3D object classification using multi-object kohonen networks

Corridoni, J.M.; Bimbo, Alberto Del; Landi, Leonardo

doi:10.1016/0031-3203(95)00132-8

Cited by 17 publications

(4 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…) SOM has been extensively used in various application fields, for example, classification (Corridoni et al, 1996;Deschenes and Noonan, 1995;Li et al, 2011;Moreno et al, 2006;Silver and Shmoish, 2008), clustering (Mangiameli et al, 1996;Murtagh, 1995;Martín-del-Brío and Serrano-Cinca, 1993), and forecasting (Van Der Voort et al, 1996). The SOM has the advantage of identifying clusters in a dataset without the restrictive assumptions of the linearity or normality of more traditional statistical techniques (Moreno et al, 2006;Mostafa, 2009).…”

Section: Self-organizing Map (Som)mentioning

confidence: 99%

Bankruptcy Type Prediction Using A Hybrid Artificial Neural Networks Model

Jo¹,

Kim²,

Shin³

2015

Journal of Intelligence and Information Systems

View full text Add to dashboard Cite

Nam-ok JoㆍHyun-jung KimㆍKyung-shik Shin 80The experimental result shows that each of five bankruptcy types has different characteristics according to financial ratios. Type 1 (severe bankruptcy) has inferior financial statements except for EBITDA (earnings before interest, taxes, depreciation, and amortization) to sales based on the clustering results. Type 2 (lack of stability) has a low quick ratio, low stockholder's equity to total assets, and high total borrowings to total assets. Type 3 (lack of activity) has a slightly low total asset turnover and fixed asset turnover. Type 4 (lack of profitability) has low retained earnings to total assets and EBITDA to sales which represent the indices of profitability. Type 5 (recoverable bankruptcy) includes firms that have a relatively good financial condition as compared to other bankruptcy types even though they are bankrupt. Based on the findings, researchers and practitioners engaged in the credit evaluation field can obtain more useful information about the types of corporate bankruptcy.In this paper, we utilized the financial ratios of firms to classify bankruptcy types. It is important to select the input variables that correctly predict bankruptcy and meaningfully classify the type of bankruptcy. In a further study, we will include non-financial factors such as size, industry, and age of the firms. Thus, we can obtain realistic clustering results for bankruptcy types by combining qualitative factors and reflecting the domain knowledge of experts.

show abstract

Section: Self-organizing Map (Som)mentioning

confidence: 99%

Bankruptcy Type Prediction Using A Hybrid Artificial Neural Networks Model

Jo¹,

Kim²,

Shin³

2015

Journal of Intelligence and Information Systems

View full text Add to dashboard Cite

show abstract

“…Also, it is necessary to test multiple Kohonen maps, which get different views or subsets, e.g., the H, S, and I components of a coloi: image, as input. There has been already promising work [4], [5], in using multiple Kohonen maps with feature based input data. The Fourier transform of the log-polar images must be replaced, so that all available information can be used, which should lead to better classification results.…”

Section: A Artificial Test Setmentioning

confidence: 99%

A pixel based approach to view based object recognition with self-organizing neural networks

Elsen

IECON '98. Proceedings of the 24th Annual Conference of the IEEE Industrial Electronics Society (Cat. No.98CH36200)

View full text Add to dashboard Cite

This paper addresses the pixel based classification of three dimensional objccts from arbitrary views. To perform this task a coding strategy, inspired by the biological model of human vision, for pixel data is described. The coding strategy ensures, that the input data is invariant against shift, scale and rotation of the object in the input domain The image data is used as input to a class of self Self Organizing Feature Maps (SOFM). To verify this approach two test sets have been generated. The first set, consisting of artificially generated images is used to examine the classification properties of the SOFMs, the second test set, examines the clustering capabilities of the SOFM when real world image data is applied to the network after it has been preprocessed to be invariant against shift, scale and rotation. It is shown, that the clustering capability of the SOFM is strongly dependant of the invariance coding of the images. I organizing neural networks, the Kohonen-Maps or

show abstract

“…SOM is an unsupervised artificial neural network proposed by Teuvo Kohonen (KO-HONEN, 1982) and based on a competitive learning. It has been extensely used for many domains such as gesture recognition (CARIDAKIS et al, 2010), segmentation, visualization, clustering (TASDEMIR;MERÉNYI, 2009) and classification tasks (CORRIDONI;BIMBO;LANDI, 1996). Currently, SOM is a very useful tool in data analysis (KOHONEN, 2013).…”

Section: Introductionmentioning

confidence: 99%

Self-organization map in complex network

Pimenta¹

View full text Add to dashboard Cite

This work is dedicated to God for allowing me to fulfill a desire of my heart and is also dedicated to my husband. Thank you for your unconditional support. I would like to thank Prof. Francisco Rodrigues for supervising this Ph.D. and for introducing me to the world of complex networks. I am very grateful to Prof. Luciano da Fontoura Costa for giving me the opportunity to work and learn from him. I am also very grateful to Prof. Cesar Comin for his pertinent comments, suggestions about the work developed in this thesis.

show abstract

3D object classification using multi-object kohonen networks

Cited by 17 publications

References 39 publications

Bankruptcy Type Prediction Using A Hybrid Artificial Neural Networks Model

Bankruptcy Type Prediction Using A Hybrid Artificial Neural Networks Model

A pixel based approach to view based object recognition with self-organizing neural networks

Self-organization map in complex network

Contact Info

Product

Resources

About