Concurrency and Computation-Practice & Experience最新文献

When leaked fuel encounters heat sources, pool fire scenarios occurring in confined fan cavity threaten engine operation safety. Various obstacles' structures, positions, and heights made pool fire propagation mechanisms complicated. Pool fire plume propagation characteristics were investigated in obstructed fan cavity. Both LES turbulent and mixed fraction diffused flame combustion models were established. Three EEC positions and heights were considered. Grid independences were validated. Effects of EEC positions and heights were examined on fire plume temperature distribution behaviors in fan cavity. The results show that fire plume temperature variations and their distributions agree well with experimental ones. The plume temperature undergoes an increase stage and a quasi-steady one with oscillations. EEC positions and heights have no evident effects on plume temperature variations at the bottom of the fan cavity. EEC with positions closer to the pool and higher heights hinders the fire propagation along the inner ring, but accelerates the fire plume floating across EEC and increases local temperature at the left side or the top of the fan cavity. EEC absence produces plume propagation at the right side of the fan cavity, makes its local temperature relatively low, and its oscillation more evident. EEC obstruction squeezes flame shapes and has unsymmetrical–symmetrical alternate variations. The fire plume develops rearwards.

Accurate prediction of magnetic core loss is paramount for advancing power electronics but is severely hindered by the nonlinear coupling of multiple factors including frequency, flux density, excitation waveform, temperature, and material properties. To address this, we propose a comprehensive data-driven framework that integrates model refinement, coupling analysis, and multiobjective optimization. First, a temperature-corrected Steinmetz equation is developed, extending its validity and reducing the mean relative prediction error by more than half. Second, the individual and synergistic effects of these key variables are quantified via regression and the Artificial Hummingbird Algorithm (AHA), pinpointing the optimal combination for global loss minimization. Third, an ultra-accurate Gradient Boosting Decision Tree (GBDT) model is established as a fast surrogate, leveraging key features like peak flux density for subsequent optimization. Finally, a constrained multiobjective optimization is performed, balancing core loss minimization against magnetic energy transfer maximization. The derived optimal design achieves a 30% core loss reduction compared to conventional benchmarks without compromising energy throughput. This work provides a systematic, data-driven pathway for the design of high-performance magnetic components, offering significant performance gains over traditional approaches.

Manual measurement of cattle body size presents challenges, such as inducing stress responses in animals and inefficiencies. For large livestock like cattle, measurement based on full point clouds involves extensive computations and interference between different cloud sections. To address this, we propose MMLG-Point, a novel deep learning model for cattle point cloud segmentation and body size measurement, which introduces a Multilevel Geometric Perception Encoder and a Transformer-based decoder architecture. The encoder integrates Kernel Point Convolution (KPConv) and Separable Structure-Aware Learning (SSAL) with residual multiscale fusion to capture local geometric structures of large livestock point clouds, while the decoder employs CrossNorm and SelfNorm (CNSN) modules to enhance generalization under limited labeled data. Furthermore, an unsupervised pretraining strategy based on masked point reconstruction is proposed, enabling the model to learn structural and semantic representations from unlabeled cattle point clouds. Experimental results demonstrate that MMLG-Point achieves outstanding segmentation accuracy with minimal supervision, obtaining an overall accuracy (OA) of 94.3% and a mean Intersection over Union (mIoU) of 89.4% on the Simmental cattle dataset using only 12 labeled samples. The model also exhibits strong cross-species generalization, achieving 92.3% OA and 86.7% mIoU on pig datasets. Based on segmentation results, an automatic cattle body measurement algorithm is developed, incorporating density analysis, curvature detection, and contour extraction to compute parameters such as withers height, hip height, body length, chest girth, and abdominal circumference, achieving a mean absolute percentage error (MAPE) below 6%. These results confirm that the proposed MMLG-Point framework provides an effective and generalizable approach for high-precision segmentation and measurement of large livestock point clouds.

Mobile application recommendation has emerged as a pivotal domain within the realm of personalized recommendation systems. Traditional mobile application sequence recommendation approaches are predominantly dedicated to the pursuit of sophisticated sequence encoders to achieve more precise representations. However, existing sequence recommendation methods primarily consider the sequential order of historical App interactions, overlooking the time intervals between applications. This oversight hinders the model's capability to fully unearth the temporal correlations in user behavior, consequently limiting the accuracy and personalization of mobile application recommendations. Moreover, the interactions between users and mobile applications are typically sparse, which weakens the model's generalization capabilities. To address these issues, we propose a novel method for mobile application sequence recommendation, incorporating time interval-aware attention and contrastive learning (called Ti-CoRe). Specifically, this approach introduces a novel sequence augmentation strategy based on similarity replacement within a contrastive learning framework. By considering textual similarities between applications, this method selectively replaces applications that possess lower similarity scores to generate augmented sequences, increasing the diversity of the sample space and mitigating data sparsity. Furthermore, integrating a time interval-aware mechanism into the BERT4Rec model, the paper presents a new T-BERT encoder. It precisely assesses the influence of fluctuating time intervals on the prediction of the subsequent mobile application, thereby ensuring a more nuanced app representation. Experiments conducted on the 360APP real dataset demonstrate that Ti-CoRe consistently outperforms various baseline models in terms of NDCG and HR metrics.

Artificial intelligence hardware accelerators are gaining increasing importance in domains such as computer vision and robotics. However, deploying Convolutional Neural Networks (CNNs) on embedded systems with constrained resources and memory continues to pose a major challenge. Motivated by the requirements of robotic vision, this paper presents a DSP-Efficient Packing Strategy (DEPS) accelerator architecture tailored for lightweight CNNs, improving both computational throughput and hardware efficiency in real-time robotic applications. Unlike previous FPGA designs that underutilize DSP blocks, the proposed DEPS enables the parallel execution of twelve 3-bit multiplications within a single DSP48E2 unit. A layer-wise pipelined mapping scheme is also proposed, which directly maps each CNN layer onto hardware without intermediate buffering, ensuring continuous computation and minimizing latency. The proposed accelerator is incorporated into an intelligent tennis serving robot, serving as the real-time vision module for object detection. Experimental results from VGG7-tiny and UltraNet demonstrate throughputs of 299.4 GOPS and 340.0 GOPS, respectively, alongside power efficiencies of 80.1 GOPS/W and 89.2 GOPS/W. The robotic system deployment confirms that superior DSP utilization is achieved, enabling rapid, energy-efficient, and reliable perception. This work highlights the potential of the proposed design for application in resource-constrained edge platforms and practical robotics.

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.