Engineering Commons^™

Missing Value Imputation For Single Omics And Multi-Omics Data, Meng Song

Dissertations

The integration analyses of multi-omics data have the advantages of extending our understanding of biological system across multiple omics layers, unraveling the functional mechanism of complex disease development, and refining the discovery of novel drug targets. However, multi-omics studies often face challenges such as data heterogeneity, missing values problem, interpretability, and imbalance classes. Among these challenges, the missing values problem is a critical issue for large cohort studies as not all samples will get a complete measurement for all the omics layers. To address the problem of missing values in multi-omics data, I focused on the imputation of completely missing …

Improved Burned Area Mapping Using Monotemporal Landsat-9 Imagery And Convolutional Shift-Transformer, Seyd Teymoor Seydi, Mojtaba Sadegh

Civil Engineering Faculty Publications and Presentations

Satellite imagery, specifically Landsat, have been widely used for mapping and monitoring wildfire burned areas. The new Landsat-9 satellite – with higher radiometric resolution compared to its predecessors, and improved temporal resolution when combined with Landsat-8 (∼8 days) – enables a wide range of applications, particularly burned area mapping (BAM). We propose a novel deep learning BAM model that leverages the strengths of the convolutional layers for deep feature generation from Landsat-9 imagery and shift-transformer block for burned area classification. The performance of the model is evaluated in five large fire case studies across the globe. BAM results are also …

Distributed Deep Learning Optimization Of Heat Equation Inverse Problem Solvers, Zhuowei Wang, Le Yang, Haoran Lin, Genping Zhao, Zixuan Liu, Xiaoyu Song

Electrical and Computer Engineering Faculty Publications and Presentations

The inversion problem of partial differential equation plays a crucial role in cyber-physical systems applications. This paper presents a novel deep learning optimization approach to constructing a solver of heat equation inversion. To improve the computational efficiency in large-scale industrial applications, data and model parallelisms are incorporated on a platform of multiple GPUs. The advanced Ring-AllReduce architecture is harnessed to achieve an acceleration ratio of 3.46. Then a new multi-GPUs distributed optimization method GradReduce is proposed based on Ring-AllReduce architecture. This method optimizes the original data communication mechanism based on mechanical time and frequency by introducing the gradient transmission scheme …

Learning Deep Time-Index Models For Time Series Forecasting, Jiale Gerald Woo, Chenghao Liu, Doyen Sahoo, Akshat Kumar, Steven Hoi

Research Collection School Of Computing and Information Systems

Deep learning has been actively applied to time series forecasting, leading to a deluge of new methods, belonging to the class of historicalvalue models. Yet, despite the attractive properties of time-index models, such as being able to model the continuous nature of underlying time series dynamics, little attention has been given to them. Indeed, while naive deep timeindex models are far more expressive than the manually predefined function representations of classical time-index models, they are inadequate for forecasting, being unable to generalize to unseen time steps due to the lack of inductive bias. In this paper, we propose DeepTime, a …

Lightweight Deep Neural Network Models For Electromyography Signal Recognition For Prosthetic Control, Ahmet Mert

Turkish Journal of Electrical Engineering and Computer Sciences

In this paper, lightweight deep learning methods are proposed to recognize multichannel electromyography (EMG) signals against varying contraction levels. The classical machine learning, and signal processing methods namely, linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), root mean square (RMS), and waveform length (WL) are adopted to convolutional neural network (CNN), and long short-term memory neural network (LSTM). Eight-channel recordings of nine amputees from a publicly available dataset are used for training and testing the proposed models considering prosthetic control strategies. Six class hand movements with three contraction levels are applied to WL and RMS-based feature extraction. After that, they …

Improving Unet Segmentation Performance Using An Ensemble Model In Images Containing Railway Lines, Mehmet Sevi̇, İlhan Aydin

Turkish Journal of Electrical Engineering and Computer Sciences

This study aims to make sense of the autonomous system and the railway environment for railway vehicles. For this purpose, by determining the railway line, information about the general condition of the line can be obtained along the way. In addition, objects such as pedestrian crossings, people, cars, and traffic signs on the line will be extracted. The rails and the rail environment in the images will be segmented with a semantic segmentation network. In order to ensure the safety of rail transport, computer vision, and deep learning-based methods are increasingly used to inspect railway tracks and surrounding objects. In …

