Noise2clean: Cross-Device Side-Channel Traces Denoising With Unsupervised Deep Learning, Honggang Yu, Mei Wang, Xiyu Song, Haoqi Shan, Hongbing Qiu, Junyi Wang, Kaichen Yang

Michigan Tech Publications, Part 1

Deep learning (DL)-based side-channel analysis (SCA) has posed a severe challenge to the security and privacy of embedded devices. During its execution, an attacker exploits physical SCA leakages collected from profiling devices to create a DL model for recovering secret information from victim devices. Despite this success, recent works have demonstrated that certain countermeasures, such as random delay interrupts or clock jitters, would make these attacks more complex and less practical in real-world scenarios. To address this challenge, we present a novel denoising scheme that exploits the U-Net model to pre-process SCA traces for “noises” (i.e., countermeasures) removal. Specifically, we …

A Bidirectional Deep Lstm Machine Learning Method For Flight Delay Modelling And Analysis, Desmond B. Bisandu, Irene Moulitsas

National Training Aircraft Symposium (NTAS)

Flight delays can be prevented by providing a reference point from an accurate prediction model because predicting flight delays is a problem with a specific space. Only a few algorithms consider predicted classes' mutual correlation during flight delay classification or prediction modelling tasks. None of these existing methods works for all scenarios. Therefore, the need to investigate the performance of more models in solving the problem of flight delay is vast and rapidly increasing. This paper presents the development and evaluation of LSTM and BiLSTM models by comparing them for a flight delay prediction. The LSTM does the feature extraction …

Modulation Recognition Method Of Mixed Signal Based On Intelligent Analysis Of Cyclic Spectrum Section, Yu Du, Xinquan Yang, Jianhua Zhang, Suchun Yuan, Huachao Xiao, Jingjing Yuan

Journal of System Simulation

Abstract: Aiming at the problems of low intelligence and poor adaptability for the existing mixed signal recognition methods, an intelligent recognition method based on cyclic spectral cross section and deep learning is proposed. For common mixed communication signals, the characteristics of zero frequency cross section of cyclic spectrum are theoretically deduced and analyzed. Two new pre-processing methods, nonlinear segmental mapping and directional pseudo-clustering are proposed, which can effectively improve the adaptability and consistency of cross section features. The pre-processed feature graph is combined with the residual network (ResNet), and the deep learning network is used to mine and analyze the …

Research On Intelligent Prediction Method Of Wargaming Air Mission, Dayong Zhang, Jingyu Yang, Xi Wu

Journal of System Simulation

Abstract: The efficient, accurate and automatic judgment of the combat mission or intention of the enemy's air targets in the battlefield is the basis of situation awareness and the key to the allocation of auxiliary combat resources. Combined with the calculation characteristics of feed forward deep neural network and long-term and short-term memory network model, two targeted basic index learners are designed, and then the weighted combination is carried out according to the cross entropy of the basic index, which can be used to further train the evaluation index of the learner. It can not only effectively prevent the model …

Deep Transfer Learning For Approximate Model Predictive Control, Samuel Arce Munoz, Junho Park, Cristina M. Stewart, Adam M. Martin, John Hedengren

Faculty Publications

Transfer learning is a machine learning technique that takes a pre-trained model that has already been trained on a related task, and adapts it for use on a new, related task. This is particularly useful in the context of model predictive control (MPC), where deep transfer learning is used to improve the training of the MPC by leveraging the knowledge gained from related controllers. One way in which transfer learning is applied in the context of MPC is by using a pre-trained deep learning model of the MPC, and then fine-tuning the controller training for a new process automation task. …

Encryption And Compression Classification Of Internet Of Things Traffic, Mariam Najdat M Saleh

