Engineering Applications of Artificial Intelligence最新文献

{"title":"PDFusion: A domain-adaptive incremental learning model based on Physical-Data Fusion for lithium-ion battery state estimation","authors":"Yufei Xie ,&nbsp;Wenlin Wang ,&nbsp;Guohua Wu ,&nbsp;Haichuan Zhang","doi":"10.1016/j.engappai.2025.110913","DOIUrl":"10.1016/j.engappai.2025.110913","url":null,"abstract":"<div><div>Accurate estimation of battery state is crucial for ensuring the safe, stable, and efficient operation of lithium-ion batteries. State of Charge (SOC) and State of Energy (SOE) are critical parameters for assessing battery health, but accurately estimating them remains challenging due to the nonlinear, non-stationary and strong coupling characteristics of complex battery charging and discharging processes. To address these issues, a novel domain-adaptive incremental learning model driven by both physical and data is proposed. To reduce state noise and covariance, a novel Kalman Filtering method is used for primary trend prediction. However, physics-based models fail to estimate the seasonal components that contain time-frequency patterns. To overcome the limitation, a data-driven model with Time-frequency Interactive Attention (TIA) is proposed to accurately capture the temporal relationships and effectively compensate for peak errors. To make the model operate across different temperature conditions, a domain-adaptive incremental learning strategy is employed. The results on Lithium iron phosphate (LFP) and Nickel Cobalt Manganese (NCM) batteries show that the proposed model outperforms current state-of-the-art (SOTAs), with the average Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) of 0.048 and 0.021 for LFP under two operating conditions, and 0.060 and 0.023 for NCM. Under Beijing Dynamic Stress test (BJDST) conditions, RMSE and MAE are reduced by 22.69% and 28.56% respectively. Under US06 Highway Driving Schedule (US06) conditions, these metrics are reduced by 41.02% and 49.09%, respectively. The algorithm exhibits high robustness to temperature, enabling precise estimation of the lithium-ion battery states.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"154 ","pages":"Article 110913"},"PeriodicalIF":7.5,"publicationDate":"2025-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143895100","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":"Defense against false data injection attacks on the electric vehicle charging stations data markets","authors":"Huqun Mu ,&nbsp;Aiping Pang ,&nbsp;Congmei Jiang ,&nbsp;Wen Yang ,&nbsp;Qianchuan Zhao","doi":"10.1016/j.engappai.2025.110983","DOIUrl":"10.1016/j.engappai.2025.110983","url":null,"abstract":"<div><div>Data-driven technology depends on high-quality training data. Although many research institutions advocate for data sharing, private data owners are often reluctant to share their data considering the privacy concerns related to potential data breaches. As a result, the availability of data limits the application of data-driven technologies in energy systems. To enhance the availability of data, we have constructed a data market model for forecasting the power demand of electric vehicle charging stations (EVCSs), enabling data transactions within this market to improve the accuracy of forecasts. Since the data market relies on communication networks to collect data, this makes it vulnerable to malicious false data injection attacks (FDIAs) during transmission, exposing the data market to serious security risks. To ensure the safe operation of this data market, this article proposes a defense method based on Wasserstein Generative Adversarial Network that combines Transformer and Convolutional Neural Network(TCWGAN). This method effectively reduces the impact of FDIAs and has a strong defense against the injection of false data, achieving an accuracy of 95.09 %.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"154 ","pages":"Article 110983"},"PeriodicalIF":7.5,"publicationDate":"2025-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143895099","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 small object detection algorithm for mine environment","authors":"Dong Liu ,&nbsp;Xin Zhao ,&nbsp;Weiqiang Fan","doi":"10.1016/j.engappai.2025.110936","DOIUrl":"10.1016/j.engappai.2025.110936","url":null,"abstract":"<div><div>The detection of protective equipment carried by underground mine operators is a crucial measure for preventing safety accidents and safeguarding personal life and property. However, current challenges include low object detection accuracy and difficulty detecting small objects, we propose a small object detection algorithm based on the improved You Only Look Once Version 8 (YOLOv8) for the mine environment. To minimize the semantic gap between features at different levels and enhance the feature fusion effect, the Asymptotic Feature Pyramid Network-Four (AFPN-F) has been designed to replace the Neck component of YOLOv8, enabling the detection model to better adapt to semantic information across varying levels. To enhance the model's sensitivity to small objects in the mine environment, a superficial feature output layer has been added to the model. This addition helps to prevent the loss of small-sized objects, which may contain limited feature information, during successive convolution operations. To address the significant differences in the scales of various objects in the mine, the More Focused Intersection over Union Loss (Focaler-IoU) is introduced as a loss function. This modification is intended to improve the handling of different types of regression samples, enhance training accuracy, and ensure that the model is more focused on small objects in the mine environment. The experimental results show that the proposed model outperforms other mainstream models. Compared to the baseline model YOLOv8, achieving an improvement of 3.7 percent in mean Average Precision (mAP), the number of parameters has been reduced by 30 percent, resulting in a model size of only 5 Megabytes. This study provides an effective solution for detecting small objects in underground mines.