Journal of Artificial Intelligence and Technology最新文献

{"title":"Automatic Code Generation for Android Applications Based on Improved Pix2code","authors":"Donglan Zou, Guangsheng Wu","doi":"10.37965/jait.2024.0515","DOIUrl":"https://doi.org/10.37965/jait.2024.0515","url":null,"abstract":"With the expansion of the Internet market, the traditional software development method has been difficult to meet the market demand due to the problems of long development cycle, tedious work and difficult system maintenance. Therefore, to improve software development efficiency, this study uses residual networks and bidirectional long short-term memory networks to improve the Pix2code model. The experiment results show that after improving the visual module of the Pix2code model using residual networks, the accuracy of the training set improves from 0.92 to 0.96, and the convergence time is shortened from 3 hours to 2 hours. After using a bidirectional long short-term memory network to improve the language module and decoding layer, the accuracy and convergence speed of the model have also been improved. The accuracy of the training set grew from 0.88 to 0.92, and the convergence time was shortened by 0.5 hours. However, models improved by bidirectional long short-term memory networks might exhibit over-fitting, and thus this study uses Dropout and Xavier normal distribution to improve the memory network. The results validate that the training set accuracy of the optimized bidirectional long short-term memory network remains around 0.92, but the accuracy of the test set has improved to a maximum of 85%. Dropout and Xavier normal distributions can effectively improve the over-fitting problem of bidirectional long short-term memory networks. Although they can also decrease the model’s stability, their gain is higher. The training and testing accuracy of the Pix2code improved by residual network and bidirectional long short-term memory network are 0.95 and 0.82, respectively, while the code generation accuracy of the original Pix2code is only 0.77. The above data indicates that the improved Pix2code model has improved the accuracy and stability of code automatic generation.","PeriodicalId":135863,"journal":{"name":"Journal of Artificial Intelligence and Technology","volume":"19 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141648562","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Vision-based Human Activity Recognition Using Local Phase Quantization","authors":"Madhuri Pandey, Richa Mishra, Ashish Khare","doi":"10.37965/jait.2024.0351","DOIUrl":"https://doi.org/10.37965/jait.2024.0351","url":null,"abstract":"Human activity recognition (HAR) has been the most active and interesting area of research in recent years due to its wide range of applications in the field, such as healthcare, security and surveillance, robotics, gaming, entertainment, etc. However, recognizing vision-based human activity is still a challenging as input sequences may have cluttered background, illumination conditions, occlusions, degradation of video quality, blurring, etc. In the literature, several state-of-the-art methods have been trained and tested on different datasets but have yet to perform adequately to a certain extent. Moreover, extracting potential features and combining appropriate methods is one of the most challenging tasks in realistic video. This paper proposes an efficient frequency-based blur-invariance local phase quantization feature extractor and multiclass SVM classifier that overcomes these challenges. The feature is invariant towards camera motion, misfocused optics, movements in the scene, and environmental conditions. The proposed feature vector is then fed to the classifier to recognize human activities. The experiment has conducted on two publicly available datasets, UCF101 and HMDB51, and has achieved 99.79% and 98.67% accuracies, respectively. The approach has also outperformed the existing state-of-the-art approaches in terms of computational cost without compromising the accuracy of HAR.","PeriodicalId":135863,"journal":{"name":"Journal of Artificial Intelligence and Technology","volume":" 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141367767","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"LRe Trans Model of Interface Visual Interaction Suitable for Preschooler Robots","authors":"Xiaoqing Yang, Jonathan Chung Ee Yong, Bo Li","doi":"10.37965/jait.2024.0488","DOIUrl":"https://doi.org/10.37965/jait.2024.0488","url":null,"abstract":"Traditional contact and non-contact methods for estimating visual interaction forces and recognizing behavior have significant drawbacks with regards to biocompatibility, sensor size, the fragility of materials, and balancing algorithm accuracy and speed. To address these limitations, the study suggests a lightweight, regularized transformer-based visual interaction behavior recognition method. The method contains three important parts: image input and slice preprocessing, global semantic representation based on deep lightweight vision Transformer, and regularized interaction behavior recognition. At the same time, the new model is able to collect and analyze preschool children's image data through a dynamic window, and then realize the visual interaction process for preschool children through machine interaction. Experiments shows that the new method achieves 97.6% accuracy and 97.5% F1 score for interaction behavior recognition on a large-scale robot interaction dataset, with a single average inference time of only 0.18 seconds. The experiment yields significant results indicating that the LRe Trans-based method for recognizing visual interaction behavior holds advantages for the specific problem of robots interacting with preschoolers. The method not only provides valuable insights into the theoretical basis of this field but also offers potential applications for future research.","PeriodicalId":135863,"journal":{"name":"Journal of Artificial Intelligence and Technology","volume":"67 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141011630","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Revolutionizing eLearning Assessments: The Role of GPT in Crafting Dynamic Content and Feedback","authors":"Michael E. Bernal","doi":"10.37965/jait.2024.0513","DOIUrl":"https://doi.org/10.37965/jait.2024.0513","url":null,"abstract":"This study presents the Learnix project that utilizes the GPT-4 large language model (LLM) to enhance interactive learning in eLearning platforms, with a specific focus on generating dynamic multiple-choice questions (MCQs) and providing tailored feedback for Python coding problems and short-answer questions. The aim was to explore how language models can be integrated into eLearning environments to create more adaptive and engaging educational experiences. Leveraging GPT-4’s advanced natural language processing capabilities, the developed platform can generate a diverse range of MCQs and offer unique feedback, significantly improving upon traditional static learning content. This approach enhances the learner’s journey, offering a more engaging and individualized educational experience. The methodology involved the integration of GPT-4 into an eLearning platform, emphasizing user interaction and content relevance. The Learnix platform was designed to handle a variety of coding problems, with the LLM generating corresponding MCQs and feedback. This method’s effectiveness was evaluated based on content quality and relevance. Results demonstrated that GPT-4’s inclusion markedly enhanced the eLearning experience by providing diverse and up-to-date content. Customized feedback is particularly effective in reinforcing learning concepts and addressing individual learning needs. Moreover, the platform showed versatility in scaling and adapting to different educational contexts, making it a valuable tool for various learning requirements. The findings of this project emphasize the transformative potential of language models and Generative AI in redefining online education, leaning towards more adaptive and engaging learning experiences. Additionally, the Learnix project underscores the importance of continual innovation in educational technology, suggesting a new paradigm where AI becomes an integral part of the teaching and learning process. The integration of GPT-4 not only enriches the learning material but also enhances the overall effectiveness of the educational process, paving the way for future advancements in AI-driven eLearning solutions.","PeriodicalId":135863,"journal":{"name":"Journal of Artificial Intelligence and Technology","volume":"57 7","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141008877","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cognitive-Inspired Computational Computing for Intelligent Health Informatics","authors":"Chinmay Chakraborty, Gabriella Casalino, Guangjie Han","doi":"10.37965/jait.2024.0543","DOIUrl":"https://doi.org/10.37965/jait.2024.0543","url":null,"abstract":"","PeriodicalId":135863,"journal":{"name":"Journal of Artificial Intelligence and Technology","volume":"91 25","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140677141","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Charging Pile Fault Prediction Model Based on GRU Network and WOA","authors":"Aihua Yang, Tianke Fang, Elcid A. Serrano, Bin Liu, Fucai Liu, Zhenxiang Chen","doi":"10.37965/jait.2024.0507","DOIUrl":"https://doi.org/10.37965/jait.2024.0507","url":null,"abstract":"The global energy structure is transforming, and new energy vehicles are becoming the future of the automobile industry. However, the development of charging piles and related facilities has not kept pace with the growth of new energy vehicles. This study uses the gated recurrent unit network and the whale algorithm to construct a high-performance charging pile fault prediction model. The proposed model, which utilizes the whale algorithm to prevent the gated recurrent unit network from falling into local optima, demonstrates improved predictive information extraction and prediction ability. The experimentally verified results indicate that the proposed model achieved 92.02% prediction accuracy, 85.66% recall, and 93.87% F1 value. Additionally, the proposed model demonstrates excellent computational ability with an average running time of under 5 minutes on both datasets. This result is a substantial reduction from the control model's running time. The experimental findings show that the study's suggested model has a good ability to anticipate fault data. Its sophistication is verified by comparative tests, which can provide a reference for subsequent research.","PeriodicalId":135863,"journal":{"name":"Journal of Artificial Intelligence and Technology","volume":" 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140691613","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Developing Soft Skills in the Artificial Intelligence Era: Communication, Business Writing, and Composition Skills","authors":"M. AlAfnan, Samira Dishari, Siti Fatimah MohdZuki","doi":"10.37965/jait.2024.0496","DOIUrl":"https://doi.org/10.37965/jait.2024.0496","url":null,"abstract":"This study explores the development of soft skills in the Artificial Intelligence era. Initially, the study, through an anonymous online survey, explored why students use AI and Large Language Models (LLMs). It was found that students use AI for general and academic purposes. From a general perspective, students use AI and LLMs for (1) convenience, (2) lack of time, and (3) lack of curiosity/interest. From an academic perspective, students use AI and LLM platforms as they (1) lack familiarity/knowledge, (2) lack basic skills, (3) lack confidence, (4) have an eagerness to score high grades, and (5) wish to provide different perspectives. To assist in developing students’ soft skills and discourage possible destructive outcomes in the AI era, the study suggests integrating AI platforms as part of teaching. This integration can be carried out by (1) introducing AI tools to students in a productive manner, (2) aligning the use of AI tools with the curriculum and teaching styles, (3) planning lessons and interactive activities using AI platforms, and (4) using AI tools to provide feedback and vice versa. In communication courses, instructors shall (1) create a supportive environment, (2) organize classroom discussions and debates, (3) create public speaking opportunities, (4) provide room for oral communication practices, (5) integrate the use of technology and multimedia, and (6) provide feedback and reflection. In business writing courses, instructors shall (1) encourage effective communication in classrooms, (2) facilitate collaboration and teamwork, (3) use role-play scenarios, (4) introduce project management tools, (5) teach professional etiquette, and (6) organize networking events. In composition