Abstract: Breadth-First Search (BFS) is a core graph algorithm that is widely used for graph analysis. As it is frequently used in many graph applications, improving the BFS performance is essential. In this paper, we present a graph ordering method that could reorder the graph nodes to achieve better data locality, thus, improving the BFS performance. Our method is based on an observation that the sibling relationships will dominate the cache access pattern during the BFS traversal. Therefore, we propose a frequency-based model to construct the graph order. First, we optimize the graph order according to the nodes’ visit frequency. Nodes with high visit frequency will be processed in priority. Second, we try to maximize the child nodes’ overlap layer by layer. As it is proved to be NP-hard, we propose a heuristic method that could greatly reduce the preprocessing overheads.We conduct extensive experiments on 16 real-world datasets. The result shows that our method could achieve comparable performance with the state-of-the-art methods while the graph ordering overheads are only about 1/15.
Abstract: We as humans use words with accompanying visual and facial cues to communicate effectively. Classifying facial emotion using computer vision methodologies has been an active research area in the computer vision field. In this paper, we propose a simple method for facial expression recognition that enhances accuracy. We tested our method on the FER-2013 dataset that contains static images. Instead of using Histogram equalization to preprocess the dataset, we used Unsharp Mask to emphasize texture and details and sharpened the edges. We also used ImageDataGenerator from Keras library for data augmentation. Then we used Convolutional Neural Networks (CNN) model to classify the images into 7 different facial expressions, yielding an accuracy of 69.46% on the test set. Our results show that using image preprocessing such as the sharpening technique for a CNN model can improve the performance, even when the CNN model is relatively simple.
Abstract: This paper presents and benchmarks a number of
end-to-end Deep Learning based models for metaphor detection in
Greek. We combine Convolutional Neural Networks and Recurrent
Neural Networks with representation learning to bear on the metaphor
detection problem for the Greek language. The models presented
achieve exceptional accuracy scores, significantly improving the
previous state-of-the-art results, which had already achieved accuracy
0.82. Furthermore, no special preprocessing, feature engineering or
linguistic knowledge is used in this work. The methods presented
achieve accuracy of 0.92 and F-score 0.92 with Convolutional
Neural Networks (CNNs) and bidirectional Long Short Term Memory
networks (LSTMs). Comparable results of 0.91 accuracy and 0.91
F-score are also achieved with bidirectional Gated Recurrent Units
(GRUs) and Convolutional Recurrent Neural Nets (CRNNs). The
models are trained and evaluated only on the basis of training tuples,
the related sentences and their labels. The outcome is a state-of-the-art
collection of metaphor detection models, trained on limited labelled
resources, which can be extended to other languages and similar
tasks.
Abstract: Speech to text in Malay language is a system that converts Malay speech into text. The Malay language recognition system is still limited, thus, this paper aims to investigate the performance of ten Malay words obtained from the online Malay news. The methodology consists of three stages, which are preprocessing, feature extraction, and speech classification. In preprocessing stage, the speech samples are filtered using pre emphasis. After that, feature extraction method is applied to the samples using Mel Frequency Cepstrum Coefficient (MFCC). Lastly, speech classification is performed using Feedforward Neural Network (FFNN). The accuracy of the classification is further investigated based on the hidden layer size. From experimentation, the classifier with 40 hidden neurons shows the highest classification rate which is 94%.
Abstract: Measuring semantic similarity between texts is calculating semantic relatedness between texts using various techniques. Our web application (Measuring Relatedness of Concepts-MRC) allows user to input two text corpuses and get semantic similarity percentage between both using WordNet. Our application goes through five stages for the computation of semantic relatedness. Those stages are: Preprocessing (extracts keywords from content), Feature Extraction (classification of words into Parts-of-Speech), Synonyms Extraction (retrieves synonyms against each keyword), Measuring Similarity (using keywords and synonyms, similarity is measured) and Visualization (graphical representation of similarity measure). Hence the user can measure similarity on basis of features as well. The end result is a percentage score and the word(s) which form the basis of similarity between both texts with use of different tools on same platform. In future work we look forward for a Web as a live corpus application that provides a simpler and user friendly tool to compare documents and extract useful information.
Abstract: Measuring semantic similarity between texts is calculating semantic relatedness between texts using various techniques. Our web application (Measuring Relatedness of Concepts-MRC) allows user to input two text corpuses and get semantic similarity percentage between both using WordNet. Our application goes through five stages for the computation of semantic relatedness. Those stages are: Preprocessing (extracts keywords from content), Feature Extraction (classification of words into Parts-of-Speech), Synonyms Extraction (retrieves synonyms against each keyword), Measuring Similarity (using keywords and synonyms, similarity is measured) and Visualization (graphical representation of similarity measure). Hence the user can measure similarity on basis of features as well. The end result is a percentage score and the word(s) which form the basis of similarity between both texts with use of different tools on same platform. In future work we look forward for a Web as a live corpus application that provides a simpler and user friendly tool to compare documents and extract useful information.
