Applied Intelligence最新文献_第8页

Confidence-adapted meta-interaction for unsupervised person re-identification 用于无监督人员重新识别的置信度自适应元交互

IF 5.3 2区计算机科学

Applied Intelligence Pub Date : 2023-08-09 DOI: 10.1007/s10489-023-04863-3

Xiaobao Li, Qingyong Li, Wenyuan Xue, Yang Liu, Fengjiao Liang, Wen Wang

{"title":"Confidence-adapted meta-interaction for unsupervised person re-identification","authors":"Xiaobao Li, Qingyong Li, Wenyuan Xue, Yang Liu, Fengjiao Liang, Wen Wang","doi":"10.1007/s10489-023-04863-3","DOIUrl":"10.1007/s10489-023-04863-3","url":null,"abstract":"<div><p>Most unsupervised person re-identification (ReID) approaches combine clustering-based pseudo-label prediction with feature learning, and perform the two steps in an alternating fashion for training ReID models. However, incorrect/noisy pseudo-labels are often present due to various variations (e.g., human pose, illumination, and viewpoint, etc.). Such noisy pseudo-labels may harm the trained ReID models. In order to use diverse variations/information while minimizing negative influence of the noisy pseudo-labels, we propose a confidence-adapted meta-interaction (CAMI) method by explicitly exploring the interaction between the believable supervision (reliable pseudo-labels) and the diverse information. Specifically, CAMI iteratively trains the ReID model in a meta-learning manner, in which the training images are dynamically divided into a reliable set and an unreliable set. At each iteration, the pseudo-labels of images are predicted by clustering and the training images are divided by the proposed confidence-adapted sample disentanglement (CASD) method. To adapt the changes of the pseudo-labels and gradually refine the division, the CASD method dynamically predicts the pseudo-label confidence. It divides the training images into the reliable set (with high confidence pseudo-labels) and the unreliable set (with low confidence pseudo-labels), respectively. Then a meta-interaction method is proposed for training the ReID model, which consists of a meta-training step to use the believable supervision of the reliable set and a meta-testing step to use the diverse information of the unreliable set. Meanwhile, a bridge model is dynamically built to refine the unreliable set based on the believable supervision from the reliable set. The CAMI is evaluated by two unsupervised person ReID settings, including the image-based and the video-based. The experimental results on four datasets demonstrate the superiority of the proposed CAMI.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"53 21","pages":"25525 - 25542"},"PeriodicalIF":5.3,"publicationDate":"2023-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"71909406","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

A hybrid-driven remaining useful life prediction method combining asymmetric dual-channel autoencoder and nonlinear Wiener process 结合非对称双通道自编码器和非线性维纳过程的混合驱动剩余使用寿命预测方法

IF 5.3 2区计算机科学

Applied Intelligence Pub Date : 2023-08-09 DOI: 10.1007/s10489-023-04855-3

Yuhang Duan, Zhen Liu, Honghui Li, Chun Zhang, Ning Zhang

{"title":"A hybrid-driven remaining useful life prediction method combining asymmetric dual-channel autoencoder and nonlinear Wiener process","authors":"Yuhang Duan, Zhen Liu, Honghui Li, Chun Zhang, Ning Zhang","doi":"10.1007/s10489-023-04855-3","DOIUrl":"10.1007/s10489-023-04855-3","url":null,"abstract":"<div><p>Remaining Useful Life (RUL) prediction is an essential aspect of Prognostics and Health Management (PHM), facilitating the assessment of mechanical components’ health statuses and their times to failure. Currently, most deep learning-based RUL prediction methods can achieve accurate RUL point estimations. However, due to sample variability and degradation randomness, point estimations may contain uncertainties. To obtain both RUL prediction values and their corresponding uncertainty estimations, this paper proposes a novel hybrid-driven prediction method that effectively combines an Asymmetric Dual-Channel AutoEncoder and the Nonlinear Wiener Process (ADCAE-NWP). To achieve comprehensive feature extraction, two feature extraction channels are parallelly combined in the encoder. Moreover, to reduce the space-time overhead of the model training process, an asymmetric form of the autoencoder is composed by using only the fully connected layer in the decoder. Subsequently, the ADCAE model is trained to construct health indicators in an unsupervised manner. Finally, the RUL Probability Density Functions (PDFs) are calculated using the NWP. RUL predictions containing uncertainty estimations are obtained by calculating expectations over confidence intervals. The proposed model is experimentally validated and compared on two datasets, and the results demonstrate that the proposed scheme achieves better prediction performance than competing approaches.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"53 21","pages":"25490 - 25510"},"PeriodicalIF":5.3,"publicationDate":"2023-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"71909318","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