Mine Water Inrush Prediction Method Based On Vmd-Dbn Model, Liu Hui, Liu Guiqin, Ning Dianyan, Fan Juan, Chen Weiming

Coal Geology & Exploration

In the process of coal mining, the loss of people and property caused by mine water inrush is extremely serious. To prevent the occurrence of water inrush accidents and grasp the law of change of water inrush, the water inrush prediction and forecasting, especially the accurate estimation of mine water inrush, is very important, which is also an important task in the prevention and control of mine water damage. To increase the prediction accuracy of mine water inrush, an efficient time series prediction model combining Variational Mode Decomposition (VMD) and Deep Belief Network (DBN) was proposed for the series of …

Terrain Characterization Via Machine Vs. Deep Learning Using Remote Sensing, Jordan Ewing, Thomas Oommen, Jobin Thomas, Anush Kasaragod, Richard Dobson, Colin Brooks, Paramsothy Jayakumar, Michael Cole, Tulga Ersal

Michigan Tech Publications, Part 1

Terrain traversability is critical for developing Go/No-Go maps for ground vehicles, which significantly impact a mission’s success. To predict the mobility of terrain, one must understand the soil characteristics. In-situ measurements performed in the field are the current method of collecting this information, which is time-consuming, costly, and can be lethal for military operations. This paper investigates an alternative approach using thermal, multispectral, and hyperspectral remote sensing from an unmanned aerial vehicle (UAV) platform. Remotely sensed data combined with machine learning (linear, ridge, lasso, partial least squares (PLS), support vector machines (SVM), and k nearest neighbors (KNN)) and deep learning …

Patient Movement Monitoring Based On Imu And Deep Learning, Mohsen Sharifi Renani

Electronic Theses and Dissertations

Osteoarthritis (OA) is the leading cause of disability among the aging population in the United States and is frequently treated by replacing deteriorated joints with metal and plastic components. Developing better quantitative measures of movement quality to track patients longitudinally in their own homes would enable personalized treatment plans and hasten the advancement of promising new interventions. Wearable sensors and machine learning used to quantify patient movement could revolutionize the diagnosis and treatment of movement disorders. The purpose of this dissertation was to overcome technical challenges associated with the use of wearable sensors, specifically Inertial Measurement Units (IMUs), as a …

Classification Of Arabic Social Media Texts Based On A Deep Learning Multi-Tasks Model, Ali A. Jalil, Ahmed H. Aliwy

Al-Bahir

The proliferation of social networking sites and their user base has led to an exponential increase in the amount of data generated on a daily basis. Textual content is one type of data that is commonly found on these platforms, and it has been shown to have a significant impact on decision-making processes at the individual, group, and national levels. One of the most important and largest part of this data are the texts that express human intentions, feelings and condition. Understanding these texts is one of the biggest challenges that facing data analysis. It is the backbone for understanding …

Long-Term Human Video Activity Quantification In Collaborative Learning Environments, Venkatesh Jatla

Electrical and Computer Engineering ETDs

Research on video activity detection has mainly focused on identifying well-defined human activities in short video segments, often requiring large-parameter systems and extensive training datasets. This dissertation introduces a low-parameter, modular system with rapid inference capabilities, capable of being trained on limited datasets without transfer learning from large-parameter systems. The system accurately detects specific activities and associates them with students in real-life classroom videos. Additionally, an interactive web-based application is developed to visualize human activity maps over long classroom videos.

Long-term video activity detection in classrooms presents challenges, such as multiple simultaneous activities, rapid transitions, long-term occlusions, duration exceeding 15 …

Research On Road Crack Recognition Model Based On Yolo V3 Deep Learning Algorithm, Su Weiguo, Wang Jingxiao

Journal of China & Foreign Highway

To address the challenges of manual intervention in road crack detection and the inaccuracy of traditional recognition algorithms, this paper proposes a road crack recognition method based on the YOLO v3 deep learning algorithm. The dataset images were first resized to 416×416 pixels. Labelme was then used to annotate cracks in the images and convert the boundary box location information. Finally, the YOLO v3 algorithm framework was employed for model training. The results show that the YOLO v3 algorithm achieves precision, recall, and F1 scores above 95%, with an image detection speed of 0.123 seconds per image. The YOLO v3 …

