Engineering Commons^™

Predicted Water Yield Of Open-Pit Metal Mines Based On A Bi-Rnn And Gms Coupling Model, Zhao Yuxing, Li Xiangwen

Coal Geology & Exploration

Objective Accurately predicting water yield of mine before mining can provide directive guidance for preventing potential water hazards and ensuring safe production. Methods To enhance the prediction accuracy and stability of water yield of open-pit metal mines, for which atmospheric precipitation acts as the primary recharge source of water, this study developed a prediction model that coupled a bidirectional recurrent neural network (Bi-RNN) and the Groundwater Modeling System (GMS) software. Specifically, based on historical forecasted precipitation data provided by the Global Forecast System (GFS), the fluctuation pattern of differences between predicted forecasted and actual precipitation was analyzed. After being corrected …

An Intelligent System Using Deep Learning For Healthcare Monitoring In Light Of The Covid-19 And Future Pandemics Based On Iot, Sara Salman Qasim, Rajaa J. Khanjar, Jamal Nasir Hasoon, Baesher Abdullateff Abad, Ali Hussein Fadil, Shajan.M. Alsowaidi

Al-Esraa University College Journal for Engineering Sciences

Recently, the Internet of Things has become a compelling research field as a new topic of research in various disciplines, particularly in the field of healthcare, because the Internet of Things is rebuilding modern healthcare systems by integrating technology, economics, and social perspectives. The development of healthcare systems from traditional to more personalized systems in which patients can be easily diagnosed, monitored and treated and many people can be helped. People are treated and cared for remotely and this is what some people need in the crisis the world has been through like COVID-19. This epidemic is caused by the …

Source Detection And Automatic Modulation Classification For Modern Antenna Array Processing, Jayakrishnan Vijayamohanan

Electrical and Computer Engineering ETDs

Source detection and automatic modulation classification are two of the most important steps in any array processing task. In this research a novel deep learning model referred to as RadioNet, is proposed that is focused on solving both these problems by reformulating them as a multi-label classification problem. Traditional approaches to both these topics face challenges in scenarios with noise, interference, fewer number of snapshots, and high number of sources. The limitations of the conventional models are investigated and overcome by the proposed solution. RadioNet is also compared with other existing state-of-the-art machine learning based solutions. The introduced model is …

Integrating Image Data Fusion And Resnet Method For Accurate Fish Freshness Classification, Yahya Layth Khaleel, Mustafa Abdulfattah Habeeb, Ghadeer Ghazi Shayea

Iraqi Journal for Computer Science and Mathematics

Fish freshness classification is critical for protecting public health and ensuring efficient economic, regulatory and environmental sustainability. Classifying accurately reduces the risk of foodborne illness, protects product quality, builds consumer trust and supports sustainable resource conservation through waste minimization. However, the traditional methods for determining fish freshness are variable, time consuming and subjective, precluding practical use. This research presents an improved framework that integrates image data fusion and a deep learning ResNet model to differentiate fresh and nonfresh fish. From multiple sources, a comprehensive dataset including 16,640 samples was curated, and data fusion was used to increase the diversity and …

Enhanced Wind Velocity Imputation Near Building Structures Using Advanced Machine Learning Techniques, Istiak Ahammed, Sujeen Song, Gang Hu, Jinwoo An, Bubryur Kim

Civil Engineering Faculty Publications

The evaluation of instantaneous wind flow patterns nearest to building architecture is crucial to ensuring structural stability, architectural integrity, and pedestrian safety. Particle image velocimetry (PIV), a technique for studying fluid flow by tracing particles, provides accurate predictions of instantaneous wind velocities (IWV). However, PIV encounters challenges in specific regions due to laser light-based experimentation, leading to missing data. Consequently, investigating the wind circulation pattern around buildings becomes more challenging. Numerous ML techniques have been employed to impute missing wind velocities at random building locations with minimal structural impact. This paper focuses on addressing this concern by utilizing a machine …

Deep Learning For Bitcoin Price Direction Prediction: Models And Trading Strategies Empirically Compared, Oluwadamilare Omole, David Enke

Engineering Management and Systems Engineering Faculty Research & Creative Works

This paper applies deep learning models to predict Bitcoin price directions and the subsequent profitability of trading strategies based on these predictions. The study compares the performance of the convolutional neural network–long short-term memory (CNN–LSTM), long- and short-term time-series network, temporal convolutional network, and ARIMA (benchmark) models for predicting Bitcoin prices using on-chain data. Feature-selection methods—i.e., Boruta, genetic algorithm, and light gradient boosting machine—are applied to address the curse of dimensionality that could result from a large feature set. Results indicate that combining Boruta feature selection with the CNN–LSTM model consistently outperforms other combinations, achieving an accuracy of 82.44%. Three …