Context-adaptable radar-based people counting via few-shot learning 基于上下文自适应雷达的少镜头学习人员计数

IF 5.3 2区计算机科学

Applied Intelligence Pub Date : 2023-08-08 DOI: 10.1007/s10489-023-04778-z

Gianfranco Mauro, Ignacio Martinez-Rodriguez, Julius Ott, Lorenzo Servadei, Robert Wille, Manuel P. Cuellar, Diego P. Morales-Santos

{"title":"Context-adaptable radar-based people counting via few-shot learning","authors":"Gianfranco Mauro, Ignacio Martinez-Rodriguez, Julius Ott, Lorenzo Servadei, Robert Wille, Manuel P. Cuellar, Diego P. Morales-Santos","doi":"10.1007/s10489-023-04778-z","DOIUrl":"10.1007/s10489-023-04778-z","url":null,"abstract":"<p>In many industrial or healthcare contexts, keeping track of the number of people is essential. Radar systems, with their low overall cost and power consumption, enable privacy-friendly monitoring in many use cases. Yet, radar data are hard to interpret and incompatible with most computer vision strategies. Many current deep learning-based systems achieve high monitoring performance but are strongly context-dependent. In this work, we show how context generalization approaches can let the monitoring system fit unseen radar scenarios without adaptation steps. We collect data via a 60 GHz frequency-modulated continuous wave in three office rooms with up to three people and preprocess them in the frequency domain. Then, using meta learning, specifically the Weighting-Injection Net, we generate relationship scores between the few training datasets and query data. We further present an optimization-based approach coupled with weighting networks that can increase the training stability when only very few training examples are available. Finally, we use pool-based sampling active learning to fine-tune the model in new scenarios, labeling only the most uncertain data. Without adaptation needs, we achieve over 80% and 70% accuracy by testing the meta learning algorithms in new radar positions and a new office, respectively.</p>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"53 21","pages":"25359 - 25387"},"PeriodicalIF":5.3,"publicationDate":"2023-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"71909518","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

Experimental analysis of similarity measurements for multivariate time series and its application to the stock market 多元时间序列相似性测度的实验分析及其在股票市场中的应用

IF 5.3 2区计算机科学

Applied Intelligence Pub Date : 2023-08-08 DOI: 10.1007/s10489-023-04874-0

Zhong-Liang Xiang, Rui Wang, Xiang-Ru Yu, Bo Li, Yuan Yu

{"title":"Experimental analysis of similarity measurements for multivariate time series and its application to the stock market","authors":"Zhong-Liang Xiang, Rui Wang, Xiang-Ru Yu, Bo Li, Yuan Yu","doi":"10.1007/s10489-023-04874-0","DOIUrl":"10.1007/s10489-023-04874-0","url":null,"abstract":"<div><p>Similarity measurement takes on critical significance in strategies that seek similar stocks based on historical data to make predictions. Stock data refers to a multidimensional time series with features of non-linearity and high noise, posing a challenge to the practical design of similarity measurement. However, the existing similarity measurements cannot better address the negative effects of the singularity of data and correlations of data in multidimensional stock price series, such that the performance of stock prediction will be reduced. In this study, a novel method named dynamic multi-factor similarity measurement (DMFSM) is proposed to accurately describe the similarity between a pair of multidimensional time series. DMFSM is capable of eliminating effects exerted by singularity and correlations of data using dynamic time warping (DTW) with Mahalanobis distance embedded and weights of series nodes in multidimensional time series. To validate the efficiency of DMFSM, several experiments were performed on a total of 675 stocks, which comprised 290 stocks from the Shanghai Stock Exchange, 285 stocks from the Shenzhen Stock Exchange, as well as 100 stocks from the Growth Enterprise Market of the Shenzhen Stock Exchange. The experiment results for mean absolute error of predictions indicated that DMFSM (0.018) outperformed similarity measurements (e.g., Euclidean distance (0.023), DTW (0.054), and dynamic multi-perspective personalized similarity measurement (0.023)).</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"53 21","pages":"25450 - 25466"},"PeriodicalIF":5.3,"publicationDate":"2023-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"71909517","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

