Digital Commons Network^™

Harnessing Ai For Sustainability: Applied Ai And Machine Learning Algorithms For Air Quality Prediction, Mohamed Ahmed Alloghani

Machine Learning Faculty Publications

The sustainability of ecosystems and human well-being are both directly impacted by air quality, which is a crucial component of environmental health. Due to its negative effects on societal advancement, the environment, and public health, the deteriorating air quality around the world has sparked serious worries. It is essential to have accurate and fast air quality forecasts in order to address this urgent problem since it can offer helpful information for making wise decisions, carrying out mitigation strategies successfully, and protecting sensitive communities. Using AI and the linear regression technique, we will investigate many facets of air quality forecasting in …

Intelligent Traffic-Service Mapping Of Network For Advanced Industrial Iot Edge Computing, Bowen Liu, Tao Zheng, Kyi Thar, Mikael Gidlund, Xiaoting Ma, Bo Lei, Hongke Zhang, Mohsen Guizani

Machine Learning Faculty Publications

The increasing number of IoT devices in the network brings new challenges to the network carrying capacity of intelligent edge computing, and the complicated network services make the demand for network resources in industrial production scenarios or ordinary network users often exceed the carrying capacity of the edge computing network. To alleviate this problem, this paper proposes an intelligent edge computing architecture that introduces network service identification, extracts and analyses the data characteristics of network traffic, and designs appropriate algorithms to classify network traffic into six different service types. This enables real-time and computing-requiring tasks to be prioritised in the …

Marine Predators Algorithm For Energy Scheduling Problem Using Renewable Energy, Sharif Naser Makhadmeh, Ammar Kamal Abasi, Mohammed Azmi Al-Betar

Machine Learning Faculty Publications

The Energy Scheduling Problem (ESP) involves scheduling smart home appliances based on electricity pricing schemes. This entails adjusting the timing of operations for these appliances across different periods. The primary aim of this scheduling approach is to reduce cost and the Peak-to-Average Ratio (PAR), while enhancing user comfort. This study employs the Marine Predators Algorithm (MPA) to address ESP and derive an optimal schedule for smart home appliances. Additionally, a renewable energy source (RES) on the basis of a PV system is introduced to further optimize appliance schedules by providing a smart home with energy, particularly during peak periods. The …

Optimum Track To Track Fusion Using Cma-Es And Lstm Techniques, Samar Fares, Amal El Fallah Seghrouchni, Frederic Barbaresco, Raed Abu Zitar

Machine Learning Faculty Publications

This paper presents two different methods for track-to-track fusion of drone tracks. The sensors are unbiased radars with fixed locations. The first method uses an offline technique based on a global optimizer called the CMA-ES algorithm and the second one uses LSTM in its different forms to learn the online adjustment of the fusion weights between the two tracks. An objective function utilizing the covariance of the fused tracks is used by the first algorithm while a cost function based on the Kullback-Leibler (KL) divergence measure is used in the second case for training the LSTM. The two methods are …

Privacy-Driven Security-Aware Task Scheduling Mechanism For Space-Air-Ground Integrated Networks, Yunfei Cai, Haipeng Yao, Yongkang Gong, Fu Wang, Ni Zhang, Mohsen Guizani

Machine Learning Faculty Publications

To implement ubiquitous intelligence of the sixth generation mobile networks (6G), space-air-ground integrated networks (SAGIN) have emerged as a promising infrastructure to provide globally seamless coverage and powerful cloud computing services. With SAGIN, Internet of Things (IoT) devices can offload compute-intensive tasks to unmanned aerial vehicles (UAVs) and satellites. However, due to the vulnerability of wireless communications to eavesdropping attacks, privacypreserving task scheduling in SAGIN is of great challenge. To address this problem, we propose a privacy-driven multi-agent proximal policy optimization-based security-aware SAGIN task scheduling mechanism, where we jointly optimize the delay, energy consumption and security utility of tasks considering …

Protein Multiple Conformation Prediction Using Multi-Objective Evolution Algorithm, Minghua Hou, Sirong Jin, Xinyue Cui, Chunxiang Peng, Kailong Zhao, Le Song, Guijun Zhang

