Applied Intelligence最新文献

{"title":"Deep learning-based diagnostic report generation for low-resolution functional medical images via cross-modal visual and textual alignment","authors":"Tao Song,&nbsp;Qiang Lin,&nbsp;Tongtong Li,&nbsp;Xianwu Zeng,&nbsp;Yongchun Cao,&nbsp;Zhengxing Man,&nbsp;Caihong Liu,&nbsp;Zhengqi Cai,&nbsp;Xiaodi Huang","doi":"10.1007/s10489-026-07456-y","DOIUrl":"10.1007/s10489-026-07456-y","url":null,"abstract":"<div><p>Automatic diagnostic report generation holds great significance in reducing physicians’ workload while improving the reliability and effectiveness of diagnostic and treatment processes. However, generating clinically faithful diagnostic reports from low-resolution nuclear medicine images remains a major challenge due to limited visual representation capacity and weak cross-modal alignment. In response, we propose a unified framework for automatic report generation from SPECT bone scintigrams that integrates domain-adaptive representation learning, fine-grained image–text alignment, and anatomy-guided supervision. Specifically, we design a Domain-Adaptive Visual Feature Extractor (DAVFE) that combines ImageNet initialization, contrastive pretraining on large-scale unlabeled SPECT data, and attention-based recalibration to enhance modality-specific visual encoding. Next, a Feature Interaction Alignment Module (FIAM) explicitly models the interactions between global narrative semantics and lesion-level textual cues, enabling fine-grained and clinically consistent cross-modal alignment. Finally, an Anatomy-guided Progressive Granularity Loss (APGL) introduces hierarchical supervision from global to lesion level, mimicking the coarse-to-fine diagnostic reasoning process of physicians. Experiments performed on 2,091 clinical bone scintigrams indicate that our approach consistently outperforms state-of-the-art baselines in both conventional natural language generation metrics (BLEU, METEOR, ROUGE-L) and a hierarchical Clinical Efficacy metric designed for lesion localization. Ablation studies further validate the complementary contributions of DAVFE, FIAM, and APGL. Human evaluation and visualization analyses confirm that the generated reports are more clinically faithful, interpretable, and reliable. Overall, the proposed approach offers a valuable pathway to achieving trustworthy and intelligent diagnostic support within nuclear medicine.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"56 14","pages":""},"PeriodicalIF":3.5,"publicationDate":"2026-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148927604","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"BFA-HARF: Robust RGB-T tracking via bidirectional feature adapter and hybrid attention with receptive fields","authors":"Can Xu,&nbsp;Weidai Xia,&nbsp;Lingmin Fan,&nbsp;Yue Zhang","doi":"10.1007/s10489-026-07466-w","DOIUrl":"10.1007/s10489-026-07466-w","url":null,"abstract":"<div><p>RGB-T object tracking aims to achieve robust, all-weather tracking in complex environments by fusing complementary information from visible (RGB) and thermal infrared (T) images. However, existing methods often suffer from insufficient feature representation and redundant cross-modal invalid information due to the lack of targeted fusion strategies for different modal features. This leads to tracking drift and reduced accuracy in complex scenarios. To address these issues, we propose the BFA-HARF Tracker. Our framework is built upon two synergistic core modules: a Bidirectional Feature Adapter (BFA) and a Hybrid Attention with Receptive Fields (HARF) module. First, the BFA module facilitates a continuous bidirectional information flow between RGB and thermal modalities throughout the backbone network, ensuring features from both sources are progressively aligned and mutually enhanced. Subsequently, the HARF module is strategically inserted to process these aligned features, where it collaboratively captures global dependencies via self-attention and fine-grained local patterns via convolution. This two-stage process of “align-then-fuse” ensures a comprehensive feature representation for the final tracking task. Extensive experiments on four public RGB-T benchmark datasets demonstrate that the proposed algorithm effectively alleviates bounding box ambiguity and tracking drift, achieving performance comparable to state-of-the-art methods.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"56 14","pages":""},"PeriodicalIF":3.5,"publicationDate":"2026-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148927625","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Adversarial fine-tuning in offline-to-online reinforcement learning for robust robot control","authors":"Shingo Ayabe,&nbsp;Hiroshi Kera,&nbsp;Kazuhiko Kawamoto","doi":"10.1007/s10489-026-07455-z","DOIUrl":"10.1007/s10489-026-07455-z","url":null,"abstract":"<div><p>Offline reinforcement learning enables sample-efficient policy acquisition without risky online interaction, yet policies trained on static datasets remain brittle under action-space perturbations such as actuator faults. This study introduces an offline-to-online framework that trains policies on clean data and then performs adversarial fine-tuning, where perturbations are injected into executed actions to induce compensatory behavior and improve resilience. A performance-aware curriculum further adjusts the perturbation probability during training via an exponential-moving-average signal, balancing robustness and stability throughout the learning process. Experiments on continuous-control locomotion tasks demonstrate that the proposed method consistently improves robustness over offline-only baselines and converges faster than training from scratch. Matching the fine-tuning and evaluation conditions yields the strongest robustness to action-space perturbations, while the adaptive curriculum strategy mitigates the degradation of nominal performance observed with the linear curriculum strategy. Overall, the results show that adversarial fine-tuning enables adaptive and robust control under uncertain environments, bridging the gap between offline efficiency and online adaptability.