Search

À medida que as Tecnologias da Informação se tornam acessíveis e são disseminadas, as organizações buscam na interconectividade destas novas formas de prover serviços de qualidade e confiança uma vez que a Tecnologia da Informação (TI) está cada vez mais integrada aos processos de negócio. A ocorrência de um incidente é um acontecimento que afeta um serviço ou sistema de TI, e a restauração do seu nível de desempenho original exige considerável esforço de recursos, físicos, humanos e administrativos. Restaurar um serviço após um incidente depende de um planejamento de recuperação estruturado. A recuperação operacional de incidentes é a capacidade de reagir a uma interrupção nos serviços e restaurar as funções críticas dos negócios da organização. Existem boas práticas que auxiliam na Gestão de Continuidade de Negócios (GCN), porém a falta de estruturação na aplicação destas, de forma alinhada e integrada, pelas organizações, impacta negativamente na estratégia de elaboração de um plano de continuidade de negócios eficiente e eficaz. O objetivo deste artigo é propor um modelo de GCN, baseado em boas práticas de Governança de TI, de forma estruturada e alinhada. Este artigo apresenta o Management Process Organization (MaPO), o qual é um modelo que define o monitoramento de recursos ativos do serviço, aplicando processos de gestão de TI, baseados na Information Technology Infrastrcture Library (ITIL), assim como Balanced Score Card (BSC), Business Impact Analysis (BIA) e gestão de riscos, baseados no Control Objectives for Information and Related Technology (COBIT), no alinhamento estratégico e organizacional, bem como implementações necessárias a atender os requisitos de negócio. O modelo MaPO partiu do princípio de estudo de serviços disponíveis de TI de uso comum, partindo desde a gestão estratégica, até a gestão operacional, sendo uma opção de ferramenta para direcionar a integração das boas práticas de mercado e aplicá-las de forma eficiente e eficaz.

Accurate traffic forecasting is crucial for the advancement of smart cities. Although there have been many studies on traffic forecasting, the accurate forecasting of traffic volume is still a challenge. To effectively capture the spatio-temporal correlations of traffic data, a deep learning-based traffic volume forecasting model called the Enhanced Information Graph Recursive Network (EIGRN) is presented in this paper. The model consists of three main parts: a Graph Embedding Adaptive Graph Convolution Network (GE-AGCN), a Modified Gated Recursive Unit (MGRU), and a local information enhancement module. The local information enhancement module is composed of a convolutional neural network (CNN), a transposed convolutional neural network, and an attention mechanism. In the EIGRN, the GE-AGCN is used to capture the spatial correlation of the traffic network by adaptively learning the hidden information of the complex topology, the MGRU is employed to capture the temporal correlation by learning the time change of the traffic volume, and the local information enhancement module is employed to capture the global and local correlations of the traffic volume. The EIGRN was evaluated using the real datasets PEMS-BAY and PeMSD7(M) to assess its predictive performance The results indicate that the forecasting performance of the EIGRN is better than the comparison models.

Reconstructing 3D models from a single image has numerous applications in fields such as VR/AR, medical imaging, and gaming. However, most mesh-based methods are limited by the use of 0-genus initial templates, which makes it difficult to reconstruct 3D meshes with complex topologies. Additionally, existing methods often prioritize reconstructing the overall shape and neglect to study local meshes with varying curvatures, resulting in a lack of correct and detailed local features in the generated meshes. This paper proposes a 3D reconstruction framework that transitions from global to local and incorporates MLP and GCN. The framework introduces a mesh pruning strategy under a 2D hole constraint to restore the correct mesh topology. Moreover, the framework fine-tunes local details by separately learning corresponding mapping functions on high-frequency and low-frequency local extended patches. The experiment with the proposed network on the ShapeNet dataset shows that the network has a CD value of 1.763 and an F-score of 85.40. The results from extensive experiments demonstrate that our proposed method outperforms existing methods in topology correction and local detail reconstruction.

In this work, a group-11 metal nanoparticle-embedded, graphitic carbon nitride-based, resistive-type sensor was developed for room temperature acetone sensing. We synthesized pure and group-11 transition metal (Cu, Ag and Au) nanoparticles embedded in graphitic carbon nitride (gCN) by thermal polycondensation and chemical reduction methods. The synthesized material was characterized using UV/visspectroscopy, FTIRspectroscopy, XRD, HRTEM, FESEM, and EDS techniques. Sensing properties such as response, response/recovery time, selectivity, and stability were calculated. This study confirms that Ag/gCN is the best material for room temperature sensing of acetone compared to Cu/gCN, Au/gCN, and pure gCN. The response of Ag/gCN for 20 ppm acetone at room temperature is 28%. The response/recovery time is 42.05/37.09 s. Moreover, the response of Ag/gCN is stable for 10 days.

As human actions can be characterized by the trajectories of skeleton joints, skeleton-based action recognition techniques have gained increasing attention in the field of intelligent recognition and behavior analysis. With the emergence of large datasets, graph convolutional network (GCN) approaches have been widely applied for skeleton-based action recognition and have achieved remarkable performances. In this paper, a novel GCN-based approach is proposed by introducing a convolutional block attention module (CBAM)-based graph attention block to compute the semantic correlations between any two vertices. By considering semantic correlations, our model can effectively identify the most discriminative vertex connections associated with specific actions, even when the two vertices are physically unconnected. Experimental results demonstrate that the proposed model is effective and outperforms existing methods.

In recent times, there has been a swift advancement in the field of cryptocurrency. The advent of cryptocurrency has provided us with convenience and prosperity, but has also given rise to certain illicit and unlawful activities. Unlike classical currency, cryptocurrency conceals the activities of criminals and exposes their behavioral patterns, allowing us to determine whether present cryptocurrency transactions are legitimate by analyzing their behavioral patterns. There are two issues to consider when determining whether cryptocurrency transactions are legitimate. One is that most cryptocurrency transactions comply with laws and regulations, but only a small portion of them are used for illegal activities, which is related to the sample imbalance problem. The other issue concerns the excessive volume of data, and there are some unknown illegal transactions, so the data set contains an abundance of unlabeled data. As a result, it is critical to accurately distinguish between which transactions among the plethora of cryptocurrency transactions are legitimate and which are illegal. This presents quite a difficult challenge. Consequently, this paper combines mutual information and self-supervised learning to create a self-supervised model on the basis of mutual information that is used to improve the massive amount of untagged data that exist in the data set. Simultaneously, by merging the conventional cross-entropy loss function with mutual information, a novel loss function is created. It is employed to address the issue of sample imbalance in data sets. The F1-Score results obtained from our experimentation demonstrate that the novel loss function in the GCN method improves the performance of cryptocurrency illegal behavior detection by four points compared with the traditional loss function of cross-entropy; use of the self-supervised network that relies on mutual information improves the performance by three points compared with the original GCN method; using both together improves the performance by six points.

