Self-organizing Neural Network Research Articles

Self-Organizing Interval Type-2 Fuzzy Neural Network Compensation Control Based on Real-Time Data Information Entropy and Its Application in n-DOF Manipulator.

In order to solve the high-precision motion control problem of the n-degree-of-freedom (n-DOF) manipulator driven by large amount of real-time data, a motion control algorithm based on self-organizing interval type-2 fuzzy neural network error compensation (SOT2-FNNEC) is proposed. The proposed control framework can effectively suppress various types of interference such as base jitter, signal interference, time delay, etc., during the movement of the manipulator. The fuzzy neural network structure and self-organization method are used to realize the online self-organization of fuzzy rules based on control data. The stability of the closed-loop control systems are proved by Lyapunov stability theory. Simulations show that the algorithm is superior to a self-organizing fuzzy error compensation network and conventional sliding mode variable structure control methods in control performance.

Seismic Sedimentologic Study on Sequence-Sediment Evolution in Fault Basin Regions

With potential hydrocarbon source rocks, the Mesozoic Lower Cretaceous interval in the Aitegle Sag of the Yingen-Ejinaqi Basin in China has a bright petroleum exploration prospect. Considering the scarcity of wells in Aitegle Sag, we have systematically carried out the research on the sequence structure and sedimentary system evolution of the Lower Cretaceous based on seismic, core, and logging data, guided by the Vail classic sequence stratigraphy, and innovatively introduced the self-organizing mapping neural network (SOM) learning algorithm to assist in seismic geological analysis. The results are as follows: (1) after RMSAmp, LyapIndex, FrctDim, and InfoEntr clustering, five zones are divided, which are corresponding to five seismic facies (showing medium-strong amplitude and parallel-subparallel reflection; medium-strong amplitude and wedge-shaped divergent reflection; medium-strong amplitude and continuous-relatively continuous, parallel-subparallel reflection; strong amplitude and continuous sheet-like or blank reflection; and weak amplitude and mound-shaped chaotic reflection, respectively), and interpreted as five subfacies including delta plain front, prodelta-shallow lake, semideep lake, deep lake, and sublacustrine fan. (2) The Lower Cretaceous formation includes one second-order sequence, three third-order sequences (SQ2–SQ4), and six system tracts. In the SQ2–SQ4 circle, the delta system formed by sediments from southeast varies remarkably in the progradational zones in different system tracts, and tectonic movements and sediment supply control the sequence stratigraphy in the study area as major factors. (3) It is feasible to apply SOM learning algorithm to seismic attribute clustering analysis. This method effectively realizes the combination of geophysical methods based on big data analysis and geological problem analysis, which not only strengthens the use of seismic data but also ensures the effectiveness and reliability of clustering results. These findings offer basic data and scientific supports for the exploration and development of unconventional reservoirs (e.g., shale and tight oil/gas reservoirs) in the Aitegle Sag and also provide new ideas for studying the sequence-sediment in the target zones in the fault basin regions with scarce wells.

AI-Based Real-Time Star Tracker

Many systems on Earth and in space require precise orientation when observing the sky, particularly for objects that move at high speeds in space, such as satellites, spaceships, and missiles. These systems often rely on star trackers, which are devices that use star patterns to determine the orientation of the spacecraft. However, traditional star trackers are often expensive and have limitations in their accuracy and robustness. To address these challenges, this research aims to develop a high-performance and cost-effective AI-based Real-Time Star Tracker system as a basic platform for micro/nanosatellites. The system uses existing hardware, such as FPGAs and cameras, which are already part of many avionics systems, to extract line-of-sight (LOS) vectors from sky images. The algorithm implemented in this research is a “lost-in-space” algorithm that uses a self-organizing neural network map (SOM) for star pattern recognition. SOM is an unsupervised machine learning algorithm that is usually used for data visualization, clustering, and dimensionality reduction. Today’s technologies enable star-based navigation, making matching a sky image to the star map an important aspect of navigation. This research addresses the need for reliable, low-cost, and high-performance star trackers, which can accurately recognize star patterns from sky images with a success rate of about 98% in approximately 870 microseconds.