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"153 ","pages":"Article 110936"},"PeriodicalIF":7.5,"publicationDate":"2025-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143895477","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":"Multi-occupant tracking with radar and wearable devices for enhanced accuracy in indoor environments","authors":"Aurora Polo-Rodríguez,&nbsp;Miguel Ángel Anguita-Molina,&nbsp;Ignacio Rojas-Ruiz,&nbsp;Javier Medina-Quero","doi":"10.1016/j.engappai.2025.110872","DOIUrl":"10.1016/j.engappai.2025.110872","url":null,"abstract":"<div><div>This work explores the integration of millimetre-wave (mmWave) radar and a minimal configuration of ultra-wideband (UWB) devices for enhanced multi-occupant tracking in real domestic environments. Using a low-cost, non-intrusive, and rapidly deployable device setup, our approach addresses key challenges in multi-occupant tracking, including individual identification and ease of installation. While mmWave radar precisely detects occupant presence, it lacks individual recognition and exhibits limited sensitivity. This limitations are addressed by incorporating a minimal configuration of UWB (wearable tags and ambient anchors), enabling individual identification through signal strength measurements. Several data autoencoder models, such as long short-term memories (LSTMs), Convolutional Neural Networks (CNN) or Transformers, were evaluated. Experiments conducted in two real-world domestic settings, each with up to three inhabitants, demonstrate the effectiveness of combining mmWave and UWB technologies for indoor multi-occupant tracking. Our results show that ConvLSTM achieves the best performance with a mean squared error (MSE) between 0,0142 and 0,0433 in single and multi-occupation, respectively. These findings suggest promising applications for accurate inhabitant tracking in ambient assisted living and other smart environment contexts.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"154 ","pages":"Article 110872"},"PeriodicalIF":7.5,"publicationDate":"2025-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143895097","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 feature matching-based method for few-shot multivariate time series anomaly detection with symmetric patch mask Siam Transformer","authors":"Jiahao Yu ,&nbsp;Xin Gao ,&nbsp;Taizhi Wang ,&nbsp;Heping Lu ,&nbsp;Baofeng Li ,&nbsp;Feng Zhai ,&nbsp;Bing Xue ,&nbsp;Zhihang Meng","doi":"10.1016/j.engappai.2025.110894","DOIUrl":"10.1016/j.engappai.2025.110894","url":null,"abstract":"<div><div>Accurate anomaly detection of industrial system operating status based on multivariate time series data is an important means to ensure the stable operation of the system. However if there is insufficient training data for the objects to be detected, it is difficult for existing deep learning methods to learn a clear outline of the normal pattern of the data under unsupervised conditions, leading to the failure of anomaly detection. This paper proposes a feature matching-based method for few-shot multivariate time series anomaly detection with a symmetric patch mask Siam Transformer (SPMST). Using only a small number of normal samples from the target domain, SPMST realizes the rapid deployment of the universal representation model pre-trained on multiple public datasets to the target domain without the need for retraining or parameter adjustment for more categories. First, two augmented views of the original data are obtained by adding a symmetric patch mask to the augmented aligned multisource data. The Transformer model is then pre-trained with reconstruction and contrastive learning tasks to acquire robust latent representations. Second, the feature support set of the target domain is obtained based on the pre-trained representation model and the proposed clustering-based support set reduction strategy, avoiding excessive consumption of computing resources. Finally, the anomaly score is calculated by combining the feature matching loss, reconstruction loss, and contrastive loss. The experimental results show that SPMST, under few-shot conditions, is not weaker than 21 state-of-the-art baselines trained with a large amount of data on 5 representative cyber–physical system datasets.