Abstract: In this paper, we propose an optimized brain computer
interface (BCI) system for unspoken speech recognition, based on
the fact that the constructions of unspoken words rely strongly on the
Wernicke area, situated in the temporal lobe. Our BCI system has four
modules: (i) the EEG Acquisition module based on a non-invasive
headset with 14 electrodes; (ii) the Preprocessing module to remove
noise and artifacts, using the Common Average Reference method;
(iii) the Features Extraction module, using Wavelet Packet Transform
(WPT); (iv) the Classification module based on a one-hidden layer
artificial neural network. The present study consists of comparing
the recognition accuracy of 5 Arabic words, when using all the
headset electrodes or only the 4 electrodes situated near the Wernicke
area, as well as the selection effect of the subbands produced by
the WPT module. After applying the articial neural network on the
produced database, we obtain, on the test dataset, an accuracy of
83.4% with all the electrodes and all the subbands of 8 levels of the
WPT decomposition. However, by using only the 4 electrodes near
Wernicke Area and the 6 middle subbands of the WPT, we obtain
a high reduction of the dataset size, equal to approximately 19% of
the total dataset, with 67.5% of accuracy rate. This reduction appears
particularly important to improve the design of a low cost and simple
to use BCI, trained for several words.
Abstract: Power distribution circuits undergo frequent network
topology changes that are often left undocumented. As a result, the
documentation of a circuit’s connectivity becomes inaccurate with
time. The lack of reliable circuit connectivity information is one of the
biggest obstacles to model, monitor, and control modern distribution
systems. To enhance the reliability and efficiency of electric power
distribution systems, the circuit’s connectivity information must be
updated periodically. This paper focuses on one critical component of
a distribution circuit’s topology - the secondary transformer to phase
association. This topology component describes the set of phase lines
that feed power to a given secondary transformer (and therefore a
given group of power consumers). Finding the documentation of this
component is call Phase Identification, and is typically performed
with physical measurements. These measurements can take time
lengths on the order of several months, but with supervised learning,
the time length can be reduced significantly. This paper compares
several such methods applied to Phase Identification for a large
range of real distribution circuits, describes a method of training
data selection, describes preprocessing steps unique to the Phase
Identification problem, and ultimately describes a method which
obtains high accuracy (> 96% in most cases, > 92% in the worst
case) using only 5% of the measurements typically used for Phase
Identification.
Abstract: Bioassay is the measurement of the potency of a chemical substance by its effect on a living animal or plant tissue. Bioassay data and chemical structures from pharmacokinetic and drug metabolism screening are mined from and housed in multiple databases. Bioassay prediction is calculated accordingly to determine further advancement. This paper proposes a four-step preprocessing of datasets for improving the bioassay predictions. The first step is instance selection in which dataset is categorized into training, testing, and validation sets. The second step is discretization that partitions the data in consideration of accuracy vs. precision. The third step is normalization where data are normalized between 0 and 1 for subsequent machine learning processing. The fourth step is feature selection where key chemical properties and attributes are generated. The streamlined results are then analyzed for the prediction of effectiveness by various machine learning algorithms including Pipeline Pilot, R, Weka, and Excel. Experiments and evaluations reveal the effectiveness of various combination of preprocessing steps and machine learning algorithms in more consistent and accurate prediction.
Abstract: DNA data have been used in forensics for decades. However, current research looks at using the DNA as a biometric identity verification modality. The goal is to improve the speed of identification. We aim at using gene data that was initially used for autism detection to find if and how accurate is this data for identification applications. Mainly our goal is to find if our data preprocessing technique yields data useful as a biometric identification tool. We experiment with using the nearest neighbor classifier to identify subjects. Results show that optimal classification rate is achieved when the test set is corrupted by normally distributed noise with zero mean and standard deviation of 1. The classification rate is close to optimal at higher noise standard deviation reaching 3. This shows that the data can be used for identity verification with high accuracy using a simple classifier such as the k-nearest neighbor (k-NN).
Abstract: The purpose of this study is providing an improved mode choice model considering parameters including age grouping of prime-aged and old age. In this study, 2010 Household Travel Survey data were used and improper samples were removed through the analysis. Chosen alternative, date of birth, mode, origin code, destination code, departure time, and arrival time are considered from Household Travel Survey. By preprocessing data, travel time, travel cost, mode, and ratio of people aged 45 to 55 years, 55 to 65 years and over 65 years were calculated. After the manipulation, the mode choice model was constructed using LIMDEP by maximum likelihood estimation. A significance test was conducted for nine parameters, three age groups for three modes. Then the test was conducted again for the mode choice model with significant parameters, travel cost variable and travel time variable. As a result of the model estimation, as the age increases, the preference for the car decreases and the preference for the bus increases. This study is meaningful in that the individual and households characteristics are applied to the aggregate model.
