Engineering Commons^™

Motion Magnification-Inspired Feature Manipulation For Deepfake Detection, Aydamir Mirzayev, Hamdi Di̇bekli̇oğlu

Turkish Journal of Electrical Engineering and Computer Sciences

Recent advances in deep learning, increased availability of large-scale datasets, and improvement of accelerated graphics processing units facilitated creation of an unprecedented amount of synthetically generated media content with impressive visual quality. Although such technology is used predominantly for entertainment, there is widespread practice of using deepfake technology for malevolent ends. This potential for malicious use necessitates the creation of detection methods capable of reliably distinguishing manipulated video content. In this work we aim to create a learning-based detection method for synthetically generated videos. To this end, we attempt to detect spatiotemporal inconsistencies by leveraging a learning-based magnification-inspired feature manipulation …

Automated Identification Of Vehicles In Very High-Resolution Uav Orthomosaics Using Yolov7 Deep Learning Model, Esra Yildirim, Umut Güneş Seferci̇k, Taşkın Kavzoğlu

Turkish Journal of Electrical Engineering and Computer Sciences

The utilization of remote sensing products for vehicle detection through deep learning has gained immense popularity, especially due to the advancement of unmanned aerial vehicles (UAVs). UAVs offer millimeter-level spatial resolution at low flight altitudes, which surpasses traditional airborne platforms. Detecting vehicles from very high-resolution UAV data is crucial in numerous applications, including parking lot and highway management, traffic monitoring, search and rescue missions, and military operations. Obtaining UAV data at desired periods allows the detection and tracking of target objects even several times during a day. Despite challenges such as diverse vehicle characteristics, traffic congestion, and hardware limitations, the …

Action Recognition Model Of Directed Attention Based On Cosine Similarity, Chen Li, Ming He, Chen Dong, Wei Li

Journal of System Simulation

Abstract: Aiming at the lack of directionality of traditional dot product attention, this paper proposes a directed attention model (DAM) based on cosine similarity. To effectively represent the direction relationship between the spatial and temporal features of video frames, the paper defines the relationship function in the attention mechanism using the cosine similarity theory, which can remove the absolute value of the relationship between features. To reduce the computational burden of the attention mechanism, the operation is decomposed from two dimensions of time and space. The computational complexity is further optimized by combining linear attention operation. The experiment is divided …

Nonuniform Sampling-Based Breast Cancer Classification, Santiago Posso

Theses and Dissertations--Electrical and Computer Engineering

The emergence of deep learning models and their success in visual object recognition have fueled the medical imaging community's interest in integrating these algorithms to improve medical diagnosis. However, natural images, which have been the main focus of deep learning models and mammograms, exhibit fundamental differences. First, breast tissue abnormalities are often smaller than salient objects in natural images. Second, breast images have significantly higher resolutions but are generally heavily downsampled to fit these images to deep learning models. Models that handle high-resolution mammograms require many exams and complex architectures. Additionally, spatially resizing mammograms leads to losing discriminative details essential …

A Survey On Few-Shot Class-Incremental Learning, Songsong Tian, Lusi Li, Weijun Li, Hang Ran, Xin Ning, Prayag Tiwari

Computer Science Faculty Publications

Large deep learning models are impressive, but they struggle when real-time data is not available. Few-shot class-incremental learning (FSCIL) poses a significant challenge for deep neural networks to learn new tasks from just a few labeled samples without forgetting the previously learned ones. This setup can easily leads to catastrophic forgetting and overfitting problems, severely affecting model performance. Studying FSCIL helps overcome deep learning model limitations on data volume and acquisition time, while improving practicality and adaptability of machine learning models. This paper provides a comprehensive survey on FSCIL. Unlike previous surveys, we aim to synthesize few-shot learning and incremental …

Multimodal Fusion For Audio-Image And Video Action Recognition, Muhammad B. Shaikh, Douglas Chai, Syed M. S. Islam, Naveed Akhtar