Browse all Theses and Dissertations

The Internet of Things (IoT) is used in many fields that generate sensitive data, such as healthcare and surveillance. Increased reliance on IoT raised serious information security concerns. This dissertation presents three systems for analyzing and classifying IoT traffic using Deep Learning (DL) models, and a large dataset is built for systems training and evaluation. The first system studies the effect of combining raw data and engineered features to optimize the classification of encrypted and compressed IoT traffic using Engineered Features Classification (EFC), Raw Data Classification (RDC), and combined Raw Data and Engineered Features Classification (RDEFC) approaches. Our results demonstrate …

A Deep Bilstm Machine Learning Method For Flight Delay Prediction Classification, Desmond B. Bisandu, Irene Moulitsas

Journal of Aviation/Aerospace Education & Research

This paper proposes a classification approach for flight delays using Bidirectional Long Short-Term Memory (BiLSTM) and Long Short-Term Memory (LSTM) models. Flight delays are a major issue in the airline industry, causing inconvenience to passengers and financial losses to airlines. The BiLSTM and LSTM models, powerful deep learning techniques, have shown promising results in a classification task. In this study, we collected a dataset from the United States (US) Bureau of Transportation Statistics (BTS) of flight on-time performance information and used it to train and test the BiLSTM and LSTM models. We set three criteria for selecting highly important features …

Aerial Lidar-Based 3d Object Detection And Tracking For Traffic Monitoring, Baya Cherif, Hakim Ghazzai, Ahmad Alsharoa, Hichem Besbes, Yehia Massoud

Electrical and Computer Engineering Faculty Research & Creative Works

The proliferation of Light Detection and Ranging (LiDAR) technology in the automotive industry has quickly promoted its use in many emerging areas in smart cities and internet-of-things. Compared to other sensors, like cameras and radars, LiDAR provides up to 64 scanning channels, vertical and horizontal field of view, high precision, high detection range, and great performance under poor weather conditions. In this paper, we propose a novel aerial traffic monitoring solution based on Light Detection and Ranging (LiDAR) technology. By equipping unmanned aerial vehicles (UAVs) with a LiDAR sensor, we generate 3D point cloud data that can be used for …

Hardware-In-The-Loop And Digital Twin Enabled Autonomous Robotics-Assisted Environment Inspection, Johnny Li, Bo Shang, Iresh Jayawardana, Genda Chen

Civil, Architectural and Environmental Engineering Faculty Research & Creative Works

Empowered by the advanced 3D sensing, computer vision and AI algorithm, autonomous robotics provide an unprecedented possibility for close-up infrastructure environment inspection in an efficient and reliable fashion. Deep neural network (DNN) learning algorithms, pretrained on the large database can empower real-time object detection as well as fully autonomous, safe robotic navigation in unstructured environments while avoiding the potential obstacle. However, the development and deployment of the robots, inspection planning and operation procedures are still tedious and segmented with tremendous manual intervention during environmental inspection and anomaly monitoring. The proposed digital twin approach is able to provide a virtual representation …

Adversarial Training Of Deep Neural Networks, Anabetsy Termini

CCAC Theses and Dissertations

Deep neural networks used for image classification are highly susceptible to adversarial attacks. The de facto method to increase adversarial robustness is to train neural networks with a mixture of adversarial images and unperturbed images. However, this method leads to robust overfitting, where the network primarily learns to recognize one specific type of attack used to generate the images while remaining vulnerable to others after training. In this dissertation, we performed a rigorous study to understand whether combinations of state of the art data augmentation methods with Stochastic Weight Averaging improve adversarial robustness and diminish adversarial overfitting across a wide …

Efficient Training On Alzheimer’S Disease Diagnosis With Learnable Weighted Pooling For 3d Pet Brain Image Classification, Xin Xing, Muhammad Usman Rafique, Gongbo Liang, Hunter Blanton, Zu Zhang, Chris Wang, Nathan Jacobs, Ai-Ling Lin

Computer Science Faculty Publications (Archived)

