the principles of proper nutrition contained in the Pyramid of Healthy Nutrition and Physical Activity for Children and Youth, the most important sources of nutrients in the diet and their role, and the principles of nutrition of people practicing sports/training. Before starting the nutritional education program and 3 months after its completion, the level of nutritional knowledge was assessed in the group of ballerinas and artistic gymnasts to evaluate the program. Results: The proposed nutritional education program had a significant impact on the level of nutritional knowledge of students aged 10–12 attending the ballet school and artistic gymnastics classes. Conclusions: The presented nutritional education program may be used as a source of information for specialists for the preparation of educational and repair programs in the group of ballet dancers or artistic gymnasts aged 10–12. Full article

Accurate walnut yield prediction is crucial for the development of the walnut industry. Traditional manual counting methods are limited by labor and time costs, leading to inaccurate walnut quantity assessments. In this paper, we propose a walnut detection method based on UAV (UAV means Unmanned Aerial Vehicle) remote sensing imagery to improve the walnut yield prediction accuracy. Based on the YOLOv11 network, we propose several improvements to enhance the multi-scale object detection capability while achieving a more lightweight model structure. Specifically, we reconstruct the feature fusion network with a hierarchical scale-based feature pyramid structure and implement lightweight improvements to the feature extraction component. These modifications result in the RSWD-YOLO network (RSWD means remote sensing walnut detection; YOLO means ‘You Only Look Once’, and it is the specific abbreviation used for a series of object detection algorithms), which is specifically designed for walnut detection. Furthermore, to optimize the detection performance under hardware resource constraints, we apply knowledge distillation to RSWD-YOLO, thereby further improving the detection accuracy. Through model deployment and testing on small edge devices, we demonstrate the feasibility of our proposed method. The detection algorithm achieves 86.1% mean Average Precision on the walnut dataset while maintaining operational functionality on small edge devices. The experimental results demonstrate that our proposed UAV remote sensing-based walnut detection method has a significant practical application value and can provide valuable insights for future research in related fields. Full article

While existing tongue detection methods have achieved good accuracy, the problems of low detection speed and excessive noise in the background area still exist. To address these problems, a fast tongue detection model based on a lightweight model and deep feature propagation (TD-DFP) is proposed. Firstly, a color channel is added to the RGB tongue image to introduce more prominent tongue features. To reduce the computational complexity, keyframes are selected through inter frame differencing, while optical flow maps are used to achieve feature alignment between non-keyframes and keyframes. Secondly, a convolutional neural network with feature pyramid structures is designed to extract multi-scale features, and object detection heads based on depth-wise convolutions are adopted to achieve real-time tongue region detection. In addition, a knowledge distillation module is introduced to improve training performance during the training phase. TD-DFP achieved 82.8% mean average precision (mAP) values and 61.88 frames per second (FPS) values on the tongue dataset. The experimental results indicate that TD-DFP can achieve efficient and accurate tongue detection, achieving real-time tongue detection. Full article

Car styling is crucial for consumer acceptance and market success. Since vehicle manufacturers produce electric vehicles, they have faced the challenge of maintaining the typicality of their original products and presenting the innovation of new technologies. We propose a method that integrates artificial intelligence (AI)-generated images and image classification technology to help designers effectively balance between typicality and novelty. We collected 118 pictures of electric vehicles and 122 pictures of fuel vehicles in 2024 from the BMW official website. Focusing on seven key visual features of the vehicles, we used the Waikato environment for knowledge analysis (WEKA) to train an image classification model on the dataset through three separate training and testing sessions. First, we used the prompts that described typical BMW design to generate images of new BMW electric vehicles in Stable Diffusion. The images consisted of 21 front views, 20 side views, and 20 rear views. The accuracy of the model of front views trained with the pyramid histogram of oriented gradients filter (PHOG)-Filter and random forest classifier was 78.5%, and the test accuracy reached 95%. The accuracy of the model of rear views trained with BinaryPatternsPyramid-Filter and random forest classifier was 80.5%, and the test accuracy was 90%. However, the accuracy of the model of side views did not reach 70%. That implies the distinction between BMW fuel vehicles and its electric vehicles is mainly based on the front and rear views, rather than the side view. The results of this study showed that integrating image classification and AI-generated images can be used to examine the balance between product typicality and novelty, and the application of machine learning and AI tools to study car style. Full article

Product semantics is essential for car styling because it shapes how consumers perceive and interact with cars, influences user experiences, and allows for product differentiation. Although many AI tools are available to assist car designers, research on applying machine learning techniques to evaluate product semantics is rare. Therefore, we developed a classification model that helps designers identify and evaluate the semantics conveyed by car styling using the Waikato Environment for Knowledge Analysis (WEKA), a machine learning tool. We used Python web scraping to collect isometric drawings and introductory articles of 1320 SUV cars of various brands from 2009 to 2024 via websites such as Car Body Design and Car Design News. We also summarized four semantic types of car styling, namely “aggressive”, “sporty”, “clean”, and “off-road”, to create the dataset. We used WEKA image classification to randomly select 792 (60%) images from the dataset to train a classification model of car styling semantics. The remaining 528 images (40%) were used for verification. The classification model trained with the Binary Pattern Pyramid Filter and the Random Forest classifier achieved an accuracy of 84.6%. The model was evaluated in terms of whether 10 SUVs created by 10 graduate design students using AI conveyed the anticipated product semantics. Seven of the ten SUVs were correctly classified and the rest were not. All of the participants agreed that the predictions were satisfactory. However, it is necessary to improve the accuracy of each semantic classification, especially the “clean” type. The results of this study demonstrate the capability of machine learning to identify the semantics of car styling effectively, improve the communication and evaluation of product semantics by designers in the design process, and create a car styling with a good appearance that resonates with consumers. Full article