Machine Learning Faculty Publications

The breakthrough of AlphaFold2 and the publication of AlphaFold DB represent a significant advance in the field of predicting static protein structures. However, AlphaFold2 models tend to represent a single static structure, and multiple-conformation prediction remains a challenge. In this work, we proposed a method named MultiSFold, which uses a distance-based multi-objective evolutionary algorithm to predict multiple conformations. To begin, multiple energy landscapes are constructed using different competing constraints generated by deep learning. Subsequently, an iterative modal exploration and exploitation strategy is designed to sample conformations, incorporating multi-objective optimization, geometric optimization and structural similarity clustering. Finally, the final population is …

Recent Advances In Quantum Computing For Drug Discovery And Development, Gautam Kumar, Sahil Yadav, Aniruddha Mukherjee, Vikas Hassija, Mohsen Guizani

Machine Learning Faculty Publications

Preserving human health is of utmost importance, and unrestricted availability of medications is essential for overall wellness. Pharmaceuticals, which consist of a wide range of therapeutic substances utilized to diagnose, treat, and improve various diseases and conditions, play a crucial part in healthcare. However, the drug research and development process is widely recognized for its lengthy duration, demanding nature, and substantial expenses. To enhance the effectiveness of this complex process, interdisciplinary groups have converged, giving rise to the field known as 'Bioinformatics'. The emergence and future advancements of Quantum Computing (QC) technologies have the potential to significantly enhance and accelerate …

Rethinking Polyp Segmentation From An Out-Of-Distribution Perspective, Ge Peng Ji, Jing Zhang, Dylan Campbell, Huan Xiong, Nick Barnes

Machine Learning Faculty Publications

Unlike existing fully-supervised approaches, we rethink colorectal polyp segmentation from an out-of-distribution perspective with a simple but effective self-supervised learning approach. We leverage the ability of masked autoencoders–self-supervised vision transformers trained on a reconstruction task–to learn in-distribution representations, here, the distribution of healthy colon images. We then perform out-of-distribution reconstruction and inference, with feature space standardisation to align the latent distribution of the diverse abnormal samples with the statistics of the healthy samples. We generate per-pixel anomaly scores for each image by calculating the difference between the input and reconstructed images and use this signal for out-of-distribution (i.e., polyp) segmentation. …

Safeguarding Patient Data-Sharing: Blockchain-Enabled Federated Learning In Medical Diagnostics, Raushan Myrzashova, Saeed Hamood Alsamhi, Ammar Hawbani, Edward Curry, Mohsen Guizani, Xi Wei

Machine Learning Faculty Publications

Medical healthcare centers are envisioned as a promising paradigm to handle vast data for various disease diagnoses using artificial intelligence. Traditional Machine Learning algorithms have been used for years, putting the sensitivity of patients' medical data privacy at risk. Collaborative data training, where multiple hospitals (nodes) train and share encrypted federated models, solves the issue of data leakage and unites resources of small and large hospitals from distant areas. This study introduces an innovative framework that leverages blockchain-based Federated Learning to identify 15 distinct lung diseases, ensuring the preservation of privacy and security. The proposed model has been trained on …

Sparsity-Aware Intelligent Massive Random Access Control For Massive Mimo Networks: A Reinforcement Learning Based Approach, Xiao Tang, Sicong Liu, Xiaojiang Du, Mohsen Guizani

Machine Learning Faculty Publications

Massive random access of devices brings great challenge to the management of radio access networks. Most of the time, the access requests in the network is sporadic. Exploiting the bursting nature, sparse active user detection (SAUD) is an efficient enabler towards efficient active user detection. However, the sparsity might be deteriorated in case of high concurrent request periods. To dynamically coordinate the access requests, a reinforcement-learning (RL)-assisted scheme of closed-loop access control utilizing the access class barring (ACB) technique is proposed, where the control policy is determined through continuous interaction between the RL agent and the environment. The proposed RL …

Stagewise Training With Exponentially Growing Training Sets, Bin Gu, Hilal Alquabeh, William De Vazelhes, Zhouyuan Huo, Heng Huang

Machine Learning Faculty Publications

In the world of big data, training large-scale machine learning problems has gained considerable attention. Numerous innovative optimization strategies have been presented in recent years to accelerate the large-scale training process. However, the possibility of further accelerating the training process of various optimization algorithms remains an unresolved subject. To begin addressing this difficult problem, we exploit the researched findings that when training data are independent and identically distributed, the learning problem on a smaller dataset is not significantly different from the original one. Upon that, we propose a stagewise training technique that grows the size of the training set exponentially …

