Physical Sciences and Mathematics Commons^™

Machine Learning Approaches In Comparative Studies For Alzheimer’S Diagnosis Using 2d Mri Slices, Zhen Zhao, Joon Huang Chuah, Chee-Onn Chow, Kaijian Xia, Yee Kai Tee, Yan Chai Hum, Khin Wee Lai

Turkish Journal of Electrical Engineering and Computer Sciences

Alzheimer’s disease (AD) is an illness that involves a gradual and irreversible degeneration of the brain. It is crucial to establish a precise diagnosis of AD early on in order to enable prompt therapies and prevent further deterioration. Researchers are currently focusing increasing attention on investigating the potential of machine learning techniques to simplify the automated diagnosis of AD using neuroimaging. The present study involved a comparison of models for the detection of AD through the utilization of 2D image slices obtained from magnetic resonance imaging brain scans. Five models, namely ResNet, ConvNeXt, CaiT, Swin Transformer, and CVT, were implemented …

Underwater Image Enhancement Algorithm For Dual Color Spaces, Xingsheng Shen, Yalin Song, Shichang Li, Xiaoshu Hu

Journal of Marine Science and Technology

Targeting issues related to low contrast, blurring, and loss of detail prevalent in underwater image enhancement algorithms, we propose a dual-color space multiscale residual network (DMR-SCNet) based on SCNet. First, we introduce the HSV color space feature extraction module, which aims to optimize the color representation and saturation of underwater images. Subsequently, we propose the RGB color space denoising module, which focuses on repairing the content and structure of underwater images to enhance their clarity and visual quality. Finally, by designing the residual attention (RAB) module, we aim to further refine the detailed representation and feature extraction of underwater images. …

An Analysis Of Precision: Occlusion And Perspective Geometry’S Role In 6d Pose Estimation, Jeffrey Choate, Derek Worth, Scott Nykl, Clark N. Taylor, Brett J. Borghetti, Christine M. Schubert Kabban

Faculty Publications

Achieving precise 6 degrees of freedom (6D) pose estimation of rigid objects from color images is a critical challenge with wide-ranging applications in robotics and close-contact aircraft operations. This study investigates key techniques in the application of YOLOv5 object detection convolutional neural network (CNN) for 6D pose localization of aircraft using only color imagery. Traditional object detection labeling methods suffer from inaccuracies due to perspective geometry and being limited to visible key points. This research demonstrates that with precise labeling, a CNN can predict object features with near-pixel accuracy, effectively learning the distinct appearance of the object due to perspective …

A Memory Efficient Deep Recurrent Q-Learning Approach For Autonomous Wildfire Surveillance, Jeremy A. Cantor

UNF Graduate Theses and Dissertations

Previous literature demonstrates that autonomous UAVs (unmanned aerial vehicles) have the po- tential to be utilized for wildfire surveillance. This advanced technology empowers firefighters by providing them with critical information, thereby facilitating more informed decision-making processes. This thesis applies deep Q-learning techniques to the problem of control policy design under the objective that the UAVs collectively identify the maximum number of locations that are under fire, assuming the UAVs can share their observations. The prohibitively large state space underlying the control policy motivates a neural network approximation, but prior work used only convolutional layers to extract spatial fire information from …

Drilling Core Identification Based On Natural Image, Gao Hui, Wu Zhenkun, Ke Yu, Tan Songcheng, He Siqi, Duan Longchen

Coal Geology & Exploration

The traditional on-site core identification and recording mainly rely on the experience of technicians, and there are many uncertain factors. Limited by the site conditions, using mobile phones or cameras to capture the natural images is the most convenient way to collect the core information. Therefore, it is necessary to study the feature information extraction technology of core image and apply it to the identification and prediction of core type and other information. Specifically, a large number of core samples were collected, the thin-section identification method was employed to determine the core types and names, and then the core images …

