Self-organizing Map Network Research Articles

Research of the Distribution of Tongue Features of Diabetic Population Based on Unsupervised Learning Technology.

Background The prevalence of diabetes increases year by year, posing a severe threat to human health. Current treatments are difficult to prevent the progression of diabetes and its complications. It is imperative to carry out individualized treatment of diabetes, but current diagnostic methods are difficult to specify an individualized treatment plan. Objective Clarify the distribution law of tongue features of the diabetic population, and provide the diagnostic basis for individualized treatment of traditional Chinese medicine (TCM) in the treatment of diabetes. Methods We use the TFDA-1 tongue diagnosis instrument to collect tongue images of people with diabetes and accurately calculate the color features, texture features, and tongue coating ratio features through the Tongue Diagnosis Analysis System (TDAS). Then, we used K-means and Self-organizing Maps (SOM) networks to analyze the distribution of tongue features in diabetic people. Statistical analysis of TDAS features was used to identify differences between clusters. Results The silhouette coefficient of the K-means clustering result is 0.194, and the silhouette coefficient of the SOM clustering result is 0.127. SOM Cluster 3 and Cluster 4 are derived from K-means Cluster 1, and the intersections account for (76.7% 97.5%) and (22.3% and 70.4%), respectively. K-means Cluster 2 and SOM Cluster 1 are highly overlapping, and the intersection accounts for the ratios of 66.9% and 95.0%. K-means Cluster 3 and SOM Cluster 2 are highly overlaid, and the intersection ratio is 94.1% and 82.1%. For the clustering results of K-means, TB-a and TC-a of Cluster 3 are the highest (P < 0.001), TB-a of Cluster 2 is the lowest (P < 0.001), and TB-a of Cluster 1 is between Cluster 2 and Cluster 3 (P < 0.001). Cluster 1 has the highest TB-b and TC-b (P < 0.001), Cluster 2 has the lowest TB-b and TC-b (P < 0.001), and TB-b and TC-b of Cluster 3 are between Cluster 1 and Cluster 2 (P < 0.001). Cluster 1 has the highest TB-ASM and TC-ASM (P < 0.001), Cluster 3 has the lowest TB-ASM and TC-ASM (P < 0.001), and TB-ASM and TC-ASM of Cluster 2 are between the Cluster 1 and Cluster 3 (P < 0.001). CON, ENT, and MEAN show the opposite trend. Cluster 2 had the highest Per-all (P < 0.001). SOM divides K-means Cluster 1 into two categories. There is almost no difference in texture features between Cluster 3 and Cluster 4 in the SOM clustering results. Cluster 3's TB-L, TC-L, and Per-all are lower than Cluster 4 (P < 0.001), Cluster 3's TB-a, TC-a, TB-b, TC-b, and Per-part are higher than Cluster 4 (P < 0.001). Conclusions The precise tongue image features calculated by TDAS are the basis for characterizing the disease state of diabetic people. Unsupervised learning technology combined with statistical analysis is an important means to discover subtle changes in the tongue features of diabetic people. The machine vision analysis method based on unsupervised machine learning technology realizes the classification of the diabetic population based on fine tongue features. It provides a diagnostic basis for the designated diabetes TCM treatment plan.

Implementation of a machine learning technique for estimating gamma direction using a coaxial High Purity Germanium detector

We demonstrate the ability to obtain the direction of the gamma rays using a standard coaxial high purity germanium (HPGe) detector using the direction-sensitive information embedded in the shape of the pre-amplified HPGe signals. We deduced the complex relationship between the shape of the signal and the direction from which the gamma-ray enters the detector active volume using a two-step machine learning technique. In the first step, we collected pulses from the HPGe detector due to a 133Ba radioactive source placed in four distinct positions around the detector while keeping the distance from the center of the detector crystal constant. A subset of the pulses collected with radioactive source kept at the four positions was used to train an artificial neural network (ANN) called a self-organizing map (SOM) to cluster the HPGe waveforms based on their shape. The trained SOM network was then utilized to produce direction-specific maps corresponding to pulses generated when the 133Ba source is at a specific location with respect to the detector. In the second step, we used the SOM-generated direction-specific maps to train another network composed of a single feedforward layer for predicting the direction of the gamma ray from the pulses produced by the HPGe detector due to the gamma energy deposition. Our results show that even without employing complex methodologies, a standard coaxial HPGe detector can estimate the direction of incoming gamma rays and thus, provide initial guidance on the gamma-emitting radioactive source direction with reference to the detector.

