Dynamic Adaptive System Research Articles

Indoor multi-sensor fusion positioning based on federated filtering

In order to meet the requirements of high-precision indoor navigation, a fast point cloud registration method based on Voxel-SIFT (Scale-Invariant Feature Transform) is proposed to improve the registration efficiency of LiDAR (Light Detection and Ranging). Due to the influence of information distribution factors, the dynamic adaptive system cannot be realized in the traditional federated filter. In this case, a hybrid federated filter based on weighted least square method is designed. It is proposed that the main filter in the hybrid federated filter adopts the minimum variance criterion and the optimal estimate of the sub-filter are fused according to the optimal coefficient weighted algorithm. The information distribution factor can be dynamically updated in real time to obtain a global optimal estimate. Finally, the experimental results show that the method can significantly improve the indoor positioning accuracy of mobile robots. The average positioning error is 0.22 m, which is more accurate than the visual odometer method or the LiDAR odometer method alone.

Explicating the Effects of Big Data Analytics Capabilities on Supply Chain Resilience Dimensions: Dynamic Capabilities Approach and Complex Adaptive System Perspective

Explicating the Effects of Big Data Analytics Capabilities on Supply Chain Resilience Dimensions: Dynamic Capabilities Approach and Complex Adaptive System Perspective

Evaluation of an Adaptive Dynamic Compensation System in Cochlear Implant Listeners.

Cochlear implant (CI) sound processing typically uses a front-end automatic gain control (AGC), reducing the acoustic dynamic range (DR) to control the output level and protect the signal processing against large amplitude changes. It can also introduce distortions into the signal and does not allow a direct mapping between acoustic input and electric output. For speech in noise, a reduction in DR can result in lower speech intelligibility due to compressed modulations of speech. This study proposes to implement a CI signal processing scheme consisting of a full acoustic DR with adaptive properties to improve the signal-to-noise ratio and overall speech intelligibility. Measurements based on the Short-Time Objective Intelligibility measure and an electrodogram analysis, as well as behavioral tests in up to 10 CI users, were used to compare performance with a single-channel, dual-loop, front-end AGC and with an adaptive back-end multiband dynamic compensation system (Voice Guard [VG]). Speech intelligibility in quiet and at a +10 dB signal-to-noise ratio was assessed with the Hochmair–Schulz–Moser sentence test. A logatome discrimination task with different consonants was performed in quiet. Speech intelligibility was significantly higher in quiet for VG than for AGC, but intelligibility was similar in noise. Participants obtained significantly better scores with VG than AGC in the logatome discrimination task. The objective measurements predicted significantly better performance estimates for VG. Overall, a dynamic compensation system can outperform a single-stage compression (AGC + linear compression) for speech perception in quiet.

Dynamic Adaptive Network-Based Fuzzy Inference System (D-ANFIS) for the Imputation of Missing Data for Internet of Medical Things Applications

Data delivery and acquisition are the main factors needed for the success of any proposed Internet of Medical Things (IoMT) systems. To achieve good performance and high quality of services in IoMT systems, data acquisition, and delivery should be performed accurately. In general, IoMT systems are usually vulnerable to the collected data with missing value(s) since missing data is the main problem that affects the overall performance of any system. This leads to a reduction in the satisfaction level of end users. Missing data for IoMT systems originates from a number of sources, including bad connections, outside attack, or sensing errors. To obtain a high performance in such systems, missing data should be imputed once occurred. In this paper, a dynamic adaptive network-based fuzzy inference system (D-ANFIS) approach is proposed to impute the missing values in a simple yet accurate manner. The major contribution is to impute the missing value(s) once received by dividing the collected data into two groups: 1) complete dataset (without missing data) and 2) incomplete dataset (with missing data). A holdout method is used to train the D-ANFIS using complete data, while the incomplete dataset is used to impute the missing value(s). Two methods are used to evaluate the final performance of IoMT application: 1) adaptive network-based fuzzy inference system (ANFIS) with genetic algorithm (ANFIS-GA) and 2) ANFIS with particle swarm optimization (ANFIS-PSO). The results show that the performance of IoMT is enhanced 5% using ANFIS-GA and 3% using ANFIS-PSO.

