Center of AI & Robotics (CAIR)

The establishment of a new artificial intelligence and robotics center here at KCST serves as another pinnacle in our ultimate goal to provide our students with the highest of cognitive skills to be able to lead in tomorrow’s job market in Kuwait. Statistics indicate that in the next six years, the global market for robotics is expected to triple its current size and cross over USD 275 Billion by 2025. Reports generated based on the global LinkedIn network for employment show that the artificial intelligence experts and robotic engineers are the major sought out job opportunities that have emerged in 2020 with an annual growth rate of 75% and 40% respectively. Therefore, the existence of a center specialized in the fields of robotics and artificial intelligence is essential not only for KCST but also for Kuwait as a whole.

Our Vision

To be a leading center in the field of AI and robotics locally and regionally.

Our Mission

To attract students and interested candidates to innovate and conduct pioneering research as well as provide high-quality consultations and studies in the field of AI and robotics.

Our Objectives

  • Spreading awareness on the culture of AI and robotics in Kuwait
  • Supporting research and researchers in the field of AI and robotics.
  • Contributing in linking the outputs of the college programs in AI and robotics.
  • Leading projects that integrate local and international expertise in the field of AI and robotics.
  • Providing high-quality consultations and studies in the field of AI and robotics.

Services

Research



×

Research


  • 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

Consultation and Studies



×

Consultation and Studies


CAIR offers consultation and studies for any project that necessitate and anyone who demands.

Student Support



×

Student Support


CAIR arranges workshops, competitions and Hackathons which help participants understand the basics and applications of AI & robotics in life. Additionaly, we provide supervision for final year project students.

Supervised Final Year Projects

Applications of machine learning for fruit maturity detection is very valuable in agricultural sector.Dates are a stable food in Kuwait and the Middle East. This project will help estimate the date fruit maturity level using Computer Vision and Deep Learning techniques. The DMLE system is designed to help local farms and the ministry of agriculture to identify the maturity level of date fruit correctly and efficiently.

Students:Al-Bader Al-Mohammed | Abdulrahman Al-Walaiti

One of the methods to diagnose COVID-19 infection is by X-ray images. But the disadvantage of using X-ray images to classify the infection is that it requires a radiology expert and takes significant time. The proposed software is used to diagnose the X-ray image of the lung to classify three classes (Normal, Covid-19, or Pneumonia). The proposed software is based on ResNet50 model, where the project team modified the model and trained it with a large dataset of the three classes. The proposed software has been programmed using Python language with the aid of some libraries like Keras, Tkinter, ...etc.

Students:Ali Alajmi | Faisal Aljeeran | Ali Alhaddad | Abduallah Alshalan

We as natural persons, enjoy the blessing of sight and we can know what is going on around us, but when talking about blind people it is difficult to perceive what is going on around the blind person, proposed project that helps the blind to approximate what is going on around them by wearing a smart system. To give the blind virtual eyes through using a set of sensors and emergency button for user location.

Students: Ajyal M Alanazi | Sumiah M Almatar | Anfal Abdulrahim | Areej Fahad

There are 70 million people who suffer from deafness in the world, and a parent has psychological suffering as a parent, every day is a challenge to protect and raise a child, this project aims to make life easier for them. The aim is to manufacture an electronic bracelet that alerts the parent if anything went wrong with the baby by sending a vibration and streaming the video in the application, and it will be affordable for anyone, in this era of technology that is available for everyone we can put it to the service of mankind.

Students: Tariq Alfulaij | Ali Alhababi | Mohsen Busakher


  • 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

Area of Interest

 
Robotics and Automation
Healthcare & Rehabilitation
Agriculture

Computer Vision
Speech Processing
 

Publications

           

    A new paper for CAIR center titled Enabling Two-Way Communication of Deaf Using Saudi Sign Language has been published on 28 November 2023 IEEE Access (IS Q1 With 3.47 Impact Factor). This paper is an output of a project 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 for CAIR center titled Enabling Two-Way Communication of Deaf Using Saudi Sign Language has been published on 28 November 2023 IEEE Access (IS Q1 With 3.47 Impact Factor). This paper is an output of a project 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.


