@misc{Rostalski2025, type = {Master Thesis}, author = {Rostalski, Sarah-Maria}, title = {Radio Astronomy Essentials: Calibration Techniques with the 2.3m Radio Telescope at Rhine-Waal University}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:1383-opus4-21533}, school = {Hochschule Rhein-Waal}, pages = {88}, year = {2025}, abstract = {This thesis discusses calibration and, in this context, multiple ways of determining the system temperature of the 2.3-metre radio telescope at Rhine-Waal University of Applied Sciences in Kamp-Lintfort. Two methods for determining the system temperature are described here: the hot/cold-method and the derivation from the radiometer equation using measurement data from a source with a known brightness temperature, in this case, S7. Both methods deliver different results, depending on the measurements and assumptions on which they are based. The results show that the data basis and uncertainties should always be considered when analysing the observational data to be able to evaluate the results correctly. Overall, the telescope is quite suitable for educational observations, especially of the 21-cm line of neutral hydrogen. Furthermore, instructions have been created for the various tasks so that the results are reproducible and comprehensible. The entire process is made transparent, from planning the observations and setting up the telescope to measuring and analysing the data. In addition, basic concepts of radio astronomy are described in theory to provide valuable background knowledge. On this basis, the use of the telescope enables students and amateur astronomers to understand and apply the basic principles of radio astronomy and to plan and carry out their own observations.}, language = {en} } @masterthesis{Yankouski2025, type = {Bachelor Thesis}, author = {Yankouski, Matsvei}, title = {Simulation of Satellite Flares and their Impact on Ground-Based Observations}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:1383-opus4-22166}, school = {Hochschule Rhein-Waal}, pages = {62}, year = {2025}, abstract = {With a growing number of satellites on Low Earth Orbit (LEO) the problem of light pollution arises, which is caused by the light reflected from satellite modules and directed to the ground-based observatories. This phenomenon is called satellite "flares" or "glints". The goal of this work is to create a physical simulation model, which can recreate the conditions when the satellite flare is visible. The model is made in Python and uses a simplified geometry of reflection, orbit, solar panel parameters, and real-time TLE data. With the developed model it is possible to evaluate a variety of scenarios: single satellite, constellation and global maps of flare distribution with the given parameters. The simulation model allows for analysing the distribution of flares of time and space and checking the effectiveness of technical and legal norms. In the flow of the work numerical simulations are performed, heat maps are created, analysis and comparison with real data are made. The obtained results demonstrate the potential of this model as an instrument for planning and scheduling observations, developing less bright satellites and creating policy measures to decrease light pollution of the night sky. The results of this thesis are fundamental for expanding the model and integrating real data of all satellites.}, language = {en} } @masterthesis{Huelshoff, type = {Bachelor Thesis}, author = {H{\"u}lshoff, Kristina}, title = {Visualisierung klimafreundlicher Baumaßnahmen am Beispiel der Stadt Xanten}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:1383-opus4-18847}, school = {Hochschule Rhein-Waal}, pages = {60}, abstract = {Due to anthropogenic climate change, cities need to be restructured. New measures are necessary to achieve climate neutral cities. With the assistance of 3D Programs, concepts against flooding, heat and in favor of mobility transition can be visualized. This thesis will emphasize why it is so relevant to take actions against climate change and will investigate which measures are helpful, especially in cities. In connection, the ideation of measures for the City of Xanten will be presented. Subsequently, the process of chosen Design Style and concepts for various Xanten locations will be explained and displayed. These elaborated concepts can be seen as a thought provoking impulse for at least Xanten, which may be realized in the future.}, language = {de} } @masterthesis{Keiffenheim, type = {Bachelor Thesis}, author = {Keiffenheim, Jan}, title = {Die Produktion von Audiodateien und deren Einbindung in Videospiele}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:1383-opus4-3494}, school = {Hochschule Rhein-Waal}, pages = {54}, abstract = {In this paper the production of audio file will be shown with examples, and how these can be put exemplarily into a video game. For this purpose different types of programs will be presented which can produce audio file. To show a small expenditure, affordable or free programs will be used for this paper. After that the paper shows how to exemplarily record and edit music, sound and voice. Finally a game engine will be used to demonstrate the inset and programming of the created audio files. This paper is especially for newcomers (and students) to introduce them to audio and sound design. With the practical instructions in this paper they can start to produce audio files by their own.