Unmanned Aerial Vehicles (UAVs) play an extremely important role in real-time object detection for maritime emergency rescue missions. However, marine accidents often occur in low-visibility weather conditions, resulting in poor image quality and a lack of object detection samples, which significantly reduces detection accuracy. To tackle these issues, we propose GD-Det, a low-data object detection model with high accuracy, specifically designed to handle limited sample sizes and low-quality images. The model is primarily composed of three components: (i) A lightweight re-parameterization feature extraction module which integrates RepVGG blocks into multi-concat blocks to enhance the model’s spatial perception and feature diversity during training. Meanwhile, it reduces computational cost in the inference phase through the re-parameterization mechanism. (ii) A cross-scale gather-and-distribute pyramid module, which helps to augment the relationship representation of four-scale features via flexible skip fusion and distribution strategies. (iii) A decoupled prediction module with three branches is to implement classification and regression, enhancing detection accuracy by combining the prediction values from tri-level features. (iv) We also use a domain-adaptive training strategy with knowledge transfer to handle low-data issues. We conducted low-data training and comparison experiments using our constructed dataset AFO-fog. Our model achieved an overall detection accuracy of 84.8%, which is superior to other models. Full article

The enumeration of spanning trees in various graph forms has been made easier by the study of electrically equivalent transformations, which was motivated by Kirchhoff’s work on electrical networks. In this work, using knowledge of difference equations, the electrically equivalent transformations and rules of weighted generating function are used to calculate the explicit formulas of the number of spanning trees of novel pyramid graph types based on some nonahedral graphs. Lastly, we compare our graphs’ entropy with that of other average-degree graphs that have been researched. Full article

As part of crystal growth experiments on transition metal oxidotellurates using chemical vapor transport reactions or hydrothermal conditions, single crystals of Ni^IITe^VIO₄ and Cu^IITe^IV₂O₅ were obtained for the first time in the form of new modifications, as revealed by crystal structure determinations from X-ray data. In the course of these investigations, the crystal structure model of the only phase of Ni^IITe^VIO₄ reported so far (from now on named α-) was corrected. Both α-(space group P2₁/c, Z = 2) and the new β-polymorph of Ni^IITe^VIO₄ (space group I4₁/a, Z = 8) can be considered derivatives (hettotypes) of the rutile structure (aristotype), as shown by detailed symmetry relationships. For CuTe₂O₅ also, only one crystalline phase has been described so far (from now on named α-) that corresponds to the mineral rajite (space group P2₁/c, Z = 2). Its anion comprises two different trigonal-pyramidal TeO₃ groups linked through corner-sharing into a ditellurite unit. The anion part of the new β-CuTe₂O₅ modification (space group P2₁/c, Z = 2), likewise, comprises two Te^IV atoms but is more complex. Here, one Te^IV atom exhibits a coordination number of 4 and is part of a ${}_{\propto }{}^1[$TeO_2/2O_2/1] chain, and the other has a coordination number of 5 and is part of a ${}_{\propto }{}^1[$TeO_2/2O_3/1]₂ dimer. The two types of anions are linked into a tri-periodic framework where both Te^IV atoms are stereochemically active. The α- and β-CuTe₂O₅ modifications show no closer structural relationship, which is also reflected in their clearly different Raman spectra. Data mining for knowledge discovery in a structure database reveals that polymorphism is a rather common phenomenon for the family of inorganic oxidotellurates. Full article

Background/Objectives: Patient navigation is vital for improving healthcare accessibility and patient experience in China’s public hospitals, where high patient demand meets limited medical resources. Patient navigators (PNs) assist patients through the complex healthcare system, but the lack of standardized training and evaluation hampers their ability to meet patient needs. This study piloted a Competencies Improvement Training Program (CITP) in a tertiary hospital to clarify PN competencies, design a feasible curriculum, assess its efficacy, and share insights with peer hospitals. Methods: The CITP used the Plan–Do–Check–Act (PDCA) framework and designed a curriculum with Miller’s Pyramid Model. Over 6 months, eight sessions were conducted, including theory, case studies, etc. The quasi-experimental design compared PN competencies and patient satisfaction before and after. Multiple instruments measured baseline competencies and program efficacy with a 6-month post-training follow-up. Results: A total of 75 PNs (75%) participated and completed all sessions. A total of 1189 patients were surveyed before training, 495 in the first month after training, and 502 in the 6-month follow-up. The CITP significantly boosted PN competency scores from 90.259 to 95.453, though it dipped to 92.721 by 6 months. Patient satisfaction with PN services improved modestly over 6 months. Challenges in applying theoretical knowledge to practical skills were noted, suggesting differentiated training based on navigator demographics. Patient satisfaction for aspects like politeness and tone was linked to patient age and education. Conclusions: The CITP enhanced PN core competencies and provided an evidence-based curriculum model. Future research should involve larger multi-center populations with longer-term follow-ups to validate the program’s effectiveness across diverse settings. Full article