Hadeel Alobaidy, Tasnime Tantawy and Shahad Talal, Department of Computer Science, University of Bahrain, Bahrain, Zallaq
This research aims to develop an optimal metro railway that connects the most popular spots for tourist places in the Kingdom of Bahrain using Dijkstra’s algorithm, complemented by a recommendation system using modified collaborative filtering and haversine algorithm. The proposed system employs software engineering principles involving agile methodology as a software process model for enhancing the adaptability and flexibility of the proposed system. The application embeds the railway route generated by Dijkstra’s algorithm to enhance the recommendations provided by the collaborative filtering algorithm, resulting in an accurate system with extraordinary potential for travellers and business owners in the future.
Bahrain Metro, Software Engineering, Agile process model, Recommendation System, Human-Computer Interaction, User- experience.
Efe Batur Giritli1, Yekta Said Can1, Alper Sen and Fatih Alagöz2, 1R&D Center, Tatilsepeti, Istanbul, TURKEY, 2Computer Engineering Dept., Bogazici University, Istanbul, Turkey
In the rapidly evolving landscape of the global tourism industry, efficient and reliable online accommodation booking systems are paramount. This study delves into the crucial role of model-based testing in enhancing the efficiency and reliability of online accommodation booking systems within the dynamic landscape of the global tourism industry. By using a behaviour driven test automation tool GraphWalker, the research employs advanced modeling techniques to meticulously capture the system’s nuances. In emphasizing the significance of modelbased testing, this research not only contributes to improved online booking experiences but also underscores its broader relevance in the domain, serving as a valuable resource for industry practitioners and researchers alike.
model based testing, graphwalker, selenium web driver, model based booking.
Renjith Ramachandran, Independent Researcher and Solutions Architect, USA
In today’s rapidly evolving digital landscape, enterprises are striving to offer a seamless and integrated customer experience across multiple touchpoints. This improved experience often leads to higher conversion rates and increased customer loyalty. To deliver such an experience, enterprises must think beyond the traditional boundaries of their architecture. The architecture of the digital ecosystem is expanding and becoming more complex, achieved either by developing advanced features in-house or by integrating with third-party solutions, thus extending the boundaries of the enterprise architecture. This complexity poses significant challenges for both observability and security in a digital ecosystem, both of which are essential for maintaining robust and resilient systems. Observability involves monitoring and understanding the internal state of a system through logging, tracing, and metrics collection, allowing organizations to diagnose performance issues and detect anomalies in real time. Meanwhile, security is focused on protecting sensitive data and ensuring service integrity by defending against threats and vulnerabilities. This paper explores the interdependencies between observability and security within digital ecosystem architectures, highlighting how enhanced observability can bolster security measures. It investigates strategies for implementing improved observability across various application layers. The data collected through these observability practices can be analyzed to identify patterns and detect potential security threats or data leaks.
Observability, Security, Digital Ecosystem Architecture
Larissa Luize de Faria Cardoso, Electrical Engineering Department Pontifical Catholic University of Rio de Janeiro, Rio de Janeiro, Brazil
Sustainable investments, guided by ESG (Environmental, Social, and Governance) criteria, have become a central focus for investors worldwide. The integration of ESG criteria into investment decisions has been shown to lead to better financial performance and lower long-term risk for companies. This study aims to develop and apply a Genetic Algorithm (GA) to optimize investment portfolios that balance financial, return, ESG criteria, and risk. The proposed methodology creates a robust and adaptable model suitable for real-world sustainable investment scenarios. By using data from companies such as Apple, Microsoft, and Tesla, this study demonstrates the effectiveness of GAs in achieving an optimal portfolio allocation. The results highlight the potential of GAs to consider multiple objectives simultaneously and provide a balanced solution that meets financial and sustainability goals.
Sustainable Investments, ESG, Genetic Algorithms, Portfolio Optimization, Financial Performance.
Moti Schneider1 and Arthur Yosef2, 1Tel Aviv-Yaffo Academic College, Israel, 2Netanya Academic College, Israel
This study presents a method to assign relative weights when constructing Fuzzy Cognitive Maps (FCMs). We introduce a method of computing relative weights of directed edges based on actual past behaviour (historical data) of the relevant concepts. There is also a discussion addressing the role of experts in the process of constructing FCMs. The method presented here is intuitive, and does not require any restrictive assumptions. The weights are estimated during the design stage of FCM and before the recursive simulations are performed.
