Explore the vast range of titles available.

Indoor thermal comfort immensely impacts the health and performance of occupants. Therefore, researchers and engineers have proposed numerous computational models to estimate thermal comfort (TC). Given the impetus toward energy efficiency, the current focus is on data-driven TC prediction solutions that leverage state-of-the-art machine learning (ML) algorithms. However, an occupant’s perception of indoor thermal comfort (TC) is subjective and multi-dimensional. Different aspects of TC are represented by various standard metrics/scales viz., thermal sensation (TSV), thermal comfort (TCV), and thermal preference (TPV). The current ML-based TC prediction solutions adopt the Single-task Learning approach, i.e., one prediction model per metric. Consequently, solutions often focus on only one TC metric. Moreover, when several metrics are considered, multiple ML models for a single indoor space lead to conflicting predictions, rendering real-world deployment infeasible. This work addresses these problems by leveraging Multi-task Learning for TC prediction in naturally ventilated buildings. First, a survey-and-measurement study is conducted in the composite climatic region of north India, in 14 naturally ventilated classrooms of 5 schools, involving 512 primary school students. Next, the dataset is analyzed for important environmental, physiological, and psycho-social factors that influence thermal comfort of children. Further, “DeepComfort”, a deep neural network based Multi-task Learning model is proposed. DeepComfort predicts multiple TC output metrics viz., TSV, TPV, and TCV, simultaneously through a single model. It is validated on ASHRAE-II database and the primary student dataset created in this study. It demonstrates high F1-scores, Accuracy (≈90%), and generalization capability, despite the challenges of illogical responses and data imbalance. DeepComfort is also shown to outperform 6 popular metric-specific single-task machine learning algorithms.

The key issue in the field of smart contract security is efficient and rapid vulnerability detection in smart contracts. Most of the existing detection methods can only detect the presence of vulnerabilities in the contract and can hardly identify their type. Furthermore, they have poor scalability. To resolve these issues, in this study, we developed a smart contract vulnerability detection model based on multi-task learning. By setting auxiliary tasks to learn more directional vulnerability features, the detection capability of the model was improved to realize the detection and recognition of vulnerabilities. The model is based on a hard-sharing design, which consists of two parts. First, the bottom sharing layer is mainly used to learn the semantic information of the input contract. The text representation is first transformed into a new vector by word and positional embedding, and then the neural network, based on an attention mechanism, is used to learn and extract the feature vector of the contract. Second, the task-specific layer is mainly employed to realize the functions of each task. A classical convolutional neural network was used to construct a classification model for each task that learns and extracts features from the shared layer for training to achieve their respective task objectives. The experimental results show that the model can better identify the types of vulnerabilities after adding the auxiliary vulnerability detection task. This model realizes the detection of vulnerabilities and recognizes three types of vulnerabilities. The multi-task model was observed to perform better and is less expensive than a single-task model in terms of time, computation, and storage.

Satellite‐based precipitation estimations provide frequent, large‐scale measurements. Deep learning has recently shown significant potential for improving estimation accuracy. Most studies have employed a two‐stage framework, which is a sequential architecture of a rain/no‐rain binary classification task followed by a rain rate regression task. This study proposes a novel precipitation retrieval framework in which these two tasks are simultaneously trained using multi‐task learning approach (MTL). Furthermore, a novel network architecture and loss function were designed to reap the benefits of MTL. The proposed two‐task model successfully achieved a better performance than the conventional single‐task model possibly due to efficient knowledge transfer between tasks. Furthermore, the product intercomparison showed that our product outperformed existing products in rain rate retrieval and also yielded better skills in the rain/no‐rain retrieval task. Plain Language Summary Satellite‐based observation can provide frequent large‐scale precipitation measurements. Recently, machine learning techniques have been widely used in satellite precipitation estimates. This study introduces a novel deep learning (DL) method using multi‐task approach. The proposed method enables the simultaneous learning of rain/no‐rain classification and rain rate estimates. The experiment determined that our method achieved a better result than the conventional DL. Furthermore, a comparison between existing products demonstrated that our method provided a better rain rate estimate and comparable rain/no‐rain classification. Key Points Multi‐task learning was devised to infer precipitation intensity and rain/no‐rain classification simultaneously Simultaneous learning demonstrated a better performance than the conventional single task learning Retrieval based on the proposed algorithm outperformed existing satellite precipitation products

The accurate recognition of emotions in conversations helps understand the speaker’s intentions and facilitates various analyses in artificial intelligence, especially in human–computer interaction systems. However, most previous methods need more ability to track the different emotional states of each speaker in a dialogue. To alleviate this dilemma, we propose a new approach, Multi-Task Learning and Multi-Fusion AudioText Emotion Recognition in Conversation (MMATERIC) for emotion recognition in conversation. MMATERIC can refer to and combine the benefits of two distinct tasks: emotion recognition in text and emotion recognition in speech, and production of fused multimodal features to recognize the emotions of different speakers in dialogue. At the core of MATTERIC are three modules: an encoder with multimodal attention, a speaker emotion detection unit (SED-Unit), and a decoder with speaker emotion detection Bi-LSTM (SED-Bi-LSTM). Together, these three modules model the changing emotions of a speaker at a given moment in a conversation. Meanwhile, we adopt multiple fusion strategies in different stages, mainly using model fusion and decision stage fusion to improve the model’s accuracy. Simultaneously, our multimodal framework allows features to interact across modalities and allows potential adaptation flows from one modality to another. Our experimental results on two benchmark datasets show that our proposed method is effective and outperforms the state-of-the-art baseline methods. The performance improvement of our method is mainly attributed to the combination of three core modules of MATTERIC and the different fusion methods we adopt in each stage.

