Arman Daliri1, Mahmood Alimoradi2, Mahdieh Zabihimayvan3 and Reza Sadeghi4*, 1Department of Computer Engineering, Karaj Branch, Islamic Azad University, 2Independent Researcher, 3Department of Computer Science, Central Connecticut State University, New Britain, CT,USA and 4*School of Computer Science and Mathematics, Marist College, Poughkeepsie, NY, USA
One of the most important problems in medical science is to make the prediction easier. This research proposes a new framework, Entropy Triangle-based Oversampling, for predicting non-sinus rhythms using a new machine learning method. This framework contains three steps: feature engineering, entropy triangle oversampling, and predicting the disease. The data set used in this research is a 12-lead electrocardiogram (ECG) database of arrhythmia research for 10,646 patients. This data set has 11 different types of heart rhythm: five sinus, and six non-sinus rhythms. In this article, we present two novelties in machine learning and medical science, which result in a prediction of non-sinus rhythms with an accuracy of higher 85%. Our experimental result, among other findings, reports that the most accurate classifier and the most useful oversampling based on Entropy Triangle are supported vector classifier and shark smell oversampling method.
Classification, Prediction, Entropy Triangle, Sinus and Non-sinus Rhythm, ECG.
Leili Nosrati1 and Laleh Nosratri2, 1Department of Computer Engineering, North Tehran Branch, Islamic Azad University, Tehran, Iran and 2Industrial Engineering, Tarbiat Modares University, Tehran, Iran
Online banking authentication has been recognized as a key factor in the security of online banking. nowadays, different methods have been developed for online banking validation which cause problems from hacker attacks and Internet theft. Our research showed that biometrics is appropriate options for dealing with these issues. In this article, different authentication protocols for online banking have been compered.
Face Authentication, Mobile Banking, Artificial Neural Network, Face Detection, Machine Learning.
Jemal Abate1*, Ashenafi Tulu2, Tamrat Delessa2, Matiyos Alemayehu2, College of Computing and Informatics, Haramaya University, Dire Dawa, Ethiopia
The pandemic of the novel coronavirus disease 2019 (COVID-19) is a public health emergency, with epidemiologic models forecasting grave implications, including high death rates, if the virus is allowed to run its course without intervention. Technology-assisted contact tracking is a useful tool for limiting disease spread during an epidemic or pandemic. Because resources for mass testing and significant amounts of vaccines are unlikely to be available for rapid use, contact tracing is considered the first and most effective approach in limiting an outbreak. Even before vaccines are available, effective contact tracking can allow societies to reopen from lockdown. The goal of contact tracing is to reduce the time it takes to contain an outbreak by automating the traditional interview-based contact tracing process. In essence have proposed a framework for contact tracing solutions to identify the contact history of an infected person.
COVID-19, Contact Tracing, Mass Surveillance, Face Recognition, Machine Learning.
Jiheng Yuan1, Victor Phan2, 1Santa Margarita Catholic High School, 22062 Antonio Pkwy, Rancho Santa Margarita, CA 92688, 2Computer Science Department, California State Polytechnic University, Pomona, CA 91768
Obesity and diabetes are prevalent health issues worldwide, especially among young people. To address this, an app was proposed to help users monitor their daily nutrient intake and prevent obesity and diabetes . The app uses AI scanning to analyze the nutrient level of food and suggests a suitable daily nutrient intake for the user based on their age and gender. Data storage allows users to track their meal history and create a personalized diet plan . The app was compared to similar systems, and it was found that live scanning is more intuitive and convenient than photo uploading. Additionally, the proposed app was tested in two experiments and was found to be effective in identifying food items and received generally positive feedback from users, but further improvements are necessary to enhance accuracy and user experience. In the first experiment, the accuracy of the AI model for predicting food items was tested using a combination of existing and customized datasets . A total of 227 food items were tested, including bananas, watermelons, peaches, tomatoes, pineapples, rice, fries, hamburgers, eggs, noodles, and other items. The results showed an overall accuracy rate of 82% for all food items tested, with pineapple having the highest accuracy at 100% and peaches having the lowest accuracy at 60%. In the second experiment, 15 participants tested the applications features and provided feedback through a survey. The results showed that the application was successful in its implementation of features and received generally positive feedback, with an average functionality rating of 8.13 and an average convenience rating of 7.67.