}, language = {de} } @masterthesis{Pruem, type = {Bachelor Thesis}, author = {Pr{\"u}m, Moritz}, title = {Automated Hyperspectral Field Scanner for Vegetation Monitoring}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:1383-opus4-2247}, school = {Hochschule Rhein-Waal}, pages = {57}, abstract = {Vegetation monitoring is an important tool in a variety of fields, e.g. precision agriculture and plants' phenotyping. The system design of existing non-invasive ground based systems is usually not open-source. Therefore, these systems cannot be reliably modified and thus are not suitable to advanced applications, such as prototyping of new sensors. This thesis describes the development of a ground based hyperspectral monitoring system for use in plant science and sensor testing. A well-documented and automated working prototype has been developed and initial tests show promising results. Further work in system modularity and redundancy is needed.}, language = {en} } @masterthesis{Schlossarek, type = {Bachelor Thesis}, author = {Schlossarek, Nina Tangyue}, title = {FinTechs in Germany - Current Status and Potential Impact on the Financial System}, school = {Hochschule Rhein-Waal}, abstract = {The development of technologies that created FinTechs have brought new possibilities for customers into life that provide a quick and convenient handling of operations by covering various segments of the financial industry. However, the innovations also implicate drawbacks: Traditional banks may be threatened due to a loss of customers. This thesis evaluates to which extent this case can be measured by executing quantitative research methods as well as qualitative research methods for the purpose of gaining information from a bank's perspective as well as opinions from customers. The result of this empirical study is that there is a certain correlation between the development of FinTechs and a threat caused by FinTechs although the latter is rather weak. Furthermore, this thesis indicates the knowledge of customers regarding FinTechs and their willingness to face said innovations.}, language = {en} } @misc{Roechert, type = {Master Thesis}, author = {R{\"o}chert, Daniel}, title = {Workload Prediction using Apache Spark and R in a Mainframe Operating System}, school = {Hochschule Rhein-Waal}, abstract = {This master thesis presents a machine learning approach using the distributed data- processing framework Apache Spark and the programming language R. The aim is to predict the time series of the Appl Percentage (ApplPerc) from the workload manager of the z/OS mainframe system using SMF 72.3 and SMF 70.1 records as input. System Management Facility (SMF) data are binary log files that are used to collect system performance data and information about system behaviour. The SMFs show how Apache Spark can be used for the pre-processing. This includes data collection, data extraction, and data selection. The machine learning algorithms are implemented in R. The input SMF datasets will be split into training and test data, and thereby applied to different machine learning and deep learning models such as random forest regression, recurrent neural network, and k-nearest neighbor regression to predict the ApplPerc. The validation of the prediction models will be proved by using cross-validation techniques to evaluate the best applied parameters for each model and therefore to locate the model with the best performance. The process of data analysis is followed by a data-mining methodology called Cross-Industry Standard Process for Data Mining (CRISP-DM), which outlines the steps involved in performing the analysis.}, language = {en} } @masterthesis{Langer, type = {Bachelor Thesis}, author = {Langer, Sven}, title = {Influence of Cryptocurrencies on the Economy: A Potential-Analysis of Bitcoin as an Alternative Currency}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:1383-opus4-6909}, school = {Hochschule Rhein-Waal}, pages = {89}, abstract = {"Right now, Bitcoin feels like the Internet before the browser" (Casares, 2020). This quote sums up most of the current thoughts on the phenomenon of a ground-breaking invention from 2008 by Satoshi Nakamoto since a major part of the world's population is still missing out on sophisticated knowledge about it. Especially in times of digitalization, it is of enormous value to be informed about current developments in technology. This thesis aims to evaluate the future development of money, especially if Bitcoin has the potential to totally replace conventional currencies. Furthermore, the strengths and shortcomings of Bitcoin will be discussed. It also reaches to determine characteristics for a currency's long-term success and which of those characteristics are fulfilled by Bitcoin. To answer the research question if Bitcoin has the potential to be an alternative currency and to test the developed hypotheses, pertinent literature is reviewed and an empirical study consisting of expert interviews which are examined using a qualitative structured content analysis method, are conducted. Afterwards, the results are critically discussed. The results of this thesis reveal that Bitcoin has the potential to become an alternative currency because it fulfills most of the criteria a currency needs to meet to be successful in the long run. Furthermore, it is evident that Bitcoin still faces vast barriers and needs to overcome enormous obstacles, which shifts the time horizon for becoming a success somewhere in the farther future. Additionally, apart from the development of cryptocurrencies, it is shown that money in general, will flow much more digitally in the short run. Besides that, this thesis offers insights about the promising future of Bitcoin's underlying core technology, the Blockchain, in various fields of application.