Change Detection Of Open-Pit Mines Based On Fm-Unet++ And Gf-2 Satellite Images, Du Shouhang, Li Wei, Xing Jianghe, Zhang Chengye, She Changchao, Wang Shaoyu, Li Jun

Coal Geology & Exploration

Automatic extraction of land use change information in open-pit mines using the remote sensing and deep learning technology is of great significance for the mining monitoring and ecological environmental protection. A novel deep learning model FM-UNet++ was constructed for the change of land use types in complex and heterogeneous mining scenarios, and the automatic change detection of open-pit mines was achieved using the Gaofen-2 (GF-2) satellite images. Firstly, the change detection dataset of open-pit mine was produced through data surveys and visual interpretation, which was augmented by data enhancement. Secondly, the FM-UNet++ for open-pit mine change detection was constructed by …

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 …

Costume Pattern Sketch Colorization And Style Transfer Based On Neural Network, Xingquan Cai, Zhijun Li, Mengyao Xi, Haiyan Sun

Journal of System Simulation

Abstract: Aiming at the problems of color overflow in pattern sketch colorization and lack of fabric texture features in style transfer, this paper proposes a method of costume pattern sketch colorization and style transfer based on neural network. This paper initializes the data set, collects the costume pattern image, extracts the costume pattern sketch, synthesizes the costume pattern sketch with color features and constructs the style data set. The research builds the conditional generative adversarial nets and achieves the costume pattern sketch with color features colorization based on the generator. The study constructs a convolutional neural network model, uses the …

Online Classification Method For Motor Imagery Eeg With Spatial Information, Fengwei Yang, Peng Chen, Kai Xi, Hualin Pu, Xueyin Liu

Journal of System Simulation

Abstract: EEG-based BCI system can help the daily life and rehabilitation training of limb movement disorders patients. Due to the low signal-to-noise ratio and large individual differences of EEG signals, the accuracy and efficiency of EEG feature extraction and classification are not high, which affects the wide application of online BCI system. A CNN with spatial information is proposed for the online classification of MI-EEG signals. The reordered MI-EEG is convolved horizontally and vertically respectively. With the contralateral effect of motor imagery ERD/ERS phenomenon, the spatial information in MI-EEG is fully utilized to achieve the real-time acquisition and classification of …

Transmission Line Insulator Recognition Based On Artificial Images Data Expansion, Yaru Wang, Kai Yang, Yongjie Zhai, Congbin Guo, Wenqing Zhao, Jie Su

Journal of System Simulation

Abstract: Deep learning method has developed rapidly in the field of computer vision, but relies on a large quantities of training data. In the task of transmission line insulator automatic detection, problems such as insufficient number of aerial insulator images and poor diversity affect the accuracy of insulator recognition. An artificial insulator images data expansion method is proposed. Artificial insulator images are created by modeling software, and a compensation network is constructed. The artificial images are compensated and optimized by compensation network, and the aerial insulator image data set is expanded by the compensated artificial insulator images. The insulator recognition …

Tactical Maneuver Strategy Learning From Land Wargame Replay Based On Convolutional Neural Network, Jiale Xu, Haidong Zhang, Donghai Zhao, Wancheng Ni

Journal of System Simulation

Abstract: Aiming at collecting the high valuable knowledge of action decisions in "man-in-the-loop" wargame's replay data, a method of using convolutional neural network to learn the tactical maneuver strategy model from the replay data of wargame is proposed. In this method, the tactical maneuver strategy is modeled as a classification problem of making a good choice from the target candidate locations under the influence of current situation. The key factors affecting commander's decision-making are summarized, and the basic situation features are defined, which are composed of seven attributes such as "maneuverability range and observation range". The feature dataset with positive …

Modulation Recognition Algorithm Based On Truncated Migration And Parallel Resnet, Yecai Guo, Qingwei Wang