Dual-Channel Side Channel Attack: Improved Aes Key Decryption By Combining Power And Electromagnetic Side Channels With Convolutional Neural Networks, Sean P. O'Neill

Theses and Dissertations

This research introduces a novel DL approach for SCA that combines power consumption and EM signals to enhance encryption key deduction by leveraging a dual-channel CNN architecture. A new dataset, consisting of simultaneous power and EM signal collections during 128-bitAES encryption, was developed to train and evaluate the model’s effectiveness. The combined approach achieved an 88% reduction in traces needed, from 50 traces to 6, for encryption key classification, outperforming traditional methods such as random forest, DPA, DEMA,and individual side channel CNN models. These findings highlight the potential of integrating multiple side channels in SCA to improve performance without the …

Causal Discovery In Time Series Data Using Deep Learning Techniques, Saima Zahin Farhana Absar

Graduate Theses and Dissertations

Causal structure learning from observational data has been an active field of research over the past decades. In the literature, different algorithms and models have been proposed, such as constrained-based methods and score-based methods including the emerging deep learning-based methods. However, most of the approaches apply to static and non-dynamic data only. In many applications, the data is temporal. For example, monitoring systems, weather surveillance systems, and stock data, to name but a few. Incorporating temporal information is an important extension of the causal discovery field. With the growth of observational data these days, the discovery of causal relationships from …

Neural Operator And Physics-Informed Deep Learning Approaches For Inverse Design Of Composites And Manufacturing Processes, Minglei Lu

All Dissertations

In this dissertation, artificial intelligence (AI) models are designed and used to accelerate inverse design of composites and manufacturing processes. The critical bottlenecks in machine learning (ML) including data availability, data quality, model generalization and adaptation, interpretability, physical consistency, and the ’black box’ nature of models for the inverse design are addressed. And the proposed AI models are tested under different engineering scenarios. Firstly, a fast deep neural operator (DNO) structure was developed to significantly reduce training time. This model was tested in the context of additive manufacturing, a transformative industrial technology that allows for the creation of materials with …

Not All Samples Are Created Equal: Task-Aware Informative Sampling And Adaptive Inference For Efficient Edge Ai, Rebati Gaire

School of Computing: Dissertations, Theses, and Student Research

The rapid proliferation of Internet of Things (IoT) devices has resulted in an unprecedented influx of data generated at the edge by billions of sensors. Traditional approaches relying on cloud-based processing are increasingly inadequate due to constraints in bandwidth, latency, and privacy. Edge computing has emerged as a transformative paradigm, enabling real-time data processing and decision-making by decentralizing computation to the edge. While the integration of deep learning into edge environments—termed edge intelligence—promises autonomous and personalized operations, it is hindered by challenges such as limited computational resources, energy constraints, and data redundancies.

This thesis addresses these challenges by presenting three …

Practical And Lightweight Defense Against Website Fingerprinting, Colman Mcguan, Chansu Yu, Kyoungwon Suh

Electrical and Computer Engineering Faculty Publications

Website fingerprinting is a passive network traffic analysis technique that enables an adversary to identify the website visited by a user despite encryption and the use of privacy services such as Tor. Several website fingerprinting defenses built on top of Tor have been proposed to guarantee a user's privacy by concealing trace features that are important to classification. However, some of the best defenses incur a high bandwidth and/or latency overhead. To combat this, new defenses have sought to be both lightweight - i.e., introduce a small amount of bandwidth overhead - and zero-delay to real network traffic. This work …

Aircraft Control, Collision Avoidance, And Remote Autonomy In Scenarios With Ground Radar Information, Jaron Charles Ellingson

Theses and Dissertations

Unmanned aircraft systems (UAS) have become integral to various modern applications, including package delivery, security, medicine, and recreation. The autonomous operation of UAS significantly enhances their utility by improving performance and reducing operator workload, enabling collaborative missions such as boundary detection, border protection, and target tracking. To ensure safe integration of UAS, more work needs to be done in the areas of control, estimation, collision avoidance, path planning, hardware implementation, and autonomous practices in general. For this dissertation we chose to focus on the critical areas of control, collision avoidance, and remote autonomy. Our research is motivated by the need …

