Engineering Commons^™

Enrichment Of Turkish Question Answering Systems Using Knowledge Graphs, Okan Çi̇ftçi̇, Fati̇h Soygazi̇, Selma Teki̇r

Turkish Journal of Electrical Engineering and Computer Sciences

Recent capabilities of large language models (LLMs) have transformed many tasks in Natural Language Processing (NLP), including question answering. The state-of-the-art systems do an excellent job of responding in a relevant, persuasive way but cannot guarantee factuality. Knowledge graphs, representing facts as triplets, can be valuable for avoiding errors and inconsistencies with real-world facts. This work introduces a knowledge graph-based approach to Turkish question answering. The proposed approach aims to develop a methodology capable of drawing inferences from a knowledge graph to answer complex multihop questions. We construct the Beyazperde Movie Knowledge Graph (BPMovieKG) and the Turkish Movie Question Answering …

A New Dynamic Classifier Selection Method For Text Classification, İsmai̇l Terzi̇, Alper Kürşat Uysal

Turkish Journal of Electrical Engineering and Computer Sciences

The primary objective of employing multiple classifier systems (MCS) in pattern recognition is to enhance classification accuracy. Dynamic classifier selection (DCS) and dynamic ensemble selection (DES) are two purposeful forms of multiple classifier systems. While DES involves the selection of a classifier set followed by decision combination, DCS opts for the choice of a single competent classifier, eliminating the necessity for classifier combination. As a consequence, DCS methods exhibit superior efficiency in terms of processing time and memory usage compared to DES methods. Moreover, a substantial performance gap exists between the performance of Oracle and both DES and DCS methods. …

Reduction In Porosity In Gmaw-P Welds Of Cp780 Galvanized Steel With Er70s-3 Electrode Using The Taguchi Methodology, Maleni García-Gómez, Francisco Fernando Curiel-López, Jaime Taha-Tijerina, Victor Hugo Lopez-Morelos, Julio César Verduzco-Juárez, Carlos Adrián García-Ochoa

Informatics and Engineering Systems Faculty Publications

In this study, the theoretical welding parameters influencing porosity formation were examined with the aim of reducing or minimizing porosity levels. An experimental design was implemented using the Taguchi methodology for data analysis, resulting in an L9 orthogonal array matrix of experiments. The welding variables considered in the orthogonal array were peak current, peak time, and frequency. Nine lap welds were performed on CP780 steel using the gas metal arc welding process with pulsed arc (GMAW-P), employing an ER70S-3 electrode as filler metal. The percentage of porosity was determined as a response variable, and the actual heat input was treated …

Development Of Satellite-Assisted Forecasting System For Vibrio Vulnificus Prevalence In Coastal Waters, Saber Aradpour

LSU Doctoral Dissertations

Vibrio vulnificus is a halophilic gamma proteobacterium that is autochthonous to coastal waters and is responsible for 50% of seafood-related deaths in the United States. This study presents a series of nowcasting and forecasting models for predicting vibrio vulnificus abundance in oysters by identifying the long-range dependence of vibrio vulnificus abundance on antecedent environmental conditions and detecting the environmental conditions using satellite remote sensing technology. It was discovered that vibrio vulnificus abundance exhibits a long-range dependence on antecedent environmental conditions which can be characterized by seven independent environmental predictors (stressors) including sea surface temperature (SST), water level (WL), sea surface …

Network Intrusion Detection Based On Machine Learning Strategies: Performance Comparisons On Imbalanced Wired, Wireless, And Software-Defined Networking (Sdn) Network Traffics, Hi̇lal Hacilar, Zafer Aydin, Vehbi̇ Çağri Güngör

Turkish Journal of Electrical Engineering and Computer Sciences

The rapid growth of computer networks emphasizes the urgency of addressing security issues. Organizations rely on network intrusion detection systems (NIDSs) to protect sensitive data from unauthorized access and theft. These systems analyze network traffic to detect suspicious activities, such as attempted breaches or cyberattacks. However, existing studies lack a thorough assessment of class imbalances and classification performance for different types of network intrusions: wired, wireless, and software-defined networking (SDN). This research aims to fill this gap by examining these networks’ imbalances, feature selection, and binary classification to enhance intrusion detection system efficiency. Various techniques such as SMOTE, ROS, ADASYN, …

