Physical Sciences and Mathematics Commons^™

Contrastive Learning For Unsupervised Auditory Texture Models, Christina Trexler

Computer Science and Computer Engineering Undergraduate Honors Theses

Sounds with a high level of stationarity, also known as sound textures, have perceptually relevant features which can be captured by stimulus-computable models. This makes texture-like sounds, such as those made by rain, wind, and fire, an appealing test case for understanding the underlying mechanisms of auditory recognition. Previous auditory texture models typically measured statistics from auditory filter bank representations, and the statistics they used were somewhat ad-hoc, hand-engineered through a process of trial and error. Here, we investigate whether a better auditory texture representation can be obtained via contrastive learning, taking advantage of the stationarity of auditory textures to …

Joint Linear And Nonlinear Computation With Data Encryption For Efficient Privacy-Preserving Deep Learning, Qiao Zhang

Electrical & Computer Engineering Theses & Dissertations

Deep Learning (DL) has shown unrivalled performance in many applications such as image classification, speech recognition, anomalous detection, and business analytics. While end users and enterprises own enormous data, DL talents and computing power are mostly gathered in technology giants having cloud servers. Thus, data owners, i.e., the clients, are motivated to outsource their data, along with computationally-intensive tasks, to the server in order to leverage the server’s abundant computation resources and DL talents for developing cost-effective DL solutions. However, trust is required between the server and the client to finish the computation tasks (e.g., conducting inference for the newly-input …

Research On The Network Of 3d Smoke Flow Super-Resolution Data Generation, Jinlian Du, Shufei Li, Xueyun Jin

Journal of System Simulation

Abstract: Aiming at the problem of low data generation efficiency due to the high complexity of solving the N-S equation of smoke flow field, a deep learning model which can generate high-resolution smoke flow data based on low-resolution smoke flow data solved by N-S equation is explored and designed. Based on the Generative Adversarial Network, the smoke data reconstruction network based on the sub voxel convolution layer is constructed. Considering the fluidity of smoke, time loss based on advection step is introduced into the loss function to realize high-precision smoke simulation. By extending the image super-resolution quality evaluation index, the …

Research On Intrusion Detection Based On Stacked Autoencoder And Long-Short Memory, Lin Shuo, An Lei, Zhijun Gao, Shan Dan, Wenli Shang

Journal of System Simulation

Abstract: As network attacks increasingly hidden, intelligent and complex. Simple machine learning cannot deal with attacks timely. A deep learning method based on the combination of SDAE and LSTM is proposed. Firstly, the distribution rules of network data are extracted intelligently layer by layer by SDAE, and the diverse anomaly features of high-dimensional data ate extracted by using coefficient penalty and reconstruction error of each coding layer. Then, LSTM’ s memory function and the powerful learning ability of sequence data are used to classify learning depth. Finally, the experiments are carried out with the UNSW-NB15 data set, which is analyzed …

Creating Synthetic Satellite Cloud Data Based On Gan Method, Wencong Cheng, Xiaokang Shi, Zhigang Wang

Journal of System Simulation

Abstract: To create the synthetic satellite cloud data in the domain of Meteorology, a method based on Generative Adversarial Networks (GAN) is proposed. Depending on ability of the nonlinear mapping and the information extraction of raster data with the deep learning network, a deep generative adversarial network model is proposed to extract the corresponding information between the numerical weather prediction(NWP) products and the satellite cloud data, and then the appropriate elements of the NWP product are chosen as the input to synthesize the corresponding satellite cloud data. The experiments are conducted on the re-analysis products of the European Centre …

Deep Learning On Image Forensics And Anti-Forensics, Zhangyi Shen

Dissertations

Image forensics protect the authenticity and integrity of digital images. On the contrary, as the countermeasures of digital forensics, anti-forensics is applied to expose the vulnerability of forensics tools. Consequently, forensics researchers could develop forensics tools against possible new attacks. This dissertation investigation demonstrates two image forensics methods based on convolutional neural network (CNN) and two image anti-forensics methods based on generative adversarial network (GAN).

Detecting unsharp masking (USM) sharpened image is the first study in this dissertation. A CNN architecture comprises four convolutional layers and a classification module is proposed to discriminate sharpened images and unsharpened images. The results …

A Deep Learning-Based Automatic Object Detection Method For Autonomous Driving Ships, Ojonoka Erika Atawodi

Master's Theses

An important feature of an Autonomous Surface Vehicles (ASV) is its capability of automatic object detection to avoid collisions, obstacles and navigate on their own.

