Aniket D. Profile

OBJEVUJTE

0,0

(0 recenze)

Nyní sledujete

Chyba při sledování uživatele.

Tento uživatel neumožňuje ostatním uživatelům, aby jej sledovali.

Tohoto uživatele již sledujete.

Váš členský plán povoluje pouze 0 sledovaných. Aktualizujte zde.

Úspěšně odebráno sledování

Při rušení sledování uživatele došlo k chybě.

Úspěšně jste doporučili uživatele

Chyba při doporučování uživatele.

Došlo k chybě. Obnovte stránku a zkuste to znovu.

E-mail byl úspěšně ověřen.

pune,

india

Aktuálně je zde 8:09 dop.

Připojil se května 3, 2007

0 Doporučení

Aniket D.

@aniketd

0,0

(0 recenze)

0,0

pune,

india

Nedostupné

Úspěšně realizované projekty

Nedostupné

V rámci rozpočtu

Nedostupné

Včas

Nedostupné

Poměr opětovného zaměstnání

Research Consultant: Machine Learning, NLP, Big Data Analytics

Research Consultant: Semantic solutions, NLP, IR , Hadoop based solutions and Data Mining

Zobrazit všechny Java Developers v India

Kontaktujte Aniket D. ohledně vaší práce

Přihlaste se a proberte všechny podrobnosti prostřednictvím chatu.

Recenze

Změny byly uloženy

K dispozici nejsou žádné recenze.

Zkušenosti

Semantic Labs

srp 2008 - Současnost

Provide research consultation for problems in the area of: * Natural Language Processing : NLP is used in developing solutions for sentiment analysis, language translation, document summarization, Named Entity such as Person/Place/Company name identification, Key concept generation etc. * Statistical Machine Learning : Machine learning algorithms provide ability to build statistical model over sufficiently large data set that can assist human in decision making. There are wide ranges of learning algo

Yahoo! R&D

dub 2007 - čvc 2008 (1 , 3 měsíce)

Worked as a software developer in Advanced Technology Group (ATG). • Information Extraction for Yahoo! Verticals: I worked in research and development team focused on information extraction from semi-structured web pages using machine learning techniques. The goal was to build a pipeline consisting of multiple phases primarily consisting of Annotation, Pattern Learning, Extraction and Filtering. Each of these modules was computationally time and memory consuming and hence was distributed over a grid. The

Persistent System Limited

čvn 2003 - čvn 2005 (2 roky)

Worked as a software developer in Life Sciences division. I worked in development team of Agilent Synapsia

Vzdělání

Master of Technology (MTech)

Indian Institute of Technology, Bombay,

India

2005 - 2007

(2 roky)

Bachelor of Engineering

Goa University,

India

1999 - 2003

(4 roky)

Kvalifikace

Sun Microsystems

2004

Publikace

GIPSCo: A Method for Comparison of Protein Structures Based on Geometric Invariants

International Conference on bioinformatics and Computational Biology (BIOCOMP), 2008 Las Vegas

Protein structure comparison is important for elucidation of evolutionary relationships, function and functionally important amino acid residues. We propose Geometric Invariant based Protein Structure Comparison (GIPSCo), an approach that compares a protein pair by using geometric invariants of local geometry of the backbone structures. The geometric invariants capture enough structural information so that the method has a relatively low false positive rate. The method first generates a list of aligned frag

Building Feature Rich POS Tagger for Morphologically Rich Languages

International Conference on NLP (ICON '07)

In this paper we present a statistical partof-speech(POS) tagger for a morphologicallyrich language: Hindi. To the best of our knowledge, our tagger achieves the highest reported tagging accuracy for Hindi. Our tagger employs the maximum entropy Markov model with a rich set of features capturing the lexical and morphological characteristics of the language. The feature set was arrived at after an exhaustive analysis of an annotated corpus. The morphological aspects are addressed by features based on informa

Protein Structure Classification Using Geometric Invariants and Dynamic Programming

Bentham Science Publishers

Classification of newly determined protein structures is important in understanding their function and mechanism of action. Currently available methods employ a global structure alignment strategy and are computationally expensive. We propose a two-step methodology with a quick screen to significantly reduce the number of candidate structures followed by global structure alignment of the query structure with the reduced set. We represent a protein structure as a sequence of local structures, codified in the