Open Access. Powered by Scholars. Published by Universities.®
- Keyword
-
- Deep learning (29)
- Computer Vision and Pattern Recognition (cs.CV) (27)
- Computer vision (25)
- Machine Learning (cs.LG) (21)
- Object detection (15)
-
- Computational linguistics (13)
- Machine learning (13)
- Semantics (13)
- Learning systems (12)
- Training (12)
- Image and Video Processing (eess.IV) (11)
- Performance (11)
- Artificial Intelligence (cs.AI) (10)
- Artificial intelligence (10)
- Computational modeling (10)
- Learn+ (10)
- Optimization (9)
- Benchmarking (8)
- COVID-19 (7)
- Convolutional neural networks (7)
- Image segmentation (7)
- Large dataset (7)
- Medical imaging (7)
- Reinforcement learning (7)
- Transformers (7)
- Classification (of information) (6)
- Deep neural networks (6)
- Digital twin (6)
- Stochastic systems (6)
- Surveys (6)
- Publication Year
Articles 1 - 30 of 299
Full-Text Articles in Entire DC Network
Decentralized Optimization Over Slowly Time-Varying Graphs: Algorithms And Lower Bounds, Dmitry Metelev, Aleksandr Beznosikov, Alexander Rogozin, Alexander Gasnikov, Anton Proskurnikov
Decentralized Optimization Over Slowly Time-Varying Graphs: Algorithms And Lower Bounds, Dmitry Metelev, Aleksandr Beznosikov, Alexander Rogozin, Alexander Gasnikov, Anton Proskurnikov
Machine Learning Faculty Publications
We consider a decentralized convex unconstrained optimization problem, where the cost function can be decomposed into a sum of strongly convex and smooth functions, associated with individual agents, interacting over a static or time-varying network. Our main concern is the convergence rate of first-order optimization algorithms as a function of the network’s graph, more specifically, of the condition numbers of gossip matrices. We are interested in the case when the network is time-varying but the rate of changes is restricted. We study two cases: randomly changing network satisfying Markov property and a network changing in a deterministic manner. For the …
Why Do We Not Stand Up To Misinformation? Factors Influencing The Likelihood Of Challenging Misinformation On Social Media And The Role Of Demographics, Selin Gurgun, Deniz Cemiloglu, Emily Arden Close, Keith Phalp, Preslav Nakov, Raian Ali
Why Do We Not Stand Up To Misinformation? Factors Influencing The Likelihood Of Challenging Misinformation On Social Media And The Role Of Demographics, Selin Gurgun, Deniz Cemiloglu, Emily Arden Close, Keith Phalp, Preslav Nakov, Raian Ali
Natural Language Processing Faculty Publications
This study investigates the barriers to challenging others who post misinformation on social media platforms. We conducted a survey amongst U.K. Facebook users (143 (57.2 %) women, 104 (41.6 %) men) to assess the extent to which the barriers to correcting others, as identified in literature across disciplines, apply to correcting misinformation on social media. We also group the barriers into factors and explore demographic differences amongst them. It has been suggested that users are generally hesitant to challenge misinformation. We found that most of our participants (58.8 %) were reluctant to challenge misinformation. We also identified moderating roles of …
A Social-Aware Gaussian Pre-Trained Model For Effective Cold-Start Recommendation, Siwei Liu, Xi Wang, Craig Macdonald, Iadh Ounis
A Social-Aware Gaussian Pre-Trained Model For Effective Cold-Start Recommendation, Siwei Liu, Xi Wang, Craig Macdonald, Iadh Ounis
Machine Learning Faculty Publications
The use of pre-training is an emerging technique to enhance a neural model's performance, which has been shown to be effective for many neural language models such as BERT. This technique has also been used to enhance the performance of recommender systems. In such recommender systems, pre-training models are used to learn a better initialisation for both users and items. However, recent existing pre-trained recommender systems tend to only incorporate the user interaction data at the pre-training stage, making it difficult to deliver good recommendations, especially when the interaction data is sparse. To alleviate this rcommon data sparsity issue, we …
