Applied Intelligence最新文献

{"title":"Light-wDEF: lightweight deepfake evaluation framework for efficient and reliable visual detection","authors":"Muhammad Yousaf,&nbsp;Sarwar Shah Khan,&nbsp;Babar Shah,&nbsp;Muhammad Shehzad Khan,&nbsp;Muhammad Awais Bacha,&nbsp;Mian Saeed Akbar,&nbsp;Ijaz Ali,&nbsp;Fernando Moreira","doi":"10.1007/s10489-026-07460-2","DOIUrl":"10.1007/s10489-026-07460-2","url":null,"abstract":"<div><p>Deepfake technology synthesizes and manipulates digital content to produce artificial videos in which an individual’s identity, facial appearance, or actions are convincingly altered. These forgeries can be highly realistic, posing serious risks to trust in digital media and undermining personal reputation, dignity, and the integrity of public discourse. This paper presents the Lightweight Deepfake Evaluation Framework (Light-wDEF)– a resource-efficient, reproducible framework tailored for large-scale evaluation of visual deepfake detectors on modest hardware. Light-wDEF combines deterministic frame sampling, batched MTCNN face extraction, streaming append-only storage with lazy offset indexing, online Albumentations augmentations, stratified splits with class-aware sampling, and robust training (AdamW, optional focal loss, per-epoch checkpointing with exact resume). Light-wDEF is designed as a reproducible and resource-conscious evaluation framework that focuses on experimental standardization, reproducibility, and efficient benchmarking of deepfake detection models. Using Light-wDEF, ConvNeXt-Base is identified as the most effective visual model in this study on the basis of AUC, balanced accuracy, F1, precision and recall while remaining compatible with Colab T4-class resource constraints. Ten modern visual models were trained and evaluated under identical conditions across five public datasets (Celeb-DF, FaceForensics++, Google DFD, FakeAVCeleb, DFDC Preview). Results show that convolutional families provide the best practical balance of discrimination and efficiency (ConvNeXt-Base achieves <span>(AUCge 0.96)</span> and <span>(text {F1}ge 0.94)</span> on the evaluated sets). The findings also expose limitations of visual-only detection on multimodal corpora such as FakeAVCeleb, motivating future multimodal fusion and domain-adaptation research. Fixed seeds, archived checkpoints, and environment metadata are provided to support exact replication.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"56 14","pages":""},"PeriodicalIF":3.5,"publicationDate":"2026-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148927129","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-view multi-scale feature enhancement and fusion for fine-grained visual classification","authors":"Ke Zhang,&nbsp;Junkai Zhong,&nbsp;Peng Gao,&nbsp;Qianhao Zhao,&nbsp;Jianlei Liu,&nbsp;Zhanhua Dong","doi":"10.1007/s10489-026-07465-x","DOIUrl":"10.1007/s10489-026-07465-x","url":null,"abstract":"<div><p>Fine-grained visual classification (FGVC) aims to distinguish highly similar subcategories within the same coarse-grained category and is important in biodiversity monitoring, intelligent transportation, and industrial inspection. However, its performance is often degraded by subtle inter-class differences, large intra-class variations, scale changes, occlusion, and cluttered backgrounds. These factors weaken discriminative responses and easily induce shortcut learning from background context, thereby limiting generalization. To address this problem, a dual-view multi-scale feature enhancement and fusion network is proposed for accurate and efficient FGVC. Specifically, a lightweight multi-scale feature enhancement module is designed to strengthen discriminative cues in features through multi-branch modeling and channel attention. A dynamic feature fusion module is then designed to align and adaptively integrate enhanced multi-level features in both spatial and channel dimensions, producing more informative representations. In addition, a dual-branch self-distillation framework is constructed, in which the raw-image branch and the enhanced-view branch share the same architecture. Combined with open-vocabulary text-guided foreground cropping and an augmented-view transfer module, the soft predictions of the enhanced branch are used to guide the raw branch toward foreground-oriented decision boundaries. During inference, only a single branch is retained, so improved performance is achieved without additional inference overhead. Extensive experiments on multiple public FGVC benchmarks demonstrate the effectiveness, robustness, and generality of the proposed method.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"56 14","pages":""},"PeriodicalIF":3.5,"publicationDate":"2026-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148927036","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":"H-PLE: hierarchical progressive layered extraction with raw-input-aware gating for multi-task recommendation under extreme label imbalance","authors":"Jinghao Xue,&nbsp;Tianxiang Yang,&nbsp;Hideo Suzuki","doi":"10.1007/s10489-026-07441-5","DOIUrl":"10.1007/s10489-026-07441-5","url":null,"abstract":"<div><p>Multi-task recommendation systems typically rely on shared representations to improve data efficiency by jointly modeling multiple user feedback signals. However, under <i>extreme label imbalance</i>, such sharing can exacerbate <i>negative transfer</i>, where improving one task degrades another. Existing multi-task architectures, such