Abstract: Application of five implementations of three data mining classification techniques was experimented for extracting important insights from tourism data. The aim was to find out the best performing algorithm among the compared ones for tourism knowledge discovery. Knowledge discovery process from data was used as a process model. 10-fold cross validation method is used for testing purpose. Various data preprocessing activities were performed to get the final dataset for model building. Classification models of the selected algorithms were built with different scenarios on the preprocessed dataset. The outperformed algorithm tourism dataset was Random Forest (76%) before applying information gain based attribute selection and J48 (C4.5) (75%) after selection of top relevant attributes to the class (target) attribute. In terms of time for model building, attribute selection improves the efficiency of all algorithms. Artificial Neural Network (multilayer perceptron) showed the highest improvement (90%). The rules extracted from the decision tree model are presented, which showed intricate, non-trivial knowledge/insight that would otherwise not be discovered by simple statistical analysis with mediocre accuracy of the machine using classification algorithms.
Abstract: This paper presents the results of a study to test whether the Javanese character manuscript image preprocessing model that have been more widely applied, can also be applied to segment of the Batak characters manuscripts. The treatment process begins by converting the input image into a binary image. After the binary image is cleaned of noise, then the segmentation lines using projection profile is conducted. If unclear histogram projection is found, then the smoothing process before production indexes line segments is conducted. For each line image which has been produced, then the segmentation scripts in the line is applied, with regard of the connectivity between pixels which making up the letters that there is no characters are truncated. From the results of manuscript preprocessing system prototype testing, it is obtained the information about the system truth percentage value on pieces of Pustaka Batak Podani Ma AjiMamisinon manuscript ranged from 65% to 87.68% with a confidence level of 95%. The value indicates the truth percentage shown the initial processing model in Javanese characters manuscript image can be applied also to the image of the Batak characters manuscript.
Abstract: Remotely sensed data are a significant source for monitoring and updating databases for land use/cover. Nowadays, changes detection of urban area has been a subject of intensive researches. Timely and accurate data on spatio-temporal changes of urban areas are therefore required. The data extracted from multi-temporal satellite images are usually non-stationary. In fact, the changes evolve in time and space. This paper is an attempt to propose a methodology for changes detection in urban area by combining a non-stationary decomposition method and stochastic modeling. We consider as input of our methodology a sequence of satellite images I1, I2, … In at different periods (t = 1, 2, ..., n). Firstly, a preprocessing of multi-temporal satellite images is applied. (e.g. radiometric, atmospheric and geometric). The systematic study of global urban expansion in our methodology can be approached in two ways: The first considers the urban area as one same object as opposed to non-urban areas (e.g. vegetation, bare soil and water). The objective is to extract the urban mask. The second one aims to obtain a more knowledge of urban area, distinguishing different types of tissue within the urban area. In order to validate our approach, we used a database of Tres Cantos-Madrid in Spain, which is derived from Landsat for a period (from January 2004 to July 2013) by collecting two frames per year at a spatial resolution of 25 meters. The obtained results show the effectiveness of our method.
Abstract: Music has always been an integral part of human’s daily lives. But, for the most people, reading musical score and turning it into melody is not easy. This study aims to develop an Automatic music score recognition system using digital image processing, which can be used to read and analyze musical score images automatically. The technical approaches included: (1) staff region segmentation; (2) image preprocessing; (3) note recognition; and (4) accidental and rest recognition. Digital image processing techniques (e.g., horizontal /vertical projections, connected component labeling, morphological processing, template matching, etc.) were applied according to musical notes, accidents, and rests in staff notations. Preliminary results showed that our system could achieve detection and recognition rates of 96.3% and 91.7%, respectively. In conclusion, we presented an effective automated musical score recognition system that could be integrated in a system with a media player to play music/songs given input images of musical score. Ultimately, this system could also be incorporated in applications for mobile devices as a learning tool, such that a music player could learn to play music/songs.
Abstract: In this paper, a data-driven dictionary approach is proposed for the automatic detection and classification of cardiovascular abnormalities. Electrocardiography (ECG) signal is represented by the trained complete dictionaries that contain prototypes or atoms to avoid the limitations of pre-defined dictionaries. The data-driven trained dictionaries simply take the ECG signal as input rather than extracting features to study the set of parameters that yield the most descriptive dictionary. The approach inherently learns the complicated morphological changes in ECG waveform, which is then used to improve the classification. The classification performance was evaluated with ECG data under two different preprocessing environments. In the first category, QT-database is baseline drift corrected with notch filter and it filters the 60 Hz power line noise. In the second category, the data are further filtered using fast moving average smoother. The experimental results on QT database confirm that our proposed algorithm shows a classification accuracy of 92%.
