Robust Model Research Articles

Advancements in Data Augmentation and Transfer Learning: A Comprehensive Survey to Address Data Scarcity Challenges

Abstract: Deep Learning (DL) models have demonstrated remarkable proficiency in image classification and recognition tasks, surpassing human capabilities. The observed enhancement in performance can be attributed to the utilization of extensive datasets. Nevertheless, DL models have huge data requirements. Widening the learning capability of such models from limited samples even today remains a challenge, given the intrinsic constraints of small datasets. The trifecta of challenges, encompassing limited labeled datasets, privacy, poor generalization performance, and the costliness of annotations, further compounds the difficulty in achieving robust model performance. Overcoming the challenge of expanding the learning capabilities of Deep Learning models with limited sample sizes remains a pressing concern even today. To address this critical issue, our study conducts a meticulous examination of established methodologies, such as Data Augmentation and Transfer Learning, which offer promising solutions to data scarcity dilemmas. Data Augmentation, a powerful technique, amplifies the size of small datasets through a diverse array of strategies. These encompass geometric transformations, kernel filter manipulations, neural style transfer amalgamation, random erasing, Generative Adversarial Networks, augmentations in feature space, and adversarial and meta- learning training paradigms. : Furthermore, Transfer Learning emerges as a crucial tool, leveraging pre-trained models to facilitate knowledge transfer between models or enabling the retraining of models on analogous datasets. Through our comprehensive investigation, we provide profound insights into how the synergistic application of these two techniques can significantly enhance the performance of classification tasks, effectively magnifying scarce datasets. This augmentation in data availability not only addresses the immediate challenges posed by limited datasets but also unlocks the full potential of working with Big Data in a new era of possibilities in DL applications.

LesionNet: an automated approach for skin lesion classification using SIFT features with customized convolutional neural network

Accurate detection of skin lesions through computer-aided diagnosis has emerged as a critical advancement in dermatology, addressing the inefficiencies and errors inherent in manual visual analysis. Despite the promise of automated diagnostic approaches, challenges such as image size variability, hair artifacts, color inconsistencies, ruler markers, low contrast, lesion dimension differences, and gel bubbles must be overcome. Researchers have made significant strides in binary classification problems, particularly in distinguishing melanocytic lesions from normal skin conditions. Leveraging the “MNIST HAM10000” dataset from the International Skin Image Collaboration, this study integrates Scale-Invariant Feature Transform (SIFT) features with a custom convolutional neural network model called LesionNet. The experimental results reveal the model's robustness, achieving an impressive accuracy of 99.28%. This high accuracy underscores the effectiveness of combining feature extraction techniques with advanced neural network models in enhancing the precision of skin lesion detection.

Deep attention for enhanced OCT image analysis in clinical retinal diagnosis

AbstractRetinal illnesses such as age-related macular degeneration (AMD) and diabetic maculopathy pose serious risks to vision in the developed world. The diagnosis and assessment of these disorders have undergone revolutionary change with the development of optical coherence tomography (OCT). This study proposes a novel method for improving clinical precision in retinal disease diagnosis by utilizing the strength of Attention-Based DenseNet, a deep learning architecture with attention processes. For model building and evaluation, a dataset of 84495 high-resolution OCT images divided into NORMAL, CNV, DME, and DRUSEN classes was used. Data augmentation techniques were employed to enhance the model's robustness. The Attention-Based DenseNet model achieved a validation accuracy of 0.9167 with a batch size of 32 and 50 training epochs. This discovery presents a promising route for more precise and speedy identification of retinal illnesses, ultimately enhancing patient care and outcomes in clinical settings by integrating cutting-edge technology with powerful neural network architectures.