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"56 14","pages":""},"PeriodicalIF":3.5,"publicationDate":"2026-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148927632","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multi-tree and multi-strategy iterative genetic programming algorithm for feature subset construction in high-dimensional data classification","authors":"Chen Zhang,&nbsp;Zezhong Zhang,&nbsp;Youping Tu,&nbsp;Honghao Zhu,&nbsp;Xiaofeng Wang,&nbsp;Xuhui Zhu","doi":"10.1007/s10489-026-07406-8","DOIUrl":"10.1007/s10489-026-07406-8","url":null,"abstract":"<div><p>High-dimensional features are widely used in fields such as gene expression analysis and finance due to their ability to capture complex system information. However, high-dimensional data often exhibit redundancy, sparsity, and nonlinear relationships, which hinder effective feature construction and pose challenges for machine learning models. Dimensionality reduction is therefore essential to transform high-dimensional data into compact, discriminative representations. Although Genetic Programming (GP) has shown potential in feature subset construction, it still faces challenges in handling high-dimensional data: (1) random terminal node selection produces low-quality individuals; (2) fixed evolutionary strategies limit the discovery of informative features; and (3) the vast search space necessitates effective dimensionality reduction. To address these issues, a multi-tree and multi-strategy iterative genetic programming (MMSGP) algorithm is proposed for feature subset construction and classification. (1) A feature-importance-based terminal node selection improves individual quality. (2) A triple iterative strategy effectively guides evolution. (3) A dynamic dual-subset feature selection reduces the search space by adaptively focusing on valuable features. Experimental results across twelve high-dimensional datasets demonstrate that MMSGP achieves substantial performance improvements compared with five baseline methods. Specifically, MMSGP attains higher average balanced classification accuracy than all baselines on nine datasets and surpasses them in macro F1-score on ten datasets. Ablation studies further confirm the effectiveness of the proposed components.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"56 14","pages":""},"PeriodicalIF":3.5,"publicationDate":"2026-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148927631","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A hybrid method integrating information clustering and one-class support vector machine for industrial anomaly detection","authors":"Zhongmin Wang,&nbsp;Zhongjian Yuan,&nbsp;Cong Gao,&nbsp;Yanping Chen","doi":"10.1007/s10489-026-07447-z","DOIUrl":"10.1007/s10489-026-07447-z","url":null,"abstract":"<div><p>Anomaly detection plays a critical role in ensuring the security of industrial control systems. As a classical anomaly detection method, One-Class Support Vector Machine (OCSVM) has been widely applied across various domains, but its performance heavily depends on the selection of kernel function parameters. Moreover, as the dimensionality of industrial data increases, the data distribution becomes sparser, making it difficult for OCSVM to capture the distribution characteristics of normal samples, thereby compromising detection performance. To address these two challenges, this paper proposes a novel industrial anomaly detection method named Information Clustering One-Class Support Vector Machine (IC-OCSVM). First, each feature dimension is treated as a separate system, and its information entropy is calculated to eliminate redundant dimensions. Subsequently, information content is introduced to characterize the differences between samples, and an explicit mapping function based on information content is designed to replace the conventional Gaussian kernel mapping, enabling OCSVM-based anomaly detection. By constructing this mapping function, the proposed method effectively avoids the dependence of traditional OCSVM on kernel parameter selection. In addition, by using information content to measure the distance between samples, the constructed OCSVM effectively alleviates the problem of data sparsity in high-dimensional data. Experiments were conducted on two industrial control system security datasets (SWaT and WADI) and compared with several state-of-the-art anomaly detection algorithms. Experimental results demonstrate that the proposed method achieves superior accuracy, attaining F1-scores of 85.91% on SWaT and 68.28% on WADI, outperforming the best baseline by 3.2% and 3.3%, respectively.