Trust Engineering for Human-AI Teams

Human-AI teaming refers to systems in which humans and artificial intelligence (AI) agents collaborate to provide significant mission performance improvements over that which humans or AI can achieve alone. The goal is faster and more accurate decision-making by integrating the rapid data ingest, learning, and analyses capabilities of AI with the creative problem solving and abstraction capabilities of humans. The purpose of this panel is to discuss research directions in Trust Engineering for building appropriate bi-directional trust between humans and AI. Discussions focus on the challenges in systems that are increasingly complex and work within imperfect information environments. Panelists provide their perspectives on addressing these challenges through concepts such as dynamic relationship management, adaptive systems, co-discovery learning, and algorithmic transparency. Mission scenarios in command and control (C2), piloting, cybersecurity, and criminal intelligence analysis demonstrate the importance of bi-directional trust in human-AI teams.

High-Speed Interval Type-2 Fuzzy System for Dynamic Crossover Parameter Adaptation in Differential Evolution and Its Application to Controller Optimization

The main contribution in this paper is the use of a new type-reduction method to improve the processing speed of Type-2 fuzzy systems for dynamic parameter adaptation in the Differential Evolution algorithm. The proposed type-reduction is an approximation to the Continuous Karnik–Mendel (CEK) method, which is the equivalent to using a traditional Interval Type-2 fuzzy system, but with lower computational cost. The motivation of this work is to verify that the proposed methodology is equivalent in performance to an Interval Type-2 fuzzy system. The first type-reduction method was proposed by Karnik and Mendel (KM), and then was followed by its enhanced version called EKM, and the continuous versions were called CKM and CEKM. In addition, there were variations of these and also other types of variations that eliminate the type-reduction process reducing the computational cost to a Type-1 defuzzification. The concept of approximation to the Continuous Karnik–Mendel (CEK) method is new in the area of metaheuristic algorithms and this is why it is in our interest to work with this methodology. We propose to use this methodology to achieve a dynamic crossover (CR) parameter adaptation in the Differential Evolution algorithm, and the objective is to use the type-reduction process and also provide a continuous solution to the defuzzification. This proposed methodology is applied to a set of mathematical functions and a control problem, for verifying the efficiency of the proposed methodology compared to the original algorithm and other existing methods in the literature.

A high-speed interval type 2 fuzzy system approach for dynamic parameter adaptation in metaheuristics

Fuzzy dynamic adaptation of parameters in meta-heuristic algorithms has recently been shown to provide an improvement in efficiency with respect to meta-heuristic algorithms with static parameters. However, executing a fuzzy inference in each iteration represents an increase in the computational cost, and this is even more critical in the case of using Type-2 Fuzzy Logic systems. On the other hand, fuzzy dynamic adaptation with Type-2 Fuzzy Logic has shown better performance when compared with respect to Type-1 Fuzzy Logic in diverse areas of application; therefore, the goal of this paper is aimed at reducing the computational cost of Type-2 Fuzzy Logic processing for dynamic adaptation of parameters in meta-heuristic algorithms. To reduce the computational cost of processing the Interval Type-2 Fuzzy system for dynamic adaptation of metaheuristic parameters, the use of an approximation to the Continuous Karnik–Mendel method (CEKM) is proposed. The proposed approach provides an analytical approximation to the CEKM method, in this way reducing the computational cost of evaluating the Interval Type-2 Fuzzy System. The performance of the proposed approach was tested with five benchmark functions and with one benchmark control problem. The proposed approach was tested with two different meta-heuristic algorithms, the Differential Evolution algorithm (DE) and the Harmony Search algorithm (HS), in both cases achieving a reduction in the computational cost, while maintaining the performance with respect to the Type-2 Dynamic adaptation of parameters with the conventional type reduction methods.

