April 27 ~ 28, 2024, Copenhagen, Denmark
Omar Ali1 and Ahmad Al-Ahmad2, 1College of Business and Entrepreneurship, Abdullah Al Salem University, Kuwait, 2Management Information Systems Department, Gulf University for Science and Technology, Kuwait
While the rapid growth of information technology (IT) adoption within organizations is evident, insufficient attention has been directed towards comprehensively addressing the associated challenges. The existing literature moreover lacks a comprehensive understanding of the whole IT adoption process which the authors address here by providing a systematic review of the challenges to technology adoption based on a total of 98 peer-reviewed articles from the business and management literature from 2018-2024. Accordingly, this review study broadens scholarly understanding of the importance of strategic IT agility and the need to keep pace with competitive information systems and IT environments. The findings enhance understanding of the pre-change and post-change process of IT adoption, expanding knowledge on adoption success and organizational strategies for achieving IT strategic agility. Three key contributions include addressing the lack of comparative studies on IT adoption challenges, adopting a unified approach with an integrated research model, and emphasizing the importance of enhancing an organization's absorptive IT capacity for strategic agility. Future research is encouraged to explore micro and macro features of IT adoption.
Challenges, Information Technology, Adoption, Strategic Agility.
Matthias Schmuck and Mircea Georgescu, Alexandru Ioan Cuza University of Iaşi, Iaşi, Romania
This paper deals with measuring the success of Data Governance as an operational Information Systems. Measuring the Success of Information Systems is an important but controversial issue and evaluating the Success of Information Systems is no easy task. Many models have been developed by researchers to support the fulfilment of both tasks. The main objective of our work as ongoing research is to examine and review the most important models of Information Systems Success. We have compared these models and discussed their relevance to the field of Data Governance. Key findings are the adapted and supplemented success factors for Data Governance and a model for measuring Data Governance based on DeLone and McLean's Information Systems Success Measurement Model.
Data Governance, Information System Success, Information System Success Measurement.
Enoch Anning, and Samuel Ato Andam-Akorful, Faculty of Geo and Civil Engineering, Regional Transport Research and Education Centre Kumasi (TRECK), Kwame Nkrumah University of Science and Technology, Kumasi
Roads play a vital role in global socioeconomic development. As such, regular monitoring and maintenance of road infrastructure are essential. However, several challenges hinder effective road maintenance in many developing countries, including data acquisition limitations, lack of dedicated databases, and the absence of a scientific methodology for road selection. This study addresses these challenges by proposing and validating a smartphone-based system for road condition assessment in Ghana. The system utilizes smartphone sensor data to calculate the international roughness index (IRI), an indicator of road quality. The pAVEmATE software application was developed to facilitate data analysis, classification of road conditions, and visualization of results. The system's accuracy was evaluated against data collected using the Roughometer III device on selected urban roads in the Awutu Senya East and Efutu districts of Ghana. Statistical analyses (ANOVA) were used to assess the system's performance. Results indicated that the smartphone-based system demonstrates satisfactory accuracy in estimating IRI and classifying road conditions. The system provides a cost-effective and convenient solution for road condition assessment, facilitating improved road maintenance practices and enhancing the overall quality of road infrastructure in Ghana.
International Roughness Index (IRI), Road Condition, Roughometer III, pAVEmATE.
Cindy Aprilia, Raditya Ardianwiliandri, Sandra Hasanefendic, and Bart Bossink, Breakthrough Technologies and Sustainable Innovation Group, Chemistry and Pharmaceutical Sciences, Faculty of Science, Vrije Universiteit Amsterdam, 1081 HZ, Amsterdam
In modern dynamic and competitive business world, strategic innovation is critical for business survival. However, the complicated relationship between stakeholders and their impact on the strategic innovation process has gotten little attention. This study seeks to address this gap by investigating the organic and multidirectional relationships between stakeholders, with a particular emphasis on how decision-making of technology adoption as a strategic innovation process might contribute to business resilience. By gathering case studies, this study hopes to shed light on ways for understanding how stakeholder connections lead to business resilience. The results of this research will benefit academics, industry, and policymakers in their efforts to encourage long-term innovation and corporate growth.
strategic innovation, technology adopted business, business, technology adoption, stakeholder relationships, organic relationships, multidirectional relationships, empirical evidence, strategies, academia, industry, policy-makers, stakeholder management, collaboration, knowledge exchange.
Jader Martins Camboim de S1,2, Matheus Ferraroni Sanches2, Rafael Roque de Souza2, J´ulio Cesar dos Reis2, Leandro Aparecido Villas2, 1Luxembourg Institute of Science and Technology (LIST), 2Institute of Computing - University of Campinas (Unicamp)
Fine-tuning language models in a downstream task is the standard approach for many stateof-the-art methodologies in the field of NLP. However, when the distribution between the source task and target task drifts, e.g., in conversational environments, these gains tend to be diminished. This article proposes a sequence of pre-training steps (a curriculum) guided by “data hacking” and grammar analysis, allowing further gradual adaptation between pre-training distributions. In our experiments, we acquired a considerable improvement from our method compared to other known pre-training approaches for the MultiWoZ task.
task-oriented dialog systems, natural language generation, curriculum learning.