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"56 14","pages":""},"PeriodicalIF":3.5,"publicationDate":"2026-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148927839","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"GenPot: A generative honeypot architecture for adaptive web and API interaction","authors":"Antonio Lara-Gutierrez,&nbsp;Juan Zamorano,&nbsp;Jose A. Onieva","doi":"10.1007/s10489-026-07442-4","DOIUrl":"10.1007/s10489-026-07442-4","url":null,"abstract":"<div><p>Honeypots are widely used as cyber-deception tools to study adversarial behaviour, yet their effectiveness is limited by a trade-off between realism and security risk. Low-interaction honeypots are easily detected, while high-interaction honeypots provide realistic data at the cost of network exposure. Recent advances suggest that Large Language Models (LLMs) can mitigate this trade-off by dynamically generating convincing outputs without requiring a vulnerable backend. In this paper, we present GenPot, a fine-tuned LLM-powered honeypot that integrates command-line, API, and dynamic web interaction to deliver realistic yet non-compromisable environments. Our approach combines supervised fine-tuning with prompt engineering, cybersecurity safeguards, and state management to simulate consistent and realistic system responses. As a proof-of-concept use case, we implement the system on top of an OpenCanary baseline simulating a Synology NAS device. To rigorously assess the framework, we conducted an exhaustive multi-dimensional evaluation encompassing deep semantic fidelity, inference latency, high-concurrency scalability, and operational energy efficiency (RPS/W). Technical results demonstrate that the optimized architecture sustains over 1,000 requests per second with near-perfect structural validity, while token-level guardrails ensure high resilience against prompt injection attacks. Crucially, we validate the system’s practical deception efficacy through a 14-day in-the-wild deployment and a human-in-the-loop credibility assessment, where experts were unable to distinguish the honeypot from a physical device (45% accuracy). Furthermore, the framework’s generalizability is proven via a rapid adaptation to a medical Fast Healthcare Interoperability Resources (FHIR) API. This work advances the current state of LLM-powered honeypots by demonstrating a reproducible, highly scalable, energy-aware, and credible approach for adaptive cyber deception.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"56 14","pages":""},"PeriodicalIF":3.5,"publicationDate":"2026-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10489-026-07442-4.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148927689","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Integrated yard crane scheduling and vehicle positioning considering gantry startup and energy consumption","authors":"Rui Hu,&nbsp;Xuan He,&nbsp;Hongtao Hu,&nbsp;Jiangang Jin,&nbsp;Yan Liang","doi":"10.1007/s10489-026-07463-z","DOIUrl":"10.1007/s10489-026-07463-z","url":null,"abstract":"<div><p>As critical components of port logistics systems, container terminals rely heavily on yard cranes (YCs) to handle large volumes of containers, where operational efficiency and energy consumption are tightly coupled and difficult to balance. While existing studies primarily emphasize efficiency-oriented YC scheduling, the substantial energy consumption induced by gantry startups and crane movements has received relatively limited attention. Moreover, YC scheduling and yard vehicle positioning constitute a highly interdependent and combinatorial decision problem, which is challenging to solve using conventional optimization approaches. To address this complex real-world scheduling problem, this study proposes an intelligent bi-objective optimization framework that simultaneously determines YC operation sequences and vehicle parking positions, with the objectives of minimizing makespan and gantry energy consumption. A mixed-integer linear programming model is formulated to explicitly characterize energy consumption arising from gantry startups, empty travel, and loaded travel. To efficiently solve the resulting large-scale and conflicting optimization problem, an improved non-dominated sorting genetic algorithm II (INSGA-II) is developed. The proposed algorithm integrates multiple intelligent strategies, including a parking-slot allocation heuristic for high-quality population initialization, problem-specific neighborhood search operators to reduce unnecessary crane movements and startup events, and a destruction-reconstruction local search mechanism to enhance solution intensification and avoid local optima. Numerical experiments based on realistic terminal operation scenarios demonstrate that the proposed intelligent optimization approach achieves high-quality trade-off solutions, significantly reducing energy consumption while maintaining operational efficiency. The results confirm the effectiveness of integrating evolutionary computing and heuristic search for intelligent decision support in complex industrial scheduling systems.