Multiple station passenger flow prediction is crucial but challenging for intelligent transportation systems. Recently, deep learning models have been widely applied in multi-station passenger flow prediction. However, flows at the same station in different periods, or different stations in the same period, always present different characteristics. These indicate that globally extracting spatio-temporal features for multi-station passenger flow prediction may only be powerful enough to achieve the excepted performance for some stations. Therefore, a novel two-step multi-station passenger flow prediction model is proposed. First, an unsupervised clustering method for station classification using pure passenger flow is proposed based on the Transformer encoder and K-Means. Two novel evaluation metrics are introduced to verify the effectiveness of the classification results. Then, based on the classification results, a passenger flow prediction model is proposed for every type of station. Residual network (ResNet) and graph convolution network (GCN) are applied for spatial feature extraction, and attention long short-term memory network (AttLSTM) is used for temporal feature extraction. Integrating results for every type of station creates a prediction model for all stations in the network. Experiments are conducted on two real-world ridership datasets. The proposed model performs better than unclassified results in multi-station passenger flow prediction.

We use a graph convolutional neural network (GCN) for regional development prediction with population, railway network density, and road network density of each municipality as development indicators. By structuring the long-term time series data from 2833 municipalities in Switzerland during the years 1910–2000 as graphs over time, the GCN model interprets the indicators as node features and produces an acceptable prediction accuracy on their future values. Moreover, SHapley Additive exPlanations (SHAPs) are used to make the results of this approach explainable. We develop an algorithm to obtain SHAP values for the GCN and a sensitivity indicator to quantify the marginal contributions of the node features. This explainable GCN with SHAP decomposes the indicator into the contribution by the previous status of the municipality itself and the influence from other municipalities. We show that this provides valuable insights into understanding the history of regional development. Specifically, the results demonstrate that the impacts of geographical and economic constraints and urban sprawl on regional development vary significantly between municipalities and that the constraints are more important in the early 20th century. The model is able to include more information and can be applied to other regions and countries., Environment and Planning B: Urban Analytics and City Science, ISSN:2399-8083, ISSN:2399-8091

The online social media ecosystem is becoming more and more confused because of more and more fake information and the social media of malicious users’ fake content; at the same time, unspeakable pain has been brought to mankind. Social robot detection uses supervised classification based on artificial feature extraction. However, user privacy is also involved in using these methods, and the hidden feature information is also ignored, such as semi-supervised algorithms with low utilization rates and graph features. In this work, we symmetrically combine BERT and GCN (Graph Convolutional Network, GCN) and propose a novel model that combines large scale pretraining and transductive learning for social robot detection, BGSRD. BGSRD constructs a heterogeneous graph over the dataset and represents Twitter as nodes using BERT representations. Corpus learning via text graph convolution network is a single text graph, which is mainly built for corpus-based on word co-occurrence and document word relationship. BERT and GCN modules can be jointly trained in BGSRD to achieve the best of merit, training data and unlabeled test data can spread label influence through graph convolution and can be carried out in the large-scale pre-training of massive raw data and the transduction learning of joint learning representation. The experiment shows that a better performance can also be achieved by BGSRD on a wide range of social robot detection datasets.

In this study, both vanadium and copper elements were anchored on graphitic carbon nitride (gCN) (denoted as V/Cu/gCN) via a thermal decomposition process as a novel nanosheet photocatalyst for the removal of monocrotophos (MCP). The prepared nanosheet features were studied by utilizing XRD, UV–Visible absorption spectrometry, PL, FE-SEM, TEM, and XPS techniques. These analytical techniques revealed the successful formation of direct Z-scheme heterojunctions of V/Cu/gCN nanosheets. The dopant materials significantly enhanced the electron–hole separation and enhanced the removal rate of MCP as compared with bulk gCN. The investigation of effective operating conditions confirmed that a higher removal of MCP could be obtained at a doping concentration of 0.3 wt% and a catalytic dosage of 8 mg with 80 min of visible-light irradiation. The generation of various reactive radicals during the degradation process of the photocatalyst was observed using a scavenging treatment process. Additionally, the scavenging process confirmed that e−, OH•, h+, and O2•− played a major role in MCP degradation. The direct Z-scheme dual-heterojunction mechanism, as well as the possible pathway for the fragmentation of MCP by the V/Cu/gCN nanosheet photocatalyst, was derived in detail. This research article provides a novel perspective on the formation of excellent semiconductor photocatalysts, which exhibit enormous potential for environmental treatments.

Temperature is an important part of meteorological factors, which are affected by local and surrounding meteorological factors. Aiming at the problems of significant prediction error and insufficient extraction of spatial features in current temperature prediction research, this research proposes a temperature prediction model based on the Graph Convolutional Network (GCN) and Bidirectional Long Short-Term Memory (BiLSTM) and studies the influence of temperature time-series characteristics, urban spatial location, and other meteorological factors on temperature change in the study area. In this research, multi-meteorological influencing factors and temperature time-series characteristics are used instead of single time-series temperature as influencing factors to improve the time dimension of the input data through time-sliding windows. Meanwhile, considering the influence of meteorological factors in the surrounding area on the temperature change in the study area, we use GCN to extract the urban geospatial location features. The experimental results demonstrate that our model outperforms other models and has the smallest root mean squared error (RMSE) and mean absolute error (MAE) in the following 14-day and multi-region temperature forecasts. It has higher accuracy in areas with stable temperature fluctuations and small temperature differences than in baseline models.

ALSC (Aspect-level Sentiment Classification) is a fine-grained task in the field of NLP (Natural Language Processing) which aims to identify the sentiment toward a given aspect. In addition to exploiting the sentence semantics and syntax, current ALSC methods focus on introducing external knowledge as a supplementary to the sentence information. However, the integration of the three categories of information is still challenging. In this paper, a novel method is devised to effectively combine sufficient semantic and syntactic information as well as use of external knowledge. The proposed model contains a sentence encoder, a semantic learning module, a syntax learning module, a knowledge enhancement module, an information fusion module and a sentiment classifier. The semantic information and syntactic information are respectively extracted via a self-attention network and a graphical convolutional network. Specifically, the KGE (Knowledge Graph Embedding) is employed to enhance the feature representation of the aspect. Then, the attention-based gate mechanism is taken to fuse three types of information. We evaluated the proposed model on three benchmark datasets and the experimental results establish strong evidence of high accuracy.