}, language = {en} } @masterthesis{Krawczyk, type = {Bachelor Thesis}, author = {Krawczyk, Adrian}, title = {Linux-Simulation als implizites Lernszenario}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:1383-opus4-8122}, school = {Hochschule Rhein-Waal}, pages = {43}, abstract = {Linux is an operating system, which is used by a limited number of people. The main idea of this project is to develop a game that not only simulates Linux, but also provides an opportunity to learn various things about the use of this operating system. The game, LinuxSimulationGame, is built with Unity and designed by following the requirements of a focus group. While in development, game tests are used to investigate the current state and quality of the game. Game tests provide feedback to the developer, which can be used to plan further changes. By using mechanics like space, objects, actions, rules and skills the game produces various situations in which a user is able to learn. By memorizing information based on a Linux operating system. Both game tests and interviews have proved an interest in this kind of gameplay. LinuxSimulationGame is a game which could result in an increase of knowledge. This would require further testing. This document describes mechanics and data needed for creation of games like LinuxSimulationGame.}, language = {de} } @misc{SamuelVarghese, type = {Master Thesis}, author = {Samuel Varghese, Bitty}, title = {Development of a Self Learning Agent to control a Gas Network Simulator}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:1383-opus4-8025}, school = {Hochschule Rhein-Waal}, pages = {88}, abstract = {Natural gas is an indispensable source of energy for industrial and domestic purposes, hence distribution and trade demands competition. In gas distribution, optimizing is a crucial task involving control decision on the network elements with respect to trader's demand at the boundary nodes. The application of artificial intelligence is becoming popular in diverse domains, making its role in gas transport networks more and more interesting. The opposite interest of the players in the network is the reason behind the thought of establishing a game analogy here. The agents as players act on the basis of the opponent's action. Since both agents perform actions from different space, a neural network model is designed for the dispatcher agent to learn to make decisions for active elements based on its experience from the sample gas transport network. Behavior of the network and its elements is depicted using an optimized gas network simulator. The representation of the gas transport network and its state is digitally transformed so that it is able to extract the features by an artificial neural network representing the environment and its rules. With the help of the trained neural network, the dispatcher agent decides the control decisions with less accumulated penalties. The results and findings of the proposed method are subjected to a comparison with the interval halving method. The results of the study will open the door for further research possibilities.}, language = {en} } @misc{Langer, type = {Master Thesis}, author = {Langer, Sven}, title = {The Impact of Leader Behavior on Team Processes}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:1383-opus4-18136}, school = {Hochschule Rhein-Waal}, pages = {96}, abstract = {The modern work environment is subject to constant change with a notable shift from individual to team-based work structures. This transition necessitates an improved un-derstanding of how managerial actions influence the dynamics within these teams, to optimally align them for success. Despite the substantial research about leader effec-tiveness and team effectiveness based on organizational performance indicators, it is rather infrequent that the direct influence of leader behavior on teams is explored. This thesis aims to address this gap by answering how leader behaviors impact team pro-cesses in the context of German medium to large-scale IT-enterprises. Using a quanti-tative cross-sectional methodology, individuals working in team-based structures under direct supervision were surveyed. Analyzing data from 94 respondents via hierarchical linear regression analysis, several significant relationships were identified. In general, leader behavior has a strong positive impact on team processes. Furthermore, task-oriented leaders have the greatest positive influence on action processes, while relation-oriented leaders have the greatest positive influence on interpersonal processes. Change-oriented leaders also significantly influence action processes and interpersonal processes, albeit less strongly than their counterparts. These results provide implications for team management practices, emphasizing the importance of leader behavior for aligning team processes in the direction of success.