• Area of Interest
  • Robotics And Automation
  • Healthcare and Rehabilitation
  • Agriculture
  • Computer Vision
  • Speech Processing


• Projects Applied for Fund
  • Artificial Intelligence-based Solution for Detecting Covid-19's Variant and Period of Infection
  • Identifying Kuwait’s dates fruit Types and Maturity Using Artificial Intelligence


• CAIR’s Sponsored Projects
  • Smart Blind System
  • Date Maturity Level Estimation (DMLE)
  • Third Ear

• Workshops
  • Robotics For Middle School Students: Design and Programming Lego EV3
  • Robotics For High School Students: Design and Programming SmartBot Robot.
  • Robotics Operating System (ROS) Basics.
  • AI For High School Students: Intro to Artificial Intelligence World.
  • Artificial Intelligence for All.


• Competitions
  • Soon


• Hackathons
  • Soon

A new paper for CAIR center titled Speech/Text to Avatar Translator for Saudi Sign Language has been presented at the 9th International Conference on Applied System Innovation 2023 (ICASI 2023), Japan, 21-25 April 2023. This project was funded by the Targeted Research Grant Program— The National Transformation Program in King Abdulaziz City for Science and Technology—Kingdom of Saudi Arabia—Grant No. 5-18-03-001-0003.

A new paper titled Reducing Children’s Obesity in the Age of Telehealth and AI/IoT Technologies in Gulf Countries has been published in System Journal (IS Q2 With 2.89 Impact Factor). This Publication has been done in collaboration with Thakaa, KSU, Saudi Arabia. King Saud University.

Abstract— Childhood obesity has become one of the major health issues in the global population. The increasing prevalence of childhood obesity is associated with serious health issues and comorbidities related to obesity. Several studies mentioned that childhood obesity became even worse recently due to the effect of COVID-19 and the consequent policies and regulations. For that reason, Internet of Things (IoT) technologies should be utilized to overcome the challenges related to obesity management and provide care from a distance to improve the health care services for obesity. However, IoT by itself is a limited resource and it is important to consider other artificial intelligent (AI) components. Thus, this paper contributes into the literature of child obesity management by introducing a comprehensive survey for obesity management covering clinical work measuring the association between sleep disturbances and childhood obesity alongside physical activity and diet and comparatively analyzing the emerging technologies used to prevent childhood obesity. It further contributes to the literature by proposing an interactive smart framework that combines clinical and emerging AI/telehealth technologies to manage child obesity. The proposed framework can be used to reduce children obesity and improve their quality of life using Machine Learning (ML). It utilizes IoT devices to integrate information from different sources and complement it with a mobile application and web-based platform to connect parents and physicians with their child.

Please use the following link to access the paper:

https://www.mdpi.com/2079-8954/10/6/241

A new paper for CAIR center titled Semantic textual similarity for modern standard and dialectal Arabic using transfer learning has been published in PLOS ONE Journal (IS Q1 With 3.75 Impact Factor). This Publication has been done in collaboration with the Center of Smart robotics research, King Saud University.

Abstract— Semantic Textual Similarity (STS) is the task of identifying the semantic correlation between two sentences of the same or different languages. STS is an important task in natural language processing because it has many applications in different domains such as information retrieval, machine translation, plagiarism detection, document categorization, semantic search, and conversational systems. The availability of STS training and evaluation data resources for some languages such as English has led to good performance systems that achieve above 80% correlation with human judgment. Unfortunately, such required STS data resources are not available for many languages like Arabic. To overcome this challenge, this paper proposes three different approaches to generate effective STS Arabic models. The first one is based on evaluating the use of automatic machine translation for English STS data to Arabic to be used in fine-tuning. The second approach is based on the interleaving of Arabic models with English data resources. The third approach is based on fine-tuning the knowledge distillation-based models to boost their performance in Arabic using a proposed translated dataset. With very limited resources consisting of just a few hundred Arabic STS sentence pairs, we managed to achieve a score of 81% correlation, evaluated using the standard STS 2017 Arabic evaluation set. Also, we managed to extend the Arabic models to process two local dialects, Egyptian (EG) and Saudi Arabian (SA), with a correlation score of 77.5% for EG dialect and 76% for the SA dialect evaluated using dialectal conversion from the same standard STS 2017 Arabic set.

