Concurrency and Computation-Practice & Experience最新文献

Data deduplication plays an important role in modern data management as it reduces storage costs and ensures consistency by eliminating redundant records. The traditional data deduplication methods are effective for exact matches but struggle with adaptability and detecting near-exact duplicate records in unstructured or complex data. Machine learning (ML) addresses these limitations by using pattern recognition, feature learning, and statistical modeling to identify subtle similarities between records. This review classifies ML-based deduplication techniques into supervised, unsupervised, semi-supervised, and deep learning methodologies. It also discusses key challenges, including class imbalance, model interpretability, and computational overhead. The paper also explores recent developments in federated learning, real-time deduplication, and multimodal techniques to highlight current trends in these areas. Finally, the paper identifies key open issues and proposes a unified perspective for scalable, real-time deduplication systems that can accommodate diverse data types, structures, and system requirements.

The rapid adoption of electric vehicles (EVs) highlights the need for intelligent systems to improve energy efficiency and optimize driving range. Since energy consumption and driving range modeling are closely related, understanding the energy consumption (EC) of EVs can provide essential insights to drivers and reduce “range anxiety.” Previous studies have relied on traditional analytical and statistical methods, which lack the representativeness of influential factors and the interpretability of the model applied in EC modeling. To address this issue, we propose an explainable ensemble machine learning model to predict EC of EVs, considering the most important features and the factors that exhibit greater influence on EC. The Spritmonitor public real-world dataset is used for this study. First, data preprocessing is conducted before feeding data into the ensemble method. Second, the Energy Consumption Rate (ECR) was predicted using Gradient Boosting Regression Trees (GBRT). The proposed predictive framework demonstrates superior prediction accuracy compared to baseline models. GBRT achieved the highest R ² (1 and 0.99 for training and testing, respectively) and the lowest MAE (0.08) and RMSE (0.16) compared to other models, including XGBoost, LightGBM, and CatBoost. Finally, SHAP (Shapley Additive exPlanations) analysis was applied to explain the proposed model and identify the most influential dynamics factors, including driving range, capacity, speed, state of charge (SOC), ambient temperature, road type, driving style, air conditioning, and heating usage. The results suggest that the proposed framework can effectively enhance the prediction of the EC of EVs and facilitates the analyze driving factors, thereby supporting intelligent trip planning, adaptive energy-aware management in transportation systems and provide insightful feedback to drivers.

Accurate forecasting of carbon emissions from power generation enterprises is essential under China's dual-control policy. Although deep learning methods show strong potential, studies on their optimal configuration remain limited. This paper proposed a hybrid deep learning framework integrating a convolutional neural network (CNN), bidirectional long short-term memory (BiLSTM), and an attention mechanism for carbon emission prediction in natural gas power plants. The present study utilized two distinct optimization methodologies: a structured design strategy encompassing light, medium, and heavy configurations, while the other employed Bayesian optimization for hyperparameter tuning. The models were evaluated using 5-fold cross-validation on 619 operational samples from two 487.1-MW condensing units in a power plant in Hainan, China. The medium configuration achieved the best balance between accuracy, efficiency, and stability, with R² = 0.9833, RMSE = 0.0342, and MAE = 0.0242. Under small-sample conditions, the structured design approach outperformed Bayesian optimization by 0.16% in accuracy while requiring only 7.42% of the training time. The proposed framework provides an efficient and interpretable reference for selecting deep learning architectures in small-sample industrial regression tasks and supports intelligent, low-carbon power generation applications.

Library inventory is vital for collection management and reader satisfaction. Conventional manual methods cannot support real-time updates, while existing automated solutions relying on centralized cloud computing suffer from bandwidth and latency limitations. To address these issues, we propose an edge-cloud collaborative real-time book inventory system. Spine detection and text recognition are executed on embedded edge devices, while the cloud handles rapid data retrieval to balance timeliness and accuracy. We design lightweight models for edge deployment, including the Library You Only Look Once (Lib-YOLO) detector with a StarNet backbone, shared convolutional head, and dual-scale hierarchical detection, supporting rotated objects for robust spine extraction. The optimized paddle practical optical character recognition (PP-OCR) pipeline removes text rectification and integrates a filtering algorithm to reduce redundant computation and improve efficiency. Deployed on an NVIDIA Jetson Nano, the system achieves 73 ms spine detection latency, 191 ms text recognition latency, and 97.1% overall accuracy under simulated library conditions. The Lib-YOLO model contains only 1.39 M parameters with 99% mean average precision (mAP), demonstrating the feasibility of precise, real-time inventorying in resource-constrained embedded environments.

Privacy-Preserving Data Sharing (PPDS) masks the individual's collected data (e.g., medical healthcare data) before being disseminated by organizations for analysis and research. Patient data contains sensitive values that must be dealt with while ensuring certain privacy conditions are met. This minimizes the risk of re-identification of an individual record from the group of privacy-preserved data. However, with the advancement in technology (i.e., Big Data, the Internet of Things (IoT), and Blockchain), the existing classical privacy-preserving techniques are becoming obsolete. In this paper, we propose a blockchain-based secure data sharing technique named “SecureChain”, which preserves the privacy of an individual record using local differential privacy (LDP). The three distinguished features of the proposed approach are lower latency, higher throughput, and improved privacy. The proposed model outperforms the benchmarks in terms of both latency and throughput. In terms of precision, the proposed method improves the accuracy to 88.53% compared to its counterparts, which achieved 49% and 85% accuracy. The results of the experiment verify that the proposed approach outperforms its counterparts.

