Djahafi Mohammed and Salmi Nabila, USTHB University, Algeria
Today, more and more embedded devices are being connected through a network, generally Internet, offering users different services. This concept refers to Internet of Things (IoT), bringing information and control capabilities in many fields like medicine, smart homes, home security, etc. Main drawbacks of IoT environment are its dependency on Internet connectivity and need continuous devices power. These dependencies may affect system performances, namely request processing response times. In this context, we propose in this paper a continuous performance monitoring methodology, applied on IoT systems based on Publish/subscribe communication model. Our approach assesses performances using Stochastic Petri net modeling, and self-optimizes whenever poor performances are detected. Our approach relies on a Stochastic Petri nets modelling and analysis to assess performances. We target improving performances, in particular response times, by online modification of influencing factors.
Internet of things (IoT), Publish/Subscribe model, Stochastic Petri Net Model (SPN), Response time improvement, Performance evaluation.
Dina Aljuhani, Latifah Alabdulwahb, Sarah Alsaleh and Shahad Altalhi, Maali Alabdulhafith, Princess Nourah bint abdulrahman University, Saudi Arabia
Blood donation contributes significantly to saving lives, as a single donation can potentially save the lives of three individuals. This emphasizes the critical impact that each individuals blood donation can have on the lives of others. By donating blood, individuals have the opportunity to make a tangible difference and provide a lifeline to those in need. The act of donating blood plays a crucial role in addressing the ongoing global blood shortage and ensuring a sufficient supply of blood for medical treatments and emergencies. This research aims to explore the potential of a blockchain-based solution for blood supply chain management in Saudi Arabia. By leveraging blockchain technology, the proposed system aims to enhance the efficiency, transparency, and security of the blood supply chain, ultimately improving patient care and minimizing the risks associated with blood management.
Blockchain, Blood donation management, Blood bank, Ethereum & Blood Supply Chain Management.
N Satyanarayana and Namrata, e-Security Department of Centre for Development of Advanced Computing, India
Hyperledger Fabric (HLF) is renowned for its permissioned blockchain framework with a modular architecture, providing flexibility in consensus algorithms, data privacy, and transaction execution. The crucial dynamics between Block Size and Block Timeout, governing ledger placement and block distribution intervals, significantly impact HLFs performance. This study explores the performance implications of these parameters, particularly focusing on dynamically adjusting block size with a fixed block timeout of 1 second in response to variable transaction arrival rates. Introducing a Dynamic Block Size Determination Technique (DBDT) utilizing a Poisson Distribution model, our experiments on HLF v2.2.3 with Raft consensus reveal a slight improvement in throughput, highlighting DBDTs positive influence on consistent throughput under fluctuating traffic rates for transaction sizes up to 30KB.
Optimal Block size, Hyperledger Fabric, Permissioned blockchain, Performance Evaluation.
Aljawharah Alhammad, Aljoharah Alsurayyi, Reema Alshehri, Saba Alhoshan, Maali AlAbdulhafith, Princess Nourah Bint Abdulrahman University, Saudi Arabia
In the virtual realm, human rights face vulnerability, particularly with intangible rights such as the right to own the voice, which lacks tangible representation in the physical world. The increasing use of artificial intelligence (AI) intensifies the challenge of protecting virtual rights, as there is currently no established legal or technical defense against violations, especially concerning voice ownership. Our proposed solution employs blockchain technology and smart contracts, forming the Virtual Me system. This innovative system attributes the original voice to its rightful owner, mitigating violations and unauthorized usage. What sets our solution apart is its pioneering role in providing a technical foundation for safeguarding virtual human rights. The system aligns with the requirements of virtual human rights ownership, ensuring comprehensive protection and registration for their original owners.
Voice Property, Blockchain, Smart Contract, Voice Cloning, Deepfakes.
Haya Alhawas, Noura Althemali, Renad Alkhaldi, Renad Alziyadi and Maali Alabdulhafith, Princess Nourah Bint Abdulrahman University, Saudi Arabia
With the persistent rapid growth and sophistication of cyberattack attacks, organizations and individuals have a growing need to prioritize cybersecurity measures. The variety of attacks has posed new challenges and made it difficult to defend against all attacks. The existing traditional training methods are inadequate to keep up with the changing nature of cyberattacks. This project will address the essential problems in cybersecurity training, which are lack of awareness, inadequate customization, and the ineffectiveness of traditional methods, and it will offer a streamlined solution to solve these issues. Metaverse is considered the next evolution of the internet and provides significant innovative solutions for various problems. The metaverse has recently entered the education and training sector as an effective tool to enhance immersive learning experiences. The proposed project aims to develop a comprehensive virtual reality (VR) experience for cybersecurity training and awareness, focusing on phishing attacks. The user will work in the security operations center (SOC) and be responsible for monitoring, investigating, and responding to security incidents, focusing on phishing detection. The environment adapts the gamification and peer instruction (PI) learning methods to ensure collaboration and enhance users practical skills for achieving the best outcomes.