Kernelized global-local discriminant information preservation for unsupervised domain adaptation 无监督领域自适应的核化全局局部判别信息保存

IF 5.3 2区计算机科学

Applied Intelligence Pub Date : 2023-08-08 DOI: 10.1007/s10489-023-04706-1

Lekshmi R, Rakesh Kumar Sanodiya, Babita Roslind Jose, Jimson Mathew

{"title":"Kernelized global-local discriminant information preservation for unsupervised domain adaptation","authors":"Lekshmi R, Rakesh Kumar Sanodiya, Babita Roslind Jose, Jimson Mathew","doi":"10.1007/s10489-023-04706-1","DOIUrl":"10.1007/s10489-023-04706-1","url":null,"abstract":"<div><p>Visual recognition has become inevitable in applications such as object detection, biometric tracking, autonomous vehicles, and social media platforms. The images have multiple factors such as image resolution, illumination, perspective and noise, resulting in a significant mismatch between the training and testing domains. Unsupervised Domain adaptation (DA) has proven an effective way to reduce the differences by adapting the knowledge from a richly labeled source domain to an unlabeled target domain. But the real-time datasets are non-linear and high-dimensional. Though kernelization can handle the non-linearity in data, the dimension needs to be reduced as the salient features of the data lie in a low-dimensional subspace. Current dimensionality reduction approaches in DA preserve either the global or local part of information of manifold data. Specifically, the data manifold’s static (subject-invariant) and dynamic (intra-subject variant) information need to be considered during knowledge transfer. Therefore, to preserve both parts of information Globality-Locality Preserving Projection (GLPP) method is applied to the labeled source domain. The other objectives are preserving the discriminant information and variance of target data, and minimizing the distribution and subspace differences between the domains. With all these objectives, we propose a unique method known as Kernelized Global-Local Discriminant Information Preservation for unsupervised DA (KGLDIP). KGLDIP aims to reduce the discrimination discrepancy geometrically and statistically between the two domains after calculating two projection matrices for each domain. Intensive experiments are conducted using five standard datasets and the analysis reveals that the proposed algorithm excels the other state-of-the-art DA approaches.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"53 21","pages":"25412 - 25434"},"PeriodicalIF":5.3,"publicationDate":"2023-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"71909520","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

Towards evolving software recommendation with time-sliced social and behavioral information 利用时间切片的社会和行为信息发展软件推荐

IF 5.3 2区计算机科学

Applied Intelligence Pub Date : 2023-08-08 DOI: 10.1007/s10489-023-04852-6

Hongqi Chen, Zhiyong Feng, Shizhan Chen, Xiao Xue, Hongyue Wu, Yingchao Sun, Yanwei Xu, Gaoyong Han

{"title":"Towards evolving software recommendation with time-sliced social and behavioral information","authors":"Hongqi Chen, Zhiyong Feng, Shizhan Chen, Xiao Xue, Hongyue Wu, Yingchao Sun, Yanwei Xu, Gaoyong Han","doi":"10.1007/s10489-023-04852-6","DOIUrl":"10.1007/s10489-023-04852-6","url":null,"abstract":"<p>Software recommendations play a crucial role in helping developers discover potential functional requirements and improve development efficiencies. As new requirements emerge in the software development process, developers’ preferences tend to change over time and social relationships. However, the existing works fall short of capturing the evolution of developers’ interests. To overcome these problems, evolving software recommendation with time-sliced social and behavioral information is proposed for capturing the dynamic interests of developers. Specifically, the different behaviors of developers are considered and graph structure features on projects are extracted by gated graph neural networks. Then, the graph attention networks are introduced to model rich developer-project interactions and social aggregation. Finally, the integration of time-sliced representations on the developer and project sides is employed through gated recurrent units to capture the dynamic interests of developers. Extensive experiments conducted on three datasets demonstrate the superiority of the proposed model over representative baseline methods across various evaluation metrics.</p>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"53 21","pages":"25343 - 25358"},"PeriodicalIF":5.3,"publicationDate":"2023-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"71909514","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

