Modified Self-Organizing Feature Map Neural Network with Semi-supervision for Change Detection in Remotely Sensed Images

Generalized part family formation through fuzzy self-organizing feature map neural network

A method for automatic detection of weld defects of short-circuit gas metal arc welding is presented. It is based on the extraction of arc signal features as well as classification of the obtained features using self-organizing feature map (SOM) neural networks in order to get the weld quality information, for example, to determine if there is a defect in the product. This is important for the online monitoring of weld quality especially in robotic welding and lays the foundation for further real-time control of weld quality.

Decomposition of interacting features using a Kohonen self-organizing feature map neural network

Traditional sensor fault diagnosis is mainly based on statistical classification methods. The discriminant functions in these methods are extremely complex, and typical samples of reference modes are not easy to get, therefore it is difficult to meet the actual requirements of a project. In view of the deficiencies of conventional sensor fault diagnosis technologies, a fault diagnosis method based on self-organizing feature map (SOFM) neural network is presented in this paper. And it is applied to the fault diagnosis of pipeline flow sensor in a dynamic system. The simulation results show that the fault diagnosis method based on SOFM neural network has a fast speed, high accuracy and strong generalization ability, which verifies the practicality and effectiveness of the proposed method.

The image edge detection is rather difficult due to its natures of diversity and complexity. For retaining correlations between the three color components of color medical images and avoiding human intervention such as setting threshold of image edge judgment, a novel edge detection method for color medical images has been proposed in this paper. The approach proposed here combines the self-organizing feature map (SOFM) neural network and quaternion. Based on the rotation characteristic of quaternion in 3D vector space and reprocessing results by calculating the Euclidean distance, an edge characteristic vector has been constructed. The SOFM neural network is trained by the vector and subsequently used for edge detection. The experimental results demonstrate the method has stronger retention capacity of the details. The noise can be removed based on the method when 30 or more neurons network is adopted.

To address the problems of high overflow rate of pipe network inspection well and low drainage efficiency, a rainwater control optimization design approach based on a self-organizing feature map neural network model (SOFM) was proposed in this paper. These problems are caused by low precision parameter design in various rainwater control measures such as the diameter of the rainwater pipe network and the green roof area ratio. This system is to be combined with the newly built rainwater pipe control optimization design project of China International Airport in Daxing District of Beijing, China. Through the optimization adjustment of the pipe network parameters such as the diameter of the rainwater pipe network, the slope of the pipeline, and the green infrastructure (GI) parameters such as the sinking green area and the green roof area, reasonable control of airport rainfall and the construction of sustainable drainage systems can be achieved. This research indicates that compared with the result of the drainage design under the initial value of the parameter, the green roof model and the conceptual model of the mesoscale sustainable drainage system, in the case of a hundred-year torrential rainstorm, the overflow rate of pipe network inspection wells has reduced by 36% to 67.5%, the efficiency of drainage has increased by 26.3% to 61.7%, which achieves the requirements for reasonable control of airport rainwater and building a sponge airport and a sustainable drainage system.

It's difficult to build precise mathematical models for complex engineering systems because of the complexity of the structure and dynamics characteristics. Intelligent fault diagnosis introduces artificial intelligence and works in a different way without building the analytical mathematical model of a diagnostic object, so it's a practical approach to solve diagnostic problems of complex systems. This paper presents an intelligent fault diagnosis method, an integrated fault-pattern classifier based on Hidden Markov Model (HMM). This classifier consists of dynamic time warping (DTW) algorithm, self-organizing feature mapping (SOFM) network and Hidden Markov Model. First, after dynamic observation vector in measuring space is processed by DTW, the error vector including the fault feature of being tested system is obtained. Then a SOFM network is used as a feature extractor and vector quantization processor. Finally, fault diagnosis is realized by fault patterns classifying with the Hidden Markov Model classifier. The importing of dynamic time warping solves the problem of feature extracting from dynamic process vectors of complex system such as aeroengine, and makes it come true to diagnose complex system by utilizing dynamic process information. Simulating experiments show that the diagnosis model is easy to extend, and the fault pattern classifier is efficient and is convenient to the detecting and diagnosing of new faults.

Since the reform and opening up, China's regional economy has developed rapidly. However, due to different starting points of economic development caused by the traditional distribution of productive forces and the differences in regions, resources, technologies, and policies, the level of economic development in different regions is uneven. Clustering analysis is a data mining method that clusters or classifies entities according to their characteristics and then discovers the whole spatial distribution law of datasets and typical patterns. It is of great significance to classify, compare, and study the economic development level of different regions in order to formulate the regional economic development strategy. In this paper, a self-organizing feature map (SOM) neural network with the hybrid genetic algorithm is used to cluster the differences of regional economic development, the clustering results are evaluated, and the empirical results are good. From this, some meaningful conclusions can be drawn, which can provide reference for the decision-making of coordinating regional economic development.