Considering The Impact Framework To Understand The Ai-Well-Being-Complex From An Interdisciplinary Perspective, Christian Montag, Preslav Nakov, Raian Ali
Considering The Impact Framework To Understand The Ai-Well-Being-Complex From An Interdisciplinary Perspective, Christian Montag, Preslav Nakov, Raian Ali
Natural Language Processing Faculty Publications
Artificial intelligence (AI) is built into many products and has the potential to dramatically impact societies around the world. This short theoretical paper aims to provide a simple framework that might help us understand how the introduction and/or use of products with AI might influence the well-being of humans. It is proposed that considering the dynamic Interplay between variables stemming from Modality, Person, Area, Culture and Transparency categories will help to understand the influence of AI on well-being. The Modality category encompasses areas such as the degree of AI being interactive, informational versus actualizing, or autonomous. The Person variable contains …
Medical Image Super-Resolution For Smart Healthcare Applications: A Comprehensive Survey, Sabina Umirzakova, Shabir Ahmad, Latif U. Khan, Taegkeun Whangbo
Medical Image Super-Resolution For Smart Healthcare Applications: A Comprehensive Survey, Sabina Umirzakova, Shabir Ahmad, Latif U. Khan, Taegkeun Whangbo
Machine Learning Faculty Publications
The digital transformation in healthcare, propelled by the integration of deep learning models and the Internet of Things (IoT), is creating unprecedented opportunities for improving patient care. However, the utilization of low-resolution images, often generated by IoT devices, introduces biases in the deep learning models, thereby affecting the overall clinical decision-making process. While super-resolution techniques have been extensively employed to transform low-resolution images into high-resolution counterparts, the challenge of achieving highly accurate image restoration remains unresolved. This is especially critical in the medical imaging domain, where even minor inaccuracies can lead to significant biases in model training and, consequently, impact …
Using Natural Language Processing And Patient Journey Clustering For Temporal Phenotyping Of Antimicrobial Therapies For Cat Bite Abscesses, Brian Hur, Karin M. Verspoor, Timothy Baldwin, Laura Y. Hardefeldt, Caitlin Pfeiffer, Caroline Mansfield, Riati Scarborough, James R. Gilkerson
Using Natural Language Processing And Patient Journey Clustering For Temporal Phenotyping Of Antimicrobial Therapies For Cat Bite Abscesses, Brian Hur, Karin M. Verspoor, Timothy Baldwin, Laura Y. Hardefeldt, Caitlin Pfeiffer, Caroline Mansfield, Riati Scarborough, James R. Gilkerson
Natural Language Processing Faculty Publications
Background: Temporal phenotyping of patient journeys, which capture the common sequence patterns of interventions in the treatment of a specific condition, is useful to support understanding of antimicrobial usage in veterinary patients. Identifying and describing these phenotypes can inform antimicrobial stewardship programs designed to fight antimicrobial resistance, a major health crisis affecting both humans and animals, in which veterinarians have an important role to play. Objective: This research proposes a framework for extracting temporal phenotypes of patient journeys from clinical practice data through the application of natural language processing (NLP) and unsupervised machine learning (ML) techniques, using cat bite abscesses …
Conic Challenge: Pushing The Frontiers Of Nuclear Detection, Segmentation, Classification And Counting, Simon Graham, Quoc Dang Vu, Mostafa Jahanifar, Martin Weigert, Uwe Schmidt, Wenhua Zhang, Jun Zhang, Sen Yang, Jinxi Xiang, Xiyue Wang, Josef Lorenz Rumberger, Elias Baumann, Peter Hirsch, Lihao Liu, Chenyang Hong, Angelica I. Aviles-Rivero, Ayushi Jain, Heeyoung Ahn, Yiyu Hong, Hussam Azzuni, Min Xu