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"56 14","pages":""},"PeriodicalIF":3.5,"publicationDate":"2026-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148927138","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Performance-interpretability trade-offs and generalization in deep learning for pneumonia detection: A benchmarking study","authors":"Francisco Gómez-Vela,&nbsp;Aurelio López-Fernandez,&nbsp;Federico Divina,&nbsp;Miguel García-Torres","doi":"10.1007/s10489-026-07398-5","DOIUrl":"10.1007/s10489-026-07398-5","url":null,"abstract":"<p>Chest X-ray imaging remains the most widely used radiological modality for pneumonia screening. While recent advances in deep learning have demonstrated strong diagnostic performance, the deployment of such models in real-world settings requires not only high accuracy but also robustness and interpretability across different model designs and populations. In this work, we present a comprehensive benchmarking study of multiple deep learning architectures for pneumonia detection. A distinctive methodological feature of this study is the use of two demographically distinct datasets: a pediatric chest X-ray dataset for training, and an independent adult population dataset for external validation. All models were evaluated under a standardized cross-validated protocol. Beyond predictive metrics, we conduct an extensive eXplainable Artificial Intelligence (XAI) analysis assessing both qualitative and quantitative properties, including explanation stability and localization fidelity. Results show that model design choices significantly influence both predictive performance and explanation behavior. In particular, certain architectures consistently achieved superior performance while producing more focused and stable explanations. The performance-interpretability ranking is preserved under external validation on a demographically distinct adult cohort, providing evidence that performance-interpretability coupling is robust to population shift and supports the generalizability of the proposed framework beyond the pediatric training distribution. This work contributes a reproducible, end-to-end methodology that jointly optimizes performance and interpretability, offering practical guidance for selecting and deploying explainable deep learning models in clinical pneumonia screening. All code and data are publicly available at: https://github.com/SynergIA-Lab/pneumoniacnn</p>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"56 14","pages":""},"PeriodicalIF":3.5,"publicationDate":"2026-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10489-026-07398-5.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148927139","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cryptanalysis on a chaos-based cryptosystem with dynamic key","authors":"Rong Zhou,&nbsp;Simin Yu","doi":"10.1007/s10489-026-07446-0","DOIUrl":"10.1007/s10489-026-07446-0","url":null,"abstract":"<div><p>This work performs the cryptanalysis on a chaotic cryptosystem with dynamic key whose position is related to ciphertext (DKPC). The DKPC could be equivalently transformed into a typical structure of permutation-diffusion, where permutation based on breadth-first search is dependent on static key only, while diffusion with dynamic feature is determined by an additional dynamic key of which the location is associated with ciphertext except the static one. The best innovation of DKPC lies in the introduction of dynamic key position to improve the security. However, it has been overestimated and there are still many vulnerabilities after analysis. This paper deciphers the permutation via an innovative approach first. Then the equivalent static and dynamic keys of diffusion are broken respectively by chosen-ciphertext attack. The complexity is much lower than that of cryptanalysis on other plaintext-related algorithms. Theoretical analysis and experimental results indicate that the cryptanalysis is effective and feasible.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"56 14","pages":""},"PeriodicalIF":3.5,"publicationDate":"2026-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148927140","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A multiobject tracking method based on dynamic adaptation and collaborative enhancement","authors":"Yuang Ji,&nbsp;Ying Guo,&nbsp;Zeyu Liu,&nbsp;Hui Li,&nbsp;Zhiyu Liu,&nbsp;Hongyi Fang","doi":"10.1007/s10489-026-07438-0","DOIUrl":"10.1007/s10489-026-07438-0","url":null,"abstract":"<div><p>Multiobject tracking (MOT) is crucial in areas like intelligent transportation, security, and augmented reality. However, current tracking methods generally fail with different object poses, similar appearances, or complicated motion patterns. A more serious case is in a crowded scene with frequent occlusions that lead to track loss and less accurate tracking. To address these issues, we propose a new MOT approach focused on dynamic adaptation and collaborative enhancement. It consists of a nonlinear adaptive kalman filter that makes adjustments in object states for detecting anomalous motions. We also introduce a nonlinear motion adjustment mechanism that optimizes the prediction step that captures object dynamics. Furthermore, we develop a multi-dimensional feature enhancement network that elaborates on appearance-enhancing exploration accumulations across scales to reduce the input image’s quality effect. To tackle identity switches caused by occlusions, we create a trajectory stitching network that compares the spatiotemporal similarity of track fragments and merges them to maintain track continuity. Our method outperforms other advanced tracking approaches on the MOT17 and MOT20 benchmarks.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"56 14","pages":""},"PeriodicalIF":3.5,"publicationDate":"2026-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148927123","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}