Applied Intelligence最新文献

{"title":"RKHS reconstruction based on manifold learning for high-dimensional data","authors":"Guo Niu,&nbsp;Nannan Zhu,&nbsp;Zhengming Ma,&nbsp;Xin Wang,&nbsp;Xi Liu,&nbsp;Yan Zhou,&nbsp;Yuexia Zhou","doi":"10.1007/s10489-024-05923-y","DOIUrl":"10.1007/s10489-024-05923-y","url":null,"abstract":"<p>Kernel trick has achieved remarkable success in various machine learning tasks, especially those with high-dimensional non-linear data. In addition, these data usually tend to have compact representation that cluster in a low-dimensional subspace. In order to offer a general and comprehensive framework for high-dimensional non-linear data, in this paper, we generalizes multiple kernel learning and subspace learning in a reconstructed reproducing kernel Hilbert space (RKHS) endowed with manifold leaning. First, we construct reconstructed kernels by fusing manifold learning and some base kernel functions, and then learn the optimal kernel by linearly combining the reconstructed kernels. The proposed MKL method can introduce different prior knowledge such as neighborhood information and classification information, to solve different tasks of high-dimensional data. Furthermore, we propose a subspace learning based on RKHS reconstruction, named MVSL for short, of which the objective function is designed with variance maximization criterion, and use an iterative algorithm to solve it. We also incorporates data discriminant information to the learning process of the modified kernel by kernel alignment criterion and a regularization term, to learning the optimal kernel matrix for RKHS reconstruction, and propose another subspace learning method, named Discriminative MVSL. Experimental results on toy and real-world datasets demonstrate that the proposed MKL and subspace learning methods are able to learn the local manifold and the global statistics information of data based on RKHS reconstruction, and thus they achieve a satisfactory performance on classification and dimension reduction tasks.</p>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 2","pages":""},"PeriodicalIF":3.4,"publicationDate":"2024-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142798426","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":"SparseGraphX: exponentially regularized optimal sparse graph for enhanced label propagation","authors":"Kanimozhi M,&nbsp;Sudhakar MS","doi":"10.1007/s10489-024-06007-7","DOIUrl":"10.1007/s10489-024-06007-7","url":null,"abstract":"<div><p>Graph-based semi-supervised learning’s inherent ability to exploit the underlying structure of data distribution for supplementing label propagation has gained momentum over recent years. However, its effectiveness highly relies on the graph's structure quality and deteriorates when dealing with high dimensional, noisy, unevenly distributed data thus, necessitating adaptivity with sparsity in graph construction. To achieve this, an Exponentially Regularized Optimal Sparse Graph (EROSG) is introduced that inculcates these characteristics by exploring local connectivity ensuring efficient label propagation with reduced complexity. Accordingly, EROSG constructs the affinity matrix using a novel distance metric to widen the sample-wise interclass deviation and strengthen the local connectivity. The resulting affinity matrix is then optimized by Lagrangian multipliers with non-negative and SoftMax constraints to yield the adaptive sparse graph facilitating label propagation. Extensive analysis of EROSG on diverse datasets demonstrates consistent and superior accuracy of over 93% with a minimum availability of 5–10% of labeled data which is lacking in its competitors. Also, EROSG’s parameter-free nature lessens realization complexity emphasizing the need of the hour.</p><h3>Graphical abstract</h3><div><figure><div><div><picture><source><img></source></picture></div></div></figure></div></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 2","pages":""},"PeriodicalIF":3.4,"publicationDate":"2024-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142811031","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":"Neural network-based adaptive reinforcement learning for optimized backstepping tracking control of nonlinear systems with input delay","authors":"Boyan Zhu,&nbsp;Hamid Reza Karimi,&nbsp;Liang Zhang,&nbsp;Xudong Zhao","doi":"10.1007/s10489-024-05932-x","DOIUrl":"10.1007/s10489-024-05932-x","url":null,"abstract":"<div><p>In this paper, the problem of adaptive optimized tracking control design is addressed for a class of nonlinear systems in strict-feedback form. The system under consideration contains input delay and has unmeasurable and restricted states within predefined compact sets. First, neural networks (NNs) are employed to approximate the unknown nonlinear dynamics, and an adaptive neural network (NN) state observer is constructed to compensate for the absence of state information. Additionally, by utilizing an auxiliary system compensation method alongside the backstepping technique, the impact of input delay is eliminated, and the generation of intermediate variables is prevented. Second, tan-type barrier optimal cost functions are established for each subsystem within the backstepping method to prevent the state variables from exceeding preselected sets. Moreover, by establishing both actor and critic NNs to execute a reinforcement learning algorithm, the optimal controller and optimal performance index function are evaluated, while relaxing the persistence of excitation condition. According to the Lyapunov stability theorem, it is demonstrated that all signals in the closed-loop system are semi-globally uniformly ultimately bounded (SGUUB), and the output signal accurately tracks a reference trajectory with the desired precision. Finally, a practical simulation example is provided to verify the effectiveness of the proposed control strategy, demonstrating its potential for real-world implementation.