General Network Model Research Articles

Predicting chlorophyll-a dynamics in the Ashtamudi estuary using ANN and ANFIS techniques

Excessive nutrients and associated high chlorophyll-a concentration are of growing concern to the public health due to the occurrence of eutrophication in aquatic bodies. Continuous monitoring of chlorophyll-a has limitations, thereby necessitating the development of prediction models. Even though chlorophyll-a prediction models are numerous, they rarely fit into estuarine conditions, which is encountered with dynamic mixing of freshwater and sea water. Thus, the present study identifies the most appropriate driving factors that are relevant for estuarine conditions through chlorophyll-a prediction models developed using Artificial Neural Network and Adaptive Neuro Fuzzy Inference System (ANFIS) approaches in the Ashtamudi estuary, India. Salinity, which is an indirect measure of the estuarine mixing intensity, has been used to replicate the dynamic mixing in the estuary. The results indicate that the model incorporating salinity along with total nitrogen, total phosphorous and turbidity well-predicted chlorophyll-a concentration with a coefficient of determination ranging from 0.73 to 0.99. General Regression Neural Network (GRNN) and ANFIS models outperformed Back Propagation Neural Network (BPNN) and Recurrent Neural Network (RNN) models. Of the various ANFIS models, the ones that used Gaussian and Generalized Bell membership functions were most appropriate for the prediction of chlorophyll-a than the models with triangular and trapezoidal membership functions. The study identified that the models that considered salinity were less sensitive and can be used for modelling chlorophyll-a. The chlorophyll-a was observed to have a direct influence of salinity at salinity values greater than 5‰. The study highlighted that estuarine mixing further enhances the primary productivity through increased penetration of light leading to higher chlorophyll-a concentration. Further the study emplasized that the predictive models are important tools fitting well within estuarine environments due to its replicability.

Fast Selection of Indoor Wireless Transmitter Locations With Generalizable Neural Network Propagation Models

Fast Selection of Indoor Wireless Transmitter Locations With Generalizable Neural Network Propagation Models

Information propagation characteristic by individual hesitant-common trend on weighted network

Within the context of contemporary society, the propagation of information is often subject to the influence of inter-individual connectivity, and individuals may exhibit divergent receptive attitudes towards identical information, a phenomenon denoted as the Hesitant-Common (HECO) trait. In light of this, the present study initially constructs a propagation network model devoid of correlation configurations to investigate the HECO characteristics within weighted social networks. Subsequently, the study employs a theoretical framework for edge partitioning, predicated on edge weights and HECO traits, to quantitatively analyze the mechanisms of individual information dissemination. Theoretical analyses and simulation outcomes consistently demonstrate that an augmentation in the proportion of common individuals facilitates both the diffusion and adoption of information. Concurrently, a phase transition crossover is observed, wherein the growth pattern of the ultimate adoption range, denoted as R(∞), transitions from a first-order discontinuous phase transition to a second-order continuous phase transition as the proportion of common individuals increases. An escalation in the weight distribution exponent is found to enhance information propagation. Furthermore, a reduction in the heterogeneity of degree distribution is conducive to the spread of information. Conversely, an increase in degree distribution heterogeneity and a diminution in the collective decision-making capacity can both exert inhibitory effects on the propagation of information.

Effects of local reduction of endogenous α-synuclein using antisense oligonucleotides on the fibril-induced propagation of pathology through the neural network in wild-type mice

