IEEE transactions on artificial intelligence最新文献_第10页

A Temporal–Spatial Graph Network With a Learnable Adjacency Matrix for Appliance-Level Electricity Consumption Prediction 一种具有可学习邻接矩阵的时空图网络用于电器级用电量预测

IEEE transactions on artificial intelligence Pub Date : 2024-11-28 DOI: 10.1109/TAI.2024.3507734

Dandan Li;Jiaxing Xia;Jiangfeng Li;Changjiang Xiao;Vladimir Stankovic;Lina Stankovic;Qingjiang Shi

{"title":"A Temporal–Spatial Graph Network With a Learnable Adjacency Matrix for Appliance-Level Electricity Consumption Prediction","authors":"Dandan Li;Jiaxing Xia;Jiangfeng Li;Changjiang Xiao;Vladimir Stankovic;Lina Stankovic;Qingjiang Shi","doi":"10.1109/TAI.2024.3507734","DOIUrl":"https://doi.org/10.1109/TAI.2024.3507734","url":null,"abstract":"Predicting the electricity consumption of individual appliances, known as appliance-level energy consumption (ALEC) prediction, is essential for effective energy management and conservation. Despite its importance, research in this area is limited and faces several challenges: 1) the correlation between the usage of different appliances has rarely been considered for ALEC prediction; 2) a learnable strategy for obtaining the optimal correlation between different appliance behaviors is lacking; and 3) it is difficult to accurately quantify the usage relationship among different appliances. To address these issues, we propose a graph-based temporal–spatial network that employs a learnable adjacency matrix for appliance-level load prediction in this work. The network comprises a temporal graph convolutional network (TGCN) and a learnable adjacency matrix that enables us to utilize correlations between appliances and quantify their relationships. To validate our approach, we compared our model with six others: a TGCN model with a fixed adjacency matrix where all elements are set to 0; a TGCN model with a fixed adjacency matrix where all elements are set to 0.5, except for the diagonal; a TGCN model with a randomly generated adjacency matrix, except for the diagonal; an Aug-LSTM model; a model with ResNetPlus architecture; and a feed-forward deep neural network. Five houses in four datasets: AMPDs, REFIT, UK-DALE, and SC-EDNRR are utilized. The metrics used in this study include root mean square error, explained variance score, mean absolute error, F-norm and coefficient of determination. Our experiments have validated the accuracy and practicality of our proposed approach across different datasets.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"6 4","pages":"989-1002"},"PeriodicalIF":0.0,"publicationDate":"2024-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143740203","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Industrial Process Monitoring Based on Deep Gaussian and Non-Gaussian Information Fusion Framework 基于深度高斯与非高斯信息融合框架的工业过程监控

IEEE transactions on artificial intelligence Pub Date : 2024-11-28 DOI: 10.1109/TAI.2024.3507732

Zhiqiang Ge

{"title":"Industrial Process Monitoring Based on Deep Gaussian and Non-Gaussian Information Fusion Framework","authors":"Zhiqiang Ge","doi":"10.1109/TAI.2024.3507732","DOIUrl":"https://doi.org/10.1109/TAI.2024.3507732","url":null,"abstract":"For industrial process monitoring, Gaussian and non-Gaussian data-driven models are two important representatives that have been developed separately in the past years. Although several attempts have been made to combine Gaussian and non-Gaussian data information for integrated process monitoring, this information fusion strategy can be further enhanced under the idea and framework of deep learning. Particularly, through collaborative learning and layer-by-layer information transformation, more patterns of both Gaussian and non-Gaussian components can be effectively extracted in different hidden layers of the deep model. Then, a further Bayesian model fusion strategy is formulated to ensemble monitoring results from both Gaussian and non-Gaussian data-driven models. Therefore, the main contribution of this article is to propose a deep Gaussian and non-Gaussian information fusion framework for data-driven industrial process monitoring. Both feasibility and superiority of the developed model are confirmed through a detailed industrial benchmark case study. Compared to both Gaussian and non-Gaussian deep models, the new deep information fusion model has obtained more satisfactory monitoring results.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"6 4","pages":"979-988"},"PeriodicalIF":0.0,"publicationDate":"2024-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143740310","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

