Digital Commons Network^™

Understanding The Impact Of Trade Policy Effect Uncertainty On Firm-Level Innovation Investment: A Deep Learning Approach, Daniel Chang, Nan Hu, Peng Liang, Morgan Swink

Research Collection School Of Computing and Information Systems

Integrating the real options perspective and resource dependence theory, this study examines how firms adjust their innovation investments to trade policy effect uncertainty (TPEU), a less studied type of firm specific, perceived environmental uncertainty in which managers have difficulty predicting how potential policy changes will affect business operations. To develop a text-based, context-dependent, time-varying measure of firm-level perceived TPEU, we apply Bidirectional Encoder Representations from Transformers (BERT), a state-of-the-art deep learning approach. We apply BERT to analyze the texts of mandatory Management Discussion and Analysis (MD&A) sections of annual reports for a sample of 22,669 firm-year observations from 3,181 unique …

End-User Device Management In The Air And Space Forces, Joshua Bonvissuto

Theses and Dissertations

When achieving technical superiority is a matter a national security, it is critical that the Department of the Air Force (DAF) employs a robust Information Technology Asset Management (ITAM) strategy that maximizes mission effectiveness. Since 2022, the Office of the Chief Information Officer (SAF/CN) has been developing a plan to transform the Air Force’s ITAM strategy, primarily intending to centralize End User Device (EUD) procurement to the DAF level. For this study, a Delphi study was conducted to gather expert opinions on key aspects of SAF/CN’s new ITAM strategy to identify strengths, weaknesses, and implementation challenges. This research provides valuable …

Artificial Intelligence And Perception: An Empirical Study, Anthony J. Neil

Theses and Dissertations

This thesis investigates the impact of adjusting artificial intelligence explainability levels’ outputs on user perception. The overarching study extends within the Explainable Artificial Intelligence (XAI) domain. It examines a spectrum of variables, including performance, cognizance, familiarity, transparency, system bias, and the overall impact of AI, to understand their collective and individual effects that enable effective professional use in an organization. The study aims to illuminate the relationship between the degree of explainability provided by large language models such as ChatGPT, Bard, and Bing AI and the performance of these models when tasked with XAI adjustments.

Text Summarization, Varun Gottam, Anusha Vunnam, Purna Sarovar Puvvada

Symposium of Student Scholars

The current era is known as the information era. Every day, millions of gigabytes of data are being transferred from one point to another. As the creation of data became easy, it became hard to keep track of the important points and the gist of data especially in areas such as research and news. To solve this conundrum, text summarization is introduced. This is a process of summarizing text from across different documents or large datasets such that it can be read and understood easily by both humans and machines.

Neutrosophic Insights Into Military Interventions: Assessing Legitimacy And Consequences In International Law, Salame Ortiz Mónica Alexandra, Jiménez Martínez Roberto Carlos, Piñas Piñas Luis Fernando

Neutrosophic Systems with Applications

This scientific paper analyzes the legitimacy of military interventions within the framework of international law and their potential consequences. It highlights the need to support these interventions with robust legal and moral reasoning due to their complexity and controversy in the international community. The interpretation of legal and ethical principles can be subjective and lead to disagreements among states and international actors. The consequences of military interventions are explored, ranging from loss of life and infrastructure destruction to population displacement, political instability, and humanitarian crises. Legality and proportionality in interventions are essential to ensuring their legitimacy, and the potential consequences …

Detecting Substance Use Disorder Using Social Media Data And Dark Web: Time And Knowledge Aware Study, Usha Lokala, Orchid Chetia Phukan, Triyasha Ghosh Dastidar, Francois Lamy, Raminta Daniulaityte, Amit Sheth

Faculty Publications

Opioid and substance misuse is rampant in the United States today, with the phenomenon known as the "opioid crisis". The relationship between substance use and mental health has been extensively studied, with one possible relationship being: substance misuse causes poor mental health. However, the lack of evidence on the relationship has resulted in opioids being largely inaccessible through legal means. This study analyzes the substance use posts on social media with opioids being sold through crypto market listings. We use the Drug Abuse Ontology, state-of-the-art deep learning, and knowledge-aware BERT-based models to generate sentiment and emotion for the social media …

Design And Development Of An Inert Controlled Environmental Chamber For Evaluation Of Contaminant Mass Transfer, Brian Magnuson, Zachary Limaye

The Journal of Purdue Undergraduate Research

No abstract provided.

