Digital Commons Network^™

[Shary] Photograph Of Cabbage Field

Miscellaneous photograph collection - UTRGV Library Edinburg

Copy negative of an unidentified man standing in a row of cabbage, in a large field of plants. The man is wearing a light-colored shirt with a tie, dark-colored pants, and a hat, and he is looking at a head of cabbage that he is holding. Several buildings are visible in the background on the left side of the image. The original print is pinned to a background with push-pins.

Part of Shary Collection.

[Shary] Photograph Of Broom Corn Crop, Shary

Miscellaneous photograph collection - UTRGV Library Edinburg

Copy negative of a field full of growing broom corn. The original print is pinned to a background with push-pins.

Part of Shary Collection.

[Rio Grande] Photograph Of Boat On The Rio Grande

Miscellaneous photograph collection - UTRGV Library Edinburg

Boat with three people floating on the Rio Grande.

[Shary] Photograph Of Bench And Trees

Miscellaneous photograph collection - UTRGV Library Edinburg

Photograph of a yard or park including a bench under a tree in the foreground, a number of trees, and an unidentified building that is partially visible in the background on the right side of the image. A person is standing near the building in the center of the image.

Part of Shary Collection.

Biomass Distribution Of Benthosema Glaciale And Maurolicus Muelleri In The North Atlantic, Fabio Berzaghi, Laurene Merillet, Anna Conchon, Morten Skogen, Emma Dolmaire, Espen Strand, Douglas Speirs, Webjørn Melle, Mary S. Wisz

Datasets

This dataset contains maps of biomass estimates of Maurolicus muelleri and Benthosema glaciale created using the output of three models from the MEESO project. Maps represent an average biomass distribution and not any specific year, please note the distribution of biomass varies in time. For more details please consult the metadata on the ICES website.

Dynamic-Superb: Towards A Dynamic, Collaborative, And Comprehensive Instruction-Tuning Benchmark For Speech, Chien Yu Huang, Ke Han Lu, Shih Heng Wang, Chi Yuan Hsiao, Chun Yi Kuan, Haibin Wu, Siddhant Arora, Kai Wei Chang

Natural Language Processing Faculty Publications

Text language models have shown remarkable zero-shot capability in generalizing to unseen tasks when provided with well-formulated instructions. However, existing studies in speech processing primarily focus on limited or specific tasks. Moreover, the lack of standardized benchmarks hinders a fair comparison across different approaches. Thus, we present Dynamic-SUPERB, a benchmark designed for building universal speech models capable of leveraging instruction tuning to perform multiple tasks in a zero-shot fashion. To achieve comprehensive coverage of diverse speech tasks and harness instruction tuning, we invite the community to collaborate and contribute, facilitating the dynamic growth of the benchmark. To initiate, Dynamic-SUPERB features …

The Clef-2024 Checkthat! Lab: Check-Worthiness, Subjectivity, Persuasion, Roles, Authorities, And Adversarial Robustness, Alberto Barrón-Cedeño, Firoj Alam, Tanmoy Chakraborty, Tamer Elsayed, Preslav Nakov, Piotr Przybyła, Julia Maria Struß, Fatima Haouari

Natural Language Processing Faculty Publications

The first five editions of the CheckThat! lab focused on the main tasks of the information verification pipeline: check-worthiness, evidence retrieval and pairing, and verification. Since the 2023 edition, it has been focusing on new problems that can support the research and decision making during the verification process. In this new edition, we focus on new problems and —for the first time— we propose six tasks in fifteen languages (Arabic, Bulgarian, English, Dutch, French, Georgian, German, Greek, Italian, Polish, Portuguese, Russian, Slovene, Spanish, and code-mixed Hindi-English): Task 1 estimation of check-worthiness (the only task that has been present in all …

Bare-Bones Based Honey Badger Algorithm Of Cnn For Sleep Apnea Detection, Ammar Kamal Abasi, Moayad Aloqaily, Mohsen Guizani

Machine Learning Faculty Publications

Sleep Apnea (SA) is a breathing disorder that many people experience during sleep. Polysomnography is the best way to diagnose SA, but it requires significant time, cost, and effort. A practical and efficient method of diagnosing SA is using a wearable sensor to record Electrocardiography (ECG) signals. Machine learning algorithms can be used to classify SA by extracting features from ECG signals. Recently, deep learning techniques such as Convolutional Neural Network (CNN) have been used to identify features from ECG data automatically. However, the large number of hyperparameters in CNN makes it challenging to perform this task manually. Metaheuristic algorithms …

