31 Slices
Medium 9781601323231

Collaborative Shared Awareness: Human-AI Collaboration

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

10

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

Collaborative Shared Awareness: Human-AI Collaboration

James A. Crowder, John N. Carbone

Raytheon Intelligence, Information, and Services

16800 E. Centretech Parkway, Aurora, Colorado 80011

Abstract - The ability to reason within an autonomous information processing system denotes the ability to infer about information, knowledge, observations and experiences, and affect changes within the system to perform new tasks previously unknown, or to perform tasks already learned more efficiently and effectively [Crowder

1996]. The act of reasoning and inferring allows an autonomous system to construct or modify representations of concepts or knowledge that the system is experiencing and learning. Reasoning allows an Artificially Intelligent

System (AIS) to fill in skeletal or incomplete information or specifications about one or more of its domains (selfassessment).

The research described here details architectures and algorithms for a cognitive system of

See All Chapters
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

Keyword Searches with Customized Preferences

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 |

69

Keyword Searches with Customized Preferences

Yu-Chin Liu, Yi-Hsuan Chiang and Yu-Lien Hsieh

Abstract—In accordance with the great business opportunities emerging through SNSs, entrepreneurs strive to explore the potential benefits by analyzing data collected from

SNSs. For example, Google+ attempts to integrate keyword searches with the individual’s social network. In this paper, we propose a new method for considering the common preferences of friends on social networks while ranking the order of related web pages returned from search engines. The simulation shows the proposed method performing well comparing to general search engines.

I. INTRODUCTION

I

NFORMATION searching has become as one of the most important tasks for on-line information retrieval. At present, there are three main methods of information searching on the

Internet: searching by web pages, by directories, and by keywords. For users, tools supporting timely searching are in great demands.

See All Chapters
Medium 9781601323231

Segment, Synthesize and Repeat: CARP Paradigm for Consumption of Digital Content

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

100

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

Segment, Synthesize and Repeat: CARP Paradigm for

Consumption of Digital Content

A. Indu Anand* and B. Anurag Wakhlu**

*Sushila Publications, P.O.Box 455, Chelmsford, Masachusetts, 01824 USA

**Coloci Inc., Chelmsford, Masachusetts, 01824 USA

Abstract. CARP (“Computer-Aided

Reading and Perusal”) is a method of collecting and aggregating intelligent crowd-sourced information or data from a document or audio/video data file, which may be used to dynamically generate relevant mark-ups for documents or other consumable data files. The marked-up version of a document or data file can be displayed on demand, and may be used for purposes such as, inter alia, to enhance efficiency, comprehension and experience of reading, listening or viewing. Combined with any input technology that permits quick scanning and suitable pre-processing, CARP can use its crowd–sourced utilities to refine the highlighting and generate customized, marked up versions of the target data file for a user.

See All Chapters

See All Slices