A Positive Feedback Mechanism of Adaptive Dynamic System

Address dynamic technology can effectively counter reconnaissance of attackers, protect Intranet hosts by hiding their real addresses. This paper combines address dynamics technology with honeypot technology, and provides adaptive strategy guidance for address dynamics by analysing attackers’ scanning tendencies. This paper designs and implements an adaptive dynamic system(ADDS) that disguises IP and MAC adaptively based on SDN. The experimental results show that the MAC and IP adaptively dynamic can achieve the optimal balance between benefits and costs, effectively deceive attackers who are sniffing in the internal network, delay the detection speed, reduce the success rate of the attackers in identifying the host, and interrupt the continuity of network attacks.

When the goal is to generate a series of activities: A self-organized simulated robot arm.

Behavior is characterized by sequences of goal oriented conducts, such as food uptake, socializing and resting. Classically, one would define for each task a corresponding satisfaction level, with the agent engaging, at a given time, in the activity having the lowest satisfaction level. Alternatively, one may consider that the agent follows the overarching objective to generate sequences of distinct activities. To achieve a balanced distribution of activities would then be the primary goal, and not to master a specific task. In this setting the agent would show two types of behaviors, task-oriented and task-searching phases, with the latter interseeding the former. We study the emergence of autonomous task switching for the case of a simulated robot arm. Grasping one of several moving objects corresponds in this setting to a specific activity. Overall, the arm should follow a given object temporarily and then move away, in order to search for a new target and reengage. We show that this behavior can be generated robustly when modeling the arm as an adaptive dynamical system. The dissipation function is in this approach time dependent. The arm is in a dissipative state when searching for a nearby object, dissipating energy on approach. Once close, the dissipation function starts to increase, with the eventual sign change implying that the arm will take up energy and wander off. The resulting explorative state ends when the dissipation function becomes again negative and the arm selects a new target. We believe that our approach may be generalized to generate self-organized sequences of activities in general.

Adaptive dynamic surface longitudinal tracking control of autonomous vehicles

Autonomous vehicles offer the opportunity of significant benefits to social life, such as improving safety, reducing crashes, decreasing fuel consumption and so on. This study presents a novel adaptive dynamic surface longitudinal tracking control strategy for autonomous vehicles to deal with the effects of non-linearities and parametric uncertainties of vehicles. First, a longitudinal vehicle model, which can describe the features of non-linear and external disturbances of autonomous vehicles, is established. Then, an adaptive dynamic surface longitudinal control system is proposed to avoid the explosion of complexity. In addition, an adaptive estimated approach based on neural networks technique is designed to approximate the model uncertainties of autonomous vehicles. The stability of the proposed adaptive control system is discussed by the Lyapunov theory. It has been illustrated for both simulation and experimental tests that the proposed adaptive control system has a remarkable longitudinal tracking performance of the autonomous vehicle.

Artificial Signal Feedback Network Mimicking Cellular Adaptivity.

Inspired by this elegant system of cellular adaptivity, we herein report the rational design of a dynamic artificial adaptive system able to sense and respond to environmental stresses in a unique sense-and-respond mode. Utilizing DNA nanotechnology, we constructed an artificial signal feedback network and anchored it to the surface membrane of a model giant membrane vesicle (GMV) protocell. Such a system would need to both senses incoming stimuli and emit a feedback response to eliminate the stimuli. To accomplish this mechanistically, our DNA-based artificial signal system, hereinafter termed DASsys, was equipped with a DNA trigger-induced DNA polymer formation and dissociation machinery. Thus, through a sequential cascade of stimulus-induced DNA strand displacement, DASsys could effectively sense and respond to incoming stimuli. Then, by eliminating the stimulus, the membrane surface would return to its initial state, realizing the formation of a cyclical feedback mechanism. Overall, our strategy opens up a route to the construction of artificial signaling system capable of maintaining homeostasis in the cellular micromilieu, and addresses important emerging challenges in bioinspired engineering.