Abstract: Hepatitis is one of the most common and dangerous diseases that affects humankind, and exposes millions of people to serious health risks every year. Diagnosis of Hepatitis has always been a challenge for physicians. This paper presents an effective method for diagnosis of hepatitis based on interval Type-II fuzzy. This proposed system includes three steps: pre-processing (feature selection), Type-I and Type-II fuzzy classification, and system evaluation. KNN-FD feature selection is used as the preprocessing step in order to exclude irrelevant features and to improve classification performance and efficiency in generating the classification model. In the fuzzy classification step, an “indirect approach” is used for fuzzy system modeling by implementing the exponential compactness and separation index for determining the number of rules in the fuzzy clustering approach. Therefore, we first proposed a Type-I fuzzy system that had an accuracy of approximately 90.9%. In the proposed system, the process of diagnosis faces vagueness and uncertainty in the final decision. Thus, the imprecise knowledge was managed by using interval Type-II fuzzy logic. The results that were obtained show that interval Type-II fuzzy has the ability to diagnose hepatitis with an average accuracy of 93.94%. The classification accuracy obtained is the highest one reached thus far. The aforementioned rate of accuracy demonstrates that the Type-II fuzzy system has a better performance in comparison to Type-I and indicates a higher capability of Type-II fuzzy system for modeling uncertainty.
Abstract: One of the major developments in machine learning in the past decade is the ensemble method, which finds highly accurate classifier by combining many moderately accurate component classifiers. In this research work, new ensemble classification methods are proposed with homogeneous ensemble classifier using bagging and heterogeneous ensemble classifier using arcing and their performances are analyzed in terms of accuracy. A Classifier ensemble is designed using Radial Basis Function (RBF) and Support Vector Machine (SVM) as base classifiers. The feasibility and the benefits of the proposed approaches are demonstrated by the means of standard datasets of intrusion detection. The main originality of the proposed approach is based on three main parts: preprocessing phase, classification phase, and combining phase. A wide range of comparative experiments is conducted for standard datasets of intrusion detection. The performance of the proposed homogeneous and heterogeneous ensemble classifiers are compared to the performance of other standard homogeneous and heterogeneous ensemble methods. The standard homogeneous ensemble methods include Error correcting output codes, Dagging and heterogeneous ensemble methods include majority voting, stacking. The proposed ensemble methods provide significant improvement of accuracy compared to individual classifiers and the proposed bagged RBF and SVM performs significantly better than ECOC and Dagging and the proposed hybrid RBF-SVM performs significantly better than voting and stacking. Also heterogeneous models exhibit better results than homogeneous models for standard datasets of intrusion detection.
Abstract: Blood cell analysis plays a significant role in the diagnosis of human health. As an alternative to the traditional technique conducted by laboratory technicians, this paper presents an automatic white blood cell (leukocyte) detection system using Image Stitching and Color Overlapping Windows. The advantage of this method is to present a detection technique of white blood cells that are robust to imperfect shapes of blood cells with various image qualities. The input for this application is images from a microscope-slide translation video. The preprocessing stage is performed by stitching the input images. First, the overlapping parts of the images are determined, then stitching and blending processes of two input images are performed. Next, the Color Overlapping Windows is performed for white blood cell detection which consists of color filtering, window candidate checking, window marking, finds window overlaps, and window cropping processes. Experimental results show that this method could achieve an average of 82.12% detection accuracy of the leukocyte images.
Abstract: Obturator Foramen is a specific structure in Pelvic
bone images and recognition of it is a new concept in medical image
processing. Moreover, segmentation of bone structures such as
Obturator Foramen plays an essential role for clinical research in
orthopedics. In this paper, we present a novel method to analyze the
similarity between the substructures of the imaged region and a hand
drawn template as a preprocessing step for computation of Pelvic
bone rotation on hip radiographs. This method consists of integrated
usage of Marker-controlled Watershed segmentation and Zernike
moment feature descriptor and it is used to detect Obturator Foramen
accurately. Marker-controlled Watershed segmentation is applied to
separate Obturator Foramen from the background effectively. Then,
Zernike moment feature descriptor is used to provide matching
between binary template image and the segmented binary image for
final extraction of Obturator Foramens. Finally, Pelvic bone rotation
rate calculation for each hip radiograph is performed automatically to
select and eliminate hip radiographs for further studies which depend
on Pelvic bone angle measurements. The proposed method is tested
on randomly selected 100 hip radiographs. The experimental results
demonstrated that the proposed method is able to segment Obturator
Foramen with 96% accuracy.