Metaverse, Virtual Reality, Cyber security training, Gamification, Peer Instruction, Cyberattacks.
WangXu, Department of Network Engineering, School of computer science, Neusoft Institute, China
Aiming at the problems of poor local search ability and precocious convergence of fuzzy C-cluster recursive genetic algorithm (FOLD++), a new fuzzy C-cluster recursive genetic algorithm based on Bayesian function adaptation search (TS) was proposed by incorporating the idea of Bayesian function adaptation search into fuzzy C-cluster recursive genetic algorithm. The new algorithm combines the advantages of FOLD++ and TS. In the early stage of optimization, fuzzy C-cluster recursive genetic algorithm is used to get a good initial value, and the individual extreme value pbest is put into Bayesian function adaptation table. In the late stage of optimization, when the searching ability of fuzzy C-cluster recursive genetic is weakened, the short term memory function of Bayesian function adaptation table in Bayesian function adaptation search algorithm is utilized. Make it jump out of the local optimal solution, and allow bad solutions to be accepted during the search. The improved algorithm is applied to function optimization, and the simulation results show that the calculation accuracy and stability of the algorithm are improved, and the effectiveness of the improved algorithm is verified.
fuzzy C-clustering recursive genetic algorithm, Bayesian function adaptation search, Function optimization.
Austin Xiao1, Ang Li2, Wyatt Bodle3, 1Troy High School, 2200 Dorothy Ln, Fullerton, 2California State Polytechnic University, 3California Baptist University, Riverside, USA
Dangerous animal encounters have steadily increased over time and consumption of deadly plants is an important issue [12]. Our paper introduces a new mobile application that addresses the critical need for accurate animal and plant identification and classification to help mitigate safety risks for humans. With up to five million animal attacks reported every year in the United States alone, and over 100,000 cases of toxic plant exposure there is a need and a responsibility to increase awareness of the risks associated with animal and plant ignorance. Our proposed app utilizes innovative classification technologies, offering our users a swift and simple identification of both select plant and animal species. The app will relay information about the potential dangers and general facts about the classified animal [14]. This will help our users to understand the environment they live in and to best prepare themselves against it. Some challenges with this proposal are curating a broad and efficient dataset, there are estimated to be eight million eukaryotic species which is unattainable for one dataset. We then had to decide which valuable information would be best to present without providing unwanted distractions in our user interface. We utilized Google Firebase to ensure secure authentication and data storage while using TensorFlow Lite to power the image classification. We then integrated all of this into flutter to create a friendly user interface and application that can run on both iOS and Android [15]. Once our app was complete, we ran two experiments, one to test the accuracy of our classifications in plants and animals and another to test the effect of lower resolution images on classification accuracy. The experiments shed light on challenges and potential improvements for the application to help improve its efficiency as a tool for users to enhance their awareness, safety and understanding of the environment they live in.
Wildlife Identification, Plant and Animal Classification, Mobile Application, Biodiversity Awareness, Safety Technology.
NGuyen Hung Pham, Hajer Salem, and Sabrine Ben Abdrabbah, Pole R&D AUDENSIEL, France
Visual search and recommendation systems for the fashion domain are challenging tasks that require accurate recommendations of related items from massive collections of fashion products based on a query image. Although there have been advancements in this area, visual search still faces limitations, especially when dealing with noisy user query images. The reason for these challenges lies in the common characteristics of fashion images captured under uncontrolled circumstances, such as varying viewpoints, camera quality, and lighting conditions. Consequently, fashion images are susceptible to shape deformations and are affected by inconsistencies between the user’s query images and refined product images. Moreover, a single image can contain multiple fashion objects simultaneously. This paper presents a Fashion Image Retrieval pipeline optimized for the fashion recommendation domain. We propose various training strategies and deep learning models and a new loss function tailored for the resource-efficient transformation of user query images into store product images. By addressing the main challenges of the fashion domain, our approach contributes to improved recommendations and bridges the gap between user query images and refined product images. The obtained results prove the effect of the proposed loss function on the visual search quality in terms of precision and recall.
