Adaptive Network Model Research Articles

Social percolation revisited: From 2d lattices to adaptive networks

The social percolation model Solomon et al. (2000) considers a 2-dimensional regular lattice. Each site is occupied by an agent with a preference xi sampled from a uniform distribution U[0,1]. Agents transfer the information about the quality q of a movie to their neighbors only if xi≤q. Information percolates through the lattice if q=qc=0.593. – From a network perspective the percolating cluster can be seen as a random–regular network with nc nodes and a mean degree that depends on qc. Preserving these quantities of the random–regular network, a true random network can be generated from the G(n,p) model after determining the link probability p. I then demonstrate how this random network can be transformed into a threshold network, where agents create links dependent on their xi values. Assuming a dynamics of the xi and a mechanism of group formation, I further extend the model toward an adaptive social network model.

Adaptive neuro-fuzzy interface system and neural network modeling for the drying kinetics of instant controlled pressure drop treated parboiled rice.

Hot air drying kinetics of paddy grains during instant controlled pressure drop (ICPD) assisted parboiling process and its impact on the quality and micro-structural properties of milled rice were investigated. Among five mathematical models, Midilli model showed best fitted outcomes for prediction of adequate drying behavior. For the mapping of moisture ratio (MR) as a function of treatment pressure (TP), decompressed state duration (DD) and drying time (DT), artificial neural network (ANN) and adaptive neuro-fuzzy interface system (ANFIS) were applied. ANFIS model (5-5-5) with Gaussian membership function demonstrated best performance when contrasted with 3-5-1 ANN architecture. Effective diffusivity of the drying process varied from 2.8 × 10-09 to 7.0 × 10-09 m2/s with the increase of TP and DD. In comparison of quality parameters with the variation of TP and DD, positive impacts on head rice yield (HRY), redness (a*) and yellowness (b*) values and negative consequences on cooking time (CT) and brightness (L*) value were observed. The outcomes additionally uncovered that parboiled rice obtained at 0.6 MPa TP, indicated best quality in terms of improved process performance, HRY, CT, color and micro-structural properties.

Adaptive spatial scale person reidentification

Person reidentification (ReID) requires the discriminative features of an entire pedestrian image to handle the problems of inaccurate person bounding box detection, background confusion, and occlusion. Many recent person ReID methods have attempted to learn the feature information of an entire pedestrian image through parts feature representations, but it is often too time consuming. Person ReID relies on discriminative pedestrian features, and different spatial scales can distinguish features by differing degrees. We propose an innovative and effective adaptive spatial scale person ReID network model based on the residual neural network (ResNet) of an instance batch normalization. Through experimental visualizations, pedestrian features extracted by ResNet from four layers are analyzed, and two layers with discriminative features are selected. Using an adaptive dimension adjustment module, different spatial scale features are aggregated and merged by the aggregation layer. To effectively learn spatial channel correlations and prevent overfitting, a multilayer distribution normalization processing module is designed to implement end-to-end training and evaluate the person ReID networks. Compared with other methods, this network model showed excellent performance on four public person ReID datasets and is superior to most current methods.

Modeling the development of internal mental models by an adaptive network model

Mental models play a crucial role in individual and organizational learning. The adaptive mental processes involved in the development of mental models are addressed here by integrating psychological and neurological theories on mental models and the learning involved. An adaptive network model has been designed for these processes and used for simulations addressing a case study of learning to drive a car. The developed model may be valuable for different ends, like in improving individual and organizational learning, in designing virtual pedagogical agents, enhancing driver safety, and self-cardriving systems.

Research on Enterprise Financial Customer Classification Method and Preference Based on Intelligent Algorithm

Compared with the past questionnaire survey, this paper applies the intelligent algorithm developed rapidly in recent years to identify the tendency of customers to buy financial products in the market. In addition, for the single state customer classification indicators based on the previous demographic information and action information, it is proposed to combine the action of market activities with demographic information; that is, the static integrated customer classification index is further combined with the improved neural network model to study the classification and preference of enterprise financial customers. Firstly, the enterprise financial customer classification model based on neural network algorithm is studied. Aiming at the shortcomings of easy falling into the local optimal solution of neural network algorithm, slow convergence speed of algorithm, and difficult setting of network structure, combined with the characteristics of genetic algorithm, the concept of adaptive genetic neural network algorithm is proposed. Then, the design of adaptive genetic neural network model is studied. Secondly, combined with the customer data of a financial enterprise and the characteristics of enterprise finance, this paper analyzes the risk influencing factors of enterprise financial customers, analyzes the customer data, evaluates the enterprise financial customers through the adaptive genetic neural network model, and realizes the classification of enterprise financial customers. Through an example, it is proved that the enterprise financial customer classification and preference model based on the adaptive genetic neural network algorithm discussed in this paper has better customer classification accuracy and can provide better method support for enterprise financial customer management.

