Applied Intelligence最新文献_第6页

Retraction Note: Incremental deep forest for multi-label data streams learning 撤稿说明：多标签数据流学习的增量深度森林

IF 3.4 2区计算机科学

Applied Intelligence Pub Date : 2024-12-16 DOI: 10.1007/s10489-024-06185-4

Shunpan Liang, Weiwei Pan, Dianlong You, Ze Liu, Ling Yin

引用次数: 0

Prompt-guided and degradation prior supervised transformer for adverse weather image restoration

IF 3.4 2区计算机科学

Applied Intelligence Pub Date : 2024-12-16 DOI: 10.1007/s10489-024-06050-4

Weihan Liu, Mingwen Shao, Lingzhuang Meng, Yuanjian Qiao, Zhiyuan Bao

{"title":"Prompt-guided and degradation prior supervised transformer for adverse weather image restoration","authors":"Weihan Liu, Mingwen Shao, Lingzhuang Meng, Yuanjian Qiao, Zhiyuan Bao","doi":"10.1007/s10489-024-06050-4","DOIUrl":"10.1007/s10489-024-06050-4","url":null,"abstract":"<div><p>The restoration of images affected by adverse weather conditions is hindered by two main challenges. The first is the restoration of fine details in severely degraded regions. The second is the interference between different types of degradation data during the model training process, which consequently reduces the restoration performance of the model on individual tasks. In this work, we propose a Transformer-based All-in-one image restoration model, called PDFormer, to alleviate the aforementioned issues. Initially, we designed an effective transformer network to capture the global contextual information in the image and utilize this information to restore the locally severely degraded regions better. Additionally, to alleviate the interference between different types of degraded data, we introduced two specialized modules: the Prompt-Guided Feature Refinement Module (RGRM) and the Degradation Mask Supervised Attention Module (MSAM). The former employs a set of learnable prompt parameters to generate prompt information, which interacts with the degraded feature through cross-attention, enhancing the discriminative ability of different degraded features in the latent space. The latter, under the supervision of the degraded mask prior, assists the model in differentiating between different degradation types and locating the regions and sizes of the degradations. The designs above permit greater flexibility in handling specific degradation scenarios, enabling the adaptive removal of different degradation artifacts to restore fine details in images. Performance evaluation on both synthetic and real data has demonstrated that our method surpasses existing approaches, achieving state-of-the-art (SOTA) performance.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 2","pages":""},"PeriodicalIF":3.4,"publicationDate":"2024-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142826378","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}

引用次数: 0

Document-level relation extraction via commonsense knowledge enhanced graph representation learning 通过常识性知识增强图表示学习进行文档级关系提取

IF 3.4 2区计算机科学

Applied Intelligence Pub Date : 2024-12-14 DOI: 10.1007/s10489-024-05985-y

Qizhu Dai, Rongzhen Li, Zhongxuan Xue, Xue Li, Jiang Zhong

{"title":"Document-level relation extraction via commonsense knowledge enhanced graph representation learning","authors":"Qizhu Dai, Rongzhen Li, Zhongxuan Xue, Xue Li, Jiang Zhong","doi":"10.1007/s10489-024-05985-y","DOIUrl":"10.1007/s10489-024-05985-y","url":null,"abstract":"<div><p>Document-level relation extraction (DocRE) aims to reason about complex relational facts among entities by reading, inferring, and aggregating among entities over multiple sentences in a document. Existing studies construct document-level graphs to enrich interactions between entities. However, these methods pay more attention to the entity nodes and their connections, regardless of the rich knowledge entailed in the original corpus.In this paper, we propose a commonsense knowledge enhanced document-level graph representation, called CGDRE, which delves into the semantic knowledge of the original corpus and improves the ability of DocRE. Firstly, we use coreference contrastive learning to capture potential commonsense knowledge. Secondly, we construct a heterogeneous graph to enhance the graph structure information according to the original document and commonsense knowledge. Lastly, CGDRE infers relations on the aggregated graph and uses focal loss to train the model. Remarkably, it is amazing that CGDRE can effectively alleviate the long-tailed distribution problem in DocRE. Experiments on the public datasets DocRED, DialogRE, and MPDD show that CGDRE can significantly outperform other baselines, achieving a significant performance improvement. Extensive analyses demonstrate that the performance of our CGDRE is contributed by the capture of commonsense knowledge enhanced graph relation representation.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 2","pages":""},"PeriodicalIF":3.4,"publicationDate":"2024-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142821422","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}