Photonic neural networks are brain-inspired information processing technology using photons instead of electrons to perform artificial intelligence (AI) tasks. However, existing architectures are designed for a single task but fail to multiplex different tasks in parallel within a single monolithic system due to the task competition that deteriorates the model performance. This paper proposes a novel optical multitask learning system by designing multiwavelength diffractive deep neural networks (D NNs) with the joint optimization method. By encoding multitask inputs into multiwavelength channels, the system can increase the computing throughput and significantly alleviate the competition to perform multiple tasks in parallel with high accuracy. We design the two-task and four-task D NNs with two and four spectral channels, respectively, for classifying different inputs from MNIST, FMNIST, KMNIST, and EMNIST databases. The numerical evaluations demonstrate that, under the same network size, multiwavelength D NNs achieve significantly higher classification accuracies for multitask learning than single-wavelength D NNs. Furthermore, by increasing the network size, the multiwavelength D NNs for simultaneously performing multiple tasks achieve comparable classification accuracies with respect to the individual training of multiple single-wavelength D NNs to perform tasks separately. Our work paves the way for developing the wavelength-division multiplexing technology to achieve high-throughput neuromorphic photonic computing and more general AI systems to perform multiple tasks in parallel.

Hydrological signatures (HS) have proven to be highly effective in calibrating physically‐based hydrological models, enhancing their process consistency. However, their integration into parameter optimization for deep learning (DL)‐based hydrological models has been limited. To address this gap, we propose a novel HS‐informed framework that dynamically integrates HS into DL parameterization through a multi‐task learning approach. This study evaluates the impact of HS integration on model performance using a large‐scale, global hydrological data set. The HS‐informed model achieved a significant performance improvement, with a median Nash‐Sutcliffe Efficiency (NSE) of 0.739, compared to 0.666 for the baseline model across the test set. Notably, the most pronounced improvements in NSE were observed in hydrologically complex basins, including baseflow‐dominated (+0.135), drought‐prone (+0.148), and flood‐prone basins (+0.159). Sensitivity analysis further revealed that the HS‐informed model could leverage extended historical input data (over 120 days) to sustain robust performance (median NSE of 0.715) over a 30‐day forecast period. Shapley Additive Explanations analysis highlighted two key mechanisms underlying these improvements: the enhanced recognition of long‐term hydrological patterns through improved memory and a better representation of catchment heterogeneity by emphasizing non‐climatic attributes. These findings demonstrate that integrating HS offers a superior approach to traditional point‐error‐based calibration in AI‐driven hydrological modeling.

Tropical cyclone (TC)‐induced rainfall is a drastic threat to human life and property, and thus rational rainstorm nowcasts within even a lead time of few hours play a key role in disaster mitigation. While recent deep learning‐based algorithms have shown promise, predictions commonly suffer from the troubles of blur, dissipation, and location errors of TC rainbands, particularly for a lead time beyond 1 hr. Here, we develop a new nowcasting model, named TyrainNow, and show a significant improvement for nowcasting rainbands with a lead time up to 2 hr. Concretely, TyrainNow employs a refined multi‐task loss function integrating geographical consistency, temporal coherence and radar image structural similarity. This tailored enhancement is architecture‐agnostic and involves subtle adjustments. Secondly, TyrainNow adopts the quantile mapping technique to correct systematic attenuation biases inherent in the neural network outputs. The new model is verified on the basis of typhoon radar composite reflectivity products in South China, with a focus on the Greater Bay Area. Specifically, the new model achieves a critical success index of 0.099 at the 40 dBZ threshold, marking a substantial improvement from 27% to 330% compared to three other benchmark models, DGMR (0.070), PredRNN‐v2 (0.023), and optical flow model (0.078), averaged over the lead times between 1 and 2 hr. We further verify the model's explainability and generalizability, and recommend it as a scalable and reliable model.