Journal of System Simulation

Abstract: A truncated migration data preprocessing algorithm is proposed for the problem of limited time series characteristics of the signal extracted by convolutional neural network. The distance unit at one end of the sampling matrix is truncated, migrated to the other end to form a new matrix, allowing the convolutional neural network to extract more sampling points and compare more symbolic information.An improved parallel ResNet is proposed, which focuses on features in both horizontal and vertical directions simultaneously by two parallel branches. The results show that the algorithm has an accuracy rate of about 10% higher than that of ordinary …

Analysis Of Patch And Sample Size Effects For 2d-3d Cnn Models Using Multiplatform Dataset: Hyperspectral Image Classification Of Rosis And Jilin-1 Gp01 Imagery, Taşkin Kavzoğlu, Eli̇f Özlem Yilmaz

Turkish Journal of Electrical Engineering and Computer Sciences

Modern hyperspectral sensors provide a huge volume of data at spectral and spatial domains with high redundancy, which requires robust methods for analysis. In this study, 2D and 3D CNN models were applied to hyperspectral image datasets (ROSIS and Jilin-1 GP01) using varying patch and sample sizes to determine their combined impacts on the performance of deep learning models. Differences in classification performances in relation to particle and sample sizes were statistically analysed using McNemar?s test. According to the findings, raising the patch and sample size enhances the performance of the 2D/3D CNN model and produces more accurate results in …

Classification And Phenological Staging Of Crops From In Situ Image Sequences By Deep Learning, Uluğ Bayazit, Deni̇z Turgay Altilar, Ni̇lgün Güler Bayazit

Turkish Journal of Electrical Engineering and Computer Sciences

Accurate knowledge of crop type information is not only valuable for verifying the declaration of farmers to obtain subsidy or insurance for the grown crop, but also for generating crop type maps that serve a variety of purposes in land monitoring and policy. On the other hand, accurate knowledge of crop phenological stage can help farm personnel apply fertilization and irrigation regimes on a timely basis. Although deep learning based networks have been applied in the past to classify the type and predict the phenological stage of crops from in situ images of fields, more advanced deep learning based networks, …

Ad-Corre: Adaptive Correlation-Based Loss For Facial Expression Recognition In The Wild, Ali Pourramezan Fard, Mohammad H. Mahoor

Electrical and Computer Engineering: Faculty Scholarship

Automated Facial Expression Recognition (FER) in the wild using deep neural networks is still challenging due to intra-class variations and inter-class similarities in facial images. Deep Metric Learning (DML) is among the widely used methods to deal with these issues by improving the discriminative power of the learned embedded features. This paper proposes an Adaptive Correlation (Ad-Corre) Loss to guide the network towards generating embedded feature vectors with high correlation for within-class samples and less correlation for between-class samples. Ad-Corre consists of 3 components called Feature Discriminator, Mean Discriminator, and Embedding Discriminator. We design the Feature Discriminator component to guide …

The Analysis And Optimization Of Cnn Hyperparameters With Fuzzy Tree Modelfor Image Classification, Kübra Uyar, Şaki̇r Taşdemi̇r, İlker Ali̇ Özkan

Turkish Journal of Electrical Engineering and Computer Sciences

The meaningful performance of convolutional neural network (CNN) has enabled the solution of various state-of-the-art problems. Although CNNs achieve satisfactory results in computer-vision problems, they still have some difficulties. As the designed CNN models are deepened to achieve much better accuracy, computational cost and complexity increase. It is significant to train CNNs with suitable topology and training hyperparameters that include initial learning rate, minibatch size, epoch number, filter size, number of filters, etc. because the initialization of hyperparameters affects classification results. On the other hand, it is not possible to make a definite inference for the hyperparameter initialization and there …

Visual Interpretability Of Capsule Network For Medical Image Analysis, Mighty Abra Ayidzoe, Yu Yongbin, Patrick Kwabena Mensah, Jingye Cai, Faiza Umar Bawah