Ultrasound Intima-Media Complex (IMC) Segmentation Using Deep Learning Models

Common carotid intima-media thickness (CIMT) is a common measure of atherosclerosis, often assessed through carotid ultrasound images. However, the use of deep learning methods for medical image analysis, segmentation and CIMT measurement in these images has not been extensively explored. This study aims to evaluate the performance of four recent deep learning models, including a convolutional neural network (CNN), a self-organizing operational neural network (self-ONN), a transformer-based network and a pixel difference convolution-based network, in segmenting the intima-media complex (IMC) using the CUBS dataset, which includes ultrasound images acquired from both sides of the neck of 1088 participants. The results show that the self-ONN model outperforms the conventional CNN-based model, while the pixel difference- and transformer-based models achieve the best segmentation performance.

Self-organizing RBF neural network based on IPSO and neural strength1

In this paper, a self-organizing RBF (SORBF) neural network with an adaptive threshold is proposed based on improved particle swarm optimization (IPSO) and neural strength (NS). The parameters and structure of SORBF can be optimized simultaneously and dynamically. Moreover, the tiresome problem of threshold setting is solved. Firstly, the network size and parameters of SORBF are mapped into the particle information of PSO. Secondly, an IPSO algorithm, based on diversity inertia weight and elite knowledge guiding, is proposed to reduce the probability of the population falling into the local optimum. Then, IPSO is used for optimizing the parameters of SORBF. Based on neuron growth intensity and competition intensity, SORBF can realize the hidden neuron addition and deletion adaptively. Moreover, the thresholds during the structure adjustment can be provided adaptively based on the network scale and neuron strength, which avoids the subjectivity setting and can improve the adaptive ability. Finally, the convergence analysis of IPSO is provided to ensure the performance of SORBF. Experiment results show that the proposed SORBF has good self-organizing ability and compact network structure compared with other methods.

Incorporating ecological connectivity into ecological functional zoning: A case study in the middle reaches of Yangtze River urban agglomeration

Ecological functional zoning is critical for multiobjective sustainable management of social-ecological systems. However, the framework of ecological functional zoning needs to be further improved. In terms of the index system, the existing “element-structure–function” index system mainly considers the structural characteristics that have a negative impact on ecological processes, e.g., disturbances, while ignoring positive impacts, e.g., connectivity, which may weaken the role of key nodes in the ecosystem and is not conducive to regional ecological protection. In terms of research methodology, the widely used self-organizing feature mapping neural network (SOFM) produces a number of clusters that easily exceed expectations, thus increasing management difficulties. Therefore, there is an urgent need to explore new combining methods. Here, an improved index system combining ecological connectivity and ecological functions and a traditional index system including only ecological functions were constructed, and a zoning method combining a self-organizing feature mapping neural network and fuzzy mean clustering (SOFM-FCM) was used for functional zoning of the middle reaches of the Yangtze River urban agglomeration. The advantages of functional zoning incorporating ecological connectivity were verified by comparing the results of both zoning procedures before and after improvement. The results indicate that the study area could be divided into ecological conservation areas, biodiversity conservation areas, urban development areas, and grain production areas. The zoning schemes before and after the improved framework were reliable compared with the national planning scheme, but there was 20.6% inconsistency in the results after the improved framework. This was mainly manifested by the shift from biodiversity conservation areas to ecological conservation areas and from urban development areas to food production areas. This shift was more conducive to improving spatial continuity and landscape multifunctionality, thus maximizing ecological conservation, pushing back smart urban growth, and achieving food security. This study expands the research perspective concerned with ecological functional zoning, and these results can provide an important reference for regional ecological protection and related research.