Conic Challenge: Pushing The Frontiers Of Nuclear Detection, Segmentation, Classification And Counting, Simon Graham, Quoc Dang Vu, Mostafa Jahanifar, Martin Weigert, Uwe Schmidt, Wenhua Zhang, Jun Zhang, Sen Yang, Jinxi Xiang, Xiyue Wang, Josef Lorenz Rumberger, Elias Baumann, Peter Hirsch, Lihao Liu, Chenyang Hong, Angelica I. Aviles-Rivero, Ayushi Jain, Heeyoung Ahn, Yiyu Hong, Hussam Azzuni, Min Xu
Computer Vision Faculty Publications
Nuclear detection, segmentation and morphometric profiling are essential in helping us further understand the relationship between histology and patient outcome. To drive innovation in this area, we setup a community-wide challenge using the largest available dataset of its kind to assess nuclear segmentation and cellular composition. Our challenge, named CoNIC, stimulated the development of reproducible algorithms for cellular recognition with real-time result inspection on public leaderboards. We conducted an extensive post-challenge analysis based on the top-performing models using 1,658 whole-slide images of colon tissue. With around 700 million detected nuclei per model, associated features were used for dysplasia grading and …
Semi-Decentralized Inference In Heterogeneous Graph Neural Networks For Traffic Demand Forecasting: An Edge-Computing Approach, Mahmoud Nazzal, Abdallah Khreishah, Joyoung Lee, Shaahin Angizi, Ala Al-Fuqaha, Mohsen Guizani
Semi-Decentralized Inference In Heterogeneous Graph Neural Networks For Traffic Demand Forecasting: An Edge-Computing Approach, Mahmoud Nazzal, Abdallah Khreishah, Joyoung Lee, Shaahin Angizi, Ala Al-Fuqaha, Mohsen Guizani
Machine Learning Faculty Publications
Prediction of taxi service demand and supply is essential for improving customer experience and provider's profit. Recently, graph neural networks (GNNs), modeling city areas as nodes in a transportation graph, have been shown efficient for this application as they utilize both local node features and the graph structure in the prediction. Still, further improvement can be achieved by either simultaneously exploiting different types of nodes/edges in the graphs or enlarging the scale of the transportation graph. However, both alternatives are challenged by the scalability of GNNs. An immediate remedy to the scalability challenge is to decentralize the GNN operation. In …
Challenging Others When Posting Misinformation: A Uk Vs. Arab Cross-Cultural Comparison On The Perception Of Negative Consequences And Injunctive Norms, Muaadh Noman, Selin Gurgun, Keith Phalp, Preslav Nakov, Raian Ali
Challenging Others When Posting Misinformation: A Uk Vs. Arab Cross-Cultural Comparison On The Perception Of Negative Consequences And Injunctive Norms, Muaadh Noman, Selin Gurgun, Keith Phalp, Preslav Nakov, Raian Ali
Natural Language Processing Faculty Publications
This study investigates the factors influencing the willingness to challenge misinformation on social media across two cultural contexts, the United Kingdom (UK) and Arab countries. A total of 462 participants completed an online survey (250 UK, 212 Arabs). The analysis revealed that three types of negative consequences (relationship cost, negative impact on the person being challenged, futility) and also injunctive norms influence the willingness to challenge misinformation. Cross-cultural comparisons using t-tests showed significant differences between the UK and the Arab countries in all factors except the injunctive norms. Multiple regression analyses identified differences between the UK and Arab participants concerning …
Improved Binary Differential Evolution With Dimensionality Reduction Mechanism And Binary Stochastic Search For Feature Selection, Behrouz Ahadzadeh, Moloud Abdar, Fatemeh Safara, Leyla Aghaei, Seyedali Mirjalili, Abbas Khosravi, Salvador García, Fakhri Karray, U. Rajendra Acharya