FCM, relative importance (weight), Fuzzy Logic, Soft Computing, Neural Networks.
Yuqi Yan1, Wenbo Zhu2 and Tiechuan Hu3, 1Olin School of Business, Washington University in Saint Louis, MO, USA, 2Physical Science Division, University of Chicago, IL, USA, 3Department of Computer Science, John Hopkins University, MD, USA
Money laundering is dangerous to the global financial institutions because it allows to hide illegal cash and supports various criminal activities. Due to reliance on manual procedures and rule-based systems, traditional Anti-Money Laundering (AML) techniques need assistance in managing the complexity and volume of contemporary financial transactions. This research explores how Large Language Models (LLMs), such as GPT-3 and BERT, can improve AML by utilizing cutting-edge natural language processing capabilities to provide more reliable and scalable money laundering detection and prevention solutions. By examining the transformational potential of LLMs in overcoming the drawbacks of conventional techniques, the research fills a significant vacuum in the present AML procedures. Enhancing transaction monitoring, refining client due diligence procedures, streamlining sanctions screening, and aiding in the production of precise suspicious activity notifications are among the primary study issues. The main assumption is that utilizing LLMs capacity to handle unstructured data and spot complex patterns, AML accuracy and efficiency will significantly increase compared to traditional systems. The goals include implementing LLMs across AML functions, assessing their effectiveness with various datasets, as well as presenting empirical research and case studies to prove their superiority. By advancing our knowledge of and ability to use LLMs in financial compliance, this research is expected to strengthen the defenses against financial crimes.
Large Language Models,Financial Compliance, Anti-Money Laundering, Natural Language Processing, GPT-3, BERT
Geetesh More, Suprio Ray and Kenneth B Kent
Existing systems used in big data processing are becoming less energy-efficient and fail to scale in terms of power consumption and area. Under big data application scenarios, the movement of large volumes of data influences performance, power efficiency, and reliability, which are the three fundamental attributes of a computing system. With data volumes and data sources continuing to increase, there has been a thrust to rethink how businesses approach data handling and storage, with one of the main objectives being maximizing performance and speed without increasing complexity and overall costs. Large-scale data centers require highly efficient server and storage systems. Existing approaches where CPUs are employed have several limitations. Traditional CPU technology limits performance, as frequency scaling approaches for performance improvements are no longer applicable. This has shifted the interest toward multicore processing. However, multicore processing again has many limitations such as I/O and memory bandwidth. FPGAs have several advantages over CPUs or GPUs. They can be used to accelerate the performance of large-scale data systems. In this paper, we survey various near-memory database acceleration on FPGAs where compute and data-centric operations are moved closer to FPGAs.
Field programmable gate array (FPGA), big data, in-memory computing, near-memory computing, Graphic Processing Unit (GPUs), SQL.
Ervin Vladić, Benjamin Mehanović, Mirza Novalić, Dino Kečo and Dželila Mehanović, Department of Information Technology, International Burch University, Sarajevo, Bosnia and Herzegovina
Over the last 10 years, social media platforms have grown into powerful machines for opinion -sharing and conversation-starting. At the same time, developments in machine learning (ML) and artificial intelligence (AI) have resulted in new approaches for analyzing huge amounts of data generated by users. To classify the sentiments represented in tweets, this research investigates sentiment analysis, a subfield of natural language processing (NLP), and machine learning. This paper provides an extensive analysis of sentiment classification on social media data by integrating approaches including data loading and overview, regulating class imbalance, text preparation and tokenization, sentiment analysis and visualization, and model evaluation. The increasing amount of user-generated information on social media has led businesses, researchers, and people to look for insights into consumer feedback, public opinion, and market trends. This has led to a rise in the popularity of sentiment analysis. Linear SVC and Logistic Regression have been determined to be the most successful machine learning models for sentiment analysis. While Logistic Regression gets 83% training accuracy and 78% testing accuracy, Linear SVC obtains 90% training accuracy and 77% testing accuracy.
Sentiment, Classification, Social media, Natural Language Processing, Models.