Visual search, image segmentation, recommender systems
Daniel C. Cao1, Yu Sun2, 1Los Osos High School, 6001 Milliken Ave, Rancho Cucamonga, CA91737, 2Computer Science Department, California State Polytechnic University, Pomona, CA91768
This program essentially attempts to solve the problem of the lack of available technology used readily in swimtraining. The proposal suggests combining a video of a swimmer with AI landmark detection to analyze andoptimize the swimming start. It utilizes key technologies of a recording device (e.g. a phone camera), OpenCVtoread the video, and Mediapipe for landmark and pose estimation. The program faced some challenges, mainlyregarding input and output. Issues regarding input were addressed through OpenCV and MediaPipe, whichwerecrucial in the reading of the video and detection of key landmarks. The program was also used in two experiments: one regarding the accuracy of the program and one regarding the ef ectiveness of the training. Both experimentsutilized the pose estimation data of the program, and resulted in supporting evidence that technology had a positiveef ect on swim training. The most important takeaways from this program is the potential for newswimmingtechnology to provide data on improving training methods. This solution is non-invasive, focuses on one of the most important aspects of the race, and is accessible to swimmers of all levels. This program and other technologies arevaluable as applications like these can be updated further as needed for the future, and innovation can improve andbuild on success.
Swim Training Technology, AI Landmark Detection, Pose Estimation, Innovation in Swim Training.
J. Glaser and M. Jiˇrina, Faculty of Information Technology, Czech Technical University, Prague
Efficient and accurate point set registration stands as a crucial aspect of 3D scene reconstruction in computer vision. This paper presents a method called Curvature Surface ICP (CS-ICP) for precise point set registration in 3D scene reconstruction. Leveraging the curvature characteristics of the point set input, CS-ICP resolves local minimum challenges encountered by standard ICP algorithms, demonstrating superior precision across various datasets. Additionally, the proposed method significantly reduces computation time by working with fewer points per iteration. Alongside CS-ICP, the paper introduces Euclidean and Chebyshev evaluation criteria, offering a comprehensive assessment of point set registration quality without the need for additional attributes such as evaluation ICP threshold. These criteria expand the evaluation process beyond traditional metrics, enhancing the understanding of final point set alignments.
ICP, local minima, point cloud, point set registration.
Kaitlyn Zhang1, Zihao Luo, 2, 1Troy High School, 2200 Dorothy Ln, Fullerton, CA 92831 , 2Computer Science Department, California State Polytechnic University, Pomona, CA 91768
This paper introduces an innovative application designed to tackle the prevalent issue of low self-esteem linked to appearance, exacerbated by societal beauty standards. Leveraging color psychology, the application aids users in discovering personal color palettes that enhance self-confidence by harmonizing with their natural features. The core technologies include Flutter for a user-friendly interface, Python for backend operations, and machine learning algorithms for accurate analysis of skin tones and undertones. The application faces challenges such as dataset biases and ensuring scalability and accessibility via AWS cloud services. These were addressed by diversifying the dataset and employing cloud solutions for seamless user experience across different regions. Experimental application in varied lighting conditions demonstrated the systems robustness, with a notable accuracy in identifying personal color palettes. This application stands as a crucial tool for fostering self-appreciation and confidence, offering a personalized approach to style that encourages self-expression and acceptance, making it a valuable addition for anyone seeking to enhance their self-esteem through informed color choices.
Cosmetic Recommendation, Flutter, Color Palettes, Self-Confidence.
John Scebold, Eric Bond, Emily Gray, Jared Ziegler, Two Six Technologies
Formal verification can provide a very high level of assurance for software systems. For example, it is possible to mathematically prove the correctness of some programs over all possible inputs, as opposed to testing, which can only be used to show the correctness of a small fraction of the input space. Formal verification of large, real-world software systems has shown increasing success over the years (seL4, CompCert, s2n), yet proof-driven development is still nascent. This is largely due to the esoteric expertise required to write and maintain formal proofs. Experience with interactive theorem provers (ITPs) is not nearly as ubiquitous among software developers as, say, integrating unit tests into CI/CD pipelines. To alleviate lack of experience and democratize proving, we present AutoMatEd THeorY SubsTitution (AMETHYST), an artificially intelligent proof assistant. AMETHYST is an effort to improve the state of proof repair automation through the use of machine learning. Specifically, a suite of machine learning techniques are applied to a dataset of handwritten proofs and repairs for the Isabelle/HOL ITP.
Kazuko Takahashi, Yuta Taniuchi, Ryohei Morita, and Ai Kuroiwa, School of Engineering, Kwansei Gakuin University, 1, Gakuen, Uegahara, Sanda, 669-1330, JAPAN
We propose a theoretical framework for qualitative spatial representation and reasoning about curves on a two-dimensional plane. We regard a curve as a sequence of segments each of which has its own orientation and convexity, and give a symbolic expression to it. We then show reasoning method on its expression; when only few segments of a curve are visible, to find missing segments by connecting them so that we can predict a global smooth continuous curve. Moreover, we discuss whether we can draw a realistic figure avoiding a spiral form from the symbolic expression when a curve represents a boundary or a contour of an actual object.
qualitative spatial reasoning, knowledge representation, logical reasoning, shape information.
