3225 Slices
Medium 9781601322340

A novel method for finding sub-classification diagnosis biomarkers of ovarian cancer

Hamid R. Arabnia; Quoc-Nam Tran (Editors) Mercury Learning and Information PDF

Int'l Conf. Bioinformatics and Computational Biology | BIOCOMP'13 |

A novel method for finding sub-classification diagnosis biomarkers of ovarian cancer

Quoc-Nam Tran† ,

The University of Texas at Tyler, USA.

Abstract— Ovarian cancer is the most lethal gynaecological malignancy, accounting for 5–6% of all cancerrelated deaths. When ovarian cancer is diagnosed at early stages, the survival rate is very high - close to

90%. However, since ovarian cancer has few early or specific symptoms, the vast majority of patients are identified when they have late-stage disease. A typical molecular sub-classification method would have a low predictive accuracy of 68%-71%. Hence, discovering cost-effective biological markers that can be used to improve the diagnosis and prognosis of the disease is an important challenge.

In this paper, we present a new statistical and data mining method, called the multi-pronged filter method, to find genetic markers and uses the markers to predict with up to 100% accuracy whether a patient has a sub-type of epithelial ovarian cancer. Our method overcomes many challenges arose from datasets of gene-expression profiles. The new method discovers novel genetic changes that occur in ovarian tumors using gene-expression profiles. We discovered that a small set of eleven gene-signatures (TFF3, FGFR4,

See All Chapters
Medium 9781601322470

Automated Financial Data Extraction – An AI Approach

Hamid R. Arabnia; David de la Fuente; Elena B. Kozerenko; Peter M. LaMonica; Raymond A. Liuzzi; Todd Waskiewicz; George Jandieri; Ashu M. G. Solo; Ivan Nunes da Silva; Fernando G. Tinetti; and Fadi Thabtah (Editors) Mercury Learning and Information PDF

Int'l Conf. Artificial Intelligence | ICAI'13 |

801

Automated Financial Data Extraction – An AI Approach

Hassan Alam, Aman Kumar, Cheryl Lee, Yuliya Tarnikova1

Abstract— Using Natural Language Processing and Pattern

Recognition methods, BCL Technologies has developed a financial data extraction system called SmartXBRL©, that simplifies and automates ways to create a compliant XBRL document. In this paper we describe the steps necessary to extract and tag detailed Notes data in a 10-Q financial document. Methods to identify and extract the face financial tables, Document and Entity Information (DEI), and

Parenthetical are also reviewed, in addition to providing updated results.

I. INTRODUCTION

XBRL (eXtensible Business Reporting Language) is a technical standard for describing financial and related data. XBRL is a way to assign standard tags to financial data in reports and systems so the values can be analyzed in context by a computer application.

XBRL compliance requires that all disclosure elements in a financial report—every numeric value and supporting reference, including footnotes—must be identified with specific “tags” according to a standardized system. These XBRL tags define the context for the disclosure elements, so that they can be analyzed as structured data.

See All Chapters
Medium 9781683922025

Late Papers- Wireless Networks

Edited by Hamid R. Arabnia, Leonidas Deligiannidis, Ashu M.G. Solo CSREA Press PDF

Int'l Conf. Wireless Networks | ICWN'17 |

107

SESSION

LATE PAPERS - WIRELESS NETWORKS

Chair(s)

TBA

ISBN: 1-60132-462-6, CSREA Press ©

108

Int'l Conf. Wireless Networks | ICWN'17 |

ISBN: 1-60132-462-6, CSREA Press ©

Int'l Conf. Wireless Networks | ICWN'17 |

109

Space-Time Coded Massive MIMO for Next

Generation Wireless Systems

Jeremy J. Ice, Reza Abdolee, and Vida Vakilian

Dept. of Computer and Electrical Engineering, California State University, Bakersfield, California

Abstract—This paper serves as an evaluation of an experimental wireless communications technique called space-time coded massive (STCM) multiple-input multiple-output (MIMO). The

STCM-MIMO system utilizes two massive MIMO antenna arrays which transmit data over two channel vectors to a user with one receive antenna. This configuration permits the system to use the asymptotic orthogonal qualities of massive MIMO pre-coding to eliminate the interference from other users’ channel vectors and signals. The system also maintains the diversity of space-time codes to recover lost data through treating each transmitting massive MIMO array similarly to how a 2×1 Alamouti spacetime code would treat each transmitting antenna. Our results show that a wireless system with the proposed STCM-MIMO technology can significantly outperform those with space-time coding techniques.

See All Chapters
Medium 9781601322470

Applying Knowledge Model to Agent Based Systems

Hamid R. Arabnia; David de la Fuente; Elena B. Kozerenko; Peter M. LaMonica; Raymond A. Liuzzi; Todd Waskiewicz; George Jandieri; Ashu M. G. Solo; Ivan Nunes da Silva; Fernando G. Tinetti; and Fadi Thabtah (Editors) Mercury Learning and Information PDF

50

Int'l Conf. Artificial Intelligence | ICAI'13 |

Applying Knowledge Model To Agent Based

Systems

Khaoula ADDAKIRI

Mohamed BAHAJ

Hassan 1 University, FSTS

Department of Mathematics and Computer Science

Khaoula.addakiri@gmail.com

Hassan 1 University, FSTS

Department of Mathematics and Computer Science mohamedbahaj@gmail.com

Abstract— Nowadays, multi-agent system is become promising means for the development of distributed systems, however its disadvantage is that it lacks the interconnection with semantic web such as Ontology Web Language (OWL). In this article, we aim to present a semantic knowledge model of an agent suitable for discrete environments as well as implementation and a use of such model using different softwares

(JENA, JADE, JESS and Protégé) in order to allows interconnection of Agent and Semantic Web technologies which can be used in an agent based application where such interconnection is needed.

Keywords— Multi Agent System ; Web Ontology Language

(OWL); Java Expert System Shell (JESS); SPARQL1.1.

See All Chapters
Medium 9781601323156

The Design of an Embedded Self-Diagnostic Hybrid Aquarium Control System

Hamid R. Arabnia, Leonidas Deligiannidis, George Jandieri, Ashu M. G. Solo, Fernando G. Tinetti CSREA Press PDF

Int'l Conf. Embedded Systems and Applications | ESA'14 |

121

The Design of an embedded Self-Diagnostic Hybrid

Aquarium Control System

Tochukwu Chiagunye, Chukwugoziem Ihekweaba, Henrieta Udeani

Computer Engineering Dept. Michael Okpara University of Agriculture, Umudike, Abia State Nigeria.

which are operating in a physical world is usually a challenge. These challenges arise from the need to develop complex firmware products that take the constraints of the physical world into account. The task is made even more challenging due to the fact that these types of systems often are developed out of phase. Initially, the mechanical parts are designed, followed by the electronics and finally the system software is developed. Any problems discovered late in the development process, can really only be corrected in the software without causing significant delays to the complete project due to longer iterative cycles in the electronics and mechanical development. These very late changes often increase the complexity of the software and the risk of introducing new bugs. Hence, a well thought-out software design can be compromised.

See All Chapters

See All Slices