Yuqi Yang1, Yu Sun2, 1Troy High School, 2200 East Dorothy Lane, Fullerton, CA 92831, 2Computer Science Department, California State Polytechnic University, Pomona, CA 91768
Music plays a vital role in therapy, offering a unique avenue for emotional expression and connection. This proposed project seeks to enhance the effectiveness of music therapy by leveraging natural language processing (NLP) techniques and machine learning to provide personalized song recommendations based on both emotional and narrative elements within lyrics, moving beyond traditional approaches that focus solely on emotional categorization [4]. By utilizing keyword matching algorithms, the project expands the scope of song selection, allowing users to explore music beyond predefined emotional categories [5]. The proposed system integrates with Firebase for efficient data storage and retrieval, while the Flutter framework facilitates the development of a user-friendly mobile application interface [6]. Through this interdisciplinary approach, the project endeavors to offer an accessible and automated music therapy experience.
Natural Language Processing, Machine Learning, Flutter, Mobile Devices.
Aaditya Baranwal, Jyotin Goel, Prashant Tandon, enu Sankhla and Sukriti Goyal, Indian Institute of Technology Jodhpur
This work addresses the challenge of domain-specific question answering through the intelligent composition of tool sequences using a large language model. We formulate the problem as utilizing a set of tools T to answer a query Q by determining the necessary tools, arguments, and execution sequence. Our approach enhances language model capabilities through prompt engineering, leveraging advanced reasoning, and adopting our custom Chain of Thoughts (CoT) inspired strategy for dynamic, cascaded user engagement. Employing multi-task learning broadens knowledge scope, while transfer learning from domains with richer tooling enhances versatility. Runtime compute costs are optimized through distillation. The evaluation shows our method excels in selecting optimal tool combinations for domain-specific queries, outperforming baseline approaches in accuracy and coverage. This approach provides a reusable framework for constructing proficient and cost-effective domain-specific Question Answering (QA) solutions. Key explorations encompass analysis of prompt engineering for tool interfaces, compositional learning across tools, transfer learning from richer domains, and prompt distillation. These facilitate the practical deployment of LLMs for industrial applications.
Query, Tool, Tool Retrieval, Chain of Thoughts(CoT) Prompting, Prompt Engineering, QA, Distillation Step by Step, Array of Thoughts(AoT), GPT, LLM, Rationale.
Kyle He1, Carlos Gonzalez2, 1Portola High School, 1001 Cadence, Irvine, CA 92618, 2UC Berkeley, 2000 Carleton Street # 2284, Berkeley, CA, 94720
SyntaxStar, a desktop program management system, aims to enhance writing quality for users. Ineffective word choices hinder engagement and effective communication, contributing to reading struggles among eighth graders which often leads to a challenging pathway in higher education [7]. SyntaxStar addresses these concerns, emphasizing the importance of writing as a fundamental communication skill, and is driven by the goal of avoiding repetition and improving clarity. Upon creation of this project, things to note are that there exists no current method to update the software automatically for users. There is also no current way of receiving user feedback, which can significantly maintain the longevity and integrity of the software design. Despite this, the pipeline has been solidified and working with an interactive frontend, a comprehensive backend that hosts the application and machine learning model [9]. With regards to performance, the concept of word similarity in the Word2Vec library was applied to not only cross-check words with their paired synonyms but also to assign a score for these synonyms [8]. Cosine similarity scores were applied and distributed onto a plot which showcases how accurately the model classified words with their appropriate synonym. In the future, the model can improve by looking at a more intensive preprocessing section by shuffling words and their parts of speech, prior to recommending a synonym. This is for the sake of adding variability and reducing bias for synonyms that wouldn’t make sense in certain contexts. To propel future growth, more marketing and publications should be incorporated to generate awareness and usage of the app. Developing more components for the software, such as a dedicated website serving as the landing page for a downloadable version, would also be beneficial.
Adaptive, Desktop Program Management System, NLP, Machine Learning.
Raghad Sili Alsahli, Rana Fahad Alobud, Lamya Abdulaziz Alsuhaibani,Munirah Fahad Alfarraj and Maali Alabdulhafith, College of Computer and Information Sciences, Princess Nourah Bint Abdul Rahman University, Saudi Arabia, Riyadh
In the wide world of networks, the concept of TCP/IP is considered one of the most important concepts, and because of its complexity, building a complete understanding is considered a challenge because it contains five layers, and each layer has its own set of protocols and functions, with a connection between the layers. TCP/IP model works behind the scenes, making it difficult to see and directly experience it. Relying just on traditional teaching methods and not taking advantage of advanced technologies causes a lack of perception and interest on the students. Findings showed that at least one AR learning object had been developed by 70% of the top-20 universities in 2018, showing the increasing use of AR technology as an educational tool. In light of the previous argument, at our project, we aim to introduce immersive techniques to address the difficulties associated with understanding the complexities of the TCP/IP model and to make students immersed in its concept, which are AR and gamification. AR is a technology that combines the virtual and real world, which in turn will help to understand the layers of the TCP/IP model and see what is happening behind its scenes. Gamification is a technique to improve engagement and increase excitement through the use of challenges and scores. By combining AR and gamification, we launch an immersive learning environment to improve learning effectiveness and capture students' attention, enhancing their engagement and immersing them in educational activities.