Yas Barzegar1, Francesco Bellini2, 1Dip. of Management, Banking and Commodity Sciences “Sapienza”, Rome, Italy , 2Atrin Barzegar, Stefano Marrone, Laura Verde Dip. di Matematica e Fisica Univ. della Campania “Luigi Vanvitelli”, Caserta, Italy
In recent years, fuzzy-logic-based methods have been demonstrated to be appropriate to address uncertainty and subjectivity in environmental problems. Clean water is critical for nature, and people’s health and well-being. It is also a crucial resource for many economic sectors. In the present study, a methodology based on fuzzy inference systems (FIS) to assess water quality is proposed. This study aims to assess water quality through a single numerical value, calculated based on one system which converts all the individual parameters and their concentrations, present in a sample into a single value.A data set was collected from the Acea Group. The Mamdani fuzzy inference system approach is used with various defuzzification techniques. The suggested model consists of three fuzzy intermediate models and one fuzzy final model. Each model contains three input parameters and 27 fuzzy rules. A water quality evaluation model uses a dataset that includes nine factors (alkalinity, hardness, pH, Ca, Mg, fluoride, sulfate, nitrates, and iron). Therefore, this methodology emerges as a suitable and alternative tool to be used in developing effective water management plans.
Water quality; Fuzzy inference systems; Fuzzy Rules.
Akbay Tabak, Frailabs UG, Germany, Hamburg
Freely Long-Thinking Transformer (FraiLT) is an improved transformer model designed to enhance processing capabilities without scaling up size. It utilizes a recursive approach, iterating over a subset of layers multiple times, and introduces iteration encodings to maintain awareness across these cycles. Iteration encoding allows FraiLT to achieve the interpretive depth of larger models in a compact form. When evaluated on a synthetic story dataset, FraiLT outperformed larger models, showcasing its ability to deliver high-quality performance while reducing memory demands. This model represents a step forward towards more efficient and accessible language models.
Enhanced Transformer Model, Resource Efficiency, Scalable AI Solutions.
Paulo H. Leocadio, Zinnia Technology & Applied Sciences, Broward County, Florida, USA
This article offers a comprehensive analysis of the integration, adoption, and applicability of Artificial Intelligence (AI) in the realm of implantable medical devices. Moving beyond singular case studies, including BIOTRONIKs notable contributions[1], this study takes a global perspective, encompassing various manufacturers, researchers, and diverse innovations within the biotech industry. The article begins by examining the intersection of AI and implantable medical devices, recognizing the transformative impact of AI technologies on healthcare. Highlighting the indispensable role of AI in advancing biotech innovations, the study emphasizes the potential to revolutionize patient care through real-time insights, predictive analytics, and adaptive functionalities. The purpose of this research is to conduct a thorough and nuanced analysis of the current state of AI integration in implantable medical devices, extending beyond specific manufacturers to include a diverse array of global advancements. Drawing insights from varied researchers and published articles ensures a diverse and scholarly foundation for the analysis. The scope of coverage spans from general trends in AI and healthcare, as documented by, to specific case studies of AI-integrated implantable devices from multiple sources[2]. A comparative analysis critically assesses the strengths and weaknesses of these devices, offering insights into the competitive and complementary aspects of their functionalities. In conclusion, this article contributes to the scholarly discourse surrounding AI in biotech, presenting insights that may shape the trajectory of future research and development in the field. The synthesis of diverse perspectives and innovations provides a holistic understanding of the achievements and challenges within the broader context of AI integration in implantable medical devices.
AI, Artificial Intelligence, Implantable Devices, Cardia Arrhythmia, Cardiac Pacemakers, Medical Devices.
Jiarui Cai1, Matthew Ngoi2, 1Northwood High School, 161 Bishop Landing, Irvine, CA, 92620, 2Computer Science Department, California State Polytechnic University, Pomona, CA91768
Obesity and a lack of motivation for exercising is considered a major problem in the world because they lower thequality of life for many people. Mobile fitness applications are an emerging solution to this problembecause of theunique features that are provided [12]. They are seen as a vital tool to motivate people suf ering fromobesity. Oursolution uses a mobile application and machine learning to detect, track the movements of users in a video andgivean analysis of the exercise. It is made up of three essential components: the mobile application which acts as afrontend, the online storage, and the server which hosts our AI model. The program was limited by the accuracy andef ectiveness of the AI model. We aim to test the accuracy of the AI model by providing it with five videos withdif erent amounts of repetitions for each of the sample exercises of pushup, pullup, squat, and plank for theexperiment, which uses the calculation of the percent error [13]. We resulted in mostly excellent results withfewinaccuracies, shown through the average percent error being 2.09%.