Computation Time Minimized Offloading In Noma-Enabled Wireless Powered Mobile Edge Computing, Wenchao Chen, Xinchen Wei, Kaikai Chi, Keping Yu, Amr Tolba, Shahid Mumtaz, Mohsen Guizani

Machine Learning Faculty Publications

Wireless powered mobile edge computing (WP-MEC), which combines mobile edge computing (MEC) and wireless power transfer (WPT), is a promising paradigm for coping with the computing power and energy constraints of wireless devices. However, how to realize the online optimal offloading decision and resource allocation in the WP-MEC system is very challenging. This paper studies the system computation completion time (SCCT) minimization problems for WP-MEC networks using non-orthogonal multiple access (NOMA) communication under binary and partial offloading modes. Due to the complexity of the optimization problems and the time-varying nature of the channel state information, we decouple the original problems …

Inter-Feature Relationship Certifies Robust Generalization Of Adversarial Training, Shufei Zhang, Zhuang Qian, Kaizhu Huang, Qiu Feng Wang, Bin Gu, Huan Xiong, Xinping Yi

Machine Learning Faculty Publications

Whilst adversarial training has been shown as a promising wisdom to promote model robustness in computer vision and machine learning, adversarially trained models often suffer from poor robust generalization on unseen adversarial examples. Namely, there still remains a big gap between the performance on training and test adversarial examples. In this paper, we propose to tackle this issue from a new perspective of the inter-feature relationship. Specifically, we aim to generate adversarial examples which maximize the loss function while maintaining the inter-feature relationship of natural data as well as penalizing the correlation distance between natural features and adversarial counterparts. As …

Tmn: An Efficient Robust Aggregator For Federated Learning, Anees Ur Rehman Hashmi, Mohammed El Amine Azz

Machine Learning Faculty Publications

The collaboration of multiple organizations, such as hospitals, with access to data, can expedite the training process, resulting in superior machine learning models with increased data availability. However, the sensitivity of medical data poses challenges to information sharing without compromising privacy and confidentiality. Federated Learning (FL) offers a promising solution by enabling collaborative training through a data-sharing-free approach. Nevertheless, a large number of FL aggregation algorithms assume clients are honest, leaving the global model vulnerable to poisoning attacks. Approaches to safeguard against such attacks often add high computational costs, making them unsuitable for practical applications. In this work, we propose …

A Multi-Objective Grey Wolf Optimizer For Energy Planning Problem In Smart Home Using Renewable Energy Systems, Sharif Naser Makhadmeh, Mohammed Azmi Al-Betar, Feras Al-Obeidat, Osama Ahmad Alomari, Ammar Kamal Abasi, Mohammad Tubishat, Zenab Elgamal, Waleed Alomoush

Machine Learning Faculty Publications

This paper presents the energy planning problem (EPP) as an optimization problem to find the optimal schedules to minimize energy consumption costs and demand and enhance users’ comfort levels. The grey wolf optimizer (GWO), One of the most powerful optimization methods, is adjusted and adapted to address EPP optimally and achieve its objectives efficiently. The GWO is adapted due to its high performance in addressing NP-complex hard problems like the EPP, where it contains efficient and dynamic parameters that enhance its exploration and exploitation capabilities, particularly for large search spaces. In addition, new energy and real-world resources based on solar …

A Property-Guided Diffusion Model For Generating Molecular Graphs, Changsheng Ma, Taicheng Guo, Qiang Yang, Xiuying Chen, Xin Gao, Shangsong Liang, Nitesh Chawla, Xiangliang Zhang

Machine Learning Faculty Publications

Inverse molecular generation is an essential task for drug discovery, and generative models offer a very promising avenue, especially when diffusion models are used. Despite their great success, existing methods are inherently limited by the lack of a semantic latent space that can not be navigated and perform targeted exploration to generate molecules with desired properties. Here, we present a property-guided diffusion model for generating desired molecules, which incorporates a sophisticated diffusion process capturing intricate interactions of nodes and edges within molecular graphs and leverages a time-dependent molecular property classifier to integrate desired properties into the diffusion sampling process. Furthermore, …

