Search Results - (( time evaluation method algorithm ) OR ( parallel extraction using algorithm ))

Optimization of extractive Automatic Text Summarization using Decomposition-based Multi-objective Differential Evolution and parallelization by Hazmi Wahab, Muhammad Hafizul

“…While the current approach yields impressive Recall-Oriented Understudy for Gisting Evaluation (ROUGE) metrics for the generated summary, it struggles with inefficiencies, mainly attributed to the substantial optimization time consumed by the ATS repair operator scheme. …”
Get full text
Get full text
Get full text

Projecting named entity tags from a resource rich language to a resource poor language by Zamin, Norshuhani, Oxley, Alan, Abu Bakar, Zainab

“…The method computes the string similarity between the English words and the list of available lexemes in a pre-built lexicon that approximates the best NE mapping.The algorithm has been effectively evaluated using our own terrorism tagged corpus; it achieved satisfactory results in terms of precision, recall, and F-measure.An evaluation of the selected open source NER tool for English is also presented.…”
Get full text
Get full text
Get full text

Projecting named entity tags from a resource rich language to a resource poor language by Zamin, N., Oxley, A., Bakar, Z.A.

“…The algorithm has been effectively evaluated using our own terrorism tagged corpus; it achieved satisfactory results in terms of precision, recall, and F-measure. …”
Get full text
Get full text

Projecting named entity tags from a resource rich language to a resource poor language by Zamin, N., Oxley, A., Bakar, Z.A.

“…The algorithm has been effectively evaluated using our own terrorism tagged corpus; it achieved satisfactory results in terms of precision, recall, and F-measure. …”
Get full text
Get full text

Projecting named entity tags from a resource rich language to a resource poor language by Zamin, N., Oxley, A., Bakar, Z.A.

“…The algorithm has been effectively evaluated using our own terrorism tagged corpus; it achieved satisfactory results in terms of precision, recall, and F-measure. …”
Get full text
Get full text

Hybrid Machine Translation Using Malay-English Language Parallel Text Extraction From Comparable Text by Yeong, Yin Lai

“…We improve the bleu score from 13.40% to 15.41% using 315,194 parallel texts. In the second problem, we propose an algorithm to extract parallel sentences and parallel fragments/subsentences from comparable texts. …”
Get full text
Get full text

Voting algorithms for large scale fault-tolerant systems by Karimi, Abbas

“…To solve this problem and gain benefits of this algorithm, we employed parallel algorithm technique and by using optimal number of processors, we could propose optimal algorithms known as Parallel Average Voting and Parallel Weighted Average Voting which both have optimal time complexity and less calculation cost. …”
Get full text
Get full text

Image classification using two dimensional wavelet coefficients with parallel computing by Ong, Yew Fai

“…This research algorithm demonstrated a very promising result with Support Vector Machines, this algorithm produces a 90% of accuracies whereas the decision tree algorithm gets 100% accuracies. …”
Get full text
Get full text

A Parallel-Model Speech Emotion Recognition Network Based on Feature Clustering by Li-Min Zhang, Giap Weng Ng, Yu-Beng Leau, Hao Yan

“…To address this issue, we proposed a novel algorithm called F-Emotion to select speech emotion features and established a parallel deep learning model to recognize different types of emotions. …”
Get full text
Get full text
Get full text
Get full text

A parallel-model speech emotion recognition network based on feature clustering by Li-Min Zhang, Giap Weng Ng, Yu-Beng Leau, Hao Yan

“…To address this issue, we proposed a novel algorithm called F-Emotion to select speech emotion features and established a parallel deep learning model to recognize different types of emotions. …”
Get full text
Get full text
Get full text

New algorithm for evaluation of electric fields due to indirect lightning strike by Izadi, Mahdi, Ab Kadir, Mohd Zainal Abidin

“…In this paper, using dipole method, Maxwell's equation and Cooray-Rubinstein formula, a new method for calculation of electric field in time domain is proposed. …”
Get full text
Get full text
Get full text

Automatic label removal from digitized weld radiographs by Soo, Say Leong, Ratnam, Mani Maran, Samad, Zahurin, Khalid, Mohd. Ashhar

“…Normality test was used to determine if the intensity profile parallel to the weld contains label pixels. …”
Get full text
Get full text
Get full text

An efficient indexing and retrieval of iris biometrics data using hybrid transform and firefly based K-means algorithm title by Khalaf, Emad Taha

“…The enhanced method combines three transformation methods for analyzing the iris image and extracting its local features. It uses a weighted K-means clustering algorithm based on the improved FA to optimize the initial clustering centers of K-means algorithm, known as Weighted K-means clustering-Improved Firefly Algorithm (WKIFA). …”
Get full text
Get full text

Parallelizing web scraping to improve performance and scalability by Na, Yi Chun

Get full text
Get full text

DESIGN AND EVALUATION OF RESOURCE ALLOCATION AND JOB SCHEDULING ALGORITHMS ON COMPUTATIONAL GRIDS by MEHMOOD SHAH, SYED NASIR

“…The four prime aspects of this work are: firstly, a model of the grid scheduling problem for dynamic grid computing environment; secondly, development of a new web based simulator (SyedWSim), enabling the grid users to conduct a statistical analysis of grid workload traces and provides a realistic basis for experimentation in resource allocation and job scheduling algorithms on a grid; thirdly, proposal of a new grid resource allocation method of optimal computational cost using synthetic and real workload traces with respect to other allocation methods; and finally, proposal of some new job scheduling algorithms of optimal performance considering parameters like waiting time, turnaround time, response time, bounded slowdown, completion time and stretch time. …”
Get full text
Get full text

Combining deep and handcrafted image features for MRI brain scan classification by Hasan, Ali M., Jalab, Hamid A., Meziane, Farid, Kahtan, Hasan, Al-Ahmad, Ahmad Salah

“…In parallel, handcrafted features are extracted using the modified gray level co-occurrence matrix (MGLCM) method. …”
Get full text
Get full text
Get full text

Sudoku Generator based on hybrid algorithm / Faridah Abdul Rahman by Abdul Rahman, Faridah

Get full text
Get full text

Evaluation of Lightning Current Using Inverse Procedure Algorithm. by Ab Kadir, Mohd Zainal Abidin, Izadi, Mahdi, Askari, Mohamad Tolou, Hajikhani, Maryam

“…In this study an inverse procedure algorithm is proposed in the time domain to evaluate lightning return stroke current based on measured electromagnetic fields at an observation point. …”
Get full text
Get full text

Robust partitioning and indexing for iris biometric database based on local features by Khalaf, Emad Taha, Mohammed, Muamer N., Kohbalan, Moorthy

“…The proposed method combines three transformation methods DCT, DWT and SVD to analyse iris images and extract their local features. Further, the scalable K-means++ algorithm is used for partitioning and classification processes, and an efficient parallel technique that divides the features groups causing the formation of two b-trees based on index keys is applied for search and retrieval. …”
Get full text
Get full text
Get full text

On comparison between Cooray-Rubinstein and FDTD methods for ground conductivity effect on horizontal electric field evaluation in time domain by Izadi, Mahdi, Ab Kadir, Mohd Zainal Abidin, Wan Ahmad, Wan Fatinhamamah, Mohd Nawi, Zawati, Esfahani, Mohammad Tolou Askari Sedehi

“…In this paper, the FDTD method and Caligaris et al. algorithm (Cooray-Rubinstein method in time domain) are applied for evaluation of horizontal electric field in the close distance from lightning channel case. …”
Get full text
Get full text