Accurately detecting cancer through gene expression analysis is crucial for early diagnosis and effective treatment. However, gene expression data's high dimensionality and redundancy pose significant challenges, such as overfitting and computational inefficiency. To address these issues, we propose a hybrid feature selection framework that integrates a filter-wrapper approach with swarm intelligence for optimized gene selection. The proposed method utilizes the Nomadic People Optimizer (NPO) in conjunction with Mutual Information (MI) to identify a relevant subset of genes from high-dimensional datasets. An optimized Support Vector Machine (SVM) is employed to further enhance classification accuracy, with its hyperparameters fine-tuned using an enhanced Salp Swarm Algorithm (SSA) incorporating a crossover operator. This hybrid approach not only reduces the search space but also mitigates overfitting by leveraging the exploration and exploitation capabilities of the NPO and SSA. Experimental results on five cancer gene expression datasets-lung adenocarcinoma (LUAD), breast cancer (GSE2034), glioblastoma multiforme (GBM), ovarian cancer (GSE2109), and colorectal adenocarcinoma (COAD)-demonstrate that the proposed NPO-SSVM achieves classification accuracies ranging from 91.25% to 97.02% with AUC-ROC values between 0.85 and 0.97. The framework achieves an average feature reduction of 51% while outperforming state-of-the-art methods (GA, PSO, GWO, SSA) by 3-12% in classification accuracy and 15% in computational efficiency. These findings confirm that NPO-SSVM provides a robust and efficient solution for gene selection in cancer detection, offering significant advancements for personalized medicine and early diagnosis.

Clustering is an unsupervised learning task that groups data points by their inherent similarities. Nonautomatic clustering algorithms face significant challenges when the true number of clusters is unknown or changes dynamically, as they require this number to be predefined. This paper provides a comprehensive review of automatic clustering algorithms specifically designed to handle such uncertainty. In this paper, these algorithms are systematically classified based on three key perspectives: clustering framework (classical vs. deep), clustering strategy (e.g., density-based, model based, graph-theoretic, subspace methods), and the use of labeled data (unsupervised vs. semi-supervised). We analyze each algorithm based on its core principles, key contributions, strengths, and limitations. Furthermore, we address the current challenges in this area and propose future research directions to enhance the scalability, robustness, and effectiveness of automatic clustering algorithms.

Variational graph auto-encoders (VGAEs) are a key tool for node clustering, but existing models face several significant challenges. These challenges include a mismatch between inference and generative models after incorporating the clustering inductive bias, as well as posterior collapse (PC), where latent representations become overly influenced by the prior distribution. In addition, in existing VGAEs, noisy clustering assignments lead to the feature randomness (FR) challenge, while the strong tradeoff between clustering accuracy and reconstruction quality results in the feature drift (FD) problem. To address these issues, we propose a multiscale contrastive VGAE (MCVGAE). This multiscale model combines cluster-level and graph-level contrastive learning with proximity-level and cluster-level self-supervised methods. MCVGAE improves the alignment between the hidden space and the data distribution and prevents PC. Moreover, it reduces FR and FD more effectively than existing techniques. Achieving impressive accuracy scores of 79.09% on Cora, 90.04% on ACM, 75.12% on Pubmed, 72.7% on Citeseer, 74.11% on DBLP, and 59.79% on Wiki clearly demonstrates the superiority of MCVGAE over 30 state-of-the-art methods.

ABSTRACT Gene selection is critical for cancer diagnosis because the ability to discover specific biomarkers has a major impact on diagnostic accuracy. Traditional approaches frequently struggle with high‐dimensional genomic data, where irrelevant or redundant characteristics might impair machine learning algorithms. Despite advances in computational approaches, there is a gap in the optimization of deep learning models for gene selection, particularly in terms of selecting the best model architecture and hyperparameters. This paper addresses three critical challenges in genomic biomarker discovery for cancer diagnosis: (1) the high‐dimensional nature of gene expression data, (2) the need for biologically interpretable feature selection, and (3) the optimization of deep learning architectures for genomic analysis. We present a novel hybrid approach combining modified genetic algorithms with deep neural networks to overcome limitations of traditional methods in handling feature redundancy and computational complexity. Our methodology introduces three key innovations: a dynamic mutation operator that adapts to population diversity, multi‐objective optimization balancing classification accuracy with biological pathway relevance, and simultaneous co‐evolution of both gene subsets and neural network architectures. The proposed system achieves state‐of‐the‐art performance, with 99.1% accuracy, 98.9% AUC‐ROC, and 99.0% F1‐score on the ISIC 2020 dataset, while maintaining clinically relevant sensitivity (98.0%) and specificity (98.5%). Extensive validation across six benchmark datasets demonstrates consistent improvements over existing machine learning and deep learning techniques, particularly in handling rare cancer subtypes and low‐resolution images. Future research directions include: (1) integration of multi‐modal clinical data to enhance rare subtype detection, (2) development of federated learning frameworks for privacy‐preserving distributed analysis, and (3) creation of explainability tools to bridge the gap between computational feature selection and clinical interpretation. The results establish our evolutionary optimization approach as both a high‐performance diagnostic tool and a flexible framework for advancing precision oncology research.