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 2","pages":""},"PeriodicalIF":3.4,"publicationDate":"2024-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142811155","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":"KnowGNN: a knowledge-aware and structure-sensitive model-level explainer for graph neural networks","authors":"Yinglong Ma,&nbsp;Xiaofeng Liu,&nbsp;Chenqi Guo,&nbsp;Beihong Jin,&nbsp;Huili Liu","doi":"10.1007/s10489-024-06034-4","DOIUrl":"10.1007/s10489-024-06034-4","url":null,"abstract":"<div><p>Model-level Graph Neural Network (GNN) explanation methods have become essential for understanding the decision-making processes of GNN models on a global scale. Many existing model-level GNN explanation methods often fail to incorporate prior knowledge of the original dataset into the initial explanation state, potentially leading to suboptimal explanation results that diverge from the real distribution of the original data. Moreover, these explainers often treat the nodes and edges within the explanation as independent elements, ignoring the structural relationships between them. This is particularly problematic in graph-based explanation tasks that are highly sensitive to structural information, which may unconsciously make the explanations miss key patterns important for the GNNs’ prediction. In this paper, we introduce KnowGNN, a knowledge-aware and structure-sensitive model-level GNN explanation framework, to explain GNN models in a global view. KnowGNN starts with a <i>seed graph</i> that incorporates prior knowledge of the dataset, ensuring that the final explanations accurately reflect the real data distribution. Furthermore, we construct a structure-sensitive edge mask learning method to refine the explanation process, enhancing the explanations’ ability to capture key features. Finally, we employ a simulated annealing (SA)-based strategy to control the explanation errors efficiently and thus find better explanations. We conduct extensive experiments on four public benchmark datasets. The results show that our method outperforms state-of-the-art explanation approaches by focusing explanations more closely on the actual characteristics of the data.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 2","pages":""},"PeriodicalIF":3.4,"publicationDate":"2024-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142798425","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":"Learner’s cognitive state recognition based on multimodal physiological signal fusion","authors":"Yingting Li,&nbsp;Yue Li,&nbsp;Xiuling He,&nbsp;Jing Fang,&nbsp;ChongYang Zhou,&nbsp;Chenxu Liu","doi":"10.1007/s10489-024-05958-1","DOIUrl":"10.1007/s10489-024-05958-1","url":null,"abstract":"<div><p>It is crucial to evaluate learning outcomes by identifying the cognitive state of the learner during the learning process. Studies utilizing Electroencephalography (EEG) and other peripheral physiological signals, combined with deep learning models, have demonstrated improved performance in cognitive state recognition. These studies have primarily focused on unimodal data, which are vulnerable to various types of noise, making it difficult to fully capture and represent cognitive states. Leveraging the complementarity between multimodal physiological signals can mitigate the impact of anomalies in unimodal data, thereby improving the accuracy and stability of cognitive state recognition. Therefore, this study proposes a multimodal physiological signal feature representation fusion model based on multi-level attention (PSFMMA). The model aims to integrate multimodal physiological signals to identify learners’ cognitive states with greater stability and accuracy. PSFMMA first extracts the temporal features of physiological signals by multiplexing the embedding layer. Subsequently, it generates signal representation vectors by further extracting semantic features through a signal feature mapping layer and enhancing important features with designed attention modules. Finally, the model employs an attention mechanism based on different signal representation vectors to fuse multimodal information for identifying learners’ cognitive states. This study designs various learning activities and collects electroencephalography (EEG), electrodermal activity (EDA), and photoplethysmography (PPG) data from 22 participants engaging in these activities to create the Based on Learning Activities Collection (BLAC) dataset. The proposed model was evaluated on the BLAC dataset, achieving an identification accuracy of 96.32 ± 0.32%. The results demonstrate that the model can effectively recognize learners’ cognitive states. Furthermore, the model’s performance was validated on the publicly available emotion classification dataset DEAP, attaining an accuracy of 99.15 ± 0.12%. The source code is available at https://github.com/chengshudaxuesheng/PSFMMA.