TCP/IP model, AR, Gamification, Immersive learning, Networks.
Yujun Wang1, Fangzhou Sun2, 1California State Polytechnic University, Pomona, CA 91768, 2Match Group LLC, 8750 N Central Expy, Suite 1400, Dallas, TX 75225
This paper presents the development of a mobile application designed to integrate event management with art history education, leveraging Dart and Flutter for frontend development and Python for backend processes, including web scraping [3]. Addressing the gap in accessible cultural education, the app combines intuitive event management with enriching art historical content, aiming to democratize art education and enhance user engagement. Through usability surveys and performance analysis, the application was evaluated for its user interface, content relevance, and technical efficiency [4]. Key findings indicated high usability and educational value, though opportunities for optimization in content loading and responsiveness were identified. Comparative analysis with existing methodologies highlighted our app's broader accessibility and interactive learning potential, surpassing limitations of classroom-bound or high-tech dependent solutions. Experimentation across various user scenarios underscored the app's effectiveness in fostering a dynamic community of art enthusiasts. The results advocate for the app's utility in making art history engaging and accessible, proposing a model for future educational tools.
Mobile Application, Art History Education, Event Management, User Engagement.
Yves Spencer Catuday, Mark Jerald De Torres and Godwin Emmanuel Tayas, Department of Electronics Engineering, Batangas State University, Batangas City,Philippines
This study presents the development of an attendance monitoring system that utilizes face recognition technology. The system is built using Python libraries and aims to provide an efficient method for tracking student attendance in educational institutions. The study discusses the rapid advancements in face recognition technology and its growing application in various fields, including security, authentication, and identification. Traditional attendance methods are often tedious and time-consuming, leading to the exploration of automated systems like the one proposed in this study. The system works by initializing a web camera and detecting student’s faces in real time. Once a face is recognized, the system marks the student’s attendance. The system has been tested with a dataset of 25 student images, achieving a recognition rate of 92% and an overall accuracy of 84%. Despite some challenges, such as the complexity of installing Python libraries and factors affecting recognition accuracy, the system demonstrates the potential for real-world application. The study concludes that face recognition libraries in Python can successfully locate and identify faces from a database, making them suitable for attendance monitoring scenarios. For future research, the study suggests adding features to adjust video quality based on surrounding conditions and incorporating a stabilizer to improve the accuracy and stability of the recognition phase. The researchers believe these enhancements could improve system performance and broader applicability. This study contributes to the growing body of research on the practical applications of face recognition technology and offers a novel approach to attendance monitoring in educational settings.
Face Recognition, Python, Attendance Monitoring System, Face Recognition Library.
Petros Dhespollari, University of West Attica, Athens, Greece
This paper outlines a mobile application architecture designed to aid users in managing stress and anxiety effectively in their daily lives. The application encompasses a range of features, including meditation, breathing exercises, and stress monitoring, to offer a comprehensive stress management tool. Beyond the technical aspects, the paper delves into ethical considerations related to user privacy and data security. The primary objective is to develop a user-friendly and impactful mobile application that equips individuals with better coping mechanisms for stress and anxiety.
Stress management, Anxiety, Mobile application, Meditation, Breathing exercises
Simge Yatkin1,2 and Tolga Ovatman1, 1Faculty of Computer and Informatics Engineering, Istanbul Technical University, Istanbul, Turkey, 2MGEO Test and Verification Directorate, ASELSAN Inc., Ankara, Turkey
DO-178C stands out as a guiding standard for aviation system development processes. This standard not only mandates ensuring the consistency of requirements in the software verification process but also recognizes it as a mandatory element. The main objective of this study is to introduce a method for analyzing and identifying inconsistencies between high-level requirements using information obtained from a data dictionary. This method aims to transform high-level requirements into logical expressions and then thoroughly examine them using a SAT Solver to detect inconsistencies. While methods focused on identifying inconsistencies among requirements often appear in the literature, this study presents a novel approach to detect contradictions between non-natural language, systematically structured, and language-independent requirements. The goal of this approach is to significantly reduce the review time of high-level requirements in the software verification process. Evaluations indicate that the use of this method results in substantial time savings in the inconsistency detection process.
Contradiction Analysis, High-Level Requirements, SAT-Solver Analysis, Software Verification Process.
