Search

Despite considerable achievements of deep learning-based side-channel analysis, overfitting represents a significant obstacle in finding optimized neural network models. This issue is not unique to the side-channel domain. Regularization techniques are popular solutions to overfitting and have long been used in various domains. At the same time, the works in the side-channel domain show sporadic utilization of regularization techniques. What is more, no systematic study investigates these techniques' effectiveness. In this paper, we aim to investigate the regularization effectiveness on a randomly selected model, by applying 4 powerful and easy-to-use regularization techniques to 8 combinations of datasets, leakage models, and deep learning topologies. The investigated techniques are L 1 , L 2 , dropout, and early stopping. Our results show that while all these techniques can improve performance in many cases, L 1 and L 2 are the most effective. Finally, if training time matters, early stopping is the best technique. [ABSTRACT FROM AUTHOR]

Graph neural networks (GNNs) typically exhibit superior performance in shallow architectures. However, as the network depth increases, issues such as overfitting and oversmoothing of hidden vector representations arise, significantly diminishing model performance. To address these challenges, this paper proposes a Two-Channel Classification Algorithm Based on Graph Attention Network (TCC_GAT). Initially, nodes exhibiting similar interaction behaviors are identified through cosine similarity, thereby enhancing the foundational graph structure. Subsequently, an attention mechanism is employed to adaptively integrate neighborhood information within the enhanced graph structure, with a multi-head attention mechanism applied to mitigate overfitting. Furthermore, the K-nearest neighbors algorithm is adopted to reconstruct the basic graph structure, facilitating the learning of structural information and neighborhood features that are challenging to capture on interaction graphs. This approach addresses the difficulties associated with learning high-order neighborhood information. Finally, the embedding representations of identical nodes across different graph structures are fused to optimize model classification performance, significantly enhancing node embedding representations and effectively alleviating the over-smoothing issue. Semi-supervised experiments and ablation studies conducted on the Cora, Citeseer, and Pubmed datasets reveal an accuracy improvement ranging from 1.4% to 4.5% compared to existing node classification algorithms. The experimental outcomes demonstrate that the proposed TCC_GAT achieves superior classification results in node classification tasks. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI), including machine learning (ML) and deep learning (DL), learns by training and is restricted by the amount and quality of training data. Training involves a tradeoff between prediction bias and variance controlled by model complexity. Increased model complexity decreases prediction bias, increases variance, and increases overfitting possibilities. Overfitting is a significantly smaller training prediction error relative to the trained model prediction error for an independent validation set. Uncertain data generate risks for AI–ML because they increase overfitting and limit generalization ability. Specious confidence in predictions from overfit models with limited generalization ability, leading to misguided water resource management, is the uncertainty-related negative consequence. Improved data is the way to improve AI–ML models. With uncertain water resource data sets, like stream discharge, there is no quick way to generate improved data. Data assimilation (DA) provides mitigation for uncertainty risks, describes data- and model-related uncertainty, and propagates uncertainty to results using observation error models. A DA-derived mitigation example is provided using a common-sense baseline, derived from an observation error model, for the confirmation of generalization ability and a threshold identifying overfitting. AI–ML models can also be incorporated into DA to provide additional observations for assimilation or as a forward model for prediction and inverse-style calibration or training. The mitigation of uncertain data risks using DA involves a modified bias–variance tradeoff that focuses on increasing solution variability at the expense of increased model bias. Increased variability portrays data and model uncertainty. Uncertainty propagation produces an ensemble of models and a range of predictions. [ABSTRACT FROM AUTHOR]

Fully connected deep neural networks are successfully applied to classification and function approximation problems. By minimizing the cost function, i.e., finding the proper weights and biases, models can be built for accurate predictions. The ideal optimization process can achieve global optima. However, do global optima always perform well? If not, how bad can it be? In this work, we aim to: 1) extend the expressive power of shallow neural networks to networks of any depth using a simple trick, 2) construct extremely overfitting deep neural networks that, despite having global optima, still fail to perform well on classification and function approximation problems. Different types of activation functions are considered, including ReLU, Parametric ReLU, and Sigmoid functions. Extensive theoretical analysis has been conducted, ranging from one-dimensional models to models of any dimensionality. Numerical results illustrate our theoretical findings. [ABSTRACT FROM AUTHOR]

