ABSTRACT In cancer genomics research, feature selection (FS) of high‐dimensional gene expression data is of great significance to improve classification accuracy and reduce feature number. Aiming at the limitations of traditional transfer functions, such as nonadaptability and being prone to fall into local optimum when dealing with high‐dimensional data, a parallel dynamic adaptive transfer function based on population diversity is proposed. Firstly, a universal mirror symmetric inversion strategy is proposed based on five different types of transfer function (TF) families. Compared with the basic TFs, the proposed strategy considers more possibilities for particles in both positive and negative directions, improving the algorithm's ability to escape local optimum. Then, time‐varying factors were taken into account, enabling adaptive adjustment of various TFs. Finally, considering the influence of algorithm population diversity, the population evolution degree (PED) was defined. A dynamic adaptive TF based on population diversity was proposed. Through PED, the TF was dynamically and adaptively adjusted to achieve better binary conversion, enhancing the exploitation and exploration capabilities of the algorithm. In the wrapper FS method, SHO was adopted as the optimizer. The proposed method enables the binary mapping of the algorithm to dynamically adaptively change during the iterative process. Eventually, it adjusts the TF mapping capability for the next iteration based on its own fitness value. In the experimental part, the performance of the proposed strategy was first tested and verified through nine UCI datasets. The results showed that ITV‐VrV1 could achieve better fitness, improve accuracy and effectively reduce the number of features. Then, ITV‐VrV1 was extended to the cancer gene expression datasets. By comparing it with other binary algorithms, it was found that ITV‐VrV1 achieved the lowest average fitness and the highest average classification accuracy on all datasets. According to the Friedman test and Wilcoxon test, it was proved that ITV‐VrV1 ranked first in terms of average fitness and average classification accuracy, ranked second in terms of average number of selected features and showed significant differences from other comparison methods. It can effectively solve the problem of FS for high‐dimensional cancer data.
ABSTRACT Diabetic retinopathy (DR) and diabetic macular edema (DME) are eye‐related diseases most commonly seen in persons with diabetes. Existing models did not achieve the desired level of accuracy or success in distinguishing DR and DME. Thus, by resolving this issue, the performance and accuracy of automated classification systems are significantly improved. Therefore, a transfer learning model is developed to simultaneously classify DR and DME grades in retinal images. Initially, the input retinal fundus images are collected from standard databases. These images are given to the proposed Transfer Learning‐based Adaptive Fused Convolutional Neural Networks (TL‐AFCNN). This model fusion is created by using a Residual Attention Network (RAN) with multidilated DenseNet techniques. In order to improve the effectiveness of simultaneous classification using TL‐ACNN, the weights from this network are fine‐tuned via the Fitness Oriented Lotus Effect Optimization Algorithm (FO‐LEA). From, the developed TL‐ACNN model, simultaneous grade classification outcomes of both DR and DME are attained. Therefore, the risk of vision loss is treated effectively by analyzing the grade‐classified outcomes from the proposed model. Finally, the simultaneous classification results attained by the suggested model are compared with existing models to verify its potential.
ABSTRACT The revenue generated from online ads has become quite significant, and as with the advancement in any sort of business, this one brings fraudsters with it. However, different forms of fraud can be performed as this work tackles the problems of click fraud in advertisements. In this case, the fraud can be performed by the party that bought the advertisement to boost its revenue, or by other malicious parties that tend to exhaust the resources for the said ad, for example. Due to this and many other scenarios, a robust solution for detecting such cases must be established. However, existing click fraud detection approaches either rely on static rule‐based systems or deep learning models with manually tuned hyperparameters, which may result in limited adaptability and suboptimal performance in complex sequential environments. Therefore, there is a need for an adaptive optimization strategy capable of effectively tuning sequential models for improved fraud detection accuracy. This work proposes three different types of recurrent neural networks (RNNs) that are combined with the attention mechanism. Furthermore, in each of the three different experiments, the networks were optimized by strong metaheuristics optimizers, the results of which were compared to establish the strongest one. This was done with the purpose of confirming the improvements to the variable neighborhood search (VNS) algorithm, which was proposed by the authors in this work. The best synthesized RNN model tuned by the suggested modified optimizer attained accuracy of 0.806569, with Matthews correlation coefficient of 0.613209.
This research expands upon our previous work on few-shot learning for multiclass classification on tabular data. Expanding on the FSL-LFMG framework, which integrates latent feature augmentation, advanced STUNT multitasking generation, and Prototypical Networks, we aim to illustrate the architecture’s flexibility in adapting to new concept tasks. Our prior research demonstrated the efficacy of FSL-LFMG in few-shot multiclass classification, outperforming traditional Tree Ensemble models and One-vs-the-rest classifiers. This research further investigates the framework’s generalization capabilities by applying it to a new concept tasks, specifically predicting customer loyalty levels based on an existing NPS segmentation model. Experimental results demonstrate substantial performance in both 1-shot and 5-shot configurations, attaining mean test accuracies of 83.95
In recent years, Deep Learning (DL) models have shown excellent results in various fields, including healthcare, but their “opaque” nature limits their trust and adoption in critical contexts. In this work, we present XAIMed2.0, an application designed to support healthcare professionals in interpreting the decisions of CNN models applied to medical image analysis. The application integrates several eXplainable AI (XAI) techniques to offer different visual explanations. The application integrates multiple eXplainable AI (XAI) techniques to generate visual explanations. Specifically, it employs several saliency map methods (Grad-CAM, Grad-CAM++, RISE, and LIME) and merges them into a cumulative visualization that highlights the regions of highest consensus across methods. To complement the visual explanations, the system uses a Large Language Model (LLM) to generate textual explanations in natural language, capable of contextualizing the results, highlighting discrepancies, and improving clinician understanding.