Adaptive Interleaver And Rate-Compatible Pldpc Code Design For Mimo Fso-Rf Systems, Liang Lv, Zhaojie Yang, Yi Fang, Mohsen Guizani

Machine Learning Faculty Publications

This paper conducts an in-depth investigation on the interleaver and error-correction codes for multiple-input multiple-output (MIMO) hybrid free space optical-radio frequency (FSO-RF) systems. Specifically, based on the unequal error protection (UEP) property between the FSO links and RF links, we first propose a novel adaptive interleaver, called protograph variable-node mutual information growth match (PVMIGM) mapping scheme, to boost the performance of MIMO FSO-RF systems with protograph low-density parity-check (PLDPC) codes. Furthermore, by exploiting the protograph extrinsic information transfer (PEXIT) algorithm, we design a type of rate-compatible PLDPC code, called improved rate-compatible PLDPC (IRP) codes, which have both low decoding thresholds …

Ai For Sustainable Agriculture: A Systematic Review, Mohamed Ahmed Alloghani

Machine Learning Faculty Publications

In the contemporary realm of agricultural research, the integration of artificial intelligence (AI) with traditional practices is progressively emerging as a focal theme. Nonetheless, the scholarly landscape has demonstrated a notable dearth in examining the intricate relationship between AI and the tripartite principles of sustainable agriculture: economic viability, environmental stewardship, and social responsibility. Utilizing the PRISMA methodology, this systematic review endeavors to bridge this gap, offering an exhaustive examination of the aforementioned relationship. The analysis revealed that while many studies have explored individualized AI applications, few have situated these advancements within a holistic sustainability framework. The findings underscore AI’s potential, …

Anomaly Detection For In-Vehicle Network Using Self-Supervised Learning With Vehicle-Cloud Collaboration Update, Jinhui Cao, Xiaoqiang Di, Xu Liu, Jinqing Li, Zhi Li, Liang Zhao, Ammar Hawbani, Mohsen Guizani

Machine Learning Faculty Publications

With the increasing communications between the In-Vehicle Networks (IVNs) and external networks, security has become a stringent problem. In addition, the controller area network bus in IVN lacks security mechanisms by design, which is vulnerable to various attacks. Thus, it is important to detect IVN anomalies for complete vehicular security. However, current studies are constrained by either requiring labeled data or failing to accurately detect message-level anomalies without labeled data. In addition, the concept drift of existing methods has become a challenge over time. To address these problems, this paper proposes an IVN anomaly detection method based on Self-supervised Learning …

Architecting Green Artificial Intelligence Products: Recommendations For Sustainable Ai Software Development And Evaluation, Mohamed Ahmed Alloghani

Machine Learning Faculty Publications

With unabated global warming and climate change, the concept of Green Artificial Intelligence has emerged in which companies in the information and communication sector are increasingly embracing sustainable methods for designing, developing, and applying AI software. This paper examines current research on Green AI coding practices, design principles, use cases, and applications, as well as policy, ethical, and regulatory issues. The overarching premise is that Green Artificial Intelligence is a promising paradigm for mitigating climate change through collaboration. However, it requires a streamlined regulatory framework combining AI policy, industry standards and best practices, and legal frameworks for addressing emerging issues …

Artificial Intelligence For Ocean Conservation: Sustainable Computer Vision Techniques In Marine Debris Detection And Classification, Mohamed Ahmed Alloghani

Machine Learning Faculty Publications

Marine debris poses a significant threat to the marine ecosystem, and its detection and removal are crucial for environmental sustainability. This study presents a comprehensive study on the application of computer vision techniques for marine debris detection, with a specific focus on the task of trash detection. The study utilizes a diverse and carefully curated dataset named “YOLOv5 Marine Debris” (or any suitable name for the YOLOv5 dataset), obtained from the Ultralytics open-source research repository for YOLOv5 models. Through the utilization of computer vision techniques, this study strives to contribute to the development of sustainable solutions for marine debris detection. …

Chatgpt's Security Risks And Benefits: Offensive And Defensive Use-Cases, Mitigation Measures, And Future Implications, Maha Charfeddine, Habib M. Kammoun, Bechir Hamdaoui, Mohsen Guizani

