Multitask Deep Learning for Human Activity, Speed, and Body Weight Estimation Using Commercial Smart Insoles

A unified modeling framework for lane change intention recognition and vehicle status prediction

ADMET property prediction via multi-task graph learning under adaptive auxiliary task selection

BackgroundMandibular structures offer resilient features for forensic identification where partial remains are available in postmortem condition. Deep learning applied to cephalometric radiographs offers an opportunity to predict demographic attributes, such as age and sex, which are critical in forensic and clinical contexts.ObjectiveThis study aimed to develop and evaluate a multitask deep learning framework for age estimation and sex prediction from cropped mandibular regions of cephalometric radiographs, comparing multiple convolutional neural network backbones and preprocessing scenarios to address class imbalance.MethodsA total of 340 anonymized cephalometric radiographs from Indonesian individuals aged 8 to 40 years were collected and manually cropped into 2 mandibular regions of interest: mandibular length and mandibular angle, producing 680 validated samples. Images were resized to 224×224 pixels and processed under 4 preprocessing scenarios: original, Synthetic Minority Oversampling Technique, StandardScaler, and Synthetic Minority Oversampling Technique+StandardScaler. Six pretrained convolutional neural network backbones (MobileNetV2, ResNet50V2, InceptionV3, InceptionResNetV2, VGG16, and VGG19) were fine-tuned within a multitask framework. Performance was evaluated using mean absolute error and mean absolute percentage error for age estimation and accuracy and F1-score for sex prediction.ResultsVGG16 achieved the best performance for age estimation, with the lowest mean absolute error of 3.19 years and mean absolute percentage error of 13.19% in the original dataset. For sex prediction, VGG16 achieved the highest accuracy (86%) and balanced F1-scores (female: 92%; male: 63%) under the StandardScaler condition, followed by VGG19 (accuracy=82%).ConclusionsCombining mandibular cropping with deep learning and balanced preprocessing scenarios enhances demographic prediction in cephalometric radiographs. The findings emphasize the potential use of artificial intelligence–assisted forensic odontology to support disaster victim identification when partial remains are available.

In recent years, multitask learning has turned out to be of great success in various applications. Though single task model training has promised great results throughout these years, it ignores valuable information which might help in estimating better learning parameters. By virtue of learning-related tasks, multitask learning has been able to generalize the models even better. In this paper, we try to enhance the feature mapping of multitask deep learning models by sharing features among related tasks and inductive transfer learning. We have explored the learning of task relationship among various tasks for acquiring more benefits from multitask learning. The proposed enhanced model is compared with two state-of-the-art multitask deep learning models, namely Hyperface and FaceNet. The results show better performance of the proposed model in predicting age, gender and ethnicity on the UTK face dataset.KeywordsNeural networksMultitask deep learningDeep learningRecurrent neural networksConvolution neural networks

Retinal diseases represent a leading cause of visual impairment and blindness worldwide, with early and accurate diagnosis being crucial for preventing irreversible vision loss. Although deep learning techniques have achieved significant advances in fundus image analysis, existing methods predominantly focus on single tasks, treating vessel segmentation and disease diagnosis as independent problems without fully leveraging their intrinsic relationships. Furthermore, the lack of transparency in deep model predictions limits clinical adoption; while full interpretability remains an open challenge, post-hoc techniques such as Grad-CAM can provide partial transparency by highlighting influential image regions. This study presents V-MNet, a vessel-guided multi-task deep learning framework that simultaneously achieves retinal vessel segmentation and multi-disease classification, and provides visual transparency through Grad-CAM-based class activation mapping to support clinical decision-making. The framework comprises three core modules: a shared encoder extracts multi-scale feature representations; a segmentation decoder employs a U-Net-style architecture to generate vessel masks; and a classification decoder incorporates an innovative vessel-guided mechanism that explicitly transfers structural priors from the segmentation branch to the classification task, enabling the model to precisely localize pathological regions. Concurrently, an integrated Grad-CAM module generates post-hoc class activation maps for each disease category, highlighting spatially relevant lesion regions for clinician review. Comprehensive experiments were conducted on four public datasets-RFMiD, ODIR-5K, DRIVE, and EyePACS-light-v2. Experiments demonstrate that V-MNet achieves a Dice coefficient of 0.831 and AUC of 0.985 for vessel segmentation tasks, and an average AUC of 0.978 with F1-score of 0.935 for multi-disease classification tasks, significantly outperforming single-task baseline models and existing state-of-the-art methods. Ablation studies systematically quantify the performance contributions of multi-task learning and the vessel-guided mechanism, confirming the effectiveness of the framework's core innovations. V-MNet demonstrates broad application potential as a computer-aided diagnostic tool by jointly leveraging vascular structure and disease pathology for superior performance and visual transparency. The vessel-guided multi-task design effectively exploits the intrinsic relationship between vessel segmentation and disease classification, while the integrated Grad-CAM module addresses the lack of model transparency, facilitating clinical adoption and supporting clinical decision-making.