}, language = {en} } @misc{Acharya, type = {Master Thesis}, author = {Acharya, Bhuwan}, title = {VISUALIZATION OF FLOOD SCENARIOS IN GERMANY IN 2021 AND FORECASTING FLOOD USING MACHINE-LEARNING MODELS}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:1383-opus4-18780}, school = {Hochschule Rhein-Waal}, pages = {132}, abstract = {Floods are the most common, devastating, and frequently occurring natural disaster nowadays. Because of climate change, Europe is expected to see an even higher number of floods in the coming decade. As floods cannot be prevented, understanding the pattern and causes and being able to forecast could significantly reduce the losses during the flood. In July 2021, Germany faced a catastrophic flood, taking more than 180 people's lives and causing around 40 billion euros of economic loss. To study the flooded region and the region at high risk, the Flood event 2021 has been visualized in this research. The Flood map has been created using a sentinel-1 image. In the visualization, floods in the Rhine River and Arh River can be seen, and the change in the pattern of flood from 12th July to 16th July has also been observed. Different models exist that try to predict floods and warn as early as possible. Since Machine learning is popular nowadays in every sector, ML models have been implemented in this study to forecast the flood. The SARIMA, Random Forest, and LSTM have been implemented using historical data to predict the flood. The Random Forest model performed better than the remaining two models. The Isolation Forest model has also been implemented to classify the data into Flood and No Flood. This model performs well with the Flood classes but struggles in capturing the No Flood class.}, language = {en} } @masterthesis{Krishnamoorthy, type = {Bachelor Thesis}, author = {Krishnamoorthy, Harriha}, title = {K{\"u}nstliche Intelligenz und nachhaltiger Fast Fashion im E-Commerce - Machbarkeitsanalyse und qualitative Analyse zur kognitiven Dissonanz der Konsumenten}, school = {Hochschule Rhein-Waal}, abstract = {This thesis deals with the consumer purchasing behavior in the fast fashion segment. The central focus includes analyzing factors such as purchase intention, e-commerce trade, consequences and environmental impacts. The first section defines terms and compares current studies to each other. This is followed by a methodical discussion. In order to assess consumer purchasing behavior, semi-structured interviews were conducted, and digital diary entries were written by participants from generation Y and Z. Based on these results shopper types were identified.}, language = {de} } @misc{Sharma, type = {Master Thesis}, author = {Sharma, Neetu}, title = {Analyzing Customer Behvior Patterns \& Predicting Online Product Return Intentions: A Data Mining Approach}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:1383-opus4-19240}, school = {Hochschule Rhein-Waal}, pages = {74}, abstract = {During the past years, it is noticeable that the e-commerce industry has emerged drastically, offering accessibility to a variety of products to the customer where they can buy products from the comfort of their home. However, it is associated with a lot of new challenges for e-commerce businesses, particularly in understanding and managing the customer behavior patterns with the rising online product returns. Since the accessibility of online shopping has risen, assessing the critical factors related to product return and prediction has become a really challenging task for e-commerce vendors. This study also aims to segment the customers based on customer behavior prediction into two categories, i.e., high return risk and low return risk customers, and further develop strategies to reduce the online returns. This study is rather structured into four integral parts, where each part provides the comprehensive analysis. The first aspect involves analyzing and identifying the customer behavior patterns leading to product returns. The second aspect predicts the online product return based on selected features and the third is to segment the customers based on online product return prediction and categorize them into high return risk, and low return risk customers. The final step involves development of strategies to reduce the product return based on the intense analysis conducted. To achieve this meaningful research outcome, data analysis is conducted to understand the customer behavior patterns, and a Random Forest feature selector is used to identify the customer behavior patterns that lead to product return. Based on the identified features, classification models were applied to classify and predict whether the customer is going to return product or not. Furthermore, in these seven classification models such as Logistic Regression, Ada Boost, Decision Tree, Naive Bayes, XG Boost, K-Nearest Neighbors, and Random Forest were implemented and used to compare the performance of the classification models to find out the best performing model. Lastly, the segmentation of customers is carried out based on the online product prediction using Logistic regression with classification threshold method into high return risk and low return risk customer categories. The results obtained help in understanding the customer behavior and reduce the online product return by developing the strategies. This study will eventually help the online businesses in reducing returns which will also enhance the customer satisfaction.