Rational Design Of Lignin-First Biorefineries Through Lignin Analysis And Deconstruction Modeling Tools, Aditya Ponukumati

McKelvey School of Engineering Graduate Student Theses & Dissertations

Lignocellulosic biomass is produced photosynthetically from atmospheric CO2 and is one of the few sources of renewable, reduced carbon that is generated on a scale comparable to demand for chemical commodities. For a sense of scale, the U.S. Energy Security and Independence Act targets the production of approximately 16 billion gallons per year of second-generation lignocellulosic biofuels by 2025. That production would generate approximately 62 million tons per year of dry lignin byproducts. The focus of this dissertation is on the valorization of these lignin components of biomass. Currently, lignin is either discarded or burned for local heat or electricity …

Adaptable Quantum Education Platform Using Learning Objects, Krishna Puja Anumula

Master's Theses

In recent years, the need to make classroom learning more interactive and engaging has become increasingly important. The lack of workforce in interdisciplinary fields such as quantum networking and quantum internet requires a new approach that addresses every learner’s individual needs. To address this challenge, this thesis introduces an adaptive learning platform rooted in the theory of learning objects and Kolb’s experiential learning model. The platform aids educators and learners in designing and utilizing various learning objects for quantum networking and quantum internet.

The platform enables educators and learners to build their own lessons and lesson plans using learning objects …

Enhancement Of Mechanical Properties Of Pcl/Pla/Dmso2 Composites For Bone Tissue Engineering, Kyung-Eun Min, Jae-Won Jang, Cheolhee Kim, Sung Yi

Mechanical and Materials Engineering Faculty Publications and Presentations

Bone tissue engineering shows potential for regenerating or replacing damaged bone tissues by utilizing biomaterials renowned for their biocompatibility and structural support capabilities. Among these biomaterials, polycaprolactone (PCL) and polylactic acid (PLA) have gained attention due to their biodegradability and versatile applications. However, challenges such as low degradation rates and poor mechanical properties limit their effectiveness. Dimethyl sulfone (DMSO₂) has emerged as a potential additive to address these limitations, offering benefits such as reduced viscosity, increased degradation time, and enhanced surface tension. In this study, we investigate tailored composites comprising PLA, PCL, and DMSO₂ to enhance mechanical …

Efficient Deep Neural Network Compression For Environmental Sound Classification On Microcontroller Units, Shan Chen, Na Meng, Haoyuan Li, Weiwei Fang

Turkish Journal of Electrical Engineering and Computer Sciences

Environmental sound classification (ESC) is one of the important research topics within the non-speech audio classification field. While deep neural networks (DNNs) have achieved significant advances in ESC recently, their high computational and memory demands render them highly unsuitable for direct deployment on resource-constrained Internet of Things (IoT) devices based on microcontroller units (MCUs). To address this challenge, we propose a novel DNN compression framework specifically designed for such devices. On the one hand, we leverage pruning techniques to significantly compress the large number of model parameters in DNNs. To reduce the accuracy loss that follows pruning, we propose a …

A New Approach: Ordinal Predictive Maintenance With Ensemble Binary Decomposition (Opmeb), Ozlem Ece Yurek, Derya Birant

Turkish Journal of Electrical Engineering and Computer Sciences

Predictive maintenance (PdM), a fundamental element of modern industrial systems, employs machine learning to monitor equipment conditions, estimate failure probabilities, and optimize maintenance schedules. Its core objective is to enhance equipment reliability, extend lifespan, and minimize costs through data-driven insights by enabling efficient maintenance scheduling, reducing downtime, and optimizing resource allocation. In this paper, we propose a novel ordinal predictive maintenance with ensemble binary decomposition (OPMEB) method for the PdM domain, considering the hierarchical nature of class labels reflecting the machine's health status, including categories like healthy, low risk, moderate risk, and high risk. The proposed OPMEB method was validated …

A Real-Time Embedded System Designed For Nilm Studies With A Novel Competitive Decision Process Algorithm, Sai̇d Mahmut Çinar, Rasi̇m Doğan, Emre Akarslan

