Search Results (96)

Accurate and timely estimation of soybean emergence at the plot scale using unmanned aerial vehicle (UAV) remote sensing imagery is essential for germplasm evaluation in breeding programs, where breeders prioritize overall plot-scale emergence rates over subimage-based counts. This study proposes PlotCounter, a deep learning regression model based on the TasselNetV2++ architecture, designed for plot-scale soybean seedling counting. It employs a patch-based training strategy combined with full-plot validation to achieve reliable performance with limited breeding plot data. To incorporate additional agronomic information, PlotCounter is extended into a multitask learning framework (MTL-PlotCounter) that integrates sowing metadata such as variety, number of seeds per hole, and sowing density as auxiliary classification tasks. RGB images of 54 breeding plots were captured in 2023 using a DJI Mavic 2 Pro UAV and processed into an orthomosaic for model development and evaluation, showing effective performance. PlotCounter achieves a root mean square error (RMSE) of 6.98 and a relative RMSE (rRMSE) of 6.93%. The variety-integrated MTL-PlotCounter, V-MTL-PlotCounter, performs the best, with relative reductions of 8.74% in RMSE and 3.03% in rRMSE compared to PlotCounter, and outperforms representative YOLO-based models. Additionally, both PlotCounter and V-MTL-PlotCounter are deployed on a web-based platform, enabling users to upload images via an interactive interface, automatically count seedlings, and analyze plot-scale emergence, powered by a multimodal large language model. This study highlights the potential of integrating UAV remote sensing, agronomic metadata, specialized deep learning models, and multimodal large language models for advanced crop monitoring. Full article

Leaf chlorophyll content (LCC), leaf area index (LAI), and above-ground biomass (AGB) are important growth parameters for characterizing potato growth and predicting yield. While deep learning has demonstrated remarkable advancements in estimating crop growth parameters, the limited availability of field data often compromises model accuracy and generalizability, impeding large-scale regional applications. This study proposes a novel deep learning model that integrates multi-task learning and few-shot learning to address the challenge of low data in growth parameter prediction. Two multi-task learning architectures, MTL-DCNN and MTL-MMOE, were designed based on deep convolutional neural networks (DCNNs) and multi-gate mixture-of-experts (MMOE) for the simultaneous estimation of LCC, LAI, and AGB from Sentinel-2 imagery. Building on this, a few-shot learning framework for growth prediction (FSLGP) was developed by integrating simulated spectral generation, model-agnostic meta-learning (MAML), and meta-transfer learning strategies, enabling accurate prediction of multiple growth parameters under limited data availability. The results demonstrated that the incorporation of calibrated simulated spectral data significantly improved the estimation accuracy of LCC, LAI, and AGB (R² = 0.62~0.73). Under scenarios with limited field measurement data, the multi-task deep learning model based on few-shot learning outperformed traditional mixed inversion methods in predicting potato growth parameters (R² = 0.69~0.73; rRMSE = 16.68%~28.13%). Among the two architectures, the MTL-MMOE model exhibited superior stability and robustness in multi-task learning. Independent spatiotemporal validation further confirmed the potential of MTL-MMOE in estimating LAI and AGB across different years and locations (R² = 0.37~0.52). These results collectively demonstrated that the proposed FSLGP framework could achieve reliable estimation of crop growth parameters using only a very limited number of in-field samples (approximately 80 samples). This study can provide a valuable technical reference for monitoring and predicting growth parameters in other crops. Full article

Lung nodule detection and segmentation are essential tasks in computer-aided diagnosis (CAD) systems for early lung cancer screening. With the growing availability of CT data and deep learning models, researchers have explored various strategies to improve the performance of these tasks. This review focuses on Multi-Task Learning (MTL) approaches, which unify or cooperatively integrate detection and segmentation by leveraging shared representations. We first provide an overview of traditional and deep learning methods for each task individually, then examine how MTL has been adapted for medical image analysis, with a particular focus on lung CT studies. Key aspects such as network architectures and evaluation metrics are also discussed. The review highlights recent trends, identifies current challenges, and outlines promising directions toward more accurate, efficient, and clinically applicable CAD solutions. The review demonstrates that MTL frameworks significantly enhance efficiency and accuracy in lung nodule analysis by leveraging shared representations, while also identifying critical challenges such as task imbalance and computational demands that warrant further research for clinical adoption. Full article