CH-Net: A Cross Hybrid Network for Medical Image Segmentation CH-Net：用于医学图像分割的交叉混合网络

IEEE transactions on artificial intelligence Pub Date : 2024-11-20 DOI: 10.1109/TAI.2024.3503541

Jiale Li;Aiping Liu;Wei Wei;Ruobing Qian;Xun Chen

{"title":"CH-Net: A Cross Hybrid Network for Medical Image Segmentation","authors":"Jiale Li;Aiping Liu;Wei Wei;Ruobing Qian;Xun Chen","doi":"10.1109/TAI.2024.3503541","DOIUrl":"https://doi.org/10.1109/TAI.2024.3503541","url":null,"abstract":"Accurate and automated segmentation of medical images plays a crucial role in diagnostic evaluation and treatment planning. In recent years, hybrid models have gained considerable popularity in diverse medical image segmentation tasks, as they leverage the benefits of both convolution and self-attention to capture local and global dependencies simultaneously. However, most existing hybrid models treat convolution and self-attention as independent components and integrate them using simple fusion methods, neglecting the potential complementary information between their weight allocation mechanisms. To address this issue, we propose a cross hybrid network (CH-Net) for medical image segmentation, in which convolution and self-attention are hybridized in a cross-collaborative manner. Specifically, we introduce a cross hybrid module (CHM) between the parallel convolution layer and self-attention layer in each building block of CH-Net. This module extracts attention with distinct dimensional information from convolution and self-attention, respectively, and uses this complementary information to enhance the feature representation of both components. In contrast to the traditional approach where each module learned independently, the CHM facilitates the interactive learning of complementary information between convolutional layer and self-attention layer, which significantly enhances the segmentation capabilities of the model. The superiority of our approach over various hybrid models is demonstrated through experimental evaluations conducted on three publicly available benchmarks: ACDC, synapse, and EM.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"6 4","pages":"934-944"},"PeriodicalIF":0.0,"publicationDate":"2024-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143740311","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

DGeC: Dynamically and Globally Enhanced Convolution 动态和全局增强卷积

IEEE transactions on artificial intelligence Pub Date : 2024-11-20 DOI: 10.1109/TAI.2024.3502577

Zihang Zhang;Yuling Liu;Zhili Zhou;Gaobo Yang;Xin Liao;Q. M. Jonathan Wu

{"title":"DGeC: Dynamically and Globally Enhanced Convolution","authors":"Zihang Zhang;Yuling Liu;Zhili Zhou;Gaobo Yang;Xin Liao;Q. M. Jonathan Wu","doi":"10.1109/TAI.2024.3502577","DOIUrl":"https://doi.org/10.1109/TAI.2024.3502577","url":null,"abstract":"We explore the reasons for the poorer feature extraction ability of vanilla convolution and discover that there mainly exist three key factors that restrict its representation capability, i.e., regular sampling, static aggregation, and limited receptive field. With the cost of extra parameters and computations, existing approaches merely alleviate part of the limitations. It drives us to seek a more lightweight operator to further improve the extracted image features. Through a closer examination of the convolution process, we discover that it is composed of two distinct interactions: spatial-wise interaction and channel-wise interaction. Based on this discovery, we decouple the convolutional blocks into these two interactions which not only reduces the parameters and computations but also enables a richer ensemble of interactions. Then, we propose the dynamically and globally enhanced convolution (DGeC), which includes several components as follows: a dynamic area perceptor block (DAP) that dynamically samples spatial cues, an adaptive global context block (AGC) that introduces the location-aware global image information, and a channel attention perceptor block (CAP) that merges different channel-wise features. The experiments on ImageNet for image classification and on COCO-2017 for object detection validate the effectiveness of DGeC. As a result, our proposed method consistently improves the performance with fewer parameters and computations. In particular, DGeC achieves a 3.1% improvement in top-1 accuracy on ImageNet dataset compared to ResNet50. Moreover, with Faster RCNN and RetinaNet, our DGeC-ResNet50 also consistently outperforms ResNet and ResNeXt.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"6 4","pages":"921-933"},"PeriodicalIF":0.0,"publicationDate":"2024-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143740315","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Consistent Counterfactual Explanations via Anomaly Control and Data Coherence 基于异常控制和数据一致性的一致反事实解释