Few‐shot cross‐receiver radio frequency fingerprinting identification based on feature separation

AbstractRadio frequency fingerprint identification (RFFI) is a widely used technique for authenticating equipment. It identifies transmitters by extracting hardware defects found in the RF front end. Recent research has focused on the impact of transmitters and wireless channels on radio frequency fingerprint (RFF). Most work is based on the same receiver assumption, while the influence of the receiver on RFF remains unresolved. This paper focuses on the impact of receiver hardware characteristics on RFF and proposes a few‐shot cross‐receiver RFFI method based on feature separation. Data augmentation with noise addition and simulated channels addresses sparse sample issues and enhances the model's robustness to channel variations. Simultaneously, feature separation is realized by reducing the correlation between transmitter and receiver features through classification loss and similarity loss. We evaluate the proposed approaches using a large‐scale WiFi dataset. It is shown that when a trained transmitter classifier is deployed on new receivers with only 30 samples per trained transmitter, the average identification accuracy of the proposed method is 83.6%. This accuracy is 9.45% higher than the baseline method without considering transmitter hardware influence. After fine‐tuning, the average identification accuracy can reach 98.25%.

A novel approach to predict buildings load based on deep learning and non-intrusive load monitoring technique, toward smart building

Short-term load forecasting is critical in managing energy production, domestic consumption, and grid integration. Short-term load forecasting is an essential tool for managing and controlling the processes required to make buildings smarter. Short-term load forecasting at this level of the network is extremely difficult due to the high uncertainty in load demand. This study presents a novel approach for predicting building loads using deep learning and non-intrusive load monitoring (NILM) techniques, aimed at enhancing smart building energy management. The methodology involves the integration of Recurrent Neural Networks (RNNs) to effectively capture temporal patterns in power consumption data, which are critical for accurate load forecasting. The model uses a feature matrix created from power signals to improve its forecast accuracy. The results show that the suggested model greatly outperforms standard models, with an overall accuracy of 97.2 %. The model's robustness is proven through comprehensive experiments, which demonstrate higher performance in short-term load forecasts. Furthermore, a comparison with existing models demonstrates the proposed approach's efficacy in recognizing and predicting load fluctuations, making it a useful tool for smart grid applications.

Inferring Surface NO2 Over Western Europe: A Machine Learning Approach With Uncertainty Quantification

AbstractNitrogen oxides (NOx = NO + NO2) are of great concern due to their impact on human health and the environment. In recent years, machine learning (ML) techniques have been widely used for surface NO2 estimation with rapid developments in computational power and big data. However, the uncertainties inherent to such retrievals are rarely studied. In this study, a novel ML framework has been developed, enhanced with uncertainty quantification techniques, to estimate surface NO2 and provide corresponding data‐induced uncertainty. We apply the Boosting Ensemble Conformal Quantile Estimator (BEnCQE) model to infer surface NO2 concentrations over Western Europe at the daily scale and 1 km spatial resolution from May 2018 to December 2021. High NO2 mainly appears in urban areas, industrial areas, and roads. The space‐based cross‐validation shows that our model achieves accurate point estimates (r = 0.8, R2 = 0.64, root mean square error = 8.08 μg/m3) and reliable prediction intervals (coverage probability, PI‐50%: 51.0%, PI‐90%: 90.5%). Also, the model result agrees with the Copernicus Atmosphere Monitoring Service (CAMS) model. The quantile regression in our model enables us to understand the importance of predictors for different NO2 level estimations. Additionally, the uncertainty information reveals the extra potential exceedance of the World Health Organization (WHO) 2021 limit in some locations, which is undetectable by only point estimates. Meanwhile, the uncertainty quantification allows assessment of the model's robustness outside existing in‐situ station measurements. It reveals challenges of NO2 estimation over urban and mountainous areas where NO2 is highly variable and heterogeneously distributed.