}, language = {en} } @masterthesis{Oha, type = {Bachelor Thesis}, author = {Oha, Kingsley}, title = {ADVANCEMENTS IN MICROSERVICE ARCHITECTURES: TACKLING DATA COMMUNICATION, SCALABILITY, AND CI/CD AUTOMATION CHALLENGES}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:1383-opus4-20463}, school = {Hochschule Rhein-Waal}, pages = {69}, abstract = {This paper delves into the optimization of microservice architectures, a critical aspect of contemporary software engineering, by focusing on three pivotal areas: efficient data communication, scalable design, and the automation of Continuous Integration/Continuous Deployment (CI/CD) processes. The study begins by examining the intricacies of data communication within microservices, identifying challenges such as network latency, data consistency, and fault tolerance. Strategies for efficient data handling, including advanced message queuing techniques and API gateways, are explored. The paper then shifts its focus to scalable design, assessing how microservices can be architected to gracefully handle varying loads and facilitate seamless scaling. This includes an analysis of containerization technologies, service orchestration, and load balancing strategies. The final part of the study addresses the automation of CI/CD processes, a cornerstone for achieving agility and high velocity in microservices development and deployment. The evaluation of modern CI/CD tools and methodologies, highlighting their role in enhancing deployment frequency, reducing lead time for changes, and improving overall system reliability. This comprehensive study aims to provide valuable insights and practical guidelines for software professionals and researchers, contributing to the refinement and advancement of microservice architectures in the dynamic world of software development.}, language = {en} } @masterthesis{Helou2025, type = {Bachelor Thesis}, author = {Helou, Ziad}, title = {Opportunities and challenges for the solar industry in Lebanon.}, school = {Hochschule Rhein-Waal}, year = {2025}, abstract = {Lebanon faces a significant energy crisis characterized by unreliable electricity supply, political instability, and outdated infrastructure. This thesis explores the potential of solar energy as a sustainable solution to address these challenges, focusing on economic, technical, and regulatory barriers while drawing comparative insights from Cyprus's renewable energy model. The research examines three primary questions regarding the economic and technical challenges hindering solar energy adoption in Lebanon, the lessons that can be learned from Cyprus to inform solutions, and the comprehensive strategies that can support the development of Lebanon's solar energy sector. The findings reveal that while Lebanon has experienced rapid growth in solar energy adoption, the sector is undermined by systemic issues such as low-quality imports, skill gaps, insufficient grid infrastructure, and the dominance of diesel generators. Comparative analysis with Cyprus underscores the importance of robust regulatory frameworks, financial accessibility, public-private partnerships, and accreditation systems for solar installers. Additionally, the analysis highlights the critical role of improving capacity factors in Lebanon, with findings showing that even a 1\% increase could supply power to over 16,000 homes, emphasizing the potential efficiency gains for Lebanon's solar energy sector. The thesis also evaluates Lebanon's progress toward its 2030 renewable energy targets, noting that while the country appears to have met these targets in percentage terms, the achievement is largely a result of reduced electricity generation rather than genuine renewable capacity growth. Recommendations include enforcing quality standards, establishing national accreditation systems, addressing corruption, and leveraging international funding for infrastructure modernization and workforce development. This research emphasizes that Lebanon's transition to renewable energy is not only a technical and economic endeavor but also a pathway to greater energy independence and environmental sustainability.}, language = {en} } @misc{Syed2025, type = {Master Thesis}, author = {Syed, Zaid Saleem}, title = {Development of an ML-based multivariate anomaly detection model for beehive monitoring using sensor and environmental data.}, school = {Hochschule Rhein-Waal}, year = {2025}, abstract = {Anomaly detection is an important aspect of beehive monitoring, enabling beekeepers to take timely action and preventing economic losses caused by the decline of the bee population. Most existing beehive monitoring systems lack machine learning (ML) capabilities for anomaly detection and rely on threshold-based methods or expensive, complex designs. This thesis utilized the DigiBee prototype, a cost- effective monitoring system, to develop an ML-based anomaly detection model using Isolation Forest. Data on temperature, humidity, sound, vibration, and weight from four active beehives was collected between May 1, 2024, and July 25, 2024, alongside environmental data—temperature, relative humidity, and precipitation—from nearby meteorological stations. Exploratory data analysis revealed several limitations: uniform outputs from vibration sensors, calibration errors in weight sensors, and multiple gaps during the data collection period. Correlation analysis indicated a limited influence of external weather variables on internal beehive conditions, while internal sensor parameters displayed stronger correlations with each other. Five models were developed, using either beehive data alone or a combination of beehive and weather data. Results showed that beehive-specific models achieved higher accuracy in detecting localized anomalies, whereas models combining data from multiple beehives generalized better but underrepresented hive-specific issues. Models incorporating weather parameters, especially precipitation, introduced noise and unnecessary dimensions, which, when excluded, improved the model's prediction by focusing on hive-specific patterns and ensuring anomaly detection remained contextually relevant.