Self-organizing Research Articles

Self-organizing hypercomplex-valued adaptive network

A novel, unsupervised, artificial intelligence system is presented, whose input signals and trainable weights consist of complex or hypercomplex values. The system uses the effect given by the complex multiplication that the multiplicand is not only scaled but also rotated. The more similar an input signal and the reference signal are, the more likely the input signal belongs to the corresponding class. The data assigned to a class during training is stored on a generic layer as well as on a layer extracting special features of the signal. As a result, the same cluster can hold a general description and the details of the signal. This property is vital for assigning a signal to an existing or a new class. To ensure that only valid new classes are opened, the system determines the variances by comparing each input signal component with the weights and adaptively adjusts its activation and threshold functions for an optimal classification decision. The presented system knows at any time all boundaries of its clusters. Experimentally, it is demonstrated that the system is able to cluster the data of multiple classes autonomously, fast, and with high accuracy.

Generative design for complex floorplans in high-rise residential buildings: A Monte Carlo tree search-based self-organizing multi-agent system (MCTS-MAS) solution

This research aims to develop an innovative generative design algorithm for complex floorplan layout designs in high-rise residential buildings. Unlike conventional methods, which treat such a task as an optimization problem, we approach it as an adaption problem to be solved by combining a self-organized multi-agent system (MAS) and Monte Carlo tree search (MCTS) algorithm. The approach involves two steps. The first is design constraints pre-processing, which comprises (a) initial user input, and (b) pre-processing for initial setup. The second is building plan generation, involving (a) perception, (b) planning, and (c) action modules. Multiple illustrative examples are explored to verify the proposed generative design algorithm in terms of robustness, efficiency, and scale. We discover that the algorithm can handle complex combinations of input constraints (e.g., number of rooms, room areas, adjacency connections, and building boundaries) and generate plausible floorplans in a robust, efficient way that can be scaled up to bigger, more complex floorplan generative design problems. With proper adaptation, the algorithm can potentially be applied to other building types, such as office or hospital buildings.

Segmentation of beach plastic fragments’ contours based on self-organizing map and multi-shape descriptors: A rapid indication of fragmentation and wearing types

Environmental plastic fragments have been verified as byproducts of large plastic and its secondary pollutants including micro and nanoplastics. There are few quantitative studies available, but their contours have values for the weathering mechanisms. We used geometric descriptors, fractal dimensions, and Fourier descriptors to characterize field and artificial polyethylene and polypropylene samples as a means of investigating the contour characteristics. It provides a methodological framework for contour classification. Unsupervised classification was performed using self-organizing neural networks with size-invariance parameters. We revealed the isometric phenomenon of plastic fragments during fragmentation, i.e., that the degree of contour rounding and complexity increase and decrease, respectively, with decreasing fragment size. With an average error rate of 8.9 %, we can distinguish artificial samples from field samples. It was also validated by the difference in Carbonyl Index between groups. We propose a two-stage process for plastic fragmentation and give three types of contour features which were key in the description of fragmented contours, i.e., size, complexity, and rounding. Our work will improve the accuracy of characterizations regarding the weathering and fragmentation processes of certain kinds of plastic fragments. The contour parameters also have the potential to be applied in more realistic scenarios and varied polymers.

Self-organizing broad network with frequency-domain analysis

The broad network (BN) based on random feature extraction has fast computational nature. However, it usually suffers from redundant features due to its randomization in dealing with massive samples, which brings the risk of overfitting. To overcome this problem, a self-organizing BN (SO-BN) is proposed in this article. First, several groups of polynomial-based fuzzy rules (P-FRs) are embedded into BN instead of the original feature nodes. Then, P-FR with the form of approximated bell functions has the capability to cope with the uncertainties of feature extraction. Second, a frequency domain parameter calculation algorithm is presented to update the parameters of P-FRs in SO-BN. Different from traditional randomization, P-FRs are shaped with frequency-domain analysis for achieving the representative features of samples. Third, an efficient self-organizing mechanism is built to adjust the structure of the enhancement layer dynamically. Then, the enhancement layer can be expanded and pruned rapidly to reduce the redundant feature as well as improve the performance of SO-BN. Finally, the proposed SO-BN is tested on two benchmark datasets and three real-world engineering applications, especially the prediction of sunspot numbers, electrical output and total phosphorus concentration. The results indicate that SO-BN can achieve superior prediction performance than other models.