Quantitative Diagnosis of TCM Syndrome Types Based on Adaptive Resonant Neural Network.

Artificial intelligence has become one of the most rapidly developing disciplines in the application field of pattern recognition. In target recognition, sometimes, there are multiple identical or similar copies of the target to be recognized in the image, and it is difficult to classify and estimate by traditional methods. In this case, it is necessary to use the SOM network to separate multiple targets and use the multiple order parameters in the improved SNN to pair the target. The change of its thickness can intuitively reflect the abnormality of its tissue. Therefore, the choroidal thickness of the central fovea can be measured to study the relationship between the choroidal structure and BRVO and arteriosclerosis. The purpose of this study is to further study the correlation between branch retinal vein occlusion and arteriosclerosis by quantitatively measuring retinal vessel diameter and choroidal thickness, to analyze the correlation between different TCM syndrome types of nonischemic BRVO and retinal arteriosclerosis, and to provide theoretical basis for clinical nonischemic BRVO TCM syndrome types and traditional Chinese medicine treatment, so as to reflect its clinical application value. In order to solve the single fixed structure of traditional SNN and poor scalability, combined with the Kohonen layer structure in the self-organizing mapping network, an improved collaborative neural network model is proposed. This paper studies the network training method and operation convergence and analyzes the converged network and the pattern classification results obtained by the network. In order to solve the single fixed structure of traditional SNN and poor scalability, combined with the Kohonen layer structure in the self-organizing mapping network, an improved collaborative neural network model is proposed. The results of our proposed improved model on the MNIST dataset can achieve the same level of current state-of-the-art machine learning classifiers in recognition accuracy with a smaller network size and network complexity.

Spatial Suitability Evaluation of Livestock and Poultry Breeding: A Case Study in Wangkui County, Heilongjiang Province, China

With the development of animal husbandry, environmental pollution caused by livestock and poultry breeding (LPB) has become a major problem faced by environmental protection departments. In response to this problem, this study established a spatial suitability evaluation system for LPB. According to the particularity of the indicators, there is a nonlinear relationship after quantification and not all elements in the matrix presented by the indexes and evaluation units have an ‘order’ relationship. Therefore, this study selects a method of combining a self-organising map network. The Hasse diagram technique and geographic information system were used to evaluate the suitability of LPB. Practical application research was conducted in Wangkui County. Most regions of Wangkui County are unsuitable for LPB, accounting for 81.23% of the total area of the county. A small part of a suitable region (434.76 km2) was determined to be a potential site for LPB. According to the results of suitable breeding regions, 17 existing large-scale livestock and poultry farms (LPFs) with unreasonable distribution were optimised for space, which are located in an urban construction area. Spatial optimisation was performed using GIS buffer and overlay analyses, providing the best relocation plot for these 17 LPFs. The results provide a scientific basis for the utilisation of livestock manure and spatial layout planning for LPB.

A Dynamic Convolution Kernel Generation Method Based on Regularized Pattern for Image Super-Resolution.

Image super-resolution aims to reconstruct a high-resolution image from its low-resolution counterparts. Conventional image super-resolution approaches share the same spatial convolution kernel for the whole image in the upscaling modules, which neglect the specificity of content information in different positions of the image. In view of this, this paper proposes a regularized pattern method to represent spatially variant structural features in an image and further exploits a dynamic convolution kernel generation method to match the regularized pattern and improve image reconstruction performance. To be more specific, first, the proposed approach extracts features from low-resolution images using a self-organizing feature mapping network to construct regularized patterns (RP), which describe different contents at different locations. Second, the meta-learning mechanism based on the regularized pattern predicts the weights of the convolution kernels that match the regularized pattern for each different location; therefore, it generates different upscaling functions for images with different content. Extensive experiments are conducted using the benchmark datasets Set5, Set14, B100, Urban100, and Manga109 to demonstrate that the proposed approach outperforms the state-of-the-art super-resolution approaches in terms of both PSNR and SSIM performance.