IEEE transactions on artificial intelligence Pub Date : 2024-11-19 DOI: 10.1109/TAI.2024.3496616

Maria Movin;Federico Siciliano;Rui Ferreira;Fabrizio Silvestri;Gabriele Tolomei

{"title":"Consistent Counterfactual Explanations via Anomaly Control and Data Coherence","authors":"Maria Movin;Federico Siciliano;Rui Ferreira;Fabrizio Silvestri;Gabriele Tolomei","doi":"10.1109/TAI.2024.3496616","DOIUrl":"https://doi.org/10.1109/TAI.2024.3496616","url":null,"abstract":"Algorithmic recourses are popular methods to provide individuals impacted by machine learning models with recommendations on feasible actions for a more favorable prediction. Most of the previous algorithmic recourse methods work under the assumption that the predictive model does not change over time. However, in reality, models in deployment may both be periodically retrained and have their architecture changed. Therefore, it is desirable that the recourse should remain valid when such a model update occurs, unless new evidence arises. We call this feature <italic>consistency</i>. This article presents anomaly control and data coherence (ACDC), a novel model-agnostic recourse method that generates counterfactual explanations, i.e., instance-level recourses. ACDC is inspired by anomaly detection methods and uses a one-class classifier to aid the search for valid, consistent, and feasible counterfactual explanations. The one-class classifier asserts that the generated counterfactual explanations lie on the data manifold and are not outliers of the target class. We compare ACDC against several state-of-the-art recourse methods across four datasets. Our experiments show that ACDC outperforms baselines both in generating consistent counterfactual explanations, and in generating feasible and plausible counterfactual explanations, while still having proximity measures similar to the baseline methods targeting the data manifold.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"6 4","pages":"794-804"},"PeriodicalIF":0.0,"publicationDate":"2024-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143740316","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Adversarial Masked Autoencoders Are Robust Vision Learners 对抗性蒙面自编码器是鲁棒的视觉学习器

IEEE transactions on artificial intelligence Pub Date : 2024-11-15 DOI: 10.1109/TAI.2024.3497912

Yuchong Yao;Nandakishor Desai;Marimuthu Palaniswami

引用次数: 0

Multiobjective Optimization for Traveling Salesman Problem: A Deep Reinforcement Learning Algorithm via Transfer Learning 旅行商问题的多目标优化：基于迁移学习的深度强化学习算法

IEEE transactions on artificial intelligence Pub Date : 2024-11-15 DOI: 10.1109/TAI.2024.3499946

Le-yang Gao;Rui Wang;Zhao-hong Jia;Chuang Liu

{"title":"Multiobjective Optimization for Traveling Salesman Problem: A Deep Reinforcement Learning Algorithm via Transfer Learning","authors":"Le-yang Gao;Rui Wang;Zhao-hong Jia;Chuang Liu","doi":"10.1109/TAI.2024.3499946","DOIUrl":"https://doi.org/10.1109/TAI.2024.3499946","url":null,"abstract":"A wide range of real applications can be modelled as the multiobjective traveling salesman problem (MOTSP), one of typical combinatorial optimization problems. Meta-heuristics can be used to address MOTSP. However, due to involving iteratively searching large solution space, they often entail significant computation time. Recently, deep reinforcement learning (DRL) algorithms have been employed in generating approximate optimal solutions to the single objective traveling salesman problems, as well as MOTSPs. This study proposes a multiobjective optimization algorithm based on DRL, called multiobjective pointer network (MOPN), where the input structure of the pointer network is redesigned to be applied to MOTSP. Furthermore, a training strategy utilizing a representative model and transfer learning is introduced to enhance the performance of MOPN. The proposed MOPN is insensitive to problem scale, meaning that a trained MOPN can address MOTSPs with different scales. Compared to meta-heuristics, MOPN takes much less time on forward propagation to obtain the pareto front. To verify the performance of our model, extensive experiments are conducted on three different MOTSPs to compare the MOPN with two state-of-the-art DRL models and two multiobjective meta-heuristics. Experimental results demonstrate that the proposed MOPN obtains the best solution with the least training time among all the compared DRL methods.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"6 4","pages":"896-908"},"PeriodicalIF":0.0,"publicationDate":"2024-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143740205","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Active Robust Adversarial Reinforcement Learning Under Temporally Coupled Perturbations 时间耦合扰动下的主动鲁棒对抗强化学习