Anomaly detection (AD) has witnessed substantial advancements in recent years due to the increasing need for identifying outliers in various engineering applications that undergo environmental adaptations. Consequently, researchers have focused on developing robust AD methods to enhance system performance. The primary challenge faced by AD algorithms lies in effectively detecting unlabeled abnormalities. This study introduces an adaptive evolutionary autoencoder (AEVAE) approach for AD in time-series data. The proposed methodology leverages the integration of unsupervised machine learning techniques with evolutionary intelligence to classify unlabeled data. The unsupervised learning model employed in this approach is the AE network. A systematic programming framework has been devised to transform AEVAE into a practical and applicable model. The primary objective of AEVAE is to detect and predict outliers in time-series data from unlabeled data sources. The effectiveness, speed, and functionality enhancements of the proposed method are demonstrated through its implementation. Furthermore, a comprehensive statistical analysis based on performance metrics is conducted to validate the advantages of AEVAE in terms of unsupervised AD.

Abstract Internet of Medical Things have vastly increased the potential for remote patient monitoring, data‐driven care, and networked healthcare delivery. However, the connectedness lays sensitive patient data and fragile medical devices open to security threats that need robust intrusion detection solutions within cloud‐edge services. Current approaches need modification to be able to handle the practical challenges that result from problems with data quality. This paper presents a hybrid intrusion detection framework that enhances the security of IoMT networks. There are three modules in the design. First, an XGBoost‐based noise detection model is used to identify data anomalies. Second, adaptive resampling with ADASYN is done to fine‐tune the class distribution to address class imbalance. Third, ensemble learning performs intrusion detection through a Random Forest classifier. This stacked model coordinates techniques that filter noise and preprocess imbalanced data, identifying threats with high accuracy and reliability. These results are then experimentally validated on the UNSW‐NB15 benchmark to demonstrate effective detection under realistically noisy conditions. The novel contributions of the work are a new hybrid structural paradigm coupled with integrated noise filtering, and ensemble learning. The proposed advanced oversampling with ADASYN gives a performance that surpasses all others with a reported 92.23% accuracy.

Abstract Given that super‐resolution (SR) aims to recover lost information, and low‐resolution (LR) images in real‐world conditions might be corrupted with multiple degradations, considering basic bicubic down‐sampling as the sole degradation significantly limits the performance of most existing SR models. This paper presents a model for simultaneous super‐resolution and blind additive white Gaussian noise (AWGN) denoising with two components (netdeg and netSR) that is based on a generative adversarial network (GAN) to achieve detailed results. netdeg, featuring residual and innovative cost‐effective ghost residual blocks with a frequency separation module for obtaining long‐range information, blindly restores a clean version of the LR image. netSR leverages slim ghost full‐frequency residual blocks to process low‐frequency (LF) and high‐frequency (HF) information via static large convolutions and pixel‐wise highlighted input‐adaptive dynamic convolutions, respectively. To address the susceptibility of dynamic layers to noise and preserve feature diversity while reducing model’s costs, static and dynamic layer features are combined and highlighted. Diverse and non‐redundant features are then processed using ghost‐style blocks. The proposed model achieves comparable SR results in bicubic down‐sampling scenarios, outperform existing SR methods in the complex task of concurrent SR and AWGN denoising, and demonstrate robustness in handling images corrupted with varying levels of AWGN.

Abstract This paper introduces a new descriptor called orientation‐magnitude response maps as a single 2D image to effectively explore motion patterns. Moreover, boosted multi‐stream CNN‐based model with various attention modules is designed for human action recognition. The model incorporates a convolutional self‐attention autoencoder to represent compressed and high‐level motion features. Sequential convolutional self‐attention modules are used to exploit the implicit relationships within motion patterns. Furthermore, 2D discrete wavelet transform is employed to decompose RGB frames into discriminative coefficients, providing supplementary spatial information related to the actors actions. A spatial attention block, implemented through the weighted inception module in a CNN‐based structure, is designed to weigh the multi‐scale neighbours of various image patches. Moreover, local and global body pose features are combined by extracting informative joints based on geometry features and joint trajectories in 3D space. To provide the importance of specific channels in pose descriptors, a multi‐scale channel attention module is proposed. For each data modality, a boosted CNN‐based model is designed, and the action predictions from different streams are seamlessly integrated. The effectiveness of the proposed model is evaluated across multiple datasets, including HMDB51, UTD‐MHAD, and MSR‐daily activity, showcasing its potential in the field of action recognition.

Abstract Nowadays, it is necessary that users have access to information in a concise form without losing any critical information. Document summarization is an automatic process of generating a short form from a document. In itemset‐based document summarization, the weights of all terms are considered the same. In this paper, a new approach is proposed for multidocument summarization based on weighted patterns and term association measures. In the present study, the weights of the terms are not equal in the context and are computed based on weighted frequent itemset mining. Indeed, the proposed method enriches frequent itemset mining by weighting the terms in the corpus. In addition, the relationships among the terms in the corpus have been considered using term association measures. Also, the statistical features such as sentence length and sentence position have been modified and matched to generate a summary based on the greedy method. Based on the results of the DUC 2002 and DUC 2004 datasets obtained by the ROUGE toolkit, the proposed approach can outperform the state‐of‐the‐art approaches significantly.