In Parkinson's disease and other synucleinopathies, fibrillar forms of α-synuclein (aSyn) are hypothesized to structurally convert and pathologize endogenous aSyn, which then propagates through the neural connections, forming Lewy pathologies and ultimately causing neurodegeneration. Inoculation of mouse-derived aSyn preformed fibrils (PFFs) into the unilateral striatum of wild-type mice causes widespread aSyn pathologies in the brain through the neural network. Here, we used the local injection of antisense oligonucleotides (ASOs) against Snca mRNA to confine the area of endogenous aSyn protein reduction and not to affect the PFFs properties in this model. We then varied the timing and location of ASOs injection to examine their impact on the initiation and propagation of aSyn pathologies in the whole brain and the therapeutic effect using abnormally-phosphorylated aSyn (pSyn) as an indicator. By injecting ASOs before or 0–14 days after the PFFs were inoculated into the same site in the left striatum, the reduction in endogenous aSyn in the striatum leads to the prevention and inhibition of the regional spread of pSyn pathologies to the whole brain including the contralateral right hemisphere. ASO post-injection inhibited extension from neuritic pathologies to somatic ones. Moreover, injection of ASOs into the right striatum prevented the remote regional spread of pSyn pathologies from the left striatum where PFFs were inoculated and no ASO treatment was conducted. This indicated that the reduction in endogenous aSyn protein levels at the propagation destination site can attenuate pSyn pathologies, even if those at the propagation initiation site are not inhibited, which is consistent with the original concept of prion-like propagation that endogenous aSyn is indispensable for this regional spread. Our results demonstrate the importance of recruiting endogenous aSyn in this neural network propagation model and indicate a possible potential for ASO treatment in synucleinopathies.

Prediction of pressure evolution in non-venting self-pressurized liquid hydrogen tanks using artificial neural network approach

Liquid hydrogen (LH2) is a future energy carrier compared to most conventional fuels. One of the practical bottlenecks in non-venting LH2 tanks is to accurately predict the pressure evolution. Accordingly, many thermal models and correlations were developed; however significant deviations arose due to inherent complex thermal phenomena which have not been addressed yet. A general artificial neural network (ANN) model has been first developed based on 448 datasets amassed from different literature sources to predict the pressure evolution under different heat fluxes, initial filling ratios, as well as tank volumes and shapes. The model has been configured with a typical multi-layer feed-forward structure using a back-propagation learning algorithm and Levenberg-Marquardt training algorithm. For the ANN model, a preliminary optimization process has been conducted for reaching the optimal values for training-to-testing datasets ratio, learning parameters and optimum network structure. Besides, some criteria were set to evaluate the ANN model performance. The ANN model with the configuration of 5-11-11-1 was found to be adopted for such a prediction task. Compared to experimental results and literature models and correlations, the ANN model has been proven to predict the pressure evolution in non-venting self-pressurized LH2 tanks with a mean square error of 1.1779 × 10−5 s2, root mean square error of 0.0034 s, mean absolute error of 6%, mean relative error of 0.2% as well as a satisfactory correlation coefficient of 0.99934 between the network outputs and corresponding targets. This research work provides an effective modeling approach based on artificial neural network to solve one complex problem related with LH2 tanks with fast, accurate and consistent results. Also, the results of the present work can offer some practical guidance for the design of LH2 tanks. Further, the present work gives some insights into new application areas of ANN which will be the emphasis of future research work.

International Comovement in the Global Production Network

Abstract This article provides a general framework to study the role of production networks in international GDP comovement. We first derive an additive decomposition of bilateral GDP comovement into components capturing shock transmission and shock correlation. We quantify this decomposition in a parsimonious multi-country, multi-sector dynamic network propagation model, using data for the G7 countries over the period 1978–2007. Our main finding is that while the network transmission of shocks is quantitatively important, it accounts for a minority of observed comovement under the estimated range of structural elasticities. Contemporaneous responses to correlated shocks in the production network are more successful at generating comovement than intertemporal propagation through capital accumulation. Extensions with multiple shocks, nominal rigidities, and international financial integration leave our main result unchanged. A combination of TFP and labour supply shocks is quantitatively successful at reproducing the observed international business cycle.

