ABSTRACT Pattern recognition and image segmentation are challenging tasks in computer vision, with applications ranging from object detection to medical imaging. Fuzzy comparison measures emerge as an effective tool in handling these tasks, especially when two feature spaces are associated with uncertainty. Recently, many fuzzy comparison measures have been proposed and applied to different kinds of real-life problems. However, these measures have certain drawbacks because of their incapability to classify very similar pairs of objects, which may not produce effective results in the problems related to pattern recognition and image segmentation. This paper investigates the derivation of new fuzzy similarity measures. The proposed measures bear a continuous nature, allowing for subtle differences and smooth transitions between levels of similarity. This characteristic enhances the precise interpretation of linguistic variables. Moreover, pattern recognition and image segmentation techniques that primarily utilised proposed fuzzy similarity measures have been developed. Certain patterns and images are considered for the implementation of the proposed techniques. The results revealed that the proposed measures are advantageous over existing similarity measures, highlighting their potential for improving performance in pattern recognition and image segmentation.

ABSTRACT The intricacy of the underwater setting makes it difficult for optical lenses to capture clear underwater photos without haze and colour distortion. Some studies use domain adaptation and transfer learning to address this issue, they aim to reduce the latent mismatch between composition and real-world data, making the space of latent data difficult to read and impractical to control. The background light is a crucial component of the decaying paradigm that directly impacts how well images are enhanced. Thus, to improve the quality of the images over the underwater, new deep-learning techniques are being designed in this paper. Here, the Adaptive Trans-ResUnet++ with Attention Mechanism-based model performs the real-time underwater image enhancement process. In addition, a novel Random Enhanced Artificial Gorilla Troops Optimizer algorithm model is used for optimising the parameters over the given model to further enhance the given model’s performance. A diverse quantitative and qualitative validation is also carried out to learn the enhancement of underwater image quality. The enhanced underwater image may be also useful in the underwater object detection process. Thus, the enhanced images obtained from the developed model are compared with the existing techniques to confirm the efficacy of the suggested underwater image enhancement process.

ABSTRACT Byzantine Fault Tolerance (BFT) is crucial for ensuring the resilience of Distributed Machine Learning (DML) systems during training under adversarial conditions. Among the rising corpus of research on BFT in DML, there is no comprehensive classification of techniques or broad analysis of different approaches. This paper provides an in-depth survey of recent advancements in BFT for DML, with a focus on first-order optimisation methods, particularly, the popular one Stochastic Gradient Descent (SGD) during the training phase. We offer a novel classification of BFT approaches based on characteristics such as the communication process, optimisation method, and topology setting. This classification aims to enhance the understanding of various BFT methods and guide future research in addressing open challenges in the field. This work provides the foundations for developing robust BFT systems, using a variety of optimisation methods to strengthen resilience.

ABSTRACT The efficacy of e-commerce conversion rates relies on precise and personalized product recommendations within recommendation systems (RS). While collaborative filtering-based RS has demonstrated success, challenges such as sparsity and cold-start issues in the user-item matrix can impede optimal functionality. To address these challenges, there is a need to integrate additional information sources, encompassing item/user profiles and textual reviews. This study introduces an innovative RS architecture that seamlessly combines self-supervised learning (SSL) and collaborative filtering techniques with BERT-DNN to surmount these obstacles. The distinctiveness of our approach lies in integrating self-supervised learning with collaborative filtering and contextualized data obtained from BERT-DNN, providing a profound understanding of item profiles to enhance comprehension of user preferences and item characteristics. This refined understanding, operational in conjunction with collaborative filtering models like ItemKNN and UserKNN, empowers the system to generate highly personalized recommendations. The proposed method entails several pivotal steps: developing the BERT language model for textual embeddings in item profiles, conducting dimensionality reduction, constructing a Deep Neural Network, implementing self-supervised learning with both UserKNN and ItemKNN CF methods, and employing an ensemble learning technique. Empirical results substantiate the efficacy of our approach, with a specific focus on the innovative fusion of BERT-DNN with self-supervised learning and KNN CF methodologies, showcasing substantial improvements across diverse performance metrics. This underscores the practical importance of leveraging contextualized BERT-DNN data, strengthening the recommendation mechanism, and ultimately enhancing the overall performance of the RS.

ABSTRACT Multimodal medical image fusion aims to aggregate significant information based on the characteristics of medical images from different modalities. Existing research in image fusion faces several major limitations, including a scarcity of paired data, noisy and inconsistent modalities, a lack of contextual relationships, and suboptimal feature extraction and fusion techniques. In response to these challenges, this research proposes a novel adaptive fusion approach. Our knowledge distillation (KD) model extracts informative features from multimodal medical images using various key components. A teacher network is employed to emphasise the suitability and complexity of capturing high-level abstract features. The soft labels are utilised to transfer the knowledge between the teacher network as well as the student network. During student network training, we minimise the divergence between these soft labels. To enhance the adaptive fusion of extracted features from different modalities, we apply a self-attention mechanism. Training this self-attention mechanism minimises the loss function, encouraging attention scores to capture relevant contextual relationships between features. Additionally, a cross-modal consistency module aligns the extracted features to ensure spatial consistency and meaningful fusion. Our adaptive fusion strategy effectively combines features to enhance the diagnostic value and quality of fused images. We employ generator and discriminator architectures for synthesising fused images and distinguishing between real and generated fused images. Comprehensive analysis is conducted on the basis of diverse evaluation measures. Experimental results demonstrate improved fusion outcomes with values of 0.92, 41.58, 7.25, 0.958, 0.759, 0.947, 0.90, 7.05, 0.0726, and 76 s for SSIM, PSNR, FF, VIF, UIQI, FMI, EITF, entropy, RMSE, and execution time, respectively.