Boris Kontsevoi1 ,1Intetics Inc., Naples, FL, USA
This paper explores the seven core principles of the Predictive Software Engineering (PSE) framework. These principles are designed to empower custom software development companies to deliver transparent and reliable solutions, all while adhering to predetermined budgets. The paper delves into each of the seven principles: Meaningful Customer Care, Transparent End-to-End Control, Proven Productivity, Efficient Distributed Teams, Disciplined Agile Delivery Process, Measurable Quality Management and Technical Debt Reduction, and Sound Human Development.
Agile, Disciplined Agile Delivery, Distributed Team, Predictive Software Engineering, Measurable Quality Management and Technical Debt Reduction System (MQM&TDR).
Joseph Willrich Lutalo, Department of Networks, Makerere University, Kampala, Uganda
Existing research shows that offering customer support in any form is a guaranteed means to boost and sustain business growth. Modern support services are steadily embracing automation to improve effectiveness, support scalability, and reduce costs, with the most promising approaches leveraging artificial assistants in the form of chatbots and interactive support services. In this project, we employ the Design Science Research method to explore and then practically implement an original, reusable, re-configurable chatbot platform for designing and delivering autonomous product and customer support services leveraging voice interactions. Further, focus was placed on leveraging a scan-to-know information access model, and we especially considered users operating on mobile computers such as smartphones, with active connectivity. The implemented chatbot platform was explored and evaluated from the context of two practical cases.
conversational agents, human-computer interaction, questionanswering system, chatbots, knowledgebases, digital voice assistants.
Li Sun and Zhulei Huang, Department of Electrical and Computer Engineering, Chengxian College, Southeast University, NanJing, CHN
Blockchain-based digital collection trading platform, the front-end design is based on Vue.js framework and Element UI component library, which realises the functions of search box, navigation bar, collection list, detail page and transaction process. The back-end is built with Springboot framework, mysql database and kafka, and combined with the self-designed blockchain system, which runs on Linux operating system. In the design of the blockchain system, remove the "mining" function to compete for the right to create blocks, instead of creating blocks for the main server, using the characteristics of the Merkel tree and the Merkel Patricia tree, to explore the application of the coalition chain that is more in line with the idea of centralisation. In particular, this paper gives considerations on the security design of the transaction system.
blockchain technology, federation chain, SpringBoot framework, digital collections.
Haruna Ali Isah, Department of Mechatronics, Faculty of Engineering Aliko Dangote University of Science and Technology, Wudil Kano
This paper examines the impact of artificial intelligence (AI) on enhancing educational standards in secondary schools, focusing on the context of Kano State, Nigeria. Specifically, the study investigates the influence of AI chatbots on academic performance and learning outcomes among students attending day schools versus boarding schools in the state. Data were collected from 43 Science and Technical secondary schools, comprising 30-day schools and 13 boarding schools. Findings suggest that students with access to AI chatbots, particularly those attending day schools and equipped with Android phones and internet connectivity, exhibit higher levels of academic intelligence compared to their counterparts in boarding schools. The paper underscores the potential of AI chatbots in facilitating research, assignments, tests, homework, and clarifications, thereby contributing to a more effective learning environment.
Artificial Intelligence, Educational Standards, Secondary Schools, Kano State, Nigeria, AI Chatbots.
Sonia Khali1, Oussama Zehri2, 1M.Sc. Automation and System Control, Faculty of New Technologies of Information and Communication (FNTIC), Kasdi Merbah University, Algeria. Senior R&D Automation Engineer, Vestel, Turkey, 2M.Sc. Automation and System Control, Faculty of New Technologies of Information and Communication (FNTIC), Kasdi Merbah University, Algeria.
well- created control strategy for optimum control of strained multivariate systems. The twin-rotor multiple-inputs multiple- outputs (TRMS) is a non-linear system with important cross-coupling between horizontal and vertical axes presenting great challenges in the conception of modelling and control. There are cases once a theoretical conception can create issues once it involves to practical implementation, especially when conception is for non-linear systems. That’s why this paper presents a notably feasible MPC conception for TRMS that has been performed with success on a laboratory TRMS benchmark. The given conception is better adapted for TRMS as a result of that it will handle the control constraints related with the system through to the optimization algorithm program underlying the MPC scheme. From the point of vision of the system, all control objectives are addressed, viz. stabilizing the system in coupled conditions and ensure that its beam can follow a specified reference path or reach the desired positions in 2DOF (two degrees of freedom) without violating control input constraints. The conception also incorporates the disturbance rejection requirement. Simulation and experimental results are presented to show that the results of the practical performance are consistent with the simulated results.
Model Predictive Controller, TRMS, Cross-coupling, MIMO system, Constrained, Multi- output.