A deep autoencoder for electric double layer capacitance prediction in electrochemical sensors

This study explores the application of a deep autoencoder neural network to accurately predict the electric double layer capacitance from real-world parameters in binary, asymmetric electrolytes under low concentration conditions. By utilizing a modest simulation-based dataset of just 250 samples, the deep autoencoder neural network model developed in this study effectively predicted the capacitance by learning the critical features and relationships of the electric double layer model and encoding this learned representation into a low-dimensional latent space. From the latent variables, the decoder block of the neural network learned to effectively recreate the high-dimensional input. To enhance the model's robustness, prevent overfitting, and better simulate real-world conditions, noise was incorporated into the training and test data. The model demonstrated strong performance across various conditions, such as ionic size, ionic charge, and surface potential, yielding satisfactory results on both clean and noisy test datasets. A key feature of this approach was the mapping of real-world electric double layer parameters to the latent variables of the model, allowing for direct input of physical parameters to predict the electric double layer capacitance. This research highlights the potential of machine learning techniques to expedite the design and analysis of complex multi-physics systems such as electrochemical sensors by reducing the dependence on extensive domain expertise throughout the design process.

Nutritional composition analysis in food images: an innovative Swin Transformer approach.

Accurate recognition of nutritional components in food is crucial for dietary management and health monitoring. Current methods often rely on traditional chemical analysis techniques, which are time-consuming, require destructive sampling, and are not suitable for large-scale or real-time applications. Therefore, there is a pressing need for efficient, non-destructive, and accurate methods to identify and quantify nutrients in food. In this study, we propose a novel deep learning model that integrates EfficientNet, Swin Transformer, and Feature Pyramid Network (FPN) to enhance the accuracy and efficiency of food nutrient recognition. Our model combines the strengths of EfficientNet for feature extraction, Swin Transformer for capturing long-range dependencies, and FPN for multi-scale feature fusion. Experimental results demonstrate that our model significantly outperforms existing methods. On the Nutrition5k dataset, it achieves a Top-1 accuracy of 79.50% and a Mean Absolute Percentage Error (MAPE) for calorie prediction of 14.72%. On the ChinaMartFood109 dataset, the model achieves a Top-1 accuracy of 80.25% and a calorie MAPE of 15.21%. These results highlight the model's robustness and adaptability across diverse food images, providing a reliable and efficient tool for rapid, non-destructive nutrient detection. This advancement supports better dietary management and enhances the understanding of food nutrition, potentially leading to more effective health monitoring applications.

Multi‐function radar work mode recognition based on residual shrinkage reconstruction recurrent neural network

AbstractIn modern electronic warfare, multi‐function radar work mode recognition is increasingly crucial. However, the challenges posed by complex electromagnetic environments, such as lost pulses, spurious pulses, and measurement errors, along with the reliance of traditional multi‐task learning strategies on clean samples, make it difficult for existing algorithms to achieve satisfactory recognition performance in real‐world scenarios. To address these issues, this paper introduces a novel residual shrinkage reconstruction recurrent neural network (RS‐RRNN). The network uses a Gated Recurrent Unit as its backbone to extract temporal features and enhances feature extraction by reconstructing the GRU's input, while also reducing dependence on clean samples. These features are then processed through a residual shrinkage structure to reduce noise, which significantly improves the model's robustness in non‐ideal scenarios. Simulations demonstrate that RS‐RNN has better performances in accuracy and robustness than existing networks.

Semi-Supervised Encrypted Malicious Traffic Detection Based on Multimodal Traffic Characteristics.

The exponential growth of encrypted network traffic poses significant challenges for detecting malicious activities online. The scale of emerging malicious traffic is significantly smaller than that of normal traffic, and the imbalanced data distribution poses challenges for detection. However, most existing methods rely on single-category features for classification, which struggle to detect covert malicious traffic behaviors. In this paper, we introduce a novel semi-supervised approach to identify malicious traffic by leveraging multimodal traffic characteristics. By integrating the sequence and topological information inherent in the traffic, we achieve a multifaceted representation of encrypted traffic. We design two independent neural networks to learn the corresponding sequence and topological features from the traffic. This dual-feature extraction enhances the model's robustness in detecting anomalies within encrypted traffic. The model is trained using a joint strategy that minimizes both the reconstruction error from the autoencoder and the classification loss, allowing it to effectively utilize limited labeled data alongside a large amount of unlabeled data. A confidence-estimation module enhances the classifier's ability to detect unknown attacks. Finally, our method is evaluated on two benchmark datasets, UNSW-NB15 and CICIDS2017, under various scenarios, including different training set label ratios and the presence of unknown attacks. Our model outperforms other models by 3.49% and 5.69% in F1 score at labeling rates of 1% and 0.1%, respectively.

