Accurately forecasting stock fluctuations can yield high investment returns while minimizing risk. However, market volatility makes these projections unlikely. As a result, stock market data analysis is significant for research. Analysts and researchers have developed various stock price prediction systems to help investors make informed judgments. Extensive studies show that machine learning can anticipate markets by examining stock data. This article proposed and evaluated different ensemble learning techniques such as max voting, bagging, boosting, and stacking to forecast the Nifty50 index efficiently. In addition, an embedded feature selection is performed to choose an optimal set of fundamental indicators as input to the model, and extensive hyperparameter tuning is applied using grid search to each base regressor to enhance performance. Our findings suggest the bagging and stacking ensemble models with random forest (RF) feature selection offer lower error rates. The bagging and stacking regressor model 2 outperformed all other models with the lowest root mean square error (RMSE) of 0.0084 and 0.0085, respectively, showing a better fit of ensemble regressors. Finally, the findings show that machine learning algorithms can help fundamental analyses make stock investment decisions.
{"title":"Stock market prediction employing ensemble methods: the Nifty50 index","authors":"Chinthakunta Manjunath, Balamurugan Marimuthu, Bikramaditya Ghosh","doi":"10.11591/ijai.v13.i2.pp2049-2059","DOIUrl":"https://doi.org/10.11591/ijai.v13.i2.pp2049-2059","url":null,"abstract":"Accurately forecasting stock fluctuations can yield high investment returns while minimizing risk. However, market volatility makes these projections unlikely. As a result, stock market data analysis is significant for research. Analysts and researchers have developed various stock price prediction systems to help investors make informed judgments. Extensive studies show that machine learning can anticipate markets by examining stock data. This article proposed and evaluated different ensemble learning techniques such as max voting, bagging, boosting, and stacking to forecast the Nifty50 index efficiently. In addition, an embedded feature selection is performed to choose an optimal set of fundamental indicators as input to the model, and extensive hyperparameter tuning is applied using grid search to each base regressor to enhance performance. Our findings suggest the bagging and stacking ensemble models with random forest (RF) feature selection offer lower error rates. The bagging and stacking regressor model 2 outperformed all other models with the lowest root mean square error (RMSE) of 0.0084 and 0.0085, respectively, showing a better fit of ensemble regressors. Finally, the findings show that machine learning algorithms can help fundamental analyses make stock investment decisions.","PeriodicalId":507934,"journal":{"name":"IAES International Journal of Artificial Intelligence (IJ-AI)","volume":"21 8","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141233969","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}
Pub Date : 2024-06-01DOI: 10.11591/ijai.v13.i2.pp2201-2211
M. D. Putro, Jane Litouw, V. Poekoel
The low-resolution input image is a crucial challenge for applying facial emotion recognition in real-world scenarios. The critical problem is that valuable object features are relatively lost in the extraction process due to their small size. On the other hand, this vision system is required by a machine to run smoothly on low-cost devices. Facial emotion recognition using a lightweight feature extractor is proposed in this study to effectively capture crucial facial components in a low-resolution image. To compromise the running speed, this work offers an efficient feature convolution to discriminate specific facial features. In addition, the system is embedded with an attentive module to capture important features and correlate them. Our model performance is evaluated on low-resolution public datasets achieving the accuracy of 97.34%, 81.10%, and 80.12% on KDEF, RFDB, and FER-plus, respectively. The practical application demands that the deep learning model can operate fast on inexpensive devices. Consequently, the model achieved a speed of 290 FPS on a CPU device.