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"154 ","pages":""},"PeriodicalIF":7.5,"publicationDate":"2025-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143895052","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 customized multi-class pavement distress segmentation method for routine repair monitoring","authors":"Hui Wang ,&nbsp;Junyang Kang ,&nbsp;Shuichao Zhang ,&nbsp;Yanmao Xiang ,&nbsp;Jun Li","doi":"10.1016/j.engappai.2025.111002","DOIUrl":"10.1016/j.engappai.2025.111002","url":null,"abstract":"<div><div>This study investigates the efficacy of intelligent detection methods for monitoring the quality of urban road asphalt pavement repairs, and focuses on addressing the challenges of identifying overlapping target pixels and differentiating between fine-scale distress and large-scale block patches, tasks that heavily rely on spatial semantics. A segmentation dataset comprising 13 classes and 5633 labels was constructed. Five semantic segmentation models including Deeplab V3+, SCTNet (Single-Branch Convolutional Neural Network with Transformer Semantic Information), FastFCN (Fast Fully Convolutional Network), MobileNet V3, and SegNext were constructed and evaluated. Despite its relatively smaller size, SCTNet exhibited the highest processing speed, while MobileNetV3 exhibited the smallest size and lowest accuracy. The SegNeXt model demonstrated superior performance in both segmentation accuracy and model complexity, making it chosen as the baseline model. Three training strategies were explored: classifying pavement as background, employing multiscale input, and integrating a weighted loss function. The model that combined all three strategies (referred to as SegNeXt_IPWM) demonstrated the most promising results. Compared to the baseline model, SegNeXt_IPWM achieved significant enhancements, with a 2.08 % increase in <em>mIoU</em> (mean Intersection over Union) and a 1.42 % improvement in mean <em>F-score</em>. Notable improvements were observed across all categories except for marking loss, with particularly substantial gains in loose (+7.75 % IoU), block patch (+6.62 % IoU), and linear crack (+4.87 % IoU) detection. Additionally, SegNeXt_IPWM demonstrated superior generalization capabilities, especially in scenarios involving background target interference, underscoring its potential for robust performance in applications.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"154 ","pages":"Article 111002"},"PeriodicalIF":7.5,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143891762","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 Dual Two-Stage Attention-based Model for interpretable hard landing prediction from flight data","authors":"Jiaxing Shang ,&nbsp;Xiaoquan Li ,&nbsp;Ruixiang Zhang ,&nbsp;Linjiang Zheng ,&nbsp;Xu Li ,&nbsp;Riquan Zhang ,&nbsp;Xinbin Zhao ,&nbsp;Fan Li ,&nbsp;Hong Sun","doi":"10.1016/j.engappai.2025.110911","DOIUrl":"10.1016/j.engappai.2025.110911","url":null,"abstract":"<div><div>Hard landings are a significant safety concern in aviation, with potential consequences ranging from poor passenger experiences to serious injuries or fatalities. Predicting and explaining hard landing events are equally important for enhancing flight safety, the former makes it possible to give proactive warnings, while the latter helps pilots identify the reasons and refine their skills. However, existing studies generally lack a comprehensive consideration for the fine-grained characteristics of flight data containing both inter-temporal and inter-parametric relationships, resulting in suboptimal prediction performance. In addition, most of existing approaches aim at improving the prediction performance but fail to provide interpretability for the causes of hard landing. To address the above problems, we propose <strong>DUTSAM</strong>, a <strong>DU</strong>al <strong>T</strong>wo-<strong>S</strong>tage <strong>A</strong>ttention-based interpretable <strong>M</strong>odel for hard landing prediction from quick access recorder (QAR) data. The model consists of dual parallel modules, each of which combines a convolutional feature encoder and a two-stage attention mechanism. The two encoders capture fine-grained characteristics by encoding multivariate data from temporal domain and parametric domain respectively. After that, the dual two-stage attention mechanism captures the inter-temporal and inter-parametric correlations in reverse order to predict hard landing and provide interpretation from both temporal and parametric perspectives. Experimental results on a real QAR dataset with 37,920 flights show that DUTSAM achieves better prediction performance compared with other state-of-the-art baselines in terms of Precision, Recall, and F1-score. Additionally, case study demonstrates that DUTSAM can uncover key flight parameters and moments strongly correlated to the hard landing events.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"154 ","pages":"Article 110911"},"PeriodicalIF":7.5,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143895101","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 explainable artificial intelligence – human collaborative model for investigating patent novelty","authors":"Hyejin Jang ,&nbsp;Byungun Yoon","doi":"10.1016/j.engappai.2025.110984","DOIUrl":"10.1016/j.engappai.2025.110984","url":null,"abstract":"<div><div>With the accumulation of technology-related big data, including the patent database, existing studies have proposed a framework for patent analysis using natural language processing models. Artificial intelligence (AI) applications require human experience and insight based on the understanding of complex environments and uncertainties and model predictive performance. However, existing research has focused on applying big data and developing automated processes. Actual user understanding and the consideration of model usability are insufficient. Studies must consider the human–machine cooperation-based approach in developing the AI model. This study proposes a collaborative approach through which the explainable AI (XAI) model, a self-explaining deep neural network for text classification, communicates with users. The proposed XAI model provides users with an explanation for the model prediction along with the prediction results for patent evaluation. Users provide feedback based on the model predictions and their explanations. The source XAI model is refined via relearning by