Investigation Of Machine Learning Driven Adaptive Control Strategy For Heat Exchanger Under Varying Fouling Conditions, Reshma Madhu Pk

Theses and Dissertations

Fouling is an undesirable and inevitable phenomenon that affects Heat Exchanger (HE) dynamics, increases maintenance cost (>50%), and loss of production. Conventional fouling prediction and control techniques demand an in-depth understanding of the HE-specific fouling dynamics. Hence, machine learning emerges as an ideal tool for learning the fouling process from the available measurement dataset.

The proposed work aims to design a machine learning-driven adaptive control technique for an industrial HE, subjected to varying fouling conditions. Naphtha cooler, an industrial HE utilized in petroleum refineries, employs cooling water to lower Naphtha temperature, but the high impurities in the recycled cooling …

Unveiling Efficiency: Investigating Distance Measures In Wastewater Treatment Using Interval-Valued Neutrosophic Fuzzy Soft Set, Muhammad Saeed, Kinza Kareem, Fatima Razzaq, Muhammad Saqlain

Neutrosophic Systems with Applications

To reduce the threats that wastewater poses to human health and the environment, water treatment techniques must be improved. The use of a procedure that includes preparation, testing, primary and secondary treatments, filtration, disinfection, and continuous monitoring is therefore required. The objective of this research is to create a hybrid notion that extends the idea of an interval-valued neutrosophic fuzzy soft set (IVNFSS) to an interval-valued neutrosophic fuzzy set. Operations like complement, union, and integration are included in the idea. To improve decision-making accuracy, a quality-assessment distance measure is incorporated, offering a numerical representation of the disparity between various factors. …

Extended Event Calculus Using Neutrosophic Logic: Method, Implementation, Analysis, Recent Progress And Future Directions, Antonios Paraskevas

Neutrosophic Systems with Applications

Brains do not reason as digital computers do. Computers reason in clear steps with statements that are either true or false, while humans reason with vague terms of common sense. Neutrosophy is a new branch of philosophy and machine intelligence that deals with neutralities, specifically the idea of indeterminacy that is evident and experienced in our everyday lives. Indeterminacy is interpreted as everything that falls between a concept, idea, statement, declaration, etc. and its opposite. The fundamental thesis of neutrosophy is to employ neutrosophic logic, an extension of fuzzy logic, to incorporate fuzzy truth into complex schemes of formal reasoning. …

Embedded Deep Learning To Improve The Performance Of Approaches For Extinct Heritage Images Denoising, Ali Salim Rasheed, Alaa Hamza Omran

Iraqi Journal for Computer Science and Mathematics

Many advanced deep convolutional neural network (DCNN) methods have proven their efficacy in reconstructing the texture of super-resolution images (SR) from low-resolution images (LR). Nevertheless, the objective of achieving super-resolution (SR) reconstruction using Deep Convolutional Neural Networks (DCNN) becomes difficult when the input image is distorted by noise. Photographs captured at the inception of the camera are presently regarded as acultural heritage that chronicles an important periodin human history; however, they are marred by low resolution and noise as a result of obsolescence and the primitive nature of the technology that captured them, in contrast to the technological advances that …

An Integrative Computational Intelligence For Robust Anomaly Detection In Social Networks, Helina Rajini Suresh, K R. Harsavarthini, R Mageswaran, Hirald Dwaraka Praveena, C Gnanaprakasam, C.Sakthi Lakshmi Priya

Iraqi Journal for Computer Science and Mathematics

Anomaly detection is one of the most important tasks for maintaining the integrity, security, and trustworthiness of online communities in a social network. This paper proposes AdaptoDetect, which represents a new framework; it discusses a new anomaly detection approach called Pufferfish Optimization Technique for feature selection, together with a Graph Embedding Autoencoder for identifying anomalies. What makes AdaptoDetect special is that, with the use of POT, it has a distinctive capability in dynamic adaptation against network changes by selecting only the most relevant features in social network data. The technique for optimization underlines the important attributes for anomaly detection so …

Pairing New Approach Of Tree Soft With Mcdm Techniques: Toward Advisory An Outstanding Web Service Provider Based On Qos Levels, Sara Fawaz Al-Baker, Ibrahim El-Henawy, Mona Mohamed

