Multi-task Learning Framework Research Articles

Temporal-Frequency Attention Focusing for Time Series Extrinsic Regression via Auxiliary Task.

Time series extrinsic regression (TSER) aims at predicting numeric values based on the knowledge of the entire time series. The key to solving the TSER problem is to extract and use the most representative and contributed information from raw time series. To build a regression model that focuses on those information suitable for the extrinsic regression characteristic, there are two major issues to be addressed. That is, how to quantify the contributions of those information extracted from raw time series and then how to focus the attention of the regression model on those critical information to improve the model's regression performance. In this article, a multitask learning framework called temporal-frequency auxiliary task (TFAT) is designed to solve the mentioned problems. To explore the integral information from the time and frequency domains, we decompose the raw time series into multiscale subseries in various frequencies via a deep wavelet decomposition network. To address the first problem, the transformer encoder with the multihead self-attention mechanism is integrated in our TFAT framework to quantify the contribution of temporal-frequency information. To address the second problem, an auxiliary task in a manner of self-supervised learning is proposed to reconstruct the critical temporal-frequency features so as to focusing the regression model's attention on those essential information for facilitating TSER performance. We estimated three kinds of attention distribution on those temporal-frequency features to perform auxiliary task. To evaluate the performances of our method under various application scenarios, the experiments are carried out on the 12 datasets of the TSER problem. Also, ablation studies are used to examine the effectiveness of our method.

Multitask learning to predict successful weaning in critically ill ventilated patients: A retrospective analysis of the MIMIC-IV database.

Weaning is an essential issue in critical care. This study explores the efficacy of multitask learning models in predicting successful weaning in critically ill ventilated patients using the Medical Information Mart for Intensive Care (MIMIC) IV database. We employed a multitask learning framework with a shared bottom network to facilitate common knowledge extraction across all tasks. We used the Shapley additive explanations (SHAP) plot and partial dependence plot (PDP) for model explainability. Furthermore, we conducted an error analysis to assess the strength and limitation of the model. Area under receiver operating characteristic curve (AUROC), calibration plot and decision curve analysis were used to determine the performance of the model. A total of 7758 critically ill patients were included in the analyses, and 78.5% of them were successfully weaned. Multitask learning combined with spontaneous breath trial achieved a higher performance to predict successful weaning compared with multitask learning combined with shock and mortality (area under receiver operating characteristic curve, AUROC, 0.820 ± 0.002 vs 0.817 ± 0.001, p < 0.001). We assessed the performance of the model using calibration and decision curve analyses and further interpreted the model through SHAP and PDP plots. The error analysis identified a relatively high error rate among those with low disease severities, including low mean airway pressure and high enteral feeding. We demonstrated that multitask machine learning increased predictive accuracy for successful weaning through combining tasks with a high inter-task relationship. The model explainability and error analysis should enhance trust in the model.

Broad Multitask Learning System With Group Sparse Regularization.

The broad learning system (BLS) featuring lightweight, incremental extension, and strong generalization capabilities has been successful in its applications. Despite these advantages, BLS struggles in multitask learning (MTL) scenarios with its limited ability to simultaneously unravel multiple complex tasks where existing BLS models cannot adequately capture and leverage essential information across tasks, decreasing their effectiveness and efficacy in MTL scenarios. To address these limitations, we proposed an innovative MTL framework explicitly designed for BLS, named group sparse regularization for broad multitask learning system using related task-wise (BMtLS-RG). This framework combines a task-related BLS learning mechanism with a group sparse optimization strategy, significantly boosting BLS's ability to generalize in MTL environments. The task-related learning component harnesses task correlations to enable shared learning and optimize parameters efficiently. Meanwhile, the group sparse optimization approach helps minimize the effects of irrelevant or noisy data, thus enhancing the robustness and stability of BLS in navigating complex learning scenarios. To address the varied requirements of MTL challenges, we presented two additional variants of BMtLS-RG: BMtLS-RG with sharing parameters of feature mapped nodes (BMtLS-RGf), which integrates a shared feature mapping layer, and BMtLS-RGf and enhanced nodes (BMtLS-RGfe), which further includes an enhanced node layer atop the shared feature mapping structure. These adaptations provide customized solutions tailored to the diverse landscape of MTL problems. We compared BMtLS-RG with state-of-the-art (SOTA) MTL and BLS algorithms through comprehensive experimental evaluation across multiple practical MTL and UCI datasets. BMtLS-RG outperformed SOTA methods in 97.81% of classification tasks and achieved optimal performance in 96.00% of regression tasks, demonstrating its superior accuracy and robustness. Furthermore, BMtLS-RG exhibited satisfactory training efficiency, outperforming existing MTL algorithms by 8.04-42.85 times.

