Showing papers in "Journal of King Saud University - Computer and Information Sciences in 2018"

TL;DR: A taxonomy for the load balancing algorithms in the cloud is presented and a brief explanation of considered performance parameters in the literature and their effects is presented in this paper.

TL;DR: An improved information hiding implemented based on difference expansion and modulus function is presented and it is shown that the proposed scheme achieves better results than the existing methods.

TL;DR: A new wrapper-based feature selection method called binary teaching learning based optimization (FS-BTLBO) algorithm which needs only common controlling parameters like population size, and a number of generations to obtain a subset of optimal features from the dataset.

TL;DR: It is shown that more effective and efficient security requirements can be elicited by the STORE methodology and that it helps the security requirement engineer to elicit security requirements in a more organized manner.

TL;DR: Six machine learning models have been used for software quality prediction on five open source software and results show that Random Forest and Bagging produce good results while Naive Bayes is least preferable for prediction.

TL;DR: The proposed method outperforms the other clustering methods with competitive dice score values for segmentation of edema and Tumor Core (TC) regions from MRI images as it creates high-quality clusters.

TL;DR: A novel cryptographic technique has been presented that uses client-side data encryption for encrypting the data before uploading it onto the cloud and it is a multifold symmetric-key cryptography technique which is based upon DNA cryptography.

TL;DR: The attempt was made to implement left and right hand movement classification after removal of the artifacts in the acquired signals of the various hand movements.

TL;DR: The hybrid imputation method proposed with respect to the dependency between the attributes and the type of incomplete attributes in order to especially improve the prediction of breast cancer recurrence outperforms all other imputation-classifier pairs in terms of specificity, sensitivity and accuracy.

TL;DR: Experimental results show that the proposed automated brain tumor segmentation method using rough-fuzzy C-means (RFCM) has achieved better performance based on statistical volume metrics than previous state-of-the-art algorithms with respect to ground truth (manual segmentation).

TL;DR: A hierarchical architectural design is proposed where numerous components are joined together for a more powerful and strong classification of the visual data.

TL;DR: A pair-based task scheduling algorithm for cloud computing environment, which is based on the well-known optimization algorithm, called Hungarian algorithm is presented, and it is shown to require O (kpl2) time for k iterations, p repetitions and l tasks.

TL;DR: This paper presents a new technique to denoise CT images with edge preservation in tetrolet domain (Haar-type wavelet transform) where a locally adaptive shrinkage rule is performed on high frequency tetrolet coefficients in such a way that noise can be reduced more effectively.

TL;DR: A Systematic Literature Review is conducted to highlight development and testing estimation process for software/application and to identify and compare existing test estimation techniques for traditional software (desktop/laptop) and for mobile software/ application.

TL;DR: Outcomes achieved with the proposed Biogeography-based optimization with adaptive neuro-fuzzy inference system are far better as compared to some recent work.

TL;DR: The work studies the insight of existing backfilling algorithm that is used to schedule deadline sensitive lease in the Open Nebula cloud platform and improves the scheduling performances with respect to maximize the task acceptance ratio and reduce the task rejection ratio.

TL;DR: A more efficient centralized group key distribution (CGKD) protocol that minimizes the computation cost of key server (KS) during key updating and the computationcost of members is balanced during key recovery.

TL;DR: A new chaos-based probabilistic symmetric encryption scheme with customizable block-size suitable for image encryption with high strength to resist statistical and cryptanalytic attacks is proposed.

TL;DR: The results of this NGCS-based cervical cancer detection technique is proved to be excellent on an average by 13% compared to the traditional graph cut oriented cancer detection approaches.

TL;DR: The diverse research gaps and challenges in VLSI design are provided, which may be helpful for the authors and the philosophers to contribute for further research.

TL;DR: Experimental results of the proposed automatic thresholding algorithm based on the acquisition of the defective region histogram and the selection of its extreme edge as the threshold value show that the proposed method outperforms the current methods in terms of defect detection.

TL;DR: It has been shown that the accuracy of the proposed approach is significantly increased and the purpose of applying the gradient method is accelerating the convergence of the used optimization algorithm.

TL;DR: A modified tensor factorization method is used for estimating the missing data in cancer diagnosis and it is suggested that the proposed method is superior to other methods in terms of RMSE, accuracy, sensitivity and specificity.

TL;DR: In this paper, a query control technique is proposed for cluster based routing protocol to reduce the broadcast expenses in clustered ad-hoc networks, which works based on broadcast repealing. But, this query broadcast is done to carry out the route-search task that leads to the unnecessary propagation of route-query even after route has been found.

TL;DR: This work introduced a novel emotion recognition scheme, Whale-Imperialist Optimization algorithm (Whale-IpCA) based Multiple Support Vector Neural Network (Multi-SVNN) classifier, for identifying the emotions in the speech signal.

TL;DR: The feature fusion can be used to achieve efficient plant identification and the accuracy of identification for leaf spectral data, leaf venation features and HOG features is validated, indicating that feature fusion technique performs better than that of non-imaging spectral signatures features only.

TL;DR: Overall, BN-grams has a higher value of topic recall than that of document pivot, and both algorithms with trending topics found in local news and Twitter trending topics are found to be accurate.

TL;DR: The problem solving approach of the teaching learning based optimization (TLBO) along with learning ability of the gradient descent learning (GDL) is used to obtain the optimal set of weight of FLANN learning model.

TL;DR: A fuzzy logic computational model is presented based on a survey to measure and classify the performance of Sudanese universities and academic staff, which includes computation of criteria weights and overall evaluation of Sudanian universities andademic staff using AHP and TOPSIS techniques.

TL;DR: This paper proposes an unsupervised Content-Based Medical Image Retrieval (CBMIR) framework based on the spatial matching of the visual words that efficiently computes the spatial similarity of visual words using a novel similarity measure called the Skip Similarity Index.