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 2","pages":""},"PeriodicalIF":3.4,"publicationDate":"2024-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142798494","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":"Dual-path decoder architecture for semantic segmentation of wheat ears","authors":"Lihui Wang,&nbsp;Yu Chen","doi":"10.1007/s10489-024-06023-7","DOIUrl":"10.1007/s10489-024-06023-7","url":null,"abstract":"<div><p>In this study, a dual-path decoder segmentation network (DPDS) is presented, which innovatively introduces a dual-path structure into a semantic segmentation network incorporating atrous spatial pyramid pooling (ASPP). A novel loss function, boundary focal loss (BFLoss), is designed specifically for wheat ears segmentation scenarios, which adaptively adjusts weights for different pixel points through the binarization of boundary information, focusing the training on the edges of wheat ears. It is suggested to apply the DPDS network in conjunction with BFLoss to the semantic segmentation of wheat ears. The experimental results demonstrated that BFLoss possesses advantages over commonly used binary cross entropy loss (BCELoss) and focal loss in semantic segmentation. Additionally, the dual-path decoder architecture was proved to reach higher precision than activating only one of the pathways. In comparative experiments with established semantic segmentation networks, the DPDS model achieved the best performance on several evaluation metrics, and attained a balance between precision and recall. Notably, the combination of DPDS and BFLoss achieved a 91.86% F1 score on the wheat ears semantic segmentation test dataset. Therefore, the DPDS model can be effectively applied to semantic segmentation scenarios of crops like wheat, and also provides new insights for the improvement of existing networks. Code is available at https://github.com/awesome-pythoner/dual-path-decoder-segment.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 2","pages":""},"PeriodicalIF":3.4,"publicationDate":"2024-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142798428","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":"An fMRI-based auditory decoding framework combined with convolutional neural network for predicting the semantics of real-life sounds from brain activity","authors":"Mingqian Zhao,&nbsp;Baolin Liu","doi":"10.1007/s10489-024-05873-5","DOIUrl":"10.1007/s10489-024-05873-5","url":null,"abstract":"<div><p>Semantic decoding, understood as predicting the semantic information carried by stimuli presented to subjects based on neural signals, is an active area of research. Previous studies have mainly focused on the visual perception process, with relatively little attention paid to complex auditory decoding. Moreover, simple linear models do not achieve optimal performance for the mapping between brain signals and natural sounds. Therefore, a robust approach that combines a pretrained audio tagging model and a nonlinear multilayer perceptron model was proposed to transfer information from non-invasive measured brain activity to deep learning features, thereby generating sound semantics. The results achieved on previously unseen subjects, training without data from the target subjects, and ultimately predicting natural-sound semantics from the fMRI data of unseen subjects. In the study with 30 subjects, the framework in research achieves 23.21% Top-1 and 51.88% Top-5 accuracy scores, which significantly exceed the baseline scores and the scores of other classical algorithms. The approach advances the decoding of auditory neural excitation with the help of deep neural networks, and the proposed model successfully completes a challenging cross-subject decoding task.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 2","pages":""},"PeriodicalIF":3.4,"publicationDate":"2024-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142798359","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":"Multivariate time series classification based on spatial-temporal attention dynamic graph neural network","authors":"Lipeng Qian,&nbsp;Qiong Zuo,&nbsp;Haiguang Liu,&nbsp;Hong Zhu","doi":"10.1007/s10489-024-06014-8","DOIUrl":"10.1007/s10489-024-06014-8","url":null,"abstract":"<div><p>Multivariate time series classification (MVTSC) has significant potential for Internet of Things applications. Recently, deep learning (DL) and graph neural network (GNN) methods have been applied to MVTSC tasks. Unfortunately, DL-based methods ignore explicit inter-series correlation modeling. Most existing GNN-based methods treat MVTS data as a static graph spanning the entire temporal trajectory, which inadequately captures changes in inter-series local correlations. To address this problem, we propose the spatial-temporal attention dynamic GNN (STADGNN), which explicitly models dynamic inter-series correlations by constructing the MVTS data into a dynamic graph structure at a finer granularity. It combines discrete Fourier transform (DFT) and discrete wavelet transform (DWT), which extract the global and local features of MVTS data in an end-to-end framework. In dynamic graph learning, spatial-temporal attention mechanisms are employed to simultaneously capture changes in inter-series local correlations and intra-series temporal dependencies without relying on predefined priors. Experimental results on 25 UEA datasets indicate that the STADGNN outperforms existing DL-based and GNN-based baseline models in MVTSC tasks.