International Journal of Computer and Applications

In this paper we give an overview of the Knowledge Base Population (KBP) track at the 2010 Text Analysis Conference. The main goal of KBP is to promote research in discovering facts about entities and augmenting a knowledge base (KB) with these facts. This is done through two tasks, Entity Linking -- linking names in context to entities in the KB -- and Slot Filling -- adding information about an entity to the KB. A large source collection of newswire and web documents is provided from which systems are to discover information. Attributes ("slots") derived from Wikipedia infoboxes are used to create the reference KB. In this paper we provide an overview of the techniques which can serve as a basis for a good KBP system, lay out the remaining challenges by comparison with traditional Information Extraction (IE) and Question Answering (QA) tasks, and provide some suggestions to address these challenges.

/pdf/knowledge-base-population-successful-approaches-and-3j2c1dzo6g.pdf

Knowledge Base Population: Successful Approaches and Challenges

Fruit classification is quite difficult because of the various categories and similar shapes and features of fruit. In this work, we proposed two novel machine-learning based classification methods. The developed system consists of wavelet entropy (WE), principal component analysis (PCA), feedforward neural network (FNN) trained by fitness-scaled chaotic artificial bee colony (FSCABC) and biogeography-based optimization (BBO), respectively. The K-fold stratified cross validation (SCV) was utilized for statistical analysis. The classification performance for 1653 fruit images from 18 categories showed that the proposed “WE + PCA + FSCABC-FNN” and “WE + PCA + BBO-FNN” methods achieve the same accuracy of 89.5%, higher than state-of-the-art approaches: “(CH + MP + US) + PCA + GA-FNN ” of 84.8%, “(CH + MP + US) + PCA + PSO-FNN” of 87.9%, “(CH + MP + US) + PCA + ABC-FNN” of 85.4%, “(CH + MP + US) + PCA + kSVM” of 88.2%, and “(CH + MP + US) + PCA + FSCABC-FNN” of 89.1%. Besides, our methods used only 12 features, less than the number of features used by other methods. Therefore, the proposed methods are effective for fruit classification.

Fruit Classification by Wavelet-Entropy and Feedforward Neural Network Trained by Fitness-Scaled Chaotic ABC and Biogeography-Based Optimization

Accurate fruit classification is difficult to accomplish because of the similarities among the various categories. In this paper, we proposed a novel fruit-classification system, with the goal of recognizing fruits in a more efficient way. Our methodology included the following steps. First, a four-step pre-processing was employed. Second, the features colour, shape, and texture were extracted. Third, we utilized principal component analysis to remove excessive features. Fourth, a novel fruit-classification system based on biogeography-based optimization BBO and feedforward neural network FNN was proposed, with the short name of BBO-FNN. The experiment employed over 1653 chromatic fruit images 18 categories by fivefold stratified cross-validation. The results showed that the proposed BBO-FNN yielded an overall accuracy of 89.11%, which was higher than the five state-of-the-art methods: genetic algorithm-FNN, artificial bee colony-FNN, particle swarm optimization-FNN, kernel support vector machine, and ant colony optimization-FNN. Also, the BBO-FNN achieved the same accuracy as fitness-scaling chaotic artificial bee colony-FNN, but it performed much faster than the latter. The proposed BBO-FNN was effective in fruit-classification in terms of classification accuracy and computation time. This indicated that it can be applied in credible use.

Fruit classification by biogeography-based optimization and feedforward neural network

Rainfall Monthly Prediction Based on Artificial Neural Network: A Case Study in Tenggarong Station, East Kalimantan - Indonesia

