Scale Features Research Articles

Cost-Effective Multispectral Sensor and Artificial Neural Networks for the Detection of Starch Adulteration in Raw Milk

This study aims to detect starch adulteration in dairy products utilizing an artificial neural network (ANN) model. Globally, milk fraud represents a significant challenge to food safety, posing substantial health risks to consumers. In this context, spectral data derived from milk samples with varying starch concentrations were processed using feature scaling and normalization techniques. The ANN model was rigorously trained and validated employing the stratified k-fold cross-validation method, demonstrating exceptional proficiency in detecting starch-adulterated milk samples and effectively differentiating among various starch concentrations. The principal findings indicate that the model achieved 100% accuracy, coupled with high levels of precision, sensitivity, and F1-scores. Future research should explore the application of this model to different types of adulteration and extend its validation on larger datasets. Furthermore, the potential adaptability of this method for other food products and field applications warrants investigation. This study offers valuable insights for milk producers, food safety professionals, and consumers, particularly highlighting the implications for small-scale rural farms, thereby enriching the discourse on food safety within short food supply chains.

PAFPT: Progressive aggregator with feature prompted transformer for underwater image enhancement

The optical characteristics of underwater environments often result in distorted underwater images, which makes it difficult to meet the needs of complex underwater environment perception. The demand for obtaining high-quality underwater images presents challenges for existing underwater image enhancement methods. In this paper, a progressive aggregator with feature prompted transformer for underwater image enhancement is presented. First, a feature prompted transformer module consisting of a feature convolutional transposed attention and a prompted feedforward neural network is proposed. It integrates feature attention mechanisms and adjusts input features through prompt weights to better focus on global information while enhancing local details, enriching texture, removing blurring, and correcting color deviation. Concurrently, a progressive aggregator consisting of four stages of up-sampling aggregation blocks is constructed to transfer features effectively and facilitate the aggregation of features of different scales at different stages to realize comprehensive attention to image details and semantic information. Besides, a region reconstruction unit is designed, and a reconstruction attention mechanism is introduced to pay attention to the bottleneck localized region to suppress noise. The performance of our method is thoroughly evaluated on public underwater image datasets: EUVP, UIEB, RUIE and SQUID. The quantitative and qualitative results indicate that our method outperforms nine state-of-the-art methods in both subjective perception and evaluation metrics, demonstrating excellent learning and generalization abilities. Additionally, the excellent results reflect the significant performance gains it brings to downstream visual applications.

Prediction of Stock Industry Sectors Listed on the Indonesia Stock Exchange (IDX) based on Financial Statements with the Random Forest Method

This research aims to predict the stock industry sector listed on the Indonesia Stock Exchange (BEI) based on financial reports using the Random Forest method. The dataset used in this research includes financial data from companies listed on the IDX in the period 2010 to 2022. The data processing process includes data cleaning, handling class imbalance with oversampling techniques using SMOTE, and feature scaling using StandardScaler. The Random Forest model is used to classify companies into appropriate industry sectors. The eval_uation results show that the model has good performance with an overall accuracy of 80.21%. Several classes showed very good performance, such as the Financials class with precision of 95.24%, recall of 100%, and F-1 score of 97.56%. However, there are also classes that show lower performance, such as the Healthcare class with a precision of 51.61% and an F-1 score of 61.54%. The confusion matrix indicates that the model is able to identify most classes accurately, although there are several classes with prediction errors.

