Search Results (2,227)

Utilizing deep learning for semantic segmentation of cropland from remote sensing imagery has become a crucial technique in land surveys. Cropland is highly heterogeneous and fragmented, and existing methods often suffer from inaccurate boundary segmentation. This paper introduces a UNet-like boundary-aware compensation model (BAFormer). Cropland boundaries typically exhibit rapid transformations in pixel values and texture features, often appearing as high-frequency features in remote sensing images. To enhance the recognition of these high-frequency features as represented by cropland boundaries, the proposed BAFormer integrates a Feature Adaptive Mixer (FAM) and develops a Depthwise Large Kernel Multi-Layer Perceptron model (DWLK-MLP) to enrich the global and local cropland boundaries features separately. Specifically, FAM enhances the boundary-aware method by adaptively acquiring high-frequency features through convolution and self-attention advantages, while DWLK-MLP further supplements boundary position information using a large receptive field. The efficacy of BAFormer has been evaluated on datasets including Vaihingen, Potsdam, LoveDA, and Mapcup. It demonstrates high performance, achieving mIoU scores of 84.5%, 87.3%, 53.5%, and 83.1% on these datasets, respectively. Notably, BAFormer-T (lightweight model) surpasses other lightweight models on the Vaihingen dataset with scores of 91.3% F1 and 84.1% mIoU. Full article

High-quality printing is a longstanding objective in the printing and replication industry. However, the methods used to evaluate print quality suffer from subjectivity and multidimensionality, relying on personal preferences and subjective perceptions to assess the quality of printed images, which poses significant limitations. To address these issues, a set of evaluation metrics aimed at assessing the quality of digital printing products is proposed to achieve evaluation results consistent with human visual perception. Given the differing imaging principles of pre-press digital images and post-scan images, these images are first preprocessed to standardize them for comparison. Next, features are extracted in both spatial and frequency domains, and similarity metrics are used to quantify the differences in features between pre-press digital images and post-scan images. Finally, a multilayer perceptron (MLP) neural network regression model is trained to predict the final objective quality scores. Experimental results on two standard databases demonstrate that this metric exhibits high consistency in both subjective and objective quality evaluation metrics for printed image quality assessment and outperforms other metrics in terms of accuracy. Full article

In this study, we refine in vitro propagation techniques for Camellia sinensis using a machine learning approach to ascertain the influence of different shooting and rooting conditions on key growth metrics. This was achieved by applying random forest (RF), XGBoost, and multilayer perceptron (MLP) models to dissect the complexities of micropropagation and rooting processes. The research unveiled significant disparities in growth metrics under varying media conditions, underscoring the profound impact of media composition on plant development. The meticulous statistical analysis, employing ANOVA, highlighted statistically significant differences in growth metrics, indicating the critical role of media composition in optimizing growth conditions. Methodologically, the study utilized explants from 2–3-year-old tea plants, which underwent sterilization before being introduced to two distinct culture media for their micropropagation and rooting phases. Statistical analyses were conducted to evaluate the differences in growth outcomes between media, while machine learning models were employed to predict the efficacy of micropropagation and rooting based on various growth regulators. This approach allowed for a comprehensive evaluation of the model’s performance in simulating plant growth under different conditions, leveraging metrics like R², RMSE, and MAE. The findings from this study significantly advance the understanding of tea plant micropropagation, highlighting the utility of machine learning models in agricultural optimization. This research contributes to enhancing micropropagation strategies for the tea plant and exemplifies the transformative potential of integrating machine learning into plant science, paving the way for improved agricultural and horticultural practices. This interdisciplinary approach offers a novel perspective on optimizing in vitro propagation processes, contributing substantially to plant tissue culture and biotechnology. Full article