Deep learning has made some significant headway in solving fundamental challenges associated with object detection and computer vision. With tremendous demand and advancement in the technologies associated with ASVs, a growing interest in applying deep learning techniques in handling challenges pertaining to autonomous ship driving has substantially increased over the years.

In this thesis, we study, design, and implement an object recognition framework that detects and recognizes objects found in the sea. We first curated …

A Fully-Automated, Deep Learning-Based Framework For Ct-Based Localization, Segmentation, Verification And Planning Of Metastatic Vertebrae, Tucker Netherton, Tucker James Netherton

Dissertations & Theses (Open Access)

Palliative radiotherapy is an effective treatment for the palliation of symptoms caused by vertebral metastases. Visible evidence of disease is localized on medical images as part of the treatment planning process. However, complicating factors such as time pressures, anatomic variants in the spine, and similarities in adjacent vertebrae are associated with wrong level treatments of the spine. In addition, erroneous manual contouring of anatomic structures is a major failure mode in radiotherapy treatment planning.

The purpose of this study is to mitigate the challenges associated with treatment planning of the spine by automating the treatment planning process for three-dimensional conformal …

Improving Treatment Of Local Liver Ablation Therapy With Deep Learning And Biomechanical Modeling, Brian Anderson, Kristy Brock, Laurence Court, Carlos Eduardo Cardenas, Erik Cressman, Ankit Patel

Dissertations & Theses (Open Access)

In the United States, colorectal cancer is the third most diagnosed cancer, and 60-70% of patients will develop liver metastasis. While surgical liver resection of metastasis is the standard of care for treatment with curative intent, it is only avai lable to about 20% of patients. For patients who are not surgical candidates, local percutaneous ablation therapy (PTA) has been shown to have a similar 5-year overall survival rate. However, PTA can be a challenging procedure, largely due to spatial uncertainties in the localization of the ablation probe, and in measuring the delivered ablation margin.

For this work, we hypothesized …

Network Traffic Anomaly Detection Method For Imbalanced Data, Shuqin Dong, Bin Zhang

Journal of System Simulation

Abstract: Aiming at the poor detection performances caused by the low feature extraction accuracy of rare traffic attacks from scarce samples, a network traffic anomaly detection method for imbalanced data is proposed. A traffic anomaly detection model is designed, in which the traffic features in different feature spaces are learned by alternating activation functions, architectures, corrupted rates and dropout rates of stacked denoising autoencoder (SDA), and the low accuracy in extracting features of rare traffic attacks in a single space is solved. A batch normalization algorithm is designed, and the Adam algorithm is adopted to train parameters of …

On-Device Deep Learning Inference For System-On-Chip (Soc) Architectures, Tom Springer, Elia Eiroa-Lledo, Elizabeth Stevens, Erik Linstead

Engineering Faculty Articles and Research

As machine learning becomes ubiquitous, the need to deploy models on real-time, embedded systems will become increasingly critical. This is especially true for deep learning solutions, whose large models pose interesting challenges for target architectures at the “edge” that are resource-constrained. The realization of machine learning, and deep learning, is being driven by the availability of specialized hardware, such as system-on-chip solutions, which provide some alleviation of constraints. Equally important, however, are the operating systems that run on this hardware, and specifically the ability to leverage commercial real-time operating systems which, unlike general purpose operating systems such as Linux, can …

Wg2An: Synthetic Wound Image Generation Using Generative Adversarial Network, Salih Sarp, Murat Kuzlu, Emmanuel Wilson, Ozgur Guler

Engineering Technology Faculty Publications

In part due to its ability to mimic any data distribution, Generative Adversarial Network (GAN) algorithms have been successfully applied to many applications, such as data augmentation, text-to-image translation, image-to-image translation, and image inpainting. Learning from data without crafting loss functions for each application provides broader applicability of the GAN algorithm. Medical image synthesis is also another field that the GAN algorithm has great potential to assist clinician training. This paper proposes a synthetic wound image generation model based on GAN architecture to increase the quality of clinical training. The proposed model is trained on chronic wound datasets with various …

Deep Learning Techniques Of Losses In Data Transmitted In Wirelesssensor Networks, Mevlüt Ersoy, Beki̇r Aksoy

Turkish Journal of Electrical Engineering and Computer Sciences

Wireless sensor network (WSN) systems are frequently used today as a result of rapid technological developments. Wireless sensor networks, which form the basis of the Internet of Things (IoT), have a wide range of use in theworld from education to health, and from military applications to home applications. It enables the data obtained fromthe sensors to be transferred between nodes with the help of end-to-end wireless protocols. In parallel with the increasingnumber of nodes in WSN, data tra?ic density also increases. Due to the limitations of the WSN network, lost packetrates also increase with increasing data tra?ic. In this study, …

