Digital Commons Network^™

Small Object Detection Techniques In Remote Sensing Images Using Aam And Raspp, Farhan Iqbal

Chulalongkorn University Theses and Dissertations (Chula ETD)

Remote sensing technology has advanced substantially, with significant research focused on identifying and recognizing small, distant objects within large-scale scenes. Despite these strides, the task remains difficult due to limitations in image resolution, varied object scales, dense object distribution, and diverse orientations. Current object detection methods often struggle to maintain the fine detail essential for small object detection, resulting in the loss of critical information. To address this, we introduce an Advanced Attention Mechanism (AAM) that combines a novel Combined Channel and Spatial Attention (CCSA) approach with Residual Atrous Spatial Pyramid Pooling (RASSP). This integration enhances detection accuracy by preserving …

Grammatical Error Correction In Thai Sentences For Deaf Students, Supachan Traitruengsakul

Chulalongkorn University Theses and Dissertations (Chula ETD)

Deaf students encounter challenges in written communication due to errors such as insertion, deletion, disorder, misusage, and misspellings. Grammatical error correction (GEC) technology can help mitigate these issues. However, existing GEC models are primarily trained on online resources from second-language hearing learners. In contrast, sentences written by deaf students suffer from a variety of errors not typically found elsewhere. To address this issue, we create the Thai Deaf Corpus (TDC), focusing on identifying and analyzing errors among deaf students in grades 7-12 across four deaf schools. Additionally, we introduce a two-stage system for the Thai-GEC model, automatically detecting and correcting …

Mhair: A Dataset Of Audio-Image Representations For Multimodal Human Actions, Muhammad Bilal Shaikh, Douglas Chai, Syed M. S. Islam, Naveed Akhtar

Research outputs 2022 to 2026

Audio-image representations for a multimodal human action (MHAiR) dataset contains six different image representations of the audio signals that capture the temporal dynamics of the actions in a very compact and informative way. The dataset was extracted from the audio recordings which were captured from an existing video dataset, i.e., UCF101. Each data sample captured a duration of approximately 10 s long, and the overall dataset was split into 4893 training samples and 1944 testing samples. The resulting feature sequences were then converted into images, which can be used for human action recognition and other related tasks. These images can …

Educating For Shalom In Engineering, Julie Wildschut

University Faculty Publications and Creative Works

Created in the image of God, humans have a unique purpose within creation. We are given the task of worshipping God (Isa 43:21), sharing the gospel of Jesus Christ (Mat 28:18-20), discovering and developing the potentials of creation (Gen 2:15), struggling and praying for shalom (Isa 1:17), and celebrating instances of God’s coming kingdom (Isa 9:1-7, Col 1:19-20). As Christian engineering educators, we have the additional task of preparing students to become capable engineers and to use those skills in response to God’s call in their lives. We have the blessing of not only teaching the technical aspects of engineering, …

Applications Of Predictive And Generative Ai Algorithms: Regression Modeling, Customized Large Language Models, And Text-To-Image Generative Diffusion Models, Suhaima Jamal

College of Graduate Studies: Theses & Dissertations

The integration of Machine Learning (ML) and Artificial Intelligence (AI) algorithms has radically changed predictive modeling and classification tasks, enhancing a multitude of domains with unprecedented analytical capabilities. Predictive modeling leverages ML and AI to forecast future trends or behaviors based on historical data, while classification tasks categorize data into distinct classes, from email filtering to medical diagnosis. Concurrently, text-to-image generation has emerged as a transformative potential, allowing visual content creation directly from textual descriptions. These advancements are pivotal in design, art, entertainment, and visual communication, as well as enhancing creativity and productivity. This work explores three significant studies in …

Affordances Of Mobile Technology To Facilitate Learning In Undergraduate Thermal-Fluid Sciences, Maeve Raphael Bakic

Boise State University Theses and Dissertations

In recent years, the pandemic has affected learning at all levels, in particular higher education, where higher levels of independence and self-motivation are required during distance learning. In engineering in particular, distance learning adds another degree of difficulty to an already complex field. Comprehension in engineering requires the repeated use of diagrams, high-level charts, and practice problems. Mobile devices, combined with a technology-enhanced curriculum, provide an excellent platform for learning in engineering as it allows for clear illustration and the transfer of complex ideas at any time and place. In alignment with the social-constructivist framework, these facets of mobile technology …