Convolutional neural network (CNN) is one of the well-known deep learning algorithms that uses convolutional filters to extract the features in the images. The most important issue when training CNN is the overfitting which prevents the model from generalization to unseen data. This paper addressed this issue by proposing a novel hybrid approach that uses bees algorithm (BA) to optimize the regularization parameter and weight regularization factor to adjust the regularization value in each convolutional layer and fully connected layer resulting in a hybrid algorithm called bees algorithm regularized convolutional neural network (BA-RCNN). It was applied to three different datasets for classification or predictions purposes and showed an improvement in the validation and testing accuracy leading to a lower difference with the training accuracy which means the overfitting is reduced comparing to the original CNN. Applying the BA-RCNN algorithm to 'Cifar10DataDir' improved the validation accuracy from 80.34% for the original CNN to 82.80% for the hybrid BA-RCNN algorithm, in the electrocardiogram the improvement was from 87.80 to 90.47% and both datasets were used for classification. Furthermore, the hybrid BA-RCNN algorithm was applied to predict the porosity percentage based on artificial porosity images and the results showed that the validation accuracy was improved from 81.67% for the original CNN to 87.33% for the hybrid BA-RCNN algorithm. [ABSTRACT FROM AUTHOR]

This study demonstrates a method for quantifying the impact of overfitting on the receiving operator characteristic curve (AUC) when using standard analysis pipelines to develop imaging biomarkers. We illustrate the approach using two publicly available repositories of radiology and pathology images for breast cancer diagnosis. For each dataset, we permuted the outcome (cancer diagnosis) values to eliminate any true association between imaging features and outcome. Seven types of classification models (logistic regression, linear discriminant analysis, Naïve Bayes, linear support vector machines, nonlinear support vector machine, random forest, and multi-layer perceptron) were fitted to each scrambled dataset and evaluated by each of four techniques (all data, hold-out, 10-fold cross-validation, and bootstrapping). After repeating this process for a total of 50 outcome permutations, we averaged the resulting AUCs. Any increase over a null AUC of 0.5 can be attributed to overfitting. Applying this approach and varying sample size and the number of imaging features, we found that failing to control for overfitting could result in near-perfect prediction (AUC near 1.0). Cross-validation offered greater protection against overfitting than the other evaluation techniques, and for most classification algorithms a sample size of at least 200 was required to assess as few as 10 features with less than 0.05 AUC inflation attributable to overfitting. This approach could be applied to any curated dataset to suggest the number of features and analysis approaches to limit overfitting. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) and machine learning (ML) aim to mimic human intelligence and enhance decision making processes across various fields. A key performance determinant in a ML model is the ratio between the training and testing dataset. This research investigates the impact of varying train-test split ratios on machine learning model performance and generalization capabilities using the BraTS 2013 dataset. Logistic regression, random forest, k nearest neighbors, and support vector machines were trained with split ratios ranging from 60:40 to 95:05. Findings reveal significant variations in accuracies across these ratios, emphasizing the critical need to strike a balance to avoid overfitting or underfitting. The study underscores the importance of selecting an optimal train-test split ratio that considers tradeoffs such as model performance metrics, statistical measures, and resource constraints. Ultimately, these insights contribute to a deeper understanding of how ratio selection impacts the effectiveness and reliability of machine learning applications across diverse fields. [ABSTRACT FROM AUTHOR]

