Neural Computing & Applications最新文献

{"title":"Contrastive learning-based video quality assessment-jointed video vision transformer for video recognition.","authors":"Jian Sun, Mohammad Mahoor","doi":"10.1007/s00521-026-11949-9","DOIUrl":"10.1007/s00521-026-11949-9","url":null,"abstract":"<p><p>Video quality significantly affects video classification. We found this problem when we classified Mild Cognitive Impairment well from clear videos, but worse from blurred ones. From then, we realized that referring to Video Quality Assessment (VQA) may improve video classification. This paper proposed Self-Supervised Learning-based Video Vision Transformer combined with No-reference VQA for video classification (SSL-V3) to fulfill the goal. SSL-V3 leverages Combined-SSL mechanism to join VQA into video classification and address the label shortage of VQA, which commonly occurs in video datasets, making it impossible to provide an accurate Video Quality Score. In brief, Combined-SSL takes video quality score as a factor to directly tune the feature map of the video classification. Then, the score, as an intersected point, links VQA and classification, using the supervised classification task to tune the parameters of VQA. SSL-V3 achieved robust experimental results on two datasets. For example, it reached an accuracy of 94.87% on some interview videos in the I-CONECT (a facial video-involved healthcare dataset), verifying SSL-V3's effectiveness.</p>","PeriodicalId":49766,"journal":{"name":"Neural Computing & Applications","volume":"38 5","pages":""},"PeriodicalIF":4.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13089767/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147724470","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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":"Sequential pattern transformer (SPT): a generative and interpretable framework for predicting disease trajectories.","authors":"Mohammad Assadi Shalmani, Masoud Khani, Amirsajjad Taleban, Zihao Yi, Jennifer T Fink, Christopher E Weber, Qiang Lu, Jake Luo","doi":"10.1007/s00521-025-11695-4","DOIUrl":"10.1007/s00521-025-11695-4","url":null,"abstract":"<p><p>The effective integration of artificial intelligence into clinical workflows requires models that go beyond simple prediction to generate comprehensive, explainable, and actionable disease trajectories. Addressing the limitations of opaque deep learning architectures and the noise inherent in electronic health records, we introduce the sequential pattern transformer (SPT), a novel framework that synergizes sequential pattern mining with generative transformer modeling. Using four years of inpatient data from 258,460 type 2 diabetes patients, we applied the PrefixSpan algorithm to distill noisy diagnostic histories into a curated vocabulary of 95,630 statistically validated disease progression patterns. A decoder-only transformer was trained exclusively on these evidence-based sequences to learn the temporal dynamics of disease evolution. This pattern-guided approach shifts the modeling paradigm from classification to probabilistic trajectory generation. The model achieved a robust 85.78% Top-5 accuracy, significantly outperforming a standard LSTM baseline (71.47%). Beyond predictive accuracy, the framework constructs a dynamic Disease Atlas, a branching tree structure that visualizes likely future pathways, augmented by multi-level explainable AI (XAI) including learned clinical clusters, SHAP-based feature attribution, and counterfactual simulations. Crucially, this methodology is domain-agnostic and capable of efficient fine-tuning, making it a transferable solution for adapting to diverse clinical conditions and local hospital settings. SPT thus offers a transparent, robust, and scalable framework for mapping the complex temporal dynamics of disease, bridging the gap between high-performance AI and interpretable clinical application.</p>","PeriodicalId":49766,"journal":{"name":"Neural Computing & Applications","volume":"38 3","pages":""},"PeriodicalIF":4.5,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13030885/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147576305","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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":"Supporting human-agent communication for explainable planning in spatial-temporal planning problems.","authors":"Alan Lindsay, Andrés A Ramírez-Duque, Bart Craenen, David A Robb, Emanuele De Pellegrin, Laurence Boé, Andrea Munafò, Ronald P A Petrick","doi":"10.1007/s00521-025-11711-7","DOIUrl":"https://doi.org/10.1007/s00521-025-11711-7","url":null,"abstract":"<p><p>The task of supporting a human operator to understand generated plans, and to explore the plan space, are important problems in automated planning. In this work, we consider the problem of plan explainability and plan space exploration in underwater autonomous vehicle missions. In this context, concepts that are useful for querying the system, such as distance and duration, will not necessarily map directly onto components of the planning model, such as actions. To overcome this difficulty, we focus on an important substructure of these problems: the multi-agent spatial-temporal (MAST) structure. Using this structure, we