Classification Of Large Scale Fish Dataset By Deep Neural Networks, Priyanka Adapa

Electronic Theses, Projects, and Dissertations

The development of robust and efficient fish classification systems has become essential to preventing the rapid depletion of aquatic resources and building conservation strategies. A deep learning approach is proposed here for the automated classification of fish species from underwater images. The proposed methodology leverages state-of-the-art deep neural networks by applying the compact convolutional transformer (CCT) architecture, which is famous for faster training and lower computational cost. In CCT, data augmentation techniques are employed to enhance the variability of the training data, reducing overfitting and improving generalization. The preliminary outcomes of our proposed method demonstrate a promising accuracy level of …

An Exhaustive Review Of Neutrosophic Logic In Addressing Image Processing Issues, Samia Mandour

Neutrosophic Systems with Applications

Since the importance of images in our lives and the advancements in computer data gathering methods, anyone can collect a large number of images, but most of them cannot be processed manually. Image processing therefore becomes appealing since various types of data may be represented and processed digitally. Image processing has become the most popular processing method, employed in security camera films, healthcare images, images from remote sensors, and naturalistic image/videos because of fast computers and processors. In order to raise cognitive function and speed up decision-making, image processing is crucial to many information access systems. Since ambiguity now permeates …

Synergising Bim And Real-Time Data For Improved Efficiency: An Irish Case Study, Ahmed Hassan, Ankur Mitra, Alan Hore, Mark Mulville

Conference Papers

The evolution of 3D visualisation and the Internet of Things (IoT) presents a substantial opportunity for integrating real-time data with Building Information Models (BIM) to improve its functionality and construction workflow efficiency. Integrating real-time data with BIM can enhance the digital representation of construction buildings’ physical and functional characteristics and provide recordable status of on-site operations. Nevertheless, the integration between Visualisation and IoT technologies with BIM remains in its preliminary stages and faces a myriad of technical and operational challenges. Furthermore, developing advanced solutions to facilitate this complex integration requires a considerable understanding of the viability and feasibility of merging …

3-Dimensional Quartic Bézier Curve Approximation Model By Using Neutrosophic Approach, Siti Nur Idara Rosli, Mohammad Izat Emir Zulkifly

Neutrosophic Systems with Applications

In a 3-dimensional data collection process, there exists noise data that cannot be included to visualize the process. Therefore, it is difficult to deal with since fuzzy set and intuitionistic fuzzy set theories did not consider the indeterminacy problem. However, using a neutrosophic approach with three memberships: truth, false, and indeterminacy membership function, the error data will be treated as uncertain data by using the indeterminacy degree. Thus, this study will visualize the 3-dimensional quartic Bézier curve model by using neutrosophic set theory. To construct the model, the neutrosophic quartic control point must first be introduced to approximate the neutrosophic …

Focal Modulation Network For Lung Segmentation In Chest X-Ray Images, Şaban Öztürk, Tolga Çukur

Turkish Journal of Electrical Engineering and Computer Sciences

Segmentation of lung regions is of key importance for the automatic analysis of Chest X-Ray (CXR) images, which have a vital role in the detection of various pulmonary diseases. Precise identification of lung regions is the basic prerequisite for disease diagnosis and treatment planning. However, achieving precise lung segmentation poses significant challenges due to factors such as variations in anatomical shape and size, the presence of strong edges at the rib cage and clavicle, and overlapping anatomical structures resulting from diverse diseases. Although commonly considered as the de-facto standard in medical image segmentation, the convolutional UNet architecture and its variants …

Dynamic Deep Neural Network Inference Via Adaptive Channel Skipping, Meixia Zou, Xiuwen Li, Jinzheng Fang, Hong Wen, Weiwei Fang

Turkish Journal of Electrical Engineering and Computer Sciences

Deep neural networks have recently made remarkable achievements in computer vision applications. However, the high computational requirements needed to achieve accurate inference results can be a significant barrier to deploying DNNs on resource-constrained computing devices, such as those found in the Internet-of-things. In this work, we propose a fresh approach called adaptive channel skipping (ACS) that prioritizes the identification of the most suitable channels for skipping and implements an efficient skipping mechanism during inference. We begin with the development of a new gating network model, ACS-GN, which employs fine-grained channel-wise skipping to enable input-dependent inference and achieve a desirable balance …