The Interplay between Craving and Impulse Control: an Adaptive Network Model for Drug Addiction Treatment

This study introduces an adaptive causal network model of the effects of treatment on drug consumption in the case of addiction. Different factors are included that have been found to affect drug consumption and are impacted by addiction treatments. To prove the validity of the model, a number of example scenarios are presented that simulate treatments of different lengths and comprehensiveness. In addition, validation was supported by parameter tuning, and verification was performed by mathematically verifying stationary points for simulations of the model.

A Fault Diagnosis Framework for Centrifugal Pumps by Scalogram-Based Imaging and Deep Learning

Centrifugal pumps are the most vital part of any process industry. A fault in centrifugal pump can affect imperative industrial processes. To ensure reliable operation of the centrifugal pump, this paper proposes a novel automated health state diagnosis framework for centrifugal pump that combines a signal to time-frequency imaging technique and an Adaptive Deep Convolution Neural Network model (ADCNN). First, the vibration signals corresponding to different health conditions of the centrifugal pump are acquired. Vibration signals obtained from the centrifugal pump carry a great deal of information and generally, statistical features are extracted from the vibration signals to retain meaningful fault information. However, these features are either insensitive to weak incipient faults or unsuitable for tracking severe faults, thus, decreasing the fault classification accuracy. To tackle this problem, a signal to time-frequency imaging technique is applied to the pump vibration signals. For this purpose, Continuous Wavelet Transform (CWT) is applied to decompose the vibration signals over different time-frequency scales and extract the pump fault information in both the time and frequency domains. The CWT scales form two-dimensional time-frequency images commonly referred to as scalograms. The CWT scalograms are then converted into grayscale images (SGI). Over the past few decades, CNN models have been established as an effective practice to process images for classification and pattern recognition. Consequently, the extracted CWTSGIs are finally provided as inputs to the proposed ADCNN architecture to achieve feature extraction and classification for centrifugal pump faults. The performance of the proposed diagnostic framework (CWTSGI + ADCNN) is validated with a vibration dataset collected from a testbed specifically designed for centrifugal pump diagnosis. The experimental results suggest that the proposed technique based on CWTSGI and ADCNN outperformed existing methods with an average performance improvement of 4.7 – 15.6%.

On Becoming a Conspiracy Thinker: A Second-Order Adaptive Network Model

This paper explores how becoming a conspiracy thinker can be modeled by an adaptive mental network model based on theories from the empirical literature. A number of simulation scenarios for different types of persons illustrate its usefulness. The model has been verified by mathematical analysis of stationary points and equilibrium values, and validated against data points representing patterns expected from the empirical literature.

An Adaptive BP Neural Network Model for Teaching Quality Evaluation in Colleges and Universities

There is currently no fair, rational, or scientific approach for evaluating college teachers’ teaching abilities. Mathematical methods are frequently used to measure the teaching capacity of college instructors in order to make it more scientific. Traditional statistical analysis evaluation models, fuzzy evaluation methods, grey decision methods, and the analytic hierarchy process (AHP) are only a few examples. Because teacher assessment is a nonlinear problem, even though the preceding methods have produced some positive results, they are vulnerable to some subjectivity. In this paper, the neural network model is incorporated into the adaptive vector and momentum of the modified BP neural network of a gradient descent method to boost the model’s convergence speed, and the model is thoroughly researched to evaluate university teaching quality, and the network structure is omitted to address the complex nonlinear problem of college and university teaching quality assessment. The model’s comprehensive evaluation of teaching activities is then bolstered by the addition of new evaluation indexes to the existing ones.

Allosteric and transport modulation of human concentrative nucleoside transporter 3 at the atomic scale.