In recent years, with the rapid development of the Internet and information technology, video websites, shopping websites, and other portals have grown rapidly. However, malicious webpages can disguise themselves as benign websites and steal users’ private information, which seriously threatens network security. Current detection methods for malicious webpages do not fully utilize the syntactic and semantic information in the web source code. In this paper, we propose a GCN-based malicious webpage detection method (GMWD), which constructs a text graph to describe and then a GCN model to learn the syntactic and semantic correlations within and between webpage source codes. We replace word nodes in the text graph with phrase nodes to better maintain the syntactic and semantic integrity of the webpage source code. In addition, we use the URL links appearing in the source code as auxiliary detection information to further improve the detection accuracy. The experiments showed that the proposed method can achieve 99.86% accuracy and a 0.137% false negative rate, achieving a better performance than other related malicious webpage detection methods.

In recent years, great progress has been made in the recognition of skeletal behaviors based on graph convolutional networks (GCNs). In most existing methods, however, the fixed adjacency matrix and fixed graph structure are used for skeleton data feature extraction in the spatial dimension, which usually leads to weak spatial modeling ability, unsatisfactory generalization performance, and an excessive number of model parameters. Most of these methods follow the ST-GCN approach in the temporal dimension, which inevitably leads to a number of non-key frames, increasing the cost of feature extraction and causing the model to be slower in terms of feature extraction and the required computational burden. In this paper, a gated temporally and spatially adaptive graph convolutional network is proposed. On the one hand, a learnable parameter matrix which can adaptively learn the key information of the skeleton data in spatial dimension is added to the graph convolution layer, improving the feature extraction and generalizability of the model and reducing the number of parameters. On the other hand, a gated unit is added to the temporal feature extraction module to alleviate interference from non-critical frames and reduce computational complexity. A channel attention mechanism based on an SE module and a frame attention mechanism are used to enhance the model’s feature extraction ability. To prevent model degradation and ensure more stable training, residual links are added to each feature extraction module. The proposed approach was ultimately able to achieve 0.63% higher accuracy on the X-Sub benchmark with 4.46 M fewer parameters than GAT, one of the best SOTA methods. Inference speed of our model reaches as fast as 86.23 sequences/(second × GPU). Extensive experimental results further validate the effectiveness of our proposed approach on three large-scale datasets, namely, NTU RGB+D 60, NTU RGB+D 120, and Kinetics Skeleton.

Blockchain network architecture is a promising technology for constructing highly secure Internet of Things (IoT) networks. IoT networks typically comprise various sensors and actuators. Blockchain network technology can be applied to secure control robots in smart factories or reliable drone deliveries in smart cities. The wide spread of transactions and shared smart contracts across blockchain networks guarantees ultimate network security. A typical wired blockchain network maintains sufficient redundancy within a stable configuration. However, IoT blockchain networks exhibit unavoidable instability. The dynamic configuration changes caused by flexible node membership make it impossible to achieve the same level of redundancy as a stable network. A trustworthy transaction spreading method provides practical transaction sharing for dynamic IoT networks. We propose a Q-learning framework and a graph convergence network (GCN) to search for the proper spreading path of each transaction. The proposed Q-learning framework determines the next spreading hop using node features. The GCN determines the reliable area based on the Q-learning results. The discovered reliable area guides the proper spreading path of transactions to the destination node. In addition, the proposed trustworthy transaction spreading was implemented over an InterPlanetary File system (IPFS). The IPFS-powered experiments confirmed the practicability of the proposed transaction spreading mechanism.

EEG-based human identification has gained a wide range of attention due to the further increase in demand for security. How to improve the accuracy of the human identification system is an issue worthy of attention. Using more features in the human identification system is a potential solution. However, too many features may cause overfitting, resulting in the decline of system accuracy. In this work, the graph convolutional neural network (GCN) was adopted for classification. Multiple features were combined and utilized as the structure matrix of the GCN. Because of the constant signal matrix, the training parameters would not increase as the structure matrix grows. We evaluated the classification accuracy on a classic public dataset. The results showed that utilizing multiple features of functional connectivity (FC) can improve the accuracy of the identity authentication system, the best results of which are at 98.56%. In addition, our methods showed less sensitivity to channel reduction. The method proposed in this paper combines different FCs and reaches high classification accuracy for unpreprocessed data, which inspires reducing the system cost in the actual human identification system.

© 2022 IEEE.One of the applications of Natural Language Processing (NLP) is to process free text data for extracting information. Information extraction has various forms like Named Entity Recognition (NER) for detecting the named entities in the free text. Biomedical named-entity extraction task is about extracting named entities like drugs, diseases, organs, etc. from texts in medical domain. In our study, we improve commonly used models in this domain, such as biLSTM+CRF model, using transformer based language models like BERT and its domain-specific variant BioBERT in the embedding layer. We conduct several experiments on several different benchmark biomedical datasets using a variety of combination of models and embeddings such as BioBERT+biLSTM+CRF, BERT+biLSTM+CRF, Fasttext+biLSTM+CRF, and Graph Convolutional Networks. Our results show a quite visible, 4% to 13%, improvements when baseline biLSTM+CRF model is initialized with pretrained language models such as BERT and especially with domain specific one like BioBERT on several datasets.

Skeleton-based action recognition is a research hotspot in the field of computer vision. Currently, the mainstream method is based on Graph Convolutional Networks (GCNs). Although there are many advantages of GCNs, GCNs mainly rely on graph topologies to draw dependencies between the joints, which are limited in capturing long-distance dependencies. Meanwhile, Transformer-based methods have been applied to skeleton-based action recognition because they effectively capture long-distance dependencies. However, existing Transformer-based methods lose the inherent connection information of human skeleton joints because they do not yet focus on initial graph structure information. This paper aims to improve the accuracy of skeleton-based action recognition. Therefore, a Graph Skeleton Transformer network (GSTN) for action recognition is proposed, which is based on Transformer architecture to extract global features, while using undirected graph information represented by the symmetric matrix to extract local features. Two encodings are utilized in feature processing to improve joints’ semantic and centrality features. In the process of multi-stream fusion strategies, a grid-search-based method is used to assign weights to each input stream to optimize the fusion results. We tested our method using three action recognition datasets: NTU RGB+D 60, NTU RGB+D 120, and NW-UCLA. The experimental results show that our model’s accuracy is comparable to state-of-the-art approaches.

Aspect-based sentiment analysis (ABSA) plays a significant role in the field of big data and aims to distinguish the sentiment polarity of specific aspects in given sentences; however, the previous works on ABSA had two limitations. They mainly considered semantic features, rather than syntactic dependency features, and paid too much attention to the context words, while ignoring the high-level interaction of multiple representations of aspects themselves. To cope with these limitations, we propose a new method based on the graph convolutional network (GCN) and the multi-head attention mechanism, called the attention interactive encoder network (AIEN). The GCN was used to obtain the syntactic information that has the greatest syntactic impact on the aspect based on the syntax dependency tree. The multi-head attention mechanism can not only obtain the context-aware information of the given aspects, but also the interaction information between multiple representations of the aspect itself. The high-level information generated by the interaction of multi-dimensional features can produce a stronger representation ability for the aspect. Our experiments with the proposed model on five benchmark datasets showed that our model outperformed other works significantly. The experimental results further demonstrated the feasibility and applicability of our proposed model in the ABSA task.

