Breast cancer remains the most prevalent cancer among women, where accurate and interpretable analysis of pathology images is vital for early diagnosis and personalized treatment planning. However, conventional single-network models fall short in balancing both performance and explainability—Convolutional Neural Networks (CNNs) lack the capacity to capture global contextual information, while Transformers are limited in modeling fine-grained local details. To overcome these challenges and contribute to the advancement of Explainable AI (XAI) in precision cancer diagnosis, this paper proposes MVT-OFML (Multi-View Transformer Online Fusion Mutual Learning), a novel and interpretable classification framework for breast cancer pathology images. MVT-OFML combines ResNet-50 for extracting detailed local features and a multi-view Transformer encoding module for capturing comprehensive global context across multiple perspectives. A key innovation is the Online Fusion Mutual Learning (OFML) mechanism, which enables bidirectional knowledge sharing between the CNN and Transformer branches by aligning both intermediate feature representations and prediction logits. This mutual learning framework enhances performance while also producing interpretable attention maps and feature-level visualizations that reveal the decision-making process of the model—promoting transparency, trust, and clinical usability. Extensive experiments on the BreakHis and BACH datasets demonstrate that MVT-OFML significantly outperforms the strongest baseline models, achieving accuracy improvements of 0.90% and 2.26%, and F 1 -score gains of 4.75% and 3.21%, respectively. By integrating complementary modeling paradigms with explainable learning strategies, MVT-OFML offers a promising AI solution for precise and interpretable breast cancer diagnosis and prognosis, supporting informed decision-making in clinical settings.
breast cancerhistopathological image classificationexplainable AICNN-Transformer hybrid
EURASIP Journal on Wireless Communications and Networking · مجلد 2025 (1)
The most innovative Service-Optimized Logging for Resource Allocation (SOL-RA) is in situations that support 6G connection. The CyberTwin architecture optimizes the quality of service provided to end users in 6G communications by using the dependability of terahertz connections and interactions of a machine-type nature. Elastically sharing elastic resources among users is made possible by the proposed resource allocation strategy, which makes use of proprietary logger functions. This ensures that efficient allocation is achieved without overlapping or lengthy wait periods. Within the framework of SOL-RA, a categorization mechanism is implemented for dense requests, which differentiates them as either stationary or priority services. Resource allocations are dynamically done based on this categorization, which enhances the organization's responsiveness to different needs. Through a tree classifier learning mechanism, CyberTwin logs play an essential part in the processing of requests and the preparation of resources. This helps to ensure that resources are distributed without inefficiency. Requests that are generating a backlog are identified and processed in parallel by the system, which significantly reduces the amount of time that is wasted waiting. In order to guarantee a specialized distribution for the categorized outputs, resource allocations are directed by CyberTwin data logs. An examination of the performance of the SOL-RA scheme takes into account important metrics such service latency, service backlog, resource usage, and request-to-response ratio. This research offers insights into the efficacy of the scheme in maximizing service quality and resource consumption in 6G settings.
International Journal of Computational Intelligence Systems · مجلد 18 (1)
Credit risk assessment uses finance-based behavioural patterns for micro-lending purposes and organizations. The repayment behaviour and credit stability patterns are analyzed across varying repayment tenures and financed amounts. Due to limited borrower data and fluctuating financial patterns, micro-lending platforms have substantial hurdles when it comes to effectively evaluating credit risk. This article introduces a Collaborative Filtering Method using Lending Pattern Analysis (CFM-LPA). The proposed method is enhanced through collaborative federated learning, enabling the analysis of these patterns. This approach evaluates the return rate, credit limit, and consumer response behaviours. Federated learning processes one or more of these factors to assess diverse lending patterns. Based on these evaluations, the behavioural factor is updated for each return period, influencing the credit risk for subsequent return periods and supporting the financial stability of micro-lending operations. The model is trained individually on the identified factors, allowing the behavioural factor to be filtered. New credit risks are identified using this filtered factor from the previous return period. These insights help define new behavioural patterns for the specified credit limit. The proposed method enhances risk detection accuracy by 14.03% and improves return rate analysis by 13.28% across financed amounts. The above abstract is also graphically presented.