Abstract— Disabled people are facing many difficulties communicating with others and involving in society. Modern societies have dedicated significant efforts to promote the integration of disabled individuals into their societies and services. Currently, smart healthcare systems are used to facilitate disabled people. The objective of this paper is to enable two-way communication of deaf individuals with the rest of society, thus enabling their migration from marginal elements of society to mainstream contributing elements. In the proposed system, we developed three modules; the sign recognition module (SRM) that recognizes the signs of a deaf individual, the speech recognition and synthesis module (SRSM) that processes the speech of a non-deaf individual and converts it to text, and an Avatar module (AM) to generate and perform the corresponding sign of the non-deaf speech, which were integrated into the sign translation companion system called Saudi deaf companion system (SDCS) to facilitate the communication from the deaf to the hearing and vice versa. This paper also contributes to the literature by utilizing our self-developed database, the largest Saudi Sign Language (SSL) database—the King Saud University Saudi-SSL (KSU-SSL). The proposed SDCS system performs 293 Saudi signs that are recommended by the Saudi Association for Hearing Impairment (SAHI) from 10 domains (healthcare, common, alphabets, verbs, pronouns and adverbs, numbers, days, kings, family, and regions).
URL:https://ieeexplore.ieee.org/document/10330906

A new paper for CAIR center titled Facilitating the Communication with Deaf People: Building a Largest Saudi Sign Language Dataset has been published in Journal of King Saud University Computer and Information Sciences (ISI Q1 With 9.06 Impact Factor).



×

A new paper for CAIR center titled Facilitating the Communication with Deaf People :Building a Largest Saudi Sign Language Dataset has been published in Journal of King Saud University Computer and Information Sciences (ISI Q1 With 9.06 Impact Factor).


Abstract— Recently, several countries have been trying hard to facilitate the integration of disabled people into their societies by ensuring equal opportunities through ease of access to social services, daily human necessities, and the labor market. Deafness is considered one of the major disabilities separating the deaf from their society. To integrate the deaf fully into society, a two-way mode of communication is required: one from the deaf to the hearing people, and the other from the hearing to the deaf. Communication from the hearing person to the deaf is generally easy and can be done through speech recognition and text-to-sign representations, but communication from the deaf to the hearing is somewhat difficult and requires a sign recognition module that recognizes the sign motions from the deaf and translates it to a text; following this, a speech synthesis module will translate this text to speech. To build the sign recognition module, a sign language dataset is required. This paper contributes to the literature by introducing a comprehensive survey of 17 Arabic sign language datasets and by developing a well-organized framework that is used to build a sign language dataset. This paper also contributes to the literature by creating the largest Saudi Sign Language (SSL) database—the King Saud University Saudi-SSL (KSU-SSL data-base)—with 293 signs, 33 signers, 145,035 samples, and 10 domains (healthcare, common, alpha-bets, verbs, pronouns and adverbs, numbers, days, kings, family, and regions). This paper also contributes to the literature by introducing a convolutional graph neural network (CGCN) architecture for sign language recognition and applying the proposed architecture to the built KSU-SSL database. The architecture is made up of a small number of separable 3DGCN layers, and is augmented with a spatial attention mechanism. This study is a part of the project that aims to develop a two-way communication system for Saudi deaf individuals.

A new paper for CAIR center titled Sentiment Analysis Using Machine Learning Model for Qatar World Cup 2022. 






×

A new paper for CAIR center titled Sentiment Analysis Using Machine Learning Model for Qatar World Cup 2022


A new paper for CAIR center titled Sentiment Analysis Using Machine Learning Model for Qatar World Cup 2022 among Different Arabic Countries Using Twitter API has been presented at the IEEE World AI IoT Congress 2023. Four students from KCST are involved in this study: Fayzah Alotaibi, Reem Alsaeedi, Fawaz Alazmi, and Saleh Alkanadari.

