CAAI Transactions on Intelligence Technology最新文献

{"title":"Brain-RetinaNet: Detection of Brain Tumour Using an Improved RetinaNet in Magnetic Resonance Imaging","authors":"Rashid Iqbal,&nbsp;Rabbia Mahum,&nbsp;Mohamed Sharaf,&nbsp;Javed Ali Khan","doi":"10.1049/cit2.70040","DOIUrl":"10.1049/cit2.70040","url":null,"abstract":"<p>Brain tumours disrupt the normal functioning of the brain and, if left untreated, can invade surrounding tissues, blood vessels, and nerves, posing a severe threat. Consequently, early detection is crucial to prevent tragic outcomes. Distinguishing brain tumours through manual detection poses a significant challenge given their diverse features, such as differing shapes, sizes, and nucleus characteristics. Therefore, this research introduces an improved architecture for tumour detection named as Brain-RetinaNet, an extension of the RetinaNet model. Brain-RetinaNet is specifically designed for automated detection and identification of brain tumours in MRI images. It utilises an advanced multiscale feature fusion mechanism within the X-module, complemented by the channel attention module. The feature fusion mechanism within the X-module progressively merges features from different scales, producing enriched feature maps that encompass valuable information. At the same time, the attention module dynamically allocates optimal weights to individual channels within the feature map, enabling the network to prioritise relevant features while reducing interference from unnecessary ones. Moreover, this study employs data augmentation technique to address the limitation of a limited number of available samples. Experimental results indicate that Brain-RetinaNet outperforms existing detectors such as YOLO, SSD, Centernet, EfficientNet, and M2det for the brain tumour detection from MRI images.</p>","PeriodicalId":46211,"journal":{"name":"CAAI Transactions on Intelligence Technology","volume":"11 1","pages":"223-237"},"PeriodicalIF":7.3,"publicationDate":"2026-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/cit2.70040","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147618056","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":"Multi-Objective Optimisation Framework for Heterogeneous Federated Learning","authors":"Jamshid Tursunboev,&nbsp;Vikas Palakonda,&nbsp;Il-Min Kim,&nbsp;Sunghwan Moon,&nbsp;Jae-Mo Kang","doi":"10.1049/cit2.70090","DOIUrl":"10.1049/cit2.70090","url":null,"abstract":"<p>Federated learning is a distributed framework that trains a centralised model using data from multiple clients without transferring that data to a central server. Despite rapid progress, federated learning still faces several unsolved challenges. Specifically, communication costs and system heterogeneity, such as nonidentical data distribution, hinder federated learning's progress. Several approaches have recently emerged for federated learning involving heterogeneous clients with varying computational capabilities (namely, heterogeneous federated learning). However, heterogeneous federated learning faces two key challenges: optimising model size and determining client selection ratios. Moreover, efficiently aggregating local models from clients with diverse capabilities is crucial for addressing system heterogeneity and communication efficiency. This paper proposes an evolutionary multiobjective optimisation framework for heterogeneous federated learning (MOHFL) to address these issues. Our approach elegantly formulates and solves a biobjective optimisation problem that minimises communication cost and model error rate. The decision variables in this framework comprise model sizes and client selection ratios for each Q client cluster, yielding a total of 2 <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mo>×</mo>\u0000 </mrow>\u0000 <annotation> ${times} $</annotation>\u0000 </semantics></math> Q optimisation parameters to be tuned. We develop a partition-based strategy for MOHFL that segregates clients into clusters based on their communication and computation capabilities. Additionally, we implement an adaptive model sizing mechanism that dynamically assigns appropriate subnetwork architectures to clients based on their computational constraints. We also propose a unified aggregation framework to combine models of varying sizes from heterogeneous clients effectively. Extensive experiments on multiple datasets demonstrate the effectiveness and superiority of our proposed method compared to existing approaches.