Detection Method Of Rural Road Pavement Damage Based On Smart Phone, Zhang Yang, He Li, Tang Qingzhou, Zhang Dejin

Journal of China & Foreign Highway

Automatic detection of rural road pavement damage is a critical prerequisite for scientific maintenance. To address issues such as high false detection rates, missed detection, and the inability to quantify damage when using smartphones for pavement damage detection, this paper proposes a novel detection method. The proposed method involves using a smartphone to capture pavement images. A region of interest is first selected in the image, followed by weighted least-squares filtering, Canny edge detection, and Hough transform line detection to identify the pavement, minimizing environmental interference and reducing false detection rates. Perspective transformation is then applied to the pavement region …

Detection Of Crypto-Ransomware Attack Using Deep Learning, Muna Jemal

Master of Science in Computer Science Theses

The number one threat to the digital world is the exponential increase in ransomware attacks. Ransomware is malware that prevents victims from accessing their resources by locking or encrypting the data until a ransom is paid. With individuals and businesses growing dependencies on technology and the Internet, researchers in the cyber security field are looking for different measures to prevent malicious attackers from having a successful campaign. A new ransomware variant is being introduced daily, thus behavior-based analysis of detecting ransomware attacks is more effective than the traditional static analysis. This paper proposes a multi-variant classification to detect ransomware I/O …

Deep Learning Of Semantic Image Labels On Hdr Imagery In A Maritime Environment, Charles Montagnoli

Doctoral Dissertations and Master's Theses

Situational awareness in the maritime environment can be extremely challenging. The maritime environment is highly dynamic and largely undefined, requiring the perception of many potential hazards in the shared maritime environment. One particular challenge is the effect of direct-sunlight exposure and specular reflection causing degradation of camera reliability. It is for this reason then, in this work, the use of High-Dynamic Range imagery for deep learning of semantic image labels is studied in a littoral environment. This study theorizes that the use HDR imagery may be extremely beneficial for the purpose of situational awareness in maritime environments due to the …

Modeling And Control Strategies For A Two-Wheel Balancing Mobile Robot, John Alan Moritz

Graduate Theses and Dissertations

The problem of balancing and autonomously navigating a two-wheel mobile robot is an increasingly active area of research, due to its potential applications in last-mile delivery, pedestrian transportation, warehouse automation, parts supply, agriculture, surveillance, and monitoring. This thesis investigates the design and control of a two-wheel balancing mobile robot using three different control strategies: Proportional Integral Derivative (PID) controllers, Sliding Mode Control, and Deep Q-Learning methodology. The mobile robot is modeled using a dynamic and kinematic model, and its motion is simulated in a custom MATLAB/Simulink environment. The first part of the thesis focuses on developing a dynamic and kinematic …

Task Offloading And Resource Allocation Based On Dl-Ga In Mobile Edge Computing, Hang Gu, Minjuan Zhang, Wenzao Li, Yuwen Pan

Turkish Journal of Electrical Engineering and Computer Sciences

With the rapid development of 5G and the Internet of Things (IoT), the traditional cloud computing architecture struggle to support the booming computation-intensive and latency-sensitive applications. Mobile edge computing (MEC) has emerged as a solution which enables abundant IoT tasks to be offloaded to edge services. However, task offloading and resource allocation remain challenges in MEC framework. In this paper, we add the total number of offloaded tasks to the optimization objective and apply algorithm called Deep Learning Trained by Genetic Algorithm (DL-GA) to maximize the value function, which is defined as a weighted sum of energy consumption, latency, and …

Wearable Sensor Gait Analysis For Fall Detection Using Deep Learning Methods, Haben Girmay Yhdego

Electrical & Computer Engineering Theses & Dissertations

World Health Organization (WHO) data show that around 684,000 people die from falls yearly, making it the second-highest mortality rate after traffic accidents [1]. Early detection of falls, followed by pneumatic protection, is one of the most effective means of ensuring the safety of the elderly. In light of the recent widespread adoption of wearable sensors, it has become increasingly critical that fall detection models are developed that can effectively process large and sequential sensor signal data. Several researchers have recently developed fall detection algorithms based on wearable sensor data. However, real-time fall detection remains challenging because of the wide …

