Adaptive Network Model Research Articles

Skeleton-based action recognition based on multidimensional adaptive dynamic temporal graph convolutional network

Due to the superior capability to process the topology of graphs, graph convolutional networks are gaining popularity in the field of action recognition based on skeleton data. However, it remains difficult to effectively extract features with more distinguishing information for both spatial and temporal dimension. A novel multidimensional adaptive dynamic temporal graph convolutional network (MADT-GCN) model for skeleton-based action recognition is proposed in this work. It consists of two modules, one multidimensional adaptive graph convolutional network (MD-AGCN) module and one dynamic temporal convolutional network (DY-TCN) module. Firstly, MD-AGCN has the ability to adaptively change the graph topology in accordance with varieties of the layers and multidimensional information of spatial, temporal, and channel dimensions that are contained in various action samples to capture the complex connections of each couple of joints. Then, DY-TCN is proposed in order to boost the representation capability to capture expressive temporal features. Moreover, the information of both the joints and bones, together with their motion information, are simultaneously modeled in a multi-stream framework, which shows notable improvements in recognition accuracy. Finally, extensive experiments are conducted on two standard datasets, NTU-RGB+D and NTU-RGB+D 120. The experimental results demonstrate the effectiveness of the proposed method.

The Third Type of Chaos in a System of Adaptively Coupled Phase Oscillators with Higher-Order Interactions

Adaptive network models arise when describing processes in a wide range of fields and are characterized by some specific effects. One of them is mixed dynamics, which is the third type of chaos in addition to the conservative and dissipative types. In this work, we consider a more complex type of connections between network elements—simplex, or higher-order adaptive interactions. Using numerical simulation methods, we analyze various characteristics of mixed dynamics and compare them with the case of pairwise couplings. We found that mixed dynamics in the case of simplex interactions is characterized by a very high similarity of a chaotic attractor to a chaotic repeller, as well as a stronger closeness of the sum of the Lyapunov exponents of the attractor and repeller to zero. This means that in the case of three elements, the conservative properties of the system are more pronounced than in the case of two.

Shuffle Graph Convolutional Network for Skeleton-Based Action Recognition

A shuffle graph convolutional network (Shuffle-GCN) is proposed to recognize human action by analyzing skeleton data. It uses channel split and channel shuffle operations to process multi-feature channels of skeleton data, which reduces the computational cost of graph convolution operation. Compared with the classical two-stream adaptive graph convolutional network model, the proposed method achieves a higher precision with 1/3 of the floating-point operations (FLOPs). Even more, a channel-level topology modeling method is designed to extract more motion information of human skeleton by learning the graph topology from different channels dynamically. The performance of Shuffle-GCN is tested under 56,880 action clips from the NTU RGB+D dataset with the accuracy 96.0% and the computational complexity 12.8 GFLOPs. The proposed method offers feasible solutions for developing practical applications of action recognition.

Combining Ecological and Socio-Environmental Data and Networks to Achieve Sustainability

Combining Ecological and Socio-Environmental Data and Networks to Achieve Sustainability

Intelligent upgrade of waste-activated sludge dewatering process based on artificial neural network model: Core influential factor identification and non-experimental prediction of sludge dewatering performance

Owing to the extremely complex compositions and origins of waste-activated sludge (WAS), the multiple physiochemical properties of WAS have impacts on its dewaterability, and there is a complex interaction relationship among the multiple physiochemical properties, which makes it difficult to identify the controlling factors on WAS dewaterability. Accordingly, there is still no unified certainty in the appropriate ranges of physiochemical properties for the optimal dewaterability of sludge from different sources, resulting in a lack of clear theoretical basis for technical selection and optimization of sludge dewatering processes. The large consumption of conditioning chemicals and low process efficiency stand for the major deficiency of existing sludge conditioning technologies. This study proposed to use a non-linear, adaptive and self-organizing artificial neural network (ANN) model to integrate the multiple physiochemical properties of WAS affecting its dewaterability, and WAS dewatering performance under certain conditioning schemes could be predicated by ANN model with the multiple physiochemical properties and conditioning operation parameters as the input arguments. Thus, the laborious filtration experiments for screening conditioning chemicals could be replaced by the input adjustment of ANN model. Rooted mean squared error (RMSE) of 6.51 and coefficient of determination (R2) of 0.73 confirmed the satisfied stability and accuracy of established ANN model. Furthermore, the predictor-exclusive method revealed that the exclusion of polar interface free energy decreased most, which reflected the importance of surface hydrophilicity reduction in sludge dewaterability improvement. All the contributions presented here were believed to provide an intelligent insight to improve the experience operation status of WAS dewatering process.