Obesity, Diabetes, Nutrient Intake Monitoring, AI Scanning.
Wang Qian and Hanipah Hussin, Faculty of Education and Liberal Studies, City University Malaysia, 46100 Petaling, Jaya, Selangor, Malaysia
This dissertation explores the application of memetic approach in teaching English writing through the internet plus tools. The study aims to provide an in-depth understanding of the effectiveness of this approach on students writing performance, their attitudes towards writing, and their motivation to learn English. The study is conducted through explanatory research, which combines both qualitative and quantitative research methods. The data is collected through surveys, interviews, and observations of students writing performances before and after the intervention. The results of the study suggest that the use of a memetic approach in English writing teaching with internet plus tools had a positive impact on EFL students writing proficiency. The students reported that the use of internet plus tools made writing more engaging, and the memetic approach helped them understand the cultural and social contexts of writing. The findings also indicate that the students writing skills significantly improved after the intervention. This research provides valuable insights into the use of a memetic approach in teaching English writing and highlights the potential benefits of internet plus tools in enhancing the students learning experiences.
Memetics; English Writing Teaching; College English; Internet Plus Tools; Exploratory Research.
Congyu Zhao1, Suraj Singh2, 1Northwood High School, 4515 Portola Pkwy, Irvine, CA 92620, 2Computer Science Department, California State Polytechnic University, Pomona, CA91768
School accidents have still been a major problem that happens frequently over decades . Safety hazards are alsothe problem that parents and teachers were worried about, especially campus fire . Schools are the main placeswhere we study and live, and are also special places where a large number of minors gather. How to do a goodjobin campus fire safety is not only related to the normal order of education and teaching on campus, but also tothesafety of teachers and students. the vital interests of households and the future of the motherland. Accordingtostatistics, more than 80% of school fires are caused by human factors, and classrooms, student dormitories, restaurants and other living places are more prone to fires. Habitual violations of regulations have become one of the main factors that cause fires . However, base on all those type of question, this paper designs an game forpreventing campus fire and other types of safety hazards might appearances at school. Our design builds upononunity engine and C# script .
Settings, Menu, Opinions, FPS, TPS.
Nathan Lee1, John Morris2, 1Northwood High School, 4515 Portola Pkwy, Irvine, CA 92620, 2Computer Science Department, California State Polytechnic University, Pomona, CA 91768
As a video game developer, the most difficult problem I ran into was creating a map for the game, as it was difficult to create non repetitive and original gameplay . My project proposes a solution to this problem as I use Answer Set Programming to create a program to procedurally generate maps for a video game . In order to test its reliability, I allowed it to generate around 10,000 maps, stored the data of each of the maps, and used the common trends I find in the data to find problems with the program and fix it in the future. In developing a video game, level creation consumes a major portion of the development total time and level procedural generation techniques can potentially mitigate this problem. This research focused on developing a VVVVVV style level generator using Answer set programming for the game Mem.experiment which was developed at the same time. VVVVVV is a 2D puzzle platformer that uses changes in direction of gravity instead of jumping for the player’s vertical movement . During the development of the level generator, 10,000 levels were created. I found out that the average total time it took between generations is 45 seconds, and the average time for ASP to generate a map is 12 seconds . This means that the process of displaying the generation took between 2x - 3x longer than generating the ASP solution.
ASP, Procedural Generation, 2D Game.
