March'2011

CONTENTS:

1)
A CONCEPTUAL FRAMEWORK FOR ADDING TEXTUAL ANNOTATIONS TO HIERARCHICAL TREES REPRESENTING ONTOLOGIES AS A MEANS OF ACHIEVING SEMANTIC INTEROPERABILITY BETWEEN DIFFERENT ONTOLOGIES OF THE SAME DOMAIN
(pp. 1-5)

Authors: A.M. Bagiwa, S.B. Junaidu

Abstract - In this paper we look at ontology matching as a problem that takes two different ontologies in the form of trees as input in to the system and produce a mapping that defines an alignment between the nodes of these trees. The framework for these paper introduces two ideas: (i) we discover a more general alignment by adding textual annotations to these nodes of thegraph; (ii) we identify semantic relations by analyzing not only the meaning residing in the node of these trees but  also to those annotations which are represented in some internal language. In this work we first take an overview of some of the currently used techniques in the field of ontology matching. We then, present our proposed approach for ontology matching as an extension to the S-Match system.

FULL MANUSCRIPT

2) DESIGN AND IMPLEMENTATION OF DIVISIVE CLUSTERING ALGORITHM FOR CATEGORICAL DATA
(pp. 6-15)

Authors: S.M.Karad, Prasad S. Halgaonkar, V.M.Wadhai and Dipti D. Patil

Abstract - A new algorithm is proposed and implemented by us, it uses a divisive approach to cluster high-dimensional categorical data. Algorithm is parameter-free, fully-automatic and is based on a two-phase iterative procedure. Assignments of Clusters are given in the first phase, and a new cluster is added to the partition by identifying and splitting a low-quality cluster. Optimization of clusters is carried out in the second phase. This algorithm is based on quality of cluster in terms of homogeneity. Suitable notion of cluster homogeneity can be defined in the context of high-dimensional categorical data, from which an effective instance of the proposed clustering scheme immediately follows. Experiment is carried out on real data; this innovative approach leads to better inter- and intra-homogeneity of the clusters obtained

FULL MANUSCRIPT

3) PROBABILISTIC NEURAL NETWORKS FOR UNCERTAIN DATA CLASSIFICATION
(pp. 16-23)

Authors: E.Venkateswara Reddy, G.V.Suresh, M.Ramesh.

Abstract - Data uncertainty is common in real-world applications due to various causes, including imprecise measurement, network latency, out-dated sources and sampling errors. As a result there is a need for tools and techniques for mining and managing uncertain data. These kinds of uncertainty have to be handled cautiously, or else the mining results could be unreliable or even wrong. We propose that when data mining is performed on uncertain data, data uncertainty has to be considered in order to obtain high quality data mining results. We present a Probabilistic Neural Network model which is suitable for classification problems. This model constitutes an adaptation of the classical RBF network where the outputs represent the class conditional distributions. Since the network outputs correspond to probability densities functions, training process is treated as maximum likelihood problem and an Expectation-Maximization (EM) algorithm is proposed for adjusting the network parameters. Experimental results show that proposed model exhibits superior classification performance on uncertain data.

FULL MANUSCRIPT

4) DYNAMIC MODELING AND ANALYSIS OF VEHICLE AIR-CONDITIONING USING STATE SPACE METHOD
(pp. 24-33)

Authors: S.Arul Selvan and P.Seethalakshmi

Abstract - Automotive Air Conditioning (AAC) system poses unique challenges for designers, to fulfill the customers comfort and efficient operation in wide changing ambient temperature (18 °C to 45 °C) and humidity (30 to 80 R.H). This paper presents the development of a state space dynamic model (SSDM) for analyzing the vehicle air conditioning in both steady and transient mode. This model includes a vehicle cabin, variable displacement capacity (VDC) compressor and an evaporator. An experimental vehicle made up of original components from the air conditioning system of a compact passenger vehicle has been developed in order to check the results from the model. This SSDM has a non linear relationship between output state variables (cabin temperature, cabin humidity) and input manipulated variables (compressor speed, blower fan speed). It confirms the developed model after linearization around the operating point was experimentally valid, to capture the transient change in system parameter and to represent the steady state operation within in the acceptable range. Thus SSDM can be especially useful in developing different control strategies like Multi loop control, Multivariable control and Model Predictive Control etc. for improving passenger comfort, fuel economy, drivability and stalling of engines.

FULL MANUSCRIPT

5) DQA: AUTOMATA WITH NEW MEMORY, PROPERTIES AND APPLICATIONS
(pp. 34-38)

Author: Biplob Kumar Debnath

Abstract - In this paper, the recognition of different classes of languages with the help of Deque Automata is described. A Deque Automaton (DQA), an extension of Queue Automaton (QA) or Circular Automaton (CA), uses queue as a store and has six basic operations. It is shown here that languages accepted by Finite Automaton (FA), Push-down Automaton (PDA), and Queue Automaton (QA) are also accepted by Deque Automaton (DQA). It is also proved that class of languages accepted by Turing Machine (TM) is a subset of that accepted by DQA i.e. DQA is Turing-equivalent and a Turing machine can be simulated by DQA. Conversions between different types of storage and DQA are shown and lower bounds of the complexity of conversions are determined then. Simulation of different automata with the help of DQA is also shown. Priorities and restricttions of DQA are also discussed for recognizing different classes of languages.