Recent developments on multiscale simulations for rheology and complex flow of polymers

AbstractThis review summarized the multiscale simulation (MSS) methods for polymeric liquids. Since polymeric liquids have multiscale characteristics of monomeric, mesoscopic, and macroscopic flow scales, MSSs that relate different hierarchical levels are adequate to reproduce flow properties accurately. Our review includes pioneering studies to the most advanced MSS studies on rheology predictions and flow simulations of polymeric liquids. We discuss two major types of MSS methods: the bottom-up and model-embedded MSS methods. The former method mainly connects all-atom molecular dynamics models and mesoscopic models to predict rheological properties. In contrast, the latter method, where a microscopic or mesoscopic model is embedded in a macroscopic computational domain, is designed to predict macroscopic flow properties. Finally, we also discuss MSS methods using machine learning techniques. Graphical abstract

Revisiting the taxonomy of Korean Ischnochiton species (Polyplacophora, Ischnochitonidae) based on a combined analysis of morphological and molecular data

Chiton species belonging to the genus Ischnochiton J. E. Gray, 1847 are commonly found in intertidal rocky shores worldwide, with the exception of the northern Atlantic and Arctic oceans. Ischnochiton species are characterised by imbricate girdle scales that are uniform in size, rounded, sculpted with striae or occasionally smooth. However, their species-level taxonomy is complicated due to the high variation in their shell microstructures. Despite more than a hundred species reported worldwide, taxonomic studies of this group remain relatively unexplored in Korean waters, with only a few species recorded to date. In this study, we compared the microstructural characteristics of tegmentum sculpture, girdle scales and radula amongst four Korean Ischnochiton species using high-resolution microscopic images and a scanning electron microscope (SEM). Along with mtDNA cox1 sequence comparison, a comprehensive analysis of their morphology revealed that I. hayamii Owada, 2018 was identified for the first time in Korean waters. This species is morphologically distinguished by its small body size of adults, smooth lateral areas on valves and small perinotum scales sculptured with weak longitudinal ribs. Phylogenetic analysis of the mtDNA cox1 sequence provides distinct resolution at the species level, but interrelationships amongst Ischnochiton species remain unresolved. Results from the morphological and molecular analyses presented in this study offer valuable taxonomic information for accurate species identification amongst closely-related Ischnochiton species.

Prediction of in-hospital mortality risk for patients with acute ST-elevation myocardial infarction after primary PCI based on predictors selected by GRACE score and two feature selection methods

IntroductionAccurate in-hospital mortality prediction following percutaneous coronary intervention (PCI) is crucial for clinical decision-making. Machine Learning (ML) and Data Mining methods have shown promise in improving medical prognosis accuracy.MethodsWe analyzed a dataset of 4,677 patients from the Regional Vascular Center of Primorsky Regional Clinical Hospital No. 1 in Vladivostok, collected between 2015 and 2021. We utilized Extreme Gradient Boosting, Histogram Gradient Boosting, Light Gradient Boosting, and Stochastic Gradient Boosting for mortality risk prediction after primary PCI in patients with acute ST-elevation myocardial infarction. Model selection was performed using Monte Carlo Cross-validation. Feature selection was enhanced through Recursive Feature Elimination (RFE) and Shapley Additive Explanations (SHAP). We further developed hybrid models using Augmented Grey Wolf Optimizer (AGWO), Bald Eagle Search Optimization (BES), Golden Jackal Optimizer (GJO), and Puma Optimizer (PO), integrating features selected by these methods with the traditional GRACE score.ResultsThe hybrid models demonstrated superior prediction accuracy. In scenario (1), utilizing GRACE scale features, the Light Gradient Boosting Machine (LGBM) and Extreme Gradient Boosting (XGB) models optimized with BES achieved Recall values of 0.944 and 0.954, respectively. In scenarios (2) and (3), employing SHAP and RFE-selected features, the LGB models attained Recall values of 0.963 and 0.977, while the XGB models achieved 0.978 and 0.99.DiscussionThe study indicates that ML models, particularly the XGB optimized with BES, can outperform the conventional GRACE score in predicting in-hospital mortality. The hybrid models' enhanced accuracy presents a significant step forward in risk assessment for patients post-PCI, offering a potential alternative to existing clinical tools. These findings underscore the potential of ML in optimizing patient care and outcomes in cardiovascular medicine.