The Covid-19 pandemic is still spreading around the world and seriously imperils humankind's health. This swift spread has caused the public to panic and look to scientists for answers. Fortunately, these scientists already have a wealth of data—the Covid-19 reports that each country releases, reports with valuable spatial-temporal properties. These data point toward some key actions that humans can take in their fight against Covid-19. Technically, the Covid-19 records can be described as sequences, which represent spatial-temporal linkages among the data elements with graph structure. Therefore, we propose a novel framework, the Interaction-Temporal Graph Convolution Network (IT-GCN), to analyze pandemic data. Specifically, IT-GCN introduces ARIMA into GCN to model the data which originate on nodes in a graph, indicating the severity of the pandemic in different cities. Instead of regular spatial topology, we construct the graph nodes with the vectors via ARIMA parameterization to find out the interaction topology underlying in the pandemic data. Experimental results show that IT-GCN is able to capture the comprehensive interaction-temporal topology and achieve well-performed short-term prediction of the Covid-19 daily infected cases in the United States. Our framework outperforms state-of-art baselines in terms of MAE, RMSE and MAPE. We believe that IT-GCN is a valid and reasonable method to forecast the Covid-19 daily infected cases and other related time-series. Moreover, the prediction can assist in improving containment policies.

With the development of big data, large-scale traffic flow forecasting which is a part of smart transportation has become an increasingly important research direction. Accurate and real-time traffic flow prediction is the key and difficult part of the traffic. The complex spatial topological structure and dynamic traffic flow information in urban roads constitute a changeable spatial correlation, and the daily traffic flow cycle and weekly traffic flow cycle constitute a complex time correlation. For the current mainstream model, there are two main limitations: 1. Most of the existing models only focus on time correlation and ignore spatial correlation. 2. Even if the spatial correlation is concerned, the topological relationship between spaces is not fully considered. This paper proposes a new traffic-flow prediction model, which named Principal Spatio-Temporal Graph Convolution Network (PST-GCN) model, which uses a combination of Principal Component Analysis (PCA), Graph Convolution Network (GCN), and Long Short-Term Memory model (LSTM). Specifically, PCA is used to reduce the dimension of data, GCN is used to learn the network topology of urban roads, LSTM is used to capture the time correlation of traffic flow. By comparing the results of different models, the proposed model is better than the current mainstream models.

The development of technology has strongly affected regional urbanization. With development of mobile communication technology, intelligent devices have become increasingly widely used in people’s lives. The application of big data in urban computing is multidimensional; it has been involved in different fields, such as urban planning, network optimization, intelligent transportation, energy consumption and so on. Data analysis becomes particularly important for wireless networks. In this paper, a method for analyzing cellular traffic data was proposed. Firstly, a method to extract trend components, periodic components and essential components from complex traffic time series was proposed. Secondly, we introduced causality data mining. Different from traditional time series causality analysis, the depth of causal mining was increased. We conducted causality verification on different components of time series and the results showed that the causal relationship between base stations is different in trend component, periodic component and essential component in urban wireless network. This is crucial for urban planning and network management. Thirdly, DIC-ST: a spatial temporal time series prediction based on decomposition and integration system with causal structure learning was proposed by combining GCN. Final results showed that the proposed method significantly improves the accuracy of cellular traffic prediction. At the same time, this method can play a crucial role for urban computing in network management, intelligent transportation, base station siting and energy consumption when combined with remote sensing map information.

Human video prediction is still a challenging problem due to the uncertainty of future actions and complexity of frame details. Recent methods tackle this problem in two steps: firstly to forecast future human poses from the initial ones, and then to generate realistic frames conditioned on predicted poses. Following this framework, we propose a novel Graph Convolutional Network (GCN) based pose predictor to comprehensively model human body joints and forcast their positions holistically, and also a stacked generative model with a temporal discriminator to iteratively refine the quality of the generated videos. The GCN based pose predictor fully considers the relationships among body joints and produces more plausible pose predictions. With the guidance of predicted poses, a temporal discriminator encodes temporal information into future frame generation to achieve high-quality results. Furthermore, stacked residual refinement generators make the results more realistic. Extensive experiments on benchmark datasets demonstrate that the proposed method produces better predictions than state-of-the-arts and achieves up to 15% improvement in PSNR.

We propose SiCaGCN, a learning system to predict the similarity of a given software code to a set of codes that are permitted to run on a computational resource, such as a supercomputer or a cloud server. This code characterization allows us to detect abusive codes. Our system relies on a structural analysis of the control-flow graph of the software codes and two different graph similarity measures: Graph Edit Distance (GED) and a singular values based metric. SiCaGCN combines elements of Graph Convolutional Neural Networks (GCN), Capsule networks, attention mechanism, and neural tensor networks. Our experimental results include a study of the trade-offs between the two similarity metrics and two variations of our learning networks, with and without the use of capsules. Our main findings are that the use of capsules reduces mean square error significantly for both similarity metrics. Use of capsules reduces the runtime to calculate the GED while increases the runtime of singular values calculation.

Among the inherent problems in recommendation systems are data sparseness and cold starts; the solutions to which lie in the introduction of knowledge graphs to improve the performance of the recommendation systems. The results in previous research, however, suffer from problems such as data compression, information damage, and insufficient learning. Therefore, a DeepFM Graph Convolutional Network (DFM-GCN) model was proposed to alleviate the above issues. The prediction of the click-through rate (CTR) is critical in recommendation systems where the task is to estimate the probability that a user will click on a recommended item. In many recommendation systems, the goal is to maximize the number of clicks so the items returned to a user can be ranked by an estimated CTR. The DFM-GCN model consists of three parts: the left part DeepFM is used to capture the interactive information between the users and items; the deep neural network is used in the middle to model the left and right parts; and the right one obtains a better item representation vector by the GCN. In an effort to verify the validity and precision of the model built in this research, and based on the public datasets ml1m-kg20m and ml1m-kg1m, a performance comparison experiment was designed. It used multiple comparison models and the MKR and FM_MKR algorithms as well as the DFM-GCN algorithm constructed in this paper. Having achieved a state-of-the-art performance, the experimental results of the AUC and f1 values verified by the CTR as well as the accuracy, recall, and f1 values of the top-k showed that the proposed approach was excellent and more effective when compared with different recommendation algorithms.