courses, instructors shall (1) embrace technology, (2) teach students to critically evaluate online sources, (3) design assignments that require critical analysis, (4) encourage creative writing assignments, (5) promote imagination and originality, and (6) conduct workshops. These practices, which are provided in line with AlAfnan’s taxonomy of educational objectives, shall assist students in developing their soft skills in a way that maintains the relevance of classroom teaching in the AI era.","PeriodicalId":135863,"journal":{"name":"Journal of Artificial Intelligence and Technology","volume":"355 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140698167","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Constructive Use of ChatGPT in the Classroom: An Empirical Study","authors":"Ram Misra, Yang Li","doi":"10.37965/jait.2024.0485","DOIUrl":"https://doi.org/10.37965/jait.2024.0485","url":null,"abstract":"ChatGPT, launched on November 30, 2022, has been adopted by the industries and academia alike. Students have started using ChatGPT for classroom assignments. In the search for the use of this tool for constructive purposes, the professor of a graduate class (MBA) on supply chain and operations management decided to require students to use ChatGPT to first generate some material for their term papers. Typically, ChatGPT generates one to two pages of original material for the student who is not well-trained in using it, which was the case for the students in this class. Then, the students were asked to use the ChatGPT-generated material as a guide to writing a 10-page long paper with new references and citations added. A comparative study is conducted to determine the usefulness of ChatGPT on this project. The preliminary results indicate that students found ChatGPT useful in generating their own papers. Meanwhile, our analysis shows beginners of ChatGPT have limited capacity to generate high-quality content based on ChatGPT. Also, text mining is  conducted to compare the readability and information density of ChatGPT-generated content and students-generated content.","PeriodicalId":135863,"journal":{"name":"Journal of Artificial Intelligence and Technology","volume":"15 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140720871","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Determinants Influencing Consumers’ Intentions to Purchase Green Products: Empirical Insights from Malaysian Consumers","authors":"Z. Rehman, Noor Aslinda Abu Seman, Amran Harun","doi":"10.37965/jait.2024.0323","DOIUrl":"https://doi.org/10.37965/jait.2024.0323","url":null,"abstract":"Consumers around the world have shifted from conventional to green products, and their green consumption is increasing. Growing demand for sustainability and environmental protection drives this shift. Consumers have become more aware of the need to reduce their carbon footprint and make more sustainable choices. Similar is the case in Malaysia as green products are available in open markets, but a low level of intention toward purchasing them still exists. With a specific focus on the Malaysian context, this study is aimed at identifying the factors that contribute to consumers' low intentions for purchasing green products. The Theory of Planned Behavior is extended with perceived environmental concern (PEC) and environmental knowledge (PEK). A survey questionnaire with a non-probability sampling technique was used, and 155 survey responses were collected from respondents in Malaysia. Using structural equation modelling (PLS-SEM), the collected data was analyzed, and the results revealed that perceived environmental concern, perceived environmental knowledge, and subjective are the strongest predictors of consumers’ intention as these factors significantly influence intention to purchase green products. Interestingly the study revealed that attitude toward green products failed to have a significant relationship with the intention to purchase green products. In green marketing contexts, our study results demonstrate that extended TPB has higher predictability than the TPB variables. The model's additional constructions (PEK and PEC) significantly contribute to a better understanding of green product purchase intention development and potentially become long-term main-stream variables.","PeriodicalId":135863,"journal":{"name":"Journal of Artificial Intelligence and Technology","volume":"60 10","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140739408","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Privacy Protection Based on Federated Learning","authors":"Bin Liu, Eric B. Blancaflor, Tianke Fang, Limin Cao","doi":"10.37965/jait.2024.0503","DOIUrl":"https://doi.org/10.37965/jait.2024.0503","url":null,"abstract":"With the development of artificial intelligence technology, more and more fields will collect relevant user data, and provide users with a better experience through data analysis. But there are also risks involved in the process of data collection, namely how to protect personal privacy data. To address this issue, this study combined differential privacy, convolutional neural networks, and federated averaging algorithms to construct a privacy protection model. The study first utilized the federated average algorithm to handle data imbalance, ensuring that each analyzed data is in a balanced state. Then, based on of data balancing, a new algorithm model was constructed using differential privacy and convolutional neural networks. Finally, it utilized a number of public datasets to verify the role of the model in privacy protection. The results showed that the model can achieve recognition accuracy of 97.27% and 93.15%, respectively , for data under the influence of privacy budget and relaxation factor. Meanwhile, the classification accuracy of the model for data can reached 95.31%, with a regression error of 9.03%. When the local iteration number of the device was 30, the testing accuracy can reached 95.28%. This indicates that methods on the grounds of federated averaging algorithm and differential privacy can maintain the accuracy of the model while protecting user privacy. The application research of models has strong practical significance.","PeriodicalId":135863,"journal":{"name":"Journal of Artificial Intelligence and Technology","volume":"31 8","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140372682","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}