Guannan Du1, Khoa Tran2, 1Sage Hill School, 20402 Newport Coast Dr, Newport Beach, CA 92657, 2Computer Science Department, California State Polytechnic University, Pomona, CA 91768
In the wake of the Covid-19 pandemic, teenagers worldwide have faced unprecedented stress and mental health challenges. This research paper presents a novel mobile application, designed as a technologically advanced solution to support the mental well-being of this vulnerable demographic [11]. Leveraging cutting-edge AI technology, the app offers personalized advice and support based on individual user inputs, such as emotional states and preferences captured through diary entries [12]. It uniquely integrates location-based volunteer activity suggestions, aiming to engage teenagers in community service, thereby enhancing their sense of purpose and connection. The core of the application includes a sophisticated AI feedback system, personalized volunteer opportunities, and a secure personal journaling feature, all tailored to meet the diverse needs of teenage users. Experimental results have demonstrated the AI system's superior accuracy in providing advice, surpassing that of human volunteers, with an accuracy rate of 80% compared to the volunteers' 75%. Additionally, user engagement experiments using A/B testing methods on UI design changes showed a significant increase in user interaction and time spent within the app, highlighting the effectiveness of the enhanced card layout over traditional Gridview layouts. These findings underscore the application's potential not only in delivering accurate, personalized mental health support but also in fostering a greater sense of community and engagement among teenagers. By addressing the pressing need for accessible, personalized mental health solutions, this work contributes significantly to the discourse on leveraging technology to mitigate the mental health crisis among youth, advocating for the broader adoption and continuous development of such innovative approaches.
Mobile Application, Interpret, Artificial Intelligence, Machine Learning.
Xi He1, Khoa Tran2, 1Northfield Mount Hermon, One Lamplighter Way, Gill, MA 01354, 2Computer Science Department, California State Polytechnic University, Pomona, CA 91768
There is a growing need for a modern platform for learning and discussing mathematics. With the development of mobile technology, mathematicians worldwide can communicate easily with each other. This paper develops an application using simple AI and data structure to build a social network for everyone to learn and appreciate math with like-minded people. We use Firebase as a backend service provider for Authentication and cloud storage with blocking posts and comments feature. The app is great for math lovers worldwide, with our experiments showing that the mean time for a complete browsing section is approximately 14.545 milliseconds and a median of 13.8 milliseconds across regions. In addition, our built-in blocking mechanism will ensure that people can feel the inclusivity and openness that allows math ideas to freely flow without fear or prejudice. For this application, we took reliability, usability, and openness into consideration. The application aims to be an open platform for every math lover and encourage people to look at math more interactively.
Flutter, Data sorting, Mobile development, Mathematics.
Mayank Choudhary and Naveen Chauhan, DoCSE, NIT Hamirpur, Himachal Pradesh, India
In medical image analysis, the diagnosis and classification of skin lesions remains a tedious task and requires experienced doctors for precise classification. Skin lesion is a common type of skin cancer that exists worldwide. Skin lesions represent a wide range of skin conditions and cancers, making their diagnosis and treatment quite challenging. Early detection is key for better outcomes, prompting researchers to explore computer-based tools for analyzing these skin issues. This paper explores the integration of technology into dermatology, aiming to facilitate more impartial diagnoses through automated systems like cutting-edge techniques in computer vision and machine learning. It dives into the hurdles faced, like dealing with unbalanced data and finding precise areas of concern. In this paper a U-Net based model for precise segmentation of skin lesions due to its ability to precisely outline boundaries and capture intricate details, crucial for accurate diagnosis and treatment planning in dermatology is proposed along with a CNN model like VGG architecture for classification. This architecture is employed due to its robustness through deep and well-defined layers, enabling extraction of complicate features and patterns.
Segmentation, Classification, U-Net, VGG, skin disease.
Bharath Kumar Reddy Kalluru1, Tirumuru Ketha2, 1Machine Learning Engineer, Frisco, Texas-75033, USA, 2Department of Artificial Intelligence, University of North Texas, USA
The burgeoning field of Generative AI relies heavily on Multifaceted Large Language Models (LLMs) to achieve tasks like NER, Document summary, Translation, Text classification, Sentiment Analysis, Text generation, Question & Answer and Document Similarity. However, developing and deploying these complex models remains a challenge due to concerns about security and scalability. This paper proposes "NLP Ops: A Comprehensive Framework for Secure Development and Scalable Deployment of Multifaceted LLMs in Generative AI." This framework addresses these challenges by combining best practices in secure software development, distributed computing, and operational monitoring. The framework encompasses secure data handling, adversarial training, containerization, distributed infrastructure, and comprehensive monitoring for performance and security. Results demonstrate that NLP Ops [mention key findings, e.g., improves security by 98%, increases processing speed by 97%. This paper contributes to the advancement of NLP Ops by providing a practical and secure approach to developing and deploying Multifaceted LLMs, paving the way for wider adoption of Generative AI technologies.
LLM, Generative AI, NLP, LLM, MLFlow.