Programming Fluid Motion Using Multi-Enzyme Micropump Systems.

In the presence of appropriate substrates, surface-anchored enzymes can act as pumps and propel fluid through microchambers. Understanding the dynamic interplay between catalytic reactions and fluid flow is vital to enhancing the accuracy and utility of flow technology. Through a combination of experimental observations and numerical modeling, we show that coupled enzyme pumps can exhibit flow enhancement, flow suppression, and changes in the directionality (reversal) of the fluid motion. The pumps' ability to regulate the flow path is due to the reaction selectivity of the enzymes; the resultant fluid motion is only triggered by the presence of certain reactants. Hence, the reactants and the sequence in which they are present in the solution and the layout of the enzyme-attached patches form an "instruction set" that guides the flowing solution to specific sites in the system. Such systems can operate as sensors that indicate concentrations of reactants through measurement of the trajectory along which the flow demonstrates a maximal speed. The performed simulations suggest that the solutal buoyancy mechanism causes fluid motion and is responsible for all of the observed effects. More broadly, our studies provide a new route for forming self-organizing flow systems that can yield fundamental insight into nonequilibrium, dynamical systems.

Self-organized free-flight arrival for urban air mobility

Urban air mobility is an innovative mode of transportation in which electric vertical takeoff and landing (eVTOL) vehicles operate between nodes called vertiports. We outline a self-organized vertiport arrival system based on deep reinforcement learning. The airspace around the vertiport is assumed to be circular, and the vehicles can freely operate inside. Each aircraft is considered an individual agent and follows a shared policy, resulting in decentralized actions that are based on local information. We investigate the development of the reinforcement learning policy during training and illustrate how the algorithm moves from suboptimal local holding patterns to a safe and efficient final policy. The latter is validated in simulation-based scenarios, including robustness analyses against sensor noise and a changing distribution of inbound traffic. Lastly, we deploy the final policy on small-scale unmanned aerial vehicles to showcase its real-world usability.

Retraction Note: Simple hemogram to support the decision-making of COVID-19 diagnosis using clusters analysis with self-organizing maps neural network

Retraction Note: Simple hemogram to support the decision-making of COVID-19 diagnosis using clusters analysis with self-organizing maps neural network

Self-organizing interval type-2 function-link fuzzy neural network control for uncertain manipulators under saturation: A predefined-time sliding-mode approach

Robotic manipulators have extensive applications in academic and industrial fields such as grabbing, welding, and machining. Nowadays, better tracking performance and faster transient response have been the fundamental demands in the field of manipulator control. However, robotic manipulators suffer from uncertainties due to various factors in real-world environments. Therefore, achieving satisfactory tracking performance for the manipulator in the presence of uncertainties is a pressing problem. Moreover, most existing control schemes struggle to determine the convergence time of the whole system and rely on specifically designed parameters via experience and prior knowledge, which leads to poor transferability and generalization. To address the abovementioned issues, a predefined-time controller based on a self-organizing interval type-2 function-link fuzzy neural network (IT2FLFNN) is proposed in this paper. Different from most existing fuzzy neural network (FNN) based control schemes, the proposed network starts from an empty rule base and it is constructed by a self-organizing mechanism during the online control process, which provides greater flexibility in terms of network structure and input partition. Also, a function-link network (FLN) is integrated into IT2FLFNN to enhance its convergence speed and rejection of uncertainties. Furthermore, to ensure the predefined-time convergence, a predefined-time sliding-mode control part is merged into the control framework and online learning laws for IT2FLFNN are established via the Lyapunov stability analysis. Finally, a comparative simulation and an experiment demonstrate the superiority of the proposed IT2FLFNN control scheme.

A framework for extending co-creative communication models to sustainability research.