A Multifrequency Data Fusion Deep Learning Model for Carbon Price Prediction

ABSTRACTIn response to the global need for effective management of carbon emissions and alignment with sustainable development goals, predicting carbon trading prices accurately is critical. This study introduces a multifrequency data fusion carbon price prediction model (MFF‐CPPM), addressing the nonlinear characteristics of carbon trading prices and inconsistent feature factor frequencies. The MFF‐CPPM consists of a feature‐extraction frontend, a multifrequency data fusion transformer, and a fusion regression layer, offering a novel methodological approach in forecasting studies. The model's validity was tested in Guangdong, China's largest carbon trading pilot market. The results demonstrated that the MFF‐CPPM outperformed baseline models in terms of carbon price‐prediction accuracy and trend forecasting. Additional trials conducted in Hubei and Beijing confirmed the model's robustness and generalization capabilities, providing valuable evidence of its effectiveness and reliability across varying market contexts. This study presents a novel predictive model for carbon trading prices, with a unique capability to harness data at differing frequencies. The MFF‐CPPM not only enhances forecasting accuracy but also offers an innovative approach to effectively incorporate multifrequency information. This advancement paves the way for flexible forecasting models in any scenario where data arrive at differing frequencies.

Incorporating Crumb Rubber in Slag-Based Geopolymer: Experimental Work and Predictive Modelling

Crumb rubber (CR), a prevalent hazardous waste material, poses significant environmental challenges that necessitate innovative management strategies. Recent studies have focused on incorporating CR and ground granulated blast furnace slag (GGBS) into geopolymer concrete (GC) to address this challenge. This research presents a novel approach that combines experimental analysis with machine learning (ML) techniques to investigate the chemical effects of these materials on GC. Initially, compressive strength (CS) tests are conducted on rubberized geopolymer (RG) concrete, and the resulting data are further analyzed through ML algorithms to enhance the understanding of material behavior. Despite numerous attempts by researchers to integrate CR into geopolymer-based materials, the challenge of mitigating strength degradation persists. Therefore, it becomes imperative to construct a predictive model that relies on new variables influencing the strength characteristics. This research develops a predictive model to assess concrete compressive strength (CS). Key variables such as CR grade (particle size), incorporation percentage, and oxide ratio were analyzed for their impact on geopolymer strength. Employing ensemble techniques, namely Bagging (BA) and Gradient boosting (GB) with five learners (M5P, random forest (RF), random tree (RT), reduced error pruning tree (REPT), and support vector machine (SVM), the study found that M5P-GB models offered the most accurate CS predictions with the highest accuracy and lowest errors. Moreover, the dataset was checked via the k-fold cross-validation technique and confirmed the developed models' robustness, reliability, and effectiveness. Furthermore, uncertainty analysis revealed that GB-M5P-unpruned models-maintained uncertainty percentages of 14.769% at 7 days and 11.277% at 28 days, which was under the 35% threshold. Additionally, the sensitivity analysis identified the CR grade and replacement percentage by volume of crusher dust (CD) as the most critical factors affecting CS. These findings underscore the importance of considering predictive model development in decision-making processes related to RG concrete properties, providing valuable insights into optimizing the model's robustness and reliability for practical applications. However, the study's reliance on specific input parameters and controlled laboratory conditions may limit the generalizability of the predictive models, necessitating further validation under diverse real-world conditions and variations in CR source and environmental factors.