as MMoE and Progressive Layered Extraction (PLE), attempt to mitigate task interference through expert-based routing, but they still rely on fully learned soft gating over shared and task-specific experts. Under severe imbalance, the gating networks are often dominated by high-frequency tasks, leading to unstable routing and insufficient representation learning for sparse tasks. To address this limitation, we propose H-PLE, a hierarchical multi-task recommendation framework built upon progressive layered extraction. H-PLE incorporates three complementary design elements: a hierarchical extraction structure that progressively separates shared and task-specific representations across stacked layers, a raw-input-aware gating mechanism (AGC) that injects the projected raw input as a residual candidate to stabilize routing under sparse supervision, and a lightweight expert-level interaction module that introduces FM-style second-order feature interactions to enhance inductive bias. The evaluation includes multi-seed runs, independent random splits, modern baselines, component ablations, calibration metrics, PR-AUC, GAUC, and threshold-optimized F1. Experiments on two real-world Tenrec video recommendation scenarios (QK and QB) with highly imbalanced engagement tasks (Like and Share) show that H-PLE-family variants consistently improve sparse-task ranking and minority-class retrieval over MMoE and PLE, while remaining competitive with or stronger than Cross-Stitch, PCGrad, and loss-rebalancing baselines (focal, class-balanced BCE), all of which underperform vanilla MMoE in our most imbalanced setting and therefore highlight the difficulty of the QB-Share scenario. The results also reveal an important limitation: the full H-PLE model is not uniformly best on every QB metric; AGC is the most robust component under the most extreme sparsity, while FM is beneficial when its interaction rank is carefully controlled.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"56 14","pages":""},"PeriodicalIF":3.5,"publicationDate":"2026-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148927037","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":"Trustworthy LLM–GNN systems: a systematic review and multi-axis taxonomy","authors":"Ruizhan Xue,&nbsp;Fang He,&nbsp;Huimin Deng,&nbsp;Maojun Wang,&nbsp;Zeyu Zhang","doi":"10.1007/s10489-026-07458-w","DOIUrl":"10.1007/s10489-026-07458-w","url":null,"abstract":"<div><p>Large language models (LLMs) give graph neural networks (GNNs) access to semantic knowledge, instruction following, and natural-language reasoning. The same integration creates new failure channels, including unsupported graph edits, prompt injection, privacy exposure, and inherited social bias. We review trustworthy LLM–GNN systems using a taxonomy that separates five trust dimensions from the operational role of the LLM. The trust dimensions are reliability, robustness, privacy, fairness, and reasoning and explainability. The operational roles are encoder, predictor, aligner, editor, and verifier or evaluator. This separation allows a method to have a primary trust objective while retaining relevant secondary effects. We use it to connect integrated methods with classical trustworthy-GNN baselines, heterophilic and hypergraph learning, few-shot settings, instruction tuning, and graph-reasoning benchmarks. The comparison focuses on threats, safeguards, evaluation settings, and reported evidence, while identifying results that cannot be compared directly. The review shows where language information helps graph learning, where it creates additional risk, and which safeguards are needed across the system lifecycle.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"56 14","pages":""},"PeriodicalIF":3.5,"publicationDate":"2026-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148927039","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":"Signature-enhanced graph spectral HAR for multivariate realized volatility forecasting","authors":"Zeyu Guo,&nbsp;Andi Han,&nbsp;Chao Wang,&nbsp;Junbin Gao","doi":"10.1007/s10489-026-07445-1","DOIUrl":"10.1007/s10489-026-07445-1","url":null,"abstract":"<div><p>This paper examines multivariate realized-volatility forecasting in globally connected equity markets. Heterogeneous AutoRegressive (HAR) models and graph signal processing (GSP)-based extensions such as the graph signal processing HAR model (GSPHAR) embed spillover structure via the magnetic Laplacian and graph Fourier transform. However, they still summarize each market’s recent history mainly through multi-scale lag averages, which can miss nonlinear within-window path information. To address this limitation, we develop a signature-enhanced graph spectral HAR framework, Sig-GSPHAR, which incorporates path-signature features extracted from each market’s 22-day volatility window and fuses them with HAR lags in the directed graph spectral domain. An empirical study on 29 stock markets and five realized-volatility proxies shows that, for one-step-ahead forecasting (<span>(varvec{h = 1})</span>), Sig-GSPHAR outperforms econometric and deep learning benchmarks and delivers consistent gains over GSPHAR, with paired one-sided Wilcoxon signed-rank tests (Holm-adjusted) indicating significance across multiple proxies. For long-horizon forecasting (<span>(varvec{h = 22})</span>), direct comparisons against GSPHAR indicate that the advantage of Sig-GSPHAR becomes more pronounced. We further show that the static spillover graph is structurally stable over the sample, equip the point forecasts with distribution-free conformal prediction intervals, and provide a detailed diagnostic of when signature features help.