Nurtech Simple Cloud Services
Moe Abdul
Mohammed Abduljabbar received the B.S. degree in Computer Information Systems from Kansas State University, USA, in 2011, and the M.S. degree in Software Engineering from United Arab Emirates University, UAE, in 2020. He is currently a Ph.D. candidate at United Arab Emirates University, specializing in cloud computing, artificial intelligence, robotics, and computer vision.
Fisheye8k: A benchmark and dataset for fisheye camera object detection
With the advance of AI, road object detection has been a prominent topic in computer vision, mostly using perspective cameras. Fisheye lens provides omnidirectional wide coverage for using fewer cameras to monitor road intersections, however with view distortions. To our knowledge, there is no existing open dataset prepared for traffic surveillance on fisheye cameras. This paper introduces an open FishEye8K benchmark dataset for road object detection tasks, which comprises 157K bounding boxes across five classes (Pedestrian, Bike, Car, Bus, and Truck). In addition, we present benchmark results of State-of-The-Art (SoTA) models, including variations of YOLOv5, YOLOR, YOLO7, and YOLOv8. The dataset comprises 8,000 images recorded in 22 videos using 18 fisheye cameras for traffic monitoring in Hsinchu, Taiwan, at resolutions of 1080x1080 and 1280x1280. The data annotation and validation process were arduous and time-consuming, due to the ultra-wide panoramic and hemispherical fisheye camera images with large distortion and numerous road participants, particularly people riding scooters. To avoid bias, frames from a particular camera were assigned to either the training or test sets, maintaining a ratio of about 70: 30 for both the number of images and bounding boxes in each class. Experimental results show that YOLOv8 and YOLOR outperform on input sizes 640x640 and 1280x1280, respectively. The dataset will be available on the GitHub link with PASCAL VOC, MS COCO, and YOLO annotation formats. The FishEye8K benchmark will provide significant contributions to the fisheye video analytics and smart city …
Revolutionizing social robotics: a cloud-based framework for enhancing the intelligence and autonomy of social robots
Social robots have the potential to revolutionize the way we interact with technology, providing a wide range of services and applications in various domains, such as healthcare, education, and entertainment. However, most existing social robotics platforms are operated based on embedded computers, which limits the robot’s capabilities to access advanced AI-based platforms available online and which are required for sophisticated physical human–robot interactions (such as Google Cloud AI, Microsoft Azure Machine Learning, IBM Watson, ChatGPT, etc.). In this research project, we introduce a cloud-based framework that utilizes the benefits of cloud computing and clustering to enhance the capabilities of social robots and overcome the limitations of current embedded platforms. The proposed framework was tested in different robots to assess the general feasibility of the solution, including a customized robot, “BuSaif”, and commercialized robots, “Husky”, “NAO”, and “Pepper”. Our findings suggest that the implementation of the proposed platform will result in more intelligent and autonomous social robots that can be utilized by a broader range of users, including those with less expertise. The present study introduces a novel methodology for augmenting the functionality of social robots, concurrently simplifying their utilization for non-experts. This approach has the potential to open up novel possibilities within the domain of social robotics.
A Deep Learning Model for MOOC Dropout Prediction Using Learner's Course-relevant Activities
Today, Open Massive Online Courses (MOOCs) have become very popular learning platforms with millions of participants. MOOCs provide a flexible distance-learning style courses usually delivered by top international universities. However, despite all benefits and features of MOOCs, these platforms have been heavily criticized due to students' high dropout rate. This have become a phenomenon on MOOCs, where users may enroll in a course but most of these users will dropout the course somewhere before the end. This has triggered the need for a development of a reliable and efficient dropout prediction model that can address this problem and maintain an encouraging learning activity. In this research, we present a deep leaning dropout predictor model to address this classification problem. By observing learner's early course activities and extensive feature engineering, we tried to predict the likelihood of …
Adding Sound Transparency to a Spacesuit: Effect on Cognitive Performance in Females
Spacesuits may block external sound. This induces sensory deprivation; a side effect is lower cognitive performance. This can increase the risk of an accident. This undesirable effect can be mitigated by designing suits with sound transparency. If the atmosphere is available, as on Mars, sound transparency can be realized by augmenting and processing external sounds. If no atmosphere is available, such as on the Moon, then an Earth-like sound can be re-created via generative AR techniques. We measure the effect of adding sound transparency in an Intra-Vehicular Activity suit by means of the Koh Block test. The results indicate that participants complete the test more quickly when wearing a suit with sound transparency.