Turkish Journal of Electrical Engineering and Computer Sciences

This paper explores the determination of any load or load combination in a power system at any moment. This process requires measurements at the main electric utility service entry of a house, known as nonintrusive measurement. To accurately identify loads, total harmonic distortion, RMS, third harmonic currents, and power consumption are considered their fingerprints. Based on these fingerprints, an algorithm called the competitive decision process is developed and integrated into an embedded system. This algorithm has a two-level decision mechanism. In the first stage, the winner loads with the highest similarity scores from each feature are determined, and the loads …

Multi-Label Voice Disorder Classification Using Raw Waveforms, Gökay Di̇şken

Turkish Journal of Electrical Engineering and Computer Sciences

Automated voice disorder systems that distinguish pathological voices from healthy ones have been developed with the aid of machine learning methods. Both clinicians and patients can benefit from these systems as they provide many advantages, compared to the invasive techniques. These systems can produce binary (healthy/pathological) or multi-class (healthy/selected pathologies) decisions. However, multiple disorders might exist in an individual’s voice. Multi-label classification should be considered in such cases. By this time, only a single report is available on this topic, where hand-crafted features were used, and a data augmentation technique was utilized to overcome class imbalances. In this study, a …

Ensemble Learning For Accurate Prediction Of Heart Sounds Using Gammatonegram Images, Sinam Ashinikumar Singh, Sinam Ajitkumar Singh, Aheibam Dinamani Singh

Turkish Journal of Electrical Engineering and Computer Sciences

The analysis of heart sound signals constitutes a pivotal domain in healthcare, with the prediction of imbalanced heart sounds offering critical diagnostic insights. However, the inherent diversity in cardiac sound patterns presents a substantial challenge in predicting imbalanced signals. Many scientific disciplines have focused a great deal of emphasis on the problem of class inequality. We introduce an ensemble learning approach employing a convolutional neural network model-based deep learning algorithm to effectively tackle the challenges associated with predicting imbalanced heart sound signals. We use a Gammatone filter bank to extract relevant features from the heard sound signal. Our approach leverages …

Detection And Classification Of Unauthorized Use Of Irrigation Motors In Agricultural Irrigation, Önder Ci̇velek, Sedat Görmüş, Hali̇l İbrahi̇m Okumuş, Orhan Gazi̇ Kederoglu

Turkish Journal of Electrical Engineering and Computer Sciences

The decarbonisation of electricity generation requires the real-time monitoring and control of grid components in order to efficiently and timely dispatch demand. This highly automated system, known as the Smart Grid, relies on smart or sensor-equipped distribution network components to optimise energy flow and minimise losses. However, energy theft, a major obstacle to efficient resource utilisation, poses a significant challenge to achieving this goal. This study proposes and evaluates a real-time telemetry and control system designed to mitigate energy theft in agricultural irrigation applications. The system increases energy efficiency by tracking the energy use in agricultural irrigation. The key challenge …

Pyrolysis Characteristics And Pore-Fracture Evolutionary Patterns Of Tar-Rich Coals, Geng Jishi, Wang Shuangming, Sun Qiang, Hou Enke, Yang Yuru, Hu Xin, Xue Shengze

Coal Geology & Exploration

Objective Extracting coal-based oil and gas from tar-rich coal through in situ pyrolysis plays a significant role in counteracting the shortage of China's oil and gas resources and enhancing the utilization efficiency of coal resources, representing a new trend for the efficient exploitation of tar-rich coals. During the in situ pyrolysis of tar-rich coals, the internal heat transfer, as well as the migration and production of pyrolysis products, is directly influenced by the oil and gas production characteristics and the characteristics of pores and fractures. Hence, it is particularly critical to identify the pyrolysis characteristics and pore-fracture evolutionary patterns of …

Multimodal Data Integration For Oncology In The Era Of Deep Neural Networks: A Review, Asim Waqas, Aakash Tripathi, Ravi P. Ramachandran, Paul A. Stewart, Ghulam Rasool