Technological advancements have opened up the possibility of digitizing the pathological landscape, enabling deep learning-based methods to analyze digitized tissue samples, i.e., whole slide images (WSIs). Attention has recently shifted toward modeling WSIs as graphs since graph representations can capture dynamic relationships. This thesis investigates different graph construction techniques in conjunction with graph-based deep learning to classify WSIs as breast cancer histological grade 1 versus histological grade 3. To that extent, multiple graph representation techniques and two graph convolutional networks, GCN and GraphSAGE, were utilized. Finally, by evaluating the proposed models on an external test set originating from a separate cohort, it is clear that both models have the capacity for binary histological grading, yielding AUC scores of 0.791 (95% CI 0.756 − 0.825) and 0.838 (95% CI 0.808 − 0.869) for the GCN and GraphSAGE models. Modeling WSIs as graphs is an exciting and emerging field; however, further work is needed to evaluate alternative graph representation techniques and graph convolutional networks. Teknologiska framsteg har öppnat upp möjligheten att digitalisera det patologiska landskapet, och möjliggjort djupinlärningsbaserade metoder att analysera digitala vävnadsprover; whole slide images (WSIs). Uppmärksamhet har skiftats mot modellering av WSIs som grafer, då grafrepresentationer är dynamiska. Den här uppsatsen undersöker diverse tekniker för grafkonstruktion tillsammans med grafbaserad djupinlärning för att klassificera WSIs som histologisk gradering 1 kontra histologisk gradering 3. För detta ändamål användes flertalet olika grafrepresentationer samt två distinkta grafbaserade faltningsnätverk, GCN och GraphSAGE. Slutligen, genom att evaluera de föreslagna modellerna på ett externt test set, härstammande från en separat kohort, så är det tydligt att båda modellerna har kapacitet för binär histologisk gradering, med AUC-värden på 0.791 (95% CI 0.756 − 0.825) samt 0.838 (95% CI 0.808 − 0.869) för GCN och GraphSAGE. Att modellera WSIs som grafer är ett spännande och framväxande område. Det behövs emellertid mer forskning för att evaluera alternativa tekniker för grafrepresentationer samt grafbaserade faltningsnätverk.

Graph Convolutional Networks (GCNs), a natural architecture for modeling graph-structured data, have recently entered the playing field of NLP as sentence encoders over dependency structure. Contemporary setups of semantic role labeling (SRL), neural machine translation (NMT), and event extraction have demonstrated the superiority of GCNs to CNN and RNN encoders, which expect inherently grid-like or sequential inputs. In this thesis, we explore GCN encoders in a fully neural paradigm of AMR parsing, taking Cai and Lam's (2020) state-of-the-art parser as the framework. We hypothesize that GCN encoders are especially well suited for this problem, following the intuition that syntactic structure strongly informs graph-based semantic structure and can be viewed as an intermediate step towards obtaining it from sequential input. Unlike in previous setups, our GCN encoder has to compete with the extremely successful Transformer baseline (the parser's default encoder), and performs only modestly worse while 1) having an order of magnitude fewer parameters, 2) incorporating explicit syntactic information, and 3) not relying on positional encoding. Our extensive experiments around GCN and Transformer (as well as BiLSTM and GAT) encoder configurations shed light on some of the settings that contribute to the successes of the respective architectures. We confirm that the "syntactic GCN" is the best-performing GCN layer, make empirical observations about Transformers and GCNs based on comparative results and dependency tree statistics, and draw parallels between the Transformer and GCN models in terms of their ability to learn relational structure.

Text classification is an essential task in natural language processing. While graph neural networks (GNNs) have successfully been applied to this problem both through graph classification and node classification approaches, their typical applications suffer from several issues. In the graph classification case, common graph construction techniques tend to leave out syntactic information. In the node classification case, most widespread datasets and applications tend to suffer from encoding relatively little information in the chosen node features. Finally, there are great benefits to be gained from combining the two GNN approaches. To tackle these concerns, we propose DepNet, a two-stage framework for text classification using GNN models. In the first stage we replace current graph construction methods by utilizing syntactic dependency parsing in order to include as much syntactic information in the GNN input as possible. In the second stage we combine both graph classification and node classification methods by utilizing the former to produce node embeddings for the latter, maximizing the potential of GNNs for text classification. We find that this technique significantly improves the performance of both graph classification and node classification approaches to text classification.

Detecting irregular or arbitrary shape text in natural scene images is a challenging task that has recently attracted considerable attention from research communities. However, limited by the CNN receptive field, these methods cannot directly capture relations between distant component regions by local convolutional operators. In this paper, we propose a novel method that can effectively and robustly detect irregular text in natural scene images. First, we employ a fully convolutional network architecture based on VGG16_BN to generate text components via the estimated character center points, which can ensure a high text component detection recall rate and fewer noncharacter text components. Second, text line grouping is treated as a problem of inferring the adjacency relations of text components with a graph convolution network (GCN). Finally, to evaluate our algorithm, we compare it with other existing algorithms by performing experiments on three public datasets: ICDAR2013, CTW-1500 and MSRA-TD500. The results show that the proposed method handles irregular scene text well and that it achieves promising results on these three public datasets.

Electric vehicles (EVs) have attracted considerable attention because of their clean and high-energy efficiency. Reasonably planning a charging station network has become a vital issue for the popularization of EVs. Current research on optimizing charging station networks focuses on the role of stations in a local scope. However, spatial features between charging stations are not considered. This paper proposes a charging station selection method based on the graph convolutional network (GCN) and establishes a charging station selection method considering traffic information and investment cost. The method uses the GCN to extract charging stations. The charging demand of each candidate station is calculated through the traffic flow information to optimize the location of charging stations. Finally, the cost of the charging station network is evaluated. A case study on charging station selection shows that the method can solve the EV charging station location problem.

We proposed a real-time detection approach for shop-floor production action, this approach took the sequence data of continuous human skeleton joints sequence as input, reconstructed the Joint Classification-Regression Recurrent Neural Networks (JCR-RNN) based on Temporal Convolution Network (TCN) and Graph Convolution Network (GCN), constructed our Temporal Action Detection Net (TAD-Net), realized real-time shop-floor production action detection

Prediction of complex regional development processes is significant for planners in order to make better decisions on providing infrastructures and services efficiently. Most of the existing prediction models are restricted to a local scale using detailed information or do not focus on long term development. This research therefore proposes a new methodology using a graph convolutional neural network (GCN) for regional development prediction, considering regional development as graph structures. Using long-term time series data from Switzerland during the years 1910 to 2000, it is demonstrated that the model shows better performance than time series analysis models. We apply Shapley Additive Explanations (SHAP) in order to gain insights into the influential factors in different municipalities and periods, and the interpretability of these SHAP values is demonstrated. The model is able to include more information and can be applied to other regions., Arbeitsberichte Verkehrs- und Raumplanung, 1678

