Retraction: M.M. Kumar , A.A. Rani , V. Sundaravazhuthi , “,” Computational Intelligence 36 , no. ( 2020 ): 1493 – 1511 , https://doi.org/10.1111/coin.12282 . The above article, published online on 05 February 2020 in Wiley Online Library ( wileyonlinelibrary.com ), has been retracted by agreement between the Editor‐in‐Chief, Diana Inkpen; and Wiley Periodicals LLC. The article was published as part of a guest‐edited special issue. Following publication, it came to our attention that the individuals named as Guest Editors of this issue were impersonated by a fraudulent entity. An investigation by the publisher found that all the articles, including this one, were accepted solely on the basis of a compromised peer review process. Therefore, a decision has been made to retract this article. The authors have been informed of the decision to retract.

Retraction: A. Selvaraj , J. Selvaraj , S. Maruthaiappan , G. C. Babu , P. M. Kumar , “,” Computational Intelligence 36 , no. ( 2020 ): 1569 – 1579 , https://doi.org/10.1111/coin.12292 . The above article, published online on 22 February 2020 in Wiley Online Library ( wileyonlinelibrary.com ), has been retracted by agreement between the Editor‐in‐Chief, Diana Inkpen; and Wiley Periodicals LLC. The article was published as part of a guest‐edited special issue. Following publication, it came to our attention that the individuals named as Guest Editors of this issue were impersonated by a fraudulent entity. An investigation by the publisher found that all the articles, including this one, were accepted solely on the basis of a compromised peer review process. Therefore, a decision has been made to retract this article. The authors do not agree with the retraction.

Retraction: B. Ponmudi , G. Balasubramanian , “,” Computational Intelligence 36 , no. ( 2020 ): 1723 – 1736 , https://doi.org/10.1111/coin.12311 . The above article, published online on 05 March 2020 in Wiley Online Library ( wileyonlinelibrary.com ), has been retracted by agreement between the Editor‐in‐Chief, Diana Inkpen; and Wiley Periodicals LLC. The article was published as part of a guest‐edited special issue. Following publication, it came to our attention that the individuals named as Guest Editors of this issue were impersonated by a fraudulent entity. An investigation by the publisher found that all the articles, including this one, were accepted solely on the basis of a compromised peer review process. Therefore, a decision has been made to retract this article. The authors have been informed of the decision to retract.

ABSTRACT Sequence alignment is one of the fundamental concepts in bioinformatics used in genome assembly, molecular evolution, and drug designing. Traditional algorithms like Needleman–Wunsch (NW) and Smith–Waterman (SW) are precise but computationally expensive. This renders them impractical whenever dealing with large‐scale datasets resulting from next‐generation sequencing (NGS) technologies. Towards addressing this challenge, we propose BioAlignNet, a novel GPU‐accelerated framework designed for efficient global sequence alignment of DNA/RNA/Protein sequences. BioAlignNet utilizes graph theory to model the alignments as shortest‐path problems in directed weighted graphs. Through incorporating an optimized and parallel edge weight computation and a parallel Shortest Path Faster Algorithm (SPFA), the framework achieves low computational complexity of where and are the lengths of the input sequences, and is the number of GPU threads per block. Rather than introducing a new alignment scoring scheme, BioAlignNet contributes a formally verified execution model for exact global alignment by recasting dynamic programming as a shortest‐path problem whose correctness is preserved under asynchronous GPU parallelism. Along with the low computational complexity, the framework also maintains biological integrity. Promising innovations include the implementation of the modular concept to accommodate different sequence types, substitution matrices, and scoring schemes, CUDA‐based parallelism of edge weight calculation, and traceback methods to build accurate alignments. BioAlignNet's evaluations conducted on various datasets show a remarkable runtime enhancement reaching up to 177 times speedup over CPU implementations, maintaining alignment optimality while giving better coverage and percentage identity. Experimental evaluations on real‐world datasets and validations through statistical significance tests demonstrate its scalability and robustness, making it suitable for genomics and proteomics. With its incorporation of biological relevance and computational optimization, BioAlignNet offers an efficient method for the alignment of large‐scale genome sequences to promote the development of molecular biology research.

ABSTRACT In this paper, to enhance the control precision and robustness of continuum robots against noise‐induced joint drift and positioning errors encountered in complex environments, a noise‐tolerant zeroing neural network (NTZNN) based control method is proposed. Starting from the kinematic characteristics of continuum robots, a spatial kinematics model is established, formulating the joint‐space‐to‐task‐space mapping. Then, a second‐order error dynamics formulation incorporating integral compensation is constructed. Leveraging the second‐order formulation, the NTZNN model is developed to derive the joint velocity control law. Furthermore, to mitigate computational complexity and address the singularity problem, an auxiliary matrix is introduced for efficient inverse estimation in the control law implementation. Theoretical analyses conclusively verify the feasibility of the NTZNN‐based control scheme and its robust performance characteristics for high‐precision control of continuum robots. Finally, the superior performance of the proposed control scheme in trajectory tracking accuracy, noise suppression, and real‐time performance is verified through simulation experiments of a three‐link continuum robot manipulator.