Accurately predicting patient clinical outcomes is a complex task that requires integrating diverse factors, including individual characteristics, treatment histories, and environmental influences. This challenge is further exacerbated by missing data and inconsistent data quality, which often hinder the effectiveness of traditional single-task learning (STL) models. Multi-Task Learning (MTL) has emerged as a promising paradigm to address these limitations by jointly modeling related prediction tasks and leveraging shared information. In this study, we proposed MTLNFM, a multi-task learning framework built upon Neural Factorization Machines, to jointly predict patient clinical outcomes. We designed a preprocessing strategy in the framework that transforms missing values into informative representations, mitigating the impact of sparsity and noise in clinical data. We leveraged the shared representation layers, composed of a factorization machine and dense neural layers that can capture high-order feature interactions and facilitate knowledge sharing across tasks for the prediction. We conducted extensive comparative experiments, demonstrating that MTLNFM outperforms STL baselines across all three tasks, achieving AUROC scores of 0.7514, 0.6722, and 0.7754, respectively. A detailed case analysis further revealed that MTLNFM effectively integrates both task-specific and shared representations, resulting in more robust and realistic predictions aligned with actual patient outcome distributions. Overall, our findings suggest that MTLNFM is a promising and practical solution for clinical outcome prediction, particularly in settings with limited or incomplete data, and can support more informed clinical decision-making and resource planning.

Accurately predicting patient clinical outcomes is a complex task that requires integrating diverse factors, including individual characteristics, treatment histories, and environmental influences. This challenge is further exacerbated by missing data and inconsistent data quality, which often hinder the effectiveness of traditional single-task learning (STL) models. Multi-Task Learning (MTL) has emerged as a promising paradigm to address these limitations by jointly modeling related prediction tasks and leveraging shared information. In this study, we proposed MTLNFM, a multi-task learning framework built upon Neural Factorization Machines, to jointly predict patient clinical outcomes on a cohort of 2001 ICU patients. We designed a preprocessing strategy in the framework that transforms missing values into informative representations, mitigating the impact of sparsity and noise in clinical data. We leveraged the shared representation layers, composed of a factorization machine and dense neural layers that can capture high-order feature interactions and facilitate knowledge sharing across tasks for the prediction. We conducted extensive comparative experiments, demonstrating that MTLNFM outperforms STL baselines across all three tasks (i.e., frailty status, hospital length of stay and mortality prediction), achieving AUROC scores of 0.7514, 0.6722, and 0.7754, respectively. A detailed case analysis further revealed that MTLNFM effectively integrates both task-specific and shared representations, resulting in more robust and realistic predictions aligned with actual patient outcome distributions. Overall, our findings suggest that MTLNFM is a promising and practical solution for clinical outcome prediction, particularly in settings with limited or incomplete data, and can support more informed clinical decision-making and resource planning.

This article proposes a novel multitask learning framework that integrates contrastive learning and natural language generation (NLG) to enhance medical image classification and report generation. The goal is to improve disease classification accuracy and interpretability in medical diagnostics. The model architecture consists of a Vision Transformer (ViT) as a visual encoder, a transformer-based text encoder, and a multimodal decoder. The visual encoder processes medical images, while the text encoder handles disease-related text prompts. These components are trained jointly using image-text contrastive loss and language generation loss. Evaluations on the MIMICCXR and Chexpert datasets show that the model with NLG (Plain + NLG) outperforms the baseline contrastive learning model (Plain) in disease classification. For example, in the MIMICCXR dataset, the accuracy for Atelectasis increased from 17.44%(Plain) to 41.5% (Plain + NLG), and for Cardiomegaly, it improved from 19.25% to 47.4%. In Chexpert, the accuracy for Atelectasis increased from 12.5% to 58.5%, and for Pleural Effusion, from 61.10% to 64.0%. The model also demonstrated improvements in F1 scores, particularly for complex diseases like Cardiomegaly and Consolidation. The proposed multitask framework effectively combines contrastive learning with NLG, leading to improved disease classification and medical report generation. This approach has potential clinical applications by enhancing AI’s interpretability and accuracy in medical decision-making.

