A5023424035- Advanced Database Systems and Queries
- Service-Oriented Architecture and Web Services
- Algorithms and Data Compression
- Natural Language Processing Techniques
- Genomics and Phylogenetic Studies
- Machine Learning in Bioinformatics
- Topic Modeling
- Advanced Text Analysis Techniques
- Robotic Path Planning Algorithms
- Semantic Web and Ontologies
- Advanced Steganography and Watermarking Techniques
- Data Mining Algorithms and Applications
- Digital Media Forensic Detection
- Distributed systems and fault tolerance
- Text and Document Classification Technologies
- Speech Recognition and Synthesis
- Distributed and Parallel Computing Systems
- Fuzzy Logic and Control Systems
- Speech and Audio Processing
- Biometric Identification and Security
- Robotics and Sensor-Based Localization
- Spam and Phishing Detection
- Chaos-based Image/Signal Encryption
- Image Retrieval and Classification Techniques
- Opportunistic and Delay-Tolerant Networks
King Saud University
2015-2024
Laboratoire d'Informatique de Paris-Nord
2015
The King's College
2014
Policy making for smart cities: innovation and social inclusive economic growth sustainability 1. Introduction This paper aims to query the scientific debate related a new generation of policy-aware cities research geared towards socially sustainability.It summarizes rationale behind relevant JSTPM Special Issue its overall objective serve as reference policymakers, educators, practitioners, government think-tank officers interested in emerging topics research.This examines state-of-the-art...
Hand gesture recognition is an attractive research field with a wide range of applications, including video games and telesurgery techniques. Another important application hand the translation sign language, which complicated structured form gestures. In fingers' configuration, hand's orientation, relative position to body are primitives expressions. The importance has increased due prevalence touchless applications rapid growth hearing-impaired population. However, developing efficient...
An Intrusion detection system is an essential security tool for protecting services and infrastructures of wireless sensor networks from unseen unpredictable attacks. Few works machine learning have been proposed intrusion in that achieved reasonable results. However, these still need to be more accurate efficient against imbalanced data problems network traffic. In this paper, we a new model detect attacks based on genetic algorithm extreme gradient boosting (XGBoot) classifier, called...
Nowadays, Internet of Things (IoT) technology has various network applications and attracted the interest many research industrial communities. Particularly, number vulnerable or unprotected IoT devices drastically increased, along with amount suspicious activity, such as botnet large-scale cyber-attacks. In order to address this security issue, researchers have deployed machine deep learning methods detect attacks targeting compromised devices. Despite these efforts, developing an efficient...
This paper presents an adaptation of the flying ant colony optimization (FACO) algorithm to solve traveling salesman problem (TSP). new modification is called dynamic (DFACO). FACO was originally proposed quality service (QoS)-aware web selection problem. Many researchers have addressed TSP, but most solutions could not avoid stagnation In FACO, a deposits pheromone by injecting it from distance; therefore, only nodes on path also neighboring receive pheromone. The amount node receives...
This paper presents a novel Arabic Sign Language (ArSL) recognition system, using selected 2D hands and body key points from successive video frames. The system recognizes the recorded signs, for both signer dependent independent modes, concatenation of 3D CNN skeleton network point convolution network. To accomplish this, we built new ArSL video-based sign database. We will present detailed methodology recording dataset, which comprises 80 static dynamic signs that were repeated five times...
Sign language is the main channel for hearing-impaired people to communicate with others. It a visual that conveys highly structured components of manual and non-manual parameters such it needs lot effort master by hearing people. recognition aims facilitate this mastering difficulty bridge communication gap between This study presents an efficient architecture sign based on convolutional graph neural network (GCN). The presented consists few separable 3DGCN layers, which are enhanced...
Recently, several countries have been trying hard to facilitate the integration of disabled people into their societies by ensuring equal opportunities through ease access social services, daily human necessities, and labor market. Deafness is considered one major disabilities separating deaf from society. To integrate fully society, a two-way mode communication required: hearing people, other deaf. Communication person generally easy can be done speech recognition text-to-sign...
Due to the maturing of digital image processing techniques, there are many tools that can forge an easily without leaving visible traces and lead problem authentication images. Based on assumption forgery alters texture micro-patterns in a descriptors be used for modeling this change; we employed two stat-of-the-art local descriptors: multi-scale Weber's law descriptor (multi-WLD) binary pattern (multi-LBP) splicing copy-move detection. As tamper not open eyes, so chrominance components...
Although fingerprint-based systems are the commonly used biometric systems, they suffer from a critical vulnerability to presentation attack (PA). Therefore, several approaches based on fingerprint biometrics have been developed increase robustness against PA. We propose an alternative approach combination of and electrocardiogram (ECG) signals. An ECG signal has advantageous characteristics that prevent replication. Combining with is potentially interesting solution reduce impact PAs in...
Sentiment is currently one of the most emerging areas research due to large amount web content coming from social networking websites. analysis a crucial process for recommending systems people. Generally, purpose sentiment determine an author’s attitude toward subject or overall tone document. There huge collection studies that make effort predict how useful online reviews will be and have produced conflicting results on efficacy different methodologies. Furthermore, many current solutions...
Speaker recognition is an important application of digital speech processing. However, a major challenge degrading the robustness speaker-recognition systems variation in emotional states speakers, such as happiness, anger, sadness, or surprise. In this paper, we propose speaker system corresponding to three states, namely emotional, neutral, and with no consideration for speaker's state (i.e., can be neutral state), two languages: Arabic English. Additionally, cross-language was applied...
A high-performance versatile computer-assisted pronunciation training (CAPT) system that provides the learner immediate feedback as to whether their is correct very helpful in learning and allows learners practice this at any time with unlimited repetitions, without presence of an instructor. In paper, we propose deep learning-based techniques build a CAPT for mispronunciation detection diagnosis (MDD) articulatory generation non-native Arabic learners. The proposed can locate error...
In recent times, the progress of machine learning has facilitated development decision support systems that exhibit predictive accuracy, surpassing human capabilities in certain scenarios. However, this improvement come at cost increased model complexity, rendering them black-box models obscure their internal logic from users. These black boxes are primarily designed to optimize limiting applicability critical domains such as medicine, law, and finance, where both accuracy interpretability...
Various image steganography techniques have been proposed. In this paper, we investigate diverse and tools. We state a set of criteria to analyze evaluate the strengths weaknesses presented techniques. propose more robust technique that takes advantages avoids limitations.
Virtual reality technologies and their applications have received increasing attention in recent years from various perspectives. The thriving numbers behind adoption exploitation for dif...
This paper presents an enhanced artificial bee colony (ABC) algorithm for solving the web service selection problem. The proposed searches best possible combination of services to satisfy user requirements. An adapted neighborhood and replacement process a swapping are used improve ABC behavior. Neighboring nodes employed enhance performance by encouraging exploration in early iterations, where bees have no knowledge regarding search space, exploitation later iterations exploit space. is...