CAAI Transactions on Intelligence Technology最新文献

Vertical federated learning (VFL) can learn a common machine learning model over vertically partitioned datasets. However, VFL are faced with these thorny problems: (1) both the training and prediction are very vulnerable to stragglers; (2) most VFL methods can only support a specific machine learning model. Suppose that VFL incorporates the features of centralised learning, then the above issues can be alleviated. With that in mind, this paper proposes a new VFL scheme, called FedBoost, which makes private parties upload the compressed partial order relations to the honest but curious server before training and prediction. The server can build a machine learning model and predict samples on the union of coded data. The theoretical analysis indicates that the absence of any private party will not affect the training and prediction as long as a round of communication is achieved. Our scheme can support canonical tree-based models such as Tree Boosting methods and Random Forests. The experimental results also demonstrate the availability of our scheme.

One of the most widely used fuzzy linear programming models is the multi-objective interval type-2 fuzzy linear programming (IT2FLP) model, which is of particular importance due to the simultaneous integration of multiple criteria and objectives in a single problem, the fuzzy nature of this type of problems, and thus, its closer similarity to real-world problems. So far, many studies have been done for the IT2FLP problem with uncertainties of the vagueness type. However, not enough studies have been done regarding the multi-objective interval type-2 fuzzy linear programming (MOIT2FLP) problem with uncertainties of the vagueness type. As an innovation, this study investigates the MOIT2FLP problem with vagueness-type uncertainties, which are represented by membership functions (MFs) in the problem. Depending on the localisation of vagueness in the problem, that is, vagueness in the objective function vector, vagueness in the technological coefficients, vagueness in the resources vector, and any possible combination of them, various problems may arise. Furthermore, to solve problems with MOIT2FLP, first, using the weighted sum method as an efficient and effective method, each of the MOIT2FLP problems is converted into a single-objective problem. In this research, these types of problems are introduced, their MFs are stated, and different solution methods are suggested. For each of the proposed methods, the authors have provided an example and presented the results in the corresponding tables.

Hardware-based sensing frameworks such as cooperative fuel research engines are conventionally used to monitor research octane number (RON) in the petroleum refining industry. Machine learning techniques are employed to predict the RON of integrated naphtha reforming and isomerisation processes. A dynamic Aspen HYSYS model was used to generate data by introducing artificial uncertainties in the range of ±5% in process conditions, such as temperature, flow rates, etc. The generated data was used to train support vector machines (SVM), Gaussian process regression (GPR), artificial neural networks (ANN), regression trees (RT), and ensemble trees (ET). Hyperparameter tuning was performed to enhance the prediction capabilities of GPR, ANN, SVM, ET and RT models. Performance analysis of the models indicates that GPR, ANN, and SVM with R² values of 0.99, 0.978, and 0.979 and RMSE values of 0.108, 0.262, and 0.258, respectively performed better than the remaining models and had the prediction capability to capture the RON dependence on predictor variables. ET and RT had an R² value of 0.94 and 0.89, respectively. The GPR model was used as a surrogate model for fitness function evaluations in two optimisation frameworks based on genetic algorithm and particle swarm method. Optimal parameter values found by the optimisation methodology increased the RON value by 3.52%. The proposed methodology of surrogate-based optimisation will provide a platform for plant-level implementation to realise the concept of industry 4.0 in the refinery.

Continuous emotion recognition is to predict emotion states through affective information and more focus on the continuous variation of emotion. Fusion of electroencephalography (EEG) and facial expressions videos has been used in this field, while there are with some limitations in current researches, such as hand-engineered features, simple approaches to integration. Hence, a new continuous emotion recognition model is proposed based on the fusion of EEG and facial expressions videos named residual multimodal Transformer (RMMT). Firstly, the Resnet50 and temporal convolutional network (TCN) are utilised to extract spatiotemporal features from videos, and the TCN is also applied to process the computed EEG frequency power to acquire spatiotemporal features of EEG. Then, a multimodal Transformer is used to fuse the spatiotemporal features from the two modalities. Furthermore, a residual connection is introduced to fuse shallow features with deep features which is verified to be effective for continuous emotion recognition through experiments. Inspired by knowledge distillation, the authors incorporate feature-level loss into the loss function to further enhance the network performance. Experimental results show that the RMMT reaches a superior performance over other methods for the MAHNOB-HCI dataset. Ablation studies on the residual connection and loss function in the RMMT demonstrate that both of them is functional.