Pymaivar: An Open-Source Python Suit For Audio-Image Representation In Human Action Recognition, Muhammad B. Shaikh, Douglas Chai, Syed M. S. Islam, Naveed Akhtar

Research outputs 2022 to 2026

We present PyMAiVAR, a versatile toolbox that encompasses the generation of image representations for audio data including Wave plots, Spectral Centroids, Spectral Roll Offs, Mel Frequency Cepstral Coefficients (MFCC), MFCC Feature Scaling, and Chromagrams. This wide-ranging toolkit generates rich audio-image representations, playing a pivotal role in reshaping human action recognition. By fully exploiting audio data's latent potential, PyMAiVAR stands as a significant advancement in the field. The package is implemented in Python and can be used across different operating systems.

Visualizing Transaction-Level Modeling Simulations Of Deep Neural Networks, Nataniel Farzan, Emad Arasteh

Engineering Technical Reports

The growing complexity of data-intensive software demands constant innovation in computer hardware design. Performance is a critical factor in rapidly evolving applications such as artificial intelligence (AI). Transaction-level modeling (TLM) is a valuable technique used to represent hardware and software behavior in a simulated environment. However, extracting actionable insights from TLM simulations is not a trivial task. We present Netmemvisual, an interactive, cross-platform visualization tool for exposing memory bottlenecks in TLM simulations. We demonstrate how Netmemvisual helps system designers rapidly analyze complex TLM simulations to find memory contention. We describe the project’s current features, experimental results with two state-of-the-art deep …

A Novel Approach For Defect Detection Of Wind Turbine Blade Using Virtual Reality And Deep Learning, Md Fazle Rabbi

Open Access Theses & Dissertations

Wind turbines are subjected to continuous rotational stresses and unusual external forces such as storms, lightning, strikes by flying objects, etc., which may cause defects in turbine blades. Hence, it requires a periodical inspection to ensure proper functionality and avoid catastrophic failure. The task of inspection is challenging due to the remote location and inconvenient reachability by human inspection. Researchers used images with cropped defects from the wind turbine in the literature. They neglected possible background biases, which may hinder real-time and autonomous defect detection using aerial vehicles such as drones or others. To overcome such challenges, in this paper, …

Digital Challenges And Opportunities Of Addressing On-Site Productivity And Safety On Construction Job Sites: An International Perspective, Ahmed Hassan, Ankur Mitra, Mark Mulville, Alan Hore

Conference papers

The slow pace of digital transformation in construction remains an impediment to the industry’s evolution. Despite rapid developments in digital technologies, the vast bulk of data generated on construction job sites remains underutilised due to the limited use of real-time data capture. The diffusion of digital solutions in construction depends on successfully capturing critical real-time data that can inform and contribute to more productive work patterns and safer job sites. Nevertheless, the construction industry’s fragmented nature has segregated the digital solutions offered by technology providers from the volatile challenges facing on-site construction practitioners.

This paper will present the early development …

Inter-Frame Video Compression Based On Adaptive Fuzzy Inference System Compression Of Multiple Frame Characteristics, Arief Bramanto Wicaksono Putra, Rheo Malani, Bedi Suprapty, Achmad Fanany Onnilita Gaffar, Roman Voliansky

Knowledge Engineering and Data Science

Video compression is used for storage or bandwidth efficiency in clip video information. Video compression involves encoders and decoders. Video compression uses intra-frame, inter-frame, and block-based methods. Video compression compresses nearby frame pairs into one compressed frame using inter-frame compression. This study defines odd and even neighboring frame pairings. Motion estimation, compensation, and frame difference underpin video compression methods. In this study, adaptive FIS (Fuzzy Inference System) compresses and decompresses each odd-even frame pair. First, adaptive FIS trained on all feature pairings of each odd-even frame pair. Video compression-decompression uses the taught adaptive FIS as a codec. The features utilized …

Contextualizing And Integrating Practices: Reclaiming Authenticity Lost From Translating Workplace Engineering Practices Into K-12 Standards, Anne E. Leak, Lindsay M. Owens, Kelly Norris Martin, Benjamin M. Zwickl