Turkish Journal of Electrical Engineering and Computer Sciences

Deep learning (DL) models are currently not widely deployed for critical tasks such as in health. This is attributable to the "black box", making it difficult to gain the trust of practitioners. This paper proposes the use of visualizations to enhance performance verification, improve monitoring, ensure understandability, and improve interpretability needed to gain practitioners' confidence. These are demonstrated through the development of a CapsNet model for the recognition of gastrointestinal tract infection. The gastrointestinal tract comprises several organs joined in a long tube from the mouth to the anus. It is susceptive to diseases that are difficult for medics to …

Monocular Pose Estimation For Automated Aerial Refueling Via Perspective-N-Point, James C. Lynch

Theses and Dissertations

Any Automated Aerial Refueling (AAR) solution requires the quick and precise estimation of the relative position and rotation of the two aircraft involved. This is currently accomplished using stereo vision techniques augmented by Iterative Closest Point (ICP), but requires post-processing to account for environmental factors such as boom occlusion. This paper proposes a monocular solution, combining a custom-trained single-shot object detection Convolutional Neural Network (CNN) and Perspective-n-Point (PnP) estimation to calculate a pose estimate with a single image. This solution is capable of pose estimation at contact point (22m) within 7cm of error and a rate of 10Hz, regardless of …

An Ensemble Approach For Patient Prognosis Of Head And Neck Tumor Using Multimodal Data, Numan Saeed, Roba Al Majzoub, Ikboljon Sobirov, Mohammad Yaqub

Computer Vision Faculty Publications

Accurate prognosis of a tumor can help doctors provide a proper course of treatment and, therefore, save the lives of many. Tradi-tional machine learning algorithms have been eminently useful in crafting prognostic models in the last few decades. Recently, deep learning algorithms have shown significant improvement when developing diag-nosis and prognosis solutions to different healthcare problems. However, most of these solutions rely solely on either imaging or clinical data. Utilizing patient tabular data such as demographics and patient med-ical history alongside imaging data in a multimodal approach to solve a prognosis task has started to gain more interest recently and …

Automatic Segmentation Of Head And Neck Tumor: How Powerful Transformers Are?, Ikboljon Sobirov, Otabek Nazarov, Hussain Alasmawi, Mohammad Yaqub

Computer Vision Faculty Publications

Cancer is one of the leading causes of death worldwide, and head and neck (H&N) cancer is amongst the most prevalent types. Positron emission tomography and computed tomography are used to detect and segment the tumor region. Clinically, tumor segmentation is extensively time-consuming and prone to error. Machine learning, and deep learning in particular, can assist to automate this process, yielding results as accurate as the results of a clinician. In this research study, we develop a vision transformers-based method to automatically delineate H&N tumor, and compare its results to leading convolutional neural network (CNN)-based models. We use multi-modal data …

Resampling And Super-Resolution Of Hexagonally Sampled Images Using Deep Learning, Dylan Flaute, Russell C. Hardie, Hamed Elwarfalli

Electrical and Computer Engineering Faculty Publications

Super-resolution (SR) aims to increase the resolution of imagery. Applications include security, medical imaging, and object recognition. We propose a deep learning-based SR system that takes a hexagonally sampled low-resolution image as an input and generates a rectangularly sampled SR image as an output. For training and testing, we use a realistic observation model that includes optical degradation from diffraction and sensor degradation from detector integration. Our SR approach first uses non-uniform interpolation to partially upsample the observed hexagonal imagery and convert it to a rectangular grid. We then leverage a state-of-the-art convolutional neural network (CNN) architecture designed for SR …

Multi-View Human Action Recognition Based On Deep Neural Network, Zhao Ying, Lu Yao, Zhang Jian, Qidi Liang, Long Wei

Journal of System Simulation

Abstract: A novel deep neural network named CNN+CA(Convolutional Neural Network plus Context Attention) model is constructed and a new recognition algorithm based on sequence matching is presented to improve the recognition accuracy of MVHAR (Multi-view Human Action Recognition). A CNN(Convolutional Neural Network) is designed to automatically learn multi-view fusion features; the CA (Context Attention) module is introduced to selectively focus on the parts of the features that are relevant for the recognition task; the proposed recognition algorithm based on sequence matching is used to realize MVHAR. The experimental results on the IXMAS dataset and the i3DPost dataset …