Image clustering has received significant attention due to the growing importance of image recognition. Researchers have explored Riemannian manifold clustering, which is capable of capturing the non-linear shapes found in real-world datasets. However, the complexity of image data poses substantial challenges for modelling and feature extraction. Traditional methods such as covariance matrices and linear subspace have shown promise in image modelling, and they are still in their early stages and suffer from certain limitations. However, these include the uncertainty of representing data using only one Riemannian manifold, limited feature extraction capacity of single kernel functions, and resulting incomplete data representation and redundancy. To overcome these limitations, the authors propose a novel approach called join multiple Riemannian manifold representation and multi-kernel non-redundancy for image clustering (MRMNR-MKC). It combines covariance matrices with linear subspace to represent data and applies multiple kernel functions to map the non-linear structural data into a reproducing kernel Hilbert space, enabling linear model analysis for image clustering. Additionally, the authors use matrix-induced regularisation to improve the clustering kernel selection process by reducing redundancy and assigning lower weights to identical kernels. Finally, the authors also conducted numerous experiments to evaluate the performance of our approach, confirming its superiority to state-of-the-art methods on three benchmark datasets.

Diagnosing individuals with autism spectrum disorder (ASD) accurately faces great challenges in clinical practice, primarily due to the data's high heterogeneity and limited sample size. To tackle this issue, the authors constructed a deep graph convolutional network (GCN) based on variable multi-graph and multimodal data (VMM-DGCN) for ASD diagnosis. Firstly, the functional connectivity matrix was constructed to extract primary features. Then, the authors constructed a variable multi-graph construction strategy to capture the multi-scale feature representations of each subject by utilising convolutional filters with varying kernel sizes. Furthermore, the authors brought the non-imaging information into the feature representation at each scale and constructed multiple population graphs based on multimodal data by fully considering the correlation between subjects. After extracting the deeper features of population graphs using the deep GCN(DeepGCN), the authors fused the node features of multiple subgraphs to perform node classification tasks for typical control and ASD patients. The proposed algorithm was evaluated on the Autism Brain Imaging Data Exchange I (ABIDE I) dataset, achieving an accuracy of 91.62% and an area under the curve value of 95.74%. These results demonstrated its outstanding performance compared to other ASD diagnostic algorithms.

Exploiting the hierarchical dependence behind user behaviour is critical for click-through rate (CRT) prediction in recommender systems. Existing methods apply attention mechanisms to obtain the weights of items; however, the authors argue that deterministic attention mechanisms cannot capture the hierarchical dependence between user behaviours because they treat each user behaviour as an independent individual and cannot accurately express users' flexible and changeable interests. To tackle this issue, the authors introduce the Bayesian attention to the CTR prediction model, which treats attention weights as data-dependent local random variables and learns their distribution by approximating their posterior distribution. Specifically, the prior knowledge is constructed into the attention weight distribution, and then the posterior inference is utilised to capture the implicit and flexible user intentions. Extensive experiments on public datasets demonstrate that our algorithm outperforms state-of-the-art algorithms. Empirical evidence shows that random attention weights can predict user intentions better than deterministic ones.

Recovering 3D human meshes from monocular images is an inherently ill-posed and challenging task due to depth ambiguity, joint occlusion, and truncation. However, most existing approaches do not model such uncertainties, typically yielding a single reconstruction for one input. In contrast, the ambiguity of the reconstruction is embraced and the problem is considered as an inverse problem for which multiple feasible solutions exist. To address these issues, the authors propose a multi-hypothesis approach, multi-hypothesis human mesh recovery (MH-HMR), to efficiently model the multi-hypothesis representation and build strong relationships among the hypothetical features. Specifically, the task is decomposed into three stages: (1) generating a reasonable set of initial recovery results (i.e., multiple hypotheses) given a single colour image; (2) modelling intra-hypothesis refinement to enhance every single-hypothesis feature; and (3) establishing inter-hypothesis communication and regressing the final human meshes. Meanwhile, the authors take further advantage of multiple hypotheses and the recovery process to achieve human mesh recovery from multiple uncalibrated views. Compared with state-of-the-art methods, the MH-HMR approach achieves superior performance and recovers more accurate human meshes on challenging benchmark datasets, such as Human3.6M and 3DPW, while demonstrating the effectiveness across a variety of settings. The code will be publicly available at https://cic.tju.edu.cn/faculty/likun/projects/MH-HMR.