Social media has become a platform for the rapid spread of persuasion techniques that can negatively affect individuals and society. Propaganda detection, a crucial task in natural language processing, aims to identify manipulative content in texts, particularly in news media, by assessing propagandistic intent. Although extensively studied in English, Arabic propaganda detection remains challenging because of the language’s morphological complexity and limited resources. Furthermore, most research has treated propaganda detection as an isolated task, neglecting the influence of sentiments and emotions. The current study addresses this gap by introducing the first multi-task learning (MTL) models for Arabic propaganda detection, integrating sentiment analysis and emotion detection as auxiliary tasks. Three MTL models are introduced: (1) MTL combining all tasks, (2) PSMTL (propaganda and sentiment), and (3) PEMTL (propaganda and emotion) based on transformer architectures. Additionally, seven task-weighting schemes are proposed and evaluated. Experiments demonstrated the superiority of our framework over state-of-the-art methods, achieving a Macro-F1 score of 0.778 and 79% accuracy. The results highlight the importance of integrating sentiment and emotion for enhanced propaganda detection; demonstrate that MTL improves model performance; and provide valuable insights into the interaction among sentiment, emotion, and propaganda. Full article

The multi-scale characteristics of remote sensing imagery have an inherent correspondence with the hierarchical structure of land cover classification systems, providing a theoretical foundation for multi-level land cover classification. However, most existing methods treat classification tasks at different semantic levels as independent processes, overlooking the semantic relationships among these levels, which leads to semantic inconsistencies and structural conflicts in classification results. We addressed this issue with a deep multi-task learning (MTL) framework, named MTL-SCH, which enables collaborative classification across multiple semantic levels. MTL-SCH employs a shared encoder combined with a feature cascade mechanism to boost information sharing and collaborative optimization between two levels. A hierarchical loss function is also embedded that explicitly models the semantic dependencies between levels, enhancing semantic consistency across levels. Two new evaluation metrics, namely Semantic Alignment Deviation (SAD) and Enhancing Semantic Alignment Deviation (ESAD), are also proposed to quantify the improvement of MTL-SCH in semantic consistency. In the experimental section, MTL-SCH is applied to different network models, including CNN, Transformer, and CNN-Transformer models. The results indicate that MTL-SCH improves classification accuracy in coarse- and fine-level segmentation tasks, significantly enhancing semantic consistency across levels and outperforming traditional flat segmentation methods. Full article

Urban morphology critically shapes environmental performance, yet few studies integrate multiple sustainability targets within a unified modeling framework for its design optimization. This study proposes a data-driven, multi-scale approach that combines parametric simulation, artificial neural network-based multi-task learning (MTL), SHAP interpretability, and NSGA-II optimization to assess and optimize urban form across 18 districts in Hong Kong. Four key sustainability targets—photovoltaic generation (PVG), accumulated urban heat island intensity (AUHII), indoor overheating degree (IOD), and carbon emission intensity (CEI)—were jointly predicted using an artificial neural network-based MTL model. The prediction results outperform single-task models, achieving R² values of 0.710 (PVG), 0.559 (AUHII), 0.819 (IOD), and 0.405 (CEI), respectively. SHAP analysis identifies building height, density, and orientation as the most important design factors, revealing trade-offs between solar access, thermal stress, and emissions. Urban form design strategies are informed by the multi-objective optimization, with the optimal solution featuring a building height of 72.11 m, building centroid distance of 109.92 m, and east-facing orientation (183°). The optimal configuration yields the highest PVG (55.26 kWh/m²), lowest CEI (359.76 kg/m²/y), and relatively acceptable AUHII (294.13 °C·y) and IOD (92.74 °C·h). This study offers a balanced path toward carbon reduction, thermal resilience, and renewable energy utilization in compact cities for either new town planning or existing district renovation. Full article