define a collection of model extensions, which include additional concepts relevant to the MAST structure. We then consider the problem of user-guided plan space exploration, and identify useful query types in this domain, including user queries based on numeric functions. These queries can make use of the extended model, allowing the user to directly reference the new concepts. In an empirical study, we demonstrate the use of the new structure within queries, and compare the new query types in our target domain, and in benchmark domains with the MAST structure. Finally, we report on a qualitative user study, where we investigate the use of these new structural concepts in underwater autonomous vehicle scenarios. Our study indicates that the extended concepts can be used in user queries and agent responses, enabling the user to better communicate their intent in shaping mission objectives, and supporting explanations with more relevant information.</p>","PeriodicalId":49766,"journal":{"name":"Neural Computing & Applications","volume":"38 10","pages":"370"},"PeriodicalIF":4.5,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13149645/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147870050","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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":"Difference rewards policy gradients.","authors":"Jacopo Castellini, Sam Devlin, Frans A Oliehoek, Rahul Savani","doi":"10.1007/s00521-022-07960-5","DOIUrl":"10.1007/s00521-022-07960-5","url":null,"abstract":"<p><p>Policy gradient methods have become one of the most popular classes of algorithms for multi-agent reinforcement learning. A key challenge, however, that is not addressed by many of these methods is multi-agent credit assignment: assessing an agent's contribution to the overall performance, which is crucial for learning good policies. We propose a novel algorithm called Dr.Reinforce that explicitly tackles this by combining difference rewards with policy gradients to allow for learning decentralized policies when the reward function is known. By differencing the reward function directly, Dr.Reinforce avoids difficulties associated with learning the <i>Q</i>-function as done by counterfactual multi-agent policy gradients (COMA), a state-of-the-art difference rewards method. For applications where the reward function is unknown, we show the effectiveness of a version of Dr.Reinforce that learns an additional reward network that is used to estimate the difference rewards.</p>","PeriodicalId":49766,"journal":{"name":"Neural Computing & Applications","volume":"37 19","pages":"13163-13186"},"PeriodicalIF":4.5,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12204931/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144530735","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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":"Int-HRL: towards intention-based hierarchical reinforcement learning.","authors":"Anna Penzkofer, Simon Schaefer, Florian Strohm, Mihai Bâce, Stefan Leutenegger, Andreas Bulling","doi":"10.1007/s00521-024-10596-2","DOIUrl":"10.1007/s00521-024-10596-2","url":null,"abstract":"<p><p>While deep reinforcement learning (RL) agents outperform humans on an increasing number of tasks, training them requires data equivalent to decades of human gameplay. Recent hierarchical RL methods have increased sample efficiency by incorporating information inherent to the structure of the decision problem but at the cost of having to discover or use human-annotated sub-goals that guide the learning process. We show that intentions of human players, i.e. the precursor of goal-oriented decisions, can be robustly predicted from eye gaze even for the long-horizon sparse rewards task of Montezuma's Revenge-one of the most challenging RL tasks in the Atari2600 game suite. We propose <i>Int-HRL</i>: Hierarchical RL with intention-based sub-goals that are inferred from human eye gaze. Our novel sub-goal extraction pipeline is fully automatic and replaces the need for manual sub-goal annotation by human experts. Our evaluations show that replacing hand-crafted sub-goals with automatically extracted intentions leads to an HRL agent that is significantly more sample efficient than previous methods.</p>","PeriodicalId":49766,"journal":{"name":"Neural Computing & Applications","volume":"37 23","pages":"18823-18834"},"PeriodicalIF":4.5,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12313806/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144776756","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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":"Deep multi-objective reinforcement learning for utility-based infrastructural maintenance optimization.","authors":"Jesse van Remmerden, Maurice Kenter, Diederik M Roijers, Charalampos Andriotis, Yingqian Zhang, Zaharah Bukhsh","doi":"10.1007/s00521-024-10954-0","DOIUrl":"10.1007/s00521-024-10954-0","url":null,"abstract":"<p><p>In this paper, we introduce multi-objective deep centralized multi-agent actor-critic (MO-DCMAC), a multi-objective reinforcement learning method for infrastructural maintenance optimization, an area traditionally dominated by single-objective reinforcement learning (RL) approaches. Previous single-objective