Improved Binary Differential Evolution With Dimensionality Reduction Mechanism And Binary Stochastic Search For Feature Selection, Behrouz Ahadzadeh, Moloud Abdar, Fatemeh Safara, Leyla Aghaei, Seyedali Mirjalili, Abbas Khosravi, Salvador García, Fakhri Karray, U. Rajendra Acharya
Machine Learning Faculty Publications
Computer systems store massive amounts of data with numerous features, leading to the need to extract the most important features for better classification in a wide variety of applications. Poor performance of various machine learning algorithms may be caused by unimportant features that increase the time and memory required to build a classifier. Feature selection (FS) is one of the efficient approaches to reducing the unimportant features. This paper, therefore, presents a new FS, named BDE-BSS-DR, that utilizes Binary Differential Evolution (BDE), Binary Stochastic Search (BSS) algorithm, and Dimensionality Reduction (DR) mechanism. The BSS algorithm increases the search capability of …
Outdoor Position Recovery From Heterogeneous Telco Cellular Data, Yige Zhang, Weixiong Rao, Kun Zhang, Lei Chen
Outdoor Position Recovery From Heterogeneous Telco Cellular Data, Yige Zhang, Weixiong Rao, Kun Zhang, Lei Chen
Machine Learning Faculty Publications
Recent years have witnessed unprecedented amounts of data generated by telecommunication (Telco) cellular networks. For example, measurement records (MRs) are generated to report the connection states between mobile devices and Telco networks, e.g., received signal strength. MR data have been widely used to localize outdoor mobile devices for human mobility analysis, urban planning, and traffic forecasting. Existing works using first-order sequence models such as the Hidden Markov Model (HMM) attempt to capture spatio-temporal locality in underlying mobility patterns for lower localization errors. The HMM approaches typically assume stable mobility patterns of the underlying mobile devices. Yet real MR datasets exhibit …
Non-Fungible Tokens (Nfts) - Survey Of Current Applications, Evolution And Future Directions, Qaiser Razi, Aryan Devrani, Harshal Abhyankar, Gss Chalapathi, Vikas Hassija, Mohsen Guizani
Non-Fungible Tokens (Nfts) - Survey Of Current Applications, Evolution And Future Directions, Qaiser Razi, Aryan Devrani, Harshal Abhyankar, Gss Chalapathi, Vikas Hassija, Mohsen Guizani
Machine Learning Faculty Publications
Non-fungible tokens (NFTs) have become an exciting technology that provides a fresh perspective on asset ownership, provenance, and value exchange. NFTs, a blockchain-based technology, are distinct and indivisible cryptographic tokens used to confirm and record the ownership of digital and physical assets in an immutable and transparent way. The fundamental block of NFT is a smart contract built on a blockchain network. This contract contains specific information about the asset it represents, such as its unique identifier, metadata, and ownership details. The information is kept private and tamper-proof due to the decentralized and distributed structure of the blockchain, boosting faith …
A Randomised Non-Descent Method For Global Optimisation, Dmitry A. Pasechnyuk, Alexander Gornov
A Randomised Non-Descent Method For Global Optimisation, Dmitry A. Pasechnyuk, Alexander Gornov
Machine Learning Faculty Publications
This paper proposes novel algorithm for non-convex multimodal constrained optimisation problems. It is based on sequential solving restrictions of problem to sections of feasible set by random subspaces (in general, manifolds) of low dimensionality. This approach varies in a way to draw subspaces, dimensionality of subspaces, and method to solve restricted problems. We provide empirical study of algorithm on convex, unimodal and multimodal optimisation problems and compare it with efficient algorithms intended for each class of problems.