Machine Learning Faculty Publications

ChatGPT has been acknowledged as a powerful tool that can radically boost productivity across a wide range of industries. It reveals potential in cybersecurity-related tasks such as social engineering. Nevertheless, this possibility raises important concerns regarding the thin line separating moral use of this technology from its harmful usage. It is imperative to address the challenges of distinguishing between legitimate and malevolent use of ChatGPT. This research paper investigates the many concerns of ChatGPT in cybersecurity, privacy and enterprise settings. It covers harmful attacker uses such as injecting malicious prompts, testing brute force attacks, preparing and developing ransomware attacks, etc. …

Criteria For Sustainable Ai Software: Development And Evaluation Of Sustainable Ai Products, Mohamed Ahmed Alloghani

Machine Learning Faculty Publications

Although the world is eager to use these new AI systems and trends to take advantage of their potential benefits, unclear implications remain evident now and in the long run. Using the dimensions of sustainability in structuring this analysis, the scope of the research revolved around exploring the strategies that may be used in developing and evaluating AI products (Z. Zhang, D. Lyu, P. Arcaini, L. Ma, I. Hasuo and J. Zhao, IEEE Trans Softw Eng 1–17, 2022). According to the research findings, the fundamental goal of AI’s design and ethical development is increasing acceptance and trust of emerging technologies. …

Cross-Modal Communication Technology: A Survey, Xin Wei, Dan Wu, Liang Zhou, Mohsen Guizani

Machine Learning Faculty Publications

In the 5G era and beyond, multi-modal services that integrate audio, visual, and haptic signals are expected to become dominant applications. To support multi-modal services, the concept of cross-modal communications, which involves collaborative audio-visual and haptic interactions, has emerged. Despite significant research about cross-modal communication technology being conducted, a comprehensive literature review on this topic is lacking. To fill this gap, this paper presents a detailed survey on cross-modal communication technology. First, it provides a highly summarized description of representative research attempts in audio-visual and haptic communications, which serve as the foundation for cross-modal communications. Then, it delves into various …

Distributed Rumor Source Detection Via Boosted Federated Learning, Ranran Wang, Yin Zhang, Wenchao Wan, Min Chen, Mohsen Guizani

Machine Learning Faculty Publications

How to localize the rumor source is a common interest of all sectors of the society. Many researchers have tried to use deep-learning-based graph models to detect rumor sources, but they have neglected how to train their deep-learning-based graph models in the noisy social network environment efficiently. Especially for deep learning models, the performance relies on the data scale. However, even though its known that a substantial amount of rumor data distributed across multiple edge servers (e.g., cross-platform), due to conflicting business interests, its challenging to coordinate all parties to train a model driven by many samples while avoiding moving …

Drone Detection With Improved Precision In Traditional Machine Learning And Less Complexity In Single Shot Detectors, Mohamad Kassab, Raed Abu Zitar, Frederic Barbaresco, Amal El Fallah Seghrouchni

Machine Learning Faculty Publications

This work presents a broad study of drone detection based on a variety of machine-learning methods including traditional and deep-learning techniques. The data sets used are images obtained from sequences of video frames in both RGB and IR formats, filtered and unfiltered. First, traditional machine learning techniques such as SVM and RF were investigated to discover their drawbacks and study their feasibility in drone detection. It was evident that those techniques are not suitable for complex data sets (sets with several non-drone objects and clutter in the background). It was observed that the sliding window size results in a bias …

Dynamic Satellite Edge Computing Offloading Algorithm Based On Distributed Deep Learning, Jiaqi Shuai, Haixia Cui, Yejun He, Moshen Guizani

Machine Learning Faculty Publications

Satellite communication networks with the characteristics of wide coverage, high deployment flexibility, and seamless communication services can provide communication services to users who don’t communicate with ground networks but directly communicate with satellites. In response to the increasing demand for user services, this paper proposes a collaborative computing offloading scheme for satellite edge computing networks with a four-layer architecture. By utilizing collaborative computing between ground users and three layers of satellites (low-orbit satellites, edge, and cloud data centers), the service quality for ground users is improved. Considering the mobility of vehicles and satellite nodes, the frequent changes in link states …

Enhancing Iot Security With Trust Management Using Ensemble Xgboost And Adaboost Techniques, Kamran Ahmad Awan, Ikram Ud Din, Ahmad Almogren, Byung Seo Kim, Mohsen Guizani