Intelligent Adaptive Dynamic Surface Control System With Recurrent Wavelet Elman Neural Networks for DSP-Based Induction Motor Servo Drives

In this paper, an intelligent adaptive dynamic surface control system (IADSCS) with recurrent wavelet Elman neural network (RWENN) for induction motor (IM) servo drive is proposed. The IADSCS comprises a dynamic surface controller (DSC), a RWENN uncertainty observer, and a robust controller. First, a computed torque controller (CTC) is designed to stabilize the IM servo drive. Then, a nonlinear disturbance observer (NDO) is designed to estimate the nonlinear lumped parameter uncertainties (PU) existed in the CTC law. However, the IM servo drive performance is degraded by the NDO error due to the PU. To improve the robustness of the IM servo drive due to external load disturbances and PU, an IADSCS is designed to achieve this purpose. In the IADSCS, the DSC is used to overcome the explosion of the complexity in the backstepping design technique and the RWENN identifier is used to approximate the lumped PU and compounded disturbances. In addition, the robust controller is designed to recover the approximation error of the RWENN. The stability of the closed-loop system is guaranteed by the Lyapunov stability theory. All control algorithms are implemented using dSPACE1104 DSP-based control computer. The simulation and experimental results show the superiority of the proposed IADSCS in external load disturbance suppression and the robustness against PU.

Construction of a dynamic adaptive optics system based on the subspace identification

Adaptive optics (AO) systems have been used in many applications, such as ground-based astronomical telescopes for improving the resolution by counteracting the effects of atmospheric turbulence. However, the traditional AO system model is not good at dealing with noise interference in the closed-loop correction. Therefore, our paper proposes a subspace system identification method based on errors-in-variables to build an accurate dynamic model of the AO system from measurement data with closed-loop system identification. Experimental simulation results show that the root mean square of the residual wavefront is smaller than that of the traditional method, whether photon noise and camera readout noise exist or not. We conclude that the identified model has good accuracy and noise disturbance compensation ability to deal with dynamic wavefront correction compared with the traditional method.

Integrating nutrition services into health care systems platforms: Where are we and where do we go from here.

Integrating maternal-child nutrition into health care services is a desirable but complex task that requires implementation research studies. This special supplement, entitled "How to Strengthen Nutrition into the Health Platform: Programmatic Evidence and Experience from Low- and Middle-Income Countries" presents a collection of mixed-methods research and case studies mostly conducted in sub-Saharan Africa that help us gain a better understanding of the barriers and facilitators for this integration to happen. Collectively, the evidence confirms that integrating nutrition services as part of health care systems and other platforms is feasible, but for that to be successful, there is a need to address strong barriers related to all six key health care systems building blocks identified by the World Health Organization. These include financing, health information systems, health workforce, supplies and technology, governance, and service delivery. Moving forward, it is crucial that more robust implementation science research is conducted within the rough and tumble of real-world programming to better understand how to best integrate and scale up nutrition services across health care systems and other platforms based on dynamic complex adaptive systems frameworks. This research can help better understand how the key health care systems building blocks need to interlock and communicate with each other to improve the policymakers' ability to integrate and scale up nutrition services in a more timely and cost-effective way.