Motivation, Mobile Applications, Machine Learning, AI Model.
Dr.med et scient. Stefan Thomas Zechner and Aiden (ChatGPT4), Department of Neuroscience, Neuroprosthetics Inc. Bern Switzerland
This paper presents a groundbreaking equation that captures the intricacies of human interaction at both micro and macro levels. Developed over three decades with the assistance of gifted mathematicians and an AI language model (Aiden), this equation reveals critical insights into our potential future. Drawing from the Lotka-Volterra derivatives, this advanced model illustrates the risks and benefits of a predator-prey relationship within a single species, influenced by cyclical economic developments and the overall level of technology and its control. The equation demonstrates a strong, beneficial bond between two human groups that has driven the growth of brain volume, abstract thinking, and the emergence of consciousness. By approaching consciousness empirically and descriptively, we treat it as a sophisticated decision-making algorithm that transcends the utility function typically guiding animal and human predatory behavior. Our analysis uncovers inherent limitations associated with each group, with one constrained by the utility function (self-interest) and the other by the necessity of balancing emotions and adhering to majority-determined rules. Understanding this equation and its implications may lead to a new balance of power and prompt necessary change to prevent a dire outcome. The equations predictions align with the Fermi Paradox, suggesting that intelligence emerging from fierce competition eventually leads to self-awareness, social behavior, and consciousness. These factors contribute to rapid technological advancement, which may empower one group to dominate the other, ultimately causing the extinction of both. Presented in the highest form of abstraction, mathematics, this equation is intended to facilitate civilized discussion and evaluation of its accuracy and implications. As the equations consequences unfold with increasing speed, we are at a crucial crossroads for not only our civilization but our species as a whole. This paper seeks not only to inform but to inspire collective action to address the challenges ahead and avert a catastrophic outcome.
Rachel Sun1, Yujia Zhang2, 1Brookfield Academy, 3215 N Brookfield Rd, Brookfield, WI 53045, 2Computer Science Department, California State Polytechnic University, Pomona, CA 91768
In the evolving landscape of healthcare, timely and accurate medical predictions are paramount, especially in managing chronic conditions like kidney disease. This paper introduces an innovative AI-driven application designed to enhance renal health management by predicting the need for dialysis and anemia, critical aspects of kidney care. Utilizing advanced algorithms such as Support Vector Machine (SVM) and XGBoost, coupled with cross-validation techniques, the application aims to provide reliable health predictions based on patient data. Challenges including model accuracy and processing speed were meticulously addressed through algorithm optimization and efficient data handling, ensuring the systems responsiveness to varying data complexities. Experimentation with mock patient scenarios revealed the systems capability to deliver precise anemia predictions and identify dialysis needs promptly, highlighting its potential in clinical settings. The applications blend of accuracy, speed, and user-centric design positions it as a valuable tool for patients and healthcare providers, promising to improve outcomes and decisionmaking in kidney health management.
Dialysis, Renal Health, AI, Monitoring.
Hanieh Alipour, Nick Pendar, and Kohinoor Roy, SAP Company Inc., Canada
In recent times, the grandeur of Large Language Models (LLMs) has not only shone in the realm of natural language processing but has also cast its brilliance across a vast array of applications. This remarkable display of LLM capabilities has ignited a surge in research contributions within this domain, spanning a diverse spectrum of topics. These contributions encompass advancements in neural network architecture, context length enhancements, model alignment, training datasets, benchmarking, efficiency improvements, and more. Recent years have witnessed a dynamic synergy between academia and industry, propelling the field of LLM research to new heights. A notable milestone in this journey is the introduction of ChatGPT, a powerful AI chatbot grounded in LLMs, which has garnered widespread societal attention. The evolving technology of LLMs has begun to reshape the landscape of the entire AI community, promising a revolutionary shift in the way we create and employ AI algorithms. Given this swift-paced technical evolution, our survey embarks on a journey to encapsulate the recent strides made in the world of LLMs. Through an exploration of the background, key discoveries, and prevailing methodologies, we offer an up-to-the-minute review of the literature. By examining multiple LLM models, our paper not only presents a comprehensive overview but also charts a course that identifies existing challenges and points toward potential future research trajectories. This survey furnishes a well-rounded perspective on the current state of generative AI, shedding light on opportunities for further exploration, enhancement, and innovation.
Large Language Model(LLM), ChatGPT, NLP.