Three-dimensional convolutional neural networks (3D CNNs) have been widely applied to analyze Alzheimer’s disease (AD) brain images for a better understanding of the disease progress or predicting the conversion from cognitively impaired (CU) or mild cognitive impairment status. It is well-known that training 3D-CNN is computationally expensive and with the potential of overfitting due to the small sample size available in the medical imaging field. Here we proposed a novel 3D-2D approach by converting a 3D brain image to a 2D fused image using a Learnable Weighted Pooling (LWP) method to improve efficient training and maintain comparable model performance. By …

Machine Learning Based Pcb/Package Stack-Up Optimization For Signal Integrity, Wenchang Huang, Jiahuan Huang, Minseok Kim, Bumhee Bae, Chulsoon Hwang, Subin Kim

Electrical and Computer Engineering Faculty Research & Creative Works

PCB/package stack-up design optimization is time-consuming and requiring a great deal of experience. Although some iterative optimization algorithms are applied to implement automatic stack-up design, evaluating the results of each iteration is still time-intensive. This paper proposes a combined Bayesian optimization-artificial neural network (BO-ANN) algorithm, utilizing a trained ANN-based surrogate model to replace a 2D cross-section analysis tool for fast PCB/package stack-up design optimization. With the acceleration of ANN, the proposed BO-ANN algorithm can finish 100 iterations in 40 seconds while achieving the target characteristic impedance. To better generalize the BO-ANN algorithm, a strategy of effective dielectric calculation is applied …

Cooperative Deep $Q$ -Learning Framework For Environments Providing Image Feedback, Krishnan Raghavan, Vignesh Narayanan, Sarangapani Jagannathan

Electrical and Computer Engineering Faculty Research & Creative Works

In This Article, We Address Two Key Challenges in Deep Reinforcement Learning (DRL) Setting, Sample Inefficiency and Slow Learning, with a Dual-Neural Network (NN)-Driven Learning Approach. in the Proposed Approach, We Use Two Deep NNs with Independent Initialization to Robustly Approximate the Action-Value Function in the Presence of Image Inputs. in Particular, We Develop a Temporal Difference (TD) Error-Driven Learning (EDL) Approach, Where We Introduce a Set of Linear Transformations of the TD Error to Directly Update the Parameters of Each Layer in the Deep NN. We Demonstrate Theoretically that the Cost Minimized by the EDL Regime is an Approximation …

Evaluation Of Different Machine Learning, Deep Learning And Text Processing Techniques For Hate Speech Detection, Nabil Shawkat

Graduate Theses/Dissertations

Social media has become a domain that involves a lot of hate speech. Some users feel entitled to engage in abusive conversations by sending abusive messages, tweets, or photos to other users. It is critical to detect hate speech and prevent innocent users from becoming victims. In this study, I explore the effectiveness and performance of various machine learning methods employing text processing techniques to create a robust system for hate speech identification. I assess the performance of Naïve Bayes, Support Vector Machines, Decision Trees, Random Forests, Logistic Regression, and K Nearest Neighbors using three distinct datasets sourced from social …

Machine Learning Models To Automate Radiotherapy Structure Name Standardization, Priyankar Bose

Theses and Dissertations

Structure name standardization is a critical problem in Radiotherapy planning systems to correctly identify the various Organs-at-Risk, Planning Target Volumes and `Other' organs for monitoring present and future medications. Physicians often label anatomical structure sets in Digital Imaging and Communications in Medicine (DICOM) images with nonstandard random names. Hence, the standardization of these names for the Organs at Risk (OARs), Planning Target Volumes (PTVs), and `Other' organs is a vital problem. Prior works considered traditional machine learning approaches on structure sets with moderate success. We compare both traditional methods and deep neural network-based approaches on the multimodal vision-language prostate cancer …

Machine Learning Assisted Framework For Advanced Subsurface Fracture Mapping And Well Interference Quantification, Mohammad Faiq Adenan

Graduate Theses, Dissertations, and Problem Reports (ETD)