WITHDRAWN: Non-Contact Blood Pressure Monitoring from Radar Signals by a Temporal-Spatial Feature Fusion Network

Non-contact blood pressure (BP) monitoring offers a comfortable and uninterrupted means of BP assessment, free from the constraints of physical contact. This capability is particularly better for the routine surveillance of BP for individuals with hypertension, burn injuries, skin sensitivities, and other pertinent conditions. In this study, we proposed a Temporal-Spatial Feature Fusion Network (TSFN), a radar-based, non-contact approach for BP monitoring. The TSFN architecture combines Residual Networks (ResNet) for the meticulous extraction of spatial features from radar signals, Gated Recurrent Unit (GRU) for the discernment of temporal dynamics, and Multiple Head Attention (MHA) to selectively emphasize crucial information. These components collectively ensure precise BP detection from radar signals. To enhance the model's robustness, a Pseudo-Huber loss function was employed to refine the optimization process, providing a smoother gradient transition and improved stability. Evaluations demonstrated impressive accuracies, with mean errors of 0.24±6.78 mmHg for systolic blood pressure (SBP) and 0.25±5.13 mmHg for diastolic blood pressure (DBP). These outcomes meet the standards set by the British Hypertension Society (BHS) for grade ‘A’ benchmarks for SBP and DBP measurements. Notably, the TSFN model avoids the need for complex feature engineering, demonstrating its effectiveness in monitoring BP fluctuations across diverse physiological states at 2s intervals. This feature highlights its potential applicability in real-time monitoring systems, offering a promising solution for continuous, non-contact BP monitoring.

Introducing a novel dataset for facial emotion recognition and demonstrating significant enhancements in deep learning performance through pre-processing techniques

Facial expression recognition (FER) plays a pivotal role in various applications, ranging from human-computer interaction to psychoanalysis. To improve the accuracy of facial emotion recognition (FER) models, this study focuses on enhancing and augmenting FER datasets. It comprehensively analyzes the Facial Emotion Recognition dataset (FER13) to identify defects and correct misclassifications. The FER13 dataset represents a crucial resource for researchers developing Deep Learning (DL) models aimed at recognizing emotions based on facial features. Subsequently, this article develops a new facial dataset by expanding upon the original FER13 dataset. Similar to the FER + dataset, the expanded dataset incorporates a wider range of emotions while maintaining data accuracy. To further improve the dataset, it will be integrated with the extended Cohn-Kanade (CK+) dataset.This paper investigates the application of modern DL models to enhance emotion recognition in human faces. By training a new dataset, the study demonstrates significant performance gains compared with its counterparts. Furthermore, the article examines recent advances in FER technology and identifies critical requirements for DL models to overcome the inherent challenges of this task effectively. The study explores several DL architectures for emotion recognition in facial image datasets, with a particular focus on convolutional neural networks (CNNs). Our findings indicate that complex architecture, such as EfficientNetB7, outperforms other DL architectures, achieving a test accuracy of 78.9 %. Notably, the model surpassed the EfficientNet-XGBoost model, especially when used with the new dataset. Our approach leverages EfficientNetB7 as a backbone to build a model capable of efficiently recognizing emotions from facial images. Our proposed model, EfficientNetB7-CNN, achieved a peak accuracy of 81 % on the test set despite facing challenges such as GPU memory limitations. This demonstrates the model's robustness in handling complex facial expressions. Furthermore, to enhance feature extraction and attention mechanisms, we propose a new hybrid model, CBAM-4CNN, which integrates the convolutional block attention module (CBAM) with a custom 4-layer CNN architecture. The results showed that the CBAM-4CNN model outperformed existing models, achieving higher accuracy, precision, and recall metrics across multiple emotion classes. The results highlight the critical role of comprehensive and diverse data in enhancing model performance for facial emotion recognition.

Operational SYM‐H Forecasting With Confidence Intervals Using Deep Neural Networks

AbstractIn this study, we develop a robust real‐time forecast system for the SYM‐H index using Deep Neural Networks and real‐time Solar Wind measurements along with Interplanetary Magnetic Field parameters. This system provides not only one‐off forecasts but also quantile‐based confidence intervals, offering a range within which the observed SYM‐H values are expected to fall, enhancing forecast reliability and usability. The model is tested both on historical level 2 science‐ready data and on preliminary observations, which are closer to the operational environment that the model is expected to work on, demonstrating the model's robustness and practical utility in real‐time scenarios. The integration of quantile forecasts into SYM‐H prediction models represents a significant advancement, providing decision‐makers with more accurate and trustworthy information to manage the hazard of geomagnetic storms.

