Electrical and Computer Engineering Commons^™

A Descriptive Analysis Of Plant Leaf Disease Detection Using Machine Learning And Deep Learning Models: A Systematic Review, Arzoo Chamoli, Anuj Kumar

Turkish Journal of Electrical Engineering and Computer Sciences

Plant leaf disease detection (PLDD) is a growing active research area with burgeoning practical applications across various sectors such as agricultural monitoring, food security, and environmental conservation. Accurate segmentation and classification of plant leaf diseases remains a key challenge in the field of plant leaf disease prediction. The challenge demands automated methods for the plant disease identification because it needs to develop better crop management systems, which will boost agricultural production. In this article, we provide a systematic review of various machine learning (ML) and deep learning (DL) methods extensively used for PLDD. The review strategy follows a formal protocol, …

Characterizing Atmospheric Turbulence With The Lunar Step Response Method, Patrick D. Carattini, Caleb J. Stilp, Katelyn M. Atkinson, Stephen C. Cain

Faculty Publications

Most methods that astronomers use to characterize the strength of atmospheric turbulence in and around their observatories use differential image motion monitors observing a star to provide the necessary data for the measurement. With the Moon becoming a greater national priority, the need to characterize atmospheric paths between observatories on Earth and the Moon is potentially going to grow in the future. To this end, the differential image motion monitor is not an ideal instrument for characterizing turbulence along paths between observatories and the Moon as the bright Moon makes it difficult to detect and locate stars in its vicinity. …

Non-Invasive Way For Detection Of Neonatal Jaundice Using Gbr, Priti V. Bhagat, Mukesh Raghuwanshi, Ashutosh D. Bagde

Chulalongkorn Medical Journal

Background: Neonatal jaundice is a common condition in newborns due to excess levels of bilirubin. The traditional method for bilirubin testing is invasive, i.e., through blood tests only, which is painful to infants. Therefore, this study uses machine learning algorithms to develop a non-invasive way to detect neonatal jaundice.

Objectives: Design a computer-aided support system to detect neonatal jaundice using machine learning algorithm.

Methods: The gradient-boosting regression model is used to predict the bilirubin level. Gradient Boosting is a robust boosting algorithm that combines several weak learners into strong learners, in which each new model is trained to minimize the …

Development And Experimental Validation Of A Non-Invasive Blood Group Detection System, Nurath K. Nurudini

Tanzania Journal of Engineering and Technology (TJET)

An individual's blood group consists of red blood cell antigens whose composition is determined by protein presence, antigen structure, and gene series. Persons aged above six months have significant anti-A and/or anti-B in their serum. During transplantation and transfusion, ABO blood group identification is the most essential factor. The conventional method involves drawing blood samples from patients, and the blood group is determined based on the antigen-antibody reaction. This method consists of adding chemical reagents. However, this requires time of operation, and throughput analysis is high, and the process is also challenging to interpret. Accurate and rapid identification of blood …

Land Target Detection Algorithm In Remote Sensing Images Based On Deep Learning, Wenyi Hu, Xiaomeng Jiang, Jiawei Tian, Shitong Ye, Shan Liu

Electrical & Computer Engineering Faculty Publications

Remote sensing technology plays a crucial role across various sectors, such as meteorological monitoring, city planning, and natural resource exploration. A critical aspect of remote sensing image analysis is land target detection, which involves identifying and classifying land-based objects within satellite or aerial imagery. However, despite advancements in both traditional detection methods and deep-learning-based approaches, detecting land targets remains challenging, especially when dealing with small and rotated objects that are difficult to distinguish. To address these challenges, this study introduces an enhanced model, YOLOv5s-CACSD, which builds upon the YOLOv5s framework. Our model integrates the channel attention (CA) mechanism, CARAFE, and …

Quantitative Assessment And Characterization Of Tool Wear Phenomena In Advanced Manufacturing Processes, Oybek Valijonovich Tuyboyov

Technical science and innovation

This paper explores the quantitative assessment and characterization of tool wear phenomena in advanced manufacturing processes, employing a multifaceted approach encompassing traditional measurements, image processing, machine learning, and predictive modeling. The study emphasizes the intricate dynamics of tool wear and its direct impact on cutting tool performance, addressing challenges in real-time monitoring and optimization of machining operations. Traditional methods like VBmax measurement are juxtaposed with advanced techniques such as the improved conditional generative adversarial net with a high-quality optimization algorithm (CGAN-HQOA), efficient channel attention destruction and construction learning (ECADCL), and shape descriptors based on contour, moments, orientations, and texture. Artificial …