Ensemble Learning Of Multiview Cnn Models For Survival Time Prediction Of Braintumor Patients Using Multimodal Mri Scans, Abdela Ahmed Mossa, Ulus Çevi̇k

Turkish Journal of Electrical Engineering and Computer Sciences

Brain tumors have been one of the most common life-threatening diseases for all mankind. There have beenhuge efforts dedicated to the development of medical imaging techniques and radiomics to diagnose tumor patients quicklyand e?iciently. One of the main aims is to ensure that preoperative overall survival time (OS) prediction is accurate.Recently, deep learning (DL) algorithms, and particularly convolutional neural networks (CNNs) achieved promisingperformances in almost all computer vision fields. CNNs demand large training datasets and high computational costs.However, curating large annotated medical datasets are difficult and resource-intensive. The performances of singlelearners are also unsatisfactory for small datasets. Thus, this study …

Neural Relation Extraction: A Review, Mehmet Aydar, Özge Bozal, Furkan Özbay

Turkish Journal of Electrical Engineering and Computer Sciences

Neural relation extraction discovers semantic relations between entities from unstructured text using deeplearning methods. In this study, we make a clear categorization of the existing relation extraction methods in termsof data expressiveness and data supervision, and present a comprehensive and comparative review. We describe theevaluation methodologies and the datasets used for model assessment. We explicitly state the common challenges inrelation extraction task and point out the potential of the pretrained models to solve them. Accordingly, we investigateadditional research directions and improvement ideas in this field.

Learning Multiview Deep Features From Skeletal Sign Language Videos Forrecognition, Ashraf Ali Shaik, Venkata Durga Prasad Mareedu, Venkata Vijaya Kishore Polurie

Turkish Journal of Electrical Engineering and Computer Sciences

The most challenging objective in machine translation of sign language has been the machine?s inability tolearn interoccluding finger movements during an action process. This work addresses the problem of teaching a deeplearning model to recognize differently oriented skeletal data. The multi-view 2D skeletal sign language video data isobtained using 3D motion-captured system. A total of 9 signer views were used for training the proposed network andthe 6 for testing and validation. In order to obtain multi-view deep features for recognition, we proposed an end-to-endtrainable multistream convolutional neural network (CNN) with late feature fusion. The fused multiview features arethen inputted to …

Turkish Sign Language Recognition Based On Multistream Data Fusion, Cemi̇l Gündüz, Hüseyi̇n Polat

Turkish Journal of Electrical Engineering and Computer Sciences

Sign languages are nonverbal, visual languages that hearing- or speech-impaired people use for communication.Aside from hands, other communication channels such as body posture and facial expressions are also valuable insign languages. As a result of the fact that the gestures in sign languages vary across countries, the significance ofcommunication channels in each sign language also differs. In this study, representing the communication channels usedin Turkish sign language, a total of 8 different data streams-4 RGB, 3 pose, 1 optical flow-were analyzed. Inception3D was used for RGB and optical flow; and LSTM-RNN was used for pose data streams. Experiments were conductedby …

Visual Object Detection For Autonomous Transport Vehicles In Smart Factories, Nazlican Gengeç, Onur Eker, Hakan Çevi̇kalp, Ahmet Yazici, Hasan Serhan Yavuz

Turkish Journal of Electrical Engineering and Computer Sciences

Autonomous transport vehicles (ATVs) are one of the most substantial components of smart factories of Industry 4.0. They are primarily considered to transfer the goods or perform some certain navigation tasks in the factory with self driving. The recent developments on computer vision studies allow the vehicles to visually perceive the environment and the objects in the environment. There are numerous applications especially for smart traffic networks in outdoor environments but there is lack of application and databases for autonomous transport vehicles in indoor industrial environments. There exist some essential safety and direction signs in smart factories and these signs …

Sleep Staging With Deep Structured Neural Net Using Gabor Layer And Dataaugmentation, Ali Erfani Sholeyan, Fereidoun Nowshiravan Rahatabad, Kamal Setaredan

