RESUMEN

In genomics, use of deep learning (DL) is rapidly growing and DL has successfully demonstrated its ability to uncover complex relationships in large biological and biomedical data sets. With the development of high-throughput sequencing techniques, genomic markers can now be allocated to large sections of a genome. By analysing allele sharing between individuals, one may calculate realized genomic relationships from single nucleotide polymorphisms (SNPs) data rather than relying on known pedigree relationships under polygenic model. The traditional approaches in genome-wide prediction (GWP) of quantitative phenotypes utilise genomic relationships in fixed global covariance modelling, possibly with some non-linear kernel mapping (for example Gaussian processes). On the other hand, the DL approaches proposed so far for GWP fail to take into account the non-Euclidean graph structure of relationships between individuals over several generations. In this paper, we propose one global convolutional neural network (GCN) and one local sub-sampling architecture (GCN-RS) that are specifically designed to perform regression analysis based on genomic relationship information. A GCN is tailored to non-Euclidean spaces and consists of several layers of graph convolutions. The GCN-RS architecture is designed to further improve the GCN's performance by sub-sampling the graph to reduce the dimensionality of the input data. Through these graph convolutional layers, the GCN maps input genomic markers to their quantitative phenotype values. The graphs are constructed using an iterative nearest neighbour approach. Comparisons show that the GCN-RS outperforms the popular Genomic Best Linear Unbiased Predictor (GBLUP) method on one simulated and three real data sets from wheat, mice and pig with a predictive improvement of 4.4% to 49.4% in terms of test mean squared error (MSE). This indicates that GCN-RS is a promising tool for genomic predictions in plants and animals. Furthermore, GCN-RS is computationally efficient, making it a viable option for large-scale applications.

RESUMEN

Tourism is an emotional sphere, and researchers focus on emotions to optimize tourism experiences. Tourism studies on emotions mostly ignore differences in emotions across demographic tourist groups by gender and age, thus limiting the understanding of emotions to the explicit characteristics of tourists' emotions. On the basis of geotagged facial expressions on social media platforms, this study aims to visualize the emotions of groups in scenic spots and then reveal the variations between groups' emotions within theme parks. By employing a facial recognition algorithm, an emotion distribution graph was proposed to represent groups' emotions in detail. Some analytical methods were combined to characterize of the emotion distribution of each group. Through a comprehensive comparison, the results suggest that there are unique characteristics of emotion distribution for each group and considerable variations between them. This study helps researchers achieve a deeper understanding of tourists' emotional differences and enhances the theorization of emotions. This research also highlights the advantages and significant practical implications of our method framework.

Asunto(s)

RESUMEN

BACKGROUND AND OBJECTIVE: Electrocardiogram (ECG) analysis is crucial in diagnosing cardiovascular diseases (CVDs). It is important to consider both temporal and spatial features in ECG analysis to improve automated CVDs diagnosis. Significant progress has been made in automated CVDs diagnosis based on ECG with the continuous development of deep learning. Current most researches often treat 12-lead ECG signals as synchronous sequences in Euclidean space, focusing primarily on extracting temporal features while overlooking the spatial relationships among the 12-lead. However, the spatial distribution of 12-lead ECG electrodes can be more naturally represented using non-Euclidean data structures, which makes the relationships among leads more consistent with their intrinsic characteristics. METHODS: This study proposes an innovative method, Convolutional Residual Graph Neural Network (Conv-RGNN), for ECG classification. The first step is to segment the 12-lead ECG into twelve single-lead ECG, which are then mapped to nodes in a graph that captures the relationships between the different leads through spatial connections, resulting in the 12-lead ECG graph. The graph is then used as input for Conv-RGNN. A convolutional neural network with a position attention mechanism is used to extract temporal sequence information and selectively integrate contextual information to enhance semantic features at different positions. The spatial features of the 12-lead ECG graph are extracted using the residual graph neural network. RESULTS: The experimental results indicate that Conv-RGNN is highly competitive in two multi-label datasets and one single-label dataset, demonstrating exceptional parameter efficiency, inference speed, model performance, and robustness. CONCLUSION: The Conv-RGNN proposed in this paper offer a promising and feasible approach for intelligent diagnosis in resource-constrained environments.