Min Yao and XinRan Zhang, College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China
Image reconstruction is an important part of positron emission tomography. Maximum Likelihood-Expectation Maximization (MLEM) is a classic algorithm in medical image reconstruction. The MLEM algorithm is a maximum likelihood algorithm based on the Poisson model. The algorithm performs maximum likelihood estimation on the data of the reconstructed image by solving the maximum expectation, and uses the pixel as the parameter to be sought, and sets the corresponding number of iterations. The likelihood function is approximated to an extreme value to obtain a maximum likelihood estimate. However, the maximum likelihood maximum algorithm has instability. With the increasing iterations, random factors such as noise in the image are amplified in the reconstruction process and the local signal is excessively increased, the noisy influence of reconstruction image increases. To solve this problem, this paper introduces the Thin Plate prior distribution on the basis of MLEM, and combines various filtering to achieve the purpose of suppressing noise and protecting edges.
Positron Emission Tomography, Maximum a Posteriori, Thin Plate Prior, Anisotropic Filtering .
OmotoshoF.S and Gbolagade K. A, Department of Computer Science, Faculty of Information and Communication Technology, Kwara State University, Malete. Nigeria
We integrate biometric technology in our applications to provide a dependable approach to the problem of user authentication.However,study as proven that there are susceptible points in typical biometric systems which are prone to manipulation by hackers. The most concerned is biometric template attacks, reason for various biometric template techniques proposed by researchers in the literature to secure biometric raw template. The main challenge of most biometric template protection techniques is decrease in recognition performance when compare to unprotected system. Also, most of them required Auxiliary Data (AD) for verification.This study will leverage on features ofResidue Number System (RNS) by integratingit withBiometric Template Protection (BTP) Transformation technique. Since, RNS is carry-free arithmetic; BTP technique based on RNS system will achieve high speed of computation because of its parallel computing nature. It will also, eliminate the need to remember auxiliary data during verification.
Biometric, Traits, Template, Transformed, Residue Number System (RNS), Parallel, Authentication, Biometric Template Protection (BTP).
Keren Brown1, David Wei2, 1Woodbridge High School, 2 Meadowbrook, Irvine, CA 92604, 2Computer Science Department, California State Polytechnic University, Pomona, CA91768
Even the best writers in history were not blessed enough to have a constant surge of inspiration, a never-endingflowof ink on paper, or fingers flying across keyboards. These blocks in creativity are commonly known as writer’s block, and many people experience this, since communication is important in every subject. Less commonly knownisdancer’s block, which is when a choreographer experiences a stop in inspiration while choreographing . Theseblocks can continue for days or even weeks, before an idea strikes the dancer, setting back the ef iciency of choreographing. When due dates come into play, such as choreographing for a production, show, or assignment, adancer cannot put forth their best choreography, and will be left feeling unsatisfied with the quality of their work. When a choreographer faces a challenge towards creating original choreography, how can one gain inspirationtoovercome this block ? How can we ensure that the inspiration given is appropriate for the song and style whichthe choreographer is designing the dance to? This paper develops an application to choreograph visuals inacreative manner, while assessing the musicality of the audio in order to reflect the same emotion in the movement. We applied our application to a jazz piece to be performed as part of a local high school dance show and conducteda qualitative evaluation of the approach. The results show that with the software application, dancers will be abletofind inspiration to continue choreographing, pushing them past a barrier of creativity, and allowing themto finishtheir dance with a quality of choreography that they can be proud to present .
Dance, Choreography, Machine Learning, Audio Analysis.
Xiaohan Feng1 and Makoto Murakami 2, 1Graduate School of Information Sciences and Arts, Toyo University, Kawagoe, Saitama, Japan, 2Dept. of Information Sciences and Arts, Toyo University, Kawagoe, Saitama, Japan
Creative writing courses have flourished in recent years. However, the accuracy of the content of some courses has yet to be examined. Character archetypes are an unavoidable topic in most courses requiring character creation. We found that some online creative courses include characters whose character archetypes are debatable. For example, the femme fatale is often considered a character archetype, but some scholars believe it is a stereotype bias. While the use of character archetypes and stereotypes in creative work is a matter of personal freedom, it is inappropriate to educationally disseminate content that is still controversial in the academic community. This study explores the history and reasons for the generalization of femme fatale, the differences between femme fatale and other character archetypes, and derives three reasons why femme fatale is inappropriate as a character archetype in creative work. This study is intended to call attention to the rigor of the content of online creative writing courses.