</p>","PeriodicalId":46211,"journal":{"name":"CAAI Transactions on Intelligence Technology","volume":"11 1","pages":"1-14"},"PeriodicalIF":7.3,"publicationDate":"2026-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/cit2.70090","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147618061","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":"Physics-Driven Deep Neural Networks for Solving the Optimal Transport Problem Associated With the Monge–Ampère Equation","authors":"Xinghua Pan,&nbsp;Zexin Feng,&nbsp;Kang Yang","doi":"10.1049/cit2.70067","DOIUrl":"10.1049/cit2.70067","url":null,"abstract":"<p>Monge–Ampère equations (MAEs) are fully nonlinear second-order partial differential equations (PDEs), which are closely related to various fields including optimal transport (OT) theory, geometrical optics and affine geometry. Despite their significance, MAEs are extremely challenging to solve. Although some classical numerical approaches can solve MAEs, their computational efficiency deteriorates significantly on fine grids, with convergence often heavily dependent on the quality of initial estimate. Research on deep learning methods for solving MAEs is still in its early stages, which predominantly addresses simple formulations with basic Dirichlet boundary conditions. Here, we propose a deep learning method based on physics-driven deep neural networks, enabling the solution of both simple and generalised MAEs with transport boundary conditions. In this method, we deal with two first-order sub-equations separated from MAE instead of solving the single MAE directly, which facilitates the imposition of transport boundary conditions and simplifies the training of neural networks. Moreover, we constrain the convexity of solution using the Lagrange multiplier method and maintain the optimisation process differentiable with bilinear interpolation. We provide three progressively complex examples ranging from a simple MAE with an analytical solution to a highly nonlinear variant arising in phase retrieval to validate the effectiveness of our method. For comparison, we benchmark against state-of-the-art deep learning approaches that have been systematically adapted to accommodate the specific requirements of each example.</p>","PeriodicalId":46211,"journal":{"name":"CAAI Transactions on Intelligence Technology","volume":"11 1","pages":"15-25"},"PeriodicalIF":7.3,"publicationDate":"2026-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/cit2.70067","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147626384","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":"Towards Interpretable Face Morphing via Unsupervised Learning of Layer-Wise and Local Features","authors":"Cheng Yu,&nbsp;Chuan Chen,&nbsp;Wenmin Wang","doi":"10.1049/cit2.70088","DOIUrl":"10.1049/cit2.70088","url":null,"abstract":"<p>Discovering meaningful face morphing is critical for applications in image synthesis. Traditional unsupervised methods rely on global or layer-wise representations, neglecting finer local details and thus limiting the control over specific facial attributes. In this work, we introduce an improved unsupervised approach that leverages contrastive learning and K-means clustering to learn both layer-wise and local features (LLF) in the latent space of StyleGAN. Our method segments latent representations into multiple local components across different layers, enabling fine-grained control over attributes such as hair, eyes, and mouth. Experimental results demonstrate that LLF outperforms existing methods by providing more interpretable facial transformations while preserving high image realism, offering a promising solution for enhanced unsupervised face morphing applications. The code is available at https://github.com/disanda/LLF.</p>","PeriodicalId":46211,"journal":{"name":"CAAI Transactions on Intelligence Technology","volume":"11 1","pages":"137-148"},"PeriodicalIF":7.3,"publicationDate":"2026-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/cit2.70088","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147637168","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":"Distributed Formation Control for Heterogeneous Robot Systems Based on Competitive Mechanism","authors":"Zhenghui Cui,&nbsp;Xiaoyi Gu,&nbsp;Ning Tan","doi":"10.1049/cit2.70081","DOIUrl":"10.1049/cit2.70081","url":null,"abstract":"<p>This paper presents an adaptive formation control method for a heterogeneous robot swarm, utilising a multilevel formation task tree to model various types of formation tasks and a single-state distributed k-winner-take-all (S-DKWTA) algorithm to address the MRTA problem. In addition, we propose an enhanced load reassignment algorithm to resolve conflicts when using S-DKWTA. The S-DKWTA algorithm demonstrates the capability to manage multiple objectives and dynamically select leaders in real-time, thereby optimising formation efficiency and reducing energy consumption. The proposed approach integrates an enhanced artificial potential field (APF) to govern the motion of heterogeneous robot systems which encompasses both unmanned ground vehicles (UGVs) and unmanned aerial vehicles (UAVs), thereby achieving collision and obstacle avoidance. Simulations employing UGVs and UAVs swarm to achieve formation movement demonstrate the efficacy of this approach. The amalgamation of S-DKWTA and improved APF ensures stable and adaptable formation control, underscoring its potential for diverse multirobot applications.