Methodological experts suggest that psychological and educational researchers should employ appropriate methods for data-driven model exploration, such as Bayesian Model Averaging and regularized regression, instead of conventional hypothesis-driven testing, if they want to explore the best prediction model. I intend to discuss practical considerations regarding data-driven methods for end-user researchers without sufficient expertise in quantitative methods. I tested three data-driven methods, i.e., Bayesian Model Averaging, LASSO as a form of regularized regression, and stepwise regression, with datasets in psychology and education. I compared their performance in terms of cross-validity indicating robustness against overfitting across different conditions. I employed functionalities widely available via R with default settings to provide information relevant to end users without advanced statistical knowledge. The results demonstrated that LASSO showed the best performance and Bayesian Model Averaging outperformed stepwise regression when there were many candidate predictors to explore. Based on these findings, I discussed appropriately using the data-driven model exploration methods across different situations from laypeople's perspectives. [ABSTRACT FROM AUTHOR]

The pursuit of fairness in machine learning models has become increasingly crucial across various applications, including bank loan approval and face detection. Despite the widespread use of artificial intelligence algorithms, concerns persist regarding biases and discrimination within these models. This study introduces a novel approach, termed "The Fairness Stitch" (TFS), aimed at enhancing fairness in deep learning models by combining model stitching and training jointly, while incorporating fairness constraints. We evaluate the effectiveness of TFS through a comprehensive assessment using two established datasets, CelebA and UTKFace. The evaluation involves a systematic comparison with the existing baseline method, fair deep feature reweighting (FDR). Our analysis demonstrates that TFS achieves a better balance between fairness and performance compared to the baseline method (FDR). Specifically, our method shows significant improvements in mitigating biases while maintaining performance levels. These results underscore the promising potential of TFS in addressing bias-related challenges and promoting equitable outcomes in machine learning models. This research challenges conventional wisdom regarding the efficacy of the last layer in deep learning models for debiasing purposes. The findings suggest that integrating fairness constraints into our proposed framework (TFS) can lead to more effective mitigation of biases and contribute to fairer AI systems.

Wireless Sensor Networks (WSNs) play a vital role in various applications, necessitating robust network security to protect sensitive data. Intrusion Detection Systems (IDSs) are crucial for preserving the integrity, availability, and confidentiality of WSNs by detecting and countering potential attacks. Despite significant research efforts, the existing IDS solutions still suffer from challenges related to detection accuracy and false alarms. To address these challenges, in this paper, we propose a Bayesian optimization-based Deep Learning (DL) model. However, the proposed optimized DL model, while showing promising results in enhancing security, encounters challenges such as data dependency, computational complexity, and the potential for overfitting. In the literature, researchers have employed Reinforcement Learning (RL) to address these issues. However, it also introduces its own concerns, including exploration, reward design, and prolonged training times. Consequently, to address these challenges, this paper proposes an Innovative Integrated RL-based Advanced DL Algorithm (IRADA) for attack detection in WSNs. IRADA leverages the convergence of DL and RL models to achieve superior intrusion detection performance. The performance analysis of IRADA reveals impressive results, including accuracy (99.50%), specificity (99.94%), sensitivity (99.48%), F1-Score (98.26%), Kappa statistics (99.42%), and area under the curve (99.38%). Additionally, we analyze IRADA's robustness against adversarial attacks, ensuring its applicability in real-world security scenarios. [ABSTRACT FROM AUTHOR]