Automated Fake News Detection System, Saja A. Al-Obaidi, Tuba Çağlıkantar

Iraqi Journal for Computer Science and Mathematics

Online news has been the majority of people’s information source in recent decades. However, a lot of the information that is accessible online is fake and sometimes even designed to mislead. It might be difficult for individuals to distinguish between certain false newspaper items and the real ones since they are so similar. Deep learning (DL) and machine learning (ML) models, among other automated false news detection (FND) techniques, are quickly becoming essential. A comparative study was conducted to analyze the performance of five prominent deep learning models across four distinct datasets, namely ISOT, FakeNewsNet, Dataset1, and Dataset2. Results indicated …

Fine And Intelligent Interpretation Of Key Geological Structures In The Metal Metallogenesis Of Coal Measures, Yang Yi, Zhao Jingtao, Li Wenyu, Shi Suzhen

Coal Geology & Exploration

Objective In order to identify the key geological structures in the metallogenic process of coal measures metal deposits, the Linxing block of Ordos Basin was taken as the research object. Based on the previous research results, geological data of the block, seismic and logging data, a geological model including tectonic volcanic activities and other events was constructed to analyze the key geological factors of deposit formation. Methods Firstly, based on the post-stack seismic data, the diffraction wave separation and imaging are realized by using the plane wave destruction filter technology, and the small-scale key geological information is extracted. Secondly, the …

Acoustic Velocity Inversion Based On Convolutional Autoencoder Embedded With Fourier Neural Operator, Li Chen, Zhao Haixia, Bai Zhaowei, Hao Yufan

Coal Geology & Exploration

Background Seismic wave inversion serves as an effective method for obtaining the characteristics of structures, lithology, and physical properties of subsurface media using the arrival times, amplitude, and waveforms of seismic waves. Seismic inversion methods based on wave equations iteratively update model parameters using forward modeling. This generally involves extensive numerical simulations and optimization calculations, requiring large quantities of computational resources and time. In recent years, neural operators for deep learning, represented by the Fourier neural operator (FNO), have gained widespread attention. However, the original FNO structure fails to effectively learn the wavefield information with sharp changes in geological structures …

Intelligent Noise Suppression For 3d Post-Stack Seismic Data Of The Junggar Basin, Mao Haibo, Zhou Xin, Li Xiaofeng, Pan Long, Lin Juan, Liu Dawei, Wang Xiaokai

Coal Geology & Exploration

Objective The Junggar Basin is recognized as a significant petroliferous basin in China, and its hydrocarbon exploration targets have shifted to deeper strata. However, the 3D seismic data of this basin suffer from low signal-to-noise ratios (SNRs) and high data volumes due to the basin's complex near-surface conditions, the great depths of exploration targets, and seismic data acquisition methods characterized by wide azimuths, broadbands, and high density. This complicates the identification of hydrocarbon exploration targets, rendering the improvement in the quality of the 3D seismic data by noise suppression vitally important. Methods The progress in the deep learning theory and …

Transient Electromagnetic Numerical Simulation Based On The Transformer Neural Network, Wang Yunhong

Coal Geology & Exploration

Objective The deep learning-based transient electromagnetic (TEM) forward and inverse modeling methods are data-driven, requiring considerable numerical simulation results as supervisory data to train and assess neural networks. The conventional finite-difference time-domain (FDTD) method for TEM numerical simulation necessitates an iterative solution of time-domain Maxwell's equations. Therefore, this method is time-consuming and computationally intensive, failing to meet the data demand of deep learning-based TEM inversion. Methods This study introduced deep learning for TEM numerical simulation. Based on the transformer neural network architecture, a neural network for deep learning-based TEM numerical simulation was designed using an encoder-decoder structure. This neural network …

An Intelligent Identifying-While-Drilling Method For Geological Features Of Roof Strata In Coal Roadways Based On A 1dcnn-Bilstm-Cbam Model, Lei Zhiyong, Wang Jiawen, Fan Dong, Lu Feifei, Chen Weiming

Coal Geology & Exploration

Objective Most roof accidents in coal roadways occur in potential caving zones such as primary fissure-bearing zones and rock fracture zones. A significant approach to preventing roof accidents is to understand the geological features of roof strata in an accurate and timely manner and optimize support schemes and parameters of roofs. However, current methods for identifying the geological features of roof strata in roadways suffer from issues such as slow identification speeds, low efficiency, and high costs, thus failing to meet the demand for safe, efficient, and intelligent coal mining. Methods This study proposed a neural network model based on …

Developing Linguistic Patterns To Mitigate Inherent Human Bias In Offensive Language Detection, Toygar Tanyel, Besher Alkurdi, Serkan Ayvaz