Journal of Pre-College Engineering Education Research (J-PEER)

K-12 students need to become familiar with engineering because 21st-century careers integrate engineering practices across all science, technology, engineering, and mathematics (STEM) fields. While the Next Generation Science Standards (NGSS) emphasize learning real science and engineering practices, further work is needed to authenticate engineering for K-12 education. The NGSS are presented in a way that merges a single general practice with a core disciplinary idea and cross-cutting concept. Based on this framing and underlying epistemology, NGSS engineering practices are often implemented as overgeneralized, isolated, and largely context-neutral. Yet, in the STEM workplace, practices are rarely done in isolation from one …

Causal Modeling Framework For Nuclear Power Plant Licensing Process, Lauren Kimberly Kiser

Theses and Dissertations

Interests in clean energy revived the nuclear power industry. For the first time in decades, innovative technologies and plant designs are being considered by regulatory agencies. This dissertation explores a Bayesian Network and AHP approach to causal modeling of the Combined License review process for new nuclear power plants (NPP). Historically lengthy and expensive, NPP licensing is critical to ensuring safe operation of the plants. With this comes a high standard for applicants to reach that can result in multiple revision cycles and long review times. New plant designs and fluctuating public support lead to a complex and dynamic series …

Application Of Image Processing In Soil Mechanics, Luke Knodel

Senior Honors Theses

Whenever someone digs a hole in the ground or takes a relaxing walk on the beach, they directly interact with the soil. In its basic form, soil consists of solid, water, and air phases. Unlike water and metals, soil is a particulate media, and the relative proportion of the individual phases significantly influences its physical properties. Various studies have analyzed soil using image processing to determine its morphological properties. Research involving the digital processing of X-ray Computed Tomography (X-ray CT) images of soil to retrieve physically meaningful information is gaining recognition. This study investigates two-dimensional X-ray CT images of unsaturated …

Using Artificial Neural Networks And Space Syntax Techniques To Understand Mass Housing Design Parameters, Veli̇ Mustafa Yönder

Architecture and Planning Journal (APJ)

The design of mass housing is a complex process that involves the use of a large number of components and parameters. The field of design has unavoidably been changed by the impact of digitalization, which has resulted in the proliferation of computational design models, data structures, artificial intelligence, and an algorithmic way of thinking. Artificial neural networks, space syntax methodologies, predefined rules will help shape the steps of the schematic design process and establish certain limitations. Within the confines of this research, predefined guidelines were used to bring about geometric variances in the design of mass houses. Both traditional and …

Flood Risk Data For Highway Projects, Nabil Ghalayini

Purdue Road School

This presentation will provide project managers and engineers with a clear understanding of available FEMA Risk MAP flood hazard data to better inform project design. This presentation will broadly define flood risk, review the FEMA flood risk database as a source of risk parameters, contrast the regulatory Special Flood Hazard Area (SFHA) with Risk MAP depth and probability grids, and highlight the variability of risk within the SFHA.

Using Ict To Motivate And Achieve Learning Outcomes In Live Teaching Of 650 Students, Juraj Petrović, Predrag Pale

Practice Papers

This paper describes efforts and practices used in teaching a Communication skills course with two full time teachers to approximately 650 enrolled students. It is focused on issues including motivating students if they consider this course to be non-essential for their professional development and a nuisance in their study, achieving learning outcomes in an efficient way, and using of ICT for assessment and self-assessment of communication skills. The ways and means of leveraging ICT in achieving these goals are presented in the paper. The potential of ICT and multimedia to motivate, keep students on schedule, gain their attention in lectures …

An Adaptive Image Restoration Algorithm Based On Hybrid Total Variation Regularization, Cong Thang Pham, Thi Thu Thao Tran, Hung Vi Dang, Hoai Phuong Dang

Turkish Journal of Electrical Engineering and Computer Sciences

In imaging systems, the mixed Poisson-Gaussian noise (MPGN) model can accurately describe the noise present. Total variation (TV) regularization-based methods have been widely utilized for Poisson-Gaussian removal with edge-preserving. However, TV regularization sometimes causes staircase artifacts with piecewise constants. To overcome this issue, we propose a new model in which the regularization term is represented by a combination of total variation and high-order total variation. We study the existence and uniqueness of the minimizer for the considered model. Numerically, the minimization problem can be efficiently solved by the alternating minimization method. Furthermore, we give rigorous convergence analyses of our algorithm. …