SDSCNet: an instance segmentation network for efficient monitoring of goose breeding conditions SDSCNet：一种有效监测鹅养殖条件的实例分割网络

IF 5.3 2区计算机科学

Applied Intelligence Pub Date : 2023-08-08 DOI: 10.1007/s10489-023-04743-w

Jiao Li, Houcheng Su, Jianing Li, Tianyu Xie, Yijie Chen, Jianan Yuan, Kailin Jiang, Xuliang Duan

{"title":"SDSCNet: an instance segmentation network for efficient monitoring of goose breeding conditions","authors":"Jiao Li, Houcheng Su, Jianing Li, Tianyu Xie, Yijie Chen, Jianan Yuan, Kailin Jiang, Xuliang Duan","doi":"10.1007/s10489-023-04743-w","DOIUrl":"10.1007/s10489-023-04743-w","url":null,"abstract":"<div><p>Improve the scientific level of the goose breeding industry and help the development of intelligent agriculture. Instance Segmentation has a pivotal role when the breeders make decisions about geese breeding. It can be used for disease prevention, body size estimation and behavioural prediction, etc. However, instance segmentation requires high performance computing devices to run smoothly due to its rich output. To ameliorate this problem, this paper constructs a novel encoder-decoder module and proposes the SDSCNet model. The reasonable use of depth-separable convolution in the module reduces the number and size of model parameters and increase execution speed. Finally, SDSCNet model enables real-time identification and segmentation of individual geese with the accuracy reached 0.933.We compare this model with numerous mainstream instance segmentation models, and the final results demonstrate the excellent performance of our model.Furthermore, deploying SDSCNet model on the embedded device Raspberry Pi 4 Model B can achieve effective detection of continuous moving scenes.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"53 21","pages":"25435 - 25449"},"PeriodicalIF":5.3,"publicationDate":"2023-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"71909516","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

DyGCN-LSTM: A dynamic GCN-LSTM based encoder-decoder framework for multistep traffic prediction DyGCN-LSTM:一种用于多步流量预测的基于动态GCN-LSTM的编码器-解码器框架

IF 5.3 2区计算机科学

Applied Intelligence Pub Date : 2023-08-08 DOI: 10.1007/s10489-023-04871-3

Rahul Kumar, João Mendes Moreira, Joydeep Chandra

{"title":"DyGCN-LSTM: A dynamic GCN-LSTM based encoder-decoder framework for multistep traffic prediction","authors":"Rahul Kumar, João Mendes Moreira, Joydeep Chandra","doi":"10.1007/s10489-023-04871-3","DOIUrl":"10.1007/s10489-023-04871-3","url":null,"abstract":"<div><p>Intelligent transportation systems (ITS) are gaining attraction in large cities for better traffic management. Traffic forecasting is an important part of ITS, but a difficult one due to the intricate spatiotemporal relationships of traffic between different locations. Despite the fact that remote or far sensors may have temporal and spatial similarities with the predicting sensor, existing traffic forecasting research focuses primarily on modeling correlations between neighboring sensors while disregarding correlations between remote sensors. Furthermore, existing methods for capturing spatial dependencies, such as graph convolutional networks (GCNs), are unable to capture the dynamic spatial dependence in traffic systems. Self-attention-based techniques for modeling dynamic correlations of all sensors currently in use overlook the hierarchical features of roads and have quadratic computational complexity. Our paper presents a new Dynamic Graph Convolution LSTM Network (DyGCN-LSTM) to address the aforementioned limitations. The novelty of DyGCN-LSTM is that it can model the underlying non-linear spatial and temporal correlations of remotely located sensors at the same time. Experimental investigations conducted using four real-world traffic data sets show that the suggested approach is superior to state-of-the-art benchmarks by <span>(varvec{25%})</span> in terms of RMSE.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"53 21","pages":"25388 - 25411"},"PeriodicalIF":5.3,"publicationDate":"2023-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"71909521","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

Recurrent auto-encoder with multi-resolution ensemble and predictive coding for multivariate time-series anomaly detection 多分辨率集成预测编码递归自动编码器在多变量时间序列异常检测中的应用