Bexarotene (BEX) was approved by the FDA in 1999 for the treatment of cutaneous T-cell lymphoma (CTCL). The poor aqueous solubility causes the low bioavailability of the drug and thereby limits the clinical application. In this study, we developed a GCN-based deep learning model (CocrystalGCN) for in-silico screening of the cocrystals of BEX. The results show that our model obtained high performance relative to baseline models. The top 30 of 109 coformer candidates were scored by CocrystalGCN and then validated experimentally. Finally, cocrystals of BEX-pyrazine, BEX-2,5-dimethylpyrazine, BEX-methyl isonicotinate, and BEX-ethyl isonicotinate were successfully obtained. The crystal structures were determined by single-crystal X-ray diffraction. Powder X-ray diffraction, differential scanning calorimetry, and thermogravimetric analysis were utilized to characterize these multi-component forms. All cocrystals present superior solubility and dissolution over the parent drug. The pharmacokinetic studies show that the plasma exposures (AUC0−8h) of BEX-pyrazine and BEX-2,5-dimethylpyrazine are 1.7 and 1.8 times that of the commercially available BEX powder, respectively. This work sets a good example for integrating virtual prediction and experimental screening to discover the new cocrystals of water-insoluble drugs.

International audience; The rise of digitization of cultural documents offers large-scale contents, opening the road for development of AI systems in order to preserve, search, and deliver cultural heritage. To organize such cultural content also means to classify them, a task that is very familiar to modern computer science. Contextual information is often the key to structure such real world data, and we propose to use it in form of a knowledge graph. Such a knowledge graph, combined with content analysis, enhances the notion of proximity between artworks so it improves the performances in classification tasks. In this paper, we propose a novel use of a knowledge graph, that is constructed on annotated data and pseudo-labeled data. With label propagation, we boost artwork classification by training a model using a graph convolutional network, relying on the relationships between entities of the knowledge graph. Following a transductive learning framework, our experiments show that relying on a knowledge graph modeling the relations between labeled data and unlabeled data allows to achieve state-of-the-art results on multiple classification tasks on a dataset of paintings, and on a dataset of Buddha statues. Additionally, we show state-of-the-art results for the difficult case of dealing with unbalanced data, with the limitation of disregarding classes with extremely low degrees in the knowledge graph.

Background Accurate detection of bleeding events from electronic health records (EHRs) is crucial for identifying and characterizing different common and serious medical problems. To extract such information from EHRs, it is essential to identify the relations between bleeding events and related clinical entities (eg, bleeding anatomic sites and lab tests). With the advent of natural language processing (NLP) and deep learning (DL)-based techniques, many studies have focused on their applicability for various clinical applications. However, no prior work has utilized DL to extract relations between bleeding events and relevant entities. Objective In this study, we aimed to evaluate multiple DL systems on a novel EHR data set for bleeding event–related relation classification. Methods We first expert annotated a new data set of 1046 deidentified EHR notes for bleeding events and their attributes. On this data set, we evaluated three state-of-the-art DL architectures for the bleeding event relation classification task, namely, convolutional neural network (CNN), attention-guided graph convolutional network (AGGCN), and Bidirectional Encoder Representations from Transformers (BERT). We used three BERT-based models, namely, BERT pretrained on biomedical data (BioBERT), BioBERT pretrained on clinical text (Bio+Clinical BERT), and BioBERT pretrained on EHR notes (EhrBERT). Results Our experiments showed that the BERT-based models significantly outperformed the CNN and AGGCN models. Specifically, BioBERT achieved a macro F1 score of 0.842, outperforming both the AGGCN (macro F1 score, 0.828) and CNN models (macro F1 score, 0.763) by 1.4% (P Conclusions In this comprehensive study, we explored and compared different DL systems to classify relations between bleeding events and other medical concepts. On our corpus, BERT-based models outperformed other DL models for identifying the relations of bleeding-related entities. In addition to pretrained contextualized word representation, BERT-based models benefited from the use of target entity representation over traditional sequence representation

At present, there is no uniform definition of annotation schemes for causal extraction, and existing methods are limited by the dependence of relations on long spans, which makes complex sentences such as multi-causal relations and nested causal relations difficult to extract. To solve these problems, a head-to-tail entity annotation method is proposed, which can express the complete semantics of complex causal relations and clearly describe the boundaries of entities. Based on this, a causal model, RPA-GCN (relation position and attention-graph convolutional networks), is constructed, incorporating GAT (graph attention network) and entity location perception. The attention layer is combined with a dependency tree to enhance the model’s ability to perceive relational features, and a bi-directional graph convolutional network is constructed to further capture the deep interaction information between entities and relationships. Finally, the classifier iteratively predicts the relationship of each word pair in the sentence and analyzes all causal pairs in the sentence by a scoring function. Experiments on SemEval 2010 task 8 and the Altlex dataset show that our proposed method has significant advantages in solving complex causal extraction compared to state-of-the-art methods.

現在ディープラーニングの発展により様々な問題が解決されているが，その問題の多くは十分なデータ 量が確保されており，少量学習データでの問題解決は依然として課題となっている．データ量が少ない場合の対 策として，データを増加させるかさ増し手法が用いられる．特に画像分野においては Generative Adversarial Network:GAN を用いた高精度な画像生成手法が注目されている．自然言語の分野においても，GAN を応用し文 章を生成する試みが広く行われているが，十分な精度の文章生成を行うのは難しい．原因の一つとして，自然言語 生成に用いられる GAN では，多くの場合構文構造は加味されていないことがあげられる．そこで，本論文では グラフ構造を畳み込む Graph Convolution を用いて，構文構造を加味した上で文章生成を行う手法を提案する．, 論文

Sign language is the most important way of communication for hearing-impaired people. Research on sign language recognition can help normal people understand sign language. We reviewed the classic methods of sign language recognition, and the recognition accuracy is not high enough because of redundant information, human finger occlusion, motion blurring, the diversified signing styles of different people, and so on. To overcome these shortcomings, we propose a multi-scale and dual sign language recognition Network (SLR-Net) based on a graph convolutional network (GCN). The original input data was RGB videos. We first extracted the skeleton data from them and then used the skeleton data for sign language recognition. SLR-Net is mainly composed of three sub-modules: multi-scale attention network (MSA), multi-scale spatiotemporal attention network (MSSTA) and attention enhanced temporal convolution network (ATCN). MSA allows the GCN to learn the dependencies between long-distance vertices, MSSTA can directly learn the spatiotemporal features, ATCN allows the GCN network to better learn the long temporal dependencies. The three different attention mechanisms, multi-scale attention mechanism, spatiotemporal attention mechanism, and temporal attention mechanism, are proposed to further improve the robustness and accuracy. Besides, a keyframe extraction algorithm is proposed, which can greatly improve efficiency by sacrificing a little accuracy. Experimental results showed that our method can reach 98.08% accuracy rate in the CSL-500 dataset with a 500-word vocabulary. Even on the challenging dataset DEVISIGN-L with a 2000-word vocabulary, it also reached a 64.57% accuracy rate, outperforming other state-of-the-art sign language recognition methods.