A comparative study of transformer based pretrained AI models for content summarization
In this study, we examine different transformer based pretrained Artificial Intelligence (AI) models on their ability to summarize text content from different sources. AI has emerged as a powerful tool in this context, offering the potential to automate and improve the process of content summarization. We mainly focus on the pretrained transformer models, such as Pegasus, T5, Bart, and ProphetNet for key point summarization from textual contents. We aim to assess the effectiveness of these models in summarizing different contents like articles, instructions, conversational dialogues, and compare and analyze their performance across different datasets. We use ROUGE metric to evaluate the quality of the generated summaries. The Facebook’s BART model had better performance across different textual datasets. We believe that our findings will offer valuable insights into the capabilities and limitations of Transformer …
A Cloud-Based 3D Digital Twin for Arabic Sign Language Alphabet Using Machine Learning Object Detection Model
People with hearing loss or hard hearing struggle with daily life activities as sign language is not widely known by the public. There are many attempts to use technology to help assist hearing loss individuals. However, most proposed solutions are standalone applications or require special hardware like a wearable glove. Our goal is to leverage cloud computing and artificial intelligence (AI) to provide a solution that is portable and does not require any special hardware. We created a lightweight 3D model and rendered it on the browser along with another lightweight object detection model for Arabic Sign Language (ArSL) for real-time detection. Our contribution is primarily based on integrating our novel functional lightweight 3D avatar model and a lightweight ArSL alphabet detection model, which is trained on public ArSL21L dataset, that are suitable to be given as a cloud service. Prototypes of the 3D digital twin …
Visualization of clandestine labs from seizure reports: Thematic mapping and data mining research directions
The problem of spatiotemporal event visualization based on reports entails subtasks ranging from named entity recognition to relationship extraction and mapping of events. We present an approach to event extraction that is driven by data mining and visualization goals, particularly thematic mapping and trend analysis. This paper focuses on bridging the information extraction and visualization tasks and investigates topic modeling approaches. We develop a static, finite topic model and examine the potential benefits and feasibility of extending this to dynamic topic modeling with a large number of topics and continuous time. We describe an experimental test bed for event mapping that uses this end-to-end information retrieval system, and report preliminary results on a geoinformatics problem: tracking of methamphetamine lab seizure events across time and space.
Web Platform for General Robot Controlling System
AbuSaif is a human-like social robot designed and built at the UAE University's Artificial Intelligence and Robotics Lab. AbuSaif was initially operated by a classical personal computer (PC), like most of the existing social robots. Thus, most of the robot's functionalities are limited to the capacity of that mounted PC. To overcome this, in this study, we propose a web-based platform that shall take the benefits of clustering in cloud computing. Our proposed platform will increase the operational capability and functionality of AbuSaif, especially those needed to operate artificial intelligence algorithms. We believe that the robot will become more intelligent and autonomous using our proposed web platform.
A Deep Learning-Based Neural Network Model for Autism Spectrum Disorder Prediction
The autism spectrum disorder (ASD) is a neuro-disorder that tremendously impacts people’s lives and today ASD is gaining its prevalence globally faster than ever. ASD affects the mental, social, and physical state of a person due to its unknown etiology, and medical professionals believe that identifying autistic traits and providing accurate analysis and early ASD detection is a relatively challenging and time-consuming task. However, diagnostic predictions for autism features could be improved using multiple methods owing to the rise and development of artificial intelligence (AI) and machine learning (ML) techniques. Therefore, this research attempts to explore the possibility of using AI deep learning techniques to assist in ASD diagnosis and prediction by proposing an effective prediction models based on deep learning Artificial Neural Networks (ANNs) and Convolutional Neural Network (CNNs). This will aid …