A new paper for CAIR center titled Ant Colony Optimization Algorithm Enhancement for Better Performance



×

A new paper for CAIR center titled Ant Colony Optimization Algorithm Enhancement for Better Performance


A new paper for CAIR center titled Ant Colony Optimization Algorithm Enhancement for Better Performance has been presented at the IEEE World AI IoT Congress 2023. In this research, we introduced the ACOStar algorithm to improve the performance of Ant Colony Optimization (ACO) by including the evaluation function of A* algorithm on the transition-probability function of ACO.

A new paper for CAIR center titled Speech/Text to Avatar Translator



×

A new paper for CAIR center titled Speech/Text to Avatar Translator for Saudi Sign Language has been presented.


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



×

A new paper titled Reducing Children’s Obesity in the Age of Telehealth and AI/IoT Technologies in Gulf Countries has been published


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

New publication in PLOS ONE Journal (IS Q1, 3.75 Impact Factor).





×

New publication in PLOS ONE Journal (IS Q1, 3.75 Impact Factor).









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

New publication in Sensor Journal: Spatial Attention-Based 3D Graph Convolutional Neural Network for Sign Language Recognition



×

New publication in Sensor Journal: Spatial Attention-Based 3D Graph Convolutional Neural Network for Sign Language Recognition

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).

Read More

Publication in the IEEE World AI IoT Congress: Machine Learning-based System for Monitoring Social Distancing and Mask Wearing



×

Publication in the IEEE World AI IoT Congress: Machine Learning-based System for Monitoring Social Distancing and Mask Wearing


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).

Read More

IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA 2022): Automatic COVID-19 Diagnostic and Classification Intelligent System (ACDCIS)



×

IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA 2022): Automatic COVID-19 Diagnostic and Classification Intelligent System (ACDCIS)

 

 

 

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

Read More

Reducing Children’s Obesity in the Age of Telehealth and AI/IoT Technologies in Gulf Countries, System Journal (IS Q2 With 2.89 Impact Factor),2022



×

Reducing Children’s Obesity in the Age of Telehealth and AI/IoT Technologies in Gulf Countries, System Journal (IS Q2 With 2.89 Impact Factor),2022



Childhood obesity is a major global health issue, worsened by COVID-19 policies. The use of IoT technologies can help manage obesity, but limited resources require AI components. This paper introduces a survey on sleep disturbances, physical activity, and diet, and analyzes emerging technologies for prevention. It proposes an interactive smart framework combining clinical and AI/telehealth technologies to manage childhood obesity using Machine Learning. The framework integrates information from various sources, connects parents and physicians, and improves children's quality of life.

Enabling Two-way Communication of Deaf Using Saudi Sign Language," IEEE Access, 2023





×

Enabling Two-way Communication of Deaf Using Saudi Sign Language," IEEE Access, 2023



This paper introduces the Saudi Deaf Companion System (SDCS), a smart healthcare solution designed to address communication challenges faced by deaf individuals. The system incorporates three modules: Sign Recognition, Speech Recognition and Synthesis, and Avatar. Utilizing the largest Saudi Sign Language database, it enables two-way communication between deaf and non-deaf individuals by recognizing and translating signs. With 293 recognized signs across different domains, the SDCS contributes to the integration of deaf individuals into society.

Fcilitating the Communication with Deaf People: Building a Largest Saudi Sign Language Dataset,” Journal of King Saud University - Computer and Information Sciences. (ISI IF 9.71)



×

Fcilitating the Communication with Deaf People: Building a Largest Saudi Sign Language Dataset,” Journal of King Saud University - Computer and Information Sciences. (ISI IF 9.71)



This paper focuses on facilitating two-way communication for deaf individuals to enhance their integration into society. It emphasizes the challenge of enabling communication from the deaf to the hearing, proposing a sign recognition module and speech synthesis. The study contributes by surveying 17 Arabic sign language datasets, creating the extensive King Saud University Saudi-SSL (KSU-SSL) database with 293 signs, and introducing a Convolutional Graph Neural Network (CGCN) architecture for sign language recognition. This research is part of a larger project aimed at developing a comprehensive communication system for Saudi deaf individuals.