Mahmud Adeleye1 and Krishna Chaitanya Rao Kathala2 1Oxford Brookes University, Oxford, OX3 0BP, United Kingdom, 2University of Massachusetts Amherst, 01002, United States of America
This paper reviews the literature on context window size extension techniques in Large Language Models (LLMs), examining their potential, limitations, and impact on performance. We survey existing research on models ranging from 8,000 to 2 million token context windows, synthesizing findings on their performance across various benchmarks and tasks. The synthesis reveals a complex relationship between context size and model performance, highlighting challenges such as the "lost in the middle" phenomenon. We discuss emerging techniques addressing these issues, including Position Interpolation and Parallel Context Windows. Our review of performance analyses on benchmarks like MMLU and HumanEval provides insights into LLMs task-specific capabilities. We conclude by outlining future research directions, emphasizing the need for more ef icient processing of long contexts and standardized evaluation methods. This survey of ers a foundation for understanding the current landscape of context windows in LLMs and potential avenues for future advancements in this rapidly evolving field.
Large Language Models (LLMs), Context Window Size Extension, Long-context Processing, Performance Evaluation.
Reihaneh Maarefdoust, Xin Zhang, Behrooz Mansour, Yuqi Song, Department of Computer Science, University of Southern Maine, Portland, USA
The discovery of new materials has been a protracted and labor-intensive endeavor, relying on iterative trial-and-error methodologies. Recently, materials informatics has been transforming this process by employing advanced data science and computational tools to expedite the discovery of novel materials, such as generative design material formulas, and predict material properties. However, predicting crystal three-dimensional structures remains a challenging task rooted in both the fundamental nature of materials and the limitations of current computational methods. Inspired by the power and success of artificial intelligence (AI) models, especially the deep learning techniques and natural language processing (NLP) algorithms, we consider capturing complex atom descriptions and relationships as text information and explore whether we can use the ability of language models to predict atomic coordinates. In this work, we explore multiple text generation models and employ the Longformer-Encoder-Decoder (LED) model to construct preliminary crystal structures based on detailed atom descriptions. Subsequently, these structures are further refined by a random forest regressor, which generates the final crystal configurations. Our experiments show this method excels in capturing the intricate atom relationships and ef ectively translating these associations into the specified crystal formats. We also focus on optimizing data representation for both atom descriptions and crystal structures and use clear metrics to evaluate accuracy and stability. Our results indicate that this method has promising potential and could improve the prediction of material crystal structures. Our source code can be accessed freely at https://anonymous.4open.science/r/Crystal-Structure-Prediction-7E1D.
Material informatics, Crystal structure prediction, Text generation, Longformer-Encoder-Decoder
Daixuan Tian1, Ivan Revilla2, 1Canyon High School, 220 S Imperial Hwy, Anaheim, CA 92807, 2Computer Science Department, California State Polytechnic University, Pomona, CA 91768
This paper presents a "Keyword Generator" web application designed to streamline the process of generating relevant keywords for URLs or descriptions using OpenAIs Generative AI model [1]. The project addresses the challenge of keyword generation, crucial for SEO and content categorization, by integrating an AI model that processes input and generates accurate keywords in real time. Experiments were conducted to evaluate the models accuracy and consistency, revealing high levels of performance, with some limitations in variability. Improvements, such as finetuning the model and integrating multilingual capabilities, are suggested to enhance effectiveness. The results highlight the potential of AI-driven keyword generation as an efficient and valuable tool for digital marketing and content creation, demonstrating the systems ability to adapt to different input types and deliver relevant results [2].
Keyword Generation, Generative AI, Natural Language Processing (NLP), SEO Optimization, Content Categorization.
Pankaj Pilaniwala1, Udit Nakhat2, 1University of Arizona, Tucson, Arizona, USA, 2University of California, Berkley, California, USA
This paper examines the current state of MLOps and emphasizes the importance of developing ML and AI-powered applications. The study commences by defining MLOps and conducting a Literature Review to highlight critical studies in this area. It then delves into the current state of MLOps, providing examples of how major tech companies implement MLOps across their organizations. Additionally, the paper discusses the benefits of utilizing MLOps and addresses deployment challenges in the current process. Furthermore, it proposes an innovative solution to improve existing practices. It presents a technical architecture system design for implementing this novel approach using GenAI to enhance and streamline the MLOps deployment process.
MLOps, Machine Learning, GenAI, Deployment.