Remote Sensing LiDAR and Hyperspectral Classification with Multi-Scale Graph Encoder–Decoder Network

The rapid development of sensor technology has made multi-modal remote sensing data valuable for land cover classification due to its diverse and complementary information. Many feature extraction methods for multi-modal data, combining light detection and ranging (LiDAR) and hyperspectral imaging (HSI), have recognized the importance of incorporating multiple spatial scales. However, effectively capturing both long-range global correlations and short-range local features simultaneously on different scales remains a challenge, particularly in large-scale, complex ground scenes. To address this limitation, we propose a multi-scale graph encoder–decoder network (MGEN) for multi-modal data classification. The MGEN adopts a graph model that maintains global sample correlations to fuse multi-scale features, enabling simultaneous extraction of local and global information. The graph encoder maps multi-modal data from different scales to the graph space and completes feature extraction in the graph space. The graph decoder maps the features of multiple scales back to the original data space and completes multi-scale feature fusion and classification. Experimental results on three HSI-LiDAR datasets demonstrate that the proposed MGEN achieves considerable classification accuracies and outperforms state-of-the-art methods.

Unsupervised anomaly detection in shearers via autoencoder networks and multi-scale correlation matrix reconstruction

As the main equipment of coal mining production, the anomaly detection of shearer is important to ensure production efficiency and coal mine safety. One key challenge lies in the limited or even absence of labeled monitoring data for the equipment, coupled with the high costs associated with manual annotation. Another challenge stems from the complex structure of the mining machines, making it difficult to reflect the overall operational state through local anomaly detection. Consequently, the application of decoupled local anomaly detection for mining machines in practical production remains challenging. This paper presents an unsupervised learning-based method for detecting anomalies in shearer. The method includes a module for constructing a Multi-scale Correlation Matrix (MSCM) of mining machine operating conditions, as well as the CNN-ConvLSTM Autoencoder (C-CLA) network. The module for constructing an MSCM enhances the representation of interrelationships between various features of the equipment from different perspectives using multiple correlation analysis methods. The C-CLA network integrates convolutional and convolutional recurrent neural networks, with the convolutional structure extracting local spatial features and the ConvLSTM structure further capturing information from different time scales and feature scales, thereby enhancing the model’s perceptual capabilities towards changes in equipment status. Finally, shearer anomaly detection is achieved through the analysis of reconstructed residual matrices. The rationality and practicality of the proposed method have been validated on our dataset, and the model’s generalization capability has been verified through repeated experiments in similar scenarios. However, due to variations in the working environment of different mining faces and differences in equipment models, implementing detection on other mining faces often requires retraining the model with new data. Furthermore, we compared our method with other anomaly detection techniques, and our detection efficiency was superior by approximately 3%. This method effectively detects anomalies in the shearer.

Occluded vehicle tracking by integrating full-scale features and trajectory correction

In order to improve the tracking drift and identity switching (IDs) problems caused by occlusion in vehicle tracking, a method for tracking occluded vehicles that integrates full-scale features and trajectory correction is proposed based on the Deep SORT algorithm. Firstly, a full-scale feature extraction network is introduced to extract the features of different scales of the target and realize adaptive dynamic fusion to enhance the target appearance characteristics. Then, a trajectory correction algorithm is proposed to repair the tracking trajectory during occlusion, and the Kalman filter parameters are updated to reduce the accumulated linear error during occlusion and optimize the target motion characteristics. Finally, the occluded vehicle is tracked by combining appearance features and motion features. The feasibility of the proposed method is verified by ablation experiments and visualization analysis. The experimental results on the KITTI dataset show that compared with the existing typical methods, the proposed method achieves the highest comprehensive score of 78.13 and the lowest number of IDs of 192, which effectively improves the IDs problem in occluded vehicle tracking and improves the robustness of vehicle tracking.

Nanostructural Influence on Optical and Thermal Properties of Butterfly Wing Scales Across Forest Vertical Strata.