Predicting nuclear masses with product-unit networks

Accurate estimation of nuclear masses and their prediction beyond the experimentally explored domains of the nuclear landscape are crucial to an understanding of the fundamental origin of nuclear properties and to many applications of nuclear science, most notably in quantifying the r-process of stellar nucleosynthesis. Neural networks have been applied with some success to the prediction of nuclear masses, but they are known to have shortcomings in application to extrapolation tasks. In this work, we propose and explore a novel type of neural network for mass prediction in which the usual neuron-like processing units are replaced by complex-valued product units that permit multiplicative couplings of inputs to be learned from the input data. This generalized network model is tested on both interpolation and extrapolation data sets drawn from the Atomic Mass Evaluation. Its performance is compared with that of common neural-network architectures, substantiating its suitability for nuclear-mass prediction. Additionally, a prediction-uncertainty measure for such complex-valued networks is proposed that allows identifying nuclides of expected large prediction error. Within and beyond the experimentally explored domain, model predictions are evaluated by computing deviations from the Garvey-Kelson relations.

Remote sensing-enhanced transfer learning approach for agricultural damage and change detection: A deep learning perspective

With the continuous advancement of science and technology, there has been a growing awareness of safety among people worldwide. Natural disasters such as wildfires, earthquakes, and floods pose persistent threats to both lives and property on our planet, which serves as our fundamental habitat. While it is impossible to prevent or entirely avert these calamities, rapid identification of affected areas and prompt damage assessment post-disaster can significantly aid in the formulation of effective rescue strategies, ultimately saving more lives. This article delves into the application of transfer learning in satellite image damage assessment—a methodology that involves transferring previously acquired knowledge to enhance a model's adaptability to new tasks. Given the limited availability of datasets for satellite image analysis, transfer learning proves to be an effective approach. Specifically, the study proposes a transfer learning method based on YOLOv5 for satellite image damage assessment. Initially, a general convolutional neural network model is trained using a substantial dataset of natural images. Subsequently, the early layers of this model are frozen, while the later layers undergo training to adapt to satellite image data. Fine-tuning is then employed to further enhance the overall model performance. The results demonstrate that this approach yields a high accuracy rate in satellite image damage assessment. Moreover, compared to conventional deep learning methods, the proposed method effectively leverages pre-trained models' knowledge, thereby reducing data dependency. Additionally, it displays robust generalization capabilities across diverse tasks and datasets, underscoring its potential for facilitating transfer learning across various domains.

Fuzzy adaptive event-triggered synchronization control mechanism for T–S fuzzy RDNNs under deception attacks

In this paper, a fuzzy-dependent adaptive event-triggered mechanism (FAETM) for synchronizing Takagi–Sugeno (T–S) fuzzy reaction–diffusion neural networks (RDNNs) is developed while considering deception attacks. Firstly, a general neural network model considering both fuzzy logic rules and reaction–diffusion terms is established. Secondly, a FAETM based on an aperiodic sampling period is presented under deception attacks to alleviate the communication burden, wherein the adaptive threshold function is dependent on membership functions. Moreover, a membership-function-dependent asymmetric Lyapunov functional (LF) is constructed, and some positive-definite and symmetric constraints of matrices are removed as a result. Based on the LF method and integral inequality techniques, the H∞ synchronization criteria for the T–S fuzzy RDNNs are presented by linear matrix inequalities (LMIs). Finally, one simulation example is exploited to demonstrate the feasibility and validity of the established method, and the outcome is applied to image secure communication.

Precision positioning based on temperature dependence self-sensing magnetostrictive actuation mechanism

The self-sensing actuator that integrates both actuation and sensing functions is an effective way to simplify the structure of electromechanical systems. This paper proposes a temperature-dependent self-sensing actuation strategy based on a self-sensing giant magnetostrictive actuator (SSGMA) by sensing online stiffness. Utilizing the developed model considering temperature-dependent hysteresis nonlinearity, the self-sensing output characteristics of SSGMA are first evaluated. The self-sensing based control system is then designed in detail. The relationship between the self-sensing signal and the output displacement of SSGMA at different temperatures is constructed by General Regression Neural Network (GRNN) model for fast recognition by the controller. On this basis, a composite control scheme that takes into account rate-dependent asymmetric hysteresis nonlinearities and combines an adaptive feedforward controller with PID feedback controller is proposed for precision actuation of SSGMA. Finally, a temperature-controlled experimental platform is assembled for verification. Experimental results demonstrate that, based on the developed model, the SSGMA is capable of accurate self-sensing output at temperatures of 22 °C, 40 °C, and 70 °C, respectively. The SSGMA with the proposed control method enables the synchronous and precise self-sensing positioning of step and multiple-frequency sinusoidal expectations at different temperatures.