Please use the following link to access the paper:

https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0272991

Abstract: New paper for CAIR titled Spatial Attention-Based 3D Graph Convolutional Neural Network for Sign Language Recognition has been published in the Sensor Journal (IS Q1 With 3.57 Impact Factor). This Publication has been done with collaboration with the Center of Smart robotics research at King Saud University. This study presents an efficient architecture for sign language recognition based on a convolutional graph neural network (GCN).

Abstract— New paper for CAIR titled Spatial Attention-Based 3D Graph Convolutional Neural Network for Sign Language Recognition has been published in the Sensor Journal (IS Q1 With 3.57 Impact Factor). This Publication has been done with collaboration with the Center of Smart robotics research at King Saud University. This study presents an efficient architecture for sign language recognition based on a convolutional graph neural network (GCN).

Abstract— Coronaviruses are a huge gathering of infections that can contaminate both creatures and people. An assortment of coronaviruses is known to cause respiratory infections in people, extending from the common cold to more extraordinary sicknesses such as the Centre East Respiratory Disorder (MERS) and extraordinary intense respiratory disorder (SARS). COVID-19 is caused by a recently distinguished coronavirus. Recognizing and diagnosing these cases of respiratory infections and the COVID-19 infection has been troublesome for health associations. Therefore, in this research, we will develop an Automatic COVID-19 Diagnostic and Classification Intelligent System (ACDCIS) based on Machine Learning (ML) algorithms and techniques. The proposed ACDCIS consists of two sub-systems the three-classifier system and two-classifier system. The two-classifier system is used to determine if the patient has a Covid-19 or not, while the three-classifier system is used to determine the type of infection COVID-19, bacterial infection, or virus pneumonia infection. The high accuracy of the proposed ACDCIS system will significantly improve the speed and precision of COVID‐19 diagnosis

Center of AI & Robotics (CAIR) wishes you a successful semester and welcomes you to visit the center

A new paper for CAIR center titled Semantic textual similarity for modern standard and dialectal Arabic using transfer learning has been published in PLOS ONE Journal (IS Q1 With 3.75 Impact Factor). This Publication has been done in collaboration with the Center of Smart robotics research, King Saud University.

Abstract:Semantic Textual Similarity (STS) is the task of identifying the semantic correlation between two sentences of the same or different languages. STS is an important task in natural language processing because it has many applications in different domains such as information retrieval, machine translation, plagiarism detection, document categorization, semantic search, and conversational systems. The availability of STS training and evaluation data resources for some languages such as English has led to good performance systems that achieve above 80% correlation with human judgment. Unfortunately, such required STS data resources are not available for many languages like Arabic. To overcome this challenge, this paper proposes three different approaches to generate effective STS Arabic models. The first one is based on evaluating the use of automatic machine translation for English STS data to Arabic to be used in fine-tuning. The second approach is based on the interleaving of Arabic models with English data resources. The third approach is based on fine-tuning the knowledge distillation-based models to boost their performance in Arabic using a proposed translated dataset. With very limited resources consisting of just a few hundred Arabic STS sentence pairs, we managed to achieve a score of 81% correlation, evaluated using the standard STS 2017 Arabic evaluation set. Also, we managed to extend the Arabic models to process two local dialects, Egyptian (EG) and Saudi Arabian (SA), with a correlation score of 77.5% for EG dialect and 76% for the SA dialect evaluated using dialectal conversion from the same standard STS 2017 Arabic set.

Please use the following link to access the paper:

https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0272991

Sunday 20-6-2022

The Center for Artificial Intelligence and Robotics (CAIR) was delighted to welcome the President of the University, Professor Khaled Al-Begain, and His Excellency Ambassador Osama Shaltout, the Ambassador of the Arab Republic of Egypt to the State of Kuwait and his accompanying delegation. The delegation was briefed on the center's activities, research interests, the center's projects, and the resulting research.