Uncovering And Mitigating Spurious Features In Domain Generalization, Saeed Karimi, Hamdi̇ Di̇bekli̇oğlu

Turkish Journal of Electrical Engineering and Computer Sciences

Domain generalization (DG) techniques strive to attain the ability to generalize to an unfamiliar target domain solely based on training data originating from the source domains. Despite the increasing attention given to learning from multiple training domains through the application of various forms of invariance across those domains, the enhancements observed in comparison to ERM are nearly insignificant under specified evaluation rules. In this paper, we demonstrate that the disentanglement of spurious and invariant features is a challenging task in conventional training since ERM simply minimizes the loss and does not exploit invariance among domains. To address this issue, we …

Enhancing Water Safety: Exploring Recent Technological Approaches For Drowning Detection, Salman Jalalifar, Andrew Belford, Eila Erfani, Amir Razmjou, Rouzbeh Abbassi, Masoud Mohseni-Dargah, Mohsen Asadnia

Research outputs 2022 to 2026

Drowning poses a significant threat, resulting in unexpected injuries and fatalities. To promote water sports activities, it is crucial to develop surveillance systems that enhance safety around pools and waterways. This paper presents an overview of recent advancements in drowning detection, with a specific focus on image processing and sensor-based methods. Furthermore, the potential of artificial intelligence (AI), machine learning algorithms (MLAs), and robotics technology in this field is explored. The review examines the technological challenges, benefits, and drawbacks associated with these approaches. The findings reveal that image processing and sensor-based technologies are the most effective approaches for drowning detection …

Stream Processor Development Using Multi-Threshold Null Convention Logic Asynchronous Design Methodology, Wassim Khalil

Graduate Theses and Dissertations

Decreasing transistor feature size has led to an increase in the number of transistors in integrated circuits (IC), allowing for the implementation of more complex logic. However, such logic also requires more complex clock tree synthesis (CTS) to avoid timing violations as the clock must reach many more gates over larger areas. Thus, timing analysis requires significantly more computing power and designer involvement than in the past. For these reasons, IC designers have been pushed to nix conventional synchronous (SYNC) architecture and explore novel methodologies such as asynchronous, self-timed architecture. This dissertation evaluates the nominal active energy, voltage-scaled active energy, …

Sharprazor: Automatic Removal Of Hair And Ruler Marks From Dermoscopy Images, Reda Kasmi, Jason Hagerty, Reagan Harris Young, Norsang Lama, Januka Nepal, Jessica Miinch, William V. Stoecker, R. Joe Stanley

Mechanical and Aerospace Engineering Faculty Research & Creative Works

Background: The removal of hair and ruler marks is critical in handcrafted image analysis of dermoscopic skin lesions. No other dermoscopic artifacts cause more problems in segmentation and structure detection. Purpose: The aim of the work is to detect both white and black hair, artifacts and finally inpaint correctly the image. Method: We introduce a new algorithm: SharpRazor, to detect hair and ruler marks and remove them from the image. Our multiple-filter approach detects hairs of varying widths within varying backgrounds, while avoiding detection of vessels and bubbles. The proposed algorithm utilizes grayscale plane modification, hair enhancement, segmentation using tri-directional …

Data-Driven Deep Learning-Based Analysis On Thz Imaging, Haoyan Liu

Graduate Theses and Dissertations

Breast cancer affects about 12.5% of women population in the United States. Surgical operations are often needed post diagnosis. Breast conserving surgery can help remove malignant tumors while maximizing the remaining healthy tissues. Due to lacking effective real-time tumor analysis tools and a unified operation standard, re-excision rate could be higher than 30% among breast conserving surgery patients. This results in significant physical, physiological, and financial burdens to those patients. This work designs deep learning-based segmentation algorithms that detect tissue type in excised tissues using pulsed THz technology. This work evaluates the algorithms for tissue type classification task among freshly …

Exploratory Analysis Of Machine Learning For Images: Methods And Applications, Meenu Ajith