The UN Sustainable Development Goals (SDGs) present a challenge due to their potential for conflicting objectives, which hinders their effective implementation. In order to address the complexity of sustainability issues, a framework capable of capturing the specificity of diverse sustainability issues while offering a common methodology applicable across contexts is required. Co-creative communication can be regarded as a key source of uncertainty within functional systems, as it can be instrumental in realizing and sustaining sustainability. In this regard, the studies in Constructive approaches to Co-creative Communication (CCC), particularly those employing artificial intelligence (AI) methodologies such as computational social science and innovation studies, hold significant value for both theoretical and applied sustainability research. However, existing CCC frameworks cannot be directly applied to sustainability research. This work bridges this gap by proposing a framework that outlines a general approach to establishing formalized definitions of sustainability from the lens of communication. This approach enables the direct application of CCC models to sustainability studies. The framework is based on systems theory and the methodologies of artificial intelligence, including computational/symbolic modeling and formal methods. This framework emphasizes the social function of co-creative communication and the interaction between the innovation process and the sustainability of the system. It can be concluded that the application of our framework enables the achievements of CCC to be directly applied to sustainability research. Researchers from different disciplines are therefore able to establish their own specific definitions of sustainability, which are tailored to their particular concerns. Our framework lays the groundwork for future sustainability studies that employs CCC, facilitating the integration of CCC insights into sustainability research and application. The outcomes of computational creativity research based on AI technologies, such as distributed artificial intelligence and self-organizing networks, can deepen the understanding of sustainability mechanisms and drive their practical applications. Furthermore, the functional role of co-creative communication in societal sustainability proposed in this work offers a novel perspective for future discussions on the evolutionary adaptation of co-creative communication.

Health State Prediction Method Based on Multi-Featured Parameter Information Fusion

The prediction of the health status of critical components is an important influence in making accurate maintenance decisions for rotating equipment. Since vibration signals contain a large amount of fault information, they can more accurately describe the health status of critical components. Therefore, it is widely used in the field of rotating equipment health state prediction. However, there are two major problems in predicting the health status of key components based on vibration signals: (1) The working environment of rotating equipment is harsh, and if only one feature in the time or frequency domain is selected for fault analysis, it will be susceptible to harsh operating environments and cannot completely reflect the fault information. (2) The vibration signals are unlabeled time series data, which are difficult to accurately convert into the health status of key components. In order to solve the above problems, this paper proposes a combined prediction model combining a bidirectional long- and short-term memory network (BiLSTM), a self-organizing neural network (SOM) and particle swarm optimization (PSO). Firstly, the SOM is utilized to fuse the fault characteristics of multiple vibration signals of key components to obtain an indicator (HI) that can reflect the health status of rotating equipment and to also compensate for the vulnerability of single signal characteristics in the time or frequency domain to environmental influences. Secondly, the K-means clustering method is employed to cluster the health indicators and determine the health state, which solves the problem of determining the health of a component from unsupervised vibration signal data which is quite difficult. Finally, the particle swarm optimized BiLSTM model is used to predict the health state of key components and the bearing dataset from the IEEE PHM 2012 Data Challenge verifies the method’s effectiveness and validity.

Degradation modeling and remaining life prediction for a multi-component system under triple uncertainties

As equipment systems are gradually moving toward large-scale and complex that comprise multi-components, the correlation between components significantly impacts the system’s degradation. Meanwhile, the system degradation process is subject to aleatory uncertainty due to inherent fluctuations, epistemic uncertainty since insufficient information, and measurement uncertainty affected by measurement noise. In this paper, a system-level RUL prediction method based on deep belief network, self-organizing map neural network and uncertain random process is proposed by combining the advantages of deep learning in extracting degraded features with the advantages of statistical-based models in quantifying uncertainty. Firstly, the monitoring variables that characterize the equipment degradation trend are selected based on multi-sensor monitoring information of a single component. Deep belief network is utilized to extract component-level deep hidden degradation features. Subsequently, a system-level health index construction method combining mutual information and self-organizing map neural network is proposed according to correlation analysis between components. Finally, a health index evolution model is constructed to predict system RUL by integrating the advantages of the multi-phase degradation model based on uncertain random processes quantifying multiple uncertainties. The superiority of the proposed method is verified through the C-MAPSS dataset provided by NASA.