RESUMEN

Many researchers have addressed the challenge of optimal pressure sensor placement for different purposes, such as leakage detection, model calibration, state estimation, etc. However, pressure data often need to serve multiple purposes, and a method to optimize sensor locations with versatility for various objectives is still lacking. In this paper, a graph-based optimal sensor placement (GOSP) framework is proposed, which aims to provide a robust and all-purpose approach to identify critical points for pressure monitoring. By analysing the spatial variation frequencies of WDN pressures, the relationship between measurements and the global variation of original pressures is established. On this basis, the D-optimality criterion is adopted to formulate the objective of GOSP, which aims to maximize the information on the spatial distribution of pressures that can be obtained from measurements. The new-proposed objective ensures that the sensor locations are compatible with various application scenarios. The proposed method was applied to a real-life distribution network, and was compared with other optimal sensor placement methods oriented towards burst detection and pipe roughness calibration. Based on comparative studies in different scenarios including unknown pressure estimation, burst detection, and model calibration, the effectiveness and robustness of the proposed method have been proved.

RESUMEN

The next basket recommendation task aims to predict the items in the user's next basket by modeling the user's basket sequence. Existing next basket recommendations focus on improving recommendation performance, and most of these methods are black-box models, ignoring the importance of providing explanations to improve user satisfaction. Furthermore, most next basket recommendation methods are designed for consumer users, and few methods are proposed for business user characteristics. To address the above problems, we propose a Knowledge Reinforced Explainable Next Basket Recommendation (KRE-NBR). Specifically, we construct a basket-based knowledge graph and obtain pretrained embeddings of entities that contain rich information of the knowledge graph. To obtain high-quality user predictive vectors, we fuse user pretrained embeddings, user basket sequence level embeddings, and user repurchase embeddings. One highlight of the user repurchase embeddings is that they are able to model business user repurchase behavior. To make the results of next basket recommendations explainable, we use reinforcement learning for path reasoning to find the items recommended in the next basket and generate recommendation explanations at the same time. To the best of our knowledge, this is the first work to provide recommendation explanations for next basket recommendations. Extensive experiments on real datasets show that the recommendation performance of our proposed approach outperforms several state-of-the-art baselines.

RESUMEN

BACKGROUND: Applying graph convolutional networks (GCN) to the classification of free-form natural language texts leveraged by graph-of-words features (TextGCN) was studied and confirmed to be an effective means of describing complex natural language texts. However, the text classification models based on the TextGCN possess weaknesses in terms of memory consumption and model dissemination and distribution. In this paper, we present a fast message passing network (FastMPN), implementing a GCN with message passing architecture that provides versatility and flexibility by allowing trainable node embedding and edge weights, helping the GCN model find the better solution. We applied the FastMPN model to the task of clinical information extraction from cancer pathology reports, extracting the following six properties: main site, subsite, laterality, histology, behavior, and grade. RESULTS: We evaluated the clinical task performance of the FastMPN models in terms of micro- and macro-averaged F1 scores. A comparison was performed with the multi-task convolutional neural network (MT-CNN) model. Results show that the FastMPN model is equivalent to or better than the MT-CNN. CONCLUSIONS: Our implementation revealed that our FastMPN model, which is based on the PyTorch platform, can train a large corpus (667,290 training samples) with 202,373 unique words in less than 3 minutes per epoch using one NVIDIA V100 hardware accelerator. Our experiments demonstrated that using this implementation, the clinical task performance scores of information extraction related to tumors from cancer pathology reports were highly competitive.

Asunto(s)

RESUMEN

Predicting drug-target interactions (DTI) is a crucial stage in drug discovery and development. Understanding the interaction between drugs and targets is essential for pinpointing the specific relationship between drug molecules and targets, akin to solving a link prediction problem using information technology. While knowledge graph (KG) and knowledge graph embedding (KGE) methods have been rapid advancements and demonstrated impressive performance in drug discovery, they often lack authenticity and accuracy in identifying DTI. This leads to increased misjudgment rates and reduced efficiency in drug development. To address these challenges, our focus lies in refining the accuracy of DTI prediction models through KGE, with a specific emphasis on causal intervention confidence measures (CI). These measures aim to assess triplet scores, enhancing the precision of the predictions. Comparative experiments conducted on three datasets and utilizing 9 KGE models reveal that our proposed confidence measure approach via causal intervention, significantly improves the accuracy of DTI link prediction compared to traditional approaches. Furthermore, our experimental analysis delves deeper into the embedding of intervention values, offering valuable insights for guiding the design and development of subsequent drug development experiments. As a result, our predicted outcomes serve as valuable guidance in the pursuit of more efficient drug development processes.