Synergy Of Human-Centered Ai And Cyber-Physical-Social Systems For Enhanced Cognitive Situation Awareness: Applications, Challenges And Opportunities, Saeed Hamood Alsamhi, Santosh Kumar, Ammar Hawbani, Alexey V. Shvetsov, Liang Zhao, Mohsen Guizani

Machine Learning Faculty Publications

This paper explores the convergence of Human-Centered AI (HCAI) and Cyber-Physical Social Systems (CPSS) in pursuing advanced Cognitive Situation Awareness (CSA). Integrating HCAI principles within CPSS fosters systems prioritizing human needs, values, and experiences, improving perception, understanding, and responsiveness to complex environments. By incorporating transparency, interpretability, and usability into Artificial Intelligence (AI) systems, the human-centered approach enhances user interaction and cooperation with intelligent systems, leading to more adaptive and efficient CPSS. The study employs a comprehensive approach to explore the intersection of HCAI and CPSS. Moreover, the paper presents case studies to illustrate real-world applications of HCAI and CPSS, such …

Task Scheduling And Trajectory Optimization Based On Fairness And Communication Security For Multi-Uav-Mec System, Yejun He, Kun Xiang, Xiaowen Cao, Mohsen Guizani

Machine Learning Faculty Publications

Unmanned aerial vehicles (UAVs) show significant potential in enhancing communication services within the mobile edge computing (MEC) system by taking their advantages on the flexible mobility and reliable line-of-sight links. However, in the scenarios with multiple UAV-MECs (UMs) operating concurrently, potential conflicts in their trajectories need to be mitigated. Thus, the 3D trajectory needs to be properly designed in a highly reliable manner. Besides, such an infrastructure-free communication paradigm also exposes a potential risk of misuse by malicious parties, which allows them to eavesdrop on private communications, posing a threat to the security and privacy. Therefore, we consider a multi-UAV-assisted …

Temporal Machine Learning Payload Prediction For Dji Matrice 100 Quadcopter Drone Based On Tracking Data, Mariam Kashkash, Amal El Fallah Seghrouchni, Frederic Barbaresco, Raed Abu Zitar

Machine Learning Faculty Publications

This paper presents three different machine-learning techniques to predict the payloads of DJI Matrice 100 quadcopter drones. The tracking data is based on real-life experimentation that is provided as open source. The payloads are 0.0, 250, 500, and 750 grams. The Machine Learning techniques are LSTM, TCN, and GRU. The values of the tracks' kinematics come from several different flights for the different loads. The tracks' kinematics in addition to some flight parameters are used in training the three models. The temporal nature of the data values triggers the need for machine learning methods that use history/memory as part of …

Using Ai To Monitor Marine Environmental Pollution: Systematic Review, Mohamed Ahmed Alloghani

Machine Learning Faculty Publications

Amidst escalating concerns about marine environmental pollution, this systematic review delves into the role and potential of artificial intelligence (AI) in monitoring and managing marine ecosystems. Through the meticulous adoption of the PRISMA methodology, various databases were scrutinized, resulting in a curated list of seminal studies that encompass AI’s diverse techniques, such as machine learning and deep learning, in marine monitoring. The findings elucidate that AI techniques offer transformative advancements in real-time data analysis, predictive modeling, and anomaly detection, making them indispensable for contemporary marine conservation efforts. However, despite their potential, AI systems also bear limitations that need thoughtful consideration. …

Walking The Talk: Practical Implementation Of Machine Learning Algorithms For Predicting Co2 Emission Footprint And Sustainability, Mohamed Ahmed Alloghani

Machine Learning Faculty Publications

The increasing levels of CO2 emissions have become a significant concern worldwide. Accurate prediction of CO2 emission levels plays a crucial role in implementing sustainable practices and driving policy decisions. This study aims to develop a machine learning model for predicting CO2 emission footprints using various socio-economic and environmental factors. The model will facilitate effective planning and decision-making in reducing global carbon emissions. The main objective of this study is to develop a machine learning model that accurately predicts CO2 emissions from fossil fuels and identifies the most important factors that contribute to these emissions. The results of this study …

