A Reduced Uncertainty-Based Hybrid Evolutionary Algorithm for Solving Dynamic Shortest-Path Routing Problem

Kusetoğulları, Hüseyin; Sharif, Md. Haidar; Leeson, Mark S.; Çelik, Turgay

doi:10.1142/s021812661550067x

Cited by 10 publications

(8 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Normally, multiple comparisons with a control algorithm are applied to statistically present that the performance of one algorithm is better than that of its alternatives in areas related to computer science [71], [126]. The main reason of applying the non-parametric tests [127] is that they do not make any assumption regarding the underlying distribution of the data.…”

Section: Results From Statistical Testsmentioning

confidence: 99%

See 1 more Smart Citation

Deep Sentiment Analysis: A Case Study on Stemmed Turkish Twitter Data

Shehu

Sharif

et al. 2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

Sentiment analysis using stemmed Twitter data from various languages is an emerging research topic. In this paper, we address three data augmentation techniques namely Shift, Shuffle, and Hybrid to increase the size of the training data; and then we use three key types of deep learning (DL) models namely recurrent neural network (RNN), convolution neural network (CNN), and hierarchical attention network (HAN) to classify the stemmed Turkish Twitter data for sentiment analysis. The performance of these DL models has been compared with the existing traditional machine learning (TML) models. The performance of TML models has been affected negatively by the stemmed data, but the performance of DL models has been improved greatly with the utilization of the augmentation techniques. Based on the simulation, experimental, and statistical results analysis deeming identical datasets, it has been concluded that the TML models outperform the DL models with respect to both training-time (TTM) and runtime (RTM) complexities of the algorithms; but the DL models outperform the TML models with respect to the most important performance factors as well as the average performance rankings.

show abstract

Section: Results From Statistical Testsmentioning

confidence: 99%

“…2 (a) shows an example of a sentence generated by the shift augmentation technique. 2) Shuffle Technique ⇒ Similar to crossover [71], the shuffle technique swaps and concatenates words of the same sentence to produce a new sentence of the same class.…”

Section: A Proposed Data Augmentation Techniquesmentioning

confidence: 99%

Deep Sentiment Analysis: A Case Study on Stemmed Turkish Twitter Data

Shehu

Sharif

et al. 2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…Larger AUC values indicate better classifier performance [67]. A complete statistical analysis [68] would be performed to compare the performance of the proposed approach with miscellaneous state-of-the-art algorithms. Kalman filter has low computational requirements.…”

Section: E Future Workmentioning

confidence: 99%

Untitled

2019

IJCSE

View full text Add to dashboard Cite

Laser scanners have a lot of advantages over conventional video cameras. Data processing in laser scanner system becomes faster and easier because there is no need to record real world videos. Besides, the problem of private life conservation is taken away. This paper proposes an approach to track objects from laser scanned dataset. Data points collected by each scan of laser scanners are considered as video frame. Support vector machine (SVM) along with Hungarian algorithm and Kalman filter are used to obtain trajectories of objects from the laser scanned dataset. Experimental results on the same laser scanned datasetshow that the method of SVM with Hungarian algorithm and Kalman filter performs better than that of its alternative having various thresholds with Hungarian algorithm and Kalman filter.

show abstract

“…Future implementation of this study will introduce the same implemented model to be clustered where multiple master nodes with nodes form similar model in a multilevel implementation depending on the size of the available number of nodes in the computer network. Miscellaneous statistical tests [16], accuracy [17], and the area under the receiver operating characteristic curves [18] would be analyzed in the long run.…”

Section: Future Workmentioning

confidence: 99%

Parallel computing for artificial neural network training

Gursoy¹,

Sharif²

2018

PEN

View full text Add to dashboard Cite

As an enormous computing power is required to get knowledge from a large volume of data, the parallel and distributed computing is highly recommended to process them. Artificial Neural Networks (ANNs) need as much as possible data to have high accuracy, whereas parallel processing can help us to save time in ANNs training. In this paper, exemplary parallelization of artificial neural network training by dint of Java and its native socket libraries has been implemented. During the experiments, it has been noticed that Java native socket implementation tends to have memory issues when a large amount of training datasets are involved in training. It has been remarked that exemplary parallelization of artificial neural network training cannot outperform drastically when additional nodes are introduced into the system after a certain point. This is comprehensively due to the network communication complexity in the system.Corresponding Author: Name Md. Haidar Sharif Affiliation International Balkan University Address Skopje, Republic of Macedonia Phone +38923214831 Email msharif@ibu.edu.mk IntroductionParallel and distributed computing are required to get knowledge from a large volume of data. Artificial Neural Networks (ANNs) need to have high accuracy, whereas parallel processing can help us to save time in ANNs training. In the literature, many articles on parallelization of neural network pieces of training can be found. Some examples are given herewith. A parallelized Back-Propagation Neural Network (BPNN) based on MapReduce computing model was introduced by Liu et al. [1]. A cascading model based classification approach was implemented to introduce fault tolerance, data replication, and load balancing. Nodes were trained for a specific class available in training dataset. As a result, a much stronger classifier could be built by the weak classifiers in the cluster. A parallelizing technique for the training of neural networks on the cluster computer was presented by Dahl et al. [2]. A full neural network was copied at each cluster node for the eight-bit parity problem. The subset of the training data in each node was randomly selected at each epoch, which is the date and time related to a computer's clock [3]. An improvement up to a factor of 11 in terms of training time as compared to sequential training was demonstrated through the obtained results. The type of neural network problem was mentioned. A different kind of exemplary parallelization was implemented. The communication costs of the approach were analysed. But it was not recommended the node parallelism in cluster computer. A comparative study along with an own technique for the performance of exemplary parallel and node parallel strategies on a cluster computer were performed by Pethick et al. [4]. The performance of various sizes of neural networks, miscellaneous dataset sizes, and the number of processors was studied. The affirmative and the negative sides of their proposed method were discussed. The cost equation introduced in their method ...

show abstract

A Reduced Uncertainty-Based Hybrid Evolutionary Algorithm for Solving Dynamic Shortest-Path Routing Problem

Cited by 10 publications

References 64 publications

Deep Sentiment Analysis: A Case Study on Stemmed Turkish Twitter Data

Deep Sentiment Analysis: A Case Study on Stemmed Turkish Twitter Data

Untitled

Parallel computing for artificial neural network training

Contact Info

Product

Resources

About