Butterfly wing scales feature complex nanostructures that influence wing coloration and various mechanical and optical properties. This configuration plays a key role in ecological interactions, flight conditions, and thermoregulation, facilitated by interactions with environmental electromagnetic energy. In tropical forests, butterflies occupy distinct vertical habitats, experiencing significant light and temperature variations. While wing nanostructures have been widely studied, their variation across different vertical flight preferences remains underexplored. This study investigates the wing nanostructures of 12 tropical butterfly species from the Nymphalidae family, focusing on their optical, morphological, and thermal properties across different forest strata. We analyzed the optical response through diffuse reflectance in the UV, Vis, and NIR ranges, correlating these findings with nanostructural configuration and thermal stability using thermogravimetric analysis (TGA). Our results reveal a significant correlation between flight stratification and wing optical responses, alongside distinct nanostructural features within each stratum. This study demonstrates the variability in butterfly wing nanostructures along the vertical stratification of the forest to cope with environmental conditions, raising new questions for future research on eco-evolutionary flight and thermal adaptations. Additionally, this underscores the importance of understanding how these structural adaptations influence butterfly interactions with their environment and their evolutionary success across different forest strata.

Understanding freshwater to marine transitional scale growth in Atlantic salmon (Salmo salar)

Abstract The first marine circulus is the scale feature associated with marine entry and has been used to support research evaluating the relationships between size, growth, and survival for Atlantic salmon. Ambiguity in growth rates and circulus deposition during the transition from freshwater to the marine environment leads to difficulty in the correct identification of the first marine circulus. In this study, scale growth occurring after the last freshwater annulus (plus-growth) was characterized for Atlantic salmon smolts migrating out of the Narraguagus River in Maine. Plus-growth was present in over 95% of scales from smolts leaving the river and represented on average 12.2% of total freshwater growth. These findings suggest plus-growth presents a significant source of error in growth analyses, if ignored, and the characterization of this scale feature helps to inform accurate identification of marine entry for future studies. Run day was a driver of plus-growth, suggesting extended freshwater residency provides opportunity for growth prior to smolt emigration. The negative association between fork length and plus-growth suggests smaller smolts that delay migration are demonstrating compensatory growth. Cumulative air temperature was positively associated with plus-growth, suggesting warming spring temperatures driven by climate change may influence size at marine entry for smolts.

PDC-YOLO: A Network for Pig Detection under Complex Conditions for Counting Purposes

Pigs play vital roles in the food supply, economic development, agricultural recycling, bioenergy, and social culture. Pork serves as a primary meat source and holds extensive applications in various dietary cultures, making pigs indispensable to human dietary structures. Manual pig counting, a crucial aspect of pig farming, suffers from high costs and time-consuming processes. In this paper, we propose the PDC-YOLO network to address these challenges, dedicated to detecting pigs in complex farming environments for counting purposes. Built upon YOLOv7, our model incorporates the SPD-Conv structure into the YOLOv7 backbone to enhance detection under varying lighting conditions and for small-scale pigs. Additionally, we replace the neck of YOLOv7 with AFPN to efficiently fuse features of different scales. Furthermore, the model utilizes rotated bounding boxes for improved accuracy. Achieving a mAP of 91.97%, precision of 95.11%, and recall of 89.94% on our collected pig dataset, our model outperforms others. Regarding technical performance, PDC-YOLO exhibits an error rate of 0.002 and surpasses manual counting significantly in speed.

Automatic Design and Monitoring of Mass Concrete Based on Information Technology

Mass concrete construction has the characteristics of large scale, complex technology, high professional requirements, and complex management. In this paper, information technology is introduced into the construction process of mass concrete, aiming to develop a system that integrates the automatic design and visual management of mass concrete construction monitoring schemes to improve its construction efficiency. In this paper, the automatic design of a mass concrete construction monitoring scheme is designed, the information of its data acquisition terminal sensor is extended, and the sensor information model is created based on the IFC framework. Finally, this paper verifies the feasibility and practicability of the automatic design and visual monitoring of the monitoring scheme through the actual case-commercial complex raft foundation. The results show that the method provides a digital and information platform for mass concrete construction, highlighting the advantages of the proposed method and the traditional method.