Nucleosides are important precursors of nucleotide synthesis in cells, and nucleoside transporters play an important role in many physiological processes by mediating transmembrane transport and absorption. During nucleoside transport, such proteins undergo a significant conformational transition between the outward- and inward-facing states, which leads to alternating access of the substrate-binding site to either side of the membrane. In this work, a variety of molecular simulation methods have been applied to comparatively investigate the motion modes of human concentrative nucleoside transporter 3 (hCNT3) in three states, as well as global and local cavity conformational changes; and finally, a possible elevator-like transport mechanism consistent with experimental data was proposed. The results of the Gaussian network model (GNM) and anisotropic network model (ANM) show that hCNT3 as a whole tends to contract inwards and shift towards a membrane inside, exhibiting an allosteric process that is more energetically favorable than the rigid conversion. To reveal the complete allosteric process of hCNT3 in detail, a series of intermediate conformations were obtained by an adaptive anisotropic network model (aANM). One of the simulated intermediate states is similar to that of a crystal structure, which indicates that the allosteric process is reliable; the state with lower energy is slightly inclined to the inward-facing structure rather than the expected intermediate crystal structure. The final HOLE analysis showed that except for the outward-facing state, the transport channels were gradually enlarged, which was conductive to the directional transport of nucleosides. Our work provides a theoretical basis for the multistep elevator-like transportation mechanism of nucleosides, which helps to further understand the dynamic recognition between nucleoside substrates and hCNT3 as well as the design of nucleoside anticancer drugs.

How Free Will Can Drive Evolution: Adaptive Network Modeling of the Role of Plasticity in Leading Evolutionary Development

This paper contributes an adaptive temporal-causal model describing how the direction of evolutionary processes can be driven by the (free) behavioral choices made by the individuals. The model was designed based on the role of behavioral plasticity as described in the literature. Simulations indeed illustrate the overall process that takes place, and verification by mathematical analysis has been performed which shows that the model does what is expected.

An Integrative Second-Order Adaptive Network Model for the Effect of L. Reuteri Probiotics in the Gut on ASD Symptoms

This paper analyses computationally the effect of the gut microbiome on social interaction deficits related to ASD. An integrative second-order adaptive network model is introduced that integrates the relevant mental and physiological causal pathways and their (second-order) adaptivity.

An adaptive network model covering metacognition to control adaptation for multiple mental models

Learning processes can be described by adaptive mental (or neural) network models. If metacognition is used to regulate learning, the adaptation of the mental network becomes itself adaptive as well: second-order adaptation. In this paper, a second-order adaptive mental network model is introduced for metacognitive regulation of learning processes. The focus is on the role of multiple internal mental models, in particular, the case of visualisation to support learning of numerical or symbolic skills. The second-order adaptive network model is illustrated by a case scenario for the role of visualisation to support learning multiplication at the primary school.

Multiple-scale uncertainty optimization design of hybrid composite structures based on neural network and genetic algorithm

A multiple-scale uncertainty optimization design framework is established for hybrid composite structures, where the stacking sequence and material patches are optimized simultaneously considering micro-scale uncertainty material and strength parameters. Firstly, the uncertainty propagation and performance calculation are implemented based on the finite-element method and classical laminated plate theory, and an adaptive neural network model is constructed to quantify the uncertainties of the natural frequency, reliability index and total cost. Furthermore, the uncertainty optimization design function for the hybrid composite structure is constructed, which maximizes the natural frequency under constraints of the reliability index and total cost, the stacking sequences and material patches are optimized using an adaptive genetic algorithm. In comparison with the determinate optimization results and optimum staking sequence with single materials in two examples with different in-plane loads and cost constraints, the proposed methodology improves the natural frequency by 2.14%–18.61% with the constraints of the reliability index and total cost under multiple scale uncertainties.

A brain-inspired cognitive support model for stress reduction based on an adaptive network model

Stress is often seen as a negative factor which affects every individual’s life quality and decision making. To help avoid or deal with extreme emotions caused by an external stressor, a number of practices have been introduced. In the scope of this paper, we take three kinds of therapy into account: mindfulness, humor, and music therapy. This paper aims to see how various practices help people to cope with stress, using mathematical modelling. We present practical implementations in the form of client–server software, incorporating the computational model which describes therapy effects for overcoming stress based on quantitative neuropsychological research. The underlying network model simulates the elicitation of an extremely stressful emotion due to a strong stress-inducing event as an external stimulus, followed by a therapy practice simulation leading to a reduction of the stress level. Each simulation is based on user input and preferences, integrating a parameter tuning process; it fits a simulation for a particular user. The client–server architecture software which has been designed and developed completely fulfills this objective. It includes server part with embedded MATLAB interaction and API for client communication.

An adaptive network model for pain and pleasure through spicy food and its desensitization

This paper aims to map out the adaptive causal pathways of processes underlying capsaicin consumption and the desensitization process of the TRPV1 receptor as a feedback loop together with pain and pleasure perception. In order to map out these causal capsaicin pathways, adaptive causal network modeling was applied, which is a way of modeling biological, neural, mental and social processes from an adaptive causal modeling perspective.