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"56 14","pages":""},"PeriodicalIF":3.5,"publicationDate":"2026-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10489-026-07445-1.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148927040","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing NWP precipitation forecasting with Rain-PostEFNet: A multi-scale deep learning approach","authors":"Farah Naz,&nbsp;Lei She,&nbsp;Xincan Sui,&nbsp;Chenghong Zhang,&nbsp;Jie Shao","doi":"10.1007/s10489-026-07457-x","DOIUrl":"10.1007/s10489-026-07457-x","url":null,"abstract":"<div><p>Accurate precipitation forecasting is essential for disaster preparedness, water resource management, and climate modeling. Numerical Weather Prediction (NWP) models, while extensively utilized, suffer from inherent limitations such as systematic biases, coarse spatial resolution, and difficulty in accurately predicting extreme rainfall events. Deep learning-based post-processing has emerged as a promising approach to refine NWP outputs, but existing methods struggle with effectively capturing multi-scale meteorological features and addressing severe class imbalances in extreme precipitation predictions. To overcome these challenges, we propose Rain-PostEFNet, a multi-scale deep learning framework for post-processing NWP precipitation forecasts that captures meteorological features across scales and mitigates severe class imbalance in extreme precipitation forecasts. It integrates EfficientNet for feature extraction, ECA-Net for adaptive channel attention, and FPN-Swin-Unet for multi-scale feature refinement, along with a multi-task learning strategy that jointly optimizes classification and regression tasks using weighted focal loss and Mean Squared Error (MSE) loss to improve predictive skill for rare heavy rain events. We evaluate our approach on the PostRainBench datasets (China, Germany, Korea) using Critical Success Index (CSI), Heidke Skill Score (HSS), and Accuracy (ACC) as evaluation metrics. Experimental results demonstrate that Rain-PostEFNet significantly outperforms state-of-the-art baselines, achieving relative CSI improvements of 63.94% in China, 4.28% in Germany, and 2.1% in Korea for moderate rainfall, and 78.34% in China, 9.09% in Germany, and 7.68% in Korea for heavy rainfall. Similarly, HSS increases by 52.18% in China and 2.95% in Germany for moderate rain, and by 52.4% in China and 6.78% in Germany for heavy rain. Additionally, an ablation study further confirms the impact of the multi-task learning framework and attention mechanisms in refining NWP predictions.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"56 14","pages":""},"PeriodicalIF":3.5,"publicationDate":"2026-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148927038","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":"Efficient and robust DNN model fingerprint with decision difference regions identification","authors":"Tianxiang Luo,&nbsp;Zi Yang,&nbsp;Xiaorui Dai,&nbsp;Bo Wang,&nbsp;Wei Wang","doi":"10.1007/s10489-026-07440-6","DOIUrl":"10.1007/s10489-026-07440-6","url":null,"abstract":"<div><p>Deep neural network (DNN) models are valuable intellectual property, and black-box ownership verification is needed when they are copied, extracted, or post-processed. Existing fingerprints can identify source-related models but may not explicitly separate them from independently trained benign models, leaving owners exposed to false-accusation risk. This paper upgrades fingerprint evidence from a source-boundary transferability heuristic to an explicit ownership-separation objective: we formulate fingerprint construction as a decision difference region (DDR) search problem and solve it with two non-invasive variants—Fast variant for low-cost screening and Selected variant for higher-confidence offline filtering—giving owners a tunable trade-off between construction cost and verification confidence. Evaluation spans CIFAR-10 and the German Traffic Sign Recognition Benchmark (GTSRB), with CIFAR-100 and Tiny-ImageNet as stress tests, across diverse source architectures, hard negatives, and extraction attacks. The results support tested verification while identifying its limits, giving practitioners ownership evidence with an explicit account of where the separation holds and where it does not.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"56 14","pages":""},"PeriodicalIF":3.5,"publicationDate":"2026-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148927013","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":"RCGELM-AE: an efficient graph embedding deep model without gradient descent","authors":"Xinyi Lin,&nbsp;Xiaoyun Chen,&nbsp;Shulan Zheng,&nbsp;Wenjian Chen","doi":"10.1007/s10489-026-07437-1","DOIUrl":"10.1007/s10489-026-07437-1","url":null,"abstract":"<div><p>Graph embedding encodes high-dimensional sparse graph data into low-dimensional features for downstream tasks. Existing Graph Autoencoders (GAEs) can integrate structural and attribute information by graph convolution, but their training relies on gradient descent often results in slow convergence and susceptibility to local optima. To address above challenges, this study proposes a model called the Residual compensation graph Convolutional Generalized Extreme Learning Machine