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 2","pages":""},"PeriodicalIF":3.4,"publicationDate":"2024-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142798360","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 multi-focus image fusion network with local-global joint attention module","authors":"Xinheng Zou,&nbsp;You Yang,&nbsp;Hao Zhai,&nbsp;Weiping Jiang,&nbsp;Xin Pan","doi":"10.1007/s10489-024-06039-z","DOIUrl":"10.1007/s10489-024-06039-z","url":null,"abstract":"<div><p>Multi-focus image fusion can obtain high-quality images by overcoming the limited depth of field of optical lenses. Benefiting from deep learning, we design a local-global joint attention module and propose a novel multi-focus image fusion network. The module essentially is an attention module. Local and global features are extracted respectively through point-wise convolution and spatial pyramid pooling. A joint attention map is produced by reducing the dimension and fusing these two features. The proposed network is mainly composed of a feature fusion module and two weight-shared dense feature extraction modules, each connected to six consecutive attention modules. Such design has two benefits: adequate extraction of initial features and capturing of local and global features. Subjective visual evaluation demonstrates that the proposed network can preserve the authenticity of fusion results. And it also reduces the appearance of artifacts and detail losses between the focus and defocus regions. Objective metric evaluation shows that the proposed network outperforms most of the existing models, such as SwinFusion, GACN, and UFA-FUSE, in Lytro, MFI-WHU, and MFFW datasets. Ablation experiments demonstrate that the design of attention and the overall framework of the network is reasonable. Overall, the proposed model can finish the multi-focus image fusion task with high quality.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 2","pages":""},"PeriodicalIF":3.4,"publicationDate":"2024-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142798303","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":"Quality prediction of multi-stage batch process based on integrated ConvBiGRU with attention mechanism","authors":"Kai Liu,&nbsp;Xiaoqiang Zhao,&nbsp;Miao Mou,&nbsp;Yongyong Hui","doi":"10.1007/s10489-024-06002-y","DOIUrl":"10.1007/s10489-024-06002-y","url":null,"abstract":"<div><p>It is important for quality prediction and monitoring to ensure the safe operation of the process. When constructing a prediction model, it is crucial to choose appropriate input variables to influence the online prediction performance and quality monitoring. Data-driven techniques have been widely used for prediction and monitoring of quality variables, but there are some difficulties in the application of batch processes, three-dimensional characteristics of data, different initial conditions, and multi-stage characteristics within batches. Therefore, we propose a quality prediction model of multi-stage batch process based on integrated ConvBiGRU with attention mechanism (MI-ConvBiGRU-AM). Firstly, Firstly, the original 3D data are expanded into 2D time slices by the batch-variable expansion method. Secondly, the 2D time slices are clustered to complete stage identification using the improved affine propagation clustering method based on the design of the Markov chain similarity matrix. At each stage, we select product quality-related modeling variables using the Maximum Relevance Minimum Redundancy (mRMR). Then, the selected variables are used to train a convolutional bi-directional gated recurrent unit with an attention mechanism (ConvBiGRU-AM). Finally, ConvBiGRU-AM model for each stage is integrated together a whole prediction model for the entire process to accomplish quality prediction, and the prediction residuals are utilized for quality monitoring. The validity of the proposed method was verified by Industrial-scale fed-batch fermentation (IFBF) process and the Hot strip mill (HSM) process. For the IFBF process, the model achieved an FDR of 99.73%, FAR of 0.54%, MAE of 0.0043, RMSE of 0.0396, MAPE of 0.0121, and R² of 0.9971. For the HSM process, the results were an FDR of 99.95%, FAR of 0.25%, MAE of 0.0053, RMSE of 0.0111, MAPE of 0.1539, and R² of 0.9990. These results demonstrate that the proposed method significantly improves prediction accuracy and achieves better quality monitoring compared to existing methods, highlighting its effectiveness for industrial applications.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 2","pages":""},"PeriodicalIF":3.4,"publicationDate":"2024-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142798356","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}