Multicenter Integration of MR Radiomics, Deep Learning, and Clinical Indicators for Predicting Hepatocellular Carcinoma Recurrence After Thermal Ablation.

To develop and validate an innovative predictive model that integrates multisequence magnetic resonance (MR) radiomics, deep learning features, and clinical indicators to accurately predict the recurrence of hepatocellular carcinoma (HCC) after thermal ablation. This retrospective multicenter cohort study enrolled patients who were diagnosed with HCC and treated via thermal ablation. We extracted radiomic features from multisequence 3T MR images, analyzed these images using a 3D convolutional neural network (3D CNN), and incorporated clinical data into the model. Model performance was evaluated using the area under the curve (AUC) of the receiver operating characteristic (ROC) curve. The study included 535 patients from three hospitals, comprising 462 males and 43 females. The RDC model, which stands for the Radiomics-Deep Learning-Clinical data model, demonstrated high predictive accuracy, achieving AUCs of 0.794 in the training set, 0.777 in the validation set, and 0.787 in the test set. Statistical analysis confirmed the model's robustness and the significant contribution of the integrated features to its predictive capabilities. The RDC model effectively predicts HCC recurrence after thermal ablation by synergistically combining advanced imaging analysis and clinical parameters. This study highlights the potential of such integrative approaches to enhance prognostic assessments in HCC patients and offers a promising tool for clinical decision-making.

Diversifying Collaborative Filtering via Graph Spreading Network and Selective Sampling.

Graph neural network (GNN) is a robust model for processing non-Euclidean data, such as graphs, by extracting structural information and learning high-level representations. GNN has achieved state-of-the-art recommendation performance on collaborative filtering (CF) for accuracy. Nevertheless, the diversity of the recommendations has not received good attention. Existing work using GNN for recommendation suffers from the accuracy-diversity dilemma, where slightly increases diversity while accuracy drops significantly. Furthermore, GNN-based recommendation models lack the flexibility to adapt to different scenarios' demands concerning the accuracy-diversity ratio of their recommendation lists. In this work, we endeavor to address the above problems from the perspective of aggregate diversity, which modifies the propagation rule and develops a new sampling strategy. We propose graph spreading network (GSN), a novel model that leverages only neighborhood aggregation for CF. Specifically, GSN learns user and item embeddings by propagating them over the graph structure, utilizing both diversity-oriented and accuracy-oriented aggregations. The final representations are obtained by taking the weighted sum of the embeddings learned at all layers. We also present a new sampling strategy that selects potentially accurate and diverse items as negative samples to assist model training. GSN effectively addresses the accuracy-diversity dilemma and achieves improved diversity while maintaining accuracy with the help of a selective sampler. Moreover, a hyper-parameter in GSN allows for adjustment of the accuracy-diversity ratio of recommendation lists to satisfy the diverse demands. Compared to the state-of-the-art model, GSN improved R @20 by 1.62%, N @20 by 0.67%, G @20 by 3.59%, and E @20 by 4.15% on average over three real-world datasets, verifying the effectiveness of our proposed model in diversifying overall collaborative recommendations.

An Optimal Multi-Modal Approach for Stock Market Price Forecasting with Fused Sentiment Analysis for Real Time Data