Research outputs 2022 to 2026

Multimodal Human Action Recognition (MHAR) is an important research topic in computer vision and event recognition fields. In this work, we address the problem of MHAR by developing a novel audio-image and video fusion-based deep learning framework that we call Multimodal Audio-Image and Video Action Recognizer (MAiVAR). We extract temporal information using image representations of audio signals and spatial information from video modality with the help of Convolutional Neutral Networks (CNN)-based feature extractors and fuse these features to recognize respective action classes. We apply a high-level weights assignment algorithm for improving audio-visual interaction and convergence. This proposed fusion-based framework utilizes …

Urban Flood Extent Segmentation And Evaluation From Real-World Surveillance Camera Images Using Deep Convolutional Neural Network, Yidi Wang, Yawen Shen, Behrouz Salahshour, Mecit Cetin, Khan Iftekharuddin, Navid Tahvildari, Guoping Huang, Devin K. Harris, Kwame Ampofo, Jonathan L. Goodall

Civil & Environmental Engineering Faculty Publications

This study explores the use of Deep Convolutional Neural Network (DCNN) for semantic segmentation of flood images. Imagery datasets of urban flooding were used to train two DCNN-based models, and camera images were used to test the application of the models with real-world data. Validation results show that both models extracted flood extent with a mean F1-score over 0.9. The factors that affected the performance included still water surface with specular reflection, wet road surface, and low illumination. In testing, reduced visibility during a storm and raindrops on surveillance cameras were major problems that affected the segmentation of flood extent. …

Understanding The Impact Of Trade Policy Effect Uncertainty On Firm-Level Innovation Investment: A Deep Learning Approach, Daniel Chang, Nan Hu, Peng Liang, Morgan Swink

Research Collection School Of Computing and Information Systems

Integrating the real options perspective and resource dependence theory, this study examines how firms adjust their innovation investments to trade policy effect uncertainty (TPEU), a less studied type of firm specific, perceived environmental uncertainty in which managers have difficulty predicting how potential policy changes will affect business operations. To develop a text-based, context-dependent, time-varying measure of firm-level perceived TPEU, we apply Bidirectional Encoder Representations from Transformers (BERT), a state-of-the-art deep learning approach. We apply BERT to analyze the texts of mandatory Management Discussion and Analysis (MD&A) sections of annual reports for a sample of 22,669 firm-year observations from 3,181 unique …

A Comparative Study Of Yolo Models And A Transformer-Based Yolov5 Model For Mass Detection In Mammograms, Damla Coşkun, Dervi̇ş Karaboğa, Alper Baştürk, Bahri̇ye Akay, Özkan Ufuk Nalbantoğlu, Serap Doğan, İshak Paçal, Meryem Altin Karagöz

Turkish Journal of Electrical Engineering and Computer Sciences

Breast cancer is a prevalent form of cancer across the globe, and if it is not diagnosed at an early stage it can be life-threatening. In order to aid in its diagnosis, detection, and classification, computer-aided detection (CAD) systems are employed. You Only Look Once (YOLO)-based CAD algorithms have become very popular owing to their highly accurate results for object detection tasks in recent years. Therefore, the most popular YOLO models are implemented to compare the performance in mass detection with various experiments on the INbreast dataset. In addition, a YOLO model with an integrated Swin Transformer in its backbone …

Infrared Imaging Segmentation Employing An Explainable Deep Neural Network, Xinfei Liao, Dan Wang, Zairan Li, Nilanjan Dey, Rs Simon, Fuqian Shi

Turkish Journal of Electrical Engineering and Computer Sciences

Explainable AI (XAI) improved by a deep neural network (DNN) of a residual neural network (ResNet) and long short-term memory networks (LSTMs), termed XAIRL, is proposed for segmenting foot infrared imaging datasets. First, an infrared sensor imaging dataset is acquired by a foot infrared sensor imaging device and preprocessed. The infrared sensor image features are then defined and extracted with XAIRL being applied to segment the dataset. This paper compares and discusses our results with XAIRL. Evaluation indices are applied to perform various measurements for foot infrared image segmentation including accuracy, precision, recall, F1 score, intersection over union (IoU), Dice …