Action Knowledge Graph For Violence Detection Using Audiovisual Features, Mustaqeem Khan, Muhammad Saad, Abbas Khan, Wail Gueaieb, Abdulmotaleb El Saddik, Giulia De Masi, Fakhri Karray

Machine Learning Faculty Publications

Detecting violent content in video frames is a crucial aspect of violence detection. Combining visual and audio cues is often the most effective way to identify violent behavior, as they complement each other. However, studies that examine the fusion of these cues in violence detection are computationally expensive and limited. To address this problem, we investigated various methods for integrating visual and audio information and proposed a Fused Vision-based Action Knowledge Graph (FV-AKG) for violence detection using audiovisual information. The authors have designed a network with three parallel branches named integrated, specialized, and scoring that capture and integrate the distinct …

Camofocus: Enhancing Camouflage Object Detection With Split-Feature Focal Modulation And Context Refinement, Maryam Nadeem, Raza Imam, Rouqaiah Al-Refai, Meriem Chkir, Mohamad Hoda, Abdulmotaleb El Saddik

Machine Learning Faculty Publications

As virtual environments continue to advance, the demand for immersive and emotionally engaging experiences has grown. Addressing this demand, we introduce Emotion enabled Virtual avatar mapping using Optimized KnowledgE distillation (EVOKE), a lightweight emotion recognition framework designed for the seamless integration of emotion recognition into 3D avatars within virtual environments. Our approach leverages knowledge distillation involving multi-label classification on the publicly available DEAP dataset, which covers valence, arousal, and dominance as primary emotional classes. Remarkably, our distilled model, a CNN with only two convolutional layers and 18 times fewer parameters than the teacher model, achieves competitive results, boasting an accuracy …

M4: Multi-Generator, Multi-Domain, And Multi-Lingual Black-Box Machine-Generated Text Detection, Liang Li, Qisheng Liao, Meiting Lai, Di Liang, Shangsong Liang

Machine Learning Faculty Publications

Pre-trained models such as BERT have achieved remarkable results in text matching tasks. However, existing models still suffer from the challenge of capturing local subtle differences when modeling complex semantic matching relationships. In this work, we find that the integration of local syntax awareness and global semantics is crucial for text matching. Meanwhile, we propose the Local and Global Syntax Graph Calibration (LG-SGC) module, which can explore local syntactic and global semantic information for the matching task. Specifically, we first introduce an auxiliary task inside BERT to capture local subtle grammatical differences. Then, we retain the original attention operation to …

Respirodynamics: A Multifaceted Dataset For Enhanced Lung Health Assessment Using Deep Learning, Ahmed Sharshar, Muhammad Sharshar, Hosam Elhady, Ahmed Aboeitta, Youssef Nafea, Yasser Ashraf, Mohammad Yaqub, Mohsen Guizani

Machine Learning Faculty Publications

Advancements in lung health assessment, a critical component in diagnosing respiratory conditions, have gained prominence in medical research. This is especially true with the advent of non-invasive techniques such as spirometry. Central to this diagnostic method are three key metrics: Forced Vital Capacity (FVC), Forced Expiratory Volume in 1 second (FEV1), and Peak Expiratory Flow (PEF). In light of the increasing need for accurate and reliable assessment tools, developing comprehensive datasets is imperative for advancing research in this field. Our paper presents RespiroDynamics: A Comprehensive Multimodal Respiratory Dataset, a total of more than 2k samples, compiled from 60 participants, covering …

Spotcrack: Leveraging A Lightweight Framework For Crack Segmentation In Infrastructure, Wong Yu Kang, Toluwani Aremu, Younes Balah, Maryam Nadeem, Ivo Gollini Navarette, Abdulmotaleb El Saddik

Machine Learning Faculty Publications

In today's data-driven world, quick access to scholarly info is vital. However, current academic search engines face challenges such as restricted text-based searching, uncertainties related to researcher names, absence of contact details, and lack of profile summaries. To mitigate these issues, we introduce ScholarFace, an innovative concept that could transform how we search for academic knowledge. It uses face recognition and language generation technology to spot scholars in photos effortlessly, giving us rich profiles and summaries of their work. It also offers an interactive chat element for users to get more insights about a scholar, reducing online search efforts. We …