An improved self-organizing mapping neural network and its application in fault diagnosis of CNC machine tool servo drive system

An improved self-organizing mapping neural network and its application in fault diagnosis of CNC machine tool servo drive system

Drone inspection path planning with self-organizing neural network of elastic Hebbian learning rule

Abstract As the scale of the power grid continues to expand, inspection scenarios become increasingly complex, and inspection and maintenance work in the power industry faces huge challenges. The traditional manual inspection mode has problems such as high cost, low efficiency, and poor safety. Using electric drones to inspect all equipment nodes in the area can effectively reduce operation and maintenance costs and ensure personnel safety. As a key technology to realize autonomous power inspection, UAV path planning needs to overcome difficulties such as long solution time and intersection of inspection paths. Therefore, this article conducts research on UAV path planning algorithms for large-scale power inspections, which is of great significance to improving the efficiency of power inspections. To avoid the occurrence of path intersections and improve the path planning effect, this paper uses the convex hull property in graph theory to design elastic Hebbian learning rules and proposes a self-organizing neural network algorithm based on elastic Hebbian learning rules.

Scale-invariant Features of X-Ray Bursts from SGR J1935+2154 Detected by Insight-HXMT

In this work, we restudy the scale-invariant features of X-ray bursts from the soft gamma repeater (SGR) J1935+2154. To compare with previous studies, we choose 75 bursts from a dedicated 33 days-long observation carried out by Insight-HXMT. We investigate the size difference distributions of net counts, duration, and waiting time. It is found that the cumulative difference distributions of net counts and duration follow the q-Gaussian models with approximately steady q-values, confirming that the scale-invariant features exist in X-ray bursts of SGR J1935+2154. Regarding the varying results of waiting time reported by Sang & Lin and Wei et al, we find that the distributions of waiting time can be well described by the q-Gaussian model. Furthermore, the q-values of waiting time remain relatively stable at the 3σ confidence level, corroborating the scale invariance in the X-ray bursts. Additionally, we note that there is no significant q-value evolution across three Insight-HXMT telescopes. These findings statistically affirm that the X-ray bursts from SGR J1935+2154 can be attributed to an fractal-diffusive self-organized criticality system with a plausible Euclidean spatial dimension S = 3, implying that X-ray bursts from SGR J1935+2154 and associated astrophysical phenomena may share a similar magnetically dominated stochastic process.

Backpressure Learning-Based Data Transmission Reliability-Aware Self-Organizing Networking for Power Line Communication in Distribution Network

Backpressure Learning-Based Data Transmission Reliability-Aware Self-Organizing Networking for Power Line Communication in Distribution Network

Robust adaptive learning control using spiking-based self-organizing emotional neural network for a class of nonlinear systems with uncertainties

For second-order general nonlinear systems with uncertainties, a control scheme combining fractional-order fast terminal sliding mode control (FOFTSMC) and self-organizing emotional neural network (SOENN) is proposed and designed. Firstly, a novel emotional neural network which can approximate the uncertainties in nonlinear systems is constructed and introduced. Meanwhile, in order to optimize the network structure and reduce the computing burden, a novel spiking-based self-organizing mechanism is added. Then the FOFTSMC is designed for second-order general nonlinear systems, and the stability and finite time convergence is proved by Lyapunov theory. Besides, the FOFTSMC and SOENN are combined to form the final control scheme, and adaptive laws of the parameters are also designed. Finally, inverted pendulum and active power filter (APF) are selected as the research objects to carry out a series of simulations and experiments to validate and highlight the effectiveness and superiority of the proposed control scheme.

A local filtering-based energy-aware routing scheme in flying ad hoc networks

Flying ad hoc network (FANET) is a new technology, which creates a self-organized wireless network containing unmanned aerial vehicles (UAVs). In FANET, routing protocols deal with important challenges due to limited energy, frequent link failures, high mobility of UAVs, and limited communication range of UAVs. Thus, a suitable path is always essential to transmit data between UAVs. In this paper, a local filtering-based energy-aware routing scheme (LFEAR) is proposed for FANETs. LFEAR improves the template of the route request (RREQ) packet by adding three fields, namely the energy, reliable distance, and movement similarity of the relevant route to create stable and energy-efficient paths. In the routing process, LFEAR presents a local filtering construction technique to avoid the broadcasting storm issue. This filter limits the broadcasting range of RREQs in the network. Accordingly, only UAVs inside this local filtered area can rebroadcast RREQs and other UAVs must eliminate these packets. After ending the route discovery process, the destination begins the route selection phase and extracts information about each discovered route, including the number of hops, route energy, reliable distance, and movement similarity. Then, the destination node calculates a score for each path based on the extracted information, selects the route with the highest score, and sends a route reply (RREP) packet to the source node through this route. Finally, the simulation process of LFEAR is performed using the NS2 simulator, and two simulation scenarios, namely change in network density and change in the speed of UAVs, are defined to evaluate network performance. In the first scenario, LFEAR improves energy consumption, packet delivery rate, network lifespan, and delay by 1.33%, 1.77%, 6.74%, and 1.71%, while its routing overhead is about 16.51% more than EARVRT. In the second scenario, LFEAR optimizes energy consumption and network lifetime by 5.55% and 5.67%, respectively. However, its performance in terms of routing overhead, packet delivery rate, and delay is 23%, 2.29%, and 6.67% weaker than EARVRT, respectively.