</p>","PeriodicalId":46211,"journal":{"name":"CAAI Transactions on Intelligence Technology","volume":"11 1","pages":"190-204"},"PeriodicalIF":7.3,"publicationDate":"2026-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/cit2.70081","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147637160","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":"Multi-Scale Transformer for Image Restoration","authors":"Wuzhen Shi,&nbsp;Youwei Pan,&nbsp;Chun Zhao,&nbsp;Yuqing Liu,&nbsp;Shaobo Zhang,&nbsp;Heng Zhang,&nbsp;Yang Wen","doi":"10.1049/cit2.70079","DOIUrl":"10.1049/cit2.70079","url":null,"abstract":"<p>Although Transformer-based image restoration methods have demonstrated impressive performance, existing Transformers still insufficiently exploit multiscale information. Previous non-Transformer-based studies have shown that incorporating multiscale features is crucial for improving restoration results. In this paper, we propose a multiscale Transformer (MST) that captures cross-scale attention among tokens, thereby effectively leveraging the multiscale patch recurrence prior of natural images. Furthermore, we introduce a channel-gate feed-forward network (CGFN) to enhance inter-channel information aggregation and reduce channel redundancy. To simultaneously utilise global, local and multiscale features, we design a multitype feature integration block (MFIB). Extensive experiments on both image super-resolution and HEVC compressed video artefact reduction demonstrate that the proposed MST achieves state-of-the-art performance. Ablation studies further verify the effectiveness of each proposed module.</p>","PeriodicalId":46211,"journal":{"name":"CAAI Transactions on Intelligence Technology","volume":"11 1","pages":"41-54"},"PeriodicalIF":7.3,"publicationDate":"2026-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/cit2.70079","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147637166","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":"Lightweight Hybrid Wafer Defect Pattern Network Based on Feedforward Efficient Attention","authors":"Zhiqiang Hu,&nbsp;Yiquan Wu","doi":"10.1049/cit2.70075","DOIUrl":"10.1049/cit2.70075","url":null,"abstract":"<p>With the increase of semiconductor integration density, in order to cope with the increase of wafer defect complexity and types, especially the low recognition accuracy of overlapping mixed defects and unknown wafer defects, this study proposes a lightweight model for wafer defect detection called LightWMNet. First, using a hierarchical attention Encoder-Decoder architecture, the features of wafer defect pattern (WDP) are channel recalibrated to generate high-resolution fine-grained features and low-resolution coarse-grained features. Secondly, the backbone network incorporates two novel attention modules—feedforward spatial attention (FFSa) and feedforward channel attention (FFCa)—to amplify responses in critical defect regions and suppress noise from stochastic discrete pixels. These mechanisms synergistically enhance feature discriminability without introducing significant parametric overhead. Finally, the Dice loss function and the cross entropy loss function are combined to jointly evaluate the segmentation and classification accuracy of the model. Experimental results on the public mixed wafer defect dataset MixedWM38 show that the pixel accuracy (PA), intersection over union (IoU) and Dice coefficient of the proposed network reach 98.26%, 94.83% and 97.22%, respectively. Without significantly increasing the computational complexity and size of the model, compared with the existing state-of-the-art (SOTA) model, the classification accuracy of lightWMNet in single defect, three mixed defects and four mixed defects is improved by 0.5%, 0.25% and 0.89% respectively. Furthermore, we used transfer learning for the first time to evaluate the model's generalisation ability for unseen defect categories. The results showed that LightWMNet still has a certain recognition ability even in untrained wafer defects.</p>","PeriodicalId":46211,"journal":{"name":"CAAI Transactions on Intelligence Technology","volume":"11 1","pages":"149-166"},"PeriodicalIF":7.3,"publicationDate":"2026-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/cit2.70075","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147566370","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":"Robotic Cell Micromanipulation Skill Learning via Imitation-Enhanced Reinforcement Learning","authors":"Youchao Zhang,&nbsp;Fanghao Wang,&nbsp;Xiangyu Guo,&nbsp;Yibin Ying,&nbsp;Mingchuan Zhou,&nbsp;Zhongliang Jiang,&nbsp;Alois Knoll","doi":"10.1049/cit2.70076","DOIUrl":"10.1049/cit2.70076","url":null,"abstract":"<p>Humans can learn complex and dexterous manipulation tasks by observing videos, imitating and exploring. Multiple end-effectors manipulation of free micron-sized deformable cells is one of the challenging tasks in robotic micromanipulation. We propose an imitation-enhanced reinforcement learning method inspired by the human learning process that enables robots to learn cell micromanipulation skills from videos. Firstly, for the microscopic robot micromanipulation