Electrical and Computer Engineering ETDs

This research focuses on implementing four different applications of machine learning on images. The various categories of digital images considered for these applications are grayscale, RGB, and infra-red images. The first framework uses an unsupervised learning strategy for detecting fire and smoke from an infra-red image dataset. This problem was solved using a classical machine learning algorithm since the dataset was small and unlabeled. Next, a semi-supervised deep learning model was used for facial expression recognition. Here we detect emotions from a moderately large dataset containing labeled and unlabeled grayscale images. The third application focused on single image superresolution, which …

Improving The Performance And Evaluation Of Computer-Assisted Semen Analysis, Ji-Won Choi

Dissertations

Semen analysis is performed routinely in fertility clinics to analyze the quality of semen and sperm cells of male patients. The analysis is typically performed by trained technicians or by Computer-Assisted Semen Analysis (CASA) systems. Manual semen analysis performed by technicians is subjective, time-consuming, and laborious, and yet most fertility clinics perform semen analysis in this manner. CASA systems, which are designed to perform the same tasks automatically, have a considerable market share, yet many studies still express concerns about their accuracy and consistency. In this dissertation, the focus is on detection, tracking, and classification of sperm cells in semen …

Recognition Of Handwritten Javanese Script Using Backpropagation With Zoning Feature Extraction, Anik Nur Handayani, Heru Wahyu Herwanto, Katya Lindi Chandrika, Kohei Arai

Knowledge Engineering and Data Science

Backpropagation is part of supervised learning, in which the training process requires a target. The resulting error is transmitted back to the units below in its training process. Backpropagation can solve complicated problems because it consumes less memory than other algorithms. In addition, it also can produce solutions with a low error rate while executing less time. In image pattern recognition, backpropagation can be utilized for cultural preservation in many places worldwide, including Indonesia. It is used to recognize picture patterns in Javanese script writings. This study concluded that feature extraction approaches, zoning, and backpropagation could be utilized to distinguish …

Parallel Approach Of Adaptive Image Thresholding Algorithm On Gpu, Adhi Prahara, Andri Pranolo, Nuril Anwar, Yingchi Mao

Knowledge Engineering and Data Science

Image thresholding is used to segment an image into background and foreground using a given threshold. The threshold can be generated using a specific algorithm instead of a pre-defined value obtained from observation or experiment. However, the algorithm involves per pixel operation, histogram calculation, and iterative procedure to search the optimum threshold that is costly for high-resolution images. In this research, parallel implementations on GPU for three adaptive image thresholding methods, namely Otsu, ISODATA, and minimum cross-entropy, were proposed to optimize their computational times to deal with high-resolution images. The approach involves parallel reduction and parallel prefix sum (scan) techniques …

New Methods In Wavelet Analysis For Applications Of The Wavelet Transform, Jeffrey D. Williams

Theses and Dissertations

A commonality in the many applications and domains where signal processing (SP)is applied is the detection of events. Detection in SP requires the identification of the occurrence of an event, within a signal, and distinguishing the occurrence from no event. In a classical application of SP, seismologists seek to detect abnormalities in an electromagnetic (EM) signal to detect or not detect the occurrence of an earthquake, represented as an anomalous EM pulse. Since many signals are noisy, such as those produced by a seismograph, it can be challenging to distinguish a significant EM pulse from incident noise. In SP, smoothing …

Optical Study Of 2-D Detonation Wave Stability, Eulaine T. Grodner

Theses and Dissertations

Fundamental optical detonation study of detonations constricted to a 2-d plane propagation, and detonations propagating around a curve. All images were processed using modern image processing techniques. The optical techniques used were shadowgraph, Schlieren, and chemiluminescence. In the 2-Dstraight channels, it was determined wave stability was a factor of cell size. It was also determined the detonation wave thickness (area between the combustion and shockwave) was a factor of how much heat available for the detonation. For the detonations propagating around a curve, it was determined the three main classifications of wave stability were stable, unstable, and detonation wave restart. …

A Two-Stage Hair Region Localization Method For Guided Laser Hair Removal, Murat Avşar, İmam Şami̇l Yeti̇k