A Long-Term Funds Predictor Based On Deep Learning, Shuiyi Kuang

Electronic Theses, Projects, and Dissertations

Numerous neural network models have been created to predict the rise or fall of stocks since deep learning has gained popularity, and many of them have performed quite well. However, since the share market is hugely influenced by various policy changes or unexpected news, it is challenging for investors to use such short-term predictions as a guide. In this paper, we try to find a suitable long-term predictor for the funds market by testing different kinds of neural network models, including the Long Short-Term Memory(LSTM) model with different layers, the Gated Recurrent Units(GRU) model with different layers, and the combination …

Enhanced Iot-Based Electrocardiogram Monitoring System With Deep Learning, Jian Ni

UNLV Theses, Dissertations, Professional Papers, and Capstones

Due to the rapid development of computing and sensing technologies, Internet of Things (IoT)-based cardiac monitoring plays a crucial role in providing patients with cost-efficient solutions for long-term, continuous, and pervasive electrocardiogram (ECG) monitoring outside a hospital setting. In a typical IoT-based ECG monitoring system, ECG signals are picked up by sensors located on the edge, and then uploaded to the remote cloud servers. ECG interpretation is performed for the collected ECGs in the cloud servers and the analysis results can be made instantly available to the patients as well as their healthcare providers.In this dissertation, we first examine the …

An Efficient Deep Learning Architecture For Turkish Lira Recognition And Counterfeit Detection, Burak İyi̇kesi̇ci̇, Ergun Erçelebi̇

Turkish Journal of Electrical Engineering and Computer Sciences

Banknote counterfeiting is a common practice worldwide. Due to the recent developments in technology, banknote imitation has become easier than before. There are different kinds of algorithms developed for the detection of counterfeit banknotes for different countries in the literature. The earlier algorithms utilized classical image processing techniques where the implementations of machine learning and deep learning algorithms appeared with the developments in the artificial intelligence field as well as the computer hardware. In this study, a novel convolutional neural networks-based deep learning algorithm has been developed that detects counterfeit Turkish Lira banknotes and their denominations using the banknote images …

Spatiotemporal Prediction Of Microstructure Evolution With Predictive Recurrent Neural Network, Amir Abbas Kazemzadeh Farizhandi, Mahmood Mamivand

Mechanical and Biomedical Engineering Faculty Publications and Presentations

Prediction of microstructure evolution during material processing is essential to control the material properties. Simulation tools for microstructure evolution prediction based on physical concepts are computationally expensive and time-consuming. Therefore, they are not practical when either there is an urgent need for microstructure morphology during the process or there is a need to generate big microstructure datasets. Essentially, microstructure evolution prediction is a spatiotemporal sequence prediction problem, where the prediction of material microstructure is difficult due to different process histories and chemistry. We propose a Predictive Recurrent Neural Network (PredRNN) model for the microstructure prediction, which extends the inner-layer transition …

Transfer Learning, Model Interpretation, And Dataset Bias Analysis For Automated Violence Detection From Video, Erik Clemens

Master's Theses (2009 -)

Many communities have installed surveillance cameras in an effort to deter and respond to violence.Due to the difficulty of constantly monitoring such camera feeds, these systems are rarely used to provide real-time information. To enable rapid alerts and information for first responders, this thesis develops a proof-of-concept system capable of automatically detecting violence from video footage. This system is developed by fine-tuning a convolutional neural network that has previously demonstrated success on general action recognition tasks. This thesis explores two new techniques to improve the accuracy of the fine-tuned model. The first is a data augmentation technique that generates aspect …

Utilizing Deep Learning Methods In The Identification And Synthesis Of Gene Regulations, Jiandong Wang

Theses and Dissertations

Gene expression is the fundamental differentiation and development process of life. Although all cells in an organism have essentially the same DNA, cell types and activities vary due to changes in gene expression. Gene expression can be influenced by many gene regulations. RNA editing contributes to the variety of RNA and proteins by allowing single nucleotide substitution. Reverse transcription can alter the expression status of genes by inducing genetic diversity and polymorphism via novel insertions, deletions, and recombination events. Gene regulation is critical to normal development because it enables cells to respond rapidly to environmental changes. However, identifying gene regulations …