IEEE transactions on artificial intelligence Pub Date : 2024-11-15 DOI: 10.1109/TAI.2024.3499938

Jiacheng Yang;Yuanda Wang;Lu Dong;Lei Xue;Changyin Sun

{"title":"Active Robust Adversarial Reinforcement Learning Under Temporally Coupled Perturbations","authors":"Jiacheng Yang;Yuanda Wang;Lu Dong;Lei Xue;Changyin Sun","doi":"10.1109/TAI.2024.3499938","DOIUrl":"https://doi.org/10.1109/TAI.2024.3499938","url":null,"abstract":"Robust reinforcement learning (RL) aims to improve the generalization of agents under model mismatch. As a major branch of robust RL, adversarial approaches formulate the problem as a zero-sum game in which adversaries seek to apply worst case perturbations to the dynamics. However, the potential constraints of adversarial perturbations are seldom addressed in existing approaches. In this article, we consider temporally coupled settings, where adversarial perturbations change continuously at a bounded rate. This kind of constraint can commonly arise in a variety of real-world situations (e.g., changes in wind speed and ocean currents). We propose a novel robust RL approach, named active robust adversarial RL (ARA-RL), that tackles this problem in an adversarial architecture. First, we introduce a type of RL adversary that generates temporally coupled perturbations on agent actions. Then, we embed a diagnostic module in the RL agent, enabling it to actively detect temporally coupled perturbations in unseen environments. Through adversarial training, the agent seeks to maximize its worst case performance and thus achieve robustness under perturbations. Finally, extensive experiments demonstrate that our proposed approach provides significant robustness against temporally coupled perturbations and outperforms other baselines on several continuous control tasks.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"6 4","pages":"874-884"},"PeriodicalIF":0.0,"publicationDate":"2024-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143740233","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

LoRaDIP: Low-Rank Adaptation With Deep Image Prior for Generative Low-Light Image Enhancement LoRaDIP：基于深度图像先验的低秩自适应生成式低光图像增强

IEEE transactions on artificial intelligence Pub Date : 2024-11-15 DOI: 10.1109/TAI.2024.3499950

Zunjin Zhao;Daming Shi

{"title":"LoRaDIP: Low-Rank Adaptation With Deep Image Prior for Generative Low-Light Image Enhancement","authors":"Zunjin Zhao;Daming Shi","doi":"10.1109/TAI.2024.3499950","DOIUrl":"https://doi.org/10.1109/TAI.2024.3499950","url":null,"abstract":"This article presents LoRaDIP, a novel low-light image enhancement (LLIE) model based on deep image priors (DIPs). While DIP-based enhancement models are known for their zero-shot learning, their expensive computational cost remains a challenge. In addressing this issue, our proposed LoRaDIP introduces a low-rank adaptation technique, significantly reducing computational expenses without compromising performance. The contributions of this work are threefold. First, we eliminate the need for estimating initial illumination and reflectance, opting instead to directly estimate the illumination map from the observed image in a generative fashion. The illumination is parameterized by a DIP network. Second, considering the overparameterization of DIP networks, we introduce a low-rank adaptation technique to decrease the number of trainable parameters, thereby reducing computational demands. Third, differing from the existing DIP-based models that rely on a preset fixed number of iterations to halt the optimization process of Retinex decomposition, we propose an automatic stopping criterion based on stable rank, preventing unnecessary iterations. LoRaDIP not only inherits the advantage of requiring only the single input image but also exhibits reduced computational costs while maintaining or even surpassing the performance of state-of-the-art models.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"6 4","pages":"909-920"},"PeriodicalIF":0.0,"publicationDate":"2024-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143740234","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Adaptive Neural Network Finite-Time Event Triggered Intelligent Control for Stochastic Nonlinear Systems With Time-Varying Constraints 时变约束随机非线性系统的自适应神经网络有限时间事件触发智能控制

IEEE transactions on artificial intelligence Pub Date : 2024-11-13 DOI: 10.1109/TAI.2024.3497913

Jia Liu;Jiapeng Liu;Qing-Guo Wang;Jinpeng Yu

引用次数: 0