Agricultural factories utilize advanced facilities and technologies to cultivate crops in a controlled environment, enhancing operational yields and reducing reliance on natural resources. This is crucial for ensuring a stable supply of agricultural products year-round and plays a significant role in the transformation of agricultural modernization. Automated Guided Vehicles (AGVs) are commonly employed in agricultural factories due to their low ownership costs and high efficiency. However, small embedded devices on AGVs face significant challenges in managing multiple tasks while maintaining the required timeliness. Multi-task learning (MTL) is increasingly employed to enhance the efficiency and performance of detection models in joint detection tasks, such as lane-line detection, pedestrian detection, and obstacle detection. The YOLOP (You Only Look for Panoptic Driving Perception) model demonstrates strong performance in simultaneously addressing these tasks; detecting lane lines in changeable agricultural factory scenarios is yet a challenging task, limiting the subsequent accurate planning and control of AGVs. This paper proposes a feedback-based network for joint detection tasks (MTNet) that simultaneously detects pedestrians, automated guided vehicles (AGVs), and QR codes, while also performing lane-line segmentation. This approach addresses the challenge faced by using embedded devices mounted on AGVs, which are unable to run multiple models for different tasks in parallel due to limited computational resources. For lane-line detection tasks, we also propose an improved YOLOP lane-line detection algorithm based on feature shift aggregation. Homemade datasets were used for training and testing. Comparative experiments of our model with different models in the target-detection and lane-line detection tasks, respectively, show the progressiveness of our model. Surprisingly, we also obtained a significant improvement in the model’s processing speed. Furthermore, we conducted ablation experiments to assess the effectiveness of our improvements in lane-line detection, all of which outperformed the original detection model. Full article

Deep coalbed methane (CBM) is rich in resources and is an important replacement resource for tight gas in China. Accurate prediction of post-fracture production and dynamic change characteristics of fractured wells of partial CBM is of great significance in predicting the final recovery rate. In terms of predicting time-series production, the problem one encounters is low prediction accuracy and poor generalisation ability under limited sample conditions. In this paper, we propose a hybrid deep neural network (AT-GRU-MTL) production prediction model based on the combination of an attention mechanism gated recurrent neural network (GRU) and multi-task learning (MTL), where the AT-GRU is responsible for capturing the nonlinear pattern of the production change, while introducing an MTL method that includes a cross-stitch network (CSN) and a weighted loss using homoskedasticity uncertainty to automatically determine the degree of sharing between multiple tasks and the weighting ratio of the total loss function. The model is applied to several typical deep CBM fracturing wells in China, and the accuracy of gas production prediction reaches 90%, while the accuracy of water production prediction is 68%. The experimental results show that, for the blocks with a very large difference in the order of magnitude of the gas and water production, it is very easy for a certain small order of magnitude to be suppressed from learning during the two-way multi-task learning process, which leads to deterioration of its prediction effect; at the same time, the adaptability of the model is evaluated, and it is found that the model is more advantageous for the wells that have been produced for approximately one year. Meanwhile, the evaluation of the model adaptability shows that the model is more dominant in the prediction of wells with production of about one and a half years. Based on the two test wells with shorter (380 days) and longer (709 days) spans, the results indicate that the model may have insufficient sensitivity to the sudden change of the ratio of gas to water and the failure of the dynamic generalisation of the matrix shrinkage–desorption coupling, and the introduction of physical constraints (such as bottomhole flow pressure, etc.) or the division of the data into the production stages may be attempted to deal with the case subsequently. The research results in this paper provide a theoretical basis for dynamic production prediction and analysis in oil and gas field sites. Full article