Henry M. Rowan College of Engineering Departmental Research

Cancer research encompasses data across various scales, modalities, and resolutions, from screening and diagnostic imaging to digitized histopathology slides to various types of molecular data and clinical records. The integration of these diverse data types for personalized cancer care and predictive modeling holds the promise of enhancing the accuracy and reliability of cancer screening, diagnosis, and treatment. Traditional analytical methods, which often focus on isolated or unimodal information, fall short of capturing the complex and heterogeneous nature of cancer data. The advent of deep neural networks has spurred the development of sophisticated multimodal data fusion techniques capable of extracting and …

In-Situ Pyrolysis Of Tar-Rich Coal: Effects On Geological Environments And Geological Guarantee Technology, Xu Shiang, Zhang Pingsong, Cheng Gang, Wu Haibo

Coal Geology & Exploration

Objective Tar-rich coal, a type of unique unconventional oil and gas resource that integrates coal, oil, and gas, can be transformed into tar, combustible gases, and semi-coke solid fuels with high added value through in-situ pyrolysis. Therefore, the in-situ pyrolysis of tar-rich coal has the potential to meet the challenges in achieving the green exploitation and clean, low-carbon utilization of coals in the traditional coal industry. Furthermore, in terms of how to reduce coal pollution emissions and enhance energy efficiency, this technology offers a new solution for attaining the goals of peak carbon dioxide emissions and carbon neutrality. It also …

Distributed Energy Trading Models Utilizing Reinforcement Learning And Game-Theoretic Based Approaches In Smart Grids, Nicholas Kemp

Electrical and Computer Engineering ETDs

Community-driven energy initiatives have become crucial for effective energy management, particularly in trading and management. The rise of Distributed Energy Resources in smart grids demands a redesign of traditional Demand Response Management (DRM) models to account for prosumers' dynamic behavior in energy markets. Decentralization, including peer-to-peer (P2P) energy trading, is vital for resilience and sustainability. This thesis introduces two coalitional DRM models: one based on hedonic community formation games, and the other combining matching theory with coalition games. These models empower prosumers to autonomously select energy trading communities using partially available data. To optimize energy consumption, two additional models are …

Ultrasonic Cigarettes: Chemicals And Cytotoxicity Are Similar To Heated-Coil Pod-Style Electronic Cigarettes., Esther E. Omaiye, Wentai Luo, Kevin J. Mcwhirter, Prue Talbot

Civil and Environmental Engineering Faculty Publications and Presentations

Our purpose was to test the hypothesis that ultrasonic cigarettes (u-cigarettes), which operate at relatively low temperatures, produce aerosols that are less harmful than heated-coil pod-style electronic cigarettes (e-cigarettes). The major chemicals in SURGE u-cigarette fluids and aerosols were quantified, their cytotoxicity and cellular effects were assessed, and a Margin of Exposure risk assessment was performed on chemicals in SURGE fluids. Four SURGE u-cigarette flavor variants ("Blueberry Ice," "Watermelon Ice," "Green Mint," and "Polar Mint") were evaluated. Flavor chemicals were quantified in fluids and aerosols using gas chromatography/mass spectrometry. Cytotoxicity and cell dynamics were assessed using the MTT assay, live-cell …

Examining Driver Injury Severity In Motor Vehicle Crashes: A Copula-Based Approach Considering Temporal Heterogeneity In A Developing Country Context, Shahrior Pervaz, Tanmoy Bhowmik, Naveen Eluru

Civil and Environmental Engineering Faculty Publications and Presentations

Using data from a developing country, the current study develops a copula-based joint modeling framework to study crash type and driver injury severity as two dimensions of the severity process. To be specific, a copula-based multinomial logit model (for crash type) and generalized ordered logit model (for driver severity) is estimated in the study. The data for our analysis is drawn from Bangladesh for the years of 2000 to 2015. Given the presence of multiple years of data, we develop a novel spline variable generation approach that facilitates easy testing of variation in parameters across time in crash type and …

A Survey On Fused Filament Fabrication To Produce Functionally Gradient Materials, Arup Dey, Monsuru Ramoni, Nita Yodo

Manufacturing & Industrial Engineering Faculty Publications

Fused filament fabrication (FFF) is a key extrusion-based additive manufacturing (AM) process for fabricating components from polymers and their composites. Functionally gradient materials (FGMs) exhibit spatially varying properties by modulating chemical compositions, microstructures, and design attributes, offering enhanced performance over homogeneous materials and conventional composites. These materials are pivotal in aerospace, automotive, and medical applications, where the optimization of weight, cost, and functional properties is critical. Conventional FGM manufacturing techniques are hindered by complexity, high costs, and limited precision. AM, particularly FFF, presents a promising alternative for FGM production, though its application is predominantly confined to research settings. This paper …