Background Purpose Methods Results Conclusion Adaptive radiotherapy (ART) workflows have been increasingly adopted to achieve dose escalation and tissue sparing under shifting anatomic conditions, but the necessity of recontouring and the associated time burden hinders a real‐time or online ART workflow. In response to this challenge, approaches to auto‐segmentation involving deformable image registration, atlas‐based segmentation, and deep learning‐based segmentation (DLS) have been developed. Despite the particular promise shown by DLS methods, implementing these approaches in a clinical setting remains a challenge, namely due to the difficulty of curating a data set of sufficient size and quality so as to achieve generalizability in a trained model.To address this challenge, we have developed an intentional deep overfit learning (IDOL) framework tailored to the auto‐segmentation task. However, certain limitations were identified, particularly the insufficiency of the personalized dataset to effectively overfit the model. In this study, we introduce a personalized hyperspace learning (PHL)‐IDOL segmentation framework capable of generating datasets that induce the model to overfit specific patient characteristics for medical image segmentation.The PHL‐IDOL model is trained in two stages. In the first, a conventional, general model is trained with a diverse set of patient data (n = 100 patients) consisting of CT images and clinical contours. Following this, the general model is tuned with a data set consisting of two components: (a) selection of a subset of the patient data (m < n) using the similarity metrics (mean square error (MSE), peak signal‐to‐noise ratio (PSNR), structural similarity index (SSIM), and the universal quality image index (UQI) values); (b) adjust the CT and the clinical contours using a deformed vector generated from the reference patient and the selected patients using (a). After training, the general model, the continual model, the conventional IDOL model, and the proposed PHL‐IDOL model were evaluated using the volumetric dice similarity coefficient (VDSC) and the Hausdorff distance 95% (HD95%) computed for 18 structures in 20 test patients.Implementing the PHL‐IDOL framework resulted in improved segmentation performance for each patient. The Dice scores increased from 0.81±$ \pm $0.05 with the general model, 0.83±0.04$ \pm 0.04$ for the continual model, 0.83±0.04$ \pm 0.04$ for the conventional IDOL model to an average of 0.87±0.03$ \pm 0.03$ with the PHL‐IDOL model. Similarly, the Hausdorff distance decreased from 3.06±0.99$ \pm 0.99$ with the general model, 2.84±0.69$ \pm 0.69$ for the continual model, 2.79±0.79$ \pm 0.79$ for the conventional IDOL model and 2.36±0.52$ \pm 0.52$ for the PHL‐IDOL model. All the standard deviations were decreased by nearly half of the values comparing the general model and the PHL‐IDOL model.The PHL‐IDOL framework applied to the auto‐segmentation task achieves improved performance compared to the general DLS approach, demonstrating the promise of leveraging patient‐specific prior information in a task central to online ART workflows. [ABSTRACT FROM AUTHOR]

BACKGROUND: The accurate recognition and early warning for plant diseases and pests are a prerequisite of intelligent prevention and control for plant diseases and pests. As a result of the phenotype similarity of the hazarded plant after plant diseases and pests occur, as well as the interference of the external environment, traditional deep learning models often face the overfitting problem in phenotype recognition of plant diseases and pests, which leads to not only the slow convergence speed of the network, but also low recognition accuracy. RESULTS: Motivated by the above problems, the present study proposes a deep learning model EResNet‐support vector machine (SVM) to alleviate the overfitting for the recognition and classification of plant diseases and pests. First, the feature extraction capability of the model is improved by increasing feature extraction layers in the convolutional neural network. Second, the order‐reduced modules are embedded and a sparsely activated function is introduced to reduce model complexity and alleviate overfitting. Finally, a classifier fused by SVM and fully connected layers are introduced to transforms the original non‐linear classification problem into a linear classification problem in high‐dimensional space to further alleviate the overfitting and improve the recognition accuracy of plant diseases and pests. The ablation experiments further demonstrate that the fused structure can effectively alleviate the overfitting and improve the recognition accuracy. The experimental recognition results for typical plant diseases and pests show that the proposed EResNet‐SVM model has 99.30% test accuracy for eight conditions (seven plant diseases and one normal), which is 5.90% higher than the original ResNet18. Compared with the classic AlexNet, GoogLeNet, Xception, SqueezeNet and DenseNet201 models, the accuracy of the EResNet‐SVM model has improved by 5.10%, 7%, 8.10%, 6.20% and 1.90%, respectively. The testing accuracy of the EResNet‐SVM model for 6 insect pests is 100%, which is 3.90% higher than that of the original ResNet18 model. CONCLUSION: This research provides not only useful references for alleviating the overfitting problem in deep learning, but also a theoretical and technical support for the intelligent detection and control of plant diseases and pests. © 2024 Society of Chemical Industry. [ABSTRACT FROM AUTHOR]