For cross-city traffic prediction, the significant heterogeneity of traffic data across cities and the requirement for privacy protection make it challenging for conventional centralized spatiotemporal graph modeling techniques to balance predictive performance and data security. Therefore, this paper proposes AT-SPNet, a personalized federated spatiotemporal modeling approach specifically designed for cross-city traffic prediction. This method decouples the spatiotemporal modeling paths through the construction of a shared temporal branch and a hidden local spatial branch, thereby mitigating the heterogeneity of cross-city traffic data while preserving privacy. In the temporal branch, Gated Recurrent Units and a multi-head attention mechanism are incorporated to capture temporal dependencies, and a Squeeze-and-Excitation module is employed to enhance the extraction of informative features. In the spatial branch, a Spatial Attention Fusion module based on a triple-attention mechanism is designed to capture spatial features from multiple spatial perspectives, combined with static graph convolution and dynamic graph attention to construct a dual-modal information fusion path. Furthermore, to alleviate the adverse effects of cross-city data heterogeneity in federated training, a personalized federated learning strategy is introduced, which enables differentiated fusion of client spatial features without sharing raw data. Experiments on four real-world traffic datasets demonstrate that AT-SPNet outperforms existing methods in both prediction accuracy and cross-city generalization, validating the effectiveness and practical applicability of the proposed approach for cross-city traffic prediction.

Brain tumors (BT) are considered a major health challenge around the world, which needs early detection; therefore, effective treatment strategies can be planned. This kind of cancer greatly diminishes the patient's quality and lifespan, which opens a gateway for early diagnosis and effective treatment. The medical professionals need assistance with this difficult and error-prone process; it is also mandatory to augment the interpretability and accuracy of the recognition model. To achieve such a goal, a hybrid deep learning model superior with explainable AI is introduced in the proposed framework, which performs brain tumor classification and model interpretation from MRI. The proposed study involves four key steps: Pre-processing, segmentation, classification, and analysis. The input images are initially pre-processed using a median-boosted Kuan Filtering (Me-KF) to remove any noise in the data and improve the subsequent segmentation procedure. After pre-processing, the Extended Multi-Inception Attention U-Net (ExMIA_U-Net) technique is added to effectively separate the brain tumor region. Finally, a deep learning method based on Convolution Attentive assisted EfficientNetB0 (CA-EfficientNetB0) is presented to categorize the many categories of brain tumors, comprising gliomas, meningiomas, pituitary tumors and normal tumors. This model uses Shapley additive explanation (SHAP), Local interpretable model-agnostic explanations (LIME), and Gradient-weighted Class Activation Mapping (Grad-CAM) for model interpretation. The proposed model uses a brain tumor classification dataset. In the results section, the proposed model is compared to many other prevailing schemes and it achieves 99.45% accuracy, 99.16% precision, 98.97% recall, and a 99.06% F1-score. The results show that an efficient, interpretable, robust and better model is developed for brain tumor classification.

In online social networks, identifying influential users is crucial for maintaining network stability and accelerating information dissemination. However, most of the existing research evaluate the influence of users according to the topological structure of local or global networks, which ignores the historical information and social interactions of users. In this work, we introduce a novel algorithm called MADS-UC to pinpoint the influential super-spreaders of information. Specifically, three kinds of activation influence between each pair of users are defined to better portray the mutual interactions with each other, and the proposed measure makes full consideration of the topological and historical information of networks, and the social interactions of users. Then, a hybrid multi-attribute decision-making algorithm is put forward to evaluate the influence of users, while the obtained three kinds of activation influence are introduced as basic indicators, and the weight for each indicator is determined from both subjective and objective dimensions. Finally, to achieve a good balance between algorithm accuracy and time complexity, the influential users are identified by considering the interactions between a user and other users within its influence range. We collect seven real-world datasets from the Sina Weibo platform in 2024 about mobile product Honor, and a series of experiments is conducted to validate the effectiveness of the MADS-UC algorithm. Experimental results show that MADS-UC surpasses six widely used algorithms in robustness, sensitivity analysis, and distinguishing capability, which is useful in accelerating the dissemination of information in the product marketing process.

Brain tumors (BT) are considered a major health challenge around the world, which needs early detection; therefore, effective treatment strategies can be planned. This kind of cancer greatly diminishes the patient's quality and lifespan, which opens a gateway for early diagnosis and effective treatment. The medical professionals need assistance with this difficult and error-prone process; it is also mandatory to augment the interpretability and accuracy of the recognition model. To achieve such a goal, a hybrid deep learning model superior with explainable AI is introduced in the proposed framework, which performs brain tumor classification and model interpretation from MRI. The proposed study involves four key steps: Pre-processing, segmentation, classification, and analysis. The input images are initially pre-processed using a median-boosted Kuan Filtering (Me-KF) to remove any noise in the data and improve the subsequent segmentation procedure. After pre-processing, the Extended Multi-Inception Attention U-Net (ExMIA_U-Net) technique is added to effectively separate the brain tumor region. Finally, a deep learning method based on Convolution Attentive assisted EfficientNetB0 (CA-EfficientNetB0) is presented to categorize the many categories of brain tumors, comprising gliomas, meningiomas, pituitary tumors and normal tumors. This model uses Shapley additive explanation (SHAP), Local interpretable model-agnostic explanations (LIME), and Gradient-weighted Class Activation Mapping (Grad-CAM) for model interpretation. The proposed model uses a brain tumor classification dataset. In the results section, the proposed model is compared to many other prevailing schemes and it achieves 99.45% accuracy, 99.16% precision, 98.97% recall, and a 99.06% F1-score. The results show that an efficient, interpretable, robust and better model is developed for brain tumor classification.