Adaptive scalable spatio-temporal graph convolutional network for PM2.5 prediction

PM2.5 Prediction is a complex task of large-scale spatio-temporal analysis, which not only needs comprehension of static geospatial knowledge and relative features but also needs to analyze the real-time situation. This paper discusses the characteristics of the static graph and the dynamic graph in spatio-temporal series tasks. An Adaptive Scalable Spatio-temporal Graph Convolutional Network(ASGCN) model is proposed to predict PM2.5. To capture and analyze the characteristics of the time series period of PM2.5, a time convolution network based on the strategies of inception and gating is proposed and used as a temporal module. A dynamic graph idea is adopted to distinguish the spatio-temporal similarity of different periods. And an adaptive weighted multilayer graph convolution network is used to process static and dynamic graphs, aiming to analyze the spatial relationship of PM2.5 stations. The convolution network with the inception and gating improves the time-series feature capture ability, and adaptive static and dynamic graphs enhance the spatial relationship analysis ability. The temporal and spatial modules of the model are relatively independent, which benefits obtaining the potential information of datasets to improve the prediction accuracy. At the same time, these modules cooperate to make the model adaptable to various data. We choose a great number of comparative models and design a thorough experimental scheme including single-step prediction, multi-step prediction, hyperparameter experiments, and ablation experiments on two real PM2.5 datasets collected in China. Finally, the model achieves performance close to or better than the current state-of-the-art models selected for comparison in prediction tasks.

Adaptive group Lasso neural network models for functions of few variables and time-dependent data

Adaptive group Lasso neural network models for functions of few variables and time-dependent data

Improving generalisability and transferability of machine-learning-based maize yield prediction model through domain adaptation

Modern problems in agricultural management require non-traditional solutions, one of which is by utilizing domain adaptive machine learning models for crop yield prediction which are able to perform reliably in different temporal or spatial domains. However, most studies have focused on the application of domain adaptation to classification tasks such as crop type identification, while the application to regression tasks such as crop yield prediction have been limited. In this study, we explore the generalisability and transferability of ordinary Deep Neural Network (DNN) and domain adaptive neural network models created using three domain adaptation algorithms, namely Discriminative Adversarial Neural Network (DANN), Kullback-Leibler Importance Estimation Procedure (KLIEP), and Regular Transfer Neural Network (RTNN). These three algorithms represent feature-based, instance-based, and parameter-based domain adaptations, respectively. Maize yield records, weather variables, and remotely sensed features from 11 states in the US corn belt acquired in 2006–2020 were compiled and segregated into classes according to temporal (year) and spatial characteristics (annual growing degree days [GDD], vapor pressure deficit [VPD], soil organic content [SOC], and green chlorophyll vegetation index/GCI). We found that models trained using datasets from temperate regions with medium-high GDD and moderate VPD perform well whereas SOC does not significantly affect the generalisability. It is not advisable to train models with datasets constrained by GCI as this feature correlates significantly with the maize yield, and adaptation between two domains that rarely intercept will not work well. We also demonstrate that Kullback-Leibler divergence computed using features from source and target domains can be used to justify the feasibility of domain adaptation. Based on the divergence, a model trained in the US (or another region with sufficient data) is expected to work reliably in other regions through domain adaptation, especially feature-based adaptation.

A novel medical image fusion method based on multi-scale shearing rolling weighted guided image filter.