Multi-granularity negotiation correction method for satellite digital twin model

Affected by uncertainty, there are errors between the digital twin model and the real system, which need to be corrected and the uncertainty of the model quantitatively evaluated as the basis for selecting the model when using it. However, the satellite digital twin model has the characteristics of multi-dynamic, multi-spatial scale, and multi-physical field coupling. The rigidity problem of differential equations and the multi-scale problem of partial differential equations will appear during numerical solution. If many telemetry parameters are corrected at the system level at the same time, the results will not converge. A multi-granularity negotiation correction framework for satellite digital twin models is proposed. The parameters are grouped by analyzing the correlation and frequency domain characteristics of telemetry parameters. Models of different granularities of satellite subsystems and components are established, and multi-granularity digital twin models are constructed on demand. The coupling relationship between different levels of satellite components is studied, and a negotiation correction method is proposed. The framework is verified using real on-orbit telemetry data. The research results show that the negotiation correction method proposed in this paper improves the RMSE accuracy by more than that of the unused one , and the correction results are more systematic and complete.

Multi-scale context-aware and boundary-guided image manipulation detection method

Aiming at the problems of traditional image manipulation detection methods, such as fuzzy boundaries, single scale of extracted features, and ignoring background information, this paper proposes an image manipulation detection method based on multi-scale context-aware and boundary-guided. First, spatial details and base features of manipulated images are extracted using an improved pyramid vision transformer. Second, information related to the edge of the falsified region is explored by an edge contextaware module to generate an edge prediction map. Again, the edge guidance module is utilized to highlight the key channels in the extracted features and reduce the interference of redundant channels. Then, the rich contextual information of the manipulated region is learned from multiple sensory fields through the multi-scale context-aware module. Finally, the feature fusion module is utilized to accurately segment the manipulated region by focusing alternately on the foreground and background of the manipulated images. Comparing this paper's method quantitatively and qualitatively on five commonly used public image manipulation detection datasets, the experimental results show that this paper's method can effectively detect manipulated regions and outperforms other methods.

Remaining Useful Life Prediction Method Based on Dual-Path Interaction Network with Multiscale Feature Fusion and Dynamic Weight Adaptation

In fields such as manufacturing and aerospace, remaining useful life (RUL) prediction estimates the failure time of high-value assets like industrial equipment and aircraft engines by analyzing time series data collected from various sensors, enabling more effective predictive maintenance. However, significant temporal diversity and operational complexity during equipment operation make it difficult for traditional single-scale, single-dimensional feature extraction methods to effectively capture complex temporal dependencies and multi-dimensional feature interactions. To address this issue, we propose a Dual-Path Interaction Network, integrating the Multiscale Temporal-Feature Convolution Fusion Module (MTF-CFM) and the Dynamic Weight Adaptation Module (DWAM). This approach adaptively extracts information across different temporal and feature scales, enabling effective interaction of multi-dimensional information. Using the Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) dataset for comprehensive performance evaluation, our method achieved RMSE values of 0.0969, 0.1316, 0.086, and 0.1148; MAPE values of 9.72%, 14.51%, 8.04%, and 11.27%; and Score results of 59.93, 209.39, 67.56, and 215.35 across four different data categories. Furthermore, the MTF-CFM module demonstrated an average improvement of 7.12%, 10.62%, and 7.21% in RMSE, MAPE, and Score across multiple baseline models. These results validate the effectiveness and potential of the proposed model in improving the accuracy and robustness of RUL prediction.

Enhancing real-time urban drainage network modeling through Crossformer algorithm and online continual learning

This study presents an innovative approach to real-time modeling of urban drainage networks, leveraging a highly accurate coupled one- and two-dimensional hydrodynamic model to generate a training dataset for node water levels. By employing global states inferred from monitoring points as model inputs, this study overcomes the limitations imposed by the scarcity of monitoring data and the challenge of capturing all node levels. The Crossformer algorithm, which simultaneously accounts for correlation at both temporal and feature scales, is applied to enhance the precision of simultaneous water level predictions across the network. Comparative analysis of different prediction patterns reveals that extending predictions based on a high-accuracy infrastructure offers more benefits than direct modifications to the algorithm's structure. In addition, this paper pioneered the application of online continuous learning concepts to update the prediction model in real time, achieving a balanced integration of measured and simulated data. Consequently, this paper establishes a complete monitoring-predicting-updating real-time simulation system for urban drainage networks.