Mgmt Promoter Methylation Status Prediction Using Mri Scans? An Extensive Experimental Evaluation Of Deep Learning Models, Numan Saeed, Muhammad Ridzuan, Hussain Alasmawi, Ikboljon Sobirov, Mohammad Yaqub
Mgmt Promoter Methylation Status Prediction Using Mri Scans? An Extensive Experimental Evaluation Of Deep Learning Models, Numan Saeed, Muhammad Ridzuan, Hussain Alasmawi, Ikboljon Sobirov, Mohammad Yaqub
Computer Vision Faculty Publications
The number of studies on deep learning for medical diagnosis is expanding, and these systems are often claimed to outperform clinicians. However, only a few systems have shown medical efficacy. From this perspective, we examine a wide range of deep learning algorithms for the assessment of glioblastoma - a common brain tumor in older adults that is lethal. Surgery, chemotherapy, and radiation are the standard treatments for glioblastoma patients. The methylation status of the MGMT promoter, a specific genetic sequence found in the tumor, affects chemotherapy's effectiveness. MGMT promoter methylation improves chemotherapy response and survival in several cancers. MGMT promoter …
Multimodal Image Synthesis And Editing: The Generative Ai Era, Fangneng Zhan, Yingchen Yu, Rongliang Wu, Jiahui Zhang, Shijian Lu, Lingjie Liu, Adam Kortylewski, Christian Theobalt, Eric Xing
Multimodal Image Synthesis And Editing: The Generative Ai Era, Fangneng Zhan, Yingchen Yu, Rongliang Wu, Jiahui Zhang, Shijian Lu, Lingjie Liu, Adam Kortylewski, Christian Theobalt, Eric Xing
Machine Learning Faculty Publications
As information exists in various modalities in real world, effective interaction and fusion among multimodal information plays a key role for the creation and perception of multimodal data in computer vision and deep learning research. With superb power in modeling the interaction among multimodal information, multimodal image synthesis and editing has become a hot research topic in recent years. Instead of providing explicit guidance for network training, multimodal guidance offers intuitive and flexible means for image synthesis and editing. On the other hand, this field is also facing several challenges in alignment of multimodal features, synthesis of high-resolution images, faithful …
Offenseval 2023: Offensive Language Identification In The Age Of Large Language Models, Marcos Zampieri, Sara Rosenthal, Preslav Nakov, Alphaeus Dmonte, Tharindu Ranasinghe
Offenseval 2023: Offensive Language Identification In The Age Of Large Language Models, Marcos Zampieri, Sara Rosenthal, Preslav Nakov, Alphaeus Dmonte, Tharindu Ranasinghe
Natural Language Processing Faculty Publications
The OffensEval shared tasks organized as part of SemEval-2019-2020 were very popular, attracting over 1300 participating teams. The two editions of the shared task helped advance the state of the art in offensive language identification by providing the community with benchmark datasets in Arabic, Danish, English, Greek, and Turkish. The datasets were annotated using the OLID hierarchical taxonomy, which since then has become the de facto standard in general offensive language identification research and was widely used beyond OffensEval. We present a survey of OffensEval and related competitions, and we discuss the main lessons learned. We further evaluate the performance …
Hybrid Flexible (Hyflex) Learning Space Design And Implementation At Graduate Level: An Iterative Process, David Santandreu Calonge, Mark Thompson, Leisa Hassock, Mohammad Yaqub
Hybrid Flexible (Hyflex) Learning Space Design And Implementation At Graduate Level: An Iterative Process, David Santandreu Calonge, Mark Thompson, Leisa Hassock, Mohammad Yaqub
Computer Vision Faculty Publications
This paper investigates the process of designing HyFlex classrooms at Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI), a graduate-level research university located in Abu Dhabi, United Arab Emirates, underpinned by the application of the EDUCAUSE Learning Space Rating System (LSRS). This investigation takes the form of a case-study and specifically focuses on the rationale, planning, design, and technology behind the implementation of the flexible HyFlex spaces as deployed in several classroom environments at MBZUAI. Iterations’ performance was assessed with the LSRS—V3. The findings should make an important contribution to the field of HyFlex learning spaces and technology-enhanced classroom design …
Clustering-Nn Based Cfo Estimation Using Random Access Preambles For 5g Non-Terrestrial Networks, Li Zhen, Luyao Cheng, Zheng Chu, Keping Yu, Pei Xiao, Mohsen Guizani
Clustering-Nn Based Cfo Estimation Using Random Access Preambles For 5g Non-Terrestrial Networks, Li Zhen, Luyao Cheng, Zheng Chu, Keping Yu, Pei Xiao, Mohsen Guizani
Machine Learning Faculty Publications
Non-terrestrial networks (NTNs) are expected to play a pivotal role in the future wireless ecosystem. Due to its high-dynamic characteristics, the accurate estimation and compensation of carrier frequency offset (CFO) are crucial for supporting 5G new radio (NR) enabled satellite direct access. With emphasis on ensuring reliable uplink synchronization, we propose a clustering-neural network based CFO estimation scheme by virtue of NR random access preambles. By leveraging the sparsity and regularity of input samples, the proposed scheme can achieve fast and precise prediction of CFOs, while establishing robustness against time uncertainty and channel variation within a satellite beam. Simulation results …
Preface: Special Issue On Nlp Approaches To Offensive Content Online, Marcos Zampieri, Isabelle Augenstein, Siddharth Krishnan, Joshua Melton, Preslav Nakov
Preface: Special Issue On Nlp Approaches To Offensive Content Online, Marcos Zampieri, Isabelle Augenstein, Siddharth Krishnan, Joshua Melton, Preslav Nakov
Natural Language Processing Faculty Publications
No abstract provided.