RESUMEN

Inferring gene regulatory networks through deep learning and causal inference methods is a crucial task in the field of computational biology and bioinformatics. This study presents a novel approach that uses a Graph Convolutional Network (GCN) guided by causal information to infer Gene Regulatory Networks (GRN). The transfer entropy and reconstruction layer are utilized to achieve causal feature reconstruction, mitigating the information loss problem caused by multiple rounds of neighbor aggregation in GCN, resulting in a causal and integrated representation of node features. Separable features are extracted from gene expression data by the Gaussian-kernel Autoencoder to improve computational efficiency. Experimental results on the DREAM5 and the mDC dataset demonstrate that our method exhibits superior performance compared to existing algorithms, as indicated by the higher values of the AUPRC metrics. Furthermore, the incorporation of causal feature reconstruction enhances the inferred GRN, rendering them more reasonable, accurate, and reliable.

Asunto(s)

RESUMEN

This article offers a comprehensive and user-friendly guide to visualizing causal theories using Single World Intervention Graphs (SWIGs). We begin with a discussion of the potential outcomes approach to causality and limitations of using Directed Acyclic Graphs (DAGs) under this framework. We then introduce SWIGs as a simple but powerful tool for integrating potential outcomes explicitly into causal diagrams. The article provides a step-by-step guide on transforming DAGs into SWIGs that includes practical insights into constructing SWIGs under various scenarios such as confounding, mediation, and sequential randomization. Highlighting the utility of SWIGs in practice, we illustrate their application in identifying the g-formula, showcasing their capacity to make causal estimands visually explicit. This article serves as a resource for epidemiologists and researchers interested in expanding their causal inference toolkit.

RESUMEN

Rotating machinery is widely used in modern industrial systems, and its health status can directly impact the operation of the entire system. Timely and accurate diagnosis of rotating machinery faults is crucial for ensuring production safety, reducing economic losses, and improving efficiency. Traditional deep learning methods can only extract features from the vertices of the input data, thereby overlooking the information contained in the relationships between vertices. This paper proposes a Legendre graph convolutional network (LGCN) integrated with a self-attention graph pooling method, which is applied to fault diagnosis of rotating machinery. The SA-LGCN model converts vibration signals from Euclidean space into graph signals in non-Euclidean space, employing a fast local spectral filter based on Legendre polynomials and a self-attention graph pooling method, significantly improving the model's stability and computational efficiency. By applying the proposed method to 10 different planetary gearbox fault tasks, we verify that it offers significant advantages in fault diagnosis accuracy and load adaptability under various working conditions.

RESUMEN

The convergence of heterogeneous wireless sensor networks provides many benefits, including increased coverage, flexible load balancing capabilities, more efficient use of network resources, and the provision of additional data by different types of sensors, thus leading to improved customer service based on more complete information. However, despite these advances, the challenge of ensuring reliability and survivability remains due to low-cost sensor requirements and the inherent unreliability of the wireless environment. Integrating different sensor networks and unifying protocols naturally leads to the creation of a network with multiple sinks, necessitating the exploration of new approaches to rational reliability assurance. The failure of some sensors does not necessarily lead to a shutdown of the network, since other sensors can duplicate information and deliver data to sinks via an increased number of alternative routes. In this paper, the reliability indicator is defined as the probability that sinks can collect data from a given number of sensors. In this context, a dedicated reliability metric is introduced and examined for its effectiveness. This metric is computed using an algorithm rooted in the modified factoring method. Furthermore, we introduce a heuristic algorithm designed for optimal sink placement in wireless sensor networks to achieve the highest level of network reliability.

RESUMEN

Wearable flexible strain sensors require different performance depending on the application scenario. However, developing strain sensors based solely on experiments is time-consuming and often produces suboptimal results. This study utilized sensor knowledge to reduce knowledge redundancy and explore designs. A framework combining knowledge graphs and graph representational learning methods was proposed to identify targeted performance, decipher hidden information, and discover new designs. Unlike process-parameter-based machine learning methods, it used the relationship as semantic features to improve prediction precision (up to 0.81). Based on the proposed framework, a strain sensor was designed and tested, demonstrating a wide strain range (300%) and closely matching predicted performance. This predicted sensor performance outperforms similar materials. Overall, the present work is favorable to design constraints and paves the way for the long-awaited implementation of text-mining-based knowledge management for sensor systems, which will facilitate the intelligent sensor design process.