Turkish Journal of Electrical Engineering and Computer Sciences

With the proliferation of social media, there has been a sharp increase in offensive content, particularly targeting vulnerable groups, exacerbating social problems such as hatred, racism, and sexism. Detecting offensive language use is crucial to prevent offensive language from being widely shared on social media. However, the accurate detection of irony, implication, and various forms of hate speech on social media remains a challenge. Natural language-based deep learning models require extensive training with large, comprehensive, and labeled datasets. Unfortunately, manually creating such datasets is both costly and error-prone. Additionally, the presence of human-bias in offensive language datasets is a major …

Designing Customized Loss Functions For Training Deep Neural Networks, Ali Pourramezan Fard

Electronic Theses and Dissertations

This dissertation explores the critical role of loss functions in enhancing the predictive performance of deep machine learning models. Loss functions are an integral element of all the ongoing advances we witness daily in this domain. I design custom loss functions and their impacts on various machine learning tasks, particularly in computer vision.

In the first stage of my research, I aim to improve the prediction performance of deep learning models by providing them with more precise feedback associated with task requirements. This led me to create the concept of assistive loss functions. My first proposed loss function, inspired by …

Strategies To Alleviate Flickering: Bayesian And Smoothing Methods For Deep Learning Classification In Video, Noah Miller, Glen Ryan Drumm, Lance Champagne, Bruce A. Cox, Trevor Bihl

Faculty Publications

Excerpt: Increasing reliance on autonomous systems requires confidence in the accuracies produced from computer vision classification algorithms. Computer vision (CV) for video classification provides phenomenal abilities, but it often suffers from “flickering” of results. Flickering occurs when the CV algorithm switches between declared classes over successive frames. Such behavior causes a loss of trust and confidence in their operations.

Impaired Speech Recognition Of Neurological Disorder Persons Using Machine Learning And Deep Learning Techniques, Vishnika Veni S

Theses and Dissertations

Speech Assistive Tools have emerged in recent years to support individuals with cognitive and neurological disorders in the field of assistive technology. People affected by neurological disorders such as autism, stroke, cerebral palsy, dysarthria, Parkinson’s disease, and brain injury often find it difficult to articulate desired sounds, resulting in impaired speech. As the population of impaired speakers continues to increase every year, there is a strong need to develop intelligent speech recognition systems for affected individuals. The primary objective of this research is to develop an Impaired Speech Recognition (ISR) system for the Tamil language. Word Recognition Accuracy (WRA) is …

Combined Machine Learning And Differential Evolution For Optimal Design Of Electric Aircraft Propulsion Motors, David R. Stewart, Matin Vatani, Rosemary E. Alden, Donovin D. Lewis, Pedram Asef, Dan M. Ionel

Electrical and Computer Engineering Graduate Research

Electric aircraft propulsion requires highly efficient and power-dense fault-tolerant electric motors optimized for specific flight profile operation. State-of-the-art design of electric motors involves substantial computational resources and combines electromagnetic finite element analysis (FEA) and optimization techniques. This paper proposes a new approach using a physics-based machine learning (ML) multi-input univariate meta-model trained on FEA and differential evolution (DE) optimization results to predict electromagnetic torque output. Hundreds of individual designs, generated through multiple generations of a DE algorithm, are analyzed by 3D FEA to create a database, which is then employed for the training and satisfactory validation of the ML model. …

Search Technology For Aircraft Debris Integrating Data Augmentation And Deep Learning Algorithm, Zhe Yang, Yinghan Cui, Lingxi Guo, Jiaxin Li, Xusheng Wu

Journal of System Simulation

Abstract: The reliable recovery of aircraft debris is of great significance for the complete acquisition of flight test data and the subsequent research and development of models. To ensure the safety of flight tests,the landing area of aircraft experiments is generally an unmanned area,and the actual landing point of the aircraft often deviates from the theoretical landing point. The characteristics of the debris target are complex and the dispersion area is large, making it difficult to search for aircraft debris solely by manpower. Aiming at the difficult problem of aircraft debris recovery in the landing area, through on UAV platforms …

M3t-Lm: A Multi-Modal Multi-Task Learning Model For Jointly Predicting Patient Length Of Stay And Mortality, Junde Chen, Qing Li, Feng Liu, Yuxin Wen