KPDet: Keypoint-based 3D object detection with Parametric Radius Learning

3D object detection requires accurate recognition of object category, size, rotation angle, and location in 3D space. Currently, many 3D object detection methods rely on the compact Bird’s Eye View (BEV) or point-wise representations to generate proposals. However, these proposal generation paradigms neglect the spatial distribution of objects, which causes difficulty in estimating the centers of objects. In this paper, we propose a keypoint-based 3D object detector, KPDet, which employs the keypoints in the neighborhood of object centers as the representation for proposal generation. The proposed KPDet first uses voxel-keypoint mapping to aggregate informative features on the subsampled keypoints from voxel-wise features, then calibrates the misalignment between the keypoints and object centers through the Object-aware Feature Pooling (OFP) module. These aligned keypoints with their corresponding features are applied to generate proposals. Since the keypoints are essential components, we further present the Structural Point Abstraction (SPA) module, which captures the anisotropic features of keypoints via constructed structural points to enhance the geometric information. In addition, based on the well-studied multi-task learning framework, we also propose a Parametric Radius Learning (PRL) strategy to adjust the sampling radius of the point-based feature aggregation process during the training procedure. Extensive experiments on the KITI and Waymo Open Dataset show that KPDet could achieve promising results compared with previous works.

Automatic detection, segmentation, and classification of primary bone tumors and bone infections using an ensemble multi-task deep learning framework on multi-parametric MRIs: a multi-center study.

To develop an ensemble multi-task deep learning (DL) framework for automatic and simultaneous detection, segmentation, and classification of primary bone tumors (PBTs) and bone infections based on multi-parametric MRI from multi-center. This retrospective study divided 749 patients with PBTs or bone infections from two hospitals into a training set (N = 557), an internal validation set (N = 139), and an external validation set (N = 53). The ensemble framework was constructed using T1-weighted image (T1WI), T2-weighted image (T2WI), and clinical characteristics for binary (PBTs/bone infections) and three-category (benign/intermediate/malignant PBTs) classification. The detection and segmentation performances were evaluated using Intersection over Union (IoU) and Dice score. The classification performance was evaluated using the receiver operating characteristic (ROC) curve and compared with radiologist interpretations. On the external validation set, the single T1WI-based and T2WI-based multi-task models obtained IoUs of 0.71 ± 0.25/0.65 ± 0.30 for detection and Dice scores of 0.75 ± 0.26/0.70 ± 0.33 for segmentation. The framework achieved AUCs of 0.959 (95%CI, 0.955-1.000)/0.900 (95%CI, 0.773-0.100) and accuracies of 90.6% (95%CI, 79.7-95.9%)/78.3% (95%CI, 58.1-90.3%) for the binary/three-category classification. Meanwhile, for the three-category classification, the performance of the framework was superior to that of three junior radiologists (accuracy: 65.2%, 69.6%, and 69.6%, respectively) and comparable to that of two senior radiologists (accuracy: 78.3% and 78.3%). The MRI-based ensemble multi-task framework shows promising performance in automatically and simultaneously detecting, segmenting, and classifying PBTs and bone infections, which was preferable to junior radiologists. Compared with junior radiologists, the ensemble multi-task deep learning framework effectively improves differential diagnosis for patients with primary bone tumors or bone infections. This finding may help physicians make treatment decisions and enable timely treatment of patients. • The ensemble framework fusing multi-parametric MRI and clinical characteristics effectively improves the classification ability of single-modality models. • The ensemble multi-task deep learning framework performed well in detecting, segmenting, and classifying primary bone tumors and bone infections. • The ensemble framework achieves an optimal classification performance superior to junior radiologists' interpretations, assisting the clinical differential diagnosis of primary bone tumors and bone infections.