Identification of pathobiomechanical markers of statokinesiograms on the example of neural network identification of a post-stroke state

The purpose of this study is neural network modeling and determination of the parameters of statokinesiograms, which are carriers of useful information about the features of postural regulation, which determined the obtained trajectory of movements of the human center of mass. A technique for obtaining informative markers by identifying clustering centroids based on self-organizing Kohonen neural networks with the Euclidean metric has been developed. Kohonen networks trained without a teacher (that is, without the use of a priori diagnostic information about the state of the subjects) are a powerful and informative method that allows you to obtain not only graphic, but also mathematical markers of health disorders in subjects, to explore the biomechanics of micromovements of the center of pressure based on a flexible mathematical apparatus – neural network cluster analysis. On the example of the identification of the post-stroke state, a neural network analysis of stabilometric data was carried out and a method for identifying pathobiomechanical markers of statokinesiograms was shown, which made it possible to standardize the type affiliation of the groups of subjects. With the help of neural networks, it was possible to identify clusters that are amenable to biomedical interpretation with a reliability of up to 95.9 %, which determines the theoretical significance of the results obtained. Decision trees and a supervised multilayer neural network were also considered. A multilayer neural net-work made it possible to identify markers of health disorders with a probability of 71.9 %.

Deep learning-based middle cerebral artery blood flow abnormality detection using flow velocity waveform derived from transcranial Doppler ultrasound

Since the brain is unlike any other organ in that it cannot store energy and has a high metabolic demand, constant blood flow is essential for healthy brain function. The maximum flow velocity waveform that is produced by transcranial doppler echo ultrasonography has different qualities for a healthy subject and a critically ill patient with conditions such as intraparenchymal or subarachnoid hemorrhage, hydrocephalus, or traumatic brain injury. Depending on the degree of the injury, the symptoms of traumatic brain damage can present themselves right away or not until days or weeks later. To aid in the early and accurate detection of patients with severe brain conditions, a classification system is proposedthat can distinguish between healthy control and patient utilizing the maximum flow velocity waveform derived from Transcranial doppler ultrasound. In this research, we manually labelled the data to remove mediocre and corrupted signals and pre-processed low-quality signals into high-quality ones using a Cycle Generative Adversarial Network (CycleGAN). This study proposes a two-stream deep learning model, DopplerNet2+, based on a Self-organized Operational Neural Network (Self-ONN), which achieves an overall accuracy, precision, recall, sensitivity, f1 score, and specificity of 99.45%, 99.45%, 99.45%, and 99.37% for the classification issue. DopplerNet2+ has a better area under the curve (AUC) of 1.00 and a better Kolmogorov-Smirnov (KS) statistic of 0.996 at the 0.812 thresholds than 11 other Self-ONN models trained with different inputs. The results show that the proposed models can successfully carry out the targeted classification task.

Event-triggered-based self-organizing fuzzy neural network control for the municipal solid waste incineration process

Event-triggered-based self-organizing fuzzy neural network control for the municipal solid waste incineration process

Self-organizing modeling and control of activated sludge process based on fuzzy neural network

The wastewater treatment process contains multiple complex biochemical reactions featured by strong nonlinear and time-varying dynamics due to the built-in discontinuity and uncertainty. Herein, a self-organizing fuzzy neural network with an efficient scheme for parsimonious (SOFNN-ESP) was orchestrated to improve the self-organizing modeling of municipal wastewater treatment process by combing predictive algorithms to deal with the complex water treatment procedure. The SOFNN-ESP algorithm could identify sewage treatment plants by a high-throughput parameter screening system and recursive least square method in real-time, which provided dynamic setting feedback and promoted water quality. The integration of the SOFNN-ESP algorithm and a model predictive control (MPC) further improved the accuracy in water quality controlling via immediately adjusting weight parameters of the network. This gradient algorithm also realized the online dynamic tracking of dissolved oxygen and nitrate nitrogen level by simultaneous tracking of multiple performance indicators and optimizing setting values of the control variable. SOFNN-ESP-MPC gave an error of <5 % when the peak error of proportional integral differential controller was >10 %. Concerning the benchmark simulation model No.1 of municipal wastewater treatment, the SOFNN-ESP-MPC method exhibited a compact network structure and outstanding generalization performance. The self-organizing modeling and predictive control strategy proposed in this study could effectively improve the prediction accuracy and control efficiency of the activated sludge process model, which is of great significance for the efficiency improvement of sewage treatment process.