ABSTRACT The rapid development of industry intelligence has promoted the importance of sorting robots, but the shortcomings of sorting tasks are also gradually obvious. The target detection of the sorting robot in the process of sorting and grasping is affected by the anchor frame setting, and its grasping efficiency and recognition effect are low. Therefore, a detection network based on an anchor frame-free regression algorithm is proposed in this study, and a positioning and grasping method of the sorting robot based on the Deep Belief Network (DBN) algorithm is proposed. The algorithm experiment shows that the prediction accuracy of the proposed anchor-free detection network in the PASCAL VOC dataset reaches 92.91, significantly higher than that of other detection networks. In addition, the sorting robot was researched and designed with high accuracy in occlusion target recognition. When the occlusion area reaches 70%, the accuracy rate is as high as 81.26%, which is far higher than other detection schemes. The above results show that in improving the sorting robot’s target recognition ability, the anchor-free detection network can significantly improve its recognition accuracy. At the same time, introducing the DBN network can improve the robot’s recognition ability for occluded targets, which is of great significance to the development of the sorting robot and the intelligent industry.

ABSTRACT Content Based Image Retrieval (CBIR) plays a significant role in identifying the similarity of images with large datasets. It is identified based on the size, colour, and texture features of the image. But in such conditions, it is complex to determine the features of query images in large datasets and does not show accurate similarity when compared with every image in the retrieval process. In order to perform an efficient similarity of images, a novel Machine Learning (ML) approach Kernelized Radial Basis Auto-Encoder Function Neural Network (Ker_RadBAEFNN) technique is proposed that performs the individual image classification in the retrieval process. Moreover, the neural networks are optimised based on the reinforcement process and perform the extraction process regarding individual images. Further,reinforcement-based optimisation estimates the images in neural networks for undertaking an automatic feature extraction of query images. The performance of the classification process is validated based on MNIST, METU, and COCO datasets that determined the efficiency of the recognition and classification process of image retrieval. The experimental analysis is carried out based on various measures such as accuracy, precision, recall, F1-score, RMSE, and MAPE for the proposed and existing GLCM-ABC, PSO-ANN, IRB-CNN, FAGWO, and OCAM methods. The analysis shows that the performance of the proposed attained better effectiveness with attained accuracy by 98% and diminished for state-of-the-art techniques as 92%, 95%, 94%, 96.8%, as well as 96%, respectively. Compared to existing methods, the accuracy rate of the proposed method is maximised by 1.3%.

ABSTRACT Nowadays, sentiment analysis is concerned with identifying and analysing text sentiment. Sentiment analysis has been used in many fields because of its applications in various domains. In the last decade, with the success of machine learning and deep learning methods, many machine- and deep-based sentiment classification have been developed and performed well on various issues. Moreover, word embeddings are important for machine learning and deep learning models since they provide input features in downstream language tasks. This paper presents a comprehensive review of word embeddings and deep learning models. Additionally, we conduct an experimental study of sentiment classification using various deep learning models and word embeddings, in which five deep learning models with four embedding techniques are compared on eight benchmark datasets. In other words, 20 models are evaluated on datasets. Finally, we discuss the performance of models from different perspectives.

ABSTRACT Feature selection plays an essential role in enhancing the efficiency and effectiveness of machine learning models, particularly in the context of large-scale datasets where the dimensionality of features presents significant challenges. This research presents a novel approach to feature selection, a critical aspect of enhancing machine learning model efficiency, particularly in the context of large-scale datasets. By integrating the Flamingo Search Algorithm (FSA), Non-dominated Sorting Genetic Algorithm III (NSGA-III), and Regularised Extreme Learning Machine (RELM), the proposed method addresses limitations in existing feature selection and multi-objective optimisation algorithms. Leveraging FSA’s emulation of flamingo behaviours, the approach achieves a balance between global exploration and local exploitation, mitigating issues like premature convergence and local optima. Integration with NSGA-III enhances multi-objective optimisation capabilities, maintaining a delicate equilibrium between convergence and diversity. FSA-RELM is employed for accurate feature assessment, given its rapid learning and suitability for large datasets with multiple labels. Experimental evaluations demonstrate the proposed method’s superiority in feature selection accuracy, classification performance, and computational efficiency compared to existing approaches. This research contributes to advancing feature selection methodologies, offering a comprehensive solution for high-dimensional datasets in machine learning and data mining applications.