Semantic textual similarity for modern standard and dialectal Arabic using transfer learning, PLOS ONE Journal (IS Q1, 3.75 Impact Factor) 2022



×

Semantic textual similarity for modern standard and dialectal Arabic using transfer learning, PLOS ONE Journal (IS Q1, 3.75 Impact Factor) 2022



Semantic Textual Similarity (STS) is crucial in natural language processing for various applications, including information retrieval, machine translation, plagiarism detection, document categorization, semantic search, and conversational systems. However, limited STS data resources are not available for many languages like Arabic. This paper proposes three approaches to generate effective STS Arabic models: automatic machine translation, interleaving Arabic models with English data resources, and fine-tuning knowledge distillation-based models. With limited resources, the models achieved an 81% correlation and improved performance in Egyptian and Saudi Arabian dialects.

Robot-Based Solution for helping the Alzheimer Patients ,2024





×

Robot-Based Solution for helping the Alzheimer Patients ,2024



The project focuses on developing a system that utilizes the Pepper humanoid robot to assist Alzheimer's patients by enhancing memory recall and providing emotional support. It leverages advanced technologies such as facial recognition and natural language processing (NLP) to enable meaningful interactions between the robot and the patient. The system operates on SoftBank Robotics' NAOqi OS, incorporating AI models for speech recognition, emotion detection, NLP, and computer vision. The accuracy of facial recognition and speech processing is influenced by the implementation of these models and the quality of the training data. The project's findings are published in the article "SLAS Technology," an ISI Journal (Q2) with an Impact Factor of 2.8.

Sentiment Analysis Using Machine Learning Model for Qatar World Cup 2022 among Different Arabic Countries Using Twitter API



×

Sentiment Analysis Using Machine Learning Model for Qatar World Cup 2022 among Different Arabic Countries Using Twitter API



IEEE World AI IoT Congress 2023, virtual conference, 7-10 June, 2023


Proposed Dataset-Preprocessing and Implementation Framework

The research paper focuses on sentiment analysis of Twitter data related to the Qatar World Cup 2022 in Arabic countries (Egypt, Oman, Syria, Palestine, Algeria, Kuwait, Iraq, Sudan, Saudi Arabia, Jordan, Bahrain, Qatar, Yemen, and the United Arab Emirates). The study employs four machine learning algorithms—logistic regression, random forest classifier, Naive Bayes classifier, and support vector machine classifier—to analyze opinions. The results show that logistic regression and support vector machine classifiers achieved the highest average accuracies at 93%, while the random forest classifier attained 92%, and the Naive Bayes classifier had an average accuracy of 88%.

KSignStart: Mobile Application Teaching Kuwaiti Sign Language for Kids , 9-10/December 2024



×

KSignStart: Mobile Application Teaching Kuwaiti Sign Language for Kids , 9-10/December 2024



International Conference and Forum on Assistive Technologies for Special Needs (ATSN'24): AI for Inclusivity and Equality, December 9–10, 2024, KCST, Kuwait.


KSignStart Proposed Dataset

The prevalence of hearing disabilities poses significant communication challenges, particularly for children who face substantial barriers in learning sign language—a vital skills for expression and interaction. According to the World Health Organization, there are 34 million children with disabling hearing loss worldwide, a figure projected to grow substantially by 2050. In Kuwait, the Public Authority for Disability Affairs reports that there are 5,122 registered civilians with hearing disabilities, with many more potentially unregistered or foreign. Our project addresses this pressing issue by developing a mobile application that uses object detection technology to facilitate sign language learning. By enabling the app to recognize everyday objects through the camera and teach their corresponding sign language representations, we aim to make learning both accessible and enjoyable for deaf children, helping them to communicate effectively with their family and peers.

