31 Slices
Medium 9781601323231

Session - Information and Knowledge Engineering and Management + Feature Extraction and AI

Hamid R. Arabnia, Leonidas Deligiannidis, Ray Hashemi, George Jandieri, Ashu M. G. Solo, and Fernando G. Tinetti CSREA Press PDF
Medium 9781601323231

Faces Recognition with Image Feature Weights and Least Mean Square Learning Approach

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

Int'l Conf. Information and Knowledge Engineering | IKE'14 |

21

Faces Recognition with Image Feature Weights and Least Mean Square

Learning Approach

Wei-Li Fang, Ying-Kuei Yang and Jung-Kuei Pan

Dept. of Electrical Engineering, National Taiwan Uni. of Sci. & Technology, Taipei, Taiwan

Email: yingkyang@yahoo.com

Abstract - Most of 2DPCA-enhanced approaches improve face recognition rate while at the expense of computation load.

In this paper, an approach is proposed to greatly improve face recognition rate with slightly increased computation load.

In this approach, the 2DPCA is applied against a face image to extract important image features for selection. A weight is then assigned to each of selected image features according to the feature’s importance to face recognition. The least mean square (LMS) algorithm is further applied to optimize the feature weights based on the recognition error rate during learning process in order to improve face recognition performance. The experiments have been conducted against

See All Chapters
Medium 9781601323231

Ontology inference using spatial and trajectory domain rules

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

Int'l Conf. Information and Knowledge Engineering | IKE'14 |

113

Ontology inference using spatial and trajectory domain rules

Rouaa Wannous

L3i Laboratory

University of La Rochelle, France

Email: rouaa.wannous@univ-lr.fr

Jamal Malki and Alain Bouju

L3i Laboratory

University of La Rochelle, France

Abstract—Capture devices give rise to a large scale spatiotemporal data describing moving object’s trajectories. These devices use different technologies like global navigation satellite system (GNSS), wireless communication, radio-frequency identification (RFID), and sensors techniques. Although capture technologies differ, the captured data share common spatial and temporal features. Thus, relational database management systems

(RDBMS) can be used to store and query the captured data. For this, RDBMS define spatial data types and spatial operations.

Recent applications show that the solutions based on traditional data models are not sufficient to consider complex use cases that require advanced data models. A complex use case refers to data, but also to domain knowledge, to spatial reasoning or others. This article presents a sample application based on trajectories that require three types of independent data models: a domain data model, a semantic model and a spatial model. We analyze each of them and propose a modeling approach based on ontologies.

See All Chapters
Medium 9781601323231

Large Scale Desalination: A Comparative Cost Affective Economic Analyses Of Nuclear, Gas and Solar Powered Plants

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

120

Int'l Conf. Information and Knowledge Engineering | IKE'14 |

Large Scale Desalination:

A Comparative Cost Affective Economic Analyses

Of Nuclear, Gas and Solar Powered Plants

Mohammed H. S. Al Ashry

Shaqra University

The Community College

Abstract: The main objective, here, is to explore the economic viability of the solar powered desalination method through a cost and benefit comparative and contrast study.

Using the initial construction expenditure, the annual maintenance cost, and energy consumed or produced a variance ratio test of the random walk hypothesis will be implemented to determine their relative financial efficiency.

This paper will also utilize the first order autoregressive multivariate estimation model to analyze the methods and identify the most productive process with most financial promise for future investment. The total deviations of the estimated variables from the actual are accounted for by the variations of the variances of the estimates from the actual.

The higher the percentage of the unexplained deviation the higher the risk involved. The portfolio variance will be utilized to measure the investment risk in the three desalination industries.

See All Chapters
Medium 9781601323231

Modeling Shared Drive Utilization Using Stochastic Techniques

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

Int'l Conf. Information and Knowledge Engineering | IKE'14 |

3

Modeling Shared Drive Utilization Using Stochastic

Techniques

Margret T. Martin, Sarah G. Nurre and Michael R. Grimaila, Senior Member, IEEE

Abstract—Information Technology (IT) units provide electronic file shared drives for utilization by personnel in their organization.

This shared electronic storage space is used for a wide variety of reasons (e.g., archival, collaboration, backups, dissemination) and is generally focused on providing areas for collaboration, as well as to augment the primary storage disk space located within each user’s computer system. The ways in which shared drives are utilized are highly dependent upon the organizational mission, who can access shared resources, the stability of the user population, end user roles, and the data retention policies enforced by the IT unit. The goal of this research is to understand what happens to information in shared disk storage within an academic institution as a function of time. Academic organizations are unique due to the transitory nature of the user population (e.g., students arrive and depart each year) and by the various roles that exist within the school. By examining the information lifecycle, we can gain insight into the differing perspectives between end users and IT units, the validity of assumptions about information rot and data aging, and develop an understanding how shared storage space is managed.

See All Chapters

See All Slices