Pak Hon Li1, Yujia Zhang2, 1Sage hill school, 20402 Newport Coast Dr, Newport Coast, CA 92657, 2Computer Science Department, California State Polytechnic University, Pomona, CA 91768
Ensuring child safety around swimming pools remains a paramount concern for parents and caregivers [4]. In this research, we present an innovative child safety system that leverages advanced computer vision technology and mobile app integration. Our system employs the YOLOv5 object detection model to continuously monitor swimming pool areas for the presence of children [5]. Upon detection, it promptly sends real-time alerts to parents' mobile apps, allowing for proactive supervision and accident prevention. We conducted two experiments to evaluate the system's performance: one focused on the object detection model's accuracy, achieving high precision and recall rates of 93.5% and 82.2%, respectively, while the other assessed the system's real-world applicability and mobile app functionality [6]. The results indicate robust child detection capabilities and reliable alerting mechanisms. By addressing limitations such as environmental factors and usability, our project strives to enhance child safety near swimming pools, offering a valuable contribution to the field of safety technology [7].
Child Safety, Computer Vision, Mobile App, Object Detection.
Carie Chen1, Carol Chen1, Justin Lou2, 1Arcadia high school, 180 Campus Drive, Arcadia, 91007, 2Computer Science Department, California State Polytechnic University, Pomona, CA 91768
Our project is centered on the concept of making music accessible to all individuals, including those with hearing impairments. Music can often play a large role in many lives, able to serve as a source of emotional comfort for many.As the numbers of hearing-impaired individuals rise significantly each year, it is important to enhance accessibility within their lives, including ways to experience the joy of music. By creating a device with vibrations and LED lights that sync with the beat/tempo of each song, this new way of music is easily accessible to all, especially to those with hearing impairments [7]. Leveraging our coding skills, we designed a program that could analyze a specific audio file. The analyzed information is then sent to our raspberry pi, connected to a haptic controller and LED lights through GPIO pins, this allows an easily accessible and functioning process for all users [8].
Musical Accessibility, Hearing Impairments, Haptic Feedback, Synchronized Music Device.
Wang Hsiao-Wen1, Chan Yao-Cheng2 Shen Yi-Jo2, Xin Yun-Jiang1, Shiau Yu-Jen2, Roy Chaoming Hsu2, 1Dept. of Horticulture, 2Dept. of Electrical Engineering, National Chiayi University, Chiayi
To improve the efficiency and accuracy of estimating the Anthracnose occupancy ratio (abbreviated as AOR, hereafter) of Mango fruit in real-time, this study employed a machine learning method andused ”Wan Li Shiang” mango as a model. The whole fruit is photographed first, and then it is cut in half, the flesh is removed and the pericarp is set flat for photo taking. The actual AOR on the pericarp of both the photo-taken whole fruit and the flatten one are first calculated using image processing to develop a training set, and the linear regression of machine learning is employed by training with the AOR training set to establish the regression model applicable to the ”Wan Li Shiang” mango in estimating the AOR of a testing whole fruit photo. Experimental results exhibited that by employing the proposed machine learning method, the AOR error between the photo of the real and the estimated flatten pericarp is less than 1% and is satisfactory by the horticultural experts. If the proposed method is designed into an App on the smartphone, it not only will be a valuable supporting tool for the commodity trading in real-time, but it also can be an intelligent assistant tool for the horticultural researchers to enhance the efficiency of the research.
Anthracnose, Image Segmentation, Machine Learning, Linear Regression, Automated Inspection.
Shengyu Wang1, Jonathan Sahagun2, 1Margaret’s Episcopal School, 31641 La Novia Ave, San Juan Capistrano, CA 92675, 2Computer Science Department, California State Polytechnic University, Pomona, CA 91768
Owning a dog entails numerous responsibilities, among which is the crucial task of dedicating sufficient time to training [1]. While the specific time investment varies, training demands unwavering commitment and effort. However, many dog owners struggle to allocate ample time, resulting in untrained canine behavior [2]. Research indicates that approximately 75% of the world's dogs lack proper training. Effective training forms the cornerstone of a harmonious human-canine relationship, fostering mutual understanding and safety [3]. Despite its significance, training requires patience, consistency, and perseverance, often underestimated by owners. Addressing this issue mandates a shift in owners' perspectives, emphasizing the importance of prioritizing training through professional guidance and obedience classes. Ultimately, investing in training enhances dogs' quality of life and strengthens the bond between owners and their beloved companions, reflecting the dedication required to ensure canine well-being in an evolving world.
Dog Training, Artificial Intelligence, Human-Canine Bond.
Abby Zhang1, Andrew Park2, 1Deep Run High School, 4801 Twin Hickory Rd, Glen Allen, VA 23059, 2Computer Science Department, California State Polytechnic University, Pomona, CA 91768
In an increasingly digital world, maintaining good posture is essential for overall health and well-being. This paper introduces a novel solution, a mobile camera system leveraging computer vision and artificial intelligence (AI) technologies, to assist individuals in maintaining better posture. The system utilizes the camera on a mobile device to continuously monitor the user's posture in real-time. Computer vision algorithms analyze the user's body position and alignment, while AI algorithms provide personalized feedback and guidance based on established ergonomic principles. Through the integration of advanced technologies, the system aims to promote awareness of posture habits and encourage corrective actions to prevent musculoskeletal issues associated with poor posture. This paper discusses the design, implementation, and evaluation of the mobile camera system, highlighting its potential to revolutionize posture management practices and improve overall health outcomes in the digital age.