Turkish Journal of Electrical Engineering and Computer Sciences

Slow wave sleep (SWS) and rapid eye movement (REM) are two of the most important sleep stages that are considered in many studies. Detection of these two sleep stages will help researchers in many applications to detect sleeprelated diseases and disorders and also in many fields of neuroscience studies such as cognitive impairment and memory consolidation. Since manual sleep staging is time-consuming, subjective, and expensive; designing an efficient automatic sleep scoring system will overcome some of these difficulties. Many studies have proposed automatic sleep staging systems with different methods. In recent years, deep learning methods show their potential in different …

Malignant Skin Melanoma Detection Using Image Augmentation By Oversamplingin Nonlinear Lower-Dimensional Embedding Manifold, Olusola Oluwakemi Abayomi-Alli, Robertas Damasevicius, Sanjay Misra, Rytis Maskeliunas, Adebayo Abayomi-Alli

Turkish Journal of Electrical Engineering and Computer Sciences

The continuous rise in skin cancer cases, especially in malignant melanoma, has resulted in a high mortality rate of the affected patients due to late detection. Some challenges affecting the success of skin cancer detection include small datasets or data scarcity problem, noisy data, imbalanced data, inconsistency in image sizes and resolutions, unavailability of data, reliability of labeled data (ground truth), and imbalance of skin cancer datasets. This study presents a novel data augmentation technique based on covariant Synthetic Minority Oversampling Technique (SMOTE) to address the data scarcity and class imbalance problem. We propose an improved data augmentation model for …

Evolution Of Histopathological Breast Cancer Images Classification Using Stochasticdilated Residual Ghost Model, Ramgopal Kashyap

Turkish Journal of Electrical Engineering and Computer Sciences

Breast cancer detection is a complex problem to solve, and it is a topic that is still being studied. Deep learning-based models aid medical science by helping to classify benign and malignant cancers and saving lives. Breast cancer histopathological image classification (BreakHis) and breast cancer histopathological annotation and diagnosis (BreCaHAD) datasets are used in the proposed model. The study led to the resolution of four essential issues: 1) Addresses the color divergence issue caused by strain normalization during image generation 2) Data augmentation uses several factors like as flip, rotation, shift, resize, and gamma value in order to overcome overfitting …

Detection Of Amyotrophic Lateral Sclerosis Disease By Variational Modedecomposition And Convolution Neural Network Methods From Event-Relatedpotential Signals, Fatma Lati̇foğlu, Firat Orhan Bulucu, Rami̇s İleri̇

Turkish Journal of Electrical Engineering and Computer Sciences

Amyotrophic lateral sclerosis (ALS), also known as motor neuron disease, is a neurological disease that occurs as a result of damage to the nerves in the brain and restriction of muscle movements. Electroencephalography (EEG) is the most common method used in brain imaging to study neurological disorders. Diagnosis of neurological disorders such as ALS, Parkinson's, attention deficit hyperactivity disorder is important in biomedical studies. In recent years, deep learning (DL) models have been started to be applied in the literature for the diagnosis of these diseases. In this study, event-related potentials (ERPs) were obtained from EEG signals obtained as a …

A Novel Approach For Intrusion Detection Systems: V-Ids, Kenan İnce

Turkish Journal of Electrical Engineering and Computer Sciences

An intrusion detection system (IDS) is a security mechanism that detects abnormal activities in a network. An ideal IDS must detect intrusion attempts and maybe categorize them for further research and keep false-positive analysis at a very low level. IDSs are used in the analysis of network traffic data at all sizes. Studies on this subject focused on machine learning techniques. Even though the performance rates are high, it is seen that processes such as data understanding, preprocessing, and consistency tests are time-consuming and laborious. For this reason, the use of deep learning (DL) models that automatically perform the mentioned …

Converting Optical Videos To Infrared Videos Using Attention Gan And Its Impact On Target Detection And Classification Performance, Mohammad Shahab Uddin, Reshad Hoque, Kazi Aminul Islam, Chiman Kwan, David Gribben, Jiang Li

Electrical & Computer Engineering Faculty Publications

To apply powerful deep-learning-based algorithms for object detection and classification in infrared videos, it is necessary to have more training data in order to build high-performance models. However, in many surveillance applications, one can have a lot more optical videos than infrared videos. This lack of IR video datasets can be mitigated if optical-to-infrared video conversion is possible. In this paper, we present a new approach for converting optical videos to infrared videos using deep learning. The basic idea is to focus on target areas using attention generative adversarial network (attention GAN), which will preserve the fidelity of target areas. …

Deep Learning For Turkish Makam Music Composition, İsmai̇l Hakki Parlak, Yalçin Çebi̇, Ci̇han Işikhan, Derya Bi̇rant