Tongue feature dataset construction and real-time detection.

Tongue diagnosis in traditional Chinese medicine (TCM) provides clinically important, objective evidence from direct observation of specific features that assist with diagnosis. However, the current interpretation of tongue features requires a significant amount of manpower and time. TCM physicians may have different interpretations of features displayed by the same tongue. An automated interpretation system that interprets tongue features would expedite the interpretation process and yield more consistent results. This study applied deep learning visualization to tongue diagnosis. After collecting tongue images and corresponding interpretation reports by TCM physicians in a single teaching hospital, various tongue features such as fissures, tooth marks, and different types of coatings were annotated manually with rectangles. These annotated data and images were used to train a deep learning object detection model. Upon completion of training, the position of each tongue feature was dynamically marked. A large high-quality manually annotated tongue feature dataset was constructed and analyzed. A detection model was trained with average precision (AP) 47.67%, 58.94%, 71.25% and 59.78% for fissures, tooth marks, thick and yellow coatings, respectively. At over 40 frames per second on a NVIDIA GeForce GTX 1060, the model was capable of detecting tongue features from any viewpoint in real time. This study constructed a tongue feature dataset and trained a deep learning object detection model to locate tongue features in real time. The model provided interpretability and intuitiveness that are often lacking in general neural network models and implies good feasibility for clinical application.

Operational transfer path analysis based on neural network

Noise, vibration, and harshness (NVH) issues induced by vibrating source to receivers are sensitive concerns in the automotive industry, significantly determining the product quality. Transfer path analysis (TPA) serves as a crucial tool in addressing these concerns. However, classical and component-based TPA methods necessitate the measurement of all transfer functions associated with the NVH phenomenon, causing high experimental costs; moreover, operational TPA (OTPA) involves matrix inversion processes that may result in the loss of important information. In this study, a neural network-based OTPA (NOTPA) method is proposed that eliminates the need for a matrix inversion process and utilizes only operational measurement. To derive the physical meaning of transmissibility obtained from the trained neural network model, the learning algorithm for NOTPA was developed, and appropriate learning rules were applied to the model. In the general neural network model, training was performed using real-valued parameters. However, the phase of the signal is crucial information in the theoretical formulation of TPA; thus, a complex-valued propagation algorithm was established. Furthermore, an appropriate activation function was chosen to derive the actual transfer mechanism from the trained complex-valued parameters. To experimentally verify the NOTPA method, a testbed resembling automotive vehicle structure was constructed. Estimation of sound pressure and noise contribution analysis were conducted using the NOTPA method and compared with conventional TPA methods. The proposed method demonstrated higher accuracy compared to the conventional OTPA method and successfully identified the main transfer path compared to the classical TPA. Furthermore, by comparing the estimated sound pressure according to the architecture of the model, the consistency of the proposed model was verified.

On propagation in networks, promising models beyond network diffusion to describe degenerative brain diseases and traumatic brain injuries.

Introduction: Connections among neurons form one of the most amazing and effective network in nature. At higher level, also the functional structures of the brain is organized as a network. It is therefore natural to use modern techniques of network analysis to describe the structures of networks in the brain. Many studies have been conducted in this area, showing that the structure of the neuronal network is complex, with a small-world topology, modularity and the presence of hubs. Other studies have been conducted to investigate the dynamical processes occurring in brain networks, analyzing local and large-scale network dynamics. Recently, network diffusion dynamics have been proposed as a model for the progression of brain degenerative diseases and for traumatic brain injuries. Methods: In this paper, the dynamics of network diffusion is re-examined and reaction-diffusion models on networks is introduced in order to better describe the degenerative dynamics in the brain. Results: Numerical simulations of the dynamics of injuries in the brain connectome are presented. Different choices of reaction term and initial condition provide very different phenomenologies, showing how network propagation models are highly flexible. Discussion: The uniqueness of this research lies in the fact that it is the first time that reaction-diffusion dynamics have been applied to the connectome to model the evolution of neurodegenerative diseases or traumatic brain injury. In addition, the generality of these models allows the introduction of non-constant diffusion and different reaction terms with non-constant parameters, allowing a more precise definition of the pathology to be studied.