}, language = {en} } @masterthesis{FopaMamene, type = {Bachelor Thesis}, author = {Fopa Mamene, Morelle}, title = {Secure Access Service Edge (SASE): Architecture, Implementation, and Performance Evaluation}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:1383-opus4-20700}, school = {Hochschule Rhein-Waal}, pages = {72}, abstract = {In today's digitally evolving world, companies are faced with modern problems like data breaches, ensuring seamless and secured access to their cloud-based assets, and the decongestion of routed traffic to their data centres which are all problems related to the ongoing digital evolution. This thesis examines the topic of Secure Access Service Edge (SASE), which is a zero-trust framework combining cutting-edge network security technologies with software-defined connectivity, and evaluates the effectiveness of its core components, such as Software Defined Wide Area Network (SD-WAN), Zero Trust Network Access (ZTNA), Cloud Access Security Broker (CASB), Secure Web Gateway (SWG), and Firewall as a Service (FWaaS), in creating a secure, fast, and reliable corporate network infrastructure. The conclusions obtained in this document are a result of analysing the network architecture of Uniper, a global company in the energy sector which produces and delivers energy, and recently shifted its resources to the cloud by adopting SASE. The outcome of the analysis revealed that, SASE indeed enhances users' experience and provides several benefits to the company's network connectivity like reduced latency, connections redundancy, and improved bandwidth. Going through this document will help understand how SASE components can work to provide a revolutionary solution to companies through a proposed implementation roadmap, and how SASE compares to traditional network security models like Virtual Private Network (VPN) and Multiprotocol Label Switching (MPLS).}, language = {en} } @misc{Hanafy, type = {Master Thesis}, author = {Hanafy, Ahmed}, title = {API Driven Form Rendering}, school = {Hochschule Rhein-Waal}, abstract = {This master's thesis investigates the challenges and opportunities associated with dynamic form rendering in user interfaces, specifically in the context of Galeria Karstadt Kaufhof (GKK), a key player in the German retail sector. Collaborating with CODUCT Solutions GmbH, this research aims to enhance GKK's operational efficiency and user experience in their digital transformation journey, focusing on Project Baldeney, a cloud-native platform that automates content management workflows. The thesis begins by outlining the limitations of traditional, static methods of form rendering, highlighting the implications for development time and error frequency. It identifies the fragmentation in the existing API-driven architectures as a critical issue affecting system reliability and user experience. Against this backdrop, the work proposes a unified, API-driven framework to dynamically render forms for many user actions, such as data input and transactions. The research takes a deep dive into existing systems—particularly Informatica's Product Information Management (PIM) software and the new software in development Article Workbench to identify user experience issues, inefficiencies, and the complexities involved. Through this examination, it offers a targeted solution to integrate various components of form management, like building, parsing, validation, and rendering, into a cohesive system. The thesis aims to contribute to software development and user experience design substantially, by targeting improved development efficiency, reduced errors, and enhanced system reliability. By achieving these objectives, the research aspires to furnish GKK with a robust solution for dynamic form rendering, thereby enhancing both user satisfaction and system performance in the fast-evolving digital landscape.}, language = {en} } @misc{Gurung, type = {Master Thesis}, author = {Gurung, Purnima}, title = {Sentiment Analysis in Nepali Tweets: Leveraging TransformerBased Pre-trained Models}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:1383-opus4-19677}, school = {Hochschule Rhein-Waal}, abstract = {Despite the remarkable achievements of large transformer-based pre-trained models like BERT, GPT in several Natural Language Processing (NLP) tasks including Sentiment Analysis (SA), challenges are still present for subdued source languages like Nepali. Nepali language is written in Devanagari script, has complex grammatical structure and diverse linguistic features. Due to the absence of balanced datasets, and computational resources for Nepali, achieving optimal result with the latest architecture remains challenging. For this reason, publicly available NLP modelsfor Nepali are very less, making research in this area difficult. This paper attempts to addressthis gap through the use of pre-trained transformer models specially tailored for Nepali from Hugging Face including BERT, DistilBERT, ALBERT, and DeBERTa for sentiment analysis in Nepali tweets on relatively balanced datasets. The models are trained on large Nepali datasets and optimized for NLP tasks involving Devanagari scripts. To evaluate the model's performance, various tokenization strategies are investigated in order to capitalize on transformer-based embedding with the SoftMax function and confusion matrix. The outcomes of models are compared using the same datasets. The study's results shows that DistilBERT achieved the highest accuracy rate of 88\% in Nepali sentiment analysis tasks, followed by BERT and DeBERTa at 83\% and 80\%, respectively. However, ALBERT showed a low accuracy of 70\%. The result of this approach shares valuable viewpoints for the field of sentiment analysis in diverse linguistic contexts.}, language = {en} }