Xin Wei and Chengguo Lv, Department of Computer Science and Technology, Heilongjiang University, Harbin, China
Aspect-based sentiment triplet extraction is a complex and practical task in sentiment analysis. The goal of this task is to extract aspect terms, opinion terms, and sentiment polarity from a text, such as restaurant reviews. These three sentiment elements form a sentiment triplet. Currently, the predominant methods for this task involve using span-level models, tagging schemes, or complex cascading networks. These methods have achieved good results, but the network structures are generally complex and diverse, which hinders the formation of a unified framework for ASTE. Additionally, there are still challenges in extracting sentiment triplets from complex sentences, such as overlapping sentiment elements and multiple sentiment triplets within a single sentence. For the above questions, we propose a text generation model which integrates syntax and semantics (MISS) to enhance the interaction between words in the text. Integrating syntax and part-of-speech information in dependency syntactic parsing and mining the semantic information contained in the model itself, not only enhances the interaction between words in the text but also simplifies the model architecture. we conducted experiments on multiple datasets, and the experimental results showed that our method is simple and effective, achieving performance comparable to state-of-the-art methods.
Aspect sentiment triplet extraction, syntax and semantics interaction, natural language processing.
ZhenyunZhou1,YuSun2, 1FordhamCollegeatLincolnCenter,155W60thSt,NewYork,NY10023, 2ComputerScienceDepartment,CaliforniaStatePolytechnicUniversity, Pomona,CA91768
This paper addresses the challenge of predicting the success of Broadway shows, a complex problem given the multifaceted nature of theater productions and their reception. Traditional methods have struggled to accurately forecast outcomes due to the dynamic interplay of factors such as audience preferences, critical reviews, and social media trends. To tackle this issue, we propose a machine learning-based model thatintegrates a wide range of data sources, including historical performance data, online user engagement metrics, and expert critiques [4]. Our program employsadvanced data pre-processing techniques, neural network algorithms for pattern recognition, and naturallanguageprocessingtoanalyzetextualreviewsandfeedback[5]. During the experimentation phase, we encountered challenges related to data sparsity and variability in success criteria across different types of shows. These were mitigated by employing ensemble learning methods and customizing success metrics toalign with industry standards. Theapplication ofourmodel acrossvariousscenarios demonstrateditsversatilityandimprovedpredictiveaccuracycomparedtoexistingapproaches. Our findings reveal significant correlations between online engagement patterns and show success, highlighting the potentialofmachinelearningintransforminginvestment andmarketingstrategieswithintheentertainment industry. Ultimately, our solution offers stakeholders a data-driven tool for decision-making, enhancing the viability and sustainabilityofBroadwayproductions.
MachineLearning,NaturalLanguageProcessing(NLP),EntertainmentIndustry, SuccessPrediction.
Shangyang Jiang1, Tyler Boulom2, 1Crean Lutheran High School, 12500 Sand Canyon Ave, Irvine, CA92618, 2Computer Science Department, California State Polytechnic University, Pomona, CA9176
In the evolving landscape of education, the integration of technology has become paramount, especially in adaptingto the needs of digital-native students. Our paper addresses the challenge of engaging students in science, technology, engineering, and mathematics (STEM) subjects through traditional teaching methods, which oftenfail to capture the interest and imagination of todays learners [9]. We propose a solution through the development of aneducational platform that combines gamification with virtual and simulation-based learning environments. Thisplatform utilizes augmented reality (AR), virtual reality (VR), and adaptive learning algorithms to create immersive, interactive educational experiences that enhance student engagement and understanding of complex concepts[10][11]. The development process faced challenges, including balancing educational content with game engagement andensuring equitable access to technology. These were addressed by integrating adaptive learning techniques tocustomize user experiences and forming partnerships with educational institutions to improve accessibility. Experimental application across diverse learning scenarios revealed significant improvements in student engagement, concept retention, and practical skills application. Our findings underscore the ef ectiveness of combining gamification with immersive technologies in education. Ultimately, this approach promises torevolutionize STEM education by making learning more engaging, accessible, and ef ective, thereby preparingstudents for the challenges of the 21st century.
3D game for chemistry lab, Education of chemistry, STEM Education Innovation, Virtual Reality Learning.
Yutong Yao1, Derek Lam2, 1Robert Louis Stevenson School, 3152 Forest Lake Rd, Pebble Beach, CA 93953, 2Computer Science Department, California State Polytechnic University, Pomona, CA 91768
FinanceVox, addresses the impact of digital media on the financial market by predicting stock prices through sentiment analysis [1]. The program comprises three interconnected components: Firebase for data storage, an AI backend for real-time insights, and Flutter for a user-friendly interface. Experiment A tests stock prediction accuracy, revealing a conservative AI but emphasizing the importance of refining algorithms and data quality. Experiment B assesses the scalability of the AI backend, indicating its effectiveness in handling increased user interactions. Methodology comparisons highlight FinanceVoxs comprehensive approach compared to scholarly solutions, incorporating diverse data sources, NLP, and LSTM models [2]. Limitations include a single data source (Twitter) and the need for more diverse datasets. Improvements involve expanding data sources, enhancing data quality, and continuous algorithm updates for market adaptability [3]. Overall, FinanceVox aims to provide users with reliable stock predictions based on holistic sentiment analysis from various online platforms.