ABSTRACT The protection of crops from pests is essential for sustainable agriculture and global food security. Traditional pest identification techniques that are based on visual examination are time‐consuming and prone to errors. Recent developments in the field of artificial intelligence (AI) and specifically deep learning (DL) enabled pests to be detected accurately and automatically. This review systematically examines DL‐based approaches, including Convolutional Neural Networks (CNNs), Transformer models, ensemble methods, and Graph Neural Networks (GNNs), for pest classification, with an emphasis on benchmark datasets, model architectures, and evaluation metrics. Transformer models, such as GNViT, achieved 99.52% accuracy and a 90.9% F1‐score on the IP102 dataset, which is approximately 10% higher than the CNNs. The Vision Transformer (ViT) model achieved 96.7% accuracy on PlantVillage. The ensemble model, like GAEnsemble, achieved excellent accuracies of 98.81% and 95.16% on D0 and SCD, respectively. CNN models had relatively lower performance on the IP102, and the GNNs showed poor performance (below 60%). This paper discusses prospective methodological enhancements, current limitations, and future prospects for developing scalable, understandable, and multi‐domain pest classification systems.

ABSTRACT Opinion summarization aims to refine opinions from large‐scale reviews, often using select‐then‐summary methods. Due to the length limitation of the input, only a small number of samples are usually selected for the summarization model, with the risk of ignoring global opinion information such as product aspects and user sentiments. Topic modeling can unsupervisedly extract topic words from texts, holding the potential for capturing global opinion. Therefore, we propose Depictor , a topic‐guided two‐stage opinion summarization approach with dual‐perspective topic modeling (BERTopic and Latent Dirichlet allocation). The dual‐perspective topic modeling extracts topic words from both semantic and statistical perspectives. Then the extracted topic information is incorporated into the generator in two ways. For the input side, the topic words are concatenated with the subset reviews from the extractor as supplementary keyword information. For the representation side, an additional topic‐driven attention mechanism focusing on the topic words is added to enable the summarization model to pay extra attention to aspect‐related keywords during the generation. Experimental results on AmaSum show that the proposed topic‐augmented method outperforms several strong baselines, indicating its effectiveness in opinion summarization.

ABSTRACT Autonomous driving decision‐making requires a deep semantic understanding of traffic scenes. In this paper, we propose the SGVLM (Semantic Graph Vision‐Language Model) architecture: a vision‐language model that enhances autonomous driving decision‐making through depth‐integrated semantic scene graph fusion. Key objects are represented as nodes (category, state) and spatial‐semantic relations as edges, enriched with pixel‐wise depth estimates from Depth‐Anything‐V2 to capture accurate inter‐object distances. These structured graph features are aggregated via a two‐layer Graph Attention Network and projected into the FastVLM's FastViTHD feature space. A cross‐modal triplet fusion layer then jointly integrates graph embeddings, visual features, and natural‐language queries. Crucially, to ensure computational efficiency without compromising the generalization power of the large‐scale backbone, we employ Low‐Rank Adaptation (LoRA), which significantly reduces the number of trainable parameters and accelerates convergence while maintaining pre‐trained performance. Empirical validation on the DriveLM‐nuScenes benchmark demonstrates that SGVLM_7B achieves relative improvements of 25.9% in BLEU‐4 and 18.6% in ROUGE‐L over the InternVL4Drive‐v2 baseline, and attains 94.56% accuracy on collision‐warning decision tasks in our TTSG‐data safety‐critical scenarios. These results confirm that depth‐integrated semantic scene graph fusion substantially enhances the model's ability to generate actionable driving decisions under complex traffic conditions.

ABSTRACT The majority of individuals in the modern world struggle with psychological sickness, which also contributes to a wide variety of physical weaknesses. Depression has become a prevalent disease that affects the mental state of individuals, and most people are suffering from it due to a lack of diagnosis and awareness. Sometimes, depression may lead to sleeping disorders, self‐harm, and recklessness. For recognizing the depressed people, numerous researchers have developed machine learning (ML) based frameworks through interviews with patients. However, those methods have inaccurate detection accuracy and possess poor efficiency. Thus, it is very challenging to identify individuals who are affected by depression. So, a novel deep learning (DL) assisted depression detection framework is proposed in this research on the DAIC‐WOZ dataset. The pre‐processed audio signals are augmented using a hybrid Synthetic Minority Oversampling Technique (SMOTE) assisted Conditional Generative Adversarial Network (cGAN) to increase the number of samples. A novel dilated convolutional integrated absolute encoding based vision transformer with Frequency Self‐attention (DCA‐AViT) is introduced for extracting deep features. Further, handcrafted extracted features are fused using a soft attention layer to provide better feature representations. For classifying the depression, a locality attention based fully connected Shuffle‐Net (LA‐FCS) is proposed, which detects the psychological distress conditions. Experimental findings of the proposed depression detection attained better performance improvements in accuracy of 98.40%, precision of 98.45%, recall of 98.41%, specificity of 99.58%, and F1‐Score of 98.43% which demonstrated the efficacy of the proposed model. Moreover, performance validation of the proposed technique outperformed all existing baseline models in depression detection.