International Journal of Intelligent Systems最新文献

The object of the study is the processes of managing project changes. The research problem concerns the development of a change management method that, based on the simulation of project execution within a digital twins environment, enables the prediction and effective management of the most probable and impactful changes. The influence of current trends on the development of digital technologies was analyzed. The necessity of applying digitalization methods to enhance the efficiency of project management was identified. It was demonstrated that digital twin–based modeling of project processes and changes provides a foundation for developing optimal management strategies. A concept for utilizing digital twins of project objects and processes to support effective change management was proposed. The goals and objectives of the study were formulated, focusing on the development of a change management method for projects based on their representation through digital twins. It was shown that modeling the impact of changes on project execution requires the application of models and methods for managing the interaction of project processes based on digital twins. The structure of the digital twin environment for projects was defined, within which the causes and impacts of changes on projects were modeled, as well as the interaction model of digital twins during project implementation, and a method for forecasting and assessing the effect of changes on project execution was developed. A method and practical tools for managing changes in projects of the developer company ICD Investments have been developed and tested in practice.

This study introduces an innovative cross-modal coattention network (CMCAN) framework, specifically designed to tackle the challenges of temporal misalignment and modality-specific feature preservation in multimodal depression detection. The architecture comprises two fundamental components: (1) guided multihead attention, which facilitates context-aware interactions across modalities, and (2) dedicated self-attention pathways that ensure the preservation of key unimodal features. To enhance the estimation of depression severity, a cascaded fusion strategy is employed, combining feature superposition with hierarchical stacking. When evaluated on a Chinese localized depression dataset, CMCAN demonstrates exceptional performance, achieving optimal results (accuracy: 0.839; precision: 0.829; recall: 0.863) with its audiovisual guided coattention module (AVGA (SA (V), SA (A))) comprising three cascaded layers. The framework consistently surpasses unimodal baselines across various emotional valence stimuli (positive, neutral, and negative) and achieves state-of-the-art performance on AVEC 2014 (MAE: 5.38). Comprehensive ablation studies validate the effectiveness of individual components, whereas comparative analyses demonstrate significant improvements over existing multimodal fusion approaches. These findings underscore the robustness and generalizability of CMCAN, validating its effectiveness in harmonizing cross-modal synergy while preserving modality-specific features, thereby advancing practical solutions for automated depression detection.

In today’s dynamic financial environment, bank loan approval systems are crucial for determining credit accessibility and maintaining economic stability. Efficient and accurate mechanisms help financial institutions minimize risks, enhance customer satisfaction, and make informed lending decisions. Traditional evaluation methods, however, often struggle with complex applicant data, underscoring the need for advanced, data-driven approaches. This study proposes an enhanced loan approval prediction framework that integrates SHAP-guided feature selection and LIME-based interpretability within a robust multiclassifier architecture. The methodology includes extensive data preprocessing, handling missing values, and encoding categorical variables, followed by SHAP to identify the most influential features. Using two Kaggle datasets, logistic regression achieved the highest performance, with 86.17% accuracy and 81% AUC on Dataset 1 and 99.06% accuracy on Dataset 2. LIME provided intuitive, visual explanations of model predictions, fostering transparency and trust. In addition, a user-friendly, real-time web application was developed for practical deployment. Overall, the study advances intelligent, interpretable, and efficient loan approval systems for modern banking.

Deep learning is widely used in many fields, but the emergence of adversarial examples threatens the application of deep learning. Various methods have been proposed to defend against adversarial attacks. However, existing defense methods either can only detect adversarial examples without restoring their original classes or merely focus on verifying the input category and attempting to recover the classes of adversarial examples while lacking awareness of whether the input has been perturbed. To develop defense approaches that simultaneously achieve both detection and correction capabilities, a heterogeneous model combinatorial defense framework (HMCDF) is proposed for adversarial attacks in this paper. In particular, we first summarize the fundamental operations, block structures, and compositional patterns that constitute the model, while analyzing how these factors influence both the functionality and robustness of the model. According to the differences in the structure of the models, the models can be divided into isomorphic models and heterogeneous models. Then, we combine heterogeneous models to construct a heterogeneous model defense framework. Within this framework, as long as a majority of models can detect adversarial examples and restore their original labels, the voting mechanism used in the framework can determine whether the input has been perturbed, ultimately outputting legitimate labels through collective decision-making. To validate the performance, we conduct extensive experiments on three public datasets: CIFAR-10, SVHN, and Mini-ImageNet. After sufficient analysis of the simulation results, we find that our proposed method outperforms the others for the detection of adversarial attacks generated by the considered attack methods and can recover the classes of the adversarial examples.