Lauren Peng Lu1 , Victor Zhou2, 1Crean Lutheran High School, 12500 Sand Canyon Ave, Irvine, CA 92618, 2Computer Science Department, California State Polytechnic University, Pomona, CA 91768
Designify is an innovative application that integrates artificial intelligence (AI) and augmented reality (AR) to revolutionize interior design [1]. The project leverages Google’s Gemini AI model to provide users with personalized furniture recommendations based on room dimensions and layout, while the AR system allows for real-time visualization and interaction with virtual furniture [2]. Two key experiments were conducted to evaluate the system’s effectiveness: the first tested the accuracy of the AI model across various room layouts, and the second measured the efficiency of user interactions within the AR environment [3]. The results showed that the AI performed well in standard room layouts but struggled with irregular spaces, while the AR system was intuitive for simpler tasks but required refinement for more complex interactions. These findings provide insights for improving both the AI’s spatial reasoning and the AR gesture system, offering a strong foundation for future development and user-centered enhancements [4].
Augmented reality, Artificial Intelligence, Interior design, Furniture Recommendation, Flutter.
Arun Kumar Ramachandran Sumangala Devi , Architect Ii- Software Testing Ust Global Inc, Glen Allen, Virginia, Usa
One of the most significant technological advancements in the healthcare sector is using machine learning (ML) for predictive analytics. This was developed in response to the growing need to analyze large amounts of data generated daily in the healthcare sector. ML has been integrated into data warehousing (DW) and Extract, Transform, and Load (ETL) processes to automate and optimize data collection and analysis. ML has not only provided a means to ensure data quality but also enabled the improvement of predictive outcomes based on the insights drawn from the clinical data analyzed through algorithms such as recurrent neural networks (RNN) and k-means algorithms. The focus of this article is on discussing how ML has been applied in various areas of healthcare for data analytics. The article also analyzes the significant benefits that have been realized through the use of ML.
Machine learning, healthcare, predictive analytics, ETL, data warehousing.
Shohreh Kia, Technische Universit at Clausthal, Germany
This project introduces an advanced monitoring and safety system for the conveyor belt of an eddy current separator, a machine designed to separate metals like aluminum and copper from materials such as plastic, wood, and other non-metals. The magnetic drum generates strong magnetic fields to facilitate separation, but the presence of ferromagnetic metals like iron can interfere with the process and create significant fire hazards. To address this, a thermal camera, integrated with a Raspberry Pi, continuously monitors the belt’s temperature. When abnormal heat is detected, the system triggers an alarm through a buzzer and sends real-time alerts and images to technicians via Telegram. This ensures immediate intervention, protecting the conveyor belt’s essential role in the separation process while minimizing safety risks, reducing operational downtime, and preventing potential machine failures.
Internet of Things (IoT); Thermal Imaging Processing; Conveyor Belt Monitoring; Automated Notification System
Shohreh Kia, Technische Universit at Clausthal, Germany
Eddy current separators with conveyor belts are essential in recycling metals such as aluminium and copper from non-metallic materials like plastic and wood. One common issue in these systems is the conveyor belt misalignment over time, which leads to belt damage, process interruption, and energy waste. This paper presents an intelligent system based on machine vision and the Internet of Things (IoT) for detection and automatic correction of conveyor belt misalignment. Belt deviations are detected in using a Raspberry Pi camera mounted above the belt and OpenCV technology. Two stepper motors are installed on either side of the conveyor to correct the belt’s position, and the image analysis and IoT-based control system activate them. The system autonomously returns the belt to the centre without halting the separator or requiring human intervention. Preliminary results indicate that this method improves device efficiency, reduces belt damage, and minimizes downtime and maintenance costs.
Image Processing; Conveyor Belt Misalignment; Stepper Motor Control; OpenCV
Kholofelo Maruma, University of South Africa, Republic of South Africa
The proliferation of electronic commerce (e-commerce) has profoundly reshaped traditional retail business models. This research paper investigates the diverse impacts of e-commerce on brick-and-mortar retail establishments, with a particular emphasis on consumer behaviour, supply chain management, and competitive strategies. By conducting a thorough review of existing literature and analysing case studies, this study elucidates the challenges and opportunities that traditional retailers encounter in the digital marketplace. The findings indicate that, while e-commerce enhances convenience and expands market reach, it also demands significant modifications in inventory management, customer engagement, and technological integration. The paper concludes by offering strategic recommendations for traditional retailers to harness e-commerce advancements, thereby ensuring sustainable growth and maintaining a competitive edge in an increasingly digital economy.
E-commerce, Traditional retail, Business models, Consumer behaviour, Supply chain management, Competitive strategies.