Neutrosophic Systems with Applications

Web services (WSs) have become dynamic because of technological advancements and internet usage. Hence, selecting a WS provider among a variety of WS providers that perform the same function is a critical process. However, the crucial point is that various consumers may have varied needs when it comes to the quality attributes of services, such as cost, response time, throughput, security, availability, etc. These aspects of Web services are known as quality of service (QoS), or non-functional characteristics. Hence, this issue is the robust motivator for conducting this study. The objective of this study is to evaluate a set of …

Fuzzy Inference Full Implication Method Based On Single Valued Neutrosophic T-Representable T-Norm: Purposes, Strategies, And A Proof-Of-Principle Study, Minxia Luo, Ziyang Sun, Donghui Xu, Lixian Wu

Neutrosophic Systems with Applications

As a generalization of intuitionistic fuzzy sets, single-valued neutrosophic sets have certain advantages in solving indeterminate and inconsistent information. In this paper, we study the fuzzy inference full implication method based on single-valued neutrosophic t-representable t-norm. Firstly, single-valued neutrosophic fuzzy inference triple I principles for fuzzy modus ponens and fuzzy modus tollens are given. Then, single-valued neutrosophic R-type triple I solutions for FMP and FMT are given. Finally, the robustness of the full implication triple I method based on the left-continuous single-valued neutrosophic t-representable t-norm is investigated. As a special case of the main results, the sensitivity of full implication …

Utilizing Culturally Responsive Strategies To Inspire African American Female Participation In Cybersecurity, Deanna Bailey, Michel Kornegay, Ladawn Partlow, Charnee Bowens, Karen Gareis, Kevin Kornegay

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

The number of African American females participating in cyber fields is significantly low. Science, technology, engineering, and mathematics (STEM) education requires a new approach to student engagement to increase African American female participation in cybersecurity. The most common approach to engaging more African American females in STEM is to provide students access to professional images or role models active in STEM; however, more is needed. More race-centered strategies beyond role modeling are necessary to attract and retain African American females in STEM. Research studies show that integrating personal experiences and making cultural connections can help improve student participation in STEM …

Me-Em 2022-23 Annual Report, Department Of Mechanical Engineering-Engineering Mechanics, Michigan Technological University

Department of Mechanical and Aerospace Engineering Annual Reports

Table of Contents

• Research Updates
• Curriculum and Instruction
• Facilities
• New Faculty
• Research, Machine Learning
• Research, Ana Dyreson
• In Memoriam
• Student Success
• Alumni Profile and Activity
• Graduates
• Faculty Awards and Honors
• Patents and Publications
• Donors
• Grants and Contracts

Inclusive Counterfactual Generation: Leveraging Llms In Identifying Online Hate, M. Atif Qureshi, Arjumand Younus, Simon Caton

Articles

Counterfactually augmented data has recently been proposed as a successful solution for socially situated NLP tasks such as hate speech detection. The chief component within the existing counterfactual data augmentation pipeline, however, involves manually flipping labels and making minimal content edits to training data. In a hate speech context, these forms of editing have been shown to still retain offensive hate speech content. Inspired by the recent success of large language models (LLMs), especially the development of ChatGPT, which have demonstrated improved language comprehension abilities, we propose an inclusivity-oriented approach to automatically generate counterfactually augmented data using LLMs. We show …

Analyzing The Impact Of Db Versus Dbb On Cost Performance In Airport Development: A Data-Driven Approach, Ramy Khalef, Islam H. El-Adaway

Civil, Architectural and Environmental Engineering Faculty Research & Creative Works

The Construction Of Airport Projects Can Be Complex And Costly Due To The Many Stakeholders Involved And Associated Strict Timelines. Traditional Delivery Methods, Such As Design-Bid-Build (DBB), Employed In Airport Projects Often Result In Major Cost Overruns Due To Multiple Facets. Design-Build (DB) Is A Construction Method That Combines Design And Construction Under A Single Entity, And It Has The Potential To Improve Cost Performance. None Have Evaluated DB From A Cost Perspective In The Airport Sector. This Research Fills This Gap. First, The Data Is Collected And Assessed For Validity. Second, Risk Ratings For Cost Performance Are Computed. Finally, …

Effects Of Psycho-Attitudinal Characteristics On Drivers’ Behavior: A Driving Simulator Study, Francesco Galante, Filomena Mauriello, Simone Fucito, Mariano Pernetti, Alfonso Montella