RL methods combine multiple objectives, such as probability of collapse and cost, into a singular reward signal through reward-shaping. In contrast, MO-DCMAC can optimize a policy for multiple objectives directly, even when the utility function is nonlinear. We evaluated MO-DCMAC using two utility functions, which use probability of collapse and cost as input. The first utility function is the threshold utility, in which MO-DCMAC should minimize cost so that the probability of collapse is never above the threshold. The second is based on the failure mode, effects, and criticality analysis methodology used by asset managers to assess maintenance plans. We evaluated MO-DCMAC, with both utility functions, in multiple maintenance environments, including ones based on a case study of the historical quay walls of Amsterdam. The performance of MO-DCMAC was compared against multiple rule-based policies based on heuristics currently used for constructing maintenance plans. Our results demonstrate that MO-DCMAC outperforms traditional rule-based policies across various environments and utility functions.</p>","PeriodicalId":49766,"journal":{"name":"Neural Computing & Applications","volume":"37 30","pages":"24719-24742"},"PeriodicalIF":4.5,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12511271/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145281527","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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":"A fairness scale for real-time recidivism forecasts using a national database of convicted offenders.","authors":"Jacob Verrey, Peter Neyroud, Lawrence Sherman, Barak Ariel","doi":"10.1007/s00521-025-11478-x","DOIUrl":"10.1007/s00521-025-11478-x","url":null,"abstract":"<p><p>This investigation explores whether machine learning can predict recidivism while addressing societal biases. To investigate this, we obtained conviction data from the UK's Police National Computer (PNC) on 346,685 records between January 1, 2000, and February 3, 2006 (His Majesty's Inspectorate of Constabulary in Use of the Police National Computer: An inspection of the ACRO Criminal Records Office. His Majesty's Inspectorate of Constabulary, Birmingham, https://assets-hmicfrs.justiceinspectorates.gov.uk/uploads/police-national-computer-use-acro-criminal-records-office.pdf, 2017). We generate twelve machine learning models-six to forecast general recidivism, and six to forecast violent recidivism-over a 3-year period, evaluated via fivefold cross-validation. Our best-performing models outperform the existing state-of-the-arts, receiving an area under curve (AUC) score of 0.8660 and 0.8375 for general and violent recidivism, respectively. Next, we construct a fairness scale that communicates the semantic and technical trade-offs associated with debiasing a criminal justice forecasting model. We use this scale to debias our best-performing models. Results indicate both models can achieve all five fairness definitions because the metrics measuring these definitions-the statistical range of recall, precision, positive rate, and error balance between demographics-indicate that these scores are within a one percentage point difference of each other. Deployment recommendations and implications are discussed. These include recommended safeguards against false positives, an explication of how these models addressed societal biases, and a case study illustrating how these models can improve existing criminal justice practices. That is, these models may help police identify fewer people in a way less impacted by structural bias while still reducing crime. A randomized control trial is proposed to test this illustrated case study, and further directions explored.</p><p><strong>Supplementary information: </strong>The online version contains supplementary material available at 10.1007/s00521-025-11478-x.</p>","PeriodicalId":49766,"journal":{"name":"Neural Computing & Applications","volume":"37 26","pages":"21607-21657"},"PeriodicalIF":4.5,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12401775/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144994036","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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":"Modeling dislocation dynamics data using semantic web technologies.","authors":"Ahmad Zainul Ihsan, Said Fathalla, Stefan Sandfeld","doi":"10.1007/s00521-024-10674-5","DOIUrl":"10.1007/s00521-024-10674-5","url":null,"abstract":"<p><p>The research in Materials Science and Engineering focuses on the design, synthesis, properties, and performance of materials. An important class of materials that is widely investigated are crystalline materials, including metals and semiconductors. Crystalline material typically contains a specific type of defect called \"dislocation\". This defect significantly affects various material properties, including bending strength, fracture toughness, and ductility. Researchers have devoted a significant effort in recent years to understanding dislocation behaviour through experimental characterization techniques and simulations, e.g., dislocation dynamics simulations. This paper presents how data from dislocation dynamics simulations can be modelled using semantic web technologies through annotating data with ontologies. We extend the dislocation ontology by adding missing concepts and aligning it with two other domain-related ontologies (i.e., the Elementary Multi-perspective Material Ontology and the Materials Design Ontology), allowing for efficiently representing the dislocation simulation data. Moreover, we present a real-world use case for representing the discrete dislocation dynamics data as a knowledge graph (DisLocKG) which can depict the relationship between them. We also developed a SPARQL endpoint that brings extensive flexibility for querying DisLocKG.