Online Estimation of Three-Directional Tire Forces Based on a Self-Organizing Neural Network

The road friction coefficient and the forces between the tire and the road have a significant impact on the stability and precise control of the vehicle. For four-wheel independent drive electric vehicles, an adaptive tire force calculation method based on the improved Levenberg–Marquarelt multi-module and self-organizing feedforward neural networks (LM-MMSOFNN) was proposed to estimate the three-directional tire forces of four wheels. The input data was provided by common sensors amounted on the autonomous vehicle, including the inertial measurement unit (IMU) and the wheel speed/rotation angle sensors (WSS, WAS). The road type was recognized through the road friction coefficient based on the vehicle dynamics model and Dugoff tire model, and then the tire force was calculated by the neural network. The computational complexity and storage space of the system were also reduced by the improved LM learning algorithm and self-organizing neurons. The estimation accuracy was further improved by using the Extended Kalman Filter (EKF) and Moving Average (MA). The performance of the proposed LM-MMSOFNN was verified through simulations and experiments. The results confirmed that the proposed method was capable of extracting important information from the sensors to estimate three-directional tire forces and accurately adapt to different road surfaces.

On the performance and interpretability of Mamdani and Takagi-Sugeno-Kang based neuro-fuzzy systems for medical diagnosis

PurposeNeuro-fuzzy systems aim to combine the benefits of artificial neural networks and fuzzy inference systems: a neural network can learn patterns from data and achieves high performance, whereas a fuzzy system matches inputs and outputs using linguistic and interpretable rules. The combination of these two techniques yields models that can both perform well and provide interpretability in a fuzzy linguistic manner. DesignIn this paper, the performance and interpretability of five neuro-fuzzy classifiers were evaluated (three Takagi-Sugeno-Kang (TSK) classifiers: adaptive neuro-fuzzy inference system (ANFIS), dynamic evolving neuro-fuzzy system (DENFIS), self-organizing fuzzy neural network (SOFNN), and two Mamdani classifiers: hybrid fuzzy inference system (HyFIS) and neuro-fuzzy classifier (NEFCLASS)). All the empirical evaluations were over four benchmark medical datasets (Wisconsin breast cancer dataset, SPECTF heart dataset, Parkinsons dataset, and diabetic retinopathy Debrecen dataset), and used five performance criteria (accuracy, precision, recall, f score, and training time) and two interpretability criteria (number of rules and number of membership functions). FindingsResults showed that the TSK-based self-organizing fuzzy neural network classifier, in general, outperformed the others. In terms of interpretability, DENFIS and NEFCLASS were the best Takagi-Sugeno-Kang and Mamdani classifiers respectively. The findings also suggested that three classifiers: DENFIS, SOFNN, and NEFCLASS achieved a good performance-interpretability tradeoff. OriginalityTo the best of our knowledge, no study has compared the neuro-fuzzy techniques presented in this paper in terms of performance and interpretability in the medical domain.

Self-Organized Neural Network Method to Identify Crash Hotspots

Crash hotspot identification (HSID) is an essential component of traffic management authorities’ efforts to improve safety and allocate limited resources. This paper presents a method for identifying hotspots using self-organizing maps (SOM). The SOM method was used to identify high-risk areas based on five commonly used HSID methods: crash frequency, equivalent property damage only, crash rate, empirical Bayes, and the societal risk-based method. Crashes on a major road in Iran were examined using the proposed method. Based on these criteria, high-risk locations were grouped into six clusters, which provided appropriate criteria for each location depending on the importance of the cluster. The findings show that the identification of crash hotspots tends to focus on areas with more crashes and deaths, demonstrating that the research methodology was appropriate.