The oil and gas industry has historically spent significant amount of capital to acquire large volumes of analog and digital data often left unused due to lack of digital awareness. It has instead relied on individual expertise and numerical modelling for reservoir development, characterization, and simulation, which is extremely time consuming and expensive and inevitably invites significant human bias and error into the equation. One of the major questions that has significant impact in unconventional reservoir development (e.g., completion design, production, and well spacing optimization), CO2 sequestration in geological formations (e.g., well and reservoir integrity), and engineered geothermal systems (e.g., …

Gated Deep Reinforcement Learning With Red Deer Optimization For Medical Image Classification, Narayanan Ganesh, Sambandan Jayalakshmi, Rama Chandran Narayanan, Miroslav Mahdal, Hossam Zawbaa, Ali Wagdy Mohamed

Articles

The brain is one of the most important and complex organs in the body, consisting of billions of individual cells. Uncontrolled growth and expansion of aberrant cell populations within or around the brain are the main causes of brain tumors. These cells have the potential to harm healthy cells and impair brain function [1]. Tumors can be detected using medical imaging techniques, which are considered the most popular and accurate way to classify different types of cancer, and this procedure is even more crucial as it is noninvasive [2]. Magnetic resonance imaging (MRI) is one such medical imaging technique that …

Schizo-Net: A Novel Schizophrenia Diagnosis Framework Using Late Fusion Multimodal Deep Learning On Electroencephalogram-Based Brain Connectivity Indices, Nitin Grover, Aviral Chharia, Rahul Upadhyay, Luca Longo

Articles

Schizophrenia (SCZ) is a serious mental condition that causes hallucinations, delusions, and disordered thinking. Traditionally, SCZ diagnosis involves the subject’s interview by a skilled psychiatrist. The process needs time and is bound to human errors and bias. Recently, brain connectivity indices have been used in a few pattern recognition methods to discriminate neuro-psychiatric patients from healthy subjects. The study presents Schizo-Net , a novel, highly accurate, and reliable SCZ diagnosis model based on a late multimodal fusion of estimated brain connectivity indices from EEG activity. First, the raw EEG activity is pre-processed exhaustively to remove unwanted artifacts. Next, six brain …

How Visual Stimuli Evoked P300 Is Transforming The Brain–Computer Interface Landscape: A Prisma Compliant Systematic Review, Jai Kalra, Prashasti Mittal, Nirmiti Mittal, Abhishek Arora, Utkarsh Tewari, Aviral Chharia, Rahul Upadhyay, Vinay Kumar, Luca Longo

Articles

Non-invasive Visual Stimuli evoked-EEGbased P300 BCIs have gained immense attention in recent years due to their ability to help patients with disability using BCI-controlled assistive devices and applications. In addition to the medical field, P300 BCI has applications in entertainment, robotics, and education. The current article systematically reviews 147 articles that were published between 2006-2021*. Articles that pass the pre-defined criteria are included in the study. Further, classification based on their primary focus, including article orientation, participants’ age groups, tasks given, databases, the EEG devices used in the studies, classification models, and application domain, is performed. The application-based classification considers …

Advances And Applications Of Dsmt For Information Fusion. Collected Works, Volume 5, Florentin Smarandache, Jean Dezert, Albena Tchamova

Branch Mathematics and Statistics Faculty and Staff Publications

This fifth volume on Advances and Applications of DSmT for Information Fusion collects theoretical and applied contributions of researchers working in different fields of applications and in mathematics, and is available in open-access. The collected contributions of this volume have either been published or presented after disseminating the fourth volume in 2015 (available at fs.unm.edu/DSmT-book4.pdf or www.onera.fr/sites/default/files/297/2015-DSmT-Book4.pdf) in international conferences, seminars, workshops and journals, or they are new. The contributions of each part of this volume are chronologically ordered.