Generally the fractal image compression is a technique based on the presentation of an image by a contractive transform, on the space of image, for which the fixed point is close to the original image. The fractal image compression is rapidly growing principle covers a wide variety of coding scheme in various domains. A large number of theoretical aspects of this concept are available. However, a few concentrations have been given to the image encoding model which justifies its proper implementation. Most fractal base schemes are not competitive with the current state of the art like JPEG, JPEG2000. To identify the performance of fractal image compression, specifically for the medical images, a comprehensive review of worldwide contributions from 1990 to 2013 has been carried out. As a result, the fractal image compression techniques are classified into four domains, i.e., spatial, frequency, soft computing, and hybrid. It is found that, fractal theory in spatial domain, fractal theory along with discrete cosine transform and wavelet transform in frequency domain, fractal theory along with fuzzy logic and neural network in soft computing domain, and combination of fractal theory along with discrete cosine transform, wavelet transform, fuzzy logic and neural network in hybrid domain are often used by the contributors. It is found that the fractal dimension and fuzzy logic approach on regular image processing are sufficiently suitable for image texture analysis. Consequently fuzzy logic is successfully applied in regular image and found outstanding results. On the basis of these facts it is anticipated that the fractal dimension and fuzzy logic could be a suitable approach in medical image compression using fractal theory as a future expansion is discussed in this review article.

/pdf/performance-of-fractal-image-compression-for-medical-images-u7ohoc64h7.pdf

Performance of Fractal Image Compression for Medical Images: A Comprehensive Literature Review

Mobile Robot Path Planning: A review

Stock market prediction is an important area of financial forecasting, which is of great interest to stock investors, stock traders and applied researchers. To determine the buy and sell time is one of the most important issues for investors in stock market. In this paper, a fuzzy approach using the famous candlestick method to stock market timing is investigated. Drawing candlesticks are very easy, but to make the system understand them is challenging. Using fuzzy logic first we try to make the system understand the candlestick formations and verify with what we can see and then we go on for forecasting the future trend using various candlestick techniques. The fuzzified candlesticks tend to represent the real market behavior more closely as done by humans. Here we have tried to develop a method by which fuzzification of candlesticks can be done and then by using the fuzzified candlesticks we can perform predictions of market movements with various candlestick patterns like Engulfing [2] and modified Engulfing (U-Turn) by establishing fuzzy rules. The type of real time data used here is the daily values of S&P CNX NIFTY 50 index used in National Stock Exchange of India for stock futures trading.

Fuzzy Candlestick Approach to Trade S&P CNX NIFTY 50 Index using Engulfing Patterns

The conventional treatment planning system (TPS) gives analytical calculations with ± 15 to 20% dose, which may lead to over exposure of critical organs or under dose of target. It is to obtain dose distribution parameters of nucletron high dose rate (HDR) microselectron v2 (mHDR-v2) 192 Ir brachytherapy source by experiment and by calculated study using Monte Carlo (MC) EGSnrc code, and to find the similarity between them, and with any past study. To validate data, another MC GEANT4 study done in this work on the same source is also presented. Different software of the computer e.g. paint, excel, etc are employed for preparation of figures and graphs. The measured study of the source was done using an in-air ionization chamber, water phantom, and measurement set-up, while the calculated study was done by modeling the set up of the measured study by using the MC EGSnrc and GEANT4. Mean and probability are used in calculation of average values, and calculation of the uncertainties in result and discussion. The measured and calculated values of dose rate constant, radial dose function, and 2D anisotropy function were found to be in agreement with each other as well as with published data. The results of this study can be used as input to TPS.

Monte Carlo and experimental dosimetric study of the mHDR-v2 brachytherapy source.

Current research on Ontologies has shown that 5 they facilitate the information retrieval, query-based interaction and knowledge management of text document resources. The authors report the implementation of the machine-generated Ontologies on the huge-text corpora that can be assumed to a part of mechanized Digital Libraries for extracting conceptual features by computing the measure of semantic closeness, upon the selectively chosen highly focused terms. This angle of visualizing text literature searching and ranking has been ignored so far in much existing work. In the present communication, a two-stage approach is implied, where a confusion matrix : a measure of true class of test instances against the predicted classes is innovatively used to derive a fuzzy preference relation matrix - the most suitably thought metric to proceed for the task of text document ranking. The authors visualize the promising results from an experimental set up laid upon a sample text corpus that served as a driving lexicon for constructing relevant concept spaces.

M. K. Kowar

Papers

Performance of Fractal Image Compression for Medical Images: A Comprehensive Literature Review

Mobile Robot Path Planning: A review

Fuzzy Candlestick Approach to Trade S&P CNX NIFTY 50 Index using Engulfing Patterns

Monte Carlo and experimental dosimetric study of the mHDR-v2 brachytherapy source.

Exploiting Confusion Matrices for Relevance Ranking of Text Documents