RESUMEN

Accurate and timely forecasting of traffic on local road networks is crucial for deploying effective dynamic traffic control, advanced route planning, and navigation services. This task is particularly challenging due to complex spatio-temporal dependencies arising from non-Euclidean spatial relations in road networks and non-linear temporal dynamics influenced by changing road conditions. This paper introduces the spatio-temporal network embedding (STNE) model, a novel deep learning framework tailored for learning and forecasting graph-structured traffic data over extended input sequences. Unlike traditional convolutional neural networks (CNNs), the model employs graph convolutional networks (GCNs) to capture the spatial characteristics of local road network topologies. Moreover, the segmentation of very long input traffic data into multiple sub-sequences, based on significant temporal properties such as closeness, periodicity, and trend, is performed. Multi-dimensional long short-term memory neural networks (MDLSTM) are utilized to flexibly access multi-dimensional context. Experimental results demonstrate that the STNE model surpasses state-of-the-art traffic forecasting benchmarks on two large-scale real-world traffic datasets.

RESUMEN

Constructing a globally consistent high-precision map is essential for the application of mobile robots. Existing optimization-based mapping methods typically constrain robot states in pose space during the graph optimization process, without directly optimizing the structure of the scene, thereby causing the map to be inconsistent. To address the above issues, this paper presents a three-dimensional (3D) LiDAR mapping framework (i.e., BA-CLM) based on LiDAR bundle adjustment (LBA) cost factors. We propose a multivariate LBA cost factor, which is built from a multi-resolution voxel map, to uniformly constrain the robot poses within a submap. The framework proposed in this paper applies the LBA cost factors for both local and global map optimization. Experimental results on several public 3D LiDAR datasets and a self-collected 32-line LiDAR dataset demonstrate that the proposed method achieves accurate trajectory estimation and consistent mapping.

RESUMEN

In urban road environments, global navigation satellite system (GNSS) signals may be interrupted due to occlusion by buildings and obstacles, resulting in reduced accuracy and discontinuity of combined GNSS/inertial navigation system (INS) positioning. Improving the accuracy and robustness of combined GNSS/INS positioning systems for land vehicles in the presence of GNSS interruptions is a challenging task. The main objective of this paper is to develop a method for predicting GNSS information during GNSS outages based on a long short-term memory (LSTM) neural network to assist in factor graph-based combined GNSS/INS localization, which can provide a reliable combined localization solution during GNSS signal outages. In an environment with good GNSS signals, a factor graph fusion algorithm is used for data fusion of the combined positioning system, and an LSTM neural network prediction model is trained, and model parameters are determined using the INS velocity, inertial measurement unit (IMU) output, and GNSS position incremental data. In an environment with interrupted GNSS signals, the LSTM model is used to predict the GNSS positional increments and generate the pseudo-GNSS information and the solved results of INS for combined localization. In order to verify the performance and effectiveness of the proposed method, we conducted real-world road test experiments on land vehicles installed with GNSS receivers and inertial sensors. The experimental results show that, compared with the traditional combined GNSS/INS factor graph localization method, the proposed method can provide more accurate and robust localization results even in environments with frequent GNSS signal loss.

RESUMEN

In this paper, we present a noise-robust approach for the 3D pose estimation of multiple people using appearance similarity. The common methods identify the cross-view correspondences between the detected keypoints and determine their association with a specific person by measuring the distances between the epipolar lines and the joint locations of the 2D keypoints across all the views. Although existing methods achieve remarkable accuracy, they are still sensitive to camera calibration, making them unsuitable for noisy environments where any of the cameras slightly change angle or position. To address these limitations and fix camera calibration error in real-time, we propose a framework for 3D pose estimation which uses appearance similarity. In the proposed framework, we detect the 2D keypoints and extract the appearance feature and transfer it to the central server. The central server uses geometrical affinity and appearance similarity to match the detected 2D human poses to each person. Then, it compares these two groups to identify calibration errors. If a camera with the wrong calibration is identified, the central server fixes the calibration error, ensuring accuracy in the 3D reconstruction of skeletons. In the experimental environment, we verified that the proposed algorithm is robust against false geometrical errors. It achieves around 11.5% and 8% improvement in the accuracy of 3D pose estimation on the Campus and Shelf datasets, respectively.

