Application of Self Organizing Map (SOM) to model a machining process

Saraee, Mohamad; Moosavi, Seyed Vahid; Rezapour, Shabnam

doi:10.1108/17410381111149666

Cited by 9 publications

(3 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The software platform was Anaconda 2.7. The specific implementations of the SOM library [46] and the RuLSIF library [16]. The Tensorflow is used for deep autoencoder implementation.…”

Section: Implementation and Data Analysismentioning

confidence: 99%

A Mobile Telematics Pattern Recognition Framework for Driving Behavior Extraction

Siami

Naderpour

2021

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

Mobile telematics is a relatively new innovation that involves collecting data on driving behavior using the internal sensors in a smartphone rather than from an in-vehicle data recorder. However, telematics data are usually not labeled, which makes extracting driving patterns from them very difficult. Therefore, unsupervised learning algorithms play an important role in this field. In addition, most current research is based on datasets developed in a laboratory or from site investigations and questionnaires, which are very different from real-world driving behaviors. To advance unsupervised learning techniques in this field, and to fill the gap in findings based on real-world data, we have developed an unsupervised pattern recognition framework for mobile telematics data. The framework comprises three main components: a self-organizing map, a nine-layers deep autoencoder, and partitive clustering algorithms. The SOM algorithm reduces the complexity of the data, the deep auto-encoder extracts the features, and the clustering algorithm groups driving events with similar patterns into behaviors. Further, given clustering with mobile telematics data is an under-researched area, we undertook an empirical comparison of five well-known clustering algorithms to determine the strengths and weaknesses of each method and which is best suited to categorizing driving styles. The study was conducted with a real-world insurance dataset containing 500,000 journeys by 2500 drivers, and the results were evaluated against three measures -Davis Boulding, Calinski Harabasz, and execution time. Overall, we find that k-means clustering and a self-organizing map were able to extract more accurate patterns than others. A statistical analysis of the 29 clusters produced by SOM and k-means, revealed 29 unique driving styles, all of which can be found in the transportation literature. The results from the study, with support from the corresponding literature review, demonstrate the efficacy of the presented framework in unsupervised settings. Additionally, the results provide a basis for developing a future risk analysis and automatic decision support system for usage-based insurance companies.

show abstract

“…The software platform was Anaconda 2.7. The specific implementations of the SOM library [46] and the RuLSIF library [16]. The Tensorflow is used for deep autoencoder implementation.…”

Section: Implementation and Data Analysismentioning

confidence: 99%

A Mobile Telematics Pattern Recognition Framework for Driving Behavior Extraction

Siami

Naderpour

2021

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

show abstract

“…Generally, SOM is a prominent unsupervised neural network model with many applications. For instance, it is applied in cases where the dimensions of the feature spaces should be evaluated and there is an excessively high level of data encountered to enable a rapid and interactive training of the neural network (Saraee et al, 2011). Due to its flexibility and visualization abilities, SOM is a suitable method for clustering applications and representation of information, which probably are difficult processes in other clustering techniques (Minis, 2007).…”

Section: Introductionmentioning

confidence: 99%

A neural network approach for retailer risk assessment in the aftermarket industry

Rezaei

Shokouhyar

Zandieh

2019

BIJ

View full text Add to dashboard Cite

Purpose Given the competitive environment and complicated relationships in supply chains in the modern era, it is important to take into account internal and external risks. In addition, proper methods must be designed to evaluate these risks correctly. The purpose of this paper is to provide a suitable map based on the artificial neural network technique to assess and classify the risk levels of retailers who have interconnected rules in the downstream of the supply chain. Design/methodology/approach In this research, a model for risk assessment with a hexagonal grid and 2D self-organizing map was applied. Findings According to the results, the model used in the study can provide a basis for classification of retailers based on the specified risk levels defined by the experts and risk managers of the company. Also with the model’s visual output, managers can have a better understanding of the distribution of the risk level of retailers. Practical implications The proposed methodology can be adopted by managers to assess the risk of members involved in the supply chain, helping them to formulate the risk mitigation strategies based on the risk levels. Originality/value As a part of the risk management process, organizations can use this developed method to reduce the existing risks imposed by the members or customers on the company.

show abstract

“…With the help of the Artificial Neural Network (ANN), the performance of automatic design can be improved. The underlying relations between input and output variables as well as interactions between input variables artificial can be analysed by neural network (Saraee et al, 2011), avoiding the drawbacks of setting generation rules subjectively, and having a better performance than the traditional automatic design.…”

Section: Introductionmentioning

confidence: 99%

Automatic Design of Main Pedestrian Entrance of Building Site Based on Machine Learning - A Case Study of Museums in China's Urban Environment

Wang¹,

Song²,

Yu³

et al. 2018

CAADRIA Proceedings

View full text Add to dashboard Cite

The main pedestrian entrance of the building site has a direct influence on the use of the buildings, so the selection of the main pedestrian entrance is very important in the process of architectural design. The correct selection of the main pedestrian entrance of building site depends on the experience of designers and environment data collected by designers, the process is time consuming and inefficient, especially when the building site located in complex urban environment. In order to improve the efficiency of design process, we used online map to collect museums information in China as training samples, and constructing artificial neural networks to predict the direction of the main pedestrian entrance. After the training, we get the prediction model with 79% prediction accuracy. Although the accuracy still need to be improved, it creates a new approach to analysis the main pedestrian entrance of the site and worth further researching.

show abstract

Application of Self Organizing Map (SOM) to model a machining process

Cited by 9 publications

References 18 publications

A Mobile Telematics Pattern Recognition Framework for Driving Behavior Extraction

A Mobile Telematics Pattern Recognition Framework for Driving Behavior Extraction

A neural network approach for retailer risk assessment in the aftermarket industry

Automatic Design of Main Pedestrian Entrance of Building Site Based on Machine Learning - A Case Study of Museums in China's Urban Environment

Contact Info

Product

Resources

About