Overview of Machine Learning

The field of machine learning is introduced at a high level of abstraction. The concepts of supervised and unsupervised learning, regression, and classification are all discussed. A major guiding notion of learning is the balance between bias, variance, and model complexity. The neural network (feed-forward and recurrent), support vector machine, random forest, self-organizing map, and Bayesian network are all examples of models that machine learning can develop. The core ideas of partitioning a dataset into training, testing, and validation sets, as well as performing cross-validation, are addressed next. The importance of the domain expert in keeping the project real is discussed next, followed by evaluating the model's goodness. The chapter ends with some practical advice on how to perform a machine learning project.

Research on an Improved SOM Model for Damage Identification of Concrete Structures

In order to solve the problem of intelligent detection of damage of modern concrete structures under complex constraints, an improved self-organizing mapping (SOM) neural network model algorithm was proposed to construct an accurate identification model of concrete structure damage. Based on the structure and algorithm of the SOM network model, the whole process of the core construction of the concrete structure damage identification network model is summarized. Combined with the damage texture characteristics of concrete structures, through the self-developed 3D laser scanning system, an improved method based on a small number of samples to effectively improve the effectiveness of network input samples is proposed. Based on the principle of network topology map analysis and its image characteristics, a SOM model improvement method that can effectively improve the accuracy of the network identification model is studied. In addition, based on the reactive powder concrete bending fatigue loading test, the feasibility and accuracy of the improved method are verified. The results show that the improved SOM concrete structure damage identification model can effectively identify unknown neuron categories in a limited sample space, and the identification accuracy of the SOM network model is improved by 4.69%. The proposed improved SOM model method fully combines the network topology and its unique image features and can accurately identify structural damage. This research contributes to the realization of high-precision intelligent health monitoring of damage to modern concrete structures. In addition, it is of great significance for the timely detection, identification and localization of early damage to structures.

Performance analysis with self-organizing map and recurrent neural network

As software aging has been discovered in many fields, some time-series methods are utilized to find a better time to make a software system become more resilient from the degradation states. However, those existing methods cannot well solve the sequence relationship of the resource consumption series in the aging problems since data series contains linear and nonlinear characteristics. In this paper, we propose a method, recurrent neural network with self-organizing map, to enhance the prediction accuracy for resource consumption series of software aging problems. In order to smooth the resource consumption series, a pre-processing process and a self-organizing map are used. To make the prediction more accurate, a recurrent neural network is used. In the experiment, the proposed method is applied to two types of resource consumption series, and the result shows that our proposed method owns better performances in two aspects.

Monthly Streamflow Modeling Based on Self-Organizing Maps and Satellite-Estimated Rainfall Data

Hydrological data provide valuable information for the decision-making process in water resources management, where long and complete time series are always desired. However, it is common to deal with missing data when working on streamflow time series. Rainfall-streamflow modeling is an alternative to overcome such a difficulty. In this paper, self-organizing maps (SOM) were developed to simulate monthly inflows to a reservoir based on satellite-estimated gridded precipitation time series. Three different calibration datasets from Três Marias Reservoir, composed of inflows (targets) and 91 TRMM-estimated rainfall data (inputs), from 1998 to 2019, were used. The results showed that the inflow data homogeneity pattern influenced the rainfall-streamflow modeling. The models generally showed superior performance during the calibration phase, whereas the outcomes varied depending on the data homogeneity pattern and the chosen SOM structure in the testing phase. Regardless of the input data homogeneity, the SOM networks showed excellent results for the rainfall-runoff modeling, presenting Nash–Sutcliffe coefficients greater than 0.90.Graphical

Oil Family Typing Using a Hybrid Model of Self-Organizing Maps and Artificial Neural Networks.

