Showing papers in "Journal of King Saud University - Computer and Information Sciences in 2022"

TL;DR: Wang et al. as discussed by the authors proposed a bidirectional convolutional recurrent neural network architecture to derive both past and future contexts by connecting two hidden layers of opposite directions to the same context.

TL;DR: In this paper , an adaptive multi-model has been realized by combining the color histogram with the Kernel Correlation Filter algorithm, and the sparse representation method has been introduced into the training process to heighten the stability of the proposed object tracking algorithm.

TL;DR: In this paper , a multiple image encryption scheme based on hyperchaotic map and 3D cube is designed, where multiple images are segmented by columns, and a regular cube is obtained by stacking multiple fixed-size planes along the z-axis direction.

TL;DR: Wang et al. as mentioned in this paper proposed a novel DeepMasknet framework capable of both the face mask detection and masked facial recognition, which can detect the people not wearing the face masks and recognizing different persons while wearing the mask.

TL;DR: In this article , a detailed overview of DM detection and self-management techniques using machine learning and artificial intelligence techniques is presented, which may prove valuable to the community of scientists employed in the area of automatic DM detection, diagnosis, and selfmanagement.

TL;DR: In this article , a diagnostic system that utilizes an optimized XGBoost (Extreme Gradient Boosting) classifier to predict heart disease was presented, which reached the high prediction accuracy of 91.8%.

TL;DR: A comprehensive review of the state-of-the-art architectures, tools and methodologies in existing implementations of capsule networks is provided in this article , highlighting the successes, failures and opportunities for further research to serve as a motivation to researchers and industry players.

TL;DR: Li et al. as discussed by the authors proposed a self-attention negative feedback network (SRAFBN) for real-time image super-resolution, which constrains the image mapping space and selects the key information of the image through the self attention negative feedback model, so that higher quality images can be generated to meet human visual perception.

TL;DR: In this article , the authors proposed the prediction model of Apple disease in the apple orchards of Kashmir valley using data analytics and Machine learning in IoT system and discussed the challenges faced when incorporating these technologies in the traditional farming approaches.

TL;DR: In this article , a state-of-the-art review is conducted on the most influential articles, conference papers, and review papers related to Blockchain published from 2013 to 2020 and indexed by the Web of Science Core CollectionTM (WoS) world's literature database.

TL;DR: In this article , the authors apply business intelligence in identifying potential customers by providing relevant and timely data to business entities in the Retail Industry, which is based on systematic study and scientific applications in analyzing sales history and purchasing behavior of the consumers.

TL;DR: In this article , the authors present a comprehensive survey of existing 6G trends, technologies, applications, industrial markets, and network structures for the most promising 6G applications and explore the business direction for 6G by introducing the most recently 6G projects in the vertical markets.

TL;DR: In this paper , 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.

TL;DR: In this paper , the authors proposed a hierarchical clustering framework based on ensemble approaches, which includes the clusters clustering technique and a novel similarity measurement, which is a Meta-Clustering Ensemble scheme based on Model Selection (MCEMS).

TL;DR: In this paper , the authors present an intuitive review about the possibilities for TinyML and identify key challenges and a future roadmap for mitigating several research issues of TinyML, including maintaining the accuracy of learning models, providing train-to-deploy facility in resource frugal tiny edge devices, optimizing processing capacity, and improving reliability.

TL;DR: In this article , the authors proposed a capable architecture of the waste management system based on deep learning and IoT, which rendered an astute way to sort digestible and indigestible waste using a convolutional neural network (CNN).

TL;DR: In this article , a meta-learning approach was used for emotion recognition from facial expressions using still images and it is robust to partial occlusions, varying head poses and illumination levels which is the novelty of this work.

TL;DR: In this paper , the authors proposed a source based DDoS defence mechanism which can be used in fog environment as well as the cloud environment to mitigate DDoS attacks, which makes use of Software Defined Network (SDN) to deploy the DDoS defender module at SDN controller.

TL;DR: Deep learning methods possess many processing layers to understand the stratified representation of data and have achieved state-of-the-art results in several domains as discussed by the authors , including text generation.

TL;DR: In this article , a hybridization of modified Particle swarm optimization and improved Q-learning algorithm named as QMPSO is proposed to enhance the performance of the machine by balancing the load among the VMs, maximize the throughput of VMs and maintain the balance between priorities of tasks.

TL;DR: In this article , a combination of conditional decision-making and machine learning approaches is used to predict hypertension and diabetes status, respectively, in a smart home health monitoring system that helps to analyze the patient's blood pressure and glucose readings at home and notifies healthcare provider in case of any abnormality detected.

TL;DR: In this article , the authors discuss the opportunities, benefits, and challenges of blockchain technology and to assist the research community in understanding the same, and also discuss the taxonomy, application/use-cases, consensus mechanisms, prospective research, future directions, and related technologies.

TL;DR: Cheng et al. as discussed by the authors used a Two Channel CNN, a low complex architecture to classify between Glioma and healthy tumor MRI samples which was successfully done with an accuracy of 98.21 percentage.

TL;DR: In this paper , a novel BiLSTM with deep CNN and Hierarchical ATtention-based deep learning model for tweet representation learning toward hate speech detection was proposed.

TL;DR: Wang et al. as mentioned in this paper proposed a novel blockchain-based secure decentralized system using IPFS for secure data transfer, where the data owner uploads an encrypted file to IPFS, which is subsequently separated into n secret sections called hash codes for data security.

TL;DR: In this paper , an efficient glaucoma master framework was introduced to segment the optic cup and optic disc to find the Cup-to-Disc-Ratio (CDR).

TL;DR: In this article , an efficient method is proposed for improving local random walk by encouraging random walk to move, in every step, towards the node which has a stronger influence, therefore, the next node is selected according to the influence of the source node.

TL;DR: In this paper , a systematically reviews is done on different types of particle swarm optimization (PSO) based scheduling strategy with set of challenges and future direction, PSO is appropriate for dynamic task scheduling, workflow scheduling and load balancing.

TL;DR: In this article , the authors proposed a multipath residual attention block (MRAB) to improve the performance of the UNet architecture for brain tumor segmentation, which achieved dice scores of 77.71%, 79.77%, 89.33%, and 77.59% on the Brain Tumor Segmentation (BraTS) dataset.

TL;DR: In this paper , the authors proposed a novel logic mining by introducing log-linear analysis to select the best attributes which formulate the logical rule that will be embedded into the energy-based ANN named Discrete Hopfield Neural Network (DHNN).