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 …

Gas-Liquid Two-Phase Flow Pattern Recognition Method Based On Convolutional Neural Network, Weiguo Tong, Xuechun Pang, Genghong Zhu

Journal of System Simulation

Abstract: Aiming at the low recognition rate and subjectivity in two-phase flow pattern recognition, a method based on Landweber iterative image reconstruction algorithm and convolutional neural network is proposed. Landweber iterative image reconstruction algorithm is used to obtain the flow pattern images and build the flow pattern image database. By means of the flow pattern identification on, different convolution layers in VGG16 network and different size and resolution of the data set samples, the parameters of network frozen convolutional layer and input image are determined.The experimental results show that the combined method of resistance tomography and convolutional neural network …

Stellar Classification Of Folded Spectra Using The Mk Classification Scheme And Convolutional Neural Networks, John Magee

Dissertations

The year 1943 saw the introduction of the Morgan-Keenan (MK) classification scheme and this replaced the existing Harvard Classification scheme. Both stellar classification scheme are fundamentally grounded in the field of spectroscopy. The Harvard Classification scheme classified stars based on stellar surface temperature. The MK Classification scheme introduced the concept of a luminosity class that is intrinsically linked to the surface gravity of a star. Temperature and luminosity class values are estimated directly from the stellar spectrum.

Machine learning is a well-established technique in astronomy. Traditionally, a spectrum is treated as a one-dimensional sequence of data. Techniques such as artificial …

An Evolutionary-Based Image Classification Approach Through Facial Attributes, Seli̇m Yilmaz, Cemi̇l Zalluhoğlu

Turkish Journal of Electrical Engineering and Computer Sciences

With the recent developments in technology, there has been a significant increase in the studies on analysisof human faces. Through automatic analysis of faces, it is possible to know the gender, emotional state, and even theidentity of people from an image. Of them, identity or face recognition has became the most important task whichhas been studied for a long time now as it is crucial to take measurements for public security, credit card verification,criminal identification, and the like. In this study, we have proposed an evolutionary-based framework that relies ongenetic programming algorithm to evolve a binary- and multilabel image classifier …

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 …

A Transfer Learning-Based Deep Learning Approach For Automated Covid-19diagnosis With Audio Data, Devri̇m Akgün, Abdullah Talha Kabakuş, Zehra Karapinar Şentürk, Arafat Şentürk, Enver Küçükkülahli

Turkish Journal of Electrical Engineering and Computer Sciences

The COVID-19 pandemic has caused millions of deaths and changed daily life globally. Countries have declared a half or full lockdown to prevent the spread of COVID-19. According to medical doctors, as many people as possible should be tested to identify their status, and corresponding actions then should be taken for COVID-19 positive cases. Despite the clear necessity of these medical tests, many countries are still struggling to acquire them. This fact clearly indicates the necessity of a large-scale, cheap, fast, and accurate alternative prescreening tool that can be used for the diagnosis of COVID-19 while waiting for the medical …

A Hybrid Convolutional Neural Network Approach For Feature Selection Anddisease Classification, Prajna Paramita Debata, Puspanjali Mohapatra

Turkish Journal of Electrical Engineering and Computer Sciences

: Many researchers have analyzed the high dimensional gene expression data for disease classification using several conventional and machine learning-based approaches, but still there exists some issues which make this task nontrivial. Due to the growing complexities of the unstructured data, the researchers focus on the deep learning approach, which is the latest form of machine learning algorithm. In the presented work, a kernel-based Fisher score (KFS) approach is implemented to extract the notable genes, and an improvised chaotic Jaya (CJaya) algorithm optimized convolutional neural network (CJaya-CNN) model is applied to classify high dimensional gene expression or microarray data. This …