Identifying the number of oil families in petroleum basins provides practical and valuable information in petroleum geochemistry studies from exploration to development. Oil family grouping helps us track migration pathways, identify the number of active source rock(s), and examine the reservoir continuity. To date, almost in all oil family typing studies, common statistical methods such as principal component analysis (PCA) and hierarchical clustering analysis (HCA) have been used. However, there is no publication regarding using artificial neural networks (ANNs) for examining the oil families in petroleum basins. Hence, oil family typing requires novel and not overused and common techniques. This paper is the first report of oil family typing using ANNs as robust computational methods. To this end, a self-organization map (SOM) neural network associated with three clustering validity indexes was employed on oil samples belonging to the Iranian part of the Persian Gulf oilfields. For the SOM network, at first, 10 default clusters were selected. Afterward, three effective clustering validity coefficients, namely, Calinski–Harabasz (CH), Silhouette (SH), and Davies–Bouldin (DB), were studied to find the optimum number of clusters. Accordingly, among 10 default clusters, the maximum CH (62) and SH (0.58) were acquired for 4 clusters. Similarly, the lowest DB (0.8) was obtained for four clusters. Thus, all three validation coefficients introduced four clusters as the optimum number of clusters or oil families. According to the geochemical parameters, it can be deduced that the corresponding source rocks of four oil families have been deposited in a marine carbonate depositional environment under dysoxic–anoxic conditions. However, oil families show some differences based on geochemical data. The number of oil families identified in the present report is consistent with those previously reported by other researchers in the same study area. However, the techniques used in the present paper, which have not been implemented so far, can be introduced as more straightforward for clustering purposes in oil family typing than those of common and overused methods of PCA and HCA.

Eye State Identification Utilizing EEG Signals: A Combined Method Using Self-Organizing Map and Deep Belief Network

Measuring brain activity through Electroencephalogram (EEG) analysis for eye state prediction has attracted attention from machine learning researchers. There have been many methods for EEG analysis using supervised and unsupervised machine learning techniques. The tradeoff between the accuracy and computation time of these methods in performing the analysis is an important issue that is rarely investigated in the previous research. This paper accordingly proposes a new method for EEG signal analysis through Self-Organizing Map (SOM) clustering and Deep Belief Network (DBN) approaches to efficiently improve the computation and accuracy of the previous methods. The method is developed using SOM clustering and DBN, which is a deep layer neural network with multiple layers of Restricted Boltzmann Machines (RBMs). The results on a dataset with 14980 instances and 15 attributes representing the values of the electrodes demonstrated that the method is efficient for EEG analysis. In addition, compared with the other supervised methods, the proposed method was able to significantly improve the accuracy of the EEG prediction.

Self-Organizing Map Network for the Decision Making in Combined Mode Conduction-Radiation Heat Transfer in Porous Medium

Self-Organizing Map Network for the Decision Making in Combined Mode Conduction-Radiation Heat Transfer in Porous Medium

Pruning Growing Self-Organizing Map Network for Human Physical Activity Identification.

Human physical activity identification based on wearable sensors is of great significance to human health analysis. A large number of machine learning models have been applied to human physical activity identification and achieved remarkable results. However, most human physical activity identification models can only be trained based on labeled data, and it is difficult to obtain enough labeled data, which leads to weak generalization ability of the model. A Pruning Growing SOM model is proposed in this paper to address the limitations of small-scale labeled dataset, which is unsupervised in the training stage, and then only a small amount of labeled data is used for labeling neurons to reduce dependency on labeled data. In training stage, the inactive neurons in network can be deleted by pruning mechanism, which makes the model more consistent with the data distribution and improves the identification accuracy even on unbalanced dataset, especially for the action categories with poor identification effect. In addition, the pruning mechanism can also speed up the inference of the model by controlling its scale.