Background/Objectives: Liver cirrhosis is a critical chronic condition with increasing global mortality and morbidity rates, emphasizing the necessity for early and accurate diagnosis. This study proposes a comprehensive deep-learning framework for the automatic diagnosis and staging of liver cirrhosis using T2-weighted MRI images. Methods: The methodology integrates stacked ensemble learning, multi-task learning (MTL), and transfer learning within an explainable artificial intelligence (XAI) context to improve diagnostic accuracy, reliability, and transparency. A hybrid model combining multiple pre-trained convolutional neural networks (VGG16, MobileNet, and DenseNet121) with XGBoost as a meta-classifier demonstrated robust performance in binary classification between healthy and cirrhotic cases. Results: The model achieved a mean accuracy of 96.92%, precision of 95.12%, recall of 98.93%, and F1-score of 96.98% across 10-fold cross-validation. For staging (mild, moderate, and severe), the MTL framework reached a main task accuracy of 96.71% and an average AUC of 99.81%, with a powerful performance in identifying severe cases. Grad-CAM visualizations reveal class-specific activation regions, enhancing the transparency and trust in the model’s decision-making. The proposed system was validated using the CirrMRI600+ dataset with a 10-fold cross-validation strategy, achieving high accuracy (AUC: 99.7%) and consistent results across folds. Conclusions: This research not only advances State-of-the-Art diagnostic methods but also addresses the black-box nature of deep learning in clinical applications. The framework offers potential as a decision-support system for radiologists, contributing to early detection, effective staging, personalized treatment planning, and better-informed treatment planning for liver cirrhosis. Full article

In resource-constrained mobile systems, efficiently handling incrementally added tasks under dynamically evolving requirements is a critical challenge. To address this, we propose aggregate pruning (AP), a framework that combines pruning with filter aggregation to optimize deep neural networks for continuous incremental multi-task learning (MTL). The approach reduces redundancy by dynamically pruning and aggregating similar filters across tasks, ensuring efficient use of computational resources while maintaining high task-specific performance. The aggregation strategy enables effective filter sharing across tasks, significantly reducing model complexity. Additionally, an adaptive mechanism is incorporated into AP to adjust filter sharing based on task similarity, further enhancing efficiency. Experiments on different backbone networks, including LeNet, VGG, ResNet, and so on, show that AP achieves substantial parameter reduction and computational savings with minimal accuracy loss, outperforming existing pruning methods and even surpassing non-pruning MTL techniques. The architecture-agnostic design of AP also enables potential extensions to complex architectures like graph neural networks (GNNs), offering a promising solution for incremental multi-task GNNs. Full article

Forest fires cause devastating damage to the natural environment, making prompt and precise detection of smoke and fires in forests crucial. When processing forest fire images based on ground and aerial perspectives, current object detection methods still encounter issues, such as inadequate detection precision, elevated false detection and omission rates, as well as difficulties in detecting small targets in complex forest environments. Multi-task learning represents a framework in machine learning where a model can handle detection and segmentation tasks concurrently, enhancing the accuracy and generalization capacity for object detection. Therefore, this study proposes a Multi-Task Learning-based Forest Smoke and Fire Detection model (MTL-FSFDet). Firstly, an improved Bilateral Filtering-Multi-Scale Retinex (BF-MSR) method for enhancing images was proposed, to lessen the effect of lighting on smoke images and improve the quality of the dataset. Secondly, a Hybrid Feature Extraction module, which integrates local and global information, was introduced to distinguish between targets and backgrounds, addressing smoke and fire detection in complex backgrounds. Furthermore, Dysample, a method utilizing point sampling, was designed to capture richer feature information when dealing with small targets. In addition, a feature fusion approach based on Context Gate Aggregation (CGA) was proposed to weightedly fuse low-level and high-level features, boosting the precision in detecting small targets. Finally, multi-task learning improves the capability to detect small targets and tackle complex scenarios by sharing the feature extraction module and leveraging refined supervision of the segmentation task. The findings from the experiments show that, in comparison to the baseline model, MTL-FSFDet improved the mAP@0.5 by 5.3%. Full article

Laser weeding is an innovative, environmentally friendly method for intra-row weed control. However, its effectiveness depends on accurate weed identification and an efficient control system. This study developed an intra-row laser weeding system for lettuce, combining deep learning and laser technology. The system consisted of three modules: perception, decision, and execution. It used an MV-UB130GM industrial camera to capture images, which are transmitted to a computer for processing. A target detection algorithm located weeds by calculating the central coordinates of anchor frames. The multi-task learning (MTL) decision system then planned the weeding path, generated instructions, and controlled the laser for weeding tasks. The YOLOv8 model, enhanced with an attention mechanism, formed the foundation of target detection. To compress the model, a class knowledge distillation method based on transfer learning was applied, resulting in a lightweight YOLOv8s-CBAM model with a mAP@0.5 of 98.9% and a size of just 6.2 MB. A simulation prototype of the laser weeding system was built, and initial experiments demonstrated that a 450 nm blue semiconductor laser effectively kills weeds in 1 s with 30 W output. Experimental results showed that the system detected and eliminated 100% of weeds in low-density scenes and achieved an 88.9% detection rate in high-density areas. The real-time detection speed reached 21.27 FPS, and the overall weeding success rate was 76.9%. This study provides valuable insights for the development of intra-row weed control systems based on laser technology, contributing to the advancement of precision agriculture. Full article