引用次数: 0

DTGA: an in-situ training scheme for memristor neural networks with high performance DTGA：高性能忆阻器神经网络的原位训练方案

IF 3.4 2区计算机科学

Applied Intelligence Pub Date : 2024-12-14 DOI: 10.1007/s10489-024-06091-9

Siyuan Shen, Mingjian Guo, Lidan Wang, Shukai Duan

{"title":"DTGA: an in-situ training scheme for memristor neural networks with high performance","authors":"Siyuan Shen, Mingjian Guo, Lidan Wang, Shukai Duan","doi":"10.1007/s10489-024-06091-9","DOIUrl":"10.1007/s10489-024-06091-9","url":null,"abstract":"<div><p>Memristor Neural Networks (MNNs) stand out for their low power consumption and accelerated matrix operations, making them a promising hardware solution for neural network implementations. The efficacy of MNNs is significantly influenced by the careful selection of memristor update thresholds and the in-situ update scheme during hardware deployment. This paper addresses these critical aspects through the introduction of a novel scheme that integrates Dynamic Threshold (DT) and Gradient Accumulation (GA) with Threshold Properties. In this paper, realistic memristor characteristics, including pulse-to-pulse (P2P) and device-to-device (D2D) behaviors, were simulated by introducing random noise to the Vteam memristor model. A dynamic threshold scheme is proposed to enhance in-situ training accuracy, leveraging the inherent characteristics of memristors. Furthermore, the accumulation of gradients during back propagation is employed to finely regulate memristor updates, contributing to an improved in-situ training accuracy. Experimental results demonstrate a significant enhancement in test accuracy using the DTGA scheme on the MNIST dataset (82.98% to 96.15%) and the Fashion-MNIST dataset (75.58% to 82.53%). Robustness analysis reveals the DTGA scheme’s ability to tolerate a random noise factor of 0.03 for the MNIST dataset and 0.02 for the Fashion-MNIST dataset, showcasing its reliability under varied conditions. Notably, in the Fashion-MNIST dataset, the DTGA scheme yields a 7% performance improvement accompanied by a corresponding 7% reduction in training time. This study affirms the efficiency and accuracy of the DTGA scheme, which proves adaptable beyond multilayer perceptron neural networks (MLP), offering a compelling solution for the hardware implementation of diverse neuromorphic systems.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 2","pages":""},"PeriodicalIF":3.4,"publicationDate":"2024-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142821443","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}

引用次数: 0

Dynamic interactive weighted feature selection using fuzzy interaction information 利用模糊交互信息进行动态交互式加权特征选择

IF 3.4 2区计算机科学

Applied Intelligence Pub Date : 2024-12-14 DOI: 10.1007/s10489-024-06026-4

Xi-Ao Ma, Hao Xu, Yi Liu

{"title":"Dynamic interactive weighted feature selection using fuzzy interaction information","authors":"Xi-Ao Ma, Hao Xu, Yi Liu","doi":"10.1007/s10489-024-06026-4","DOIUrl":"10.1007/s10489-024-06026-4","url":null,"abstract":"<div><p>Traditional information theory-based feature selection methods are designed for discrete features, which require additional discretization steps when working with continuous features. In contrast, fuzzy information theory-based feature selection methods can handle continuous features directly. However, most existing fuzzy information theory-based feature selection methods do not consider the dynamic interaction between candidate features and the already selected ones. To address this issue, we propose a dynamic weighted feature selection method based on fuzzy interaction information that can handle continuous features. First, we use fuzzy information theory metrics to characterize the concepts of feature relevance, redundancy, and interaction. Second, we define a fuzzy interaction weight factor that can quantify the redundancy and interaction between features by using fuzzy interaction information. Third, we design a novel feature selection algorithm called fuzzy dynamic interactive weighted feature selection (FDIWFS) by combining the fuzzy interaction weight factor with a sequential forward search strategy. To evaluate the effectiveness of FDIWFS, we compare it with eight state-of-the-art feature selection methods on fifteen publicly available datasets. The results of comparative experiments demonstrate that FDIWFS outperforms the other methods in terms of classification performance.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 2","pages":""},"PeriodicalIF":3.4,"publicationDate":"2024-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142821444","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}