</p>","PeriodicalId":49766,"journal":{"name":"Neural Computing & Applications","volume":"37 18","pages":"11737-11753"},"PeriodicalIF":4.5,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12174205/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144334315","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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":"Balancing misclassification errors in image-based inference using problem domain semantics and a nested cascade architecture.","authors":"Xin Du, Rajesh Jena, Katayoun Farrahi, Mahesan Niranjan","doi":"10.1007/s00521-025-11613-8","DOIUrl":"10.1007/s00521-025-11613-8","url":null,"abstract":"<p><p>Pattern recognition models, particularly neural networks, often focus on maximising classification accuracy. However, in practice, the types of errors made (misclassification between different classes) can have varying associated costs. Current methods overlook varying misclassification error types. Misclassification labels can either be available from expert knowledge or derived from semantics of textual descriptions of class labels. Exploiting such misclassification costs can have significant implications when deploying machine learning systems. Here, using five examples from image and tabular domains, we show how a deep neural architecture trained in a nested layer-wise fashion (cascade learning) in which early layers solve easier problems than later ones could exploit such hierarchical aspects of class labels. We employ a measure of performance called \"severity\" of errors and show how emphasis could be placed on classes that are deeper in the hierarchy, ignoring errors that arise between semantic neighbours.</p><p><strong>Supplementary information: </strong>The online version contains supplementary material available at 10.1007/s00521-025-11613-8.</p>","PeriodicalId":49766,"journal":{"name":"Neural Computing & Applications","volume":"37 31","pages":"26021-26036"},"PeriodicalIF":4.5,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12535507/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145338090","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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":"Fourier convolutional decoder: reconstructing solar flare images via deep learning.","authors":"Merve Selcuk-Simsek, Paolo Massa, Hualin Xiao, Säm Krucker, André Csillaghy","doi":"10.1007/s00521-025-11283-6","DOIUrl":"10.1007/s00521-025-11283-6","url":null,"abstract":"<p><p>Reconstructing images from observational data is a complex and time-consuming process, particularly in astronomy, where traditional algorithms like CLEAN require extensive computational resources and expert interpretation to distinguish genuine features from artifacts, especially without ground truth data. To address these challenges, we developed the Fourier convolutional decoder (FCD), a custom-made overcomplete autoencoder trained on simulated data with available ground truth. This enables the network to generate outputs that closely approximate expected ground truth. The model's versatility was demonstrated on both simulated and observational datasets, with a specific application to data from the spectrometer/telescope for imaging X-rays (STIX) on the solar orbiter. In the simulated environment, FCD's performance was evaluated using multiple-image reconstruction metrics, demonstrating its ability to produce accurate images with minimal artifacts. For observational data, FCD was compared with benchmark algorithms, focusing on reconstruction metrics related to Fourier components. Our evaluation found that FCD is the fastest imaging method, with runtimes on the order of milliseconds. Its computational cost is comparable to the most efficient reconstruction algorithm and 280 <math><mo>×</mo></math> faster than the slowest imaging method for single-image reconstruction on a CPU. Additionally, its runtime can be reduced by an order of magnitude for multiple-image reconstruction on a GPU. FCD outperforms or matches state-of-the-art methods on simulated data, achieving a mean MS-SSIM of 0.97, LPIPS of 0.04, PSNR of 35.70 dB, a Dice coefficient of 0.83, and a Hausdorff distance of 5.08. Finally, on experimental STIX observations, FCD remains competitive with top methods despite reduced performance compared to simulated data.</p>","PeriodicalId":49766,"journal":{"name":"Neural Computing & Applications","volume":"37 20","pages":"15573-15604"},"PeriodicalIF":4.5,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12234595/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144602115","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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}