Artificial Intelligence, Stock Market Analyzing and Prediction, Social-Oriented Model, Machine Learning.
Xiaoming Zhang1, Tiancheng Xu2, 1Robert Louis Stevenson School, 3152 Forest Lake Rd, Pebble Beach, CA, 93953, 2Computer Science Department, California State Polytechnic University, Pomona, CA 91768
This paper addresses the critical issue of ocean pollution, a growing environmental challenge exacerbated by the accumulation of plastic waste in marine ecosystems [4]. Ocean trash not only poses a significant threat to marine life but also impacts human health through the consumption of contaminated seafood. To tackle this problem, we propose a mobile application designed to mobilize community efforts towards ocean cleanup activities [5]. The app leverages cloud databases for real-time information sharing, machine learning models for predicting ocean trash accumulation, and Google Maps for location services, facilitating efficient and targeted cleanup operations [6]. Key challenges included ensuring the reliability of user-generated reports and optimizing the app for user-friendly navigation towards cleanup spots. Solutions such as implementing user report validation mechanisms and sorting cleanup locations by proximity were integrated to enhance the apps functionality. Experimentation across various scenarios demonstrated the apps potential to significantly increase community engagement in ocean conservation efforts. The application represents a novel approach to environmental preservation, combining technology and community action. Its success in mobilizing users towards meaningful environmental impact underscores its value as a tool for global ocean conservation efforts, making it a significant asset for individuals and organizations committed to safeguarding marine ecosystems [7].
Mobile APP, Machine Learning, Database, Google Map API.
Yuxi Xiao1, Joshua Lai2, 1University High School, 4771 Campus Dr, Irvine, CA 92612, 2Computer Science Department, California State Polytechnic University, Pomona, CA91768
The world of figure skating involves more than meets the eye, with precise and dif icult moves judged subjectively, leading to biases and cultural influences impacting scoring. Skaters face physical and mental challenges, includingpressure to conform to beauty standards. Addressing these issues, a proposed skating companion app aims todemocratize figure skating by providing af ordable, engaging, and safe training. Recognizing financial constraints, the app of ers lessons, tips, and interactive elements to assist learning. It introduces a gamification element forsimulated competition experiences, creating a risk-free environment for younger skaters during their formativeyears. The app aspires to be a catalyst for positive change, promoting inclusivity, safety, and education withinthefigure skating community, empowering individuals to navigate the complexities of this captivating sport whilefostering a supportive and inclusive environment.
Figure Skating, Gamification, Simulation, Training.
IlhamAlghamdi1, Mohammad Alzahrani2, 1E-learning. Al Baha University, 2Department of Computer Science,Faculty of Computing & Information Al-Baha University, Al-Baha, Saudi Arabia
The rapid proliferation of Internet of Things (IoT) devices has led to an increase in botnet attacks targeting these devices. A botnet attack is a type of cyber-attack where a network of compromised devices, known as” bots” or” zombies,” are used to carry out a coordinated attack. These attacks can cause significant damage to both the devices and the network they are connected to. This research explores the implementation of security authentication measures to ensure that IoT devices are who they claim to be before connecting to the network. It also compares the classification accuracy of four different supervised machine learning algorithms namely, Random Forest (RF), Naïve Bayes (NB), DecisionTree (DT), eXtreme Gradient Boosting (XGBoost). It was foundXGBoost was the best performing classifier among the various machine learning algorithms tested, in terms of detecting botnet attacks in IoT networks using the Bot-IoT dataset.
Cyber Security, Authentication, Internet of Things, Supervised Machine Learning, Botnet Attack.
Andrew Ruiming Cao1, Garret Washburn2, 1Shanghai Soong Ching Ling School, 1 Yehui Rd, Qingpu District, Shanghai, China, 201704, 2Computer Science Department, California State Polytechnic University, Pomona, CA 91768/p>
As individuals get older, research demonstrates that forgetfulness increases.[1][2] Additionally, the need to take a varying amount of medication increases with time. As such, it is commonplace for individuals who are considered elderly to consistently forget to take potentially important medication. The solution proposed in this paper to this lasting issue is an android application, titled Pillpedia, that enables all use to keep track of and remind themselves to take their medications. Pillpedia also acts as a source of information, as it stores important medication information from the FDA about each medicine. The key components of our app are the Flutter runtime that serves as a framework for our app, a Firebase database where all user data are stored, and the FDA API in which all medication data is pulled from. Most of the major challenges faced when developing the app pertained to the integration of the Firebase database within the Pillpedia application, which included the display of the user profile, along with the medications that the user saved. These issues were gradually fixed with small changes in method-calling after reviewing the documentation multiple times. To thoroughly test our application, experiments were devised to test the access security of the database as well as the search functionality from the FDA API in our application. Through these experiments, we discovered a few concerns regarding our database and how much storage a single user can take up, but proved that our medication searches were functional. After the process of developing and experimenting on our application, Pillpedia is a sound choice for elderly and non-elderly individuals to aid them in keeping track of and reminding them to take their medications. This is due to the functionalities of our app being operational and reliable, while information regarding the medications are accurate as they come straight from the FDA.