Co-segmentation assisted cross-modality person re-identification

We present a deep learning-based method for Visible-Infrared person Re-Identification (VI-ReID). The major contribution lies in the incorporation of co-segmentation into a multi-task learning framework for VI-ReID, where the co-segmentation concept aids in making the distributions of RGB images and IR images the same for the same identity but diverse for different identities. Accordingly, a novel multi-task learning based model, i.e., co-segmentation assisted VI-ReID (CSVI), is proposed in this paper. Specifically, the co-segmentation network first takes as the inputs the modality-shared features extracted from a set of RGB and IR images by using the VI-ReID model. Then, it exploits their semantic similarities for predicting the person masks of the common identities within the input RGB and IR images by using a cross-modality center based weight generation module and a segmentation decoder. Doing so enables the VI-ReID model to extract more additional modality-shared shape features for boosting performance. Meanwhile, the co-segmentation network implicitly establishes the interactions among the set of RGB and IR images, thus further bridging the large modality discrepancies. Our model’s effectiveness and superiority are verified through experimental comparisons with state-of-the-art algorithms on several benchmark datasets.

A Deep Multi-Tasking Approach Leveraging on Cited-Citing Paper Relationship For Citation Intent Classification

Citations are crucial artifacts to provide additional information to the reader to comprehend the research under concern. There are different roles that citations play in scientific discourse. Correctly identifying the intent of the citations finds applications ranging from predicting scholarly impact, finding idea propagation, to text summarization. With the rapid growth in scientific literature, the need for automated methods to classify citations is now growing intense. However, we can only fully understand the intent of a citation if we look at the citation context in the citing paper and also the primary purpose of the cited article. In this work, we propose a neural multi-task learning framework that harnesses the structural information of the research papers and the cited paper’s information for the effective classification of citation intents. We analyze the impact of three auxiliary tasks on the performance of our approach for citation classification. Our experiments on three benchmark citation classification datasets show that incorporating cited paper information (title) shows that our deep neural model achieves a new state-of-the-art on the ACL-ARC dataset with an absolute increase of 5.3% in the F1 score over the previous best model. We also achieve comparable performance with respect to the best-performing systems in the SDP 2021 3C Shared task on Citation Context Classification. We make our codes available at https://github.com/Tirthankar-Ghosal/citationclassification-SCIM

Heterogeneous graph neural networks for fraud detection and explanation in supply chain finance

It is a critical mission for financial service providers to discover fraudulent borrowers in a supply chain. The borrowers’ transactions in an ongoing business are inspected to support the providers’ decision on whether to lend the money. Considering multiple participants in a supply chain business, the borrowers may use sophisticated tricks to cheat, making fraud detection challenging. In this work, we propose a multitask learning framework, MultiFraud, for complex fraud detection with reasonable explanation. The heterogeneous information from multi-view around the entities is leveraged in the detection framework based on heterogeneous graph neural networks. MultiFraud enables multiple domains to share embeddings and enhance modeling capabilities for fraud detection. The developed explainer provides comprehensive explanations across multiple graphs. Experimental results on five datasets demonstrate the framework’s effectiveness in fraud detection and explanation across domains.

A Multi-Task Learning Framework of Stable Q-Compensated Reverse Time Migration Based on Fractional Viscoacoustic Wave Equation

Q-compensated reverse time migration (Q-RTM) is a crucial technique in seismic imaging. However, stability is a prominent concern due to the exponential increase in high-frequency ambient noise during seismic wavefield propagation. The two primary strategies for mitigating instability in Q-RTM are regularization and low-pass filtering. Q-RTM instability can be addressed through regularization. However, determining the appropriate regularization parameters is often an experimental process, leading to challenges in accurately recovering the wavefield. Another approach to control instability is low-pass filtering. Nevertheless, selecting the cutoff frequency for different Q values is a complex task. In situations with low signal-to-noise ratios (SNRs) in seismic data, using low-pass filtering can make Q-RTM highly unstable. The need for a small cutoff frequency for stability can result in a significant loss of high-frequency signals. In this study, we propose a multi-task learning (MTL) framework that leverages data-driven concepts to address the issue of amplitude attenuation in seismic records, particularly when dealing with instability during the Q-RTM (reverse time migration with Q-attenuation) process. Our innovative framework is executed using a convolutional neural network. This network has the capability to both predict and compensate for the missing high-frequency components caused by Q-effects while simultaneously reconstructing the low-frequency information present in seismograms. This approach helps mitigate overwhelming instability phenomena and enhances the overall generalization capacity of the model. Numerical examples demonstrate that our Q-RTM results closely align with the reference images, indicating the effectiveness of our proposed MTL frequency-extension method. This method effectively compensates for the attenuation of high-frequency signals and mitigates the instability issues associated with the traditional Q-RTM process.

Toward explainable AI (XAI) for mental health detection based on language behavior.