First Part of this book presents some theoretical advances on DSmT, dealing mainly with modified Proportional Conflict Redistribution Rules (PCR) of …

Ensemble Transformer Architecture For Efficient And Real Time Sign Language Translation, Sumeet Ghegade

Master's Projects

Sign language is a form of visual language that uses face expression and hand gestures to communicate thoughts and concepts. The term refers to multiple visual languages that share some common visual cues but differ in their grammar and syntax. Sign language translation (SLT) is a crucial step in closing the communication gap between hearing and hearingimpaired people. The study of SLT using machine learning has gotten a lot of interest during the last three years but despite progress, SLT research is still in its early phases. Most of the previous approaches first convert the signs to glosses and then …

An Effective Transfer Learning Based Landmark Detection Framework For Uav-Based Aerial Imagery Of Urban Landscapes, Bishwas Praveen, Vineetha Menon, Tathagata Mukherjee, Bryan Mesmer, Sampson Gholston, Steven Corns

Engineering Management and Systems Engineering Faculty Research & Creative Works

Aerial imagery captured through airborne sensors mounted on Unmanned Aerial Vehicles (UAVs), aircrafts, satellites, etc. in the form of RGB, LiDAR, multispectral or hyperspectral images provide a unique perspective for a variety of applications. These sensors capture high-resolution images that can be used for applications related to mapping, surveying, and monitoring of crops, infrastructure, and natural resources. Deep learning based algorithms are often the forerunners in facilitating practical solutions for such data-centric applications. Deep learning-based landmark detection is one such application which involves the use of deep learning algorithms to accurately identify and locate landmarks of interest in images captured …

Skin Lesion Segmentation In Dermoscopic Images With Noisy Data, Norsang Lama, Jason Hagerty, Anand Nambisan, Ronald Joe Stanley, William Van Stoecker

Electrical and Computer Engineering Faculty Research & Creative Works

We Propose a Deep Learning Approach to Segment the Skin Lesion in Dermoscopic Images. the Proposed Network Architecture Uses a Pretrained Efficient Net Model in the Encoder and Squeeze-And-Excitation Residual Structures in the Decoder. We Applied This Approach on the Publicly Available International Skin Imaging Collaboration (ISIC) 2017 Challenge Skin Lesion Segmentation Dataset. This Benchmark Dataset Has Been Widely Used in Previous Studies. We Observed Many Inaccurate or Noisy Ground Truth Labels. to Reduce Noisy Data, We Manually Sorted All Ground Truth Labels into Three Categories — Good, Mildly Noisy, and Noisy Labels. Furthermore, We Investigated the Effect of Such …

Comparative Adjudication Of Noisy And Subjective Data Annotation Disagreements For Deep Learning, Scott David Williams

Browse all Theses and Dissertations

Obtaining accurate inferences from deep neural networks is difficult when models are trained on instances with conflicting labels. Algorithmic recognition of online hate speech illustrates this. No human annotator is perfectly reliable, so multiple annotators evaluate and label online posts in a corpus. Labeling scheme limitations, differences in annotators' beliefs, and limits to annotators' honesty and carefulness cause some labels to disagree. Consequently, decisive and accurate inferences become less likely. Some practical applications such as social research can tolerate some indecisiveness. However, an online platform using an indecisive classifier for automated content moderation could create more problems than it solves. …

An Empirical Study Of Pre-Trained Model Reuse In The Hugging Face Deep Learning Model Registry, Wenxin Jiang, Nicholas Synovic, Matt Hyatt, Taylor R. Schorlemmer, Rohan Sethi, Yung-Hsiang Lu, George K. Thiruvathukal, James C. Davis

Department of Electrical and Computer Engineering Faculty Publications

Deep Neural Networks (DNNs) are being adopted as components in software systems. Creating and specializing DNNs from scratch has grown increasingly difficult as state-of-the-art architectures grow more complex. Following the path of traditional software engineering, machine learning engineers have begun to reuse large-scale pre-trained models (PTMs) and fine-tune these models for downstream tasks. Prior works have studied reuse practices for traditional software packages to guide software engineers towards better package maintenance and dependency management. We lack a similar foundation of knowledge to guide behaviors in pre-trained model ecosystems.