Modeling Powder Spreadability In Powder-Based Processes Using The Discrete Element Method, Austin T. Sutton, M. Hossein Sehhat, Ming C. Leu, Joseph W. Newkirk

Mechanical and Aerospace Engineering Faculty Research & Creative Works

Powder-bed fusion (PBF) processes refer to a subset of Additive Manufacturing (AM) techniques where powder is spread on the build-plate before melting (by a laser or electron beam). While PBF processes are attractive due to their ability for realizing complex structures that are either difficult or impossible to create through conventional means, the parts fabricated with these techniques can exhibit defects such as pores, inclusions, and excessive surface roughness. To minimize these defects, much research has been dedicated towards process maturation by optimizing laser or electron beam parameters. However, these developmental efforts typically do not address the recoating process where …

Pilot Experiment For Underground In-Situ Pyrolysis Of Tar-Rich Coal In The Northern Shaanxi Province, Duan Zhonghui, Yang Fu, Wang Zhendong, Ma Li, Duan Xiaoqing, Cao Husheng, Chen Liang

Coal Geology & Exploration

Objective The breakthrough of the pilot experiment for underground in-situ pyrolysis of tar-rich coal in the northern Shaanxi has added new vitality to the research on in-situ conversion of fossil energy such as tar-rich coal and oil shale, and the results have attracted wide attention both inside and outside the industry. The research on underground in-situ pyrolysis of tar rich coal is still in its infancy, lacking systematic research on field engineering data.Methods Based on the pilot experiment, the main geological conditions and engineering difficulties have been clarified, and the progress of underground in-situ pyrolysis has been summarized. The …

Geological Factors Controlling The Occurrence Of Carboniferous-Permian Tar-Rich Coals In The Ningdong Coalfield, Huang Pengcheng, Guo Weiyong, Ji Xiaoyan, Cai Feifei, Zhang Zhifeng, Huang Kang, Cheng Yunqiang, Liu Zheng, Wang Bei, Chen Rong, Shi Qingmin

Coal Geology & Exploration

Objective The Ningdong Coalfield of the Ordos Basin boasts abundant tar-rich coal resources, of which tar-rich coals in the Carboniferous-Permian coal seams exhibit unique occurrence characteristics due to differences in thermal evolution and sedimentary environments. Methods This study analyzed the occurrence characteristics and critical material composition of tar-rich coals in the Hongdunzi and Siguquan mining areas. Based on this, it explored the controlling effects of the degree of coalification and sedimentary environment on the tar yield. Results and Conclusions The results indicate that the Carboniferous-Permian coal seams in the Ningdong Coalfield exhibit average tar yields ranging from 7.15% to 11.07%, …

Distributions Of Products From The Pyrolysis Of Tar-Rich Coals For Tar Extraction In Northern Shaanxi Province, China, Yu Zunyi, Guo Wei, Yang Panxi, Gao Kun, Yang Fu, Ma Li, Wang Jing, Li Hongqiang, Yang Bolun, Wu Zhiqiang

Coal Geology & Exploration

Objective Tar-rich coals stand as a special type of coal resource that integrates coal, oil, and gas properties. These coals, boasting abundant hydrogen-rich structures such as side chains and bridge bonds with aliphatic structures, are prone to crack and produce tar and gas during pyrolysis. These establish tar-rich coals as ideal raw materials that produce oil and gas through thermal conversion. Presently, the research into tar extraction from tar-rich coals through pyrolysis remains in its initial stage, and exploring the impacts of technological conditions, including heat carrier, heating type, and pyrolysis temperature, on the pyrolysis process holds critical significance for …

Simulation Of The Pyrolysis Process Of Tar-Rich Coals In An H2O Atmosphere Based On The Reactive Force Field Molecular Dynamics, Huang Zibo, Liu Qianru, Liu Hong, Zhou Wenjing, Wei Jinjia