Kentucky Transportation Center Presentations

Human factors are crucial in causing traffic crashes and researchers try to identify and understand these factors to explore patterns of risky driving behavior and its consequences. It is clear that human factors play a crucial role in the causation of traffic accidents, and researchers are trying to identify and understand these factors. That is why it is important to explore the patterns that identify drivers prone to risky driving behavior and the possible negative consequences of that behavior At this aim, an experiment was conducted using the VERA dynamic driving simulator at the Road Safety Laboratory of the University …

The Trouble With Technology, John O'Connor

Conference Papers

In contemporary education, technology is either hailed as the panacea for affordable mass education or dreaded as a threat to our humanity. At the European Culture and Technology Laboratory, technology is understood in the context of the Ancient Greek origin of the word: technē—meaning a system or a method of making or doing, an art or a craft; a technique or a practice, even a way of thinking. The tools humans use are not merely a means of intervention in our environment but also a way of becoming human and thus, technology has a fundamental impact on our identity and …

Bert-Based Detection Of Ai-Generated Text For Content Verification, Soham Biren Katlariwala

2024 REYES Proceedings

With advancements in AI-driven natural language generation, distinguishing between AI-generated and human-written text has become imperative for ensuring content authenticity across industries. This study explores the effectiveness of Bidirectional Encoder Representations from Transformers (BERT) in addressing this classification challenge. Utilizing a diverse dataset and robust preprocessing techniques, BERT achieved a peak F1-score of 0.94364, outperforming traditional models such as Logistic Regression and Support Vector Machines. The results underscore the potential of transformer-based models in addressing real-world con- tent verification problems. Future enhancements include fine-tuning and expanding datasets for greater generalizability.

การจัดลำดับความสำคัญของบทวิจารณ์ของผู้ใช้ซอฟต์แวร์โดยคำนึงถึงประสบการณ์ผู้ใช้โดยใช้การเรียนรู้ของเครื่อง, ลักษณ์สิปาง สาครวิจิตรี

Chulalongkorn University Theses and Dissertations (Chula ETD)

ปัจจุบันตลาดโมไบล์แอปพลิเคชันมีการแข่งขันสูง นักพัฒนาจึงจำเป็นต้องให้ความสำคัญกับบทวิจารณ์ของผู้ใช้ซึ่งบ่งบอกถึงความคิดเห็นและประสบการณ์ของผู้ใช้งานจริง เพื่อนำไปสู่การปรับปรุงและพัฒนาฟังก์ชันการทำงานให้ตรงตามความต้องการของผู้ใช้มากยิ่งขึ้น อย่างไรก็ตาม แอปพลิเคชันยอดนิยมมักมีบทวิจารณ์จำนวนมาก ทำให้เกิดข้อจำกัดในการที่นักพัฒนาจะสามารถอ่านและวิเคราะห์บทวิจารณ์ทั้งหมดได้อย่างมีประสิทธิภาพ เพื่อจัดการกับปัญหาดังกล่าว งานวิจัยฉบับนี้จึงนำเทคโนโลยีการเรียนรู้ของเครื่องเข้ามาช่วยในการจำแนกประเภทของบทวิจารณ์ โดยพิจารณาจากเนื้อหาในบทวิจารณ์ของผู้ใช้ซึ่งอาจสะท้อนถึงปัญหา ข้อบกพร่อง หรือข้อเสนอในการพัฒนาฟังก์ชันใหม่ ข้อมูลที่ได้จะถูกนำไปใช้จัดลำดับความสำคัญของการแก้ไขปรับปรุงตามผลกระทบที่มีต่อประสบการณ์ของผู้ใช้ งานวิจัยนี้ได้กำหนดหมวดหมู่ของบทวิจารณ์ไว้ทั้งหมด 5 ประเภท ได้แก่ ปัญหาด้านความจำเป็นพื้นฐาน, ปัญหาด้านการปฏิบัติ, ปัญหาด้านความเพลิดเพลิน, ปัญหาด้านความแปลกใหม่ และปัญหาอื่น ๆ ซึ่งสะท้อนลำดับความสำคัญของปัญหาจากมุมมองของผู้ใช้ ในการพัฒนาโมเดลการเรียนรู้ของเครื่องพบว่าโมเดลเบิร์ตมีประสิทธิภาพสูงกว่าโมเดลเอสวีเอ็ม แรนดอมฟอเรสต์ และโลจิสติกรีเกรสชัน โดยมีค่าความเที่ยงเป็น 0.72 ค่าเรียกกลับเป็น 0.719 ค่าเอฟวันเป็น 0.719 และค่าความแม่นเป็น 0.722 นอกจากนี้ งานวิจัยยังได้พัฒนาเว็บแอปพลิเคชันต้นแบบที่ใช้โมเดลเบิร์ตที่สร้างขึ้น เพื่อช่วยให้นักพัฒนาสามารถนำไปใช้วิเคราะห์และจัดลำดับความสำคัญของงานการบำรุงรักษาโมไบล์แอปพลิเคชัน โดยเว็บแอปพลิเคชันจะช่วยลดภาระในการอ่านบทวิจารณ์จำนวนมาก พร้อมทั้งสกัดข้อมูลที่สำคัญออกมาให้เห็นภาพรวมของความต้องการของผู้ใช้