Traditional volatile organic compounds (VOCs) detection models separate component identification and concentration prediction, leading to low feature utilization and limited learning in small-sample scenarios. Here, we realize a Residual Fusion Network based on multi-task learning (MTL-RCANet) to implement component identification and concentration prediction of VOCs. The model integrates channel attention mechanisms and cross-fusion modules to enhance feature extraction capabilities and task synergy. To further balance the tasks, a dynamic weighted loss function is incorporated to adjust weights dynamically according to the training progress of each task, thereby enhancing the overall performance of the model. The proposed network achieves an accuracy of 94.86% and an R² score of 0.95. Comparative experiments reveal that using only 35% of the total data length as input data yields excellent identification performance. Moreover, multi-task learning effectively integrates feature information across tasks, significantly improving model efficiency compared to single-task learning. Full article

This paper proposes a novel Ordinal Regression Multi-Task Learning (OR-MTL) framework to address challenges in multi-task diagnosis of PD in Gas-Insulated Switchgear (GIS). GIS PD diagnosis typically involves tasks such as discharge-type identification and severity assessment, which is essentially an ordinal regression problem facing challenges such as high label noise and inconsistent ranking of prediction outcomes. To address these challenges, the OR-MTL framework introduces two key innovations: a dynamic task-weighting strategy based on excess risk estimation, which mitigates the negative impact of label noise on multi-task learning weight allocation, and an ordinal regression loss function based on conditional probability, which ensures consistent prediction ranking through conditional probability chains. Experiments on GIS PD datasets demonstrate that the excess risk-based task-weighting strategy exhibits superior robustness compared to traditional methods in high-noise environments, while the proposed ranking consistency loss function significantly improves the accuracy of severity assessment and reduces errors. Ablation studies further validate the effectiveness of the complete OR-MTL framework. This research not only provides an efficient solution for GIS PD diagnosis but also offers new insights and methodologies for multi-task learning involving ordinal regression tasks. Full article

Aspect-based sentiment analysis (ABSA) through joint task learning aims to simultaneously identify aspect terms and predict their sentiment polarities. However, existing methods face two major challenges: (1) Most existing studies focus on the sentiment polarity classification task, ignoring the critical role of aspect term extraction, leading to insufficient performance in capturing aspect-related information; (2) existing methods typically model the two tasks independently, failing to effectively share underlying features and semantic information, which weakens the synergy between the tasks and limits the overall performance of the model. In order to resolve these issues, this research suggests a unified framework model through joint task learning, named MTL-GCN, to simultaneously perform aspect term extraction and sentiment polarity classification. The proposed model utilizes dependency trees combined with self-attention mechanisms to generate new weight matrices, emphasizing the locational information of aspect terms, and optimizes the graph convolutional network (GCN) to extract aspect terms more efficiently. Furthermore, the model employs the multi-head attention (MHA) mechanism to process input data and uses its output as the input to the GCN. Next, GCN models the graph structure of the input data, capturing the relationships between nodes and global structural information, fully integrating global contextual semantic information, and generating deep-level contextual feature representations. Finally, the extracted aspect-related features are fused with global features and applied to the sentiment classification task. The proposed unified framework achieves state-of-the-art performance, as evidenced by experimental results on four benchmark datasets. MTL-GCN outperforms baseline models in terms of F1_ATE, accuracy, and F1_SC metrics, as demonstrated by experimental results on four benchmark datasets. Additionally, comparative and ablation studies further validate the rationale and effectiveness of the model design. Full article