Vd-Net: An Edge Vision-Based Surveillance System For Violence Detection, Abbas Khan, Mustaqeem Khan, Wail Gueaieb, Abdulmotaleb El Saddik, Giulia De Masi, Fakhri Karray

Machine Learning Faculty Publications

Camouflage Object Detection (COD) involves the challenge of isolating a target object from a visually similar background, presenting a formidable challenge for learning algorithms. Drawing inspiration from state-of-the-art (SOTA) Focal Modulation Networks, our objective is to proficiently modulate the foreground and background components, thereby capturing the distinct features of each. We introduce a Feature Split and Modulation (FSM) module to attain this goal. This module efficiently separates the object from the background by utilizing foreground and background modulators guided by a supervisory mask. For enhanced feature refinement, we propose a Context Refinement Module (CRM), which considers features acquired from FSM …

A Single-Photon Lidar Observes Atmospheric Clouds At Decimeter Scales: Resolving Droplet Activation Within Cloud Base, Fan Yang, Alexander B. Kostinski, Zeen Zhu, Katia Lamer, Edward Luke, Pavlos Kollias, Yong Meng Sua, Pei Hou, Raymond Shaw, Andrew M. Vogelmann

Michigan Tech Research Data

Clouds, crucial for understanding climate, begin with droplet formation from aerosols, but observations of this fleeting activation step are lacking in the atmosphere. Here we use a time-gated time-correlated single-photon counting lidar to observe cloud base structures at decimeter scales. Results show that the air-cloud interface is not a perfect boundary but rather is a transition zone where transformation of aerosol particles into cloud droplets occurs. The observed distributions of first-arriving photons within the transition zone reflect vertical development of a cloud, including droplet activation and condensational growth. Further, the highly resolved vertical profile of backscattered photons above cloud base …

Experimental Data For: "Effects Of Network Connectivity And Functional Diversity Distribution On Human Collective Ideation", Yiding Cao, Yingjun Dong, Minjun Kim, Neil G. Maclaren, Sriniwas Pandey, Shelley D. Dionne, Francis J. Yammarino, Hiroki Sayama

Systems Science and Industrial Engineering Faculty Scholarship

This is the dataset collected from our online human-subject experiments described in the following manuscript:

Yiding Cao, Yingjun Dong, Minjun Kim, Neil G. MacLaren, Sriniwas Pandey, Shelley D. Dionne, Francis J. Yammarino, and Hiroki Sayama:
"Effects of Network Connectivity and Functional Diversity Distribution on Human Collective Ideation"
https://arxiv.org/abs/2307.04284

A Young Dancer With Hand Pain And Tremors, Brittney Hulsey

PA Faculty Publications

No abstract provided.

199965, David Kerstetter

PERC Albacore sPAT Data

Datasets (and supporting material) from 4sPAT electronic tags deployed on albacore caught by pelagic longline gear in the western North Atlantic.

199953, David Kerstetter

PERC Albacore sPAT Data

Datasets (and supporting material) from 4sPAT electronic tags deployed on albacore caught by pelagic longline gear in the western North Atlantic.

199949, David Kerstetter

PERC Albacore sPAT Data

Datasets (and supporting material) from 4sPAT electronic tags deployed on albacore caught by pelagic longline gear in the western North Atlantic.

199946, David W. Kerstetter

PERC Albacore sPAT Data

Datasets (and supporting material) from 4sPAT electronic tags deployed on albacore caught by pelagic longline gear in the western North Atlantic.

Flannery O'Connor And Storytelling Unit Of Study, Caroline Lacksen, Natalie Puckett, Keith Pruett, Erin Smith, Nathan Pearson, Lashonda Hurst, Jessica Mcquain, Timothy Connors

Writing for Success

The Writing for Success grant sponsored by the federal Department of Education pioneered the creation of a standards-based fifth grade unit of study focused on Flannery O’Connor and the theme of local storytelling. This project utilizes an author study, digital humanities, and intensive writing instruction to engage students with an important Georgia writer and boost their interest and engagement with various forms of written and oral expression.

Through exposure to a variety of communication forms, including narrative, informational, and opinion writing in addition to oral history, poetry, song, and podcasting, students gain confidence in evaluating the context and audience of …