Development and Analysis of a Versatile Dataset of Speech, Real and Synthesized, of Arabic Learners



×

Development and Analysis of a Versatile Dataset of Speech, Real and Synthesized, of Arabic Learners



3rd International Conference on Computing and Information Technology (ICCIT), TABUK, KINGDOM OF SAUDI ARABIA, 13-14, September 2023


developing Arabic-CAPT-s corpus using the fast speech 2 model

In this paper, the authors address the limited availability of Computer-Aided Pronunciation Training (CAPT) datasets for Arabic compared to other languages. They introduce a versatile dataset for Arabic CAPT systems, created by leveraging the King Saud University Speech Database (KSU-SD), originally designed for speaker recognition. The newly developed corpus includes real and synthesized speech from around 60 non-native Arabic speakers representing diverse nationalities. The dataset is transcribed, segmented, and annotated, making it suitable for building Arabic CAPT systems. The paper not only outlines the dataset development process but also provides an analysis of text and speech errors within the corpus. The verification of the dataset was conducted using multiple CAPT systems

Spatial Attention-Based 3D Graph Convolutional Neural Net-work for Sign Language Recognition, Sensor Journal (IS Q1 With 3.57 Impact Factor) 2022



×

Spatial Attention-Based 3D Graph Convolutional Neural Net-work for Sign Language Recognition, Sensor Journal (IS Q1 With 3.57 Impact Factor) 2022



This study presents an efficient architecture for sign language recognition using a convolutional graph neural network (GCN). The architecture consists of a few separable 3DGCN layers, enhanced by a spatial attention mechanism. This architecture avoids over-smoothing problems and enhances spatial context representation of gestures. The architecture has shown outstanding results on various datasets.

Automatic COVID-19 Diagnostic and Classification Intelligent System (ACDCIS)



×

Automatic COVID-19 Diagnostic and Classification Intelligent System (ACDCIS)



2022 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA 2022), June 24-26, 2022


Sample of Data-A

The research addresses the challenges in identifying and diagnosing respiratory infections, particularly COVID-19, caused by a novel coronavirus. To tackle this issue, the study proposes an Automatic COVID-19 Diagnostic and Classification Intelligent System (ACDCIS) based on Machine Learning (ML). ACDCIS comprises two sub-systems: a two-classifier system for determining the presence of COVID-19 and a three-classifier system for specifying the type of infection (COVID-19, bacterial infection, or viral pneumonia infection). The goal is to enhance diagnostic speed with the high accuracy of the proposed ACDCIS system.

Machine Learning-based System for Monitoring Social Distancing and Mask Wearing



×

Machine Learning-based System for Monitoring Social Distancing and Mask Wearing



IEEE World AI IoT Congress 2022, Seattle, USA, 6-9 june, 2022


Proposed system.

The paper addresses the challenges of controlling epidemics caused by the rapid spread of viruses like COVID-19. To mitigate this, the study proposes a smart machine learning-based system designed for monitoring social distancing and mask-wearing compliance. The system is employed to identify individuals violating mask-wearing rules or not adhering to social distancing guidelines. The objective is to enhance epidemic control, reduce the transmission of COVID-19, and emphasize the importance of social distancing. Experimental results demonstrate the robustness and accuracy of the proposed system.

Kuwaiti Sign Language Recognition Using the YOLOv5 Machine Learning Model, 9-10/December 2024



×

Kuwaiti Sign Language Recognition Using the YOLOv5 Machine Learning Model, 9-10/December 2024



International Conference and Forum on Assistive Technologies for Special Needs (ATSN'24): AI for Inclusivity and Equality, December 9–10, 2024, KCST, Kuwait.

Sign language recognition has advanced for several languages, yet Arabic sign language remains underexplored in research, leaving a significant gap in accessibility tools for Arabic speakers. This paper introduces a recognition system leveraging YOLOv5 (You Only Look Once Version 5), a leading object detection model, to classify the 28 letters of the Arabic alphabet. YOLOv5’s high speed and accuracy enable it to detect and classify Arabic hand gestures in real-time, addressing the unique challenges of Arabic sign language recognition. The model was trained on a comprehensive dataset containing thousands of images representing each letter, achieving strong classification results with certain classes reaching perfect accuracy of 100%. To assess the model’s performance, evaluation metrics such as preci sion, recall, and mean Average Precision (mAP) were employed, demonstrating its practicality for real-world applications. Results indicate that YOLOv5’s architecture, with its efficient feature extraction and real-time processing, reliably handles the complex hand gesture variations in Arabic sign language. Its capability to distinguish subtle differences in hand positions makes it a valuable tool for educational applications, accessibility solutions for the deaf and hard-of-hearing, and future advancements in sign language translation systems. This study contributes a robust Arabic sign language recognition model, addressing an essential need for improved accessibility and communication for Arabic speaking users.