Infrared thermography has been investigated in recent studies to monitor body surface temperature and correlate it with animal welfare and performance factors. In this context, this study proposes the use of the thermal signature method as a feature extractor from the temperature matrix obtained from regions of the body surface of laying hens (face, eye, wattle, comb, leg, and foot) to enable the construction of a computational model for heat stress level classification. In an experiment conducted in climate-controlled chambers, 192 laying hens, 34 weeks old, from two different strains (Dekalb White and Dekalb Brown) were divided into groups and housed under conditions of heat stress (35 °C and 60% humidity) and thermal comfort (26 °C and 60% humidity). Weekly, individual thermal images of the hens were collected using a thermographic camera, along with their respective rectal temperatures. Surface temperatures of the six featherless image areas of the hens’ bodies were cut out. Rectal temperature was used to label each infrared thermography data as “Danger” or “Normal”, and five different classifier models (Random Forest, Random Tree, Multilayer Perceptron, K-Nearest Neighbors, and Logistic Regression) for rectal temperature class were generated using the respective thermal signatures. No differences between the strains were observed in the thermal signature of surface temperature and rectal temperature. It was evidenced that the rectal temperature and the thermal signature express heat stress and comfort conditions. The Random Forest model for the face area of the laying hen achieved the highest performance (89.0%). For the wattle area, a Random Forest model also demonstrated high performance (88.3%), indicating the significance of this area in strains where it is more developed. These findings validate the method of extracting characteristics from infrared thermography. When combined with machine learning, this method has proven promising for generating classifier models of thermal stress levels in laying hen production environments. Full article

In recent years, smart windows have attracted widespread attention due to their ability to respond to external stimuli such as light, heat, and electricity, thereby intelligently adjusting the ultraviolet, visible, and near-infrared light in solar radiation. VO₂(M) undergoes a reversible phase transition from an insulating phase (monoclinic, M) to a metallic phase (rutile, R) at a critical temperature of 68 °C, resulting in a significant difference in near-infrared transmittance, which is particularly suitable for use in energy-saving smart windows. However, due to the multiple valence states of vanadium ions and the multiphase characteristics of VO₂, there are still challenges in preparing pure-phase VO₂(M). Machine learning (ML) can learn and generate models capable of predicting unknown data from vast datasets, thereby avoiding the wastage of experimental resources and reducing time costs associated with material preparation optimization. Hence, in this paper, four ML algorithms, namely multi-layer perceptron (MLP), random forest (RF), support vector machine (SVM), and extreme gradient boosting (XGB), were employed to explore the parameters for the successful preparation of VO₂(M) films via magnetron sputtering. A comprehensive performance evaluation was conducted on these four models. The results indicated that XGB was the top-performing model, achieving a prediction accuracy of up to 88.52%. A feature importance analysis using the SHAP method revealed that substrate temperature had an essential impact on the preparation of VO₂(M). Furthermore, characteristic parameters such as sputtering power, substrate temperature, and substrate type were optimized to obtain pure-phase VO₂(M) films. Finally, it was experimentally verified that VO₂(M) films can be successfully prepared using optimized parameters. These findings suggest that ML-assisted material preparation is highly feasible, substantially reducing resource wastage resulting from experimental trial and error, thereby promoting research on material preparation optimization. Full article

Putting sensors on the bodies of animals to automate animal activity recognition and gain insight into their behaviors can help improve their living conditions. Although previous hard-coded algorithms failed to classify complex time series obtained from accelerometer data, recent advances in deep learning have improved the task of animal activity recognition for the better. However, a comparative analysis of the generalizing capabilities of various models in combination with different input types has yet to be addressed. This study experimented with two techniques for transforming the segmented accelerometer data to make them more orientation-independent. The methods included calculating the magnitude of the three-axis accelerometer vector and calculating the Discrete Fourier Transform for both sets of three-axis data as the vector magnitude. Three different deep learning models were trained on this data: a Multilayer Perceptron, a Convolutional Neural Network, and an ensemble merging both called a hybrid Convolutional Neural Network. Besides mixed cross-validation, every model and input type combination was assessed on a goat-wise leave-one-out cross-validation set to evaluate its generalizing capability. Using orientation-independent data transformations gave promising results. A hybrid Convolutional Neural Network with $L^2$-norm as the input combined the higher classification accuracy of a Convolutional Neural Network with the lower standard deviation of a Multilayer Perceptron. Most of the misclassifications occurred for behaviors that display similar accelerometer traces and minority classes, which could be improved in future work by assembling larger and more balanced datasets. Full article

