Showing papers in "Journal of King Saud University - Computer and Information Sciences in 2019"

TL;DR: An overview of feature selection techniques and instability of the feature selection algorithm is provided and some of the solutions which can handle the different source of instability are presented.

TL;DR: A new reliable hybrid method for an anomaly network-based IDS (A-NIDS) using artificial bee colony (ABC) and AdaBoost algorithms in order to gain a high detection rate (DR) with low false positive rate (FPR) is proposed.

TL;DR: A comprehensive review of the state of the art architectures, tools and methodologies in existing implementations of capsule networks highlights the successes, failures and opportunities for further research to serve as a motivation to researchers and industry players to exploit the full potential of this new field.

TL;DR: A subject independent emotion recognition technique is proposed from EEG signals using Variational Mode Decomposition (VMD) as a feature extraction technique and Deep Neural Network as the classifier that performs better compared to the state of the art techniques in subject-independent emotion recognition from EEG.

TL;DR: This work analyzes the feasibility and accuracy of thermal imaging in the field of pothole detection using convolutional neural networks approach of deep learning and shows that images were correctly identified with the best accuracy of 97.08% using one of the pre-trained convolutionAL neural networks based residual network models.

TL;DR: This study is based on the RFM (Recency, Frequency and Monetary) model and deploys dataset segmentation principles using K-Means Algorithm and results are compared with various parameters like Sales Recency, Sales Frequency and Sales Volume.

TL;DR: A novel Source based DDoS defence mechanism which can be used in fog environment as well as the cloud environment to mitigate DDoS attacks and provides deep learning (DL) based detection method which makes use of the network traffic analysis mechanisms to filter and forward the legitimate packets to the server and can block the infected packets to cause further attacks.

TL;DR: A new Fitness based Glowworm swarm with Fruitfly Algorithm (FGF), which is the hybridization of Glowworm Swarm Optimization and Fruitfly Optimization algorithm (FFOA) to choose the best CH in WSN to maximize the lifetime of network as well as energy efficiency.

TL;DR: Experimental results with respect to peak signal-to-noise ratio (PSNR), embedding capacity (EC), structural similarity index (SSIM), and the comparative analysis with recently proposed state-of-art approaches exhibit the superiority of the proposed approach.

TL;DR: This proposed new binary grasshopper optimization algorithm is tested and compared to five well-known swarm-based algorithms used in feature selection problem and demonstrated that the proposed approach could outperform the other tested methods.

TL;DR: A Hybrid Artificial Bee Colony and Monarchy Butterfly Optimization Algorithm (HABC-MBOA)-based Cluster Head Selection Scheme is proposed for the predominant selection of cluster heads under clustering process and plays an anchor role in eliminating inadequacy of ABC algorithm towards global search potential.

TL;DR: A roadmap of steps for making these websites inclusive and barrier-free for PwDs is presented, in terms of metrics such as a number of problems, warnings and a status of success criteria violations.

TL;DR: The proposed Taylor C-SSA algorithm shows best performance in terms of energy, number of alive nodes, delay, and throughput values of 0.129, 42, 0.291, and 0.1, respectively.

TL;DR: This paper proposes a new anonymization scheme of data privacy for e-health records which differs from existing approaches in its ability to prevent from identity disclosure even faced with adversaries having pertinent background knowledge.

TL;DR: This work has developed a CNN model from scratch by training the model with the Tamil characters in offline mode and has achieved good recognition results on both the training and testing datasets.

TL;DR: A signer independent novel vision-based gesture recognition system which is capable of recognizing single handed static and dynamic gestures, double-handed static gestures and finger spelling words of Indian Sign Language (ISL) from live video is proposed.

TL;DR: It is indicated that the perceived usefulness of a wearable IoT device provides the strongest motivation for individuals to use it at the workplace, and applying the ANFIS approach helps improve the predictability of user intention to use IoT devices.

TL;DR: This paper proposes simple generic techniques using neural network for the summarization task for Indian legal judgment documents utilizing the word and sentence embeddings for capturing the semantics and tackles the problem of unavailability of labelled data for the task.

TL;DR: The experimental analysis indicates that the JHE based technique produces better results than the state-of-the-art HE based contrast enhancement algorithms, and produces the best results even for images having a narrow dynamic range.

TL;DR: From simulations, it is found that the modified dimension and additional inertia weight factor of Bat Algorithm proves to be more effective than the basic Bat Al algorithm in terms of searching for a solution while improving quality of results in all cases or significantly improving convergence speed.

TL;DR: This paper provides a comprehensive survey of periocular biometrics and a deep insight of various aspects such as utility ofperiocular region as a stand-alone modality, periacular region and its fusion with iris, application of peroocular region in smart phone authentication and the role of peruocular regionIn soft biometric classification etc.

TL;DR: An ECC-based mutual authentication protocol for smart grid communication using biometric approach that takes much less communication and computation costs compared with other existing protocols in SG environment and is convenient for practical application in SG communication.

TL;DR: An enhanced machine learning-based predictive model is proposed to improve the efficiency of anti-phishing schemes and indicates a remarkable performance with 0.04% False Positive and 99.96% accuracy for both SVM and NB predictive models.

TL;DR: The proposed dilated hybrid edge detection on the three most significant bits (MSB) pixels of cover images with the aim of expanding the edge area so as to increase the data embedding capacity in image steganography succeeded in improving the quality of imperceptibility.

TL;DR: A time efficient optimization method based on machine learning algorithms to detect the best embedding parameter for image watermarking with both robustness and imperceptibility is proposed and it has been found that the proposed method consumes very less time for the evaluation of optimum solutions.

TL;DR: This paper investigates the problem involved with pattern mining approaches and associated techniques such as Apache Hadoop, Apache Spark, parallel and distributed processing, and examines major developments in parallel, distributed, and scalable pattern mining.

TL;DR: The proposed ensemble method is based on integrating a rule-based classifier with machine learning techniques, while utilizing content-based features that depend on N-gram features and Negation handling and achieves a classification accuracy of 95.25% and 99.98% for the two experimented datasets.

TL;DR: The effectiveness of the external memory usage in search diversification is evidenced and such usage improves the performance of the hybrid Elitist-Ant System over diverse datasets and problems.

TL;DR: Improved Scalable l-Diversity (ImSLD) approach is proposed which is the extension of Improved Scalable k-Anonymity (ImSKA) for scalable anonymization in this paper, based on scalable k-anonymization that uses MapReduce as a programming paradigm.

TL;DR: In this article, a load balancing framework for workflows execution has been proposed to optimize the utilization of VMs with uniform load distribution, which is based on the hybridization of heuristic techniques with metaheuristic algorithm.