La traduction, un processus évolutif vu en rétroaction par la théorie de construction de niche

Translation, an Evolving Process seen in Retroaction by Niche Construction Theory This article delves into the translation process as a complex, self-organised system, viewed through the lens of niche construction theory. It highlights three key aspects: the modification of translation’s environmental conditions, the selection pressures acting on translation as it shapes its environment, and the evolutionary responses observed within the translation process. Firstly, it underlines how translation modifies its own environmental conditions through feedback loops between translators and their practices. Drawing on the insights of Gideon Toury and Kobus Marais, this perspective portrays translation as a dynamic and retroactive system. For example, the semantic evolution of the term “translate” itself reflects the dynamic interaction between translators and their environments. This model illustrates how translation continually shapes and redefines its context, resulting in a continuously evolving discipline. Additionally, the article explores the selection pressures that impact translation, akin to natural selection, where translation serves as a cultural and linguistic vector undergoing processes of variation, adaptation, and heredity. It examines how translation adapts to changing environments while preserving knowledge. Moreover, the article examines evolutionary responses observable in the translation process, such as computer-assisted translation, machine translation, and translation memories. These examples underscore translation’s capacity for self-observation, self-organisation, and self-creation (autopoiesis), reflecting its inherent complexity and adaptability. In conclusion, the article draws parallels between the translation process and biological niche construction, particularly focusing on the feedback law. It proposes a conceptual framework for understanding the factors contributing to the translation environment, emphasizing the complexity and multiplicity inherent in translation processes. This niche construction theory provides insights into the dynamic nature of translation and its reciprocal relationship with its environment. As technology, particularly AI, advances, the translation niche may evolve into a cognitive niche, enhancing our ability to observe and control the translation process. Thus, this study advocates for an interdisciplinary approach that bridges sociological and biological perspectives, paving the way for future research in the evolving landscape of translation studies..

Game Model of Stable Cooperation During Resource Distribution in Self-Organized Emergency Management System

Game Model of Stable Cooperation During Resource Distribution in Self-Organized Emergency Management System

A deep reinforcement learning-based intelligent QoS optimization algorithm for efficient routing in vehicular networks

With the rapid development of Telematics, Vehicle Self-Organizing Networks (VANETs) play an increasingly critical role in Intelligent Transportation Systems (ITS). Especially in the environment without roadside assistance units (RSUs), how to effectively manage inter-vehicle communication and improve the stability and communication efficiency of the network has become a hot topic of current research. In this paper, a Deep Reinforcement Learning-based Intelligent QoS-optimized efficient routing algorithm for vehicular networks (DRLIQ) is proposed for VANETs with/without RSU environments, and routing methods are proposed respectively. Among them, in RSU-free environment, the DRLIQ algorithm utilizes the powerful processing capability of deep reinforcement learning to intelligently select the optimal data transmission path by dynamically learning and adapting to the changes in the vehicular network, thus effectively reducing communication interruptions and delays, and improving the accuracy of data transmission. The performance of the DRLIQ algorithm under different vehicle densities is evaluated in simulation experiments and compared with current popular algorithms. The experimental results show that the DRLIQ algorithm outperforms the comparison algorithms in reducing the number of communication interruptions, BER and network delay, especially in vehicle-dense environments. In addition, the DRLIQ algorithm shows higher adaptability and stability in coping with network topology changes and vehicle dynamics.