High-resolution LAI data can provide more detailed information for remote sensing applications. However, for deep learning-based LAI retrieval methods, a training dataset composed of sensor data with a moderate or low spatial resolution cannot be directly applied to derive LAI from high-spatial-resolution sensor data due to distribution discrepancies between different sensor data. Following in this insight, we proposed a multi-task adversarial transfer learning framework, named DANN_MT. This framework leverages an adaptive adversarial training strategy to extract domain-invariant features between MODIS and Landsat surface reflectance data, enabling the retrieval of high-resolution LAI. To address the incomplete consistency between tasks of generating corresponding moderate-resolution LAI and high-resolution LAI, the DANN_MT model is designed with multi-task learning. Comparison results suggest that the retrieved high-resolution LAI exhibit reasonable spatial distribution and seasonality. Direct validation demonstrates that the retrieved high-resolution LAI (RMSE for the GBOV sites: 0.86, RMSE for the IMAGINES sites: 0.82) have a higher accuracy than the SNAP LAI (RMSE for the GBOV sites: 0.93, RMSE for the IMAGINES sites: 0.95). These conclusions reveal that the knowledge learned from the moderate-spatial-resolution dataset is successfully transferred to produce the high-spatial-resolution LAI from Landsat surface reflectance using the proposed DANN_MT model.

In this paper, we provide a series of multi-tasking benchmarks for simultaneously detecting spoofing at the segmental and utterance levels in the PartialSpoof database. First, we propose the SELCNN network, which inserts squeeze-and-excitation (SE) blocks into a light convolutional neural network (LCNN) to enhance the capacity of hidden feature selection. Then, we implement multi-task learning (MTL) frameworks with SELCNN followed by bidirectional long short-term memory (Bi-LSTM) as the basic model. We discuss MTL in PartialSpoof in terms of architecture (uni-branch/multi-branch) and training strategies (from-scratch/warm-up) step-by-step. Experiments show that the multi-task model performs better than single-task models. Also, in MTL, binary-branch architecture more adequately utilizes information from two levels than a uni-branch model. For the binary-branch architecture, fine-tuning a warm-up model works better than training from scratch. Models can handle both segment-level and utterance-level predictions simultaneously overall under binary-branch multi-task architecture. Furthermore, the multi-task model trained by fine-tuning a segmental warm-up model performs relatively better at both levels except on the evaluation set for segmental detection. Segmental detection should be explored further.

Objective. Deep learning (DL)-based automated contouring and treatment planning has been proven to improve the efficiency and accuracy of radiotherapy. However, conventional radiotherapy treatment planning process has the automated contouring and treatment planning as separate tasks. Moreover in DL, the contouring and dose prediction tasks for automated treatment planning are done independently.Approach. In this study, we applied the multi-task learning (MTL) approach in order to seamlessly integrate automated contouring and voxel-based dose prediction tasks, as MTL can leverage common information between the two tasks and be able to increase the efficiency of the automated tasks. We developed our MTL framework using the two datasets: in-house prostate cancer dataset and the publicly available head and neck cancer dataset, OpenKBP.Main results. Compared to the sequential DL contouring and treatment planning tasks, our proposed method using MTL improved the mean absolute difference of dose volume histogram metrics of prostate and head and neck sites by 19.82% and 16.33%, respectively. Our MTL model for automated contouring and dose prediction tasks demonstrated enhanced dose prediction performance while maintaining or sometimes even improving the contouring accuracy. Compared to the baseline automated contouring model with the Dice score coefficients of 0.818 for prostate and 0.674 for head and neck datasets, our MTL approach achieved average scores of 0.824 and 0.716 for these datasets, respectively.Significance. Our study highlights the potential of the proposed automated contouring and planning using MTL to support the development of efficient and accurate automated treatment planning for radiotherapy.