An automated epileptic seizure detection using optimized neural network from EEG signals

AbstractAmong the central nervous system (neurological) disorders, epilepsy is considered to be a dangerous and chronic disorder that causes recurring seizures, showing unusual behaviour for some period of time, shaking of hands and legs, loss of sensation and awareness. It occurs when electrical activities in the brain become abnormal. The test performed in order to detect epileptic seizures is known as electroencephalograph (EEG) signal test which is conducted by analysing the electrical impulses in the brain. The manual identification process of EEG brain signals is time consuming and a laborious task. So the neurologists may sometimes give a varying result which may affect the performance of detecting epileptic seizures. The combination of manual identification of the signal and machine learning technique will be able to provide a correct result in a confusion situation reducing analytic and therapeutic errors that are unavoidable in human clinical practice. The existing approaches of detection of epileptic seizures cannot correctly train their network if the size of the dataset is very large thus obtaining lower classification accuracy. An optimized neural network technique is proposed in this work for automatic detection of Epileptic seizure using EEG signals of the brain. The EEG signals are used for feature extraction by applying Discrete Wavelet Transform (DWT). Using the extracted features, input samples are created and then fed to a hybrid model which is a combination of self‐organizing neural network (SONN) and multilayer perceptron (MLP) trained with a genetic algorithm (GA). This model acts as a classifier for detecting Epileptic seizures by classifying the samples into two classes namely Non‐Epileptic and Epileptic class. Clustering is performed first for the large dataset samples using SONN and for each cluster, an MLP‐GA network is used to train the samples belonging to the same cluster. Performing clustering helps to correctly train the MLP networks for obtaining high classification accuracy. GA has been specifically chosen as a learning algorithm instead of Backpropagation (BP) algorithm for MLP because GA can find the global minima thus solving the local minima problem faced by BP algorithm. The performance measures are evaluated thereby achieving precision value of 98%, recall value of 100%, F1 score value of 98.99% and an overall accuracy of 99.2%. The proposed hybrid method using SONN and MLP‐GA has more potential to classify the EEG signals.

Scalable cognitive developmental network: A strategy for integrating new perception online using relation evolution SOINN

Cognitive development can make robots more intelligent. However, current cognitive robots are still limited to learning fixed types of information. To this end, we propose a scalable cognitive developmental network (SCDN) based on self-organizing incremental neural network (SOINN), which allows new types of perception information to be added into the existing cognitive network online. SCDN has three hierarchical layers for developing concrete and abstract knowledge. Firstly, the sample layer learns the sample features of four modal information, including shape, color, name and taste. Secondly, the symbol layer generates respective symbol representations. Finally, the associative layer realizes the fusion of new perception information and native networks. Specifically, the Relation Evolution SOINN (RE-SOINN) is proposed in the associative layer to add new information into existing relationships, which contributes to the evolution of associative relationships. We evaluate the performance of SCDN on a fruits and vegetables dataset. Experimental results show that SCDN can effectively learn unknown sensory information online and form the correct link with the known information without learning from scratch.

Optimal control of sewage treatment process using a dynamic multi-objective particle swarm optimization based on crowding distance

A variety of multi-objective optimization algorithms has been extensively investigated in the past decades to tackle the optimal decision of sewage treatment process. However, achieving the ideal solutions is challenging in the multi-criteria decision-making process from Pareto optimal sets due to the complicated relationships among influencing factors, especially in the case of large decision variables involved in the wastewater treatment process. We thus proposed an improved dynamic multi-objective particle swarm optimization algorithm based on crowding distance (DMOPSO-CD) to obtain global optimal solutions for the balance between energy consumption (EC) and effluent quality (EQ) in sewage treatment processes. The algorithm consists of optimization modules and a self-organizing fuzzy neural network, improving the global searching ability of particles, maintaining the diversity of non-inferior solutions, and solving the multi-objective vital issues in the optimization of sewage treatment process. The proposed optimization algorithm was applied to benchmark simulation model No.1, and the optimization results showed that the EC for wastewater treatment in dry, rainy, and storm weather was reduced by 7.87%, 6.28%, and 7.30%, respectively. This methodology outperformed several widely applied algorithms, including the multi-objective cuckoo search, non-dominated sorting genetic algorithm-II, and improving Pareto evolutionary algorithm in terms of EQ and EC, which opens a new window for the optimal decision of sewage treatment.