Smart Street Light Control: A Review On Methods, Innovations, And Extended Applications, Fouad Agramelal, Mohamed Sadik, Youssef Moubarak, Saad Abouzahir
Smart Street Light Control: A Review On Methods, Innovations, And Extended Applications, Fouad Agramelal, Mohamed Sadik, Youssef Moubarak, Saad Abouzahir
Computer Vision Faculty Publications
As urbanization increases, streetlights have become significant consumers of electrical power, making it imperative to develop effective control methods for sustainability. This paper offers a comprehensive review on control methods of smart streetlight systems, setting itself apart by introducing a novel light scheme framework that provides a structured classification of various light control patterns, thus filling an existing gap in the literature. Unlike previous studies, this work dives into the technical specifics of individual research papers and methodologies, ranging from basic to advanced control methods like computer vision and deep learning, while also assessing the energy consumption associated with each …
Lightweight Multi-Class Support Vector Machine-Based Medical Diagnosis System With Privacy Preservation, Sherif Abdelfattah, Mohamed Baza, Mohamed Mahmoud, Mostafa M. Fouda, Khalid Abualsaud, Elias Yaacoub, Maazen Alsabaan, Mohsen Guizani
Lightweight Multi-Class Support Vector Machine-Based Medical Diagnosis System With Privacy Preservation, Sherif Abdelfattah, Mohamed Baza, Mohamed Mahmoud, Mostafa M. Fouda, Khalid Abualsaud, Elias Yaacoub, Maazen Alsabaan, Mohsen Guizani
Machine Learning Faculty Publications
Machine learning, powered by cloud servers, has found application in medical diagnosis, enhancing the capabilities of smart healthcare services. Research literature demonstrates that the support vector machine (SVM) consistently demonstrates remarkable accuracy in medical diagnosis. Nonetheless, safeguarding patients’ health data privacy and preserving the intellectual property of diagnosis models is of paramount importance. This concern arises from the common practice of outsourcing these models to third-party cloud servers that may not be entirely trustworthy. Few studies in the literature have delved into addressing these issues within SVM-based diagnosis systems. These studies, however, typically demand substantial communication and computational resources and …
A Unified Query-Based Paradigm For Camouflaged Instance Segmentation, Bo Dong, Jialun Pei, Rongrong Gao, Tian Zhu Xiang, Shuo Wang, Huan Xiong
A Unified Query-Based Paradigm For Camouflaged Instance Segmentation, Bo Dong, Jialun Pei, Rongrong Gao, Tian Zhu Xiang, Shuo Wang, Huan Xiong
Machine Learning Faculty Publications
Due to the high similarity between camouflaged instances and the background, the recently proposed camouflaged instance segmentation (CIS) faces challenges in accurate localization and instance segmentation. To this end, inspired by query-based transformers, we propose a unified query-based multi-task learning framework for camouflaged instance segmentation, termed UQFormer, which builds a set of mask queries and a set of boundary queries to learn a shared composed query representation and efficiently integrates global camouflaged object region and boundary cues, for simultaneous instance segmentation and instance boundary detection in camouflaged scenarios. Specifically, we design a composed query learning paradigm that learns a shared …
Pnt-Edge: Towards Robust Edge Detection With Noisy Labels By Learning Pixel-Level Noise Transitions, Wenjie Xuan, Shanshan Zhao, Yu Yao, Juhua Liu, Tongliang Liu, Yixin Chen, Bo Du, Dacheng Tao
Pnt-Edge: Towards Robust Edge Detection With Noisy Labels By Learning Pixel-Level Noise Transitions, Wenjie Xuan, Shanshan Zhao, Yu Yao, Juhua Liu, Tongliang Liu, Yixin Chen, Bo Du, Dacheng Tao
Machine Learning Faculty Publications