Назви гончарів у середньоанглійській мові: детермінантний аналіз синонімічного ряду

Background: The article deals with the scientific problem of the reconstruction of language evolution in the aspect of historical dynamics of linguistic processes in the semantic system of the English language. The topicality of the research is determined by the need to study the issues of the theories of language development, language changes, modern systemic linguistics and language interference in the parameters of the complex dynamic adaptive system on the basis of the numerical empirical material within the long chronological period in different functions. Purpose: It is relevant to study the development of a particular series of synonyms as a sub-system within the lexical-semantic group in the aspect of determinant analysis. The research methodology is the combination of the traditional linguistic methods together with new systemic functional techniques of the reconstruction of the evolution of semantic system. The aim of the article is to reconstruct the development of the semantic subsystem of the names of potters in Middle English by establishing the specifics of the support of the internal determinant of the semantic group of occupational terms in Middle English at the level of the series of synonyms. The tasks of the research are the following: to make analyses of the etymological composition of the word-stems, functional differentiation and chronological stratification of the first written attestations of the Middle English names of potters. The subject of the study is the etymological composition, functional differentiation and chronological stratification of the Middle English occupational terms. The object of the study is the series of synonyms – the names of potters as a subsystem of the semantic group of Middle English occupational terms. Results: There 8 names of potters in Middle English, forming 0.33% of the total number of Middle English occupational terms. The formation of the series of synonyms under study predominantly belongs to the 12th – 15th centuries, only one word being neologism of the Modern English period. The ratio of English words, loan-blends and borrowings is 55 %:15.5 %:12.5 %. Discussion: The scientific novelty of the research lies in the new functional approach to the history of vocabulary study, as well as the usage of new techniques of linguistic investigation applied to the new object of the study, esp. a particular series of synonyms as a constituent part of the larger systems of language. The results indicate the strict subordination of functioning and development of the series of synonyms of the Middle English names of potters to the language determinant of the semantic group of occupational terms and the English language as a whole. The article draws the prospective of further studies in the field of language evolution of the semantic system in the aspect of determinant analysis of its subsystems.

Synergistic Network Connectivity among Urban Areas Based on Non-Linear Model of Housing Prices Dynamics

Abstract The assumption of a strong positive relationship between the specificity of an urban area and the operation of the housing market, which responds to megatrends in the market environment, has been the foundation of the research concept adopted for this study. The study treats the housing markets as complex, adaptive dynamic systems which develop through synergistic network responses. This paper employs a nonlinear critically-damped harmonic oscillator model and phase diagrams to describe the dynamics of housing prices (in the years 2006-2016) in order to demonstrate the synergistic network connections in selected Polish cities. In another important part of the study, the authors propose to employ non-classical dynamic measures, i.e. the absolute time of delay, relaxation time and a long-term level of equilibrium. The study has shown that network connections are strongly synchronized during periods of housing market instability (2006-2007), whereas the process of unsynchronization is observed during a period of stability (2008-2016). Moreover, phase diagrams have been used to demonstrate the similarity of trends in housing prices as well as the shapes of individual trajectories and the existence of multiple points of quasi-equilibrium.

Power production prediction of wind turbines using a fusion of MLP and ANFIS networks

Access to accurate power production prediction of a wind turbine in future hours enables operators to detect possible underperformance and anomalies in advance. This may enable more proactive and strategic operations optimisation. This study examines common Supervisory Control And Data Acquisition (SCADA) data over a period of 20 months for 21 pitch regulated 2.3 MW turbines. In this study, an algorithm is proposed to impute values of data that are missing, out-of-range, or outliers. It is shown that an appropriate combination of a decision tree and mean value for imputation can improve the data analysis and prediction performance by the creation of a smoother dataset. In addition, principal component analysis is employed to extract parameters with power production influence based on all available signals in the SCADA data. Then, a new data fusion technique is applied, combining dynamic multilayer perceptron (MLP) and adaptive neuro-fuzzy inference system (ANFIS) networks to predict future performance of wind turbines. This prediction is made on a scale of one-hour intervals. This novel combination of feature extraction, imputation, and MLP/ANFIS fusion performs well with favourably low prediction error levels. Thus, such an approach may be a valuable tool for turbine power production prediction.