Pattern dynamics analysis of a reaction–diffusion network propagation model

In this paper, considering the spatial propagation behavior of Internet rumor, we propose a new reaction–diffusion rumor propagation model with time delay in social networks. Based on this, we discuss the stability conditions at the equilibrium point and analyze the Turing instability for the approximation propagation system. Simultaneously, the amplitude equations for the approximation system are derived by multiscale analysis. We use numerical simulation to compare the effect of parameter size, period, and time delay on the patterns. Moreover, we compare the different reactivity of the system in the WS networks and the BA networks. Finally, we plot the corresponding amplitude equations patterns by controlling the parameters and verify the correctness of the theoretical results.

A general dual-pathway network for EEG denoising.

Scalp electroencephalogram (EEG) analysis and interpretation are crucial for tracking and analyzing brain activity. The collected scalp EEG signals, however, are weak and frequently tainted with various sorts of artifacts. The models based on deep learning provide comparable performance with that of traditional techniques. However, current deep learning networks applied to scalp EEG noise reduction are large in scale and suffer from overfitting. Here, we propose a dual-pathway autoencoder modeling framework named DPAE for scalp EEG signal denoising and demonstrate the superiority of the model on multi-layer perceptron (MLP), convolutional neural network (CNN) and recurrent neural network (RNN), respectively. We validate the denoising performance on benchmark scalp EEG artifact datasets. The experimental results show that our model architecture not only significantly reduces the computational effort but also outperforms existing deep learning denoising algorithms in root relative mean square error (RRMSE)metrics, both in the time and frequency domains. The DPAE architecture does not require a priori knowledge of the noise distribution nor is it limited by the network layer structure, which is a general network model oriented toward blind source separation.

Prediction of Converter Tapping Weight Based on Principal Component Analysis–Whale Optimization Algorithm–Backpropagation Algorithm Neural Network Model

Tapping weight is an important parameter in converter blowing process, wherein precisely predicting the quantity of steel required in an alloy baking converter can effectively guide the requirement of alloy ingredients. In practical production, the main approach is empirical estimation, despite its low accuracy. Employing a general neural network model for prediction requires to gather the converter blowing parameters and endpoint temperature measurement sampling parameters as the model inputs. However, this data cannot be obtained until the blowing process reaches its endpoint, rendering it impractical for alloy batching that requires advance preparation for baking. In this study, a principal component analysis–whale optimization algorithm–backpropagation algorithm (PCA–WOA–BP) neural network tapping prediction model is developed using raw material parameters available before alloy baking as input. This model is integrated into the intelligent alloy reduction model of a factory. The model achieves a regression coefficient R2 of 0.823, with 98.53% of furnaces having a prediction error of less than 2 t. The tapping weight of 20 consecutive heats in actual production is predicted; the error range is less than 80% within 1 t, and the converter tapping weight is predicted accurately.

Integrating somatic mutation profiles with structural deep clustering network for metabolic stratification in pancreatic cancer: a comprehensive analysis of prognostic and genomic landscapes.

Pancreatic cancer is a globally recognized highly aggressive malignancy, posing a significant threat to human health and characterized by pronounced heterogeneity. In recent years, researchers have uncovered that the development and progression of cancer are often attributed to the accumulation of somatic mutations within cells. However, cancer somatic mutation data exhibit characteristics such as high dimensionality and sparsity, which pose new challenges in utilizing these data effectively. In this study, we propagated the discrete somatic mutation data of pancreatic cancer through a network propagation model based on protein-protein interaction networks. This resulted in smoothed somatic mutation profile data that incorporate protein network information. Based on this smoothed mutation profile data, we obtained the activity levels of different metabolic pathways in pancreatic cancer patients. Subsequently, using the activity levels of various metabolic pathways in cancer patients, we employed a deep clustering algorithm to establish biologically and clinically relevant metabolic subtypes of pancreatic cancer. Our study holds scientific significance in classifying pancreatic cancer based on somatic mutation data and may provide a crucial theoretical basis for the diagnosis and immunotherapy of pancreatic cancer patients.