Groundwater contamination source recognition is an important prerequisite for subsequent remediation efforts. To overcome the limitations of single inversion methods, this study proposed a two-stage inversion framework by integrating two primary inversion approaches—simulation-optimization and simulation-data assimilation—thereby enhancing inversion accuracy. In the first stage, the ensemble smoother with multiple data assimilation method (a type of simulation-data assimilation) conducted a global broad search to provide better initial values and ranges for the second stage. In the subsequent stage, a collective decision optimization algorithm (a type of simulation-optimization) was used for a refined deep search, further enhancing the final inversion accuracy. Additionally, a deep learning method, the multilayer perceptron, was utilized to establish a surrogate of the simulation model, reducing computational costs. These theories and methods were applied and validated in a hypothetical scenario for the synchronous identification of the contamination source and boundary conditions. The results demonstrated that the proposed two-stage inversion framework significantly improved search accuracy compared to single inversion methods, with a mean relative error and mean absolute error of just 4.95% and 0.1756, respectively. Moreover, the multilayer perceptron surrogate model offered greater approximation accuracy to the simulation model than the traditional shallow learning surrogate model. Specifically, the coefficient of determination, mean relative error, mean absolute error, and root mean square error were 0.9860, 9.72%, 0.1727, and 0.47, respectively, highlighting its significant advantages. The findings of this study can provide more reliable technical support for practical case applications and improve subsequent remediation efficiency. Full article

The objective and automatic detection of the sleep–wake cycle (SWC) stages is essential for the investigation of its physiology and dysfunction. Here, we propose a machine learning model for the classification of SWC stages based on the measurement of synchronization between neural oscillations of different frequencies. Publicly available electrophysiological recordings of mice were analyzed for the computation of phase–amplitude couplings, which were then supplied to a multilayer perceptron (MLP). Firstly, we assessed the performance of several architectures, varying among different input choices and numbers of neurons in the hidden layer. The top performing architecture was then tested using distinct extrapolation strategies that would simulate applications in a real lab setting. Although all the different choices of input data displayed high AUC values (>0.85) for all the stages, the ones using larger input datasets performed significantly better. The top performing architecture displayed high AUC values (>0.95) for all the extrapolation strategies, even in the worst-case scenario in which the training with a single day and single animal was used to classify the rest of the data. Overall, the results using multiple performance metrics indicate that the usage of a basic MLP fed with highly descriptive features such as neural synchronization is enough to efficiently classify SWC stages. Full article

Wetland mapping is a critical component of environmental monitoring, requiring advanced techniques to accurately represent the complex land cover patterns and subtle class differences innate in these ecosystems. This study aims to address these challenges by proposing CVTNet, a novel deep learning (DL) model that integrates convolutional neural networks (CNNs) and vision transformer (ViT) architectures. CVTNet uses channel attention (CA) and spatial attention (SA) mechanisms to enhance feature extraction from Sentinel-1 (S1) and Sentinel-2 (S2) satellite data. The primary goal of this model is to achieve a balanced trade-off between Precision and Recall, which is essential for accurate wetland mapping. The class-specific analysis demonstrated CVTNet’s proficiency across diverse classes, including pasture, shrubland, urban, bog, fen, and water. Comparative analysis showed that CVTNet outperforms contemporary algorithms such as Random Forest (RF), ViT, multi-layer perceptron mixer (MLP-mixer), and hybrid spectral net (HybridSN) classifiers. Additionally, the attention mechanism (AM) analysis and sensitivity analysis highlighted the crucial role of CA, SA, and ViT in focusing the model’s attention on critical regions, thereby improving the mapping of wetland regions. Despite challenges at class boundaries, particularly between bog and fen, and misclassifications of swamp pixels, CVTNet presents a solution for wetland mapping. Full article