Environmental Metrics In Action: Exploring U.S. Superfund Sites Affiliated With The Fashion Industry, Nidia K. Trejo

Textile Society of America: Symposium Proceedings

Little is known of Superfund sites, long-term clean up sites, affiliated with the apparel and footwear supply chain in the United States. The United States Environmental Protection Agency (US EPA) manages the clean up of contaminated sites that pose a significant risk to human health and the environment under the Superfund program. A site can become contaminated if hazardous waste from industrial operations are mismanaged or dumped into the environment, in an uncontrolled manner. In this study, a proposed Superfund site (Mohawk Tannery in Nashua, New Hampshire), an active Superfund site (Ciba-Geigy Corp. in Toms River, New Jersery), and a …

The Impact Of Journalistic Cultures On Social Media Discourse: Us Primary Debates In Cross-Lingual Online Spaces, Lea Hellmueller, Lindita Camaj, Sebastián Vallejo Vera, Peggy Lindner

Engineering Management and Systems Engineering Faculty Research & Creative Works

This cross-lingual project examines how social media posts of Spanish- and English-language media impact incivility in user comments during the 2020 primary political debates in the United States. We analyzed Facebook posts of news organizations that hosted the debates and used a state-of-the-art machine-learning model to analyze the corresponding comments. Our findings reveal distinct journalistic cultures on the post-level: English-language media are significantly more likely to use interpretation while Spanish-language media employ more audience-engagement and factual reporting strategies. We argue that in order to understand incivility in social media discourse during political debates, we need to consider journalistic cultures: While …

Stock Price Trend Prediction Using Emotion Analysis Of Financial Headlines With Distilled Llm Model, Rithesh H. Bhat

Computer Science and Engineering Theses - Archive

Capturing the volatility of stock prices helps individual traders, stock analysts, and institutions alike increase their returns in the stock market. Financial news headlines have been shown to have a significant effect on stock price mobility. Lately, many financial portals have restricted web scraping of stock prices and other related financial data of companies from their websites. In this study we demonstrate that emotion analysis of financial news headlines alone can be sufficient in predicting stock price movement, even in the absence of any financial data. We propose an approach that eliminates the need for web scraping of financial data. …

Understanding The Construction Workforce Needs Of The Future: Technology, Skills, Diversity, Bassam Ramadan

Theses and Dissertations--Civil Engineering

The U.S. construction industry stands at a crossroads. The looming age cliff is about to present its most serious challenges yet, coinciding with a shortage of qualified skilled professionals. As the demands of the construction industry continue to grow, it continues to lack the manpower to meet those demands. In order to meet the rising demands of construction needs in the near future, the construction industry needs to focus on improving workforce performance and productivity, and increasing the size of the construction labor force. Existing research highlights the importance of technological adoption and workforce skills, and that gender and ethnic …

Sdebuddy - Code Documentation Using Large Language Models, Nischay Nagendra

Master's Projects

In this fast developing world of software development, it is crucial to maintain the quality of code and the developers’ productivity. This can be done effectively with good code documentation. SDEBuddy uses the latest generation of Large Language Models (LLMs) and finetuning procedures to create code documentation. In this project, state-of-the-art models such as Llama2 and Llama3 are employed to mimic the behavior of the given code and produce documentation. Such models are tuned for various programming languages and documentation formats using LoRA and QLoRA fine-tuning approaches. These models are evaluated in terms of the BLEU score, ROUGE score and …