reflecting on user feedback. This study experiments to assess model improvement using the human collaboration method. As for the human collaborative method, this study considers the process of human intervention independent of the XAI model's results as well as the method of human participation based on the explanation presented by the XAI model. The experimental results verified the XAI model performance, showing the highest accuracy (0.890) and F1 score (0.916), such that the model can be applied efficiently to patent evaluation. The XAI–human collaboration model presented in this study can also be expanded and applied to technology intelligence tasks. However, the collaborative approach in this study has complete trust in human advice from technical experts; thus, subsequent collaborative XAI models could be improved by communicating bidirectionally with human resources as a complementary relationship.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"154 ","pages":"Article 110984"},"PeriodicalIF":7.5,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143891751","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 prototypes contrastive learning based semi-supervised segmentation method for intelligent medical applications","authors":"Tianai Yue ,&nbsp;Rongtao Xu ,&nbsp;Jingqian Wu ,&nbsp;Wenjie Yang ,&nbsp;Shide Du ,&nbsp;Changwei Wang","doi":"10.1016/j.engappai.2025.110905","DOIUrl":"10.1016/j.engappai.2025.110905","url":null,"abstract":"<div><div>In medical intelligence applications, the labeling of medical data is crucial and expensive, so it becomes urgent to explore labeling-efficient ways to train applications. Semi-supervised techniques for medical image segmentation have demonstrated potential, effectively training models using scarce labeled data alongside a wealth of unlabeled data. Therefore, semi-supervised medical image segmentation is a key issue in engineering applications of medical intelligence. Consistency constraints based on prototype alignment provide an intuitively sensible way to discover valuable insights from unlabeled data that can motivate segmentation performance. In this work, we propose a Dual prototypes Contrastive Network to motivate semi-supervised medical segmentation accuracy by imposing image-level global prototype and pixel-level local prototype constraints. First, we introduce a Background-Separation Global Prototype Contrastive Learning technique that utilizes the natural mutual exclusivity of foreground and background to separate the inter-class distances and encourage the segmentation network to obtain segmentation results that are more complete and do not contain background regions. Second, we design a Cross-Consistent Local Prototype Contrastive Learning techniques to extend the perturbation consistency of the two networks to the prototype’s localized response to the feature map, thereby shaping a more stable intra-class prototype space and producing accurate and robust pixel-level predictions. Finally, we comprehensively evaluate our method on mainstream semi-supervised medical image segmentation benchmarks and settings, and experimental results show that our proposed method outperforms current state-of-the-art methods. Specifically, our method achieves a Dice Coefficient score of 91.8 on the Automatic Cardiac Diagnosis Challenge dataset using only 10% labeled data training, 1.1% ahead of the second best method. Code is available at <span><span>https://github.com/yuelily2024/DPC</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"154 ","pages":"Article 110905"},"PeriodicalIF":7.5,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143895098","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 edge-guided defect segmentation network for in-service aerospace engine blades","authors":"Xianming Yang ,&nbsp;Kechen Song ,&nbsp;Shaoning Liu ,&nbsp;Fuqi Sun ,&nbsp;Yiming Zheng ,&nbsp;Jun Li ,&nbsp;Yunhui Yan","doi":"10.1016/j.engappai.2025.110974","DOIUrl":"10.1016/j.engappai.2025.110974","url":null,"abstract":"<div><div>Currently, 80 % of in-service aerospace engine blade defect detection relies on manual visual assessment. Operators use a borescope to capture images of the blade surface and make judgments based on their experience and expertise. However, this method is costly and time-consuming. With the widespread application of artificial intelligence across various fields, its strong capabilities in automated defect detection are becoming increasingly evident. To meet the demand for efficient defect detection in aero-engine blades, we have constructed a dataset based on videos collected from real inspection scenarios, ensuring alignment with actual defect types.</div><div>Based on this dataset, we analyze existing defect detection methods for in-service aero-engine blades and propose an improved edge-guided and channel-enhanced network using the \"Transformer\" architecture. Our method leverages global edge information from \"Segment Anything (SAM)\" to guide learning, while the channel shuffling module boosts feature capture. Experimental results show an mean intersection over union (mIoU) of 88.13 % and a detection speed of 30.6 frames per second (FPS) on a single graphics processing unit (GPU), meeting real-world efficiency needs. The code will be publicly available at the link: <span><span>https://github.com/Newbiejy/EGCIENet_In-service-blade-defect-detection</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"154 ","pages":"Article 110974"},"PeriodicalIF":7.5,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143891754","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}