Posture, Artificial Intelligence, Raspberry Pi, Flutter.
Zhijun Zhang1, Austin Amakye Ansah2, Ang Li3, 1Columbia International College, 1003 Main St W, Hamilton, ON L8S 4P3, 2The University of Texas at Arlington, 701 S Nedderman Dr, Arlington, TX 76019, 3California State Polytechnic University, Pomona, CA 91768
Some people keep journals to track their mental health or keep a record of things happening in their lives [9]. While journaling can help identify patterns in mood and tackle stress and anxiety at the root cause, only 8 percent of the population do it. With the 8.58 billion mobile subscriptions in use worldwide, we take advantage of mobile applications to deliver a quick on-the-go solution for mobile journaling that can be used free of charge [10]. This application utilizes NLP to determine user mood and provide tasks and goals that the user can work towards to improve their well-being. The NLP model developed in this paper has an accuracy of about 91% in correctly classifying moods on a sequence of words in a validation dataset. The model is good enough for most text-based emotional sentiment analysis needs but could be re-trained to attain better results.
Journal, AI, Mental Health, Chat.
Li Sun, Yingxia Zhang, Hao Xu and Zhaolong Jia, Department of Electrical and Computer Engineering, Chengxian College, Southeast University, NanJing, CHN
In the computer professional course, the experiment of computer instruction and execution has the characteristics of "the information evolution process is invisible, and the computer microstructure is inaccessible", and by using the virtual simulation experiment of instruction based on VR technology, it provides a more intuitive way for students to understand the abstract concepts. This experiment constructed a command demonstration system with the help of Unity 3D development platform, through the study of command execution, an abstract and difficult to understand computer work process, and combined with 3D model visual display of command execution, achieved an intuitive image of the teaching effect, which will help students to understand the basic concepts related to the computer command system and command execution, and enhance the importance of the design of command system ie appropriate in this document. Although formatting instruction the computer system. This will help students understand the basic concepts of computer instruction system and instruction execution, and enhance the importance of instruction system design in computer system.
Instruction systems; virtual simulation; principles of computer composition; 3D model visualisation.
Junhan Wang1, Jonathan Sahagun2, 1Santa Margarita Catholic High School, 22062 Antonio Pkwy, Rancho Santa Margarita, CA 92688, 2Computer Science Department, California State Polytechnic University, Pomona, CA 91768
In this paper, we tackle the pressing communication gap between the Deaf and hearing communities, an issue affecting millions of individuals worldwide [1][2]. The proposed solution is a machine learning-powered application that translates sign language into text in real-time, allowing Deaf and hearing individuals to communicate directly [3]. The development faced challenges such as acquiring a diverse and accurate dataset and managing real-time processing of gestures. Experimentation involved testing the model's accuracy across multiple users, revealing promising outcomes. Two existing methodologies, a sensor-based glove and a single-camera solution, were compared, highlighting areas for potential enhancement in our approach. Despite the diversity of sign languages and their unique grammatical structures, the project represents a significant step towards more accessible communication. It highlights the potential for further advancement in machine learning applications for translation and inclusivity.
Artificial Intelligence, Machine Learning, Gesture Recognition, Sign Language Translatio
Khaled A. Dweikat1 and Tahani Bsharat2, 1Faculty of Educational Sciences , Associate Professor, Al-Quds Open University, Palestine, 2International Islamic University Malaysia (IIUM).Assistant Professor
The study explored the perceptions of university students majoring in English language and literature at a Palestinian university towards Microsoft Teams during the war on Gaza that started on the seventh of October 2023. The study also sought to investigate the students’ readiness and acceptance of Microsoft-based online learning. To achieve these objectives, a sample of 145 EFL students studying at the Department of English Language and Literature at Al-Quds Open University (QOU) was randomly chosen to fill out an online questionnaire sent to their accounts on the academic portal of QOU in the first semester of the academic year 2023/2024. The collected data were analyzed using SPSS software. Findings indicated a positive perception with a mean score of 3.85. Distractions during MST sessions were a major concern, with a mean score of 3.21, indicating a need for further investigation. However, no significant differences were found based on gender, location, or study level. The study highlights the positive effects of MST, and contextual variables' impact, in addition to highlighting challenges like distractions and creating a supportive learning environment. The study recommends enhancing concentration through interventions and addressing home distractions, but its generalizability is limited to a single university and the long-term effects of MST usage should be explored.
Students’ Perceptions, Readiness, Acceptance, Microsoft Teams-Based Learning, War on Gaza.