MotivationMachine learning models for predicting cell-type-specific transcription factor (TF) binding sites have become increasingly more accurate thanks to the increased availability of next-generation sequencing data and more standardized model evaluation criteria. However, knowledge transfer from data-rich to data-limited TFs and cell types remains crucial for improving TF binding prediction models because available binding labels are highly skewed towards a small collection of TFs and cell types. Transfer prediction of TF binding sites can potentially benefit from a multitask learning approach; however, existing methods typically use shallow single-task models to generate low-resolution predictions. Here, we propose NetTIME, a multitask learning framework for predicting cell-type-specific TF binding sites with base-pair resolution.ResultsWe show that the multitask learning strategy for TF binding prediction is more efficient than the single-task approach due to the increased data availability. NetTIME trains high-dimensional embedding vectors to distinguish TF and cell-type identities. We show that this approach is critical for the success of the multitask learning strategy and allows our model to make accurate transfer predictions within and beyond the training panels of TFs and cell types. We additionally train a linear-chain conditional random field (CRF) to classify binding predictions and show that this CRF eliminates the need for setting a probability threshold and reduces classification noise. We compare our method’s predictive performance with two state-of-the-art methods, Catchitt and Leopard, and show that our method outperforms previous methods under both supervised and transfer learning settings.Availability and implementationNetTIME is freely available at https://github.com/ryi06/NetTIME and the code is also archived at https://doi.org/10.5281/zenodo.6994897.Supplementary informationSupplementary data are available at Bioinformatics online.

The brown rice rate (BRR), milled rice rate (MRR), and head rice rate (HRR) are important indicators of rice milling quality. The simultaneous detection of these three metrics holds significant economic value for rice milling quality assessments. In this study, hyperspectral imaging was employed to estimate the rice milling quality attributes of two rice varieties (Xiushui121 and Zhehujing26). Partial Least Squares Regression (PLSR), Support Vector Regression (SVR), Convolutional Neural Networks (CNNs), and Backpropagation Neural Networks (BPNNs) were used to establish both single-task and multi-task models for the prediction of milling quality attributes. Most multi-task models demonstrated a higher prediction accuracy compared with their corresponding single-task models. Among single-task models, BPNNs outperformed the others in predicting BRR and HRR, with correlation coefficients (r) up to 0.9. SVR excelled in forecasting the MRR. In multi-task learning, BPNNs exhibited relatively better performance, with r values exceeding 0.81 for all three indicators. SHapley Additive exPlanations (SHAP) analysis was used to explore the relationship between wavelength and rice milling quality attributes. This study confirmed that this nondestructive detection method for rice milling quality using hyperspectral imaging combined with machine learning and deep learning algorithms could effectively assess rice milling quality, thus contributing to breeding and growth management in the industry.

Multi-task learning aims to learn multiple tasks jointly by exploiting their relatedness to improve the generalization performance for each task. Traditionally, to perform multi-task learning, one needs to centralize data from all the tasks to a single machine. However, in many real-world applications, data of different tasks may be geo-distributed over different local machines. Due to heavy communication caused by transmitting the data and the issue of data privacy and security, it is impossible to send data of different task to a master machine to perform multi-task learning. Therefore, in this paper, we propose a distributed multi-task learning framework that simultaneously learns predictive models for each task as well as task relationships between tasks alternatingly in the parameter server paradigm. In our framework, we first offer a general dual form for a family of regularized multi-task relationship learning methods. Subsequently, we propose a communication-efficient primal-dual distributed optimization algorithm to solve the dual problem by carefully designing local subproblems to make the dual problem decomposable. Moreover, we provide a theoretical convergence analysis for the proposed algorithm, which is specific for distributed multi-task relationship learning. We conduct extensive experiments on both synthetic and real-world datasets to evaluate our proposed framework in terms of effectiveness and convergence.

Due to the recent vast availability of transportation traffic data, major research efforts have been devoted to traffic prediction, which is useful in many applications such as urban planning, traffic management and navigations systems. Current prediction methods that independently train a model per traffic sensor cannot accurately predict traffic in every situation (e.g., rush hours, constructions and accidents) because there may not exist sufficient training samples per sensor for all situations. To address this shortcoming, our core idea is to explore the commonalities of prediction tasks across multiple sensors who behave similarly in a specific traffic situation. Instead of building a model independently per sensor, we propose a Multi-Task Learning (MTL) framework that aims to first automatically identify the traffic situations and then simultaneously build one forecasting model for similar-behaving sensors per traffic situation. The key innovation here is that instead of the straightforward application of MTL where each "task" corresponds to a sensor, we relate each MTL's "task" to a traffic situation. Specifically, we first identify these traffic situations by running clustering algorithms on all sensors' data. Subsequently, to enforce the commonalities under each identified situation, we use the group Lasso regularization in MTL to select a common set of features for the prediction tasks, and we adapt efficient FISTA algorithm with guaranteed convergence rate. We evaluated our methods with a large volume of real-world traffic sensor data; our results show that by incorporating traffic situations, our proposed MTL framework performs consistently better than naively applying MTL per sensor. Moreover, our holistic approach, under different traffic situations, outperforms all the best traffic prediction approaches for a given situation by up to 18% and 30% in short and long term predictions, respectively.