引用次数: 0

PUA-Net: end-to-end information hiding network based on structural re-parameterization

IF 3.4 2区计算机科学

Applied Intelligence Pub Date : 2024-12-13 DOI: 10.1007/s10489-024-06081-x

Feng Lin, Ru Xue, Shi Dong, Fuhao Ding, Yixin Han

{"title":"PUA-Net: end-to-end information hiding network based on structural re-parameterization","authors":"Feng Lin, Ru Xue, Shi Dong, Fuhao Ding, Yixin Han","doi":"10.1007/s10489-024-06081-x","DOIUrl":"10.1007/s10489-024-06081-x","url":null,"abstract":"<div><p>Image hiding aims to secretly embed secret information into a cover image and then recover the hidden data with minimal or no loss at the receiving end. Many works on steganography and deep learning have proved the huge prospects of deep learning in the field of image information hiding. However, current deep learning-based steganography research exposes significant limits, among which key issues such as how to improve embedding capacity, imperceptibility, and robustness remain crucial for image-hiding tasks. This article introduces PUA-Net, a new end-to-end neural network model for image steganography. PUA-Net consists of three main components: 1) the CbDw attention module, 2) the attention gate module, and 3) the partial combination convolution module. Each of these components utilizes structural reparameterization operations. In addition, we propose a residual image minimization loss function and use a combination of loss functions based on this loss function. This model can seamlessly embed bit stream information of different capacities into images to generate stego images that are imperceptible to the human eye. Experimental results confirm the effectiveness of our model, achieving an RS-BPP of 5.98 when decoding the extracted secret information and recovering the cover image. When only the extracted secret information is output, the model achieves a maximum RS-BPP of 6.94. Finally, experimental results show that our PUA-Net model outperforms deep learning-based steganography approaches on COCO, ImageNet, and BOSSbase datasets, including GAN-based methods such as Stegastamp and SteganoGAN.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 2","pages":""},"PeriodicalIF":3.4,"publicationDate":"2024-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142810843","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}

引用次数: 0

Double fuzzy relaxation local information C-Means clustering

IF 3.4 2区计算机科学

Applied Intelligence Pub Date : 2024-12-13 DOI: 10.1007/s10489-024-06078-6

Yunlong Gao, Xingshen Zheng, Qinting Wu, Jiahao Zhang, Chao Cao, Jinyan Pan

{"title":"Double fuzzy relaxation local information C-Means clustering","authors":"Yunlong Gao, Xingshen Zheng, Qinting Wu, Jiahao Zhang, Chao Cao, Jinyan Pan","doi":"10.1007/s10489-024-06078-6","DOIUrl":"10.1007/s10489-024-06078-6","url":null,"abstract":"<div><p>Fuzzy c-means clustering (FCM) has gained widespread application because of its ability to capture uncertain information in data effectively. However, attributed to the prior assumption of identical distribution, traditional FCM is sensitive to noise and cluster size. Modified methods incorporating local spatial information can enhance the robustness to noise. However, they tend to balance cluster sizes, resulting in poor performance when dealing with imbalanced data. Modified methods learning the statistical characteristics of data are feasible to handle imbalanced data. However, they are often sensitive to noise due to the ignorance of local information. Aiming at the lack of method that can simultaneously alleviate the sensitivity to noise and cluster size, a double fuzzy relaxation local information c-means clustering algorithm (DFRLICM) is proposed in this paper. Firstly, sample relaxation is introduced to explore potential clustering results and enhance inter-class separability. Secondly, to cooperate with the relaxation, we design fuzzy weights to record the imbalance situation of data clusters, enhancing the capability of algorithm in dealing with imbalanced data. Thirdly, we introduce fuzzy factor to account for the preservation of local structures in data and improve the robustness of algorithm. Finally, we integrate the three elements into a unified model framework to achieve the combination optimization of robustness to noise and insensitivity to cluster size simultaneously. Extensive experiments are conducted and the results demonstrate that the proposed algorithm indeed achieves a balance between robustness to noise and insensitivity to cluster size.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 2","pages":""},"PeriodicalIF":3.4,"publicationDate":"2024-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142811319","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}