Ant Colony Optimization Algorithm Enhancement for Better Performance



×

Ant Colony Optimization Algorithm Enhancement for Better Performance



IEEE World AI IoT Congress 2023, virtual conference, 7-10 June, 2023


Proposed Dataset-Preprocessing and Implementation Framework

The research focuses on swarm intelligence, a scientific field inspired by natural swarm systems, with various algorithms addressing optimization problems. Notable algorithms include Firefly Algorithm, Ant System, Particle Swarm Optimization, Intelligent Water Drops, Ant Colony Optimization, and Artificial Bee Colony. The study introduces the ACOStar algorithm, aiming to enhance Ant Colony Optimization (ACO) by incorporating the evaluation function of the A* algorithm into ACO's transition-probability function. The proposed algorithm is successfully applied to the shortest path problem, demonstrating improved performance, success, and accuracy in various experiments.

×

Welcome to CAIR first workshop!

Workshop Topic: End-to-End Deep Learning based Automatic Speech Recognition Systems using NeMo

Instructor: Dr. Mohammed Mahdi Algabri
Location: KCST Campus
Day and Date: Wednesday - 27 July, 2022
Time: 1:00 PM – 4:00 PM
Prerequisite: Basic knowledge of the Python programming
P.S:Please don’t forget to:
  • Bring your laptops with you.
  • Create a google account for google colab.
Please note that whomever attends the workshop at the campus will receive a certificate!
The registration will be closed on 25th July, 2022
For any inquiries please contact cair@kcst.edu.kw

News

CAIR was honored by a visit of The IWG (International Women’s Group)



×



CAIR was honored by a visit of The IWG (International Women’s Group) consists of the VIP women in the society. International Women’s Group Kuwait, is an international association for women of all nationalities living in Kuwait, connecting through friendship and culture.

Announcement for membership!





×

Be a part of the future, be with CAIR to achieve your ambition.

Benefits of membership

  • Using the center's resources and equipment to carry out the member's research tasks.
  • Priority in participation for the center's scientific, educational activities, and competitions.
  • Support the registration fees for Scientific Conferences & Journals.
  • Receive the center's publications and studies in email.

To register please click the link below

https://docs.google.com/forms/d/1m2gKsCDjZmxsGec_ozKmX40bzo9HH3EOcgiqVY8o8n4/viewform?edit_requested=true

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



×


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

New publication in PLOS ONE Journal (IS Q1, 3.75 Impact Factor).




×

New publication in PLOS ONE Journal (IS Q1, 3.75 Impact Factor).

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

His Excellency Osama Shaltout, The Ambassador of the Arab Republic of Egypt to the State of Kuwait



×

His Excellency Osama Shaltout, The Ambassador of the Arab Republic of Egypt to the State of Kuwait



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.

New publication in the IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA 2022), Dalian, China




×



New paper for CAIR center has been presented in the IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA 2022), the new research is called an Automatic COVID-19 Diagnostic and Classification Intelligent System (ACDCIS) based on Machine Learning (ML) algorithms and techniques. The 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.

New publication in Sensor Journal (IS Q1, 3.57 Impact Factor). New paper for CAIR center 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 colobration 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).

New publication in the IEEE World AI IoT Congress 2022, Seattle, USA





×

New publication in the IEEE World AI IoT Congress 2022, Seattle, USA



New paper for CAIR center has been presented in the IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA 2022), the new research is called Machine Learning-based System for Monitoring Social Distancing and Mask Wearing algorithms and techniques. The developed system introduced a smart machine learning-based system for monitoring social distancing and mask wearing. The proposed system is used to monitor people and identify those who violate the rules of mask wearing or do not observe social distancing. It will help to control the epidemic, reduce the spread of COVID-19 and stress the importance of social distancing. The experimental results of the proposed system illustrate its robustness and accuracy.

New publication in Sensor Journal (Spatial Attention-Based 3D Graph Convolutional Neural Network for Sign Language Recognition)





×


New paper for CAIR center 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).