Kazhal Abdi1, Mehdi Sarkhosh1, Fatemeh Moafian2, 1Applied Linguistics English Department, Urmia State University, Urmia, Iran, 2Applied Linguistics English Department, Kosar University of Bojnord, Bojnord, Iran
Lexical knowledge development has always been a seriously challenging task for L2 learners throughout their language learning process, and the necessity of identifying the most efficient L2 vocabulary input encoding for a long-term retention has been an arising controversy in the field in a constant manner. In this regard, this study was an attempt to explore the efficiency of single- and dual-coding representation of L2 vocabulary items in recalling and retention of concrete words in two succeeding and distinct phases. In Phase One, four distinct groups of male and female language learners (n=80) received target concrete word instruction within the framework of verbal- (i.e., word-only flashcards and L1 equivalents) and visual-coding channels (i.e., picture-supported flashcards). In Phase Two, three distinct groups of participants (n=60) were provided with verbal-, visual-, and dual-coding (i.e., verbal representation paired with pictures and L1 equivalents) instructions of target concrete words. A comparison of pretest and posttest scores in each of the two phases provided support to pairing verbal-coding of L2 vocabulary teaching with visual imagery and dual-coding for concrete word items. It was then implied that solely focusing on verbal encoding could hinder language learners from building the L2 lexicon in an efficient and progressive manner, which could in turn overshadow their communicative language ability in the target language.
single-coding; visual imagery; dual-coding; concrete word
Xie Kanqi , Mohamad Yusof Darus, Liao Boxun, Ding Nan, College of Computing, Informatics and Mathematics,Universiti Teknologi MARA(UiTM) ,Shah Alam, Selangor, Malaysia
Distributed Denial of Service (DDoS) attacks pose a significant threat to network security. In response, this paper examines the potential of countering DDoS attacks through the integration of SoftwareDefined Networking (SDN). SDN, with its separation of network control logic from underlying routers and switches, allows for centralized control and facilitates communication between software components. Moreover, the synergy of SDN with Machine Learning (ML) and Deep Learning (DL) technologies offers a promising avenue for effective threat mitigation. This systematic review explores the evolving landscape of information security defense frameworks within the context of Internet of Things (IoTs) security. Over the past five years, numerous articles have contributed to the understanding of SDN based DDoS defense architecture. This review encompasses various aspects, including the design of SDN based DDoS frameworks, implementation steps, data analysis methods, DDoS data sources, and application scenarios of defense frameworks. Performance and characteristics of different defense technologies are analyzed, addressing common challenges in the research field. The insights provided in this paper aim to serve as a valuable reference for researchers seeking to develop efficient and reliable DDoS defense frameworks within the SDN paradigm.
Software Defined Networks (SDN), Distributed Denial of Service (DDos)，IoT，Machine Learning and Deep Learning.
Kaiwen Yang, Tyler Boulom, San Juan Hills High School, 29211 Stallion Ridge, San Juan Capistrano, CA 92675, Computer Science Department, California State Polytechnic University, Pomona, CA 91768
This paper addresses the critical gap in public knowledge and skill in performing Cardiopulmonary Resuscitation (CPR), a key factor in increasing survival rates in cardiac arrest scenarios [1]. Despite the importance of CPR, traditional training methods often fail to reach or engage the general population effectively. Our proposal introduces an innovative, interactive digital CPR training platform that combines the latest in educational technology with the principles of gamification and simulation-based learning [2]. Key components include a user-friendly interface, realtime feedback mechanisms, and scenario based simulations that cater to a wide range of learning styles and environments. Challenges such as ensuring the physical accuracy of CPR techniques and broadening accessibility were addressed through the integration of adaptive learning algorithms and offline functionalities [3]. Experimentation across various settings demonstrated significant improvements in users' CPR knowledge, skills, and confidence. The results underscore the platform's potential to democratize CPR training, making it more accessible, engaging, and effective. Our project offers a scalable solution to a widespread public health issue, advocating for its adoption as a standard in CPR education.
CPR, Digital Training, Interactive Simulations, Gamification.
Boming Wen, Tyler Boulom, Tarbut V'Torah, 5 federation way, Irvine, CA 92603, Computer Science Department, California State Polytechnic University, Pomona, CA 91768
This project aims to solve financial illiteracy with a game designed for kids [14]. In modern day America, especially among teenagers and children, there has been a lack of education in economics. The paper took a look at multiple sources and revealed that over 75% of teenagers lack confidence in their financial knowledge, according to Key Financial Literacy [10]. In a CNBC interview, 17-year-old Emmalina Simonis, a senior at JA Academy in Orlando, Florida, showed that children are aware of current financial issues and are motivated to learn however they lack access to necessary resources [12]. In the same article 45% of teens said education was the best way to address financial illiteracy. This project integrated fundamental concepts such as interest and stocks, providing children with a solid foundation of financial understanding. While developing the game, there were many challenges such as needing to make an easier method for implementing concepts without overwhelming players with information. After testing in different scenarios, it was determined that introducing straightforward concepts proved more effective than overloading children with excessive information. Making the project an accessible and efficient way for kids to learn financial basics [15].
Financial literacy, Children, Teens, Project Based Learning.