China’s vast rural landscape exhibits pronounced regional disparities in both foundational resources and development potential. In the context of nationwide rural revitalization efforts, the emergent divergence in village development pathways underscores a pressing need for context-specific, classified interventions. To furnish a scientifically grounded typology of villages and inform differentiated development planning, this investigation focuses on Hubei Province as an illustrative case. Synthesizing survey data from 32,457 villages, we developed a multidimensional evaluation framework encompassing four pivotal domains: economic vitality, social service provision, ecological integrity, and cultural value. Leveraging the Self-Organizing Feature Map (SOFM) neural network—an unsupervised machine learning algorithm—we performed a cluster analysis on multi-source, heterogeneous datasets. This technique enabled the objective delineation of spatial typological patterns among Hubei’s villages, elucidated their underlying classification architecture shaped by multifaceted drivers, and demonstrated the methodological robustness and applicability of this approach for large-scale village categorization. Grounded in the derived typologies and informed by strategic directives from higher-tier planning instruments, we conducted a nuanced examination of the distinctive attributes characterizing each village type. The findings provide scientific evidence and decision-making support for village classification and rural revitalization planning in Hubei Province, with valuable implications for other regions with similar development foundations in China.

In this article, a one-dimensional self-organizing feature map (SOFM) neural network integrated with semi-supervised learning is used to predict the class label of gene expression data under the scarcity of the labeled patterns. Iterative learning of the semi-supervised SOFM network is carried out using a few labeled patterns along with some selected unlabeled patterns. The unlabeled patterns, for which the maximum target value is greater than a threshold, are selected as the confident ones. Results are found to be encouraging.KeywordsSemi-supervised learninggene expression dataself- organizing feature map

SummaryIn order to suppress the interference in local area networks, this paper presents a Wireless Local Area Networks (WLAN) interference self‐optimization method based on a Self‐Organizing Feature Map (SOM) neural network model. This method trains the model by using original data sets as the initial vector set and using the whole Signal to Interference plus Noise Ratio (SINR) vector generated by the change of one Wireless Access Point (AP) channel as the basic feature. After the training, the SOM neural network can quickly locate the fault AP and optimize the network according to the changes of the network environment. Simulation results reveal that the proposed scheme can efficiently locate the AP where interference happens and optimize the interference with an improved user experience. Copyright © 2016 John Wiley & Sons, Ltd.

At present, study on the non-asbestos gasket materials is the hotspot research in static sealing field. The non-asbestos sealing gaskets research and development has made great strides into the practical phase. Formula is an important factor of material, which determines performance of material. In order to obtain well performance, it is needed to optimization formula to get optimal formula that not only improve performance of non-asbestos gasket, but also reduce development time accordingly reduce cost of non-asbestos gasket. Classification of raw materials can be transformed into a mathematical clustering problem. It means that according to some algorithm, there will be some sort of input values of similar links together. Many neural networks were widely used in the classification of different materials. A method of classification by using neural network to the known 15 kinds of the non-asbestos gaskets of formula data was proposed in this paper. By using the PNN (probabilistic neural network), LVQ(Learning Vector Quantization) neural network and SOM (Self-Organizing Feature Map) neural network respectively to classify the non-asbestos gaskets to find a suitable method in the classification of non-asbestos gaskets formula. The results indicated that PNN neural network and LVQ neural network method based on the data that provided in the paper both can effectively classify, while SOM neural network can not classify them ideally, thus it provides a new theoretical basis for the classification of the non-asbestos gaskets.

Combining rough set theory and self-organizing feature map (SOFM) neural network, a method was presented for the car's plate character recognition. The features of the training samples were extracted to build up the decision table; the discretization algorithm of decision attributes was proposed based on the clustering ability of SOFM network; the rough set theory was applied to reduce the decision table. Finally, the reduced decision attributes were used to construct neural network recognizing machine. The method can reduce the numbers of attributes in the decision table, simplify the structure of neural network and improve the ability of generality. The experiment results of the car's plate character recognition show that the algorithms are practical and effective.

A novel approach for fault detection and isolation (FDI) is proposed. In order to detect the faults that reflect themselves as fault-induced frequency changes at certain time instants in the measured signal, wavelet analysis is applied to capture such changes and extract fault features on line and in real-time. An improved self-organizing feature map (SOM) neural network is then used to isolate the fault. By introducing the concept of hierarchy training and zone recognizing, the improved SOM neural network proposed in this paper has achieved higher clustering and matching-up precision compared to the conventional SOM network. Therefore, the proposed FDI scheme is more accurate.

To obtain a speaker’s pronunciation characteristics, a method is proposed based on an idea from bionics, which uses spectrogram statistics to achieve a characteristic spectrogram to give a stable representation of the speaker’s pronunciation from a linear superposition of short-time spectrograms. To deal with the issue of slow network training and recognition speed for speaker recognition systems on resource-constrained devices, based on a traditional SOM neural network, an adaptive clustering self-organizing feature map SOM (AC-SOM) algorithm is proposed. This algorithm automatically adjusts the number of neurons in the competition layer based on the number of speakers to be recognized until the number of clusters matches the number of speakers. A 100-speaker database of characteristic spectrogram samples was built and applied to the proposed AC-SOM model, yielding a maximum training time of only 304 s, with a maximum sample recognition time of less than 28 ms. Comparing to other approaches, the proposed method offers greatly improved training and recognition speed without sacrificing too much recognition accuracy. The promising results suggest that the proposed method satisfies real-time data processing and execution requirements for edge intelligence systems better than other speaker recognition methods.