Volume 3 Issue 3
Authors: B. Mallikarjuna; A. Nagaraju; V. Rajendraprasad; K.V Ramanaiah
Abstract: In this paper we represent the images as a collection of patches, each of which belongs to latent theme that is shared across images as well as categories [1]. Various face detection techniques have been proposed over the past decade. Generally, a large number of features are required to be selected for training purposes of face detection system. Often some of these features are irrelevant and do not contribute directly to the face detection algorithm. This creates unnecessary computation and usage of large memory space. In this paper we propose to enlarge the features search space by enriching it with more types of features. With an additional seven new feature types, we show how Genetic Algorithm (GA) can be used, within the Adaboost framework, to find sets of features which can provide better classifiers with a shorter training time. The technique is referred to as GA Boost for our face detection system. The GA carries out an evolutionary search over possible features search space which results in a higher number of feature types and sets selected in less time. Experiments on a set of images from BioID database proved that by using GA to search on large number of feature types and sets, GA Boost is able to obtain cascade of boosted classifiers for a face detection system that can give higher detection rates, lower false positive rates and less training time but gives higher detection rates.
Keywords: Genetic Algorithm; GA Boost; Adaboost Framework; Cascade of Classifiers; Adaboost
Authors: Prakash Prakash Persad; Jorrel Bisnath
Abstract: Traditional North Indian religious music has, for the most part, used traditional drums like the tabla. This article describes the work that has been done thus far in integrating a robotic drummer in a music band. It illustrates a user centred design approach for the creation of an interface to be used by musicians working with the robot. The interface is designed to be used during a training session for the creation of a tabla accompaniment piece with little additional training or technical knowledge. The first iteration of the design was created and formative testing was conducted. Users were successfully able to use the interface to complete a series of tasks and recommendations were gathered for improving the next iteration.
Keywords: Human-Robotic Interaction; Robotic Drumming; Tabla
Authors: Isak Karabegovi?; Ermin Husak
Abstract: An assumption for satisfaction of needs and technological efficacy is related to: scientific knowledge, manufacturing operations, general technical organizational stage, engineering experience, equipment expediency and other vocational and human skills. Technological efficacies imply an improvement of technical solutions in automation domain of technological processes and application of intelligent systems in different industrial branches where automobile industry belongs to. There are a number of industrial robot applications in automobile industry today, in Asia and in other continents in the world. Their application is motivated by technical and economical reasons like: quality improvement of the completed products, fallout decrease (in montage processes), rate enlargement of the quality homogeneity-constancy (in all processes linked to robot application repeatability), security operation rate enlargement ( in aggressive, burning, explosive and other areas, with the high rate of robot protection), decrease of the necessary work force in routine and repeatability processes, manufacture cost minimising and overall maintenance, fulfilment of demands required by a competition and more rigorous quality standards. This paper provides an analysis of industrial robot application in automobile industry in countries of Asia with an overview on application trend and future development of the same industry.
Keywords: Industrial Robot; Automobile Industry; Robot Application; New Technologies; Automobile
Authors: Fatima Faiza Ahmed; Fatima Saima hmed
Abstract: The semantic web is one of the most promising and emerging areas of computer science. Its ability to make information that is only human understandable to be understood and processed by machines increases its relevance and time efficiency. In this paper we present a semantic web application that contains a dynamic knowledge base holding hotel related information, which is updated at every run from the information provided in the hotels’ websites, and a natural language querying platform where the user can enter his free form natural language queries. DL Query is used as the engine that performs the retrieval of data from the ontology. A simple user experiment shows that the system is time effective and helpful in decision making.
Keywords: Information Extraction; Semantic Web; DL Queries; Hotel Search Model
Authors: Katsuhiro Honda; Akira Notsu; Yuki Tezuka
Abstract: In this paper, we introduce low-priority cut-in (moratorium) to chain form reinforcement learning, which we proposed as Simple Reinforcement Learning for a reinforcement learning agent that has small memory. In the real world, learning is difficult because there are an infinite number of states and actions that need a large number of stored memory and learning time. To solve the problem, better estimated values are categorized as “GOOD” in the reinforcement learning process. Additionally, the alignment sequence of estimated values is changed because they are regarded as an important sequence themselves. However, the method is heavily affected by the action policy. If an agent tends to search many states, its memory overflows with low-value data. Thus, low-priority cut-in (moratorium) enhances the method in order to solve this problem. We conducted some simulations and observed the influence of our methods. Several simulation results show good influence on learning.
Keywords: Reinforcement Learning; Q-learning; State-action Set Categorization