IF 5.3 2区计算机科学

Applied Intelligence Pub Date : 2023-08-08 DOI: 10.1007/s10489-023-04764-5

Heejeong Choi, Subin Kim, Pilsung Kang

{"title":"Recurrent auto-encoder with multi-resolution ensemble and predictive coding for multivariate time-series anomaly detection","authors":"Heejeong Choi, Subin Kim, Pilsung Kang","doi":"10.1007/s10489-023-04764-5","DOIUrl":"10.1007/s10489-023-04764-5","url":null,"abstract":"<div><p>As large-scale time-series data can easily be found in real-world applications, multivariate time-series anomaly detection has played an essential role in diverse industries. It enables productivity improvement and maintenance cost reduction by preventing malfunctions and detecting anomalies based on time-series data. However, multivariate time-series anomaly detection is challenging because real-world time-series data exhibit complex temporal dependencies. For this task, it is crucial to learn a rich representation that effectively contains the nonlinear temporal dynamics of normal behavior. In this study, we propose an unsupervised multivariate time-series anomaly detection model named RAE-MEPC which learns informative normal representations based on multi-resolution ensemble reconstruction and predictive coding. We introduce multi-resolution ensemble encoding to capture the multi-scale dependency from the input time series. The encoder hierarchically aggregates the multi-scale temporal features extracted from the sub-encoders with different encoding lengths. From these encoded features, the reconstruction decoder reconstructs the input time series based on multi-resolution ensemble decoding where lower-resolution information helps to decode sub-decoders with higher-resolution outputs. Predictive coding is further introduced to encourage the model to learn more temporal dependencies of the time series. Experiments on real-world benchmark datasets show that the proposed model outperforms the benchmark models for multivariate time-series anomaly detection.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"53 21","pages":"25330 - 25342"},"PeriodicalIF":5.3,"publicationDate":"2023-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"71909515","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: 1

An effective embedding algorithm for blind image watermarking technique based on Hessenberg decomposition 一种有效的基于Hessenberg分解的图像盲水印嵌入算法

IF 5.3 2区计算机科学

Applied Intelligence Pub Date : 2023-08-08 DOI: 10.1007/s10489-023-04903-y

Phuong Thi Nha, Ta Minh Thanh, Nguyen Tuan Phong

{"title":"An effective embedding algorithm for blind image watermarking technique based on Hessenberg decomposition","authors":"Phuong Thi Nha, Ta Minh Thanh, Nguyen Tuan Phong","doi":"10.1007/s10489-023-04903-y","DOIUrl":"10.1007/s10489-023-04903-y","url":null,"abstract":"<div><p>For digital image copyright protection, watermarking techniques are a promising solution and are of interest to many researchers. In watermarking schemes based on matrix transformation, the embedding element and embedding formula play a very important role in maintaining the quality of a watermark image and the robustness of the watermark. In this paper, a blind image watermarking scheme based on Hessenberg decomposition, where the improvement focuses on the embedding element and embedding formula, is proposed. First, the structure of the Hessenberg factorization is analysed to obtain the most suitable embedding element. Accordingly, this is the first time that the element on the second row and the second column of the upper Hessenberg matrix is selected as an embedding element in a Hessenberg-based image watermarking scheme because of its energy concentration and stability. Second, an improved embedding formula is proposed to address the limitations of previous studies. In the proposed formula, constraint conditions are added to limit the change in all blocks, and a scaling factor is applied to guarantee a trade-off between invisibility and robustness. Here, the scaling factor is carefully calculated by repeating various experiments under different image attacks to achieve an optimal value. Therefore, our proposed embedding formula not only minimizes the modification of the host image after embedding but also helps maintain the robustness of the extracted watermark. Third, to increase the security of the proposed scheme, the watermark image is encoded by the Arnold transform before it is embedded into the host image. The experimental results show that the proposed approach defeats the compared methods in terms of invisibility and execution time. Moreover, the proposed scheme can resist most common attacks when the average normalized correlation value is higher than 0.93 and the extracted watermarks are always clearly recognized.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"53 21","pages":"25467 - 25489"},"PeriodicalIF":5.3,"publicationDate":"2023-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"71909519","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