Coal Geology & Exploration

Objective Tar-rich coal resources, abundant in China, can be converted into energy products (e.g., chemicals and gas/liquid fuels) through pyrolysis, thus alleviating the country’s dependence on oil and gas imports. A thorough understanding of the product evolution and reaction mechanisms of the pyrolysis of tar-rich coals is crucial to research into the clean and efficient conversion processes of coals. Methods Based on the reactive force field molecular dynamics (ReaxFF MD), this study simulated the pyrolysis process of tar-rich coals (long-flame coals) and explored the impacts of the H₂O atmosphere on the distribution of pyrolytic products, along with the …

Spatiotemporal Distributions Of Typical Contaminants From The In-Situ Pyrolysis Of Tar-Rich Coals, Tian Hua, Zhang Ruolin, Wang Qianji, Wu Xiaoyu, Zhang Lei, Zhang Lingru, Fang Siyuan

Coal Geology & Exploration

Objective and Methods Under high temperatures, oil and gas produced from the in situ pyrolysis of tar-rich coals will migrate toward and accumulate in the overburden strata after passing through the fracture zones on the coal seam roof, causing potential contamination risks for the underground environment. To understand the release and distribution characteristics of typical contaminants generated from the underground pyrolysis of tar-rich coals, this study investigated the typical tar-rich coals from the Shenfu mining area of the Jurassic coalfield in northern Shaanxi Province. Based on data on the stratigraphic structures and lithology and using the self-developed equipment for similarity …

Downhole Heaters For In-Situ Pyrolysis Of Tar-Rich Coals：A Review And Prospects, Wang Zhendong, Duan Zhonghui, Yang Fu, Ma Li

Coal Geology & Exploration

Significance China boasts abundant tar-rich coal resources, which prove to be potential coal-based oil and gas resources capable of ensuring China's energy security. Extracting hydrogen while preserving carbon through the in-situ pyrolysis of tar-rich coals has developed into a trend in the clean and low-carbon utilization of coal resources. Downhole heaters serve as critical equipment for the efficient in-situ pyrolysis of tar-rich coals. Advances Based on investigations and the systematic collection of relevant information and data, this study offers a brief introduction of the currently used methods for in-situ convection heating, focusing on the present situation of the research and …

Exploring The Pyrolysis Of Tar-Rich Coals Under The Catalysis Of Cerium-Modified Magnetic Core-Shell Hzsm-5, Zhou Anning, Zhang Zhi, Chen Yongan, Zhang Huaiqing, Bai Zhuangwei, Shi Zhiwei, He Xinfu

Coal Geology & Exploration

Objective Tar-rich coals are valuable resources integrating coal, tar, and gas properties. Catalytic pyrolysis serves as a significant approach for achieving green and low-carbon development of tar-rich coals. However, the research and development of efficient and recyclable catalysts for the pyrolysis of tar-rich coals remains highly challenging. Methods With HZSM-5@SiO₂@MgFe₂O₄ (HSMF) as the raw material, this study prepared HZSM-5@SiO₂@MgFe₂O₄ (mHSMF) with a hierarchical porous structure using the hydrothermal method and alkali modification, followed by the preparation of cerium-modified mHSMF (5-CeO₂/mHSMF) using the precipitation method. Employing a fixed-bed reactor, …

Vertiport Ventures: Assessing Operational Feasibility For Evtol Integration In São Paulo’S Helipad And Heliport Infrastructure, Peter E. O'Reilly, Ramy A. Rahimi, Jorge Luiz Rosa Marques, Marco Aurélio Feitosa De A. L. Babadopulos1

Publications

The objective of this study is to assess the operational viability of introducing Electric Vertical Take-Of and Landing (eVTOL) vehicles in São Paulo and its metropolitan area, utilizing existing helipads and helicopter infrastructure. eVTOL aircraft, capable of vertical take-of and landing like helicopters, difer from traditional helicopters in their propulsion systems, with eVTOLs typically featuring multiple smaller electric motor-driven propulsion units instead of internal combustion engines and mechanical transmissions (Schuchardt et al. 2023). The study specifcally targets eVTOLs with the capacity to transport a minimum of four passengers and one pilot for distances of at least 50 km. Appendix provides …