Abstract: This study presents an innovative fusion-based methodology that integrates real-time stock market technical indicators with news sentiment analysis from financial news feeds to enhance stock selection decisions. The proposed framework employs a Bidirectional Long Short-Term Memory (Bi-LSTM) model for forecasting stock prices and a Deep Neural Network (DNN) used in conjunction with transformer-based model for sentiment classification, both optimized through the incorporation of real-time datasets. To further refine feature selection, Artificial Bee Colony (ABC) and Firefly algorithms are utilized, significantly improving the accuracy of price trend predictions and sentiment analysis. Technical indicators from stock market data are processed using the Bi-LSTM model to predict future stock prices. Concurrently, sentiment data from the Economic Times is pre-processed through Term Frequency-Inverse Document Frequency (TF-IDF) vectorization and pre-trained transformer models to extract key sentiment scores. The ABC algorithm enhances textual feature selection, while the Firefly algorithm reduces skewness in the error distribution of technical indicators, thereby improving the alignment between forecasted and actual stock prices. The fusion mechanism integrates predicted price movements with sentiment analysis to provide actionable insights for stock selection. The decision-making framework classifies stocks based on the consistency between price movements and sentiment: stocks predicted to rise with positive sentiment are labelled as "Sure Selection"; rising prices with negative sentiment are categorized as "Dicey Selection"; declining prices with positive sentiment result in a "Risky Selection"; and negative sentiment with falling prices trigger an "Avoid Selection". The proposed approach achieved a prediction accuracy of 67.00% for the Bi-LSTM model, with a precision of 0.714, recall of 0.695, and an F1 score of 0.677, demonstrating the model's robustness. The mean absolute error (MAE) for the Bi-LSTM model was 4.30, indicating strong predictive performance. The combined use of ABC and Firefly algorithms optimizes both technical and sentiment features, significantly contributing to the overall performance of the prediction model. By fusing multiple data sources and employing advanced optimization techniques, this methodology offers a unique and effective solution for stock market prediction and decision-making

Detecting emerald ash borer boring vibrations using an encoder-decoder and improved DenseNet model.

Forest ecosystems are under constant threat from wood-boring pests such as the Emerald ash borer (EAB), which remain elusive owing to their hidden life cycles within tree trunks. Early detection is vital to mitigate economic and ecological damage. The main current monitoring method is manual detection which is ineffective at early stages of infestation. This study introduces VibroEABNet, a deep learning-based joint recognition network designed to enhance the detection of EAB boring vibration signals, with a novel approach integrating denoising and recognition modules. The proposed VibroEABNet model demonstrated exceptional performance, achieving an average accuracy of 98.98% across multiple signal-to-noise ratios (SNRs) in test datasets and a remarkable 97.5% accuracy in real forest datasets, surpassing traditional models and other deep learning networks evaluated in this study. These findings were supported by rigorous noise resistance analysis and real dataset evaluation, indicating the model's robustness and reliability in practical applications. Furthermore, the model's efficiency was highlighted by its inference time of 26 ms and a compact model size of 8.43 MB, underscoring its suitability for deployment in resource-limited environments. The development of VibroEABNet marks a significant advancement in pest detection methodologies, offering a scalable, accurate and efficient solution for early monitoring of wood-boring pests. The integration of a denoising module within the network structure addresses the challenge of environmental noise, one of the primary limitations in acoustic monitoring of pests. Currently, this research is limited to a specific pest. Future work will focus on the applicability of this network to other wood-boring pests. © 2024 Society of Chemical Industry.

An Innovative Deep Neural Network Model for Precise Calorie Burn Prediction from Physical Activity Data

Accurate prediction of calories burned during physical activities is crucial for various applications in health monitoring, fitness tracking, and personalized nutrition. Traditional methods often lack the precision needed for individualized estimates, which has increased interest in advanced machine learning approaches. This research introduces a deep learning model designed to predict calories burned with enhanced accuracy by capturing complex, non-linear relationships in the data. The model employs a multilayer perceptron neural network, Leaky ReLU activations, dropout regularization, and the Adam optimizer to improve generalizability and prevent overfitting. The evaluation of training and validation loss over epochs demonstrated the model's robustness and capacity to generalize effectively to novel data. The model's performance was evaluated using various metrics, achieving superior results with a remarkable Mean Absolute Error (MAE) of 0.27% and an accuracy of 99.73%, outperforming other models discussed in the literature. These findings indicate that deep learning offers significant potential for improving calorie prediction models, providing more reliable fitness and health management tools.