Narcissism and fame: a complex network model for the adaptive interaction of digital narcissism and online popularity

Social media like Twitter or Instagram play the role of fertile platforms for self-exhibition and allow their users to earn a good repute. People higher in grandiosity share their contents in a charismatic way and as a result, they are successful in gaining attention from others, which may also influence their responses and behaviors. Such attention and repute enable them to be a trendsetter or a socially recognized maven. In this paper, we present a complex adaptive mental network model of a narcissist to see how popularity can adaptively influence his/her behavior. To analyze and to support behavior showed by our model, we used some key performance indicators from the literature to study the popularity and narcissism of 30 Instagram profiles. The results of the—both computational and empirical—study indicate that our presented computational adaptive network model in general shows the behavior found from the empirical data.

Spontaneous symmetry breaking of active phase in coevolving nonlinear voter model.

We study an adaptive network model driven by a nonlinear voter dynamics. Each node in the network represents a voter and can be in one of two states that correspond to different opinions shared by the voters. A voter disagreeing with its neighbor's opinion may either adopt it or rewire its link to another randomly chosen voter with any opinion. The system is studied by means of the pair approximation in which a distinction between the average degrees of nodes in different states is made. This approach allows us to identify two dynamically active phases: a symmetric and an asymmetric one. The asymmetric active phase, in contrast to the symmetric one, is characterized by different numbers of nodes in the opposite states that coexist in the network. The pair approximation predicts the possibility of spontaneous symmetry breaking, which leads to a continuous phase transition between the symmetric and the asymmetric active phases. In this case, the absorbing transition occurs between the asymmetric active and the absorbing phases after the spontaneous symmetry breaking. Discontinuous phase transitions and hysteresis loops between both active phases are also possible. Interestingly, the asymmetric active phase is not displayed by the model where the rewiring occurs only to voters sharing the same opinion, studied by other authors. Our results are backed up by Monte Carlo simulations.

Performance evaluation of shell and tube heat exchanger through ANN and ANFIS model for dye recovery from textile effluents

ABSTRACT Performance of Shell and Tube Heat Exchanger for treatment of textile industry wastewater as a secondary treatment process is reported. An Adaptive Neuro-Fuzzy Inference System and Artificial Neural Network models were used for predicting the accuracy of the process. Condensate flow (m3/hr), feed inlet temperature (°C) and steam flow (kg/cm) for textile effluents were used to predict the condensate temperature (°C). The accuracy of the developed model was validated using Absolute Mean Relative Error, Root Mean Square, and Absolute fraction of variance. The different combinations of input parameters were determined with preceding parameters of the model. Comparison of the models indicated the advantage of ANFIS model over ANN model. Seventh configuration values of ANN reported 0.971%, 1.175%, and 0.9456 of the Absolute Mean Relative Error, Root Mean Square, and Absolute fraction of variance respectively. Similarly, the ANFIS reported 0.381%, 0.532%, and 0.9998 of the Absolute Mean Relative Error, Root Mean Square, and Absolute fraction of variance respectively. ANFIS model was found to be more effective in predicting the condensate temperature with a high Absolute fraction of variance R2 = 0.9998 the results were in line with the experimental data. In the present study the complication of nonlinear process has been resolved using ANFIS modeling technique. The treated water could be recycled using this process. Optimization of the process parameters helps in minimizing water consumption and offers economic benefits for wastewater treatment.

Auto-adaptive learning-based workload forecasting in dynamic cloud environment

To maintain elasticity and scalability of resources at cloud data centers, future workload prediction has become an indispensable requirement. However, there is high variance in resource demands, due to sudden peaks, drop of workload, noise and redundancy in user demands, that hinders accurate workload forecast. This article aims to present workload prediction adaptive neural network model to forecast average workload over consecutive prediction intervals in anticipation. The prediction model adaptively learns traces of workload for particular prediction interval from historical data by applying proposed novel Auto Adaptive Differential Evolution (AADE) algorithm. The two benchmark datasets viz. NASA and Saskatchewan HTTP traces are used for evaluating the performance of the proposed work. Experimental results reveal that AADE-trained neural network outperforms state-of-the-art schemes and achieves accuracy improvement upto 98.9%, 97.4% and 94.8% compared to Average, Backpropagation (BP) and Self adaptive Differential Evolution (SaDE) learning based workload prediction schemes respectively. In addition, the speed of convergence of AADE learning algorithm is observed to be 2-10 times faster than BP and SaDE based forecasting approaches for both datasets.