Online Education, Creative Course, Femme Fatal, Archetype, stereotype.
Soumaya Kaakour, Marketing, Lebanon
The purpose of this paper is to examine the aspects affecting intention to use e-learning by extending the Technology acceptance model (TAM) with the following external variables (computer self-efficacy, perceived enjoyment and personnel innovativeness). The model is applied on a sample of students from Lebaneseprivate universities. Findings indicated that all hypotheses are acceptedexcept the relationship between computer self-efficacy(CSE) and perceived usefulness (PU) and the relationship between perceived enjoyment (PE)and perceived ease of use (PEOU). Thus, this studyrevalidate the TAM theory. Results give opportunities to more investigations determining factors affecting the adoption of e-learning.
Technology acceptance model, computer self-efficacy, perceived enjoyment, personnel innovativeness, perceived usefulness, perceived ease of use, attitude, intention to use e-learning.
Nteboheng Patricia Mefi and Samson Nambei Asoba, Department of Public Management and Administration, Walter Sisulu University
Virtualisation in higher education emerged as a new imperative after the covid-19 pandemic as well as the technological revolution. Technological revolution and virtualisation have, however, put attention once more on socioeconomic inequalities in South Africa. Inequalities in readiness and adoption of digital systems have been observed along geographical as well as socioeconomic dimensions in resulting in a need to inquire on the state of virtualisation in different contexts. The study sought to describe the state of virtualisation at a selected university in the Eastern Cape Province which is considered one of the poorest in South Africa. Specifically, the state of virtualisation was described in terms of three dimensions, namely; (1) perception of academics on virtualisation, (1) attitudes of academics on virtualisation and (2) university initiatives in promoting virtualisation. The study adopted a qualitative design based on interviews with nine (9) academics from a selected university in the Eastern Cape. The perceptions of virtualisation were found to be consistent with those of the literature where virtualisation was considered to imply remote teaching and learning, digitalisation as were as non-physical educational strategies. Virtualisation was found to be associated with both negative and positive attitudes. Positive attitudes were related to views that virtualisation was flexible, associated with learning everyone and increased access to education. Negative attitudes were found to stem from information overload as well as sentiments that virtualisation needed specialised resources and training. It was found that University has done considerably better in training academics as well as in providing them with relevant tools for virtualisation. The study recommends strengthening virtualisation to ensure every academic benefits from using it.
Virtualisation, Higher Education, Remote Learning, University, Technology.
1Nteboheng Patricia Mefi and 2Emmanuel I Edoun, 1Department of Public Management and Administration, Walter Sisulu University, 2Department of Operations Management, University of Johannesburg
With increased virtualization of high education given the Fourth Industrial Revolution (4IR) as well as in response to the Covid-19 pandemic concern has been raised over the implication of this on the job satisfaction of academics. The aim of this study was to determine the effectiveness of the support given to academics in ensuring job satisfaction of the academics working online. A quantitative methodology which was based on the collection of data using a questionnaire given to academics was adopted. The results indicated that sixty percent (60.4%) of the respondents had received some support by university management. Most support for the virtual environment was provided through workshops and training. However, the support given was not consistent with the other finding that eighty six percent (86%) of the academics had indicated that the major factor affecting their job satisfaction was connectivity and lack of cooperation of students (42.6%). It is encouraged that HEIs should strengthen their relationships and cooperation with supportive institutions for virtualisation such as ESKOM as well as the private and public community.
Virtualisation, organisational support, covid-19, technology, innovation.