引用次数: 0

Reinforcement-learning-based decentralized event-triggered control of partially unknown nonlinear interconnected systems with state constraints

IF 3.4 2区计算机科学

Applied Intelligence Pub Date : 2024-12-13 DOI: 10.1007/s10489-024-06072-y

Chunbin Qin, Yinliang Wu, Tianzeng Zhu, Kaijun Jiang, Dehua Zhang

{"title":"Reinforcement-learning-based decentralized event-triggered control of partially unknown nonlinear interconnected systems with state constraints","authors":"Chunbin Qin, Yinliang Wu, Tianzeng Zhu, Kaijun Jiang, Dehua Zhang","doi":"10.1007/s10489-024-06072-y","DOIUrl":"10.1007/s10489-024-06072-y","url":null,"abstract":"<div><p>In many applications with great potential, safety is critical as it needs to meet strict safety specifications within physical constraints. This paper studies the decentralized event-triggered control problem of a class of partially unknown nonlinear interconnected systems with state constraints under the reinforcement learning approach. First, by introducing a control barrier function into the performance function of each auxiliary subsystem with state constraints, the system state can be operated within a user-defined safe set. And then, the original control problem can be translated equivalently into finding or searching optimal event-triggered control policies that combine to form the desired decentralized controller, resulting in significant savings in communication resources. Compared with the traditional actor-critic network structure approach, the proposed identifier-critic network structure can loosen the constraints on the system dynamics and eliminate the errors arising from approximating the actor network. Updating the weight vectors in the critic network by gradient descent and concurrent learning techniques removes the need for the traditional persistence of excitation conditions. Furthermore, it is rigorously proved that all the signals of the interconnected nonlinear system are bound according to the Lyapunov stability theory. Last, the effectiveness of the proposed control scheme is verified by simulation examples.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 2","pages":""},"PeriodicalIF":3.4,"publicationDate":"2024-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142821132","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}

引用次数: 0

BiNext-Cervix: A novel hybrid model combining BiFormer and ConvNext for Pap smear classification

IF 3.4 2区计算机科学

Applied Intelligence Pub Date : 2024-12-13 DOI: 10.1007/s10489-024-06025-5

Minhui Dong, Yu Wang, Zeyu Zang, Yuki Todo

{"title":"BiNext-Cervix: A novel hybrid model combining BiFormer and ConvNext for Pap smear classification","authors":"Minhui Dong, Yu Wang, Zeyu Zang, Yuki Todo","doi":"10.1007/s10489-024-06025-5","DOIUrl":"10.1007/s10489-024-06025-5","url":null,"abstract":"<div><p>Cervical cancer is the fourth most prevalent cancer among women worldwide and a major contributor to cancer-related mortality in females. Manually classifying cytopathology screening slides remains one of the most important and commonly used methods for diagnosing cervical cancer. However, this method requires the participation of medical experts and is highly labor intensive. Consequently, in regions with limited medical resources, prompt cervical cancer diagnosis is challenging. To address this issue, the BiNext-Cervix model, a new deep learning framework, has been proposed to rapidly and accurately diagnose cervical cancer via Pap smear images. BiNext-Cervix employs Tokenlearner in the initial stage to facilitate interaction between two pixels within the image, enabling the subsequent network to better understand the image features. Additionally, the BiNext-Cervix integrates the recently introduced ConvNext and BiFormer models, allowing for deep exploration of image information from both local and global perspectives. A fully connected layer is used to fuse the extracted features and perform the classification. The experimental results demonstrate that combining ConvNext and BiFormer achieves higher accuracy than using either model individually. Furthermore, the proposed BiNext-Cervix outperforms other commonly used deep learning models, showing superior performance.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 2","pages":""},"PeriodicalIF":3.4,"publicationDate":"2024-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142811191","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}

引用次数: 0

Retraction Note: An optimal deep learning-based LSTM for stock price prediction using twitter sentiment analysis

IF 3.4 2区计算机科学

Applied Intelligence Pub Date : 2024-12-13 DOI: 10.1007/s10489-024-06184-5

T. Swathi, N. Kasiviswanath, A. Ananda Rao

引用次数: 0