Medium- and Long-Term Distributed Photovoltaic Power Prediction Based on Multiple Time Series Feature and Multiple-Model Fusion

Distributed photovoltaic power stations have advantages such as local direct power supply and reduced transmission energy consumption, and whose demands are constantly being developed. Conducting research on medium- and long-term distributed photovoltaic prediction will have significant value for applications such as the electricity trade market, power grid operation, and the planning of new power stations. Due to characteristics such as long time dependence, disperse power stations, and strong randomness, making accurate and stable predictions becomes very difficult. In this research, we propose a multiple time series feature and multiple-model fusion-based ensemble learning model for medium- and long-term distributed photovoltaic power prediction (M2E-DPV). Considering the wave influence and the differences in distributions in different areas of photovoltaic power, multiple feature combinations are designed to increase feature expression ability and adaptability. Based on the boost ensemble learning model, trained on a single model of different time scale features, the optimal scoring strategy is used for multiple model fusion in the rolling prediction process, and finally, time-segmented probabilistic correction is performed. The experiment results show the effectiveness of the M2E-DPV under multiple feature combinations and multi-model fusion strategies. The average MAPE, R2, and ACC indicators are 0.15, 0.96, and 0.91, respectively. Compared with other methods, there is a significant improvement, indicating that the prediction ability of the model framework proposed in this paper is advanced and robust.

A machine learning classifier-based approach for diabetes mellitus risk prediction.

Currently, Diabetes Mellitus (DM) can be life-threatening due to the dietary habits and lifestyle choices of individuals. Diabetes is characterised by elevated levels of glucose in the blood and an excess of protein in the blood. Poor eating habits and lifestyles are largely responsible for the rise in overweight, obesity, and various related conditions. This study investigated many diabetes-related risk forecasting techniques and algorithms. The eight machine learning (ML) algorithms used the diabetes dataset to test various prediction techniques, including a Support Vector Classifier, gradient-boosting, multilayer perceptron, random forest, K-nearest neighbors, logistic regression, extreme gradient boosting, and decision tree. To enhance the diabetic prediction ability of the model, we suggested using Feature Engineering (FE) and feature scaling. For our investigation, we utilized the Mendeley dataset on diabetes to assess the capacity of the model to predict diabetes. We developed a model by using Python programming and eight classification techniques. The Random Forest with 99.21%, Gradient Boosting with 99.61%, Extreme Gradient Boosting, and Decision Tree achieved the highest F1 score (99.81%), accuracy rate (99.80%), precision (99.81%), and recall (99.81%) of all classification approaches.

The Identification of Network Intrusions with Generative Artificial Intelligence Approach for Cybersecurity

Generative Artificial Intelligence (Generative AI) offers a paradigm shift to the way robots perceive and interact with data. Generative AI approaches aim to produce new data samples that closely match the original dataset, in contrast to standard AI models that concentrate on tasks such as categorisation or prediction. This ability has broad implications for a variety of fields, including network security. New generation of network intrusion defense brought forth by Generative AI is revolution using the area of network security. In this work, investigates the revolutionary potential of Generative AI in network intrusion detection, with the goal of developing a proactive and adaptable cyber protection mechanism. In this work the use of Generative AI use for identifying network intrusions, using the NSL-KDD dataset. The work begins with meticulous data preprocessing using handling missing values, encoding, feature scaling, and feature extraction to enhance the dataset and then focuses on using Generative AI for intrusion detection. In this work many models have been used like SVM, AE, DAE, and GANs, and in this GANs has the best accuracy with 91.12% compared with other models.