Birendra Raj Sharma Pokharel, Action on Disability Rights and Development-Nepal
Persons With Disabilities face disadvantage resulting from impairment and disability associated with barriers that limit their participation. ICT particularly offers enormous opportunities to Persons with visual disabilities if this is designed in a way to meet universal design to improve the quality of millions of their life. Lack of accessible ICT creates barriers in education, employment, online services and social participation. There are widespread barriers for promoting accessible ICT in Nepal that is observed in three major components such as accessibility, adoptability and affordability which was examined by the personal experiences of 100 key informants. It found that the ICT should reflect the goal of fostering Education, greater participation and inclusion of Persons with visual disabilities. It is concluded that, Dignity, Efficacy, Non-discrimination, Inclusion, Autonomy and Livelihood are the six indicators of meaningful inclusion, hence, the indicator of digital inclusion is "Accessible ICT mitigating DENIAL of Persons with visual disabilities".
Visual, Disability, Accessibility, Adoptability, Affordability.
Dr. Mohamed Yacine, Action Learning Institute, Algeria
In incubators and pre-incubation in universities, theoretical perspectives, such as social learning theory and action learning theory, are used to evaluate the influence of action learning in the development of entrepreneur’s potential, which aim to launch start-ups in sustainable development; from four factors, naming, (1) self-efficacy; (2) thinking and describing precisely what their MVP will look like; (3) dealing with various challenges; and (4) demonstrating Proof Of Concept. For this purpose, the researcher conducted a research through 2 case studies with 71 incubated entrepreneurs using a research methodology that combined several qualitative techniques. Participatory observation, semi-directive interviews, and analysis of learning deliverables were utilized to examine differences in entrepreneurs’ potential. The study provides evidence that entrepreneurship education based on action learning methods may positively influence the entrepreneurial potential of entrepreneurs.
Action Learning, sustainable development entrepreneurship, incubation, entrepreneurs’ potential.
Hank Cao1, Marisabel Chang2, 1West High School, 20401 Victor St Torrance CA, 90503, 2Computer Science Department, California State Polytechnic University, Pomona, CA 91768
Contemporary high schools have seen a significant rise in student-led clubs, whether they are academic, sports, or special-interest related. In them, students are able to collaborate with other like-minded peers and develop their unique hobbies and interests. However, in many of these high schools and especially those of ours, we have observed a lack of motivation and participation associated with poor club organization and communication. Inspired by existing software utilized by these clubs and building upon their features, we have designed and implemented a user-club system intended to help a myriad of clubs in high schools and colleges to manage their club events and membership . Two experiments were conducted to test the effectiveness of two different applications designed to help high school clubs manage their events and membership. For the first experiment, 10 participants tested a user-club system, and for the second experiment, another 10 participants tested an application. Both experiments showed positive results, with participants providing feedback on the applications functionality and convenience. However, a few participants reported issues, indicating that refinement may be necessary for optimal usability. In the first experiment, most participants reported improvement in their club s participation and member interest, but a few reported little to no improvement, suggesting that the system may not be effective for all types of clubs. Further testing and refinement are necessary for both applications to determine their effectiveness for different types of clubs and user populations.
Mobile Development, Social, School
Billy Hsu1, Marisabel Chan2, 1Crean Lutheran High School, 12500 Sand Canyon Ave. Irvine, CA 92618-110, 2Computer Science Department, California State Polytechnic University, Pomona, CA 91768
When engaging in outdoor activities like walking in a park or having a picnic, it is crucial to keep in mind the potential dangers that may exist in certain areas, such as the presence of thieves or criminals. Recent public shootings underscore the importance of being mindful of one s surroundings and taking necessary precautions to ensure a safe and enjoyable experience. Therefore, it is crucial to educate people on the significance of staying vigilant, particularly in unfamiliar environments. Simple measures like staying in well-lit areas, avoiding isolated places, and being alert to suspicious people can significantly reduce the risk of falling prey to these dangers. By promoting safety measures and increasing awareness, individuals can fully appreciate the natural beauty of their surroundings without compromising their safety. To solve this issue we developed a game involving zombies that spawn in the darkness and chase the player, who can use a map to check for zombies beyond their radius. The goal is to escape in a vehicle or kill all the zombies, but escaping is the better option as it is nearly impossible to beat all the zombies. The game encourages the player to run and pay attention to their surroundings to avoid getting attacked by zombies. It also emphasizes the importance of cooperation and teamwork, as being a lone wolf is not a viable option in real life situations . The objective of the game is survival, not victory. Understanding player preferences is essential to creating an enjoyable gaming experience. Two experiments demonstrate the importance of collaboration and communication in gaming. The first study found that survival and health-related features were rated higher than action-packed features, suggesting that players value these aspects more . The second study found that incorporating voice communication in cooperative games can enhance teamwork and improve overall performance. Trust, shared goals, support, and communication were crucial to teamwork, and players provided positive feedback on their experience. Further research with larger samples is necessary to confirm the findings.