videos, a multi-task observation (MTO) network is designed to identify the two end-effectors and the manipulated objects to obtain the spatiotemporal trajectories. The spatiotemporal constraints of the robot's actions are obtained by the task-parameterised hidden Markov model (THMM). To simultaneously address the safety and dexterity of robot micromanipulation, an imitation learning optimisation-based soft actor-critic (ILOSAC) algorithm is proposed in which the robot can perform skill learning by demonstration and exploration. The proposed method is capable of performing complex cell manipulation tasks in a realistic physical environment. Experiments indicated that compared with current methods and manual remote manipulation, the proposed framework achieved a shorter operation time and less deformation of cells, which is expected to facilitate the development of robot skill learning.</p>","PeriodicalId":46211,"journal":{"name":"CAAI Transactions on Intelligence Technology","volume":"11 1","pages":"123-136"},"PeriodicalIF":7.3,"publicationDate":"2026-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/cit2.70076","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147626368","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":"Fixed-Time Zeroing Neural Dynamics for Adaptive Coordination of Multi-Agent Systems","authors":"Cheng Hua,&nbsp;Xinwei Cao,&nbsp;Jianfeng Li,&nbsp;Shuai Li","doi":"10.1049/cit2.70089","DOIUrl":"10.1049/cit2.70089","url":null,"abstract":"<p>This paper presents an adaptive multi-agent coordination (AMAC) strategy suitable for complex scenarios, which only requires information exchange between neighbouring robots. Unlike traditional multi-agent coordination methods that are solved by neural dynamics, the proposed strategy displays greater flexibility, adaptability and scalability. Furthermore, the proposed AMAC strategy is reconstructed as a time-varying complex-valued matrix equation. By introducing a dynamic error function, a fixed-time convergent zeroing neural network (FTCZNN) model is designed for the online solution of the AMAC strategy, with its convergence time upper bound derived theoretically. Finally, the effectiveness and applicability of the coordination control method are demonstrated by numerical simulations and physical experiments. Numerical results indicate that this method can reduce the formation error to the order of <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mn>1</mn>\u0000 <msup>\u0000 <mn>0</mn>\u0000 <mrow>\u0000 <mo>−</mo>\u0000 <mn>6</mn>\u0000 </mrow>\u0000 </msup>\u0000 </mrow>\u0000 <annotation> $1{0}^{-6}$</annotation>\u0000 </semantics></math> within 1.8 s.</p>","PeriodicalId":46211,"journal":{"name":"CAAI Transactions on Intelligence Technology","volume":"11 1","pages":"267-278"},"PeriodicalIF":7.3,"publicationDate":"2026-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/cit2.70089","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147618035","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":"Tibetan Data Augmentation via GAN-Based Handwritten Text Generation","authors":"Dorje Tashi,&nbsp;Bingtian Chen,&nbsp;Tianying Sheng,&nbsp;Yongbin Yu,&nbsp;Xiangxiang Wang,&nbsp;Jin Zhang,&nbsp;Lobsang Yeshi,&nbsp;Rinchen Dongrub,&nbsp;Thupten Tsering,&nbsp;Nyima Tashi","doi":"10.1049/cit2.70078","DOIUrl":"10.1049/cit2.70078","url":null,"abstract":"<p>Increased awareness of Tibetan cultural preservation, along with technological advancements, has led to significant efforts in academic research on Tibetan. However, the structural complexity of the Tibetan language and limited labeled handwriting data impede advancements in Optical Character Recognition (OCR) and other applications. To address these challenges, this paper proposes an innovative Tibetan data augmentation technique, using Generative Adversarial Networks (GANs) to synthesise arbitrary handwriting images in variable calligraphic styles based on inputs. Moreover, our method leverages a Real-Fake Cross Inputs Strategy during training to enhance generation diversity and improve model generalisability in generating handwritten text beyond the training set and pre-defined corpus. The model was trained on three Tibetan handwriting datasets, including Umê style numerals, Uchen style consonants, and Khyug-yig style words. Experimental results demonstrate that the model successfully generates realistic and recognisable Tibetan numeral and consonant handwriting, achieving Fréchet Inception Distance (FID) scores of 14.45 and 27.63, respectively. The proposed method's effectiveness in augmenting OCR models was validated as evidenced by a reduced OCR Word Error Rate (WER) on the augmented datasets.</p>","PeriodicalId":46211,"journal":{"name":"CAAI Transactions on Intelligence Technology","volume":"11 1","pages":"55-65"},"PeriodicalIF":7.3,"publicationDate":"2026-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/cit2.70078","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147618142","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}