Background Diabetic Retinopathy (DR) is the most common and serious microvascular complication in the diabetic population. Using computer-aided diagnosis from the fundus images has become a method of detecting retinal diseases, but the detection of multiple lesions is still a difficult point in current research. Methods This study proposed a multi-label classification method based on the graph convolutional network (GCN), so as to detect 8 types of fundus lesions in color fundus images. We collected 7459 fundus images (1887 left eyes, 1966 right eyes) from 2282 patients (1283 women, 999 men), and labeled 8 types of lesions, laser scars, drusen, cup disc ratio ($$C/D>0.6$$ C / D > 0.6 ), hemorrhages, retinal arteriosclerosis, microaneurysms, hard exudates and soft exudates. We constructed a specialized corpus of the related fundus lesions. A multi-label classification algorithm for fundus images was proposed based on the corpus, and the collected data were trained. Results The average overall F1 Score (OF1) and the average per-class F1 Score (CF1) of the model were 0.808 and 0.792 respectively. The area under the ROC curve (AUC) of our proposed model reached 0.986, 0.954, 0.946, 0.957, 0.952, 0.889, 0.937 and 0.926 for detecting laser scars, drusen, cup disc ratio, hemorrhages, retinal arteriosclerosis, microaneurysms, hard exudates and soft exudates, respectively. Conclusions Our results demonstrated that our proposed model can detect a variety of lesions in the color images of the fundus, which lays a foundation for assisting doctors in diagnosis and makes it possible to carry out rapid and efficient large-scale screening of fundus lesions.

This report is done in collaboration with WirelessCar for the master of science thesis at Halmstad University. Many different parameters influence fuel consumption. The objective of the report is to evaluate if Graph neural networks are a practical model to perform fuel consumption prediction on areas. The model uses a partitioning of geographical locations of trip observations to capture their spatial information. The project also proposes a method to capture the non-stationary behavior of vehicles by defining a vehicle node as a separate entity. The model then captures their different features in a dense layer neural network and utilizes message passing to capture context about neighboring nodes. The model is compared to a baseline neural network with a similar network architecture as the graph neural network. The data is partitioned to define an area with Kmeans and static gridnet partition with and without terrain details. This partition is used to structure a homogeneous graph that is underperforming. The practical drawbacks of the initial homogeneous graph are inspected and addressed to develop a heterogeneous graph that can outperform the neural network baseline.

International audience; Named entity recognition (NER) is an information extraction technique that aims to locate and classify named entities (e.g., organizations, locations,...) within a document into predefined categories. Correctly identifying these phrases plays a significant role in simplifying information access. However, it remains a difficult task because named entities (NEs) have multiple forms and they are context dependent. While the context can be represented by contextual features, the global relations are often misrepresented by those models. In this paper, we propose the combination of contextual features from XLNet and global features from Graph Convolution Network (GCN) to enhance NER performance. Experiments over a widely-used dataset, CoNLL 2003, show the benefits of our strategy, with results competitive with the state of the art (SOTA).

In recent years, there has been a lot of research using reinforcement learning algorithms to train 2-legged robots to move, but there are still many challenges. The authors propose the GCTD3 method, which takes the idea of using Graph Convolutional Networks to represent the kinematic link features of the robot, and combines this with the Twin-Delayed Deep Deterministic Policy Gradient algorithm to train the robot to move. Graph Convolutional Networks are very effective in graph-structured problems such as the connection of the joints of the human-like robots. The GCTD3 method shows better results on the motion trajectories of the bipedal robot joints compared with other reinforcement learning algorithms such as Twin-Delayed Deep Deterministic Policy Gradient, Deep Deterministic Policy Gradient and Soft Actor Critic. This research is implemented on a 2-legged robot model with six independent joint coordinates through the Robot Operating System and Gazebo simulator.

An accurate and reliable forecast for traffic flow is regarded as one of the foundational functions in an intelligent transportation system. In this paper, a new model for traffic flow forecasting, named EnGS-DGR, is designed based on ensemble learning of graph convolutional network (GCN), sequence-to-sequence (Seq2Seq) learning model, and dynamic graph reconfiguration (DGR) algorithm. At the first stage, instead of employing entire nodes in the traffic network, the DGR algorithm is proposed to reconstruct the traffic graph topology consisting of traffic nodes with tight correlation under a specific forecasting interval, where the degree of correlation among the traffic nodes is quantized from the perspective of multi-view clustering. At the second stage, GCN-Seq2Seq integration strategy is introduced to extract the data of the spatio-temporal dependence and forecast traffic flow. We applied the proposed EnGS-DGR to two different datasets from the highways of Los Angeles County and of California’s Bay Area; the simulation results show that the proposed EnGS-DGR is superior to other eight popular models for traffic flow forecasting in terms of three common performance metrics.

Data deduplication techniques removing repeated or redundant data from the storage. In recent days, more data has been generated and stored in the storage environment. More redundant and semantically similar content of the data occupied in the storage environment due to this storage efficiency will be reduced and cost of the storage will be high. To overcome this problem, we proposed a method hybrid bidirectional encoder representation from transformers for text semantics using graph convolutional network hybrid bidirectional encoder representation from transformers (BERT) model for text semantics (HBTSG) word embedding-based deep learning model to identify near duplicates based on the semantic relationship between text documents. In this paper we hybridize the concepts of chunking and semantic analysis. The chunking process is carried out to split the documents into blocks. Next stage we identify the semantic relationship between documents using word embedding techniques. It combines the advantages of the chunking, feature extraction, and semantic relations to provide better results.

© 2020 The Authors. Computer Animation and Virtual Worlds published by John Wiley & Sons, Ltd. Human motion prediction is a fundamental problem in understanding human natural movements. This task is very challenging due to the complex human body constraints and diversity of action types. Due to the human body being a natural graph, graph convolutional network (GCN)-based models perform better than the traditional recurrent neural network (RNN)-based models on modeling the natural spatial and temporal dependencies lying in the motion data. In this paper, we develop the GCN-based models further by adding densely connected links to increase their feature utilizations and address oversmoothing problem. More specifically, the GCN block is used to learn the spatial relationships between the nodes and each feature map of the GCN block propagates directly to every following block as input rather than residual linked. In this way, the spatial dependency of human motion data is exploited more sufficiently and the features of different level of scale are fused more efficiently. Extensive experiments demonstrate our model achieving the state-of-the-art results on CMU dataset.