Public safety awareness, Outdoor safety, 2D top-down game.
Azam Rabiee, Alok Goel, Johnson D’Souza, Saurabh Khanwalkar, Course Hero, Inc.
Online learning platforms provide learning materials and answers to students’ academic questions by experts, peers, or systems. This paper explores question-type identification as a step in content understanding for an online learning platform. The aim of the question-type identifier is to categorize question types based on their structure and complexity, using the question text, subject, and structural features. We have defined twelve question-type classes, including Multiple-Choice Question (MCQ), essay, and others. We have compiled an internal dataset of students’ questions and used a combination of weak-supervision techniques and manual annotation. We then trained a BERT-based ensemble model on this dataset and evaluated this model on a separate human-labeled test set. Our experiments yielded an F1-score of 0.94 for MCQ binary classification and promising results for 12-class multilabel classification. We deployed the model in our online learning platform as a crucial enabler for content understanding to enhance the student learning experience.
Question-Type Identification, Content Understanding, Learning Platform, BERT, Education.
Pallavi Sharma and Min Chen, Computing and Software Systems, University of Washington Bothell, Bothell, USA
With the explosion of data in the digital age, it is an important yet challenging task to extract meaningful information from long texts. In this paper, a novel framework is presented to facilitate users in extracting summaries and keywords from long texts at real-time. It uses a hybrid approach based on feature extraction and unsupervised learning to generate quality summaries. In addition, it integrates machine learning with semantic methods to extract keywords and phrases from the source text. The framework is deployed as a mobile app that allows users to manage, share and listen to the extracted information to improve user experience. To test the effectiveness of the work, experimental and research evaluations are carried out on DUC 2002 dataset using ROGUE parameters. Results demonstrate a higher F1-score than the state-of-theart methods used for extractive summarization on the same dataset. Experiment also shows an accuracy of 70% for the keyword extraction method, which is in par with other work in the field.
Keyword Extraction, Summarization, Text Synthesis, Unsupervised Learning.
Amelia Kahn, Department of Philosophy, University at Buffalo
Words like “likely”, “highly probable”, and “high confidences”, or terms of estimative probability, are widely used in intelligence, medicine, scientific research, and many other fields. These natural language terms are indispensable, but they can pose problems when used in data-tagging and semantic web applications, because their meaning can vary from community to community, and even between contexts within the same community. I use the use of terms of estimative probability within the intelligence community as a case study to examine what issues arise when trying to manage data with these terms. I then propose a system for modelling TEPs using OWL ontologies in a way that minimizes ambiguity and conforms with the ISO standard top-level ontology, Basic Formal Ontology (BFO), along with several mid-level ontologies in the field.
Ontology, Estimative Probability, Confidence, Risk, Subjective Credence, Semantic Web
Casson Qin1, Jack Wagner2, 1Diamond Bar High School, 21400 Pathfinder Rd, Diamond Bar, CA 91765, 2Computer Science Department, California State Polytechnic University, Pomona, CA 91768
This study evaluated the accuracy and reliability of Voice Note Taking, a technology designed to transcribe spoken language and support note-taking. The experiment analyzed the transcription accuracy and word definition selection feature of Voice Note Taking using a series of audio files featuring individuals speaking in English in different settings. The results showed that Voice Note Taking is reliable and accurate, with an overall transcription accuracy rate of 87.81%. However, the study identified room for improvement, particularly in improving accuracy in noisy environments and developing more sophisticated algorithms for word definition selection. Future research could explore the integration of advanced natural language processing techniques to improve the accuracy of word definition selection, including leveraging machine learning algorithms to recognize the specific context and meaning of words. Several previous studies have shown the potential of mobile note-taking apps to enhance student achievement, satisfaction, and accessibility, suggesting further research in this area. Overall, this study highlights the strengths and limitations of Voice Note Taking and provides insight into potential areas for future development.