Relying on large-scale training data with pixel-level labels, previous edge detection methods have achieved high performance. However, it is hard to manually label edges accurately, especially for large datasets, and thus the datasets inevitably contain noisy labels. This label-noise issue has been studied extensively for classification, while still remaining under-explored for edge detection. To address the label-noise issue for edge detection, this paper proposes to learn Pixel-level Noise Transitions to model the label-corruption process. To achieve it, we develop a novel Pixel-wise Shift Learning (PSL) module to estimate the transition from clean to noisy labels as a displacement field. Exploiting …
Artst: Arabic Text And Speech Transformer, Hawau Olamide Toyin, Amirbek Djanibekov, Ajinkya Kulkarni, Hanan Al Darmaki
Artst: Arabic Text And Speech Transformer, Hawau Olamide Toyin, Amirbek Djanibekov, Ajinkya Kulkarni, Hanan Al Darmaki
Natural Language Processing Faculty Publications
We present ArTST, a pre-trained Arabic text and speech transformer for supporting open-source speech technologies for the Arabic language. The model architecture follows the unified-modal framework, SpeechT5, that was recently released for English, and is focused on Modern Standard Arabic (MSA), with plans to extend the model for dialectal and code-switched Arabic in future editions. We pre-trained the model from scratch on MSA speech and text data, and fine-tuned it for the following tasks: Automatic Speech Recognition (ASR), Text-To-Speech synthesis (TTS), and spoken dialect identification. In our experiments comparing ArTST with SpeechT5, as well as with previously reported results in …
An Incremental Gray-Box Physical Adversarial Attack On Neural Network Training, Rabiah Al-Qudah, Moayad Aloqaily, Bassem Ouni, Mohsen Guizani, Thierry Lestable
An Incremental Gray-Box Physical Adversarial Attack On Neural Network Training, Rabiah Al-Qudah, Moayad Aloqaily, Bassem Ouni, Mohsen Guizani, Thierry Lestable
Machine Learning Faculty Publications
Neural networks have demonstrated remarkable success in learning and solving complex tasks in a variety of fields including cognitive cities. Nevertheless, the rise of those networks in modern computing has been accompanied by concerns regarding their vulnerability to adversarial attacks. In this work, we propose a novel gradient-free, gray box, incremental attack that targets the training process of neural networks. The proposed attack, which implicitly poisons the intermediate data structures that retain the training instances between training epochs acquires its high-risk property from attacking data structures that are typically unobserved by professionals. Hence, the attack goes unnoticed despite the damage …
Harris Hawks Feature Selection In Distributed Machine Learning For Secure Iot Environments, Neveen Hijazi, Moayad Aloqaily, Bassem Ouni, Fakhri Karray, Merouane Debbah
Harris Hawks Feature Selection In Distributed Machine Learning For Secure Iot Environments, Neveen Hijazi, Moayad Aloqaily, Bassem Ouni, Fakhri Karray, Merouane Debbah
Machine Learning Faculty Publications
The development of the Internet of Things (IoT) has dramatically expanded our daily lives, playing a pivotal role in the enablement of smart cities, healthcare, and buildings. Emerging technologies, such as IoT, seek to improve the quality of service in cognitive cities. Although IoT applications are helpful in smart building applications, they present a real risk as the large number of interconnected devices in those buildings, using heterogeneous networks, increases the number of potential IoT attacks. IoT applications can collect and transfer sensitive data. Therefore, it is necessary to develop new methods to detect hacked IoT devices. This paper proposes …
Text Augmentation For Semantic Frame Induction And Parsing, Saba Anwar, Artem Shelmanov, Nikolay Arefyev, Alexander Panchenko, Chris Biemann