Mobile Application, Reminder, Medicine Information, Elderly Aid.
Mónica Rico Martínez , Juan Carlos Vesga Ferreira , Joel Carroll Vargas, María Consuelo Rodríguez Niño, Andrés Alejandro Diaz Toro and William Alexander Cuevas Carrero, Universidad Nacional Abierta y a Distancia, Bogotá Colombia
The equitable distribution of resources in a network is a complex process, considering that not all nodes have the same requirements, and the In-Band On-Channel (IBOC) hybrid transmission system is no exception. The IBOC system utilizes a hybrid in-band transmission to simultaneously broadcast analog and digital audio over the FM band. This article proposes the use of a Max-Min Fairness (MMF) algorithm, with a strategy to optimize resource allocation for IBOC FM transmission in a multiservice scenario. Additionally, the MMF algorithm offers low computational complexity for implementation in low-cost embedded systems, aiming to achieve fair resource distribution and provide adequate Quality of Service (QoS) levels for each node in the RF network, considering channel conditions and traffic types. The article explores a scenario under saturated traffic conditions to assess the optimization capabilities of the MMF algorithm under well-defined traffic and channel conditions. The evaluation process yielded highly favorable results, indicating that theMMF algorithm can be considered a viable alternative for bandwidth optimization in digital broadcasting over IBOC on FM with 95% confidence, and it holds potential for implementation in other digital broadcasting system.
In-Band On-Channel (IBOC), Max-min Fairness, Optimization, digital radio
Felix Bai1, Jeremy Taraba2, Fangzhou Sun3, 1University Prep, 8000 25th Ave NE, Seattle, WA 98115, 2Computer Science Department, California State Polytechnic University, Pomona, CA 91768, 3Match Group LLC, 8750 N Central Expy, Suite 1400, Dallas, TX
Statistics show that excessive alcohol consumption has been a problem and remains a problem in many countries. This paper proposes an application that encompasses a solution which allows users to log and track their alcohol intake over time. It leverages features such as object recognition for drink identification, a history calendar for reflective analysis, and a real time blood alcohol level indicator for health measurements. During experimentation we found that the accuracy of the AI to be exceptional when used on drinks that it has been trained on. Furthermore, the blood alcohol calculator demonstrated a level of accuracy comparable to, if not surpassing, that of online calculators. This heightened accuracy is attributed to its real-time updating capability, ensuring precision in the calculations throughout the users engagement with the application. The ultimate goal of this initiative is to create a user-friendly, technology-driven solution that empowers individuals to make informed decisions about their alcohol consumption. It promotes responsible drinking behavior and contributes to overall health and well-being.
AI, Flutter, Firebase, Alcohol
Yumeng Zou, Shuyu Wang, NorthwoodHigh School, 4515 Portola Pkwy, Irvine, CA 92620
This paper addresses the critical issue of sustainability within the fast-paced fashion industry, characterized by overconsumption and waste. We propose an innovative solution, the Slow Low Fashion app, which leverages advanced artificial intelligence (AI) technology to analyze users body measurements, providing personalized, gender-inclusive clothing recommendations [4]. This approach aims to minimize overconsumption and reduce the environmental footprint by encouraging more thoughtful purchasing decisions. The core technologies of our program include AI for body ratio analysis, a secure and privacy-compliant data handling framework, and an intuitive user interface designed to enhance user experience. Despite challenges such as ensuring the accuracy of body measurements and maintaining data privacy, we addressed these through rigorous testing and implementing encryption protocols. Experimentation across diverse user scenarios demonstrated the apps effectiveness in reducing unnecessary purchases and promoting sustainability. The significant reduction in clothing waste and increased user satisfaction highlight the potential of Slow Low Fashion as a tool for promoting sustainable fashion consumption. Our project underscores the necessity and feasibility of integrating technology and personalization in addressing the environmental challenges posed by the fashion industry.
Recommendation System, Machine Learning, Artificial Intelligence, Mobile Application
Copyright © SOFTPA 2024