Cognitive Digital Modelling For Hyperspectral Image Classification Using Transfer Learning Model, Mohammad Shabaz, Mukesh Soni

Turkish Journal of Electrical Engineering and Computer Sciences

Deep convolutional neural networks can fully use the intrinsic relationship between features and improve the separability of hyperspectral images, which has received extensive in recent years. However, the need for a large number of labelled samples to train deep network models limits the application of such methods. The idea of transfer learning is introduced into remote sensing image classification to reduce the need for the number of labelled samples. In particular, the situation in which each class in the target picture only has one labelled sample is investigated. In the target domain, the number of training samples is enlarged by …

Spoken Language Processing And Modeling For Aviation Communications, Aaron Van De Brook

Doctoral Dissertations and Master's Theses

With recent advances in machine learning and deep learning technologies and the creation of larger aviation-specific corpora, applying natural language processing technologies, especially those based on transformer neural networks, to aviation communications is becoming increasingly feasible. Previous work has focused on machine learning applications to natural language processing, such as N-grams and word lattices. This thesis experiments with a process for pretraining transformer-based language models on aviation English corpora and compare the effectiveness and performance of language models transfer learned from pretrained checkpoints and those trained from their base weight initializations (trained from scratch). The results suggest that transformer language …

Faster, Cheaper, And Better Cfd: A Case For Machine Learning To Augment Reynolds-Averaged Navier-Stokes, John Peter Romano Ii

Mechanical & Aerospace Engineering Theses & Dissertations

In recent years, the field of machine learning (ML) has made significant advances, particularly through applying deep learning (DL) algorithms and artificial intelligence (AI). The literature shows several ways that ML may enhance the power of computational fluid dynamics (CFD) to improve its solution accuracy, reduce the needed computational resources and reduce overall simulation cost. ML techniques have also expanded the understanding of underlying flow physics and improved data capture from experimental fluid dynamics.

This dissertation presents an in-depth literature review and discusses ways the field of fluid dynamics has leveraged ML modeling to date. The author selects and describes …

Style Transfer Network For Generating Opera Makeup Details, Fengquan Zhang, Duo Cao, Xiaohan Ma, Baijun Chen, Jiangxiao Zhang

Journal of System Simulation

Abstract: To address the problem of the loss of local style details in cross-domain image simulation, a ChinOperaGAN network framework suitable for opera makeup is designed from the perspective of protecting the excellent traditional culture. In order to solve the style translation of differences in two image domains, multiple overlapping local adversarial discriminators are proposed in the generative adversarial network. Since paired opera makeup data are difficult to obtain, a synthetic image is generated by combining the source image makeup mapping to effectively guide the transfer of local makeup details between images. In view of the characteristics of opera makeup …

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 …

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 …

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 …

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 …

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 …

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 …

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 …

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 …

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 …

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 …

Adversarial Training Of Deep Neural Networks, Anabetsy Termini

CCE 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 …

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. …

Transfer Learning Using Infrared And Optical Full Motion Video Data For Gender Classification, Alexander M. Glandon, Joe Zalameda, Khan M. Iftekharuddin, Gabor F. Fulop (Ed.), David Z. Ting (Ed.), Lucy L. Zheng (Ed.)

Electrical & Computer Engineering Faculty Publications

This work is a review and extension of our ongoing research in human recognition analysis using multimodality motion sensor data. We review our work on hand crafted feature engineering for motion capture skeleton (MoCap) data, from the Air Force Research Lab for human gender followed by depth scan based skeleton extraction using LIDAR data from the Army Night Vision Lab for person identification. We then build on these works to demonstrate a transfer learning sensor fusion approach for using the larger MoCap and smaller LIDAR data for gender classification.