Text Augmentation For Semantic Frame Induction And Parsing, Saba Anwar, Artem Shelmanov, Nikolay Arefyev, Alexander Panchenko, Chris Biemann
Natural Language Processing Faculty Publications
Semantic frames are formal structures describing situations, actions or events, e.g., Commerce buy, Kidnapping, or Exchange. Each frame provides a set of frame elements or semantic roles corresponding to participants of the situation and lexical units (LUs)—words and phrases that can evoke this particular frame in texts. For example, for the frame Kidnapping, two key roles are Perpetrator and the Victim, and this frame can be evoked with lexical units abduct, kidnap, or snatcher. While formally sound, the scarce availability of semantic frame resources and their limited lexical coverage hinders the wider adoption of frame semantics across languages and domains. …
Yet Another Model For Arabic Dialect Identification, Ajinkya Kulkarni, Hanan Al Darmaki
Yet Another Model For Arabic Dialect Identification, Ajinkya Kulkarni, Hanan Al Darmaki
Natural Language Processing Faculty Publications
In this paper, we describe a spoken Arabic dialect identification (ADI) model for Arabic that consistently outperforms previously published results on two benchmark datasets: ADI-5 and ADI-17. We explore two architectural variations: ResNet and ECAPA-TDNN, coupled with two types of acoustic features: MFCCs and features exratected from the pre-trained self-supervised model UniSpeech-SAT Large, as well as a fusion of all four variants. We find that individually, ECAPA-TDNN network outperforms ResNet, and models with UniSpeech-SAT features outperform models with MFCCs by a large margin. Furthermore, a fusion of all four variants consistently outperforms individual models. Our best models outperform previously reported …
Metaverse Key Requirements And Platforms Survey, Akbobek Abilkaiyrkyzy, Ahmed Elhagry, Fedwa Laamarti, Abdulmotaleb El Saddik
Metaverse Key Requirements And Platforms Survey, Akbobek Abilkaiyrkyzy, Ahmed Elhagry, Fedwa Laamarti, Abdulmotaleb El Saddik
Computer Vision Faculty Publications
The growing interest in the metaverse has led to an abundance of platforms, each with its own unique features and limitations. This paper's objective is two-fold. First, we aim at providing an objective analysis of requirements that need to be fulfilled by metaverse platforms. We survey a broad set of criteria including interoperability, immersiveness, persistence, multimodal and social interaction, scalability, level of openness, configurability, market access, security, and blockchain integration, among others. Second, we review a wide range of existing metaverse platforms, and we critically evaluate their ability to meet the requirements listed. We identify their limitations, which must be …
Dtitd: An Intelligent Insider Threat Detection Framework Based On Digital Twin And Self-Attention Based Deep Learning Models, Zhi Qiang Wang, Abdulmotaleb El Saddik
Dtitd: An Intelligent Insider Threat Detection Framework Based On Digital Twin And Self-Attention Based Deep Learning Models, Zhi Qiang Wang, Abdulmotaleb El Saddik
Computer Vision Faculty Publications
Recent statistics and studies show that the loss generated by insider threats is much higher than that generated by external attacks. More and more organizations are investing in or purchasing insider threat detection systems to prevent insider risks. However, the accurate and timely detection of insider threats faces significant challenges. In this study, we proposed an intelligent insider threat detection framework based on Digital Twins and self-attentions based deep learning models. First, this paper introduces insider threats and the challenges in detecting them. Then this paper presents recent related works on solving insider threat detection problems and their limitations. Next, …