Streamlining Public Engagement In Transportation Projects Using Text Analytics, Alireza Shamshiri

Civil Engineering Dissertations - Archive

Infrastructure projects impact a broad range of stakeholders, particularly local communities, whose engagement is critical for successful outcomes. Despite the importance of public engagement in these projects, traditional methods of capturing and analyzing public opinion often fail to fully represent the diverse, genuine perspectives involved. This has led to conflicts between community members and project sponsors. On the other hand, despite advancements in text analytics, including natural language processing (NLP) and its subfields such as topic modeling, sentiment analysis, and neural networks, their functionalities and effectiveness in analyzing public opinion in the domain of infrastructure projects have not been fully …

แบบจำลองการจัดลำดับความสำคัญของความเสี่ยงของยูสเซอร์สตอรีสำหรับการจัดลำดับความสำคัญโดยใช้ตรรกะคลุมเครือ, เปรม สุนทรภาส

Chulalongkorn University Theses and Dissertations (Chula ETD)

ในกระบวนการพัฒนาซอฟต์แวร์แบบแอไจล์ ยูสเซอร์สตอรีเป็นองค์ประกอบสำคัญที่สะท้อนความต้องการของผู้ใช้ แต่หากยูสเซอร์สตอรีมีคุณภาพไม่เพียงพอ อาจก่อให้เกิดความเสี่ยงที่ส่งผลกระทบต่อความสำเร็จของโครงการอย่างมีนัยสำคัญ ดังนั้นงานวิจัยนี้จึงนำเสนอแบบจำลองการจัดลำดับความสำคัญของความเสี่ยงของยูสเซอร์สตอรีโดยใช้ตรรกะคลุมเครือ เพื่อช่วยให้สามารถจัดการกับความไม่แน่นอนในการตัดสินใจได้อย่างมีประสิทธิภาพ โดยเริ่มจากการนิยามความเสี่ยงของยูสเซอร์สตอรีจำนวน 12 ประเภท พร้อมทั้งกำหนดเกณฑ์การประเมินใน 2 ด้าน ได้แก่ ด้านความพยายามในการบริหารจัดการ และด้านข้อจำกัดในการบริหารจัดการ จากนั้นจึงประยุกต์ใช้ตรรกะคลุมเครือร่วมกับตัวแปรภาษาและฟังก์ชันความเป็นสมาชิกในการคำนวณค่าคะแนนความเสี่ยง และจัดลำดับความสำคัญผ่านแบบจำลองที่พัฒนาขึ้น ผลการประเมินการใช้งานแบบจำลองกับผู้มีประสบการณ์ในโครงการแอไจล์พบว่า แบบจำลองสามารถช่วยในการจำแนกความเสี่ยงได้อย่างเหมาะสมและมีความสอดคล้องกับความคิดเห็นของผู้ประเมิน ซึ่งผลการประเมินสะท้อนถึงความสมเหตุสมผลของแบบจำลองและความสามารถในการประยุกต์ใช้จริง ดังนั้นงานวิจัยนี้จึงเป็นประโยชน์ต่อทีมพัฒนาในการประเมินและจัดลำดับความเสี่ยงของยูสเซอร์สตอรีได้อย่างเป็นระบบ และเพิ่มประสิทธิภาพในการบริหารความเสี่ยงในโครงการพัฒนาซอฟต์แวร์แบบแอไจล์ได้ดียิ่งขึ้น

Improving Question Answering Retrieval System Through Multi-Result Ranking Model, Danupat Khamnuansin

Chulalongkorn University Theses and Dissertations (Chula ETD)

Recent trends in various industries involve integrating artificial intelligence (AI) systems to enhance operational efficiency. Among these advancements, AI-supported question-answering (QA) systems have gained significant attention. These systems typically employ a two-stage process, integrating QA system capabilities with Information Retrieval (IR) methods. The introduction of the Retrieval Question Answering (ReQA) has further refined this process, offering a more practical solution, aiming to improve real-world applicability. Considering the wide availability of diverse QA retrieval models, employing a combination of multiple systems presents as a viable solution. However, the approach to combining QA retrieval systems remains relatively limited. We propose a method …