Deep learning has shown great promise in hydrological modeling, especially when large sample data sets are used to capture generalizable patterns across basins. However, challenges remain in addressing data scarcity and ensuring model reliability, particularly when key hydrological observations are modeled as individual tasks. In this study, we shift from traditional single‐task learning (STL) to multi‐task learning (MTL) to leverage the interconnections among hydrological variables and potentially improve modeling outcomes in data‐limited settings. Using a Long Short‐Term Memory (LSTM) neural network with the Catchment Attributes and Meteorology for Large‐Sample Studies data set, we developed an MTL model to predict streamflow and evapotranspiration across 591 basins. The MTL model exhibited comparable predictions for streamflow and evapotranspiration to STL models, with similar spatiotemporal generalization across varying data sizes. MTL's strength appeared when using LSTM cell state probes to predict the non‐target variable, surface soil moisture (SSM), showing slightly higher correlation coefficients. This highlights MTL's ability to capture intrinsic hydrological rules, enhancing model reliability. Leveraging this ability, we further explored MTL's advantages under two data‐limited scenarios: one with less‐observed SSM data and another with no available streamflow data. In both cases, MTL, supported by another well‐observed variable, outperformed STL models by a notable difference. These findings highlight MTL's potential to address the challenges of hydrological modeling in data‐limited basins. As Earth observation data continues to grow, MTL could become a valuable approach for building more reliable and generalizable hydrological models.

Passenger flow prediction has drawn increasing attention in the deep learning research field due to its great importance in traffic management and public safety. The major challenge of this essential task lies in multiple spatiotemporal correlations that exhibit complex non-linear correlations. Although both the spatial and temporal perspectives have been considered in modeling, most existing works have ignored complex temporal correlations or underlying spatial similarity. In this paper, we identify the unique spatiotemporal correlation of urban metro flow, and propose an attention-based deep spatiotemporal network with multi-task learning (ADST-Net) at a citywide level to predict the future flow from historical observations. ADST-Net uses three independent channels with the same structure to model the recent, daily-periodic and weekly-periodic complicated spatiotemporal correlations, respectively. Specifically, each channel uses the framework of residual networks, the rectified block and the multi-scale convolutions to mine spatiotemporal correlations. The residual networks can effectively overcome the gradient vanishing problem. The rectified block adopts an attentional mechanism to automatically reweigh measurements at different time intervals, and the multi-scale convolutions are used to extract explicit spatial relationships. ADST-Net also introduces an external embedding mechanism to extract the influence of external factors on flow prediction, such as weather conditions. Furthermore, we enforce multi-task learning to utilize transition passenger flow volume prediction as an auxiliary task during the training process for generalization. Through this model, we can not only capture the steady trend, but also the sudden changes of passenger flow. Extensive experimental results on two real-world traffic flow datasets demonstrate the obvious improvement and superior performance of our proposed algorithm compared with state-of-the-art baselines.

Purpose Although bone mineral density (BMD) measurement using dual‐energy x‐ray absorptiometry (DXA) is the most common method of diagnosing osteoporosis, it is not widely used to screen patients. In this exploratory study, we developed a multi‐task learning model that predicts BMD from chest radiographs using clavicular features and supports network explainability. Methods The proposed multi‐task learning model integrates segmentation and regression tasks by incorporating a regression branch into the U‐Net architecture in an end‐to‐end manner. A total of 1600 patients who underwent chest radiography and DXA of the lumbar vertebrae were included in this study. We compared the BMD predictive performance of the mean absolute error (MAE) and Pearson correlation coefficient (R value) between the proposed multi‐task learning model and the single‐task learning model, which was defined as the comparison model that only performed BMD prediction. Additionally, model performance for classifying osteoporosis, osteopenia, and normal bone status was evaluated via reclassification analysis based on the World Health Organization (WHO) criteria. Confusion matrices were generated, and classwise and macro‐averaged performance metrics were calculated. To confirm the rationale for the BMD predictions, we evaluated heat maps generated using the gradient‐weighted class activation mapping technique to determine whether the highlighted regions overlapped with the clavicle. Results The multi‐task learning model demonstrated superior predictive performance (MAE of 0.092 g/cm2 and R value of 0.769) compared with the single‐task learning model (MAE of 0.101 g/cm2 and R value of 0.724), a statistically significant (p < 0.001) difference in MAE. Bland–Altman analysis showed that the multi‐task learning model had good agreement with narrower limits of agreement, although a bias was present (bias: −0.013 g/cm2; limits of agreement: −0.248 to 0.223 g/cm2). In contrast, the single‐task model showed slightly wider agreement limits (bias: −0.003 g/cm2; limits of agreement: −0.257 to 0.252 g/cm2). In the reclassification analysis based on the WHO criteria, the multi‐task learning model resulted in fewer misclassifications than the single‐task learning model. The macro‐averaged sensitivity, specificity, precision, and F1 score were 0.647, 0.826, 0.680, and 0.659, respectively, for the multi‐task model, compared with 0.597, 0.809, 0.660, and 0.616, respectively, for the single‐task model. The heat maps in the multi‐task learning model highlighted different regions compared with the single‐task model, the clavicular area. Conclusion The proposed multi‐task learning model demonstrated the predictive rationale by focusing on the clavicle in chest radiographs, which is clinically relevant to BMD, and showed improved performance compared with the single‐task model.