Turkish Journal of Electrical Engineering and Computer Sciences

Removal of hair using laser is a widely used method, where our goal is to permanently remove hair by using laser to cause heat in order to thermally damage the hair follicle. However, currently available laser hair removal systems affect the outer skin layers besides hair follicles. This is a disadvantage of classical methods with major health risks. We propose a method to overcome these health risks by guiding the laser beam only to automatically localized hair regions. This study aims to develop an automated feature-based hair region localization method as an integral part of the proposed hair removal system …

A Novel Hybrid Decision-Based Filter And Universal Edge-Based Logical Smoothingadd-On To Remove Impulsive Noise, Rajanbir Singh Ghumaan, Prateek Jeet Singh Sohi, Nikhil Sharma, Bharat Garg

Turkish Journal of Electrical Engineering and Computer Sciences

This paper presents a novel hybrid filter along with a universal extension to remove salt and pepper noise even at a very high noise density. The proposed filter initially specifies a threshold and then denoises the image using a combination of linear, nonlinear, and probabilistic techniques. Furthermore, to improve the quality, a universal add-on is presented which uses edge detection and smoothening techniques to brush out fine details from the restored image. To evaluate the efficacy, the proposed and existing filtering techniques are implemented in MATLAB and simulated with benchmark images. The simulation results show that the proposed filter is …

Bibliometric Review On Image Based Plant Phenotyping, Shrikrishna Ulhas Kolhar, Jayant Jagtap

Library Philosophy and Practice (e-journal)

Plant phenotyping is a quantitative description of structural, physiological and temporal traits of plants resulting from interaction of plant genotypes with the environment. A rapid development is in progress in the field of image-based plant phenotyping. Plant phenotyping has wide range of applications in plant breeding research, plant growth prediction, biotic and abiotic stress analysis, crop management and early disease detection. The main motive is to provide detailed bibliometric review in order to know the available literature and current research trends in the area of plant phenotyping using plant images. The bibliometric analysis is primarily based on Scopus, web of …

Atmospheric Turbulence Distortion In Video: Restoration Utilizing Sparse Analysis, Benjamin J. Sanda

Dissertations

The removal of atmospheric turbulence (AT) distortion in long range imaging is one of the most challenging areas of research in imaging processing with an immediate need for solutions in several applications such as in military and transportation systems. AT exacerbates distortion due to non-linear geometric blur and scintillations in long-distance images and videos, severely reducing image quality and information interpretation. AT negatively impacts both human and computer vision systems, compromising visibility essential for accurate object identification and tracking.

In this dissertation, a novel sparse analysis framework is developed to address efficient AT blur and scintillation removal in video. Operating …

Image Processing Of Technological Objects, Lyudmila Petrovna Varlamova

Chemical Technology, Control and Management

The article considers the problem of creating a smoke detection and fire detection system for technological objects. Fire detection is carried out using a vision system. Monitoring of technological objects is carried out using an unmanned aerial vehicle. For further actions, processing and classification of images is necessary. When observing the technological apparatuses of the chemical and petrochemical industry, problems arise associated with the large size, distribution and extent of objects. There may be situations in which there are violations of the technological regulations and, as a result, the occurrence of fire, fire and smoke. Using the technology of unmanned …

Image Denoising Using Deep Convolutional Autoencoder With Feature Pyramids, Ekrem Çeti̇nkaya, Mustafa Furkan Kiraç

Turkish Journal of Electrical Engineering and Computer Sciences

Image denoising is 1 of the fundamental problems in the image processing field since it is the preliminary step for many computer vision applications. Various approaches have been used for image denoising throughout the years from spatial filtering to model-based approaches. Having outperformed all traditional methods, neural-network-based discriminative methods have gained popularity in recent years. However, most of these methods still struggle to achieve flexibility against various noise levels and types. In this paper, a deep convolutional autoencoder combined with a variant of feature pyramid network is proposed for image denoising. Simulated data generated by Blender software along with corrupted …

Anatomical Fraction Segmentation In The Biomass Bales, Rahul Reddy Kancharla, William A. Smith, Elisa H. Barney Smith, Jordan L. Klinger