低分辨率输入图像是在现实世界场景中应用面部情绪识别的关键挑战。问题的关键在于，由于图像尺寸较小，有价值的对象特征在提取过程中会相对丢失。另一方面，机器要求这种视觉系统能在低成本设备上流畅运行。本研究提出使用轻量级特征提取器进行面部情绪识别，以有效捕捉低分辨率图像中的关键面部组件。为了降低运行速度，本研究提供了一种高效的特征卷积方法来识别特定的面部特征。此外，该系统还嵌入了一个细心模块，以捕捉重要特征并将其关联起来。我们在低分辨率公共数据集上对模型性能进行了评估，在KDEF、RFDB和FER-plus上的准确率分别达到97.34%、81.10%和80.12%。实际应用要求深度学习模型能够在廉价设备上快速运行。因此，该模型在 CPU 设备上的运行速度达到了 290 FPS。
{"title":"Low-resolution facial emotion recognition on low-cost devices","authors":"M. D. Putro, Jane Litouw, V. Poekoel","doi":"10.11591/ijai.v13.i2.pp2201-2211","DOIUrl":"https://doi.org/10.11591/ijai.v13.i2.pp2201-2211","url":null,"abstract":"The low-resolution input image is a crucial challenge for applying facial emotion recognition in real-world scenarios. The critical problem is that valuable object features are relatively lost in the extraction process due to their small size. On the other hand, this vision system is required by a machine to run smoothly on low-cost devices. Facial emotion recognition using a lightweight feature extractor is proposed in this study to effectively capture crucial facial components in a low-resolution image. To compromise the running speed, this work offers an efficient feature convolution to discriminate specific facial features. In addition, the system is embedded with an attentive module to capture important features and correlate them. Our model performance is evaluated on low-resolution public datasets achieving the accuracy of 97.34%, 81.10%, and 80.12% on KDEF, RFDB, and FER-plus, respectively. The practical application demands that the deep learning model can operate fast on inexpensive devices. Consequently, the model achieved a speed of 290 FPS on a CPU device.","PeriodicalId":507934,"journal":{"name":"IAES International Journal of Artificial Intelligence (IJ-AI)","volume":"25 19","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141234924","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}
Pub Date : 2024-06-01DOI: 10.11591/ijai.v13.i2.pp1782-1793
Muhammad Yazid Al Qahar, Y. Ruldeviyani, Ulfah Nur Mukharomah, Miftahul Agtamas Fidyawan, Ramadhoni Putra
Social security administration for health or Badan Penyelenggara Jaminan Sosial Kesehatan (BPJS Kesehatan), as a public legal entity, has a critical role in the health of the Indonesian population. BPJS Kesehatan introduced the Mobile national health insurance or jaminan kesehatan nasional (JKN) application to enhance its services, enabling Indonesians to access it directly. Nevertheless, the rating of the Mobile JKN application on the Google Play Store has shown a gradual decline over time. Therefore, this study was conducted to analyze the factors influencing the user experience of the Mobile JKN application, utilizing the review data obtained from the Google Play Store. Sentiment analysis using the Naïve Bayes (NB) classification model and support vector machine (SVM) combined with synthetic minority oversampling technique (SMOTE) and slang word replacement. The results obtained an accuracy value of 93.33%, precision of 93.76%, recall of 93.33%, and F1-score of 93.43%. A further analysis was conducted using online service quality factors to obtain the main factors influencing the experience of Mobile JKN application users. The evaluation findings revealed that factors of security, ease of use, and timeliness are three fundamental aspects that should be given immediate attention by BPJS Kesehatan while improving the Mobile JKN application in the future.
卫生社会保障管理机构（Badan Penyelenggara Jaminan Sosial Kesehatan，BPJS Kesehatan）作为一个公共法律实体，在印度尼西亚人口的健康方面发挥着至关重要的作用。BPJS Kesehatan 推出了移动国民健康保险（Jaminan Kesehatan nasional (JKN)）应用程序，以加强其服务，使印尼人能够直接获得服务。然而，随着时间的推移，移动 JKN 应用程序在 Google Play 商店的评分逐渐下降。因此，本研究利用从 Google Play 商店获得的评论数据，分析影响移动 JKN 应用程序用户体验的因素。情感分析采用奈伊夫贝叶斯（NB）分类模型和支持向量机（SVM），并结合合成少数超采样技术（SMOTE）和俚语替换。结果显示，准确率为 93.33%，精确率为 93.76%，召回率为 93.33%，F1 分数为 93.43%。利用在线服务质量因素进行了进一步分析，以获得影响移动 JKN 应用程序用户体验的主要因素。评估结果表明，安全性、易用性和及时性是 BPJS Kesehatan 在未来改进移动 JKN 应用程序时应该立即关注的三个基本方面。
{"title":"Factor analysis influencing Mobile JKN user experience using sentiment analysis","authors":"Muhammad Yazid Al Qahar, Y. Ruldeviyani, Ulfah Nur Mukharomah, Miftahul Agtamas Fidyawan, Ramadhoni Putra","doi":"10.11591/ijai.v13.i2.pp1782-1793","DOIUrl":"https://doi.org/10.11591/ijai.v13.i2.pp1782-1793","url":null,"abstract":"Social security administration for health or Badan Penyelenggara Jaminan Sosial Kesehatan (BPJS Kesehatan), as a public legal entity, has a critical role in the health of the Indonesian population. BPJS Kesehatan introduced the Mobile national health insurance or jaminan kesehatan nasional (JKN) application to enhance its services, enabling Indonesians to access it directly. Nevertheless, the rating of the Mobile JKN application on the Google Play Store has shown a gradual decline over time. Therefore, this study was conducted to analyze the factors influencing the user experience of the Mobile JKN application, utilizing the review data obtained from