Design of an Energy Management Strategy for a Parallel Hybrid Electric Bus Based on an IDP-ANFIS Scheme

A critical challenge in the energy management of hybrid electric vehicles is how to intelligently distribute the power between engine and electric motor with a significant reduction in fuel consumption and emissions. In this paper, iterative dynamic programming (IDP) and adaptive neurofuzzy inference system (ANFIS)-based energy management strategy was proposed for a parallel hybrid electric bus. First, IDP was used to obtain the optimal control trajectories for a specific driving cycle. During the iterative process, a modified gear-shifting strategy was introduced to achieve a good tradeoff between the fuel economy and the drivability performance. Next, multi-ANFIS networks were designed and trained to learn the control law from the available optimal trajectories. Finally, the real-time energy management controller based on the IDP-ANFIS was built to coordinate the output of the two power sources, which reduces the fuel consumption and emissions. The simulation and experimental results reveal that the IDP-ANFIS is feasible, and the performance is superior to that of the equivalent consumption minimization strategy and rule-based method.

SMART Education Framework for Adaptation Content Presentation

The rapid growth of the Educational System (ES) has changed traditional learning behavior and presented a new situation to learners. To address the ever increasing needs and challenges associated with ES, a strategic methods and techniques of Adaptive Learning System (ALS) is adapted, which the primary objective is the adaptation of content, presentation, and navigation. In this paper, we suggest a new framework to adapt the Content Presentation to the preferences of learners and physical disability with learners who suffer from the visual and hearing limitations to stimulate the content. This framework is intended to be integrated in Dynamic Adaptive Hypermedia System (DAHS)in a manner that increases the learner’s perceived quality, high level of adaptivity and reliability.

Feasibility of dynamic adaptive passive scattering proton therapy with computed tomography image guidance in the lung.

Hypo-fractionated proton beam therapy (PBT) is an approach that has been increasingly explored over the past decade. It requires high geometric accuracy for targeting of the PBT beams. However, image-guided PBT is currently commonly performed with kV X-ray images of bony anatomy. A dynamic adaptive passive scattering PBT system using computed tomography-based three-dimensional image guidance was developed, and its effectiveness was then evaluated retrospectively in patients with nonsmall cell lung cancer (NSCLC). The dynamic adaptive PBT system consisted of computed tomography-based image registration and proton dose calculation using a simplified Monte Carlo algorithm, with a range adaptation system that could adjust the range shifter thickness to alter the dose distribution. Three patients were retrospectively analyzed. All plans, which each had a total dose of 60 Gy (relative biological effectiveness; RBE), were generated using two fields (Gantry angles: 270 degree and 180 degree) in a passive scattering method. Three dose distributions were generated for each patient according to the following different registrations: bone registration, tumor registration, and tumor registration with range adaptation. The following dosimetric parameters were compared with the original plan: target dose coverage at D95% for the clinical target volume (CTV), homogeneity of D5% to D95% for the CTV, and dose distributions in normal tissue (Dmax of Spinal cord and V20 Gy of lung). For the bone registration method, the average D95% and D5% to D95% for the CTV showed average differences from the original plan of -3.7 ± 4.1 Gy (mean ± 1SD; RBE) and 3.6 ± 3.9 Gy (RBE) respectively. The tumor registration method achieved better coverage than the bone registration method, although the dosimetric parameters for coverage and homogeneity still showed average differences in -2.0 ± 2.3 Gy (RBE) and 1.9 ± 2.2 Gy (RBE) respectively. The range adaptive plan showed comparable coverage and homogeneity [D95%: -1.0 ± 1.3 Gy (RBE) and D5% to D95%: 0.9 ± 1.0 Gy (RBE) on average] to the original plan, as well as demonstrating similar normal tissue sparing. The approach could be completed in less than 10 min, including CT acquisition, image registration, dose recalculation with range optimization, and the operator's visual verification. The tumor dose coverage in patients with NSCLC may deteriorate as a result of respiratory or body movement if daily proton range adaptation is not performed. Our approach may provide higher geometric accuracy for localization of the tumor, and the dynamic range adaptation enables us to achieve the planned dose distribution for hypo-fractionated PBT in the lung.