Autoencoder (RCGELM-AE), which is built on the Extreme Learning Machine Autoencoder (ELM-AE) and incorporates two key designs. Firstly, it embeds graph convolution operations between the input and hidden layers, compensating for GELM-AE’s inherent inability to capture the topological information of graphs. Secondly, it introduces a residual compensation mechanism that extracts deep-level features from the reconstruction errors of the encoder. This mechanism not only avoids the over-smoothing risk caused by repeatedly stacked graph propagation commonly observed in deep graph models, but also enhances the model’s representational power. Specifically, in link prediction tasks, AUC and AP are improved by 4.11%–8.93% and 4.01%–10.01%. In node classification tasks, F1-micro and F1-macro scores increase by 0.42%–4.97% and 0.48%–5.27%, respectively, with a notable reduction in running time. Overall, this framework offers a novel, gradient-descent-free solution for achieving efficient and effective graph embedding.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"56 14","pages":""},"PeriodicalIF":3.5,"publicationDate":"2026-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148927014","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":"Micro-expression recognition via optical strain and spectral-spatial gating networks","authors":"Siyu Xiong,&nbsp;Jun Wang,&nbsp;Xuan Huang,&nbsp;Kiminori Sato,&nbsp;Bo Wu","doi":"10.1007/s10489-026-07464-y","DOIUrl":"10.1007/s10489-026-07464-y","url":null,"abstract":"<div><p>Micro-expression recognition (MER) is a challenging task due to the transient nature of facial movements and their susceptibility to interference from rigid head motion and high-frequency sensor noise. Current approaches, which often rely on raw optical flow or purely data-driven architectures, struggle to decouple subtle muscle deformations from this global noise. To address these issues, we propose a Spectral-Spatial-Strain Network (S3Net), a unified physics-aware framework. First, we introduce an early fusion strategy utilizing Dual TV-L1 optical flow and optical strain. By calculating the strain magnitude, we provide the network with a physical prior that helps emphasize non-rigid muscle movements and reduce the influence of head rotations. Second, we design a Spectral Gating Block (SGB) integrated into the ResNet backbone, which leverages the frequency domain to filter sensor noise. Third, a Strain Excitation Block (SEB) is used to recalibrate high-level features in the strain-fused feature stream. Extensive experiments under the official Micro-Expression Grand Challenge 2019 (MEGC2019) 442-sample composite protocol (SAMM, CASME II, and SMIC) demonstrate the effectiveness of our method. S3Net achieves an Unweighted F1-score (UF1) of 85.38% and an Unweighted Average Recall (UAR) of 85.96% on the composite benchmark with the Top-K + flip test-time augmentation (TTA) setting. We also report a strict leave-one-subject-out (LOSO) reference using a fixed stochastic weight averaging (SWA) schedule without held-out-subject checkpoint selection. Together, these results present S3Net under both the final Top-K + flip TTA setting and the stricter no-held-out-selection fixed-SWA reference, while the additional ablation, robustness, efficiency, and statistical analyses clarify the scope and limitations of the method.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"56 14","pages":""},"PeriodicalIF":3.5,"publicationDate":"2026-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148926396","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":"DiffKT: a diffusion model for fine-grained knowledge tracing","authors":"Ruidi Liu,&nbsp;Yong Niu,&nbsp;Hu Li","doi":"10.1007/s10489-026-07459-9","DOIUrl":"10.1007/s10489-026-07459-9","url":null,"abstract":"<div><p>Accurately modeling learners’ evolving knowledge states is a long-standing challenge in intelligent education systems, especially under fine-grained temporal dynamics and inherently noisy learning interactions. Most existing knowledge tracing methods rely on deterministic graph-based or sequential modeling, which often struggle to disentangle genuine knowledge mastery from interaction noise such as guessing and careless errors. To address these challenges, this paper proposes DiffKT, a diffusion-based framework for fine-grained knowledge tracing that models learners’ knowledge states as probabilistic distributions rather than fixed point estimates. DiffKT integrates a dual-graph representation to capture student–question interactions and question–skill associations, together with a state-space sequence model that efficiently encodes long-range learning dependencies with linear complexity. Building upon these representations, a conditional diffusion model with an adaptive noise scheduling strategy is introduced to explicitly distinguish different types of interaction noise, enabling robust denoising and more accurate estimation of latent knowledge states. Extensive experiments on three real-world educational datasets demonstrate that DiffKT consistently outperforms advanced knowledge tracking methods in terms of prediction accuracy and stability, highlighting its effectiveness in modeling noisy and fine-grained learning behaviors.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"56 14","pages":""},"PeriodicalIF":3.5,"publicationDate":"2026-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148871690","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}