the Google Play Store. Sentiment analysis using the Naïve Bayes (NB) classification model and support vector machine (SVM) combined with synthetic minority oversampling technique (SMOTE) and slang word replacement. The results obtained an accuracy value of 93.33%, precision of 93.76%, recall of 93.33%, and F1-score of 93.43%. A further analysis was conducted using online service quality factors to obtain the main factors influencing the experience of Mobile JKN application users. The evaluation findings revealed that factors of security, ease of use, and timeliness are three fundamental aspects that should be given immediate attention by BPJS Kesehatan while improving the Mobile JKN application in the future.","PeriodicalId":507934,"journal":{"name":"IAES International Journal of Artificial Intelligence (IJ-AI)","volume":"75 13","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141231144","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}
Pub Date : 2024-06-01DOI: 10.11591/ijai.v13.i2.pp2333-2341
Vinay R, Thejas B U, H. A. V. Sharma, Shobha G, Poonam Ghuli
Chatbots are conversational agents which interact with users and simulate a human interaction. Companies use chatbots on their customer-facing sites to enhance user experience by answering questions about their products and directing users to relevant pages on the site. Existing Chatbots which are used for this purpose give responses based on pre-defined FAQs only. In this paper, we propose a framework for a chatbot which combines two approaches - retrieval from a knowledge base consisting of question answer pairs, combined with a natural language search mechanism which can scan through the paragraphs of text information. A feedback-based knowledge base update is implemented which provides continuous improvement in user experience. The framework achieves a result of 81.73 percent answer matching on SQuAD 1.1 and 69.21 percent answer matching on SQuAD 2.0. The framework also performs well on languages such as Spanish (67.32 percent answer match), Russian (61.43 percent answer match), Arabic (51.63 percent answer match) etc. by means of zero shot learning.
{"title":"A multilingual semantic search chatbot framework","authors":"Vinay R, Thejas B U, H. A. V. Sharma, Shobha G, Poonam Ghuli","doi":"10.11591/ijai.v13.i2.pp2333-2341","DOIUrl":"https://doi.org/10.11591/ijai.v13.i2.pp2333-2341","url":null,"abstract":"Chatbots are conversational agents which interact with users and simulate a human interaction. Companies use chatbots on their customer-facing sites to enhance user experience by answering questions about their products and directing users to relevant pages on the site. Existing Chatbots which are used for this purpose give responses based on pre-defined FAQs only. In this paper, we propose a framework for a chatbot which combines two approaches - retrieval from a knowledge base consisting of question answer pairs, combined with a natural language search mechanism which can scan through the paragraphs of text information. A feedback-based knowledge base update is implemented which provides continuous improvement in user experience. The framework achieves a result of 81.73 percent answer matching on SQuAD 1.1 and 69.21 percent answer matching on SQuAD 2.0. The framework also performs well on languages such as Spanish (67.32 percent answer match), Russian (61.43 percent answer match), Arabic (51.63 percent answer match) etc. by means of zero shot learning.","PeriodicalId":507934,"journal":{"name":"IAES International Journal of Artificial Intelligence (IJ-AI)","volume":"53 47","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141232308","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}
Pub Date : 2024-06-01DOI: 10.11591/ijai.v13.i2.pp1312-1325
Usha Muniraju, Thangamuthu Senthil Kumaran
The transmission of biomedical signals in real-time is extremely difficult and necessitates the use of cloud and internet of things (IoT) infrastructure. Security is also an important consideration, however, to achieve this, a reconstruction method is developed where the entire signal is fed as an input, just the primary portion, the entire signal is taken then encoded, and then deliver to the destination. It is unlocked using a reconstruction technique without any signal attenuation. The key difficulty is how to manage the sensor network once the input is prepared for transmission. This has problems with extremely high network energy consumption and accurate data collection. The accuracy of data reconstruction through is improved by compressive sensing. The lifespan of the network as a whole could be extended, in this study; the proposed proposed system convolutional neural network (PS-CNN) is an integrated model that combines feature selection and auto-encoder. In order to produce the most useful features for particular tasks, our algorithm can eventually separate the appropriate task units from the irrelevant tasks.