Workshop

Sheikha Fadia Al Saad Competition and Award Workshop, 04-Feb to present,2025



×

Sheikha Fadia Al Saad Competition and Award Workshop, 04-Feb to present,2025:



The Sheikha Fadia Al Saad Competition and Award workshop, starting on February 4, 2025, aims to equip students and teachers with essential skills for the competition. The workshop offers four specialized courses: Artificial Intelligence (AI), Robotics, Internet of Things (IoT), and Cybersecurity. Middle and secondary school students receive hands-on training to enhance their technical and problem-solving abilities, while teachers from primary, middle, and secondary schools are trained to support and guide their students effectively. This comprehensive program ensures all participants are well-prepared for the competition.

Building Skills in Digital Transformation and Artificial Intelligence, July 21 to August 1, 2024



×

Building Skills in Digital Transformation and Artificial Intelligence, July 21 to August 1, 2024



The "Building Skills in Digital Transformation and Artificial Intelligence" boot camp, held at KCST (Kuwait College of Science and Technology) from July 21 to August 1, 2024, was designed for students, professionals, and hobbyists. The event covered topics like machine learning, robotics, cybersecurity, and IoT development. The CAIR Center led the "Robotics and Human Interaction: Programming and Applications" workshop from July 28 to August 1, focusing on robotics fundamentals, programming, and human-robot interaction. The camp successfully fostered innovation and creative problem-solving among participants.

Ghabgathon Competition, held in April 2024





×

Ghabgathon Competition, held in April 2024



The Ghabgathon Competition, held in April 2024 at KCST, was an exciting cybersecurity challenge focused on Intrusion Detection System (IDS) design and programming. Participants engaged in hands-on problem-solving, testing their skills in network security, threat detection, and system protection. The competition provided a dynamic environment for students to enhance their cybersecurity expertise while fostering teamwork and innovation. Ghabgathon not only strengthened participants' technical abilities but also highlighted the importance of cybersecurity in today’s digital world.

Kuwaiti Sign Language for SmarTar a Smart Educational Avatar,2023-2024





×

Kuwaiti Sign Language for SmarTar a Smart Educational Avatar,2023-2024



On February 19, 2024, Mr. Hamad from the Kuwait National Guard, whom we had the pleasure of meeting at the AI gathering at Kuwait University, contributed his expertise to our groundbreaking project—SmarTar: A Smart Educational Avatar for Kuwaiti Sign Language. We believe that involving Mr. Hamad, given his specialization in Kuwaiti Sign Language, could significantly enhance the development and success of this initiative. Mr. Hamad's crucial expertise is essential for building our project, which was discussed during the one-day workshop held on February 19, 2024.

Al Mulla Exchange Hackathon , Feb 2024



×

Al Mulla Exchange Hackathon , Feb 2024



The Al Mulla Exchange Hackathon, held in February 2024 at KCST, brought together innovative minds to tackle real-world challenges in mobile app design. Participants engaged in an intensive competition, focusing on developing creative and practical solutions within a limited timeframe. The hackathon provided students with hands-on experience in coding, UI/UX design, and problem-solving, fostering collaboration and technical skill development. This event not only encouraged innovation but also showcased the potential of young developers in shaping the future of financial technology.

Assembling the TurtleBot, Fall (2023/2024)



×

Assembling the TurtleBot, Fall (2023/2024)



On November 14-15,2023, the students attended the workshop to learned about the TurtleBot Waffle Pi and got to put the robot together. It was like a fun puzzle that helped them understand how robots work. The workshop made learned about the ROS, software, and the hardware.

High school training workshop, (2023/2024)





×

High school training workshop, (2023/2024)



On 12-in until know, Decmber,2023/4. The center is actively helping high school students with their upcoming competition project. The students have chosen to use the Pepper robot for their geology project, and the center is guiding them through understanding both the hardware and software aspects of this technology. The students have learned what the Pepper robot can do, thanks to the center's support. This collaboration showcases the center's commitment to assisting and empowering the next generation of innovators, making the connection between what they learn and how they apply it in the real world.