In this work, we present the first empirical investigation of PTM reuse. …

Artificial Intelligence In Prediction Of The Remaining Useful Life Of Wind Turbine Shaft Bearings, Jinsiang Shaw, B.J. Wu

Journal of Marine Science and Technology–Taiwan

Long-term periodic rotation and unstable load changes in wind turbines can cause unexpected damage to high-speed shaft bearings (HSSBs). In this study, after preprocessing of the HSSB vibration signal, four different models for predicting bearing degradation in terms of remaining useful life (RUL) in days were investigated: support vector regression (SVR), convolutional neural networks (CNN), long short-term memory (LSTM), and CNN-LSTM. The experimental results revealed that the CNN achieved the best mean absolute error (MAE), at 0.44 days, based on frequency response plot using the fast Fourier transform (FFT), while that of the CNN-LSTM model predicted using the amplitude profile …

Computational Mechanisms Of Face Perception, Jinge Wang

Graduate Theses, Dissertations, and Problem Reports (ETD)

The intertwined history of artificial intelligence and neuroscience has significantly impacted their development, with AI arising from and evolving alongside neuroscience. The remarkable performance of deep learning has inspired neuroscientists to investigate and utilize artificial neural networks as computational models to address biological issues. Studying the brain and its operational mechanisms can greatly enhance our understanding of neural networks, which has crucial implications for developing efficient AI algorithms. Many of the advanced perceptual and cognitive skills of biological systems are now possible to achieve through artificial intelligence systems, which is transforming our knowledge of brain function. Thus, the need for …

A Survey On Artificial Intelligence-Based Acoustic Source Identification, Ruba Zaheer, Iftekhar Ahmad, Daryoush Habibi, Kazi Y. Islam, Quoc Viet Phung

Research outputs 2022 to 2026

The concept of Acoustic Source Identification (ASI), which refers to the process of identifying noise sources has attracted increasing attention in recent years. The ASI technology can be used for surveillance, monitoring, and maintenance applications in a wide range of sectors, such as defence, manufacturing, healthcare, and agriculture. Acoustic signature analysis and pattern recognition remain the core technologies for noise source identification. Manual identification of acoustic signatures, however, has become increasingly challenging as dataset sizes grow. As a result, the use of Artificial Intelligence (AI) techniques for identifying noise sources has become increasingly relevant and useful. In this paper, we …

Instantaneous Frequency Estimation Of Fm Signals Under Gaussian And Symmetric Alpha-Stable Noise: Deep Learning Versus Time-Frequency Analysis, Huda Saleem Razzaq, Zahir M. Hussain

Research outputs 2022 to 2026

Deep learning (DL) and machine learning (ML) are widely used in many fields but rarely used in the frequency estimation (FE) and slope estimation (SE) of signals. Frequency and slope estimation for frequency-modulated (FM) and single-tone sinusoidal signals are essential in various applications, such as wireless communications, sound navigation and ranging (SONAR), and radio detection and ranging (RADAR) measurements. This work proposed a novel frequency estimation technique for instantaneous linear FM (LFM) sinusoidal wave using deep learning. Deep neural networks (DNN) and convolutional neural networks (CNN) are classes of artificial neural networks (ANNs) used for the frequency and slope estimation …

Cooperative Deep Q -Learning Framework For Environments Providing Image Feedback, Krishnan Raghavan, Vignesh Narayanan, Sarangapani Jagannathan

Publications

In this article, we address two key challenges in deep reinforcement learning (DRL) setting, sample inefficiency, and slow learning, with a dual-neural network (NN)-driven learning approach. In the proposed approach, we use two deep NNs with independent initialization to robustly approximate the action-value function in the presence of image inputs. In particular, we develop a temporal difference (TD) error-driven learning (EDL) approach, where we introduce a set of linear transformations of the TD error to directly update the parameters of each layer in the deep NN. We demonstrate theoretically that the cost minimized by the EDL regime is an approximation …