Medical image fusion is a crucial technology for biomedical diagnoses. However, current fusion methods struggle to balance algorithm design, visual effects, and computational efficiency. To address these challenges, we introduce a novel medical image fusion method based on the multi-scale shearing rolling weighted guided image filter (MSRWGIF). Inspired by the rolling guided filter, we construct the rolling weighted guided image filter (RWGIF) based on the weighted guided image filter. This filter offers progressive smoothing filtering of the image, generating smooth and detailed images. Then, we construct a novel image decomposition tool, MSRWGIF, by replacing non-subsampled shearlet transform's non-sampling pyramid filter with RWGIF to extract richer detailed information. In the first step of our method, we decompose the original images under MSRWGIF to obtain low-frequency subbands (LFS) and high-frequency subbands (HFS). Since LFS contain a large amount of energy-based information, we propose an improved local energy maximum (ILGM) fusion strategy. Meanwhile, HFS employ a fast and efficient parametric adaptive pulse coupled-neural network (AP-PCNN) model to combine more detailed information. Finally, the inverse MSRWGIF is utilized to generate the final fused image from fused LFS and HFS. To test the proposed method, we select multiple medical image sets for experimental simulation and confirm its advantages by combining seven high-quality representative metrics. The simplicity and efficiency of the method are compared with 11 classical fusion methods, illustrating significant improvements in the subjective and objective performance, especially for color medical image fusion.

An Adaptive Neural Network Model for Predicting Breast Cancer Disease in Mapped Nucleotide Sequences

An Adaptive Neural Network Model for Predicting Breast Cancer Disease in Mapped Nucleotide Sequences

A novel fully adaptive neural network modeling and implementation using colored Petri nets

A novel fully adaptive neural network modeling and implementation using colored Petri nets

Modeling Emerging Interpersonal Synchrony and its Related Adaptive Short-Term Affiliation and Long-Term Bonding: A Second-Order Multi-Adaptive Neural Agent Model.

When people interact, their behavior tends to become synchronized, a mutual coordination process that fosters short-term adaptations, like increased affiliation, and long-term adaptations, like increased bonding. This paper addresses for the first time how such short-term and long-term adaptivity induced by synchronization can be modeled computationally by a second-order multi-adaptive neural agent model. It addresses movement, affect and verbal modalities and both intrapersonal synchrony and interpersonal synchrony. The behavior of the introduced neural agent model was evaluated in a simulation paradigm with different stimuli and communication-enabling conditions. Moreover, in this paper, mathematical analysis is also addressed for adaptive network models and their positioning within the landscape of adaptive dynamical systems. The first type of analysis addressed shows that any smooth adaptive dynamical system has a canonical representation by a self-modeling network. This implies theoretically that the self-modeling network format is widely applicable, which also has been found in many practical applications using this approach. Furthermore, stationary point and equilibrium analysis was addressed and applied to the introduced self-modeling network model. It was used to obtain verification of the model providing evidence that the implemented model is correct with respect to its design specifications.

Classification of autism based on short-term spontaneous hemodynamic fluctuations using an adaptive graph neural network

Background:Short-term spontaneous hemodynamic fluctuations were collected by the functional near-infrared spectroscopy (fNIRS) system to classify children with autism spectrum disorder (ASD) and typical development (TD), and to explore abnormalities in the left inferior frontal gyrus in ASD. Methods:Using the fNIRS data of 25 children with ASD and 22 children with TD, a graph neural network combined with the temporal convolution module and the graph convolution module was used, to extract the spatio-temporal features of the data and achieve accurate classification of ASD. Results:The graph neural network was used to obtain a good classification result in the left inferior frontal gyrus, with an accuracy of 97.1%, precision of 95.1%, and specificity of 93.4%. It was found that the 5th channel (which is located in BA 10) and the 8th channel (which is located in BA 47) in the left inferior frontal gyrus were closely correlated with ASD. Comparison with previously used method(s):Compared with the previous deep learning model using the same input, the accuracy of our model has increased by up to 13%, and the correlation between channels in the left inferior frontal gyrus area with the best classification effect was explored through the graph neural network. Conclusion:The adaptive graph neural network (AGNN) model may be able to mine more valuable information to distinguish ASD from TD and in addition, the left inferior frontal gyrus may have greater investigative value.