Turkish Journal of Electrical Engineering and Computer Sciences

In this paper, we introduce a new deep-learning-based system that can compose structured Turkish makam music (TMM) in the symbolic domain. Presented artificial TMM composer (ATMMC) takes eight initial notes from a human user and completes the rest of the piece. The backbone of the composer system consists of multilayered long short-term memory (LSTM) networks. ATMMC can create pieces in Hicaz and Nihavent makams in Şarkı form, which can be viewed and played with Mus2, a notation software for microtonal music. Statistical analysis shows that pieces composed by ATMMC are approximately 84% similar to training data. ATMMC is an open-source …

Image Forgery Detection Based On Fusion Of Lightweight Deep Learning Models, Amit Doegar, Srinidhi Hiriyannaiah, Siddesh Gaddadevara Matt, Srinivasa Krishnarajanagar Gopaliyengar, Maitreyee Dutta

Turkish Journal of Electrical Engineering and Computer Sciences

Image forgery detection is one of the key challenges in various real time applications, social media and online information platforms. The conventional methods of detection based on the traces of image manipulations are limited to the scope of predefined assumptions like hand-crafted features, size and contrast. In this paper, we propose a fusion based decision approach for image forgery detection. The fusion of decision is based on the lightweight deep learning models namely SqueezeNet, MobileNetV2 and ShuffleNet. The fusion decision system is implemented in two phases. First, the pretrained weights of the lightweight deep learning models are used to evaluate …

A Hybrid Approach Based On Transfer And Ensemble Learning For Improvingperformances Of Deep Learning Models On Small Datasets, Tunç Gülteki̇n, Aybars Uğur

Turkish Journal of Electrical Engineering and Computer Sciences

The need for high-volume data is one of the challenging requirements of the deep learning methods, and it makes it harder to apply deep learning algorithms to domains in which the data sources are limited, in other words, small. These domains may vary from medical diagnosis to satellite imaging. The performances of the deep learning methods on small datasets can be improved by the approaches such as data augmentation, ensembling, and transfer learning. In this study, we propose a new approach that utilizes transfer learning and ensemble methods to increase the accuracy rates of convolutional neural networks for classification tasks …

Brain Tumor Detection From Mri Images With Using Proposed Deep Learningmodel: The Partial Correlation-Based Channel Selection, Atinç Yilmaz

Turkish Journal of Electrical Engineering and Computer Sciences

A brain tumor is an abnormal growth of a mass or cell in the brain. Early diagnosis of the tumor significantly increases the chances of successful treatment. Artificial intelligence-based systems can detect the tumor in early stages. In this way, it could be possible to detect a tumor and resolve this problem that may endanger human life early. In the study, the partial correlation-based channel selection formula was presented that allowed the selection of the most prominent feature that differs from the other studies in the literature. Additionally, the multi-channel convolution structure was proposed for the feature network phase of …

Deep-Learning-Based Spraying Area Recognition System Forunmanned-Aerial-Vehicle-Based Sprayers, Shahbaz Khan, Muhammad Tufail, Muhammad Tahir Khan, Zubair Ahmed Khan, Shahzad Anwer

Turkish Journal of Electrical Engineering and Computer Sciences

Unmanned aerial vehicle (UAV)-based spraying system employing machine learning techniques is a recent advancement in precision agriculture for precise spraying, promoting saving chemicals (pesticide/herbicide), and enhancing their effectiveness. This study aims to develop an efficient deep learning system for UAV-based sprayers, which has the capability to accurately recognize spraying areas. A deep learning system is proposed and developed incorporating a faster region-based convolutional neural network (R-CNN) for the imagery collected. In order to develop a classifier for identifying spraying areas from nonspraying areas, four different agriculture croplands and orchards were considered. All the experiments were performed in agriculture fields through …

Utilizing Resonant Scattering Signal Characteristics Via Deep Learning For Improvedclassification Of Complex Targets, Tuğçe Toprak, Mustafa Alper Selver, Mustafa Seçmen, Emi̇ne Yeşi̇m Zoral

Turkish Journal of Electrical Engineering and Computer Sciences

Object classification using late-time resonant scattering electromagnetic signals is a significant problem found in different areas of application. Due to their unique properties, spherical objects play an essential role in this field both as a challenging target and a resource of analytical late-time resonant scattering electromagnetic signals. Although many studies focus on their detailed analysis, the challenges associated with target classification by resonant late-time resonant scattering electromagnetic signals from multilayer spheres have not been investigated in detail. Moreover, existing studies made the simplifying assumption that the objects having (one or more) layers constitute equal permeability values at the core and …