Background: The LA hybrid lily &lsquo, Aladdin&rsquo, has both excellent traits of Longiflorum hybrids and Asiatic hybrids&mdash, such as big and vivid flower, strong stem, high self-propagation coefficient, and shorter low temperature time required to release bulb dormancy in contrast to Oriental hybrids. A genome-wide transcriptional analysis using transcriptome RNA-Seq was performed in order to explore whether there is a gibberellin floral induction pathway in the LA hybrid lily. Subsequently, gene co-expression network analysis was used to analyze the possible interactions of key candidate genes screened from transcriptome data. At the same time, a series of physiological, biochemical, and cultivation tests were carried out. Results: The content of five endogenous hormones changed sharply in the shoot apex during the treatment of 200 mg/L exogenous gibberellin and the ratio of ABA/GA3 dropped and stayed at a lower level after 4 hours&rsquo, treatment from the higher levels initially, reaching a dynamic balance. In addition, the metabolism of carbohydrates in the bulbs increase during exogenous gibberellin treatment. A total of 124,041 unigenes were obtained by RNA-seq. With the transcriptome analysis, 48,927 unigenes and 48,725 unigenes respectively aligned to the NR database and the Uniprot database. 114,138 unigenes, 25,369 unigenes, and 19,704 unigenes respectively aligned to the COG, GO, and KEGG databases. 2148 differentially expression genes (DEGs) were selected with the indicators RPKM &ge, 0, FDR &le, 0.05 and |log2(ratio)| &ge, 2. The number of the upregulated unigenes was significantly more than the number of the downregulated unigenes. Some MADS-box genes related to flowering transformation&mdash, such as AGL20, SOC1, and CO&mdash, were found to be upregulated. A large number of gibberellin biosynthesis related genes such as GA2ox, GA3ox, GA20ox, Cytochrome P450, CYP81, and gibberellin signal transduction genes such as DELLA, GASA, and GID1 were significantly differentially expressed. The plant hormones related genes such as NCED3 and sugar metabolism related genes such as &alpha, amylase, sucrose synthase hexokinase, and so on were also found expressing differentially. In addition, stress resistance related genes such as LEA1, LEA2, LEA4, serine/threonine protein kinase, LRR receptor-like serine/threonine protein kinase, P34 kinase, histidine kinase 3 and epigenetic related genes in DNA methylation, histone methylation, acetylation, ubiquitination of ribose were also found. Particularly, a large number of transcription factors responsive to the exogenous gibberellin signal including WRKY40, WRKY33, WRKY27, WRKY21, WRKY7, MYB, AP2/EREBP, bHLH, NAC1, NAC2, and NAC11 were found to be specially expressing. 30 gene sequences were selected from a large number of differentially expressed candidate genes for qRT-PCR expression verification (0, 2, 4, 8, and 16 h) and compared with the transcriptome expression levels. Conclusions: 200mg/L exogenous GA3 can successfully break the bulb&rsquo, s dormancy of the LA hybrid lily and significantly accelerated the flowering process, indicating that gibberellin floral induction pathway is present in the LA lily &lsquo, With the GCNs analysis, two second messenger G protein-coupled receptor related genes that respond to gibberellin signals in the cell were discovered. The downstream transport proteins such as AMT, calcium transport ATPase, and plasma membrane ATPase were also discovered participating in GA signal transduction. Transcription factors including WRKY7, NAC2, NAC11, and CBF specially regulated phosphorylation and glycosylation during the ubiquitination degradation process of DELLA proteins. These transcription factors also activated in abscisic acid metabolism. A large number of transcription factors such as WRKY21, WRKY22, NAC1, AP2, EREB1, P450, and CYP81 that both regulate gibberellin signaling and low-temperature signals have also been found. Finally, the molecular mechanism of GA floral induction pathway in the LA hybrid lily &lsquo, was constructed.

Tactile sensors provide useful contact data during the interaction with an object which can be used to accurately learn to determine the stability of a grasp. Most of the works in the literature represented tactile readings as plain feature vectors or matrix-like tactile images, using them to train machine learning models. In this work, we explore an alternative way of exploiting tactile information to predict grasp stability by leveraging graph-like representations of tactile data, which preserve the actual spatial arrangement of the sensor's taxels and their locality. In experimentation, we trained a Graph Neural Network to binary classify grasps as stable or slippery ones. To train such network and prove its predictive capabilities for the problem at hand, we captured a novel dataset of approximately 5000 three-fingered grasps across 41 objects for training and 1000 grasps with 10 unknown objects for testing. Our experiments prove that this novel approach can be effectively used to predict grasp stability. This work has been funded by the Spanish Government with Feder funds (TIN2016-76515-R and DPI2015-68087-R), by two grants for PhD studies (FPU15/04516 and BES-2016-07829), by regional projects (GV/2018/022 and GRE16-19) and by the European Commission (COMMANDIA SOE2/P1/F0638), action supported by Interreg-V Sudoe.

En el presente TFM se estudian y evalúan cuatro diferentes algoritmos de clustering: método coexp (formado porWGCNA y k-means), k-means convencional y dos modelos de mezcla finitos. En primer lugar se implementan todos los modelos de clustering, se busca el número de clusters óptimo en base a diferentes criterios estadísticos como BIC, AIC y el método de codo y por último, las particiones generadas por dichos métodos se visualizan y se comparan entre sí con la ayuda de una serie de métricas (o medidas) de validación externa. Se han usado medidas basadas en el conteo de pares (counting based measures) como el índice de Rand ajustado (Adjusted Rand Index, ARI) y en información teórica (information theoreticbased measures) como la variación de la información normalizada (Normalized Variation of Information, NVI) y distancia de información normalizada (Normalized Distance of Information, NID). En el present TFM s'estudien i avaluen quatre diferents algorismes de clustering: mètode coexp (format porWGCNA i k-means), k-means convencional i dos models de mescla finits. En primer lloc s'implementen tots els models de clustering, es busca el nombre de clústers òptim sobre la base de diferents criteris estadístics com BIC, AIC i el mètode de colze i finalment, les particions generades per aquests mètodes es visualitzen i es comparen entre si amb l'ajuda d'una sèrie de mètriques (o mesures) de validació externa. S'han usat mesures basades en el comptatge de parells (counting based measures) com l'índex de Rand ajustat (Adjusted Rand Index, ARI) i en informació teòrica (information theoreticbased measures) com la variació de la informació normalitzada (Normalized Variation of Information, NVI) i distància d'informació normalitzada (Normalized Distance of Information, NID). Presently TFM, it has been studied and evaluated four different clustering algorithms: coexp method (WGCNA + k-means), k-means conventional and two mixture models. First of all, it will implement all clustering models, search optimum clusters numbers statistical criteria-based as BIC, AIC and elbow method, at last, the final partitions generated by those methods are visualized are compared via external validation metrics (measures). Various clustering comparison measures have been used, counting-based measures as Adjusted Rand index (ARI) and information theoretic-based as Normalized Variation of Information (NVI) and Normalized Distance of Information (NID).