As genomic selection emerges as a promising breeding method for both plants and animals, numerous methods have been introduced and applied to various real and simulated data sets. Research suggests that no single method is universally better than others; rather, performance is highly dependent on the characteristics of the data and the nature of the prediction task. This implies that each method has its strengths and weaknesses. In this study, we exploit this notion and propose a different approach. Rather than comparing multiple methods to determine the best one for a particular study, we advocate combining multiple methods to achieve better performance than each method in isolation. In pursuit of this goal, we introduce and develop a computational method of the stacked generalization within ensemble methods. In this method, the meta-model merges predictions from multiple base models to achieve improved performance. We applied this method to plant and animal data and compared its performance with currently available methods using standard performance metrics. We found that the proposed method yielded a lower or comparable mean squared error in predicting phenotypes compared to the current methods. In addition, the proposed method showed greater resistance to overfitting compared to the current methods. Further analysis included statistical hypothesis testing, which showed that the proposed method outperformed or matched the current methods. In summary, the proposed stacked generalization integrates currently available methods to achieve stable and better performance. In this context, our study provides general recommendations for effective practices in genomic selection. [ABSTRACT FROM AUTHOR]

Training complex deep neural networks can result in overfitting when the networks are trained from random weight initialization on small datasets. Augmentation helps to reduce the negative effects of overfitting. The findings in computer vision and audio recognition research reveals that the performance of machine learning classifiers is significantly improved when augmentation is used. In the context of ecology, researchers conduct field surveys whereby microphones are placed in some location and audio data is recorded over a period of time. There is however no guarantee that the particular species of interest in the field survey will vocalize frequently near the microphone. Thus, the amount of data captured for the species of interest might be limited, and it may then be the source of overfitting. The main contribution of this paper is in performing experiments with time and frequency masking, and noise addition augmentation techniques in training a visual convolutional neural networks (CNN) repurposed for pattern recognition in acoustic spectrograms. These techniques increased the audio examples for the pin-tailed whydah and the Cape robin-chat to create a robust audio vocalization classifiers. To evaluate the performance of the augmentation techniques we conducted a comparison between experiments run with and without augmentation. We chose to use CNN as our classifier given that they are state-of-the-art in audio recognition tasks and they have revealed good performance. In the used augmentation techniques; time masking achieved 90.2% as the highest testing accuracy while pink noise is the most successful best classifier. [ABSTRACT FROM AUTHOR]

Travel time reliability is known to be a critical issue in the contexts of both travellers' choices and decisions and freight transportation. The temporal variability of travel time is known as reliability and is affected by numerous factors. Traffic volume, incidents and inclement weather are among the most profound factors, and their effects have been the subject of many studies. The work reported in this article is unique due to the simultaneous implementation of a genetic algorithm (GA) with multiple machine learning (ML) methods. A GA can eliminate overfitting, which is a common problem in ML models. The numerical results showed that the performance of the K-nearest neighbours method was significantly enhanced when a GA was imposed on it. In terms of the stability ratio, a 12% decrease was observed; the mean squared errors for the training set and the testing set decreased, but the reductions were not significant. To further illustrate the advantages of GA implementation, the numbers of predictions with a mean absolute percentage error greater than 0.05 were compared and a notable reduction was found. Sensitivity analysis was carried out to determine how the planning time index responds to fluctuations of independent variables. [ABSTRACT FROM AUTHOR]

This paper explores enduring influences on life satisfaction using empirical analysis of World Values Survey (WVS) data (four versions of the most comprehensive dataset, namely 1.6, 2.0, 3.0 and 4.0). Five significant values emerged—financial satisfaction, happiness, freedom of choice, health, and democracy. Through rigorous selection processes and various statistical techniques, a subset of three determinants resulted, along with consecrated socio-demographic variables such as age, gender, marital status, social class, and settlement size. Advanced methodologies such as feature selection, random and non-random cross-validations, overfitting removal, collinearity and reverse causality checks, and different regressions served to evaluate and validate robust models. Nomograms helped to predict life satisfaction probabilities. The findings contribute to understanding life satisfaction dynamics and offer practical insights for future research and policy. [ABSTRACT FROM AUTHOR]