{"title":"An auto-encoder bio medical signal transmission through custom convolutional neural network","authors":"Usha Muniraju, Thangamuthu Senthil Kumaran","doi":"10.11591/ijai.v13.i2.pp1312-1325","DOIUrl":"https://doi.org/10.11591/ijai.v13.i2.pp1312-1325","url":null,"abstract":"The transmission of biomedical signals in real-time is extremely difficult and necessitates the use of cloud and internet of things (IoT) infrastructure. Security is also an important consideration, however, to achieve this, a reconstruction method is developed where the entire signal is fed as an input, just the primary portion, the entire signal is taken then encoded, and then deliver to the destination. It is unlocked using a reconstruction technique without any signal attenuation. The key difficulty is how to manage the sensor network once the input is prepared for transmission. This has problems with extremely high network energy consumption and accurate data collection. The accuracy of data reconstruction through is improved by compressive sensing. The lifespan of the network as a whole could be extended, in this study; the proposed proposed system convolutional neural network (PS-CNN) is an integrated model that combines feature selection and auto-encoder. In order to produce the most useful features for particular tasks, our algorithm can eventually separate the appropriate task units from the irrelevant tasks.","PeriodicalId":507934,"journal":{"name":"IAES International Journal of Artificial Intelligence (IJ-AI)","volume":"5 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141230085","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}
Pub Date : 2024-06-01DOI: 10.11591/ijai.v13.i2.pp1388-1397
Dewa Gede, Hendra Divayana, A. Adiarta, N. Santiyadnya, P. Wayan, Arta Suyasa, M. Lissia, Andayani, I. Nyoman, Indhi Wiradika, I. Kadek, Arta Wiguna
This study aimed to show the user interface design form of the context-input-process-product (CIPP) evaluation application based on weighted product as a measuring tool for the effectiveness level of blended learning in health colleges. This research approach was development research. The development model used was Borg and Gall. It focused on the design stage, initial trials, and revisions. The initial test of the user interface design involved 32 respondents. The tool for conducting it was in the form of a questionnaire, which contains 16 questions. The research was at the health colleges in Buleleng Regency. The data analysis technique of the initial test results was quantitative descriptive. It compared the percentage level of user interface design quality from the weighted product-based CIPP evaluation application with a quality standard which referred to a five scale. The results of this study indicated that the quality of the user interface design was relatively good. The research result’s impact on educational evaluation was new knowledge for pedagogic evaluators in maximizing the development of digital-based evaluation tools by integrating the decision support system method (weighted product) with the educational evaluation model (CIPP model).
本研究旨在展示基于加权产品的情境-输入-过程-产品（CIPP）评价应用程序的用户界面设计形式，以此作为衡量卫生学院混合式学习有效性水平的工具。该研究方法属于开发研究。使用的开发模型是 Borg 和 Gall 模型。其重点是设计阶段、初步试验和修订。用户界面设计的初步测试有 32 名受访者参与。测试工具是一份包含 16 个问题的调查问卷。研究地点在布勒伦地区的卫生学院。初步测试结果的数据分析技术是定量描述性的。它将基于加权产品的 CIPP 评估应用程序的用户界面设计质量百分比水平与五级质量标准进行了比较。研究结果表明，用户界面设计的质量相对较好。该研究成果对教育评价的影响是为教学评价人员提供了新的知识，通过将决策支持系统方法（加权产品）与教育评价模型（CIPP 模型）相结合，最大限度地开发基于数字化的评价工具。
{"title":"User interface design of context-input-process-product evaluation application based on weighted product","authors":"Dewa Gede, Hendra Divayana, A. Adiarta, N. Santiyadnya, P. Wayan, Arta Suyasa, M. Lissia, Andayani, I. Nyoman, Indhi Wiradