Data Mining: Next Generation Challenges and FutureDirections

Purpose Due to rapid technological evolution driven by display manufacturers, the television (TV) market of flat panel displays has been fast growing with the advancement of digital technologies in broadcasting service. Recently, organic light-emitting diode (OLED) successfully penetrated into the large-size TV market, catching up with light-emitting diode (LED)-liquid-crystal display (LCD). This paper aims to investigate the market penetration of OLED technologies by determining their technology adoption rates based on a diffusion model. Design/methodology/approach Through the rapid evolution of information and communication technology, as well as a flood of data from diverse sources such as research awards, journals, patents, business press, newspaper and Internet social media, data mining, text mining, tech mining and database tomography have become practical techniques for assisting the forecaster to identify early signs of technological change. The information extracted from a variety of sources can be used in a technology diffusion model, such as Fisher-Pry where emerging technologies supplant older ones. This paper uses a comparison-based prediction method to forecast the adoption and diffusion of next-generation OLED technologies by mining journal and patent databases. Findings In recent years, there has been a drastic reduction of patents related to LCD technologies, which suggests that next-generation OLED technology is penetrating the TV market. A strong industry adoption for OLED has been found. A high level of maturity is expected by 2026. Research limitations/implications For OLED technologies that are closely tied to industrial applications such as electronic display devices, it may be better to use more industry-oriented data mining, such as patents, market data, trade shows, number of companies or startups, etc. The Fisher-Pry model does not address the level of sales for each technology. Therefore, the comparison between the Bass model and the Fisher-Pry model would be useful to investigate the market trends of OLED TVs further. Another step for forecasting could include using industry experts and a Delphi model for forecasting (and further validation). Originality/value Fisher-Pry growth curves for journal publications and patents follow the expected sequence. Specially, journal publications and patents growth curves are close for OLED technologies, indicating a strong industry adoption.

Download Full-text

Data Mining: The Next Generation (Data Mining: Die nächste Generation)

it - Information Technology ◽

10.1524/itit.2005.47.5_2005.308 ◽

2005 ◽

Vol 47 (5) ◽

Author(s):

Johann-Christoph Freytag ◽

Raghu Ramakrishnan ◽

Rakesh Agrawal

Keyword(s):

Data Mining ◽

Research And Development ◽

First Generation ◽

Pattern Discovery ◽

Database Systems ◽

Important Application ◽

Next Generation ◽

Critical Problems ◽

Conference Center

SummaryData Mining has enjoyed great popularity in recent years, with advances in both research and commercialization. The first generation of data mining research and development has yielded several commercially available systems, both stand-alone and integrated with database systems, produced scalable versions of algorithms for many classical data mining problems and introduced novel pattern discovery problems. In July 2004 researchers from a variety of backgrounds assembled at the Dagstuhl Conference Center in Germany for a workshop to re-assess the current directions of the field, to identify critical problems that require attention, and to discuss ways to increase the flow of ideas across the different disciplines that Data Mining has brought together. The workshop did not seek to draw up an agenda for the field of data mining. Rather, it offers the participants' perspective on two technical directions – compositionality and privacy – and describes some important application challenges which drove the discussion.

Download Full-text

Observed Antibody Space: a resource for data mining next generation sequencing of antibody repertoires

10.1101/316026 ◽

2018 ◽

Cited By ~ 1

Author(s):

Aleksandr Kovaltsuk ◽

Jinwoo Leem ◽

Sebastian Kelm ◽

James Snowden ◽

Charlotte M. Deane ◽

...

Keyword(s):

Data Mining ◽

Immune System ◽

Next Generation Sequencing ◽

Sequence Diversity ◽

Immunoglobulin Gene ◽

Next Generation ◽

Natural Diversity ◽

Antibody Repertoires ◽

Generation Sequencing

AbstractAntibodies are immune system proteins that recognize noxious molecules for elimination. Their sequence diversity and binding versatility have made antibodies the primary class of biopharmaceuticals. Recently it has become possible to query their immense natural diversity using next-generation sequencing of immunoglobulin gene repertoires (Ig-seq). However, Ig-seq outputs are currently fragmented across repositories and tend to be presented as raw nucleotide reads, which means nontrivial effort is required to reuse the data for analysis. To address this issue, we have collected Ig-seq outputs from 53 studies, covering more than half a billion antibody sequences across diverse immune states, organisms and individuals. We have sorted, cleaned, annotated, translated and numbered these sequences and make the data available via our Observed Antibody Space (OAS) resource at antibodymap.org. The data within OAS will be regularly updated with newly released Ig-seq datasets. We believe OAS will facilitate data mining of immune repertoires for improved understanding of the immune system and development of better biotherapeutics.

Download Full-text