RESUMEN

Spatiotemporal (ST) graph modeling has garnered increasing attention recently. Most existing methods rely on a predefined graph structure or construct a single learnable graph throughout training. However, it is challenging to use a predefined graph structure to capture dynamic ST changes effectively due to evolving node relationships over time. Furthermore, these methods typically utilize only the original data, neglecting external temporal factors. Therefore, we put forward a novel time-varying graph convolutional network model that integrates external factors for multifeature ST series prediction. Firstly, we construct a time-varying adjacency matrix using attention to capture dynamic spatial relationships among nodes. The graph structure adapts over time during training, validation, and testing phases. Then, we model temporal dependence by dilated causal convolution, leveraging gated activation unit and residual connection. Notably, the prediction accuracy is enhanced through the incorporation of embedding absolute time and the fusion of multifeature. This model has been applied to three real-world multifeature datasets, achieving state-of-the-art performance in all cases. Experiments show that the method has high accuracy and robustness when applied to multifeature and multivariate ST series problems.

RESUMEN

This work initiates a concept of reduced reverse degree based RR D M -Polynomial for a graph, and differential and integral operators by using this RR D M -Polynomial. In this study twelve reduced reverse degree-based topological descriptors are formulated using the RR D M -Polynomial. The topological descriptors, denoted as T D 's, are numerical invariants that offer significant insights into the molecular topology of a molecular graph. These descriptors are essential for conducting QSPR investigations and accurately estimating physicochemical attributes. The structural and algebraic characteristics of the graphene and graphdiyne are studied to apply this methodology. The study involves the analysis and estimation of Reduced reverse degree-based topological descriptors and physicochemical features of graphene derivatives using best-fit quadratic regression models. This work opens up new directions for scientists and researchers to pursue, taking them into new fields of study.

RESUMEN

Background: Resting-state brain networks represent the interconnectivity of different brain regions during rest. Utilizing brain network analysis methods to model these networks can enhance our understanding of how different brain regions collaborate and communicate without explicit external stimuli. However, analyzing resting-state brain networks faces challenges due to high heterogeneity and noise correlation between subjects. This study proposes a brain structure learning-guided multi-view graph representation learning method to address the limitations of current brain network analysis and improve the diagnostic accuracy (ACC) of mental disorders. Methods: We first used multiple thresholds to generate different sparse levels of brain networks. Subsequently, we introduced graph pooling to optimize the brain network representation by reducing noise edges and data inconsistency, thereby providing more reliable input for subsequent graph convolutional networks (GCNs). Following this, we designed a multi-view GCN to comprehensively capture the complexity and variability of brain structure. Finally, we employed an attention-based adaptive module to adjust the contributions of different views, facilitating their fusion. Considering that the Smith atlas offers superior characterization of resting-state brain networks, we utilized the Smith atlas to construct the graph network. Results: Experiments on two mental disorder datasets, the Autism Brain Imaging Data Exchange (ABIDE) dataset and the Mexican Cocaine Use Disorders (SUDMEX CONN) dataset, show that our model outperforms the state-of-the-art methods, achieving nearly 75% ACC and 70% area under the receiver operating characteristic curve (AUC) on both datasets. Conclusions: These findings demonstrate that our method of combining multi-view graph learning and brain structure learning can effectively capture crucial structural information in brain networks while facilitating the acquisition of feature information from diverse perspectives, thereby improving the performance of brain network analysis.

RESUMEN

Alzheimer's disease (AD) has been conceptualized as a syndrome of brain network dysfunction. Recent imaging connectomics studies have provided unprecedented opportunities to map structural and functional brain networks in AD. By reviewing molecular, imaging, and computational modeling studies, we have shown that highly connected brain hubs are primarily distributed in the medial and lateral prefrontal, parietal, and temporal regions in healthy individuals and that the hubs are selectively and severely affected in AD as manifested by increased amyloid-beta deposition and regional atrophy, hypo-metabolism, and connectivity dysfunction. Furthermore, AD-related hub degeneration depends on the imaging modality with the most notable degeneration in the medial temporal hubs for morphological covariance networks, the prefrontal hubs for structural white matter networks, and in the medial parietal hubs for functional networks. Finally, the AD-related hub degeneration shows metabolic, molecular, and genetic correlates. Collectively, we conclude that the brain-network-hub-degeneration framework is promising to elucidate the biological mechanisms of network dysfunction in AD, which provides valuable information on potential diagnostic biomarkers and promising therapeutic targets for the disease.