Ice formation on aircraft surfaces poses significant safety risks, and current detection systems often struggle to provide accurate, real-time predictions. This paper presents the development and comprehensive evaluation of a smart ice control system using a suite of machine learning models. The system utilizes various sensors to detect temperature anomalies and signal potential ice formation. We trained and tested supervised learning models (Logistic Regression, Support Vector Machine, and Random Forest), unsupervised learning models (K-Means Clustering), and neural networks (Multilayer Perceptron) to predict and identify ice formation patterns. The experimental results demonstrate that our smart system, driven by machine learning, accurately predicts ice formation in real time, optimizes deicing processes, and enhances safety while reducing power consumption. This solution holds the potential for improving ice detection accuracy in aviation and other critical industries requiring robust predictive maintenance. Full article

Morse code recognition plays a very important role in the application of human–machine interaction. In this paper, based on the carbon nanotube (CNT) and polyurethane sponge (PUS) composite material, a flexible tactile CNT/PUS sensor with great piezoresistive characteristic is developed for detecting Morse code precisely. Thirty-six types of Morse code, including 26 letters (A–Z) and 10 numbers (0–9), are applied to the sensor. Each Morse code was repeated 60 times, and 2160 (36 × 60) groups of voltage time-sequential signals were collected to construct the dataset. Then, smoothing and normalization methods are used to preprocess and optimize the raw data. Based on that, the long short-term memory (LSTM) model with excellent feature extraction and self-adaptive ability is constructed to precisely recognize different types of Morse code detected by the sensor. The recognition accuracies of the 10-number Morse code, the 26-letter Morse code, and the whole 36-type Morse code are 99.17%, 95.37%, and 93.98%, respectively. Meanwhile, the Gated Recurrent Unit (GRU), Support Vector Machine (SVM), Multi-Layer Perceptron (MLP), and Random Forest (RF) models are built to distinguish the 36-type Morse code (letters of A–Z and numbers of 0–9) based on the same dataset and achieve the accuracies of 91.37%, 88.88%, 87.04%, and 90.97%, respectively, which are all lower than the accuracy of 93.98% based on the LSTM model. All the experimental results show that the CNT/PUS sensor can detect the Morse code’s tactile feature precisely, and the LSTM model has a very efficient property in recognizing Morse code detected by the CNT/PUS sensor. Full article

Drowsiness is a main factor for various costly defects, even fatal accidents in areas such as construction, transportation, industry and medicine, due to the lack of monitoring vigilance in the mentioned areas. The implementation of a drowsiness detection system can greatly help to reduce the defects and accident rates by alerting individuals when they enter a drowsy state. This research proposes an electroencephalography (EEG)-based approach for detecting drowsiness. EEG signals are passed through a preprocessing chain composed of artifact removal and segmentation to ensure accurate detection followed by different feature extraction methods to extract the different features related to drowsiness. This work explores the use of various machine learning algorithms such as Support Vector Machine (SVM), the K nearest neighbor (KNN), the Naive Bayes (NB), the Decision Tree (DT), and the Multilayer Perceptron (MLP) to analyze EEG signals sourced from the DROZY database, carefully labeled into two distinct states of alertness (awake and drowsy). Segmentation into 10 s intervals ensures precise detection, while a relevant feature selection layer enhances accuracy and generalizability. The proposed approach achieves high accuracy rates of 99.84% and 96.4% for intra (subject by subject) and inter (cross-subject) modes, respectively. SVM emerges as the most effective model for drowsiness detection in the intra mode, while MLP demonstrates superior accuracy in the inter mode. This research offers a promising avenue for implementing proactive drowsiness detection systems to enhance occupational safety across various industries. Full article