FULL MANUSCRIPT

6) ACCURATE POWER MEASUREMENT OF HIGH POWER GAN DEVICES FOR W-CDMA BASE STATION APPLICATION
(pp. 39-41)

Authors: Armin Liero, Roland Gesche

Abstract - A method of accurate power measurement is presented here based on a   load and source pull measurement system. The measurement was carried out for a packaged high power   GaN  powerbar fabricated  and packaged  in FBH, Berlin. Commercial source and/or load pull measurement systems for packaged transistors use a standard test fixture where the device is placed with the tuners located outside the periphery which introduce in many cases a serious problem of inaccurate results due to high impedance mismatch at the input and at the output of the device. The method presented here is a simple pre-matching on the test fixture. The pre-matching network is designed on basis of small signal S-parameter measurement.  Load and sourcepull measurement is then done with the combination of pre-matching network and tuner.  Final transformation networks were built based on  large signal  input and output impedances.

FULL MANUSCRIPT

7) BROADBAND L-PROBE FED INVERTED HYBRID E-H MICROSTRIP PATCH ARRAY ANTENNA FOR 3G SMART ANTENNA SYSTEM TESTBED
(pp. 42-45)

Authors: Zainol Abidin Abdul Rashid, Mohammad Tariqul Islam, Ng Kok Jiunn

Abstract - In this paper a compact and broadband L-probe fed inverted hybrid E-H microstrip path 4x1 array antenna was developed for 3G smart antenna system testbed. The 4x1 uniform linear array antenna was designed to operate at 1.885 to 2.2GHz with a total bandwidth of 315MHz. The array elements were based on  the  novel broadband inverted hybrid E-H  (IHEH) L-probe  fed microstrip patch, which offers 22% size reduction to the conventional rectangular microstrip patch antenna. The developed antenna has an impedance bandwidth of 17.32% (VSWR≤1.5), 21.78% (VSWR≤2) with respect to center frequency 2.02GHz, and with an achievable gain of 11.9dBi. The design antenna offer a broadband, compact, and mobile solution for a 3G smart antenna testbed to fully characterized the IMT-2000 radio specifications and system performances.

FULL MANUSCRIPT

8) ALGORITHM FOR SHIFTING IMAGES STORED IN PEANO MASK TREES
(pp. 46-50)

Authors: Mohammad Kabir Hossain, William Perrizo

Abstract - Peano Trees are a data-mining ready data structure that can also be used for image compression. The ability to be able to rotate, scale or translate images is an integral part of image processing while searching through images in the image database. This paper presents an algorithm for translation of images in any direction of the two dimensional plane. The paper assumes that the images to be worked upon are stored the Peano Mask Tree format (Peano Trees are introduced below). The algorithm will provide the advantage of image processing while the image is in the Peano Tree format, it will not be necessary to generate the original bit pattern of the image to perform the task of translation.

FULL MANUSCRIPT

9) PRIVACY PROTECTION IN MULTI-AGENT BASED APPLICATIONS
(pp. 51-56)

Authors: Eiji Kamioka, Shigeki Yamada

Abstract - In many multi-agent based applications, software agents share their private information with each other to reach their goals. But the agents may not always be willing to let other agents take away the shared private information. Also a malicious agent may steal unauthorized data from visited user host and send them to illicit personnel or sneak them away, resulting in privacy loss. In this paper we address the privacy issues in multi-gent based applications and propose a privacy protection model named iCOP for such applications. Participating agents are trapped in the iCOP host in which they interact with one another and solve the problem by sharing their private inputs. They are restricted from sending out any data except the computational result to the outside world. They cannot sneak away the private input data of other agents or illegally accessed data. We also developed a prototype of our proposed model and a number of mobile agents for experiments. The experimental results demonstrate the effectiveness of the iCOP model in protecting user privacy in multi-agent based applications.

FULL MANUSCRIPT

10) USING HMM FOR FORECASTING STOCK MARKET INDEX
(pp. 57-61)

Authors: Md. Rafiul Hassan, Baikunth Nath and Rezaul Begg

Abstract - Prediction of future stock values due to randomness and non-linearity in the data is a challenging problem for the financial investment markets. Numerous models are available to approximately predict these non-linear events. Recently, much research attention and interest has focused in this area, including models based on ANN, SVM and FIS.  In this paper, we propose a stock prediction system based on HMM because of its proven suitability for modeling dynamic systems and pattern classification. We apply the HMM methodology to predict the Australian Stock Index ASX100 for the next few days using available past datasets. The results obtained using HMM are encouraging. Finally, we recommend development of hybrid models by combining HMM with other soft computing paradigms, for example ANN ANFIS or GA, to improve prediction results further.

FULL MANUSCRIPT