Face Recognition using Principal Component Analysis and Clustered Self-Organizing Map

Face recognition is one of the cornerstones of the face processing schemes that composed the contemporary intelligent vision-based interactive systems between computers and humans. Instead of using neurons of the Self-Organized Map (SOM) neural network to cluster the facial data, in this work, we applied an agglomerative hierarchical clustering to cluster the neurons of the SOM network, which in turns, used to cluster the facial dataset. In prior, Principal Component Analysis (PCA) is employed to reduce the dimension of the facial data as well as to establish the initial state of SOM neurons. The design of the clustered-SOM recognition engine involves post-training steps that labeled the clustered SOM neurons resulting in a supervised SOM network. The effectiveness of the proposed model is demonstrated using the well-known ORL database. Using five images per person for SOM training, the proposed recognizer results in a recognition rate of 94.7%, whereas using nine images raise the recognition rate up to 99.33%. The facial recognizer has attained a notable reliability and robustness against the additive white Gaussian noise, where increasing the level of noise variance from 0 to 0.09, the recognition rate decreased only by 8%. Furthermore, time cost is analyzed, where using 200 images for training takes less than 4 seconds to be performed, whereas testing using a new set of 200 images takes less than 0.013 seconds which is competitive to many artificial intelligence and machine learning based schemes.

Inter-Purchase Time Prediction Based on Deep Learning

Inter-purchase time is a critical factor for predicting customer churn. Improving the prediction accuracy can exploit consumer’s preference and allow businesses to learn about product or pricing plan weak points, operation issues, as well as customer expectations to proactively reduce reasons for churn. Although remarkable progress has been made, classic statistical models are difficult to capture behavioral characteristics in transaction data because transaction data are dependent and short-, medium-, and long-term data are likely to interfere with each other sequentially. Different from literature, this study proposed a hybrid inter-purchase time prediction model for customers of on-line retailers. Moreover, the analysis of differences in the purchase behavior of customers has been particularly highlighted. The integrated self-organizing map and Recurrent Neural Network technique is proposed to not only address the problem of purchase behavior but also improve the prediction accuracy of inter-purchase time. The permutation importance method was used to identify crucial variables in the prediction model and to interpret customer purchase behavior. The performance of the proposed method is evaluated by comparing the prediction with the results of three competing approaches on the transaction data provided by a leading e-retailer in Taiwan. This study provides a valuable reference for marketing professionals to better understand and develop strategies to attract customers to shorten their inter-purchase times.

THE INFLUENCE OF THE FILM FORMED ON THE PRATO CHEESE SURFACE DURING THE NaCl AND KCl SALTING PROCESS: APPLICATION OF THE FINITE ELEMENT METHOD AND NEURAL NETWORKS OF THE SELF-ORGANIZING MAP (SOM) AND MULTILAYER PERCEPTRON (MLP) TYPES

Sodium chloride is used in the cheese salting process as it promotes sensory changes and food preservation. However, in excess can cause hypertension problems, and for this reason, it has been partially replaced by potassium chloride. In the present work, Prato cheese was subjected to joint diffusion of NaCl and KCl by immersion in static and stirred brine. The salt concentration values on the cheese surface were determined as a function of time. They were tabulated and presented to the self-organizing map (SOM)-type neural networks and the multilayer perceptron (MLP) for analysis and modeling of the film formed on the surface of the cheese during static and dynamic salting. The SOM network showed that the behavior of the diffusive process, on the surface of the cheese, depends on the analyzed position and that the points in which occupy similar positions, concerning the distance from the edge, have similar behavior. Regression models for NaCl and KCl were significant at the 5% level and can be used for predictive purposes.

RUL Prediction of Rolling Bearings Based on a DCAE and CNN

Predicting the remaining useful life (RUL) of mechanical equipment can improve production efficiency while effectively reducing the life cycle cost and failure rate. This paper proposes a method for predicting the remaining service life of equipment through a combination of a deep convolutional autoencoder (DCAE) and a convolutional neural network (CNN). For rolling bearings, a health indicator (HI) could be built by combining DCAE and self-organizing map (SOM) networks, performing more advanced characterization against the original vibration data and modeling the degradation state of the rolling bearings. The HI serves as the label of the original vibration data, and the original data with such label is input into the prediction model of the RUL based on a one-dimensional convolutional neural network (1D-CNN). The model was trained for predicting the RUL of a rolling bearing. The bearing degradation dataset was evaluated to verify the method’s effectiveness. The results demonstrate that the constructed HI can characterize the bearing degradation state effectively and that the method of predicting the RUL can accurately predict the bearing degradation trend.