Advances in artificial intelligence (AI) in general and Natural Language Processing (NLP) in particular are paving the new way forward for the automated detection and prediction of mental health disorders among the population. Recent research in this area has prioritized predictive accuracy over model interpretability by relying on deep learning methods. However, prioritizing predictive accuracy over model interpretability can result in a lack of transparency in the decision-making process, which is critical in sensitive applications such as healthcare. There is thus a growing need for explainable AI (XAI) approaches to psychiatric diagnosis and prediction. The main aim of this work is to address a gap by conducting a systematic investigation of XAI approaches in the realm of automatic detection of mental disorders from language behavior leveraging textual data from social media. In pursuit of this aim, we perform extensive experiments to evaluate the balance between accuracy and interpretability across predictive mental health models. More specifically, we build BiLSTM models trained on a comprehensive set of human-interpretable features, encompassing syntactic complexity, lexical sophistication, readability, cohesion, stylistics, as well as topics and sentiment/emotions derived from lexicon-based dictionaries to capture multiple dimensions of language production. We conduct extensive feature ablation experiments to determine the most informative feature groups associated with specific mental health conditions. We juxtapose the performance of these models against a "black-box" domain-specific pretrained transformer adapted for mental health applications. To enhance the interpretability of the transformers models, we utilize a multi-task fusion learning framework infusing information from two relevant domains (emotion and personality traits). Moreover, we employ two distinct explanation techniques: the local interpretable model-agnostic explanations (LIME) method and a model-specific self-explaining method (AGRAD). These methods allow us to discern the specific categories of words that the information-infused models rely on when generating predictions. Our proposed approaches are evaluated on two public English benchmark datasets, subsuming five mental health conditions (attention-deficit/hyperactivity disorder, anxiety, bipolar disorder, depression and psychological stress).

Regional wind-photovoltaic combined power generation forecasting based on a novel multi-task learning framework and TPA-LSTM

Regional wind-photovoltaic combined power generation forecasting based on a novel multi-task learning framework and TPA-LSTM

Traffic Accident Risk Prediction via Multi-View Multi-Task Spatio-Temporal Networks

Abnormal traffic incidents such as traffic accidents have become a significant health and development threat with the rapid urbanization of many countries. The challenges of accurate traffic risk forecasting are three-fold. First, traffic accident data in some areas of a city is sparse, especially for a fine-grained prediction, which may cause the zero inflation problem during model training. Second, the spatio-temporal correlations of the traffic accidents are rather complex and non-linear, which is difficult to capture by existing shallow models like regression. Third, the occurrence of traffic accidents can be significantly affected by various context features including weather, POI and road network features. To address the above challenges, this paper proposes a Multi-View Multi-Task Spatio-Temporal Networks (MVMT-STN) model to forecast fine- and coarse-grained traffic accident risks of a city simultaneously. Specifically, to address the data sparsity issue in a fine-grained prediction, we adopt a multi-task learning framework to jointly forecast both fine- and coarse-grained traffic accident risks by considering their spatial associations. We conduct extensive experiments over two large real traffic accident datasets. The results show that MVMT-STN improves the performance of traffic accident risk prediction in both fine- and coarse-grained prediction by a large margin compared with existing state-of-the-art.

Explaining legal judgments: A multitask learning framework for enhancing factual consistency in rationale generation

The explanation of legal judgments is crucial for the transparency, fairness, and trustworthiness, aiming to provide rationales for decision-making. While previous works have focused on improving the accuracy of legal judgment prediction, the lack of explainability seriously limits the practical application of these methods. Many researchers have dedicated effort to extracting or generating rationales as explanations for legal judgments, ignoring the factual consistency of these rationales. Inconsistencies between rationales and fact descriptions severely impact their applicability. To address these issues, we investigate Event Chain – ordered sequences of events related to criminal behavior – as an intermediate representation in the fact descriptions, to enhance the representation of causal relationships among events, and focus on crucial events within the fact description. Specifically, we propose a multi-task learning approach, dubbed LegalMind, that introduces Event Chain as an auxiliary task and jointly models Event Chain and rationale in a unified decoder, to improve factual consistency in rationale generation. The experiment results show that our model outperforms the state-of-the-art methods, achieving improvements of 7.65% and 6.65% in AVG-BLEU on the CJO dataset and LAIC2021 dataset respectively compared to BART-C3VG. Furthermore, in comparison to BART-C3VG, our model demonstrated superior performance with increases of 6.17% and 8.33% in factual consistency on the CJO and LAIC2021 datasets, respectively.