Evaluation of satisfaction with and relief vs. workload by ageneral practitioner-centered dementia care project: early information and support in dementia (FIDEM) in Göttingen, Germany

Early information and support in dementia (FIDEM) is across-sectoral, general practitioner-centered network model for the improvement of community-based care of people with dementia and their caregivers by systematically assigning them to non-physician healthcare providers. To describe the implementation of FIDEM in Göttingen, Germany and to exploratorily evaluate satisfaction and relief vs. additional workload. FIDEM was established in Göttingen in 2017. Community-based and district-based networks consisted of medical (general practitioners) and non-medical cooperation partners (occupational therapists, care counselling, other non-medical care providers) and were instructed to efficiently share information. During biannual network meetings from August 2017 to October 2019, aself-developed questionnaire for quality management and evaluation of the aspects of the project described above was filled out by participants attending the meetings. Consecutive recruitment resulted in 7 networks by October 2019, with participation of 29 general practitioners and 46 non-medical care providers, serving as cooperation partners. Quantitative evaluation of 80 FIDEM cooperation partners revealed high satisfaction ratings with all aspects of the model (Mfrom 7.22 to 7.87 out of possible "10"), with partially higher ratings on the part of primary care physicians. Furthermore, all participants reported areduction in workload due to participation, which was significantly higher for primary care physicians across all scales (all p-values < 0.001). FIDEM has been implemented in Göttingen beyond afunded pilot project phase. High satisfaction ratings and considerable relief in workload suggest the continuation of FIDEM along with afull evaluation and, provided positive results, its consolidation of and transfer to other regions in Germany.

Application of General Regression Neural Network Algorithm in Data Mining for Predicting Glass Sales and Inventory Quantity

FF Jaya Glass is a shop that supplies and installs 3 mm to 12 mm glass. The store obtained glass from suppliers to be processed in shape and size according to customers’ order. After completing the customer's order, the shop worker will install the glass at the requested location. Unfortunately, currently stores do not utilize sales data to predict sales either manually or by utilizing technology. As a result, the store cannot predict when the number of glass orders will increase or decrease. In addition, errors often occur when ordering glass for the next period. As a result, stores often run out of glass supplies due to the large number of glass orders so that the achievement of profits is not optimal. This study aims to identify sales variables in glass sales data and build a general regression neural network model as a data mining method. In addition, this study aims to iterate to find the best value in the sales data training process, design and create applications according to user needs, and conduct system validation tests. The general regression neural network method is used to predict sales. The results of this study indicate that the application of general regression neural networks can be used to predict sales. This will make it easier for the store to provide glass supplies in the coming months with an accuracy of 98.1%.

Graph Convolutional-Based Deep Residual Modeling for Rumor Detection on Social Media

The popularity and development of social media have made it more and more convenient to spread rumors, and it has become especially important to detect rumors in massive amounts of information. Most of the traditional rumor detection methods use the rumor content or propagation structure to mine rumor characteristics, ignoring the fusion characteristics of the content and structure and their interaction. Therefore, a novel rumor detection method based on heterogeneous convolutional networks is proposed. First, this paper constructs a heterogeneous map that combines both the rumor content and propagation structure to explore their interaction during rumor propagation and obtain a rumor representation. On this basis, this paper uses a deep residual graph convolutional neural network to construct the content and structure interaction information of the current network propagation model. Finally, this paper uses the Twitter15 and Twitter16 datasets to verify the proposed method. Experimental results show that the proposed method has higher detection accuracy compared to the traditional rumor detection method.