An integrated condition monitoring method for rolling element bearings based on perceptual vibration hashing and SOM

Rolling element bearings are widely used in rotating machinery. Bearing faults will result in damage to property. So, the condition monitoring of bearings is of great significance, but few methods can achieve both degradation assessment and fault diagnosis. In this paper, an integrated condition monitoring method for rolling element bearings based on perceptual vibration hashing (PVH) and self-organizing maps (SOM) is proposed. Distance matric based on PVH is used as a health indicator for degradation assessment, in which the baseline of healthy state is selected based on the clustering centre of SOM instead of experience. When the value of health indicator exceeds the pre-set threshold, visualized fault diagnosis can also be achieved by training the SOM network. The effectiveness of the developed method is verified with the vibration data from accelerated degradation tests of rolling element bearings.

Evaluation of the Impacts of Abandoned Mining Areas: A Case Study with Benthic Macroinvertebrate Assemblages.

Mining activities are among the most long-lasting anthropogenic pressures on streams and rivers. Therefore, detecting different benthic macroinvertebrate assemblages in the areas recovered from mining activities is essential to establish conservation and management plans for improving the freshwater biodiversity in streams located near mining areas. We compared the stability of benthic macroinvertebrate communities between streams affected by mining activities (Hwangjicheon: NHJ and Cheolamcheon: NCA) and the least disturbed stream (Songjeonricheon: NSJ) using network analysis, self-organizing map, and indicator species analysis. Species richness was lowest at sites where stream sediments were reddened or whitened due to mining impacts in NHJ and NCA. Among functional feeding groups, the ratio of scrapers was lower (i.e., NHJ) or not observed (i.e., NCA) in the affected sites by mining. The networks (species interactions) were less connected in NHJ and NCA than in NSJ, indicating that community stability decreased in the area affected by mining activity. We identified five groups based on the similarity of benthic macroinvertebrate communities according to the gradients of mining impacts using a self-organizing map. the samples from the reference stream (clusters 1 and 5), sites located near the mining water inflow area (cluster 4), sites where stream sediments acid-sulfated (cluster 2), and sites that had recovered from mining impacts (cluster 3). Among the 40 taxa selected as indicators defined from the five clusters in self-organizing map, only few (Physa acuta, Tipula KUa, and Nemoura KUb) indicator species were selected in each cluster representing the mining-impacted sites. Our results highlighted that the benthic macroinvertebrate community complexity was lower in streams affected by mining activity. Furthermore, the range of disturbed areas in the streams, where conservation and management plans should be prioritized, can be quantified by examining alterations in the benthic macroinvertebrate community.

Self-Organizing Maps for Clustering Hyperspectral Images On-Board a CubeSat

Hyperspectral remote sensing reveals detailed information about the optical response of a scene. Self-Organizing Maps (SOMs) can partition a hyperspectral dataset into clusters, both to enable more analysis on-board the imaging platform and to reduce downlink time. Here, the expected on-board performance of the SOM algorithm is calculated within two different satellite operational procedures: one in which the SOM is trained prior to imaging, and another in which the training is part of the operations. The two procedures are found to have advantages that are suitable to quite different situations. The computational requirements for SOMs of different sizes are benchmarked on the target hardware for the HYPSO-1 mission, and dimensionality reduction (DR) is tested as a way of reducing the SOM network size. We find that SOMs can run on the target on-board processing hardware, can be trained reasonably well using less than 0.1% of the total pixels in a scene, are accelerated by DR, and can achieve a relative quantization error of about 1% on scenes acquired by a previous hyperspectral imaging satellite, HICO. Moreover, if class labels are assigned to the nodes of the SOM, these networks can classify with a comparable accuracy to support vector machines, a common benchmark, on a few simple scenes.