Artificial Intelligence ABC, Fall (2022/2023)





×

Artificial Intelligence ABC, Fall (2022/2023)



In the fall of 2022/2023, participants were introduced to the realm of Artificial Intelligence (AI) during a visit to the Center of AI and Robotics (CAIR). This experience delved into the forefront of AI innovation, featuring a firsthand look at cutting-edge technologies, including the Pepper robot and various other robots and AI software crafted by CAIR. The tour provided valuable insights into the advancements achieved during that period, offering a glimpse into the transformative potential of AI. This visit to CAIR served as a snapshot of the dynamic and inspiring developments within the field of AI, leaving participants with a deeper appreciation for the ingenuity and progress made in the fall of 2022/2023.

Programming Humanoid Robots (Pepper Robot an example),2022-2023



×

Programming Humanoid Robots (Pepper Robot an example),2022-2023



The two-day workshop on "Programming Humanoid Robots (Pepper Robot)" was a condensed yet intensive immersion into the world of humanoid robotics. This workshop provided participants with a focused and hands-on experience in programming and interacting with the Pepper Robot.

AI and Transfer learning for Image Classification,2021-2022





×

AI and Transfer learning for Image Classification,2021-2022



The three-day workshop on Image Classification conducted over the course of 2021-2022 provided participants with an extensive and in-depth exploration of the techniques and methodologies involved in image classification. With a focus on imparting practical skills, the workshop allowed attendees to delve into various aspects of image classification, from understanding underlying algorithms to hands-on experience with state-of-the-art tools and frameworks.

Building and assembling the Tetrix robot,2021-2022



×

Building and assembling the Tetrix robot,2021-2022



The two-day workshop on Building and Assembling the Tetrix Robot, conducted over the course of two days, provided participants with hands-on experience in constructing and assembling the Tetrix robot. Designed to be an immersive and practical learning opportunity, the workshop focused on the intricate process of building a functional robot using the Tetrix system.

End-to-End Deep Learning based Automatic Speech Recognition Systems using NeMo,2021-2022



×

End-to-End Deep Learning based Automatic Speech Recognition Systems using NeMo,2021-2022



The one-day workshop on "End-to-End Deep Learning based Automatic Speech Recognition (ASR) Systems using NeMo" held over a concise three-hour session provided participants with a focused and intensive exploration of automatic speech recognition leveraging deep learning techniques with the NeMo framework. Throughout the workshop, attendees engaged in a streamlined curriculum, emphasizing the end-to-end process of developing ASR systems.

PROJECTS

The Fading Memory: Advancing Alzheimer’s Care in Kuwait



Speak with Your Eyes: Kuwait’s AI Gateway to Sign Language





Actives

In recent months, the CAIR (Center for Artificial Intelligence and Robotics) center actively participated in noteworthy events within our domain. We had the honor of representing the Kuwait College of Science and Technology at the AI gathering hosted by Kuwait University, where we shared insights and advancements in artificial intelligence. Additionally, we attended a beneficial VEX workshop organized by Kuwait University to prepare our students for the upcoming VEX competition. The insights gained during the workshop were invaluable, enhancing our readiness for the forthcoming competition. This demonstrates our commitment to fostering expertise in AI and robotics and staying well-prepared for competitive events in our field.

Next-Generation Healthcare: Integrating Imaging & Informatics for Collaborative Care 12-13/Feb/2025



×

Next-Generation Healthcare: Integrating Imaging & Informatics for Collaborative Care 12-13/Feb/2025



Eng.Hajar Alsulaili with guests

Peper robot with Dr. Elham Abbas Al Dosari and Dr. Mohammed

AI exhibition at the Kuwait university




×

AI exhibition at the Kuwait university:



Kuwait national robotics competition workshop



×

Kuwait national robotics competition workshop



In the VEX Competition workshop at Kuwait University on January 15-16, 2024, our student team engaged in a two-day learning experience. On the first day, they grasped the competition rules and hardware, laying a strong foundation. The following day focused on practical aspects, covering software skills. Notably, our students showcased a commendable spirit of collaboration by assisting other teams. This workshop not only enhanced their technical proficiency but also exemplified the values of teamwork and professionalism within the VEX community.