Comparison of Two Document Clustering Techniques which use Neural Networks

Mokris, I.; Skovajsová, Lenka

doi:10.1109/icccyb.2008.4721382

Cited by 8 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Akar dari pohon atau dendogram menggambarkan jumlah cluster, sementara daunnya akan menggambarkan letak satu elemen atau objek dalam satu cluster tertentu [14]. Dalam penelitian ini, algoritma yang digunakan adalah pendekatan bottom-up manner, yaitu dimulai dari mengasumsikan bahwa jumlah cluster adalah sama dengan jumlah elemen dan pada setiap penambahan height, cluster akan digabungkan hingga jumlah yang diinginkan atau sesuai dengan penentuan k optimal [15].…”

Section: Hierarchical Clusteringunclassified

Analisis Perbandingan Metode Hierarchical dan Non-Hierarchical dalam Pembentukan Cluster Provinsi di Indonesia Berdasarkan Indikator Women Empowerment

Aselnino,

Wijayanto

2024

IJAS

View full text Add to dashboard Cite

The focus on improving the quality of women’s live to lessen discrimination and gender inequality is set in the fifth’s goals of SDGs. In Indonesia, the RPJMN 2020-2024 contains measure to improve the contribution of women to equitable development. The Central Bureau of Statistics has developed several indicators related to gender, including Gender Development Index (GDI) an Gender Empowerment Index (GEI), which contain women’s improvement on education and health as well as their participation in economic and political fields. The Ministry of Women’s Empowerment and Child Protection did a quadrant analysis to split Indonesia’s 34 provinces into four categories based solely on GDI and GEI using the national average as a constraint. This study compares the Hierarchical, K-Means, and Fuzzy C-Means method to form number of clusters in Indonesia based on the gender development and empowerment in 2021 in order to complement the quadrant analysis. To choose the number of optimum cluster, Elbow method and Calinski-Harabasz Index were used and the best k value is five. From the validation with Silhoutte Index, K-Means was chosen as the best clustering model.Keywords: clustering; fuzzy; k-means; hierarchical; women empowerment

show abstract

Section: Hierarchical Clusteringunclassified

Analisis Perbandingan Metode Hierarchical dan Non-Hierarchical dalam Pembentukan Cluster Provinsi di Indonesia Berdasarkan Indikator Women Empowerment

Aselnino,

Wijayanto

2024

IJAS

View full text Add to dashboard Cite

show abstract

“…Each section/subsection of the documents is transformed into a vector space, where the entries of vector are TF-IDF values. Finally, cosine similarity [20], is used to investigate hierarchical relevance between the reformulated query (expanded query) and sections/subsections in a Vector Space Model (VSM) model. N -grams (N <= 3) is used to create new tokens from the preprocessed sections, new tokens are included with uni-grams in a Bag of words [24].…”

Section: Document Reconstructionmentioning

confidence: 99%

Automatic knowledge extraction from OCR documents using hierarchical document analysis

Masum

Kosaraju

Bayramoglu³

et al. 2018

Proceedings of the 2018 Conference on Research in Adaptive and Convergent Systems

View full text Add to dashboard Cite

Industries can improve their business efficiency by analyzing and extracting relevant knowledge from large numbers of documents. Knowledge extraction manually from large volume of documents is labor intensive, unscalable and challenging. Consequently, there have been a number of attempts to develop intelligent systems to automatically extract relevant knowledge from OCR documents. Moreover, the automatic system can improve the capability of search engine by providing application-specific domain knowledge. However, extracting the efficient information from OCR documents is challenging due to highly unstructured format [1, 11, 18, 26]. In this paper, we propose an efficient framework for a knowledge extraction system that takes keywords based queries and automatically extracts their most relevant knowledge from OCR documents by using text mining techniques. The framework can provide relevance ranking of knowledge to a given query. We tested the proposed framework on corpus of documents at GE Power where document consists of more than hundred pages in PDF.

show abstract

“…This final metric is a scaled variant of cosine similarity. Such a measure of cosine similarity has wide usage across several fields, of which we cite a few examples . Although this method is the most abstract—and perhaps least intuitive—of the three, we have found it useful in identifying what we have termed “dynamic domains.” These domains are (not necessarily local) sets of residues with similar dynamics, as indicated by their correlated motion vectors.…”

Section: Introductionmentioning

confidence: 99%

Visualizing correlated motion with HDBSCAN clustering

et al. 2017

View full text Add to dashboard Cite

Correlated motion analysis provides a method for understanding communication between and dynamic similarities of biopolymer residues and domains. The typical equal-time correlation matrices-frequently visualized with pseudo-colorings or heat maps-quickly convey large regions of highly correlated motion but hide more subtle similarities of motion. Here we propose a complementary method for visualizing correlations within proteins (or general biopolymers) that quickly conveys intuition about which residues have a similar dynamic behavior. For grouping residues, we use the recently developed non-parametric clustering algorithm HDBSCAN. Although the method we propose here can be used to group residues using correlation as a similarity matrix-the most straightforward and intuitive method-it can also be used to more generally determine groups of residues which have similar dynamic properties. We term these latter groups" Dynamic Domains", as they are based not on spatial closeness but rather closeness in the column space of a correlation matrix. We provide examples of this method across three human proteins of varying size and function-the Nf-Kappa-Beta essential modulator, the clotting promoter Thrombin and the mismatch repair protein (dimer) complex MutS-alpha. Although the examples presented here are from all-atom molecular dynamics simulations, this visualization technique can also be used on correlations matrices built from any ensembles of conformations from experiment or computation.

show abstract

Comparison of Two Document Clustering Techniques which use Neural Networks

Cited by 8 publications

References 11 publications

Analisis Perbandingan Metode Hierarchical dan Non-Hierarchical dalam Pembentukan Cluster Provinsi di Indonesia Berdasarkan Indikator Women Empowerment

Analisis Perbandingan Metode Hierarchical dan Non-Hierarchical dalam Pembentukan Cluster Provinsi di Indonesia Berdasarkan Indikator Women Empowerment

Automatic knowledge extraction from OCR documents using hierarchical document analysis

Visualizing correlated motion with HDBSCAN clustering

Contact Info

Product

Resources

About