Engineering Faculty Articles and Research

Ensuring accurate predictions of inpatient length of stay (LoS) and mortality rates is essential for enhancing hospital service efficiency, particularly in light of the constraints posed by limited healthcare resources. Integrative analysis of heterogeneous clinic record data from different sources can hold great promise for improving the prognosis and diagnosis level of LoS and mortality. Currently, most existing studies solely focus on single data modality or tend to single-task learning, i.e., training LoS and mortality tasks separately. This limits the utilization of available multi-modal data and prevents the sharing of feature representations that could capture correlations between different tasks, ultimately …

Targeted Weed Management Of Palmer Amaranth Using Robotics And Deep Learning (Yolov7), Amlan Balabantaray, Shaswati Behera, Cheetown Liew, Nipuna Chamara, Mandeep Singh, Amit J. Jhala, Santosh Pitla

Department of Agricultural and Biological Systems Engineering: Faculty Publications

Effective weed management is a significant challenge in agronomic crops which necessitates innovative solutions to reduce negative environmental impacts and minimize crop damage. Traditional methods often rely on indiscriminate herbicide application, which lacks precision and sustainability. To address this critical need, this study demonstrated an AI-enabled robotic system, Weeding robot, designed for targeted weed management. Palmer amaranth (Amaranthus palmeri S. Watson) was selected as it is the most troublesome weed in Nebraska. We developed the full stack (vision, hardware, software, robotic platform, and AI model) for precision spraying using YOLOv7, a state-of-the-art object detection deep learning technique. The …

A Neural Network-Based Method For Analyzing Diffracted Wave Velocity, Tao Junhong, Zhao Jingtao, Sheng Tongjie

Coal Geology & Exploration

Background In seismic imaging, accurate velocity models are crucial for characterizing subsurface structures in a fine-scale manner. Notably, in coal mining, small-scale geological structures like faults and collapse columns are closely associated with mining accidents. These structures typically occur as diffracted waves in seismograms.Objective and Methods To effectively image these small-scale geological bodies, fine-scale velocity modeling using diffracted wave information is particularly important. Hence, this study proposed a neural network-based method for analyzing diffracted-wave velocity. First, diffracted-wave velocity spectra were generated using the gathers of diffracted waves that were separated in the common virtual source domain. Second, a gamma-ray …

A Global Model-Agnostic Rule-Based Xai Method Based On Parameterized Event Primitives For Time Series Classifiers, Ephrem T. Mekonnen, Luca Longo, Pierpaolo Dondio

Articles

Time series classification is a challenging research area where machine learning and deep learning techniques have shown remarkable performance. However, often, these are seen as black boxes due to their minimal interpretability. On the one hand, there is a plethora of eXplainable AI (XAI) methods designed to elucidate the functioning of models trained on image and tabular data. On the other hand, adapting these methods to explain deep learning-based time series classifiers may not be straightforward due to the temporal nature of time series data. This research proposes a novel global post-hoc explainable method for unearthing the key time steps …

Development Of Message Passing-Based Graph Convolutional Networks For Classifying Cancer Pathology Reports, Hong Jun Yoon, Hilda B. Klasky, Andrew E Blanchard, J. Blair Christian, Eric B Durbin, Xiao Cheng Wu, Antoinette Stroup, Jennifer Doherty, Linda Coyle, Lynne Penberthy, Georgia D Tourassi

School of Public Health Faculty Publications

Background: Applying graph convolutional networks (GCN) to the classification of free-form natural language texts leveraged by graph-of-words features (TextGCN) was studied and confirmed to be an effective means of describing complex natural language texts. However, the text classification models based on the TextGCN possess weaknesses in terms of memory consumption and model dissemination and distribution. In this paper, we present a fast message passing network (FastMPN), implementing a GCN with message passing architecture that provides versatility and flexibility by allowing trainable node embedding and edge weights, helping the GCN model find the better solution. We applied the FastMPN model to …

A Multimodal Residual Spatial-Temporal Fusion Model Based On Automatic Sleep Classification, Yecai Guo, Shuang Tong

Journal of System Simulation

Abstract: Highly accurate sleep staging plays a crucial role in correctly assessing sleep conditions. Aiming at the problem that the existing convolutional network cannot obtain the topological characteristics of physiological signals, a sleep staging algorithm based on multi-modal residual spatio-temporal fusion is proposed. Time-frequency images and spatio-temporal images are obtained using short-time Fourier transform and adaptive map convolution, which are converted into high-dimensional feature vectors; lightweight interaction of feature information flow is realized through time-frequency feature and spatiotemporal feature extraction modules; the feature enhancement fusion module fuses feature information to outputs sleep staging results. The results show that the model …