In the context of Industry 4.0, improving energy efficiency in smart factories has emerged as a key priority to drive sustainable industrial growth. However, identifying optimal energy-saving solutions is challenging due to the inherent uncertainty and complexity in decision-making. This study addresses these challenges by proposing a multi-criteria decision-making (MCDM) framework that leverages intuitionistic fuzzy sets (IFSs) to manage ambiguity in the evaluation process. To advance this framework, we develop a suite of novel aggregation operators (AOs), including the intuitionistic fuzzy softmax Dubois-Prade (IFSDP), intuitionistic fuzzy softmax interactive Dubois-Prade weighted average (IFSIDPWA), intuitionistic fuzzy softmax interactive Dubois-Prade ordered weighted average (IFSIDPOWA), and intuitionistic fuzzy softmax interactive Dubois-Prade weighted geometric (IFSIDPWG), which effectively handle uncertainty and vagueness in the criteria assessments. The method based on the removal effects of criteria (MEREC) is utilized to objectively determine the criteria weights, ensuring a robust evaluation structure. For ranking, the alternatives are evaluated through the ranking of alternatives using functional mapping of criteria sub-intervals into a Single Interval (RAFSI) approach. A case study involving eight criteria and five energy-saving solutions demonstrates the framework's feasibility, with results confirming the effectiveness of our AOs and RAFSI technique in guiding decision-makers toward sustainable energy solutions for smart factories. This framework is poised to support sustainable manufacturing practices in Industry 4.0, fostering greener and more efficient industrial operations.
Accurate brain tumor detection is essential for prompt treatment and better patient outcomes. Nevertheless, segmentation errors and classification constraints plague current approaches. With the goal of improving brain tumor detection accuracy and dependability, this research holds hope for improved patient outcomes and a greater understanding of tumor pathology. This paper introduces a novel DeepNeuroXpert (DN-XPert) model to segment and classify brain tumors, accompanied by three other models: the NSAS-Net or Nested Self-Attentive Segmentation Network (NSAS-Net), AI2CF Classification that is Attention-Integrated Inception Capsule Fusion (AI2CF) Classification, and WPSO for Parameter Tuning which stands for Wombat-Pelican Synergy Optimization. Our research is focused on addressing the challenges in medical image analysis. We propose new ways to enhance precision and dependability of brain tumor detection using DN-Xpert, a technique that uses advanced deep learning methods for accurate segmentation and classification of tumors in the brain. Furthermore, the DN-Xpert and its partner models have shown high-level performance by exceeding benchmarks with accuracy that goes up to 99.4 % and precision, recall, and F1-score metrics reaching a maximum of 99 %. This outstanding accuracy emphasizes the potential power of our unique approaches in changing how we detect and classify brain tumors.
Fundoscopic diagnosis involves assessing the proper functioning of the eye’s nerves, blood vessels, retinal health, and the impact of diabetes on the optic nerves. Fundus disorders are a major global health concern, affecti... | Find, read and cite all the research you need on Tech Science Press
With the increasing complexity of hotel selection, traditional decision-making models often struggle to account for uncertainty and interrelated criteria. Multi-criteria decision-making (MCDM) techniques, particularly those b... | Find, read and cite all the research you need on Tech Science Press
hotel recommendationtourist preferencescircular intuitionistic fuzzy setsmulti-criteria decision making
IEEE Transactions on Computational Social Systems · مجلد 13 (1) · 1058-1068
The advent of the Intelligence of Social Things (IoST) paradigm has created new prospects for improving false news detection by utilizing interconnected social networks, facilitating the amalgamation of many data sources including user behaviors, social interactions, and contextual information. Multiple techniques exist for identifying false information, with individual methods often concentrating on aspects such as news substance, social context, or external veracity. Establishing dissemination networks, examining the structural traits and methods of fake news spread on Weibo and Twitter. Nonetheless, it possesses limitations in enabling the two modes to concentrate more efficiently on their individual preferences. By using entity linking to expand the entity terminology in news content and semantic mining to augment the style vocabulary in news material, the Pref-FEND model was developed. The graph neural network’s capacity to effectively capture node properties was improved by learning and using five different types of words as node representations in the graph network. A heterogeneous degree-aware graph convolutional network was concurrently incorporated, yielding enhancements of 2.8% and 1.9% in F1-score relative to the fact-based singular model GET. Additionally, when integrated with LDAVAE+GET for concurrent detection, the F1-scores were enhanced by 1.1% and 1.3%, respectively, in comparison to Pref-FEND. The experimental findings confirm the efficacy of the suggested enhancements to the model.