Multi-level category-aware graph neural network for session-based recommendation

Graph neural network (GNN)-based models have achieved state-of-the-art performance in session-based recommendation (SBR). In our research, we observe that the subsequence-level intra-category item–item transition can reflect user preference under specific category, thus enhancing recommendation performance. This is overlooked by some existing category-aware SBR models. Moreover, most existing SBR models focus solely on item prediction. However, we find that item prediction and category prediction are closely related, which can respectively serve as the main task and the auxiliary task within a joint multi-task learning (MTL) framework to enhance the performance of the main task. In this paper, we propose an SBR model named Multi-level Category-aware Graph Neural Network (MCGNN) that captures multi-level information involved in a session including subsequence-level intra-category item–item transition, and performs both item prediction and category prediction in an MTL manner. To achieve this, we propose to construct an intra-category graph for each session to model subsequence-level intra-category item–item transition, sequence-level category–category transition and item–category relation. We also construct a sequence graph for each session to model sequence-level item–item transition. These two graphs capture the multi-level information involved in a session. Next, we apply GNNs to learn item representations and category representations through the two graph views. Finally, we perform item prediction and category prediction in a joint MTL framework. Our experimental results on three widely used datasets show the superiority of our proposed MCGNN.

Deep learning-based regional ECG diagnosis platform.

To enable the intelligent diagnosis of a variety of common Electrocardiogram (ECG), we investigate the deep learning-based ECG diagnosis system. From January 2015 to December 2019, four consecutive years of 100,120 conventional 12-lead ECG data were collected in our hospital. Utilizing this dataset, we constructed a deep learning model designed to intelligently diagnose prevalent ECG anomalies by employing a multi-task learning framework. The system performance was evaluated using various metrics, including sensitivity, specificity, negative predictive value, positive predictive value, and so forth. Additionally, we employed an ECG intelligent diagnostic platform for clinical application to undertake real-time online analysis of 2500 conventional 12-lead ECG samples in June 2020, aiming to validate our model. At this stage, we compared the performance of our model against the traditional manual identification method. The efficacy of the ECG intelligent diagnostic model was notably high for common and straightforward ECG patterns, such as sinus rhythm (F1=98.01%), sinus tachycardia (F1=96.26%), sinus bradycardia (F1=94.88%), and a normal electrocardiogram (F1=91.71%), as well as for Premature Ventricular Contractions (F1=91.62%). Nevertheless, when diagnosing rarer and more intricate ECG anomalies, the system requires an increased number of samples to refine the deep learning models. During the validation stage, our model exhibited better efficiency in terms of accuracy, labor time and labor cost when compared to the manual identification approach. Our deep learning-driven intelligent ECG diagnostic model clearly demonstrates significant clinical utility. The integrated artificial intelligence diagnosis system not only has the potential to augment physicians in their diagnostic processes but also offers a viable avenue to reduce associated labor costs.

GAABind: a geometry-aware attention-based network for accurate protein-ligand binding pose and binding affinity prediction.

Protein-ligand interactions are increasingly profiled at high-throughput, playing a vital role in lead compound discovery and drug optimization. Accurate prediction of binding pose and binding affinity constitutes a pivotal challenge in advancing our computational understanding of protein-ligand interactions. However, inherent limitations still exist, including high computational cost for conformational search sampling in traditional molecular docking tools, and the unsatisfactory molecular representation learning and intermolecular interaction modeling in deep learning-based methods. Here we propose a geometry-aware attention-based deep learning model, GAABind, which effectively predicts the pocket-ligand binding pose and binding affinity within a multi-task learning framework. Specifically, GAABind comprehensively captures the geometric and topological properties of both binding pockets and ligands, and employs expressive molecular representation learning to model intramolecular interactions. Moreover, GAABind proficiently learns the intermolecular many-body interactions and simulates the dynamic conformational adaptations of the ligand during its interaction with the protein through meticulously designed networks. We trained GAABind on the PDBbindv2020 and evaluated it on the CASF2016 dataset; the results indicate that GAABind achieves state-of-the-art performance in binding pose prediction and shows comparable binding affinity prediction performance. Notably, GAABind achieves a success rate of 82.8% in binding pose prediction, and the Pearson correlation between predicted and experimental binding affinities reaches up to 0.803. Additionally, we assessed GAABind's performance on the severe acute respiratory syndrome coronavirus 2 main protease cross-docking dataset. In this evaluation, GAABind demonstrates a notable success rate of 76.5% in binding pose prediction and achieves the highest Pearson correlation coefficient in binding affinity prediction compared with all baseline methods.