Computer Vision Aided Hotspot Creation In Virtual Environments, Lama A. Affara, Bilal E. Nakhal

Architecture and Planning Journal (APJ)

Hotspot creation is one of the most important modules within virtual environments which helps show the navigators of these environments some information about semantic elements within it and facilitate the navigation between the virtual spaces. In this paper, a system for automatic hotspot proposals and creation in virtual environments is proposed. The system uses computer vision modules to automatically propose hotspot locations in addition to identifying and creating these hotspots with candidate labels. Two main modules used in the system are object detection and scene segmentation. The scene segmentation helps give candidate hotspot areas and provides an overall understanding of …

Using Deep Learning To Generate Front And Backyards In Landscape Architecture, Mehmet O. Senem, Mustafa Koç, Hayriye E. Tunçay, İmdat As

Architecture and Planning Journal (APJ)

The use of artificial intelligence (AI) engines in the design disciplines is a nascent field of research, which became very popular over the last decade. In particular, deep learning (DL) and related generative adversarial networks (GANs) proved to be very promising. While there are many research projects exploring AI in architecture and urban planning, e.g., in order to generate optimal floor layouts, massing models, evaluate image quality, etc., there are not many research projects in the area of landscape architecture - in particular the design of two-dimensional garden layouts. In this paper, we present our work using GANs to generate …

Characterizing Location-Based Electromagnetic Leakage Of Computing Devices Using Convolutional Neural Networks To Increase The Effectiveness Of Side-Channel Analysis Attacks, Ian C. Heffron

Theses and Dissertations

SCA attacks aim to recover some sort of secret information, often in the form of a cipher key, from a target device. Some of these attacks focus on either power-based leakage, or EM-based leakage. Neural networks have recently gained in popularity as tools in SCA attacks. Near-field EM probes with high-spatial resolution enable attackers to isolate physical locations above a processor. This enables attackers to exploit the spatial dependencies of algorithms running on said processor. These spatial dependencies result in different physical locations above a chip emanating different signal strengths. The strengths of different locations can be mapped using the …

Tempnet – Temporal Super-Resolution Of Radar Rainfall Products With Residual Cnns, Muhammed Ali Sit, Bongchul Seo, Ibrahim Demir

Civil, Architectural and Environmental Engineering Faculty Research & Creative Works

The temporal and spatial resolution of rainfall data is crucial for environmental modeling studies in which its variability in space and time is considered as a primary factor. Rainfall products from different remote sensing instruments (e.g., radar, satellite) have different space-time resolutions because of the differences in their sensing capabilities and post-processing methods. In this study, we developed a deep-learning approach that augments rainfall data with increased time resolutions to complement relatively lower-resolution products. We propose a neural network architecture based on Convolutional Neural Networks (CNNs), namely TempNet, to improve the temporal resolution of radar-based rainfall products and compare the …

Inducing Sparsity Within High-Dimensional Remote Sensing Modalities For Lightning Prediction, Grace E. Metzgar

Theses and Dissertations

The uncertainty of lightning constantly threatens many weather-sensitive fields where the slightest presence of lightning can endanger valuable personnel and assets. The consequences of delaying operations have incited the research of methods that can accurately predict the location of future lightning strikes from the current weather conditions. High-dimensional remote sensing modalities contain information capable of detecting significant patterns and intensities within storms that could indicate the presence of lightning. This thesis induces sparsity into convolutional neural networks (CNNs) and remote sensing modalities through a combination of regularization and tensor decomposition techniques to call attention to sparse features that are most …

3d Point Cloud Classification With Acgan-3d And Vacwgan-Gp, Onur Ergün, Yusuf Sahi̇lli̇oğlu

Turkish Journal of Electrical Engineering and Computer Sciences

Machine learning and deep learning techniques are widely used to make sense of 3D point cloud data which became ubiquitous and important due to the recent advances in 3D scanning technologies and other sensors. In this work, we propose two networks to predict the class of the input 3D point cloud: 3D Auxiliary Classifier Generative Adversarial Network (ACGAN-3D) and Versatile Auxiliary Conditional Wasserstein Generative Adversarial Network with Gradient Penalty (VACWGAN-GP). Unlike other classifiers, we are able to enlarge the limited data set with the data produced by generative models. We consequently aim to increase the success of the model by …