In various domains, including everyday activities, agricultural practices, and medical treatments, the escalating challenge of antibiotic resistance poses a significant concern. Traditional approaches to studying antibiotic resistance genes (ARGs) often require substantial time and effort and are limited in accuracy. Moreover, the decentralized nature of existing data repositories complicates comprehensive analysis of antibiotic resistance gene sequences. In this study, we introduce a novel computational framework named TGC-ARG designed to predict potential ARGs. This framework takes protein sequences as input, utilizes SCRATCH-1D for protein secondary structure prediction, and employs feature extraction techniques to derive distinctive features from both sequence and structural data. Subsequently, a Siamese network is employed to foster a contrastive learning environment, enhancing the model’s ability to effectively represent the data. Finally, a multi-layer perceptron (MLP) integrates and processes sequence embeddings alongside predicted secondary structure embeddings to forecast ARG presence. To evaluate our approach, we curated a pioneering open dataset termed ARSS (Antibiotic Resistance Sequence Statistics). Comprehensive comparative experiments demonstrate that our method surpasses current state-of-the-art methodologies. Additionally, through detailed case studies, we illustrate the efficacy of our approach in predicting potential ARGs. Full article

The main objective of this study is to analyze the drying kinetics of Citrus medica by using the freeze-drying method at various thicknesses (3, 5, and 7 mm) and cabin pressures (0.008, 0.010, and 0.012 mbar). Additionally, the study aims to evaluate the efficacy of an artificial neural network (ANN) in estimating crucial parameters like dimensionless mass loss ratio (MR), moisture content, and drying rate. Feedforward multilayer perceptron (MLP) neural network architecture was employed to model the freeze-drying process of Citrus medica. The ANN architecture was trained using a dataset covering various drying conditions and product characteristics. The training process, including hyperparameter optimization, is detailed and the performance of the ANN is evaluated using robust metrics such as RMSE and R². As a result of comparing the experimental MR with the predicted MR of the ANN modeling created by considering various product thicknesses and cabin pressures, the R² was found to be 0.998 and the RMSE was 0.010574. Additionally, color change, water activity, and effective moisture diffusivity were examined in this study. As a result of the experiments, the color change in freeze-dried Citrus medica fruits was between 6.9 ± 0.2 and 21.0 ± 0.6, water activity was between 0.4086 ± 0.0104 and 0.5925 ± 0.0064, effective moisture diffusivity was between 4.19 × ${10}^{-11}$ and 21.4 × ${10}^{-11}$, respectively. In freeze-drying experiments conducted at various cabin pressures, it was observed that increasing the slice thickness of Citrus medica fruit resulted in longer drying times, higher water activity, greater color changes, and increased effective moisture diffusivity. By applying the experimental data to mathematical models and an ANN, the optimal process conditions were determined. The results of this study indicate that ANNs can potentially be applied to characterize the freeze-drying process of Citrus medica. Full article

The objective of basic oxygen furnace (BOF) steelmaking is to achieve molten steel with final carbon content, temperature, and phosphorus content meeting the requirements. Accurate prediction of the above properties is crucial for end-point control in BOF steelmaking. Traditional prediction models typically use multi-variable input and single-variable output approaches, neglecting the coupling relationships between different property indicators, making it difficult to predict multiple outputs simultaneously. Consequently, a multi-output prediction model based on the fusion of deep convolution and attention mechanism networks (FDCAN) is proposed. The model inputs include scalar data, such as the properties of raw materials and target molten steel, and time series data, such as lance height, oxygen supply intensity, and bottom air supply intensity during the blowing process. The FDCAN model utilizes a fully connected module to extract nonlinear features from scalar data and a deep convolution module to process time series data, capturing high-dimensional feature representations. The attention mechanism then assigns greater weight to significant features. Finally, multiple multi-layer perceptron modules predict the outputs—final carbon content, temperature, and phosphorus content. This structure allows FDCAN to learn complex relationships within the input data and between input and output variables. The effectiveness of the FDCAN model is validated using actual BOF steelmaking data, achieving hit rates of 95.14% for final carbon content within ±0.015 wt%, 84.72% for final temperature within ±15 °C, and 88.89% for final phosphorus content within ±0.005 wt%. Full article