In the contemporary digital era, images are omnipresent, serving as pivotal entities in conveying information, authenticating experiences, and substantiating facts. The ubiquity of image editing tools has precipitated a surge in image forgeries, notably through copy-move attacks where a portion of an image is copied and pasted within the same image to concoct deceptive narratives. This phenomenon is particularly perturbing considering the pivotal role images play in legal, journalistic, and scientific domains, necessitating robust forgery detection mechanisms to uphold image integrity and veracity. While advancements in Convolutional Neural Networks (CNN) have propelled copy-move forgery detection, existing methodologies grapple with limitations concerning the detection efficacy amidst complex manipulations and varied dataset characteristics. Additionally, a palpable void exists in comprehensively understanding and exploiting dataset heterogeneity to enhance detection capabilities. This heralds a pronounced exigency for innovative CNN architectures and nuanced understandings of dataset intricacies to augment detection capabilities, which has remained notably underexplored in the prevailing literature. Against this backdrop, our research broaches novel frontiers in copy-move forgery detection by introducing an innovative CNN architecture meticulously tailored to discern the subtlest manipulations, even amidst intricate image contexts. An extensive analysis of multiple datasets – MICC-F220, MICC-F600, and a combined variant – enables us to delineate a granular understanding of their attributes, thereby shedding unprecedented light on their influences on detection performance. Further, our research goes beyond mere detection, delving deep into comprehensive analyses of varied datasets and conducting additional experiments with differential training-validation sets and randomly labeled data to scrutinize the robustness and reliability of our model. We not only meticulously document and analyze our findings but also juxtapose them against extant models, offering an exhaustive comparative analysis. [ABSTRACT FROM AUTHOR]

Today, skin cancer is considered one of the most dangerous and common cancers in the world, demanding special attention. Skin cancer can be developed in different types, including melanoma, actinic keratosis, basal cell carcinoma, squamous cell carcinoma, and Merkel cell carcinoma. Among them, melanoma is considered to be more unpredictable. However, melanoma cancer can be diagnosed at early stages, which increases the possibility of successful treatment. Automatic classification of skin lesions is a challenging task due to diverse forms and grades of the disease, which demands the implementation of novel methods. Deep convolutional neural networks (CNNs) have shown an excellent potential for data and image classification. In this article, we examine the problem of skin lesion classification using CNN techniques. Remarkably, we present that prominent classification accuracy of lesion detection can be achieved through proper design and application of transfer learning framework on pre-trained neural networks. This can be accomplished without the need for data augmentation techniques; specifically, we merged the core architectures of VGG16 and VGG19, which were pretrained on a generic dataset, into a modified AlexNet network. We then fine-tuned this combined architecture using a subject-specific dataset consisting of dermatology images. The convolutional neural network was trained using 2541 images. In particular, dropout was employed to mitigate overfitting. Finally, we assessed the model's performance by applying the K-fold cross validation method. The proposed model improved classification accuracy with an increase of 3% (from 94.2% to 98.18%) compared to other methods. [ABSTRACT FROM AUTHOR]

Copyright of Computer Measurement & Control is the property of Magazine Agency of Computer Measurement & Control and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Artificial intelligence (AI) and machine learning (ML) aim to mimic human intelligence and enhance decision making processes across various fields. A key performance determinant in a ML model is the ratio between the training and testing dataset. This research investigates the impact of varying train-test split ratios on machine learning model performance and generalization capabilities using the BraTS 2013 dataset. Logistic regression, random forest, k nearest neighbors, and support vector machines were trained with split ratios ranging from 60:40 to 95:05. Findings reveal significant variations in accuracies across these ratios, emphasizing the critical need to strike a balance to avoid overfitting or underfitting. The study underscores the importance of selecting an optimal train-test split ratio that considers tradeoffs such as model performance metrics, statistical measures, and resource constraints. Ultimately, these insights contribute to a deeper understanding of how ratio selection impacts the effectiveness and reliability of machine learning applications across diverse fields.