Adaptive graph convolutional network-based short-term passenger flow prediction for metro

With the development and acceleration of urbanization, urban metro traffic is gradually growing up to a large network, and the structure of topology between stations becomes more complex, which makes it increasingly difficult to capture the spatial dependency. The vertical and horizontal interlacing of multiple lines makes the stations distributed topologically, and the traditional graph convolution is implemented on the adjacency matrix generated based on a priori knowledge, which cannot reflect the actual spatial dependence between stations. To address these problems, this paper proposes an adaptive graph convolutional network model (Adapt-GCN), which replaces the fixed adjacency matrix obtained from a priori knowledge in the traditional GCN with a trainable adaptive adjacency matrix. This can not only effectively adjust the weights of correlations between adjacent stations, but also adaptively capture the spatial dependencies between non-adjacent stations. This paper uses the Shanghai Metro dataset to verify the effectiveness of the model in improving prediction accuracy and reducing training time.

An adaptive endogenous network model for dynamic interbank lending market with central bank

In this paper, an adaptive endogenous model is introduced to explain the formation and evolution mechanism of interbank lending market with central bank. We investigate the evolution of structure of interbank lending market and the impact of structure of bank assets, bank adaptive behaviors, liquidity and dispersion on the resilience of interbank lending market, respectively. Simulation results demonstrate that the structure of the initial interbank lending market has scale-free and small-world features, which keeps in the evolution of the network. Moreover, we find risk gathering requires relatively long time but the outbreak is concentrated and percentage of defaults is a nonmonotonic function of percentage of initial liquid assets. Furthermore, we discover that moderate liquidity hoarding helps to reduce risk contagion effect in the initial stage of contagion while excessive hoarding of liquidity increases the fragility of the network.

DADFN: dynamic adaptive deep fusion network based on imaging genomics for prediction recurrence of lung cancer

Objective. Recently, imaging genomics has increasingly shown great potential for predicting postoperative recurrence of lung cancer patients. However, prediction methods based on imaging genomics have some disadvantages such as small sample size, high-dimensional information redundancy and poor multimodal fusion efficiency. This study aim to develop a new fusion model to overcome these challenges. Approach. In this study, a dynamic adaptive deep fusion network (DADFN) model based on imaging genomics is proposed for predicting recurrence of lung cancer. In this model, the 3D spiral transformation is used to augment the dataset, which better retains the 3D spatial information of the tumor for deep feature extraction. The intersection of genes screened by LASSO, F-test and CHI-2 selection methods is used to eliminate redundant data and retain the most relevant gene features for the gene feature extraction. A dynamic adaptive fusion mechanism based on the cascade idea is proposed, and multiple different types of base classifiers are integrated in each layer, which can fully utilize the correlation and diversity between multimodal information to better fuse deep features, handcrafted features and gene features. Main results. The experimental results show that the DADFN model achieves good performance, and its accuracy and AUC are 0.884 and 0.863, respectively. This indicates that the model is effective in predicting lung cancer recurrence. Significance. The proposed model has the potential to help physicians to stratify the risk of lung cancer patients and can be used to identify patients who may benefit from a personalized treatment option.

A controlled adaptive computational network model of a virtual coach supporting speaking up by healthcare professionals to optimise patient safety

Previous reports show that a substantial proportion of (near) medical errors in the operating theatre is attributable to ineffective communication between healthcare professionals. Speaking up about observed medical errors is a safety behaviour which promotes effective communication between health care professionals, consequently optimising patient care by reducing medical error risk. Speaking up by healthcare professionals (e.g., nurses, residents) remains difficult to execute in practice despite increasing awareness of its importance. Therefore, this paper discourses a computational model concerning the mechanisms known from psychological, observational, and medical literature which underlie the speaking up behaviour of a health care professional. It also addresses how a doctor may respond to the communicated message. Through several scenarios we illustrate what pattern of factors causes a healthcare professional to speak up when witnessing a (near) medical error. We moreover demonstrate how introducing an observant agent can facilitate effective communication and help to ensure patient safety through speaking up when a nurse can not. In conclusion, the current paper introduces an adaptive computational model which predicts speaking up behaviour from the perspective of the speaker and receiver, with the addition of a virtual coach to further optimise patient safety when a patient could be in harm’s way.