Discovering Child Sexual Abuse Material Creators’ Behaviors And Preferences On The Dark Web, Vuong Ngo, Rahul Gajula, Christina Thorpe, Susan Mckeever

Articles

Background: Producing, distributing or discussing child sexual abuse materials (CSAM) is often committed through the dark web in order to remain hidden from search engines and regular users. Additionally, on the dark web, the CSAM creators employ various techniques to avoid detection and conceal their activities. The large volume of CSAM on the dark web presents a global social problem and poses a significant challenge for helplines, hotlines and law enforcement agencies.

Objective: Identifying CSAM discussions on the dark web and uncovering associated metadata insights into characteristics, behaviours and motivation of CSAM creators.

Participants and Setting: We have conducted an …

Strategies Automotive Manufacturing Managers Use To Deliver Work In Alignment With Project Milestones, Sashidhar Mr. Sankaranarayanan

Walden Dissertations and Doctoral Studies

Project managers working in manufacturing firms in the automotive industry frequently face challenges such as cost overruns, schedule delays, and scope changes. Project managers often lack effective strategies to ensure that different departments deliver their work in alignment with project milestones, which can negatively affect project success rates. Grounded in the balanced scorecard framework, the purpose of this qualitative single case study was to explore strategies managers in the automotive manufacturing industry used in their different departments to deliver their work in alignment with project milestones. The participants were three project managers who had successfully implemented strategies that reduced the …

Synergising Bim And Real-Time Data For Improved Efficiency: An Irish Case Study, Ahmed Hassan, Ankur Mitra, Alan Hore, Mark Mulville

Conference papers

The evolution of 3D visualisation and the Internet of Things (IoT) presents a substantial opportunity for integrating real-time data with Building Information Models (BIM) to improve its functionality and construction workflow efficiency. Integrating real-time data with BIM can enhance the digital representation of construction buildings’ physical and functional characteristics and provide recordable status of on-site operations. Nevertheless, the integration between Visualisation and IoT technologies with BIM remains in its preliminary stages and faces a myriad of technical and operational challenges. Furthermore, developing advanced solutions to facilitate this complex integration requires a considerable understanding of the viability and feasibility of merging …

Management Education In An Engineering Environment. The Case Of Bme, Mária Szalmáné Csete, Emma Lógó, Bence Bodrogi, Tamás Koltai

Practice Papers

Engineering higher education institutes need to integrate new skills and competences into their practice and curricula to accelerate the sustainability transition.

This paper introduces the interdisciplinary upskilling of engineering students enrolled in engineering programs at the Budapest University of Technology and Economics (BME) and which has been provided by the Faculty of Economic and Social Sciences (GTK) since 1998. The BME GTK delivers an educational experience that fits into the environment defined by the engineering faculties at BME. The BME GTK has experience of more than a quarter of a century in engineering education related to socio-economic and management upskilling. …

A-Eye Tech: Framework To Evaluate An Ai Construction Visibility Platform, Ahmed Hassan, Alan V. Hore, Mark Mulville

Conference Papers

The authors present the early stages of an Irish government-funded project, A-EYE. This disruptive technology seeks to create a construction visualisation platform that enables measurable productivity advantages through passive data capture and real-time delivery of mission-critical information in an accessible form. The authors outline how they will utilise data captured during construction site operations using camera and sensor equipment to monitor construction resources and processes. Moreover, the positive impact of easy access to visualised data on collaboration between construction stakeholders is discussed. Extensive user-experience research data will be captured after deploying the technology on live projects to create interactive dashboards …

Determining The Interest For A Drone Certification Course, Joel Alberto Ventura

Construction Management

The purpose of this study is to explore the interest of the Construction Management students at California Polytechnic State University, San Luis Obispo with drone usage and acquiring a drone license. This research paper analyzes students' prior skill sets that were gained from a past internship or class and if that exposure to drones is sufficient enough to apply those skills to the construction industry. Implementing a drone certification course will benefit both the students and companies in the construction industry. Within the construction industry there is a rise in popularity with using technology devices to track and collect data, …