Machine Learning Faculty Publications

As next-generation networking environments become increasingly complex and integral to the fabric of digital transformation as the traditional perimeter-based security model proves inadequate. The Zero Trust framework emerges as a critical solution to this challenge, advocating for a security model that assumes no implicit trust and requires verification at every step. The rapid growth of the Internet of Things (IoT) creates an environment of millions of interacting devices that radically transform today’s digital environment. In such conditions, the problem of identifying malicious and compromised nodes among IoT devices becomes mandatory to maintain trustworthy environment. The main objective of this research …

Escm: An Efficient And Secure Communication Mechanism For Uav Networks, Haoxiang Luo, Yifan Wu, Gang Sun, Hongfang Yu, Mohsen Guizani

Machine Learning Faculty Publications

UAV (unmanned aerial vehicle) is rapidly gaining traction in various human activities and has become an integral component of the satellite-air-ground-sea (SAGS) integrated network. As high-speed moving objects, UAVs not only have extremely strict requirements for communication delay, but also cannot be maliciously controlled as a weapon by the attacker. Therefore, it is necessary to design an efficient and secure communication mechanism (ESCM) for the UAV network (a mobile ad hoc network composed of multiple UAVs). For high efficiency, ESCM provides a routing protocol based on the artificial bee colony (ABC) algorithm to accelerate communications between UAVs. Meanwhile, we use …

From Control Application To Control Logic: Plc Decompile Framework For Industrial Control System, Chao Sang, Jun Wu, Jianhua Li, Mohsen Guizani

Machine Learning Faculty Publications

Industrial Control System (ICS) depends on the underlying Programmable Logical Controllers (PLCs) to run. As such, the security of the internal control logic of the PLCs is the top concern of ICS. Reversing analysis and forensic work against PLC require extracting control logic from the control application running inside PLC, which is still an unresolved problem. To address the challenge, we propose a PLC decompile framework named CLEVER, which can analyze the control application and extract the control logic. First, we propose a simulation execution based code extraction method, which is utilized to filter the control logic related data. Then, …

Gai-Iov: Bridging Generative Ai And Vehicular Networks For Ubiquitous Edge Intelligence, Gaochang Xie, Zehui Xiong, Xinyuan Zhang, Renchao Xie, Song Guo, Mohsen Guizani, H. Vincent Poor

Machine Learning Faculty Publications

The growth of intelligent vehicular services, like augmented reality (AR) road simulation, underscores the need for rapid, multi-modal content generation. Generative artificial intelligence (GAI) models, known for their swift production of diverse artificial intelligence-generated content (AIGC), stand out as a prime solution. However, integrating cloud-centric GAI models into vehicular networks is fraught with challenges. Notably, to offer specialized generative edge intelligence (EI) and boost vehicular AIGC, GAI models need to tap into user data and utilize significant computation resources. Moreover, their deployment across vehicular networks is essential for proximity-based distributed inferences. Yet, edge devices are resource-limited, and data sharing can …

Generative Ai For Transformative Healthcare: A Comprehensive Study Of Emerging Models, Applications, Case Studies, And Limitations, Siva Sai, Aanchal Gaur, Revant Sai, Vinay Chamola, Mohsen Guizani, Joel J.P.C. Rodrigues

Machine Learning Faculty Publications

Generative artificial intelligence (GAI) can be broadly described as an artificial intelligence system capable of generating images, text, and other media types with human prompts. GAI models like ChatGPT, DALL-E, and Bard have recently caught the attention of industry and academia equally. GAI applications span various industries like art, gaming, fashion, and healthcare. In healthcare, GAI shows promise in medical research, diagnosis, treatment, and patient care and is already making strides in real-world deployments. There has yet to be any detailed study concerning the applications and scope of GAI in healthcare. Addressing this research gap, we explore several applications, real-world …

Green Mobile App Development: Building Sustainable Products, Mohamed Ahmed Alloghani

Machine Learning Faculty Publications

In the digital innovation landscape, the integration of sustainability and mobile app development emerges as a critical convergence, exemplifying the blend of technological advancements with environmental awareness. Guided by the PRISMA framework, this systematic review meticulously navigated a spectrum of academic sources to identify prevailing insights, emerging trends, and discernible gaps in the realm of green mobile app development. Employing methodological rigor, diverse databases were consulted, and salient studies were selected. Subsequent data extraction and analysis processes revealed the transformative potential of digitalization with an emphasis on Sustainable Development Goals. Notably, emerging paradigms such as the Green Internet of Things …