A knowledge-interpretable multi-task learning framework for automated thyroid nodule diagnosis in ultrasound videos

Ultrasound has become the most widely used modality for thyroid nodule diagnosis, due to its portability, real-time feedback, lack of toxicity, and low cost. Recently, the computer-aided diagnosis (CAD) of thyroid nodules has attracted significant attention. However, most existing techniques can only be applied to either static images with prominent features (manually selected from scanning videos) or rely on ’black boxes’ that cannot provide interpretable results. In this study, we develop a user-friendly framework for the automated diagnosis of thyroid nodules in ultrasound videos, by simulating the typical diagnostic workflow used by radiologists. This process consists of two orderly part-to-whole tasks. The first interprets the characteristics of each image using prior knowledge, to obtain corresponding frame-wise TI-RADS scores. Associated embedded representations not only provide diagnostic information for radiologists but also reduce computational costs. The second task models temporal contextual information in an embedding vector sequence and selectively enhances important information to distinguish benign and malignant thyroid nodules, thereby improving the efficiency and generalizability of the proposed framework. Experimental results demonstrated this approach outperformed other state-of-the-art video classification methods. In addition to assisting radiologists in understanding model predictions, these CAD results could further ease diagnostic workloads and improve patient care.

Multi-task learning framework to predict the status of central venous catheter based on radiographs

Hospital patients can have catheters and lines inserted during the course of their admission to give medicines for the treatment of medical issues, especially the central venous catheter (CVC). However, malposition of CVC will lead to many complications, even death. Clinicians always detect the status of the catheter to avoid the above issues via X-ray images. To reduce the workload of clinicians and improve the efficiency of CVC status detection, a multi-task learning framework for catheter status classification based on the convolutional neural network (CNN) is proposed. The proposed framework contains three significant components which are modified HRNet, multi-task supervision including segmentation supervision and heatmap regression supervision as well as classification branch. The modified HRNet maintaining high-resolution features from the start to the end can ensure to generation of high-quality assisted information for classification. The multi-task supervision can assist in alleviating the presence of other line-like structures such as other tubes and anatomical structures shown in the X-ray image. Furthermore, during the inference, this module is also considered as an interpretation interface to show where the framework pays attention to. Eventually, the classification branch is proposed to predict the class of the status of the catheter. A public CVC dataset is utilized to evaluate the performance of the proposed method, which gains 0.823 AUC (Area under the ROC curve) and 82.6% accuracy in the test dataset. Compared with two state-of-the-art methods (ATCM method and EDMC method), the proposed method can perform best.

Differentially Private Federated Multi-Task Learning Framework for Enhancing Human-to-Virtual Connectivity in Human Digital Twin

Differentially Private Federated Multi-Task Learning Framework for Enhancing Human-to-Virtual Connectivity in Human Digital Twin

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

Accurately detecting and predicting Lane Change (LC) processes of human-driven vehicles can help autonomous vehicles better understand their surrounding environment, recognize potential safety hazards, and improve traffic safety. This paper focuses on LC processes, first developing a Temporal Convolutional Network (TCN) with an attention mechanism (ATM) model to recognize LC intention. Then, considering the intrinsic relationship among output variables, the Multi-Task Learning (MTL) framework is employed to simultaneously predict multiple LC vehicle status indicators. Furthermore, a unified modeling framework for LC intention recognition and driving status prediction (LC-IR-SP) is developed. The results indicate that the classification accuracy of LC intention was improved from 95.83% to 98.20% when incorporating the ATM into the TCN model. For LC vehicle status prediction issues, Pearson's correlation coefficient indicates that metrics extracted from LC processes show stronger correlation than those extracted from Lane-keeping processes. Consequently, three multi-tasking learning models are constructed based on the MTL framework. The results indicate that the MTL with Long Short-Term Memory (MTL-LSTM) model outperforms the MTL with TCN (MTL-TCN) and MTL with TCN-ATM (MTL-TCN-ATM) models. Compared to the corresponding single-task model, the MTL-LSTM model demonstrates an average decrease of 26.04% in MAE and 25.19% in RMSE. The LC-IR-SP model developed holds great potential in enhancing autonomous vehicles' perception and prediction capabilities, such as identifying LC behaviors, calculating real-time traffic conflict indices, and improving vehicle control strategies.