Natural Language Processing , Speech Recognition, Note Taking, Mathematics.
Sarah Vuningoma1 Maria Rosa Lorini2 and Wallace Chigona3, 1Department of Information Systems, University of Cape Town, Cape Town, South Africa, 2School of Management, University of London, London, UK, 3Department of Information Systems, University of Cape Town, Cape Town, South Africa
Mobile phones have the potential to contribute towards reducing isolation and loneliness, and to assist in improving interpersonal relations and fostering assimilation processes. Mobile phones may facilitate the incorporation of refugees into a new place. The purpose of this study is to assess how the use of mobile phones helps refugees to mitigate the effects of culture in the host country. Data for the study were collected using semi-structured interviews. The sample consisted of 27 participants. The participants were refugees living in South Africa. Data were analysed using thematic analysis. The study demonstrate that the refuges face a myriad challenges in their host country, including lack of local culture skills, separation of family and friends from their home countries, obstacle in obtaining the legal documents, and the difficulties of becoming integrated into the new environment. The use of mobile phones offers refugees several benefits, such as developing language and culture knowledge, integrated in the host country, facilitating communication, and finding many opportunities. At the same time, mobile phones enable refugees in South Africa to navigate culture shock.
Mobile phones, culture shock, refugees, South Africa.
Dr Parkavi K, Ratnesh Kumar Maurya, School of Computing Science and Engineering, VIT University, Chennai, India
Abstractive text generation is the task of creating a summary or paraphrase of a given text document or piece of text. It is a challenging task as it requires the model to understand and accurately represent the original text or any document, as well as to generate new text that is coherent and grammatically correct. In this report, we explore the use of longshort-term memory (LSTM) and neural networks for abstractive text generation. LSTM are a kind of recurrent neural network (RNN) that are effective in learning enduring dependencies in data and have been successful in a variety of NLP tasks. We describe the steps involved in training an LSTM model for abstractive text generation, including datapreprocessing, model design, and optimization. We also discuss the challenges and limitations of using LSTM models for this task, and suggest areas for future research.
LSTM, Abstractive text summarization, RNN, NLP
Chia Sheng Shih1, Jonathan Sahagun2, 1Pacific Academy Irvine, 4947 Alton Parkway, Irvine, CA 92604, 2Computer Science Department, California State Polytechnic University, Pomona, CA91768
According to the CDC, 13.7% of adults in the United States have mobility issues, which is about 42 million peoplewho have that issue. The purpose of this paper is to utilize artificial intelligence and robotics packaged in a3Dprinted Circle of Command to help make the lives of those 42 million people easier . A raspberry pi is usedtopower and process the voice control commands and turn the voice commands into actions that respond tothecommands . The voice control is achieved through three microphones that are embedded from the inside of theCircle of Command using holes to listen to any potential voice commands, and as the raspberry pi can’t input analog output which is outputted from the microphones, the microphones and the raspberry pi are connected toananalog to digital converter that allows the raspberry pi and the microphones to exchange information smoothlyRobotics is used in the stepper motor and the gear that is used to turn the top of the lazy susan, which is 3Dprintedso that there are gears on the inside of the top. There is also a home switch that will home the lazy susan. Thereisno practical application of this AI Robotic Circle of Command as it is just a prototype, and so there are no results, but it is hoped that it will be able to change some of the 42 million lives once the production of the production model begins, the production model will be larger than the prototype as the prototype serves as only a proof of concept andshows that this idea is actually doable .
Artificial Intelligance, Circle of Command, Mobility Issues, Voice Control/Command
Copyright © SNLP 2023