A Lightweight Deep Learning Based Microwave Brain Image Network Model for Brain Tumor Classification Using Reconstructed Microwave Brain (RMB) Images.

Computerized brain tumor classification from the reconstructed microwave brain (RMB) images is important for the examination and observation of the development of brain disease. In this paper, an eight-layered lightweight classifier model called microwave brain image network (MBINet) using a self-organized operational neural network (Self-ONN) is proposed to classify the reconstructed microwave brain (RMB) images into six classes. Initially, an experimental antenna sensor-based microwave brain imaging (SMBI) system was implemented, and RMB images were collected to create an image dataset. It consists of a total of 1320 images: 300 images for the non-tumor, 215 images for each single malignant and benign tumor, 200 images for each double benign tumor and double malignant tumor, and 190 images for the single benign and single malignant tumor classes. Then, image resizing and normalization techniques were used for image preprocessing. Thereafter, augmentation techniques were applied to the dataset to make 13,200 training images per fold for 5-fold cross-validation. The MBINet model was trained and achieved accuracy, precision, recall, F1-score, and specificity of 96.97%, 96.93%, 96.85%, 96.83%, and 97.95%, respectively, for six-class classification using original RMB images. The MBINet model was compared with four Self-ONNs, two vanilla CNNs, ResNet50, ResNet101, and DenseNet201 pre-trained models, and showed better classification outcomes (almost 98%). Therefore, the MBINet model can be used for reliably classifying the tumor(s) using RMB images in the SMBI system.

Trajectory Tracking Control Method for Omnidirectional Mobile Robot Based on Self-Organizing Fuzzy Neural Network and Preview Strategy

This paper proposes a new trajectory tracking control scheme for the four mecanums wheel omnidirectional mobile robot (FM-OMR). Considering the influence of uncertainty on tracking accuracy, a self-organizing fuzzy neural network approximator (SOT1FNNA) is proposed to estimate the uncertainty. In particular, since the structure of traditional approximation network is preset, it will cause problems such as input constraints and rule redundancy, resulting in low adaptability of the controller. Therefore, a self-organizing algorithm including rule growth and local access is designed according to the tracking control requirements of omnidirectional mobile robots. In addition, a preview strategy (PS) based on Bezier curve trajectory re-planning is proposed to solve the problem of tracking curve instability caused by the lag of tracking starting point. Finally, the simulation verifies the effectiveness of this method in tracking and trajectory starting point optimization.

A self-organizing incremental neural network for imbalance learning

A self-organizing incremental neural network for imbalance learning

Energy-balanced neuro-fuzzy dynamic clustering scheme for green & sustainable IoT based smart cities

The Internet of Things (IoT) is a pervasive computing technology that provides solutions to critical sustainable smart city applications. Each sustainable application has its own set of requirements, including energy efficiency, Quality of Service (QoS), hardware, and software resources. Even though green IoT devices operate in a resource-constrained environment. Monitoring, recognizing, and responding to activities that entail continuous access to timely information in a partially or fully distributed ecosystem is a difficult task. To overcome the challenges of resource management in the IoT, we proposed an energy-efficient Dynamic Clustering Routing (DCR) protocol using a neuro-fuzzy technique for restricting the resources of IoT devices. The proposed protocol uses a dynamic self-organizing neural network to create dynamic clusters in a network. The test-bed analysis is for computing the real-time event detection and clustering sensor nodes using TinyOS. The simulation result shows that the proposed protocol achieved a significant gain over peer-competing well-known green communication routing protocols like Low-energy Adaptive Clustering Hierarchy (LEACH) and Low-energy Adaptive Clustering Hierarchy-Centralized (LEACH-C). The proposed model results show that using neuro-fuzzy logic is effective for sustainable IoT devices and green smart city applications in terms of resource management and dynamic clustering. The result analysis shows that the proposed protocol shows an average 35% significant gain on the First Node Dies (FND), Last Node Dies (LND), the number of packets sent to CH & BS, network convergence time, network overhead, and average packet delay to compare with the LEACH and LEACH-C.