A Domain Adaptive Convolutional Neural Network for sEMG-Based Gait Phase Recognition Against to Speed Changes

Gait phase recognition based on surface electromyography (sEMG) signals provides a human–robot interface (HRI) for rehabilitation robots. However, a high-performance deep learning model requires to be calibrated on a large amount of data and frequently recalibrated for new gait speeds, which raises a burden on users. In this article, a domain adaptive convolutional neural network (DACNN) model for sEMG-based gait phase recognition against speed changes is proposed, which only needs to be pretrained on a comfortable gait speed (C.G.) and quick recalibrated on new gait speeds. Specifically, a CNN-based backbone model (BM) is first constructed and pretrained using C.G. data. Then, a domain adaptation (DA) algorithm is applied for recalibration, which allows the BM to learn speed-invariant representation with a small amount of new speed data. Four subjects participated in the experiment and were required to walk at four gait speeds, and three BMs based on AlexNet, LeNet, and fusion-data-CNN (FDCNN) were set as architectural options. Compared with the fine-tuning (FT) and non-recalibration (NoRC) strategies, the results show that the proposed method significantly outperforms both baseline methods. By recalibrating on 6-s data, the proposed method can achieve an accuracy improvement of 1.5%–6.1% compared with FT and 58%–81% compared with NoRC. The average gait phase recognition accuracies are 58.13% for AlexNet, 81.56% for LeNet, and 81.53% for FDCNN, respectively. The average mean absolute errors for gait event identification are 48, 85, and 66 ms, respectively. These results indicate that the DACNN with low recalibration burden can improve the usability of sEMG-based pattern recognition systems.

Adaptive dynamical systems modelling of transformational organizational change with focus on organizational culture and organizational learning

Transformative Organizational Change becomes more and more significant both practically and academically, especially in the context of organizational culture and learning. However computational modeling and a formalization of organizational change and learning processes are still largely unexplored. This paper aims to provide an adaptive network model of transformative organizational change and translate a selection of organizational learning and change processes into computationally modelled processes. Additionally, it sets out to connect the dynamic systems view of organizations to self-modelling network models. The creation of the model and the implemented mechanisms of organizational processes are based on extrapolations of an extensive literature study and grounded in related work in this field, and then applied to a specified hospital-related case scenario in the context of safety culture. The model was evaluated by running several simulations and variations thereof. The results of these were investigated by qualitative analysis and comparison to expected emergent behaviour based on related available academic literature. The simulations performed confirmed the occurrence of an organizational transformational change towards a constant learning culture by offering repeated and effective learning and changes to organizational processes. Observations about various interplays and effects of the mechanism have been made, and they exposed that acceptance of mistakes as a part of learning culture facilitates transformational change and may foster sustainable change in the long run. Further, the model confirmed that the self-modelling network model approach applies to a dynamic systems view of organizations and a systems perspective of organizational change. The created model offers the basis for the further creation of self-modelling network models within the field of transformative organizational change and the translated mechanisms of this model can further be extracted and reused in a forthcoming academic exploration of this field.

Adaptive network modeling of the influence of leadership and communication on learning within an organization

This research addresses the influence of leadership and communication on learning within an organisation by direct mutual interactions in dyads. This is done in combination with multilevel organizational learning as an alternative route, which includes feed forward and feedback learning. The results show that effective communication (triggered by the active team leader, and/or by natural, informal communication), leads to a faster learning process within an organization compared to the longer route via feed forward and feedback formal organisational learning. However, this more direct form of bilateral learning in general may take more of the employee’s time, as a quadratic number of dyadic interactions in general is less efficient than a linear number of interactions needed for feed forward and feedback organisational learning.