Electrical and Computer Engineering Faculty Publications and Presentations

According to the Bioenergy Technologies Office (BETO), creating a robust next-generation domestic bioenergy industry is an essential pathway for providing sustainable renewable energy alternatives. Using non-food feedstocks, like corn-stover and forest residue, in the biorefineries doesn't affect the food supply chain. In the commercial-scale bioenergy operations, a significant development in the technological advancements is required to determine the biomass feedstock quality at the preprocessing stage. The penetrating ability of the x-rays helps study the big biomass bales, but the feedstock heterogeneity—physical size, shape, and chemical composition—poses a significant challenge during milling, conveyance, feeding, and biofuel conversion processes. The inherent complexity …

Video And Image Super-Resolution Via Deep Learning With Attention Mechanism, Xuan Xu

Graduate Theses, Dissertations, and Problem Reports (ETD)

Image demosaicing, image super-resolution and video super-resolution are three important tasks in color imaging pipeline. Demosaicing deals with the recovery of missing color information and generation of full-resolution color images from so-called Color filter Array (CFA) such as Bayer pattern. Image super-resolution aims at increasing the spatial resolution and enhance important structures (e.g., edges and textures) in super-resolved images. Both spatial and temporal dependency are important to the task of video super-resolution, which has received increasingly more attention in recent years. Traditional solutions to these three low-level vision tasks lack generalization capability especially for real-world data. Recently, deep learning methods …

On Action Quality Assessment, Paritosh Parmar

UNLV Theses, Dissertations, Professional Papers, and Capstones

In this dissertation, we tackle the task of quantifying the quality of actions, i.e., how well an

action was performed using computer vision. Existing methods used human body pose-based features to express the quality contained in an action sample. Human body pose estimation in actions such as sports actions, like diving and gymnastic vault, is particularly challenging, since the athletes undergo convoluted transformations while performing their routines. Moreover, pose-based features do not take into account visual cues such as water splash in diving. Visual cues are taken into account by human judges. In our first work, we show that using …

Foreground Removal In A Multi-Camera System, Daniel T. Mortensen

All Graduate Theses and Dissertations, Spring 1920 to Summer 2023

Traditionally, whiteboards have been used to brainstorm, teach, and convey ideas with others. However distributing whiteboard content remotely can be challenging. To solve this problem, A multi-camera system was developed which can be scaled to broadcast an arbitrarily large writing surface while removing objects not related to the whiteboard content. Related research has been performed previously to combine multiple images together, identify and remove unrelated objects, also referred to as foreground, in a single image and correct for warping differences in camera frames. However, this is the first time anyone has attempted to solve this problem using a multi-camera system. …

System And Method For Radio Tomographic Image Formation, Richard K. Martin

AFIT Patents

A system and method for generating radio tomographic images is provided. A plurality of transceivers positioned around a region to be imaged is divided into a plurality of pixels. A control apparatus is configured to cause each of the plurality of transceivers in turn to send a signal to each of the other transceivers. The control apparatus is further configured to determine an attenuation in the received signals, generate weighing, derivative, and attenuation matrices from the signals, group the pixels into a plurality of provinces, select each province in turn and solve for a change in attenuation in each of …

Erratum: "Imaging The Three‐Dimensional Orientation And Rotational Mobility Of Fluorescent Emitters Using The Tri‐Spot Point Spread Function", Oumeng Zhang, Jin Lu, Tianben Ding, Matthew D. Lew

Electrical & Systems Engineering Publications and Presentations

In the original paper, a calibration error exists in the image-formation model used to analyze experimental images taken by our microscope, causing a bias in the orientation measurements in Figs. 2 and 3. The updated measurements are shown in Fig. E1. We have also updated the supplementary material for the original article to discuss the revised PSF model and estimation algorithms (supplementary material 2) and show the revised model and measurements (Figs. S1, S3, S7, S8, and S10–S13).

Segmentation And Registration Based Automatic Cancer Proton Treatment Analysis, Yang Zhang

Open Access Theses & Dissertations

Due to its low side effects, proton therapy is rapidly developing around the world. However, the time and labor it takes to deliver the treatment have prevented widespread use in the clinic setting. For this reason, an automatic proton treatment analysis system is needed to improve efficiency during the treatment process.

The challenge lies in improving the accuracy and speed of the current proton treatment analysis system. The Range shifter correction factor is considered the same value under any given condition in our treatment system. This approximate algorithm limits the accuracy of the proton treatment analysis system. In addition, medical …