Contextual information parsing is one of the most important subtasks of conversational KBQA. However, existing methods often assume the independence of utterance and model them in isolation. In this paper, we propose a Dependency paRsing-Enhanced converSational queStion AnswerinG systEm, DRESSAGE, which can effectively model long-range semantic dependencies in the conversation history. This is a multitask neural semantic parsing model. The model can perform explicit dependency parsing for several history questions and the current question and enhance the entity recognition module and the question encoding module with the parsing tree. The performance of the DRESSAGE model is tested on the widely used CSQA dataset and gets SOTA in the overall effect, which proves the effectiveness of this model.

Facial expression recognition (FER) remains a challenging task in computer vision. Recent works have shown excellent performance in overall recognition accuracy, but its accuracy significantly decreases when recognizing similar expressions. This is due to interclass homogeneity and intraclass heterogeneity. To address these issues, we propose a novel dual-stage network called DUAL, inspired by contrastive learning. First, we increase the distance between negative samples while reducing the distance between positive ones. This is achieved by dynamically updating pairs of comparison samples. Second, we introduce a two-stage network architecture. The first stage uses two branches to extract image features and facial keypoint features. These branches interact to learn coarse-grained features through mutual guidance. The second stage focuses on fine-grained features using scale-specific residual blocks. This allows the model to identify facial regions that are critical for recognizing expressions. We conducted extensive experiments on multiple datasets. The results show that DUAL surpasses state-of-the-art models in items of performance. Additionally, the model shows high accuracy even in noisy conditions, highlighting its robustness.

Artificial intelligence (AI) systems are increasingly adopted in high-stakes domains such as healthcare and finance, so the demand for transparency and interpretability has grown substantially. EXplainable AI (XAI) methods have emerged to address this challenge, but individual techniques often offer limited, fragmented insights. This paper introduces Meta-explainers, a novel ensemble-based XAI framework that integrates multiple explanation types—specifically relevance-based and counterfactual methods—into unified, multifaceted and complementary meta-explanations. Inspired by meta-classification principles, our approach structures the explanation process into five stages: generation, grouping, evaluation, aggregation, and visualization. Each stage is designed to preserve the unique strengths of individual XAI techniques while enhancing their interpretability and coherence when combined. Experimental results on both image (MNIST) and tabular (Breast Cancer) datasets show that Meta-explainers consistently outperform individual and state-of-the-art ensemble explanation methods in terms of explanation quality, as measured by established metrics. This work paves the way toward more holistic and user-centered AI explainability with a flexible methodology that can be extended to incorporate additional explanation paradigms.

This paper introduces a cost-effective prompt optimization strategy for ancient Chinese word segmentation using large language models, aiming to mitigate the substantial computational resources and training expenses of fine-tuning. We developed two knowledge-enhanced frameworks, a General Knowledge Prompt framework and a Domain-Specific Knowledge Prompt framework, and evaluated their effectiveness across various ancient Chinese corpora using seven mainstream LLMs, including ERNIE Bot, Qwen, SparkDesk, DeepSeek, ChatGPT, Gemini, and Copilot. Our findings confirm that both prompt frameworks enhance the segmentation capability of LLMs to varying extents, with the Domain-Specific Knowledge Prompt framework yielding the most significant improvements. Notably, the DeepSeek model achieves 94.01% F1 score (94.24% precision, 93.79% recall) on the test set, while the Qwen model demonstrates a remarkable 15.73% increase in the F1 score with the Domain-Specific Knowledge Prompt framework. Our ablation studies indicate that the entries Rules and Examples are the most crucial to the success of prompt frameworks, effectively addressing the challenges of rule inconsistency and insufficient annotated data.

With the rise of neural networks and pre-trained models such as BERT, abstractive text summarization techniques have received widespread attention. Nevertheless, traditional extractive text summarization methods still hold substantial research value due to their low computational cost, interpretability, and robustness. In algorithms like TextRank and its variants, graph nodes are typically constructed based on surface-level lexical features. These graphs often fail to incorporate many contextual relationships, such as coreference relationships among nodes, resulting in fragmented representations of key concepts. For edge construction, a sliding window of size T is commonly used to connect word nodes within the window. However, these methods often fall short in modeling the rich contextual dependencies embedded in the document. Several recent studies have demonstrated that semantic graphs can effectively improve the accuracy of text summarization. In this paper, we construct a more interpretable semantic graph from syntax trees and propose a novel unsupervised algorithm based on the personalized PageRank algorithm for summary extraction. We utilize tree transformation methods to enrich word-level information for graph construction, define node-merging rules to reduce graph complexity, use coreference chains to merge coreferring entities across sentences for enriching contextual links, and introduce the concept of Meta Node sets to capture thematic relationships that are not fully represented by syntactic dependencies or coreference chains alone. By clustering semantically related words, Meta Nodes enhance the graph’s ability to reflect deeper contextual coherence across the document. Compared with previous TextRank-based methods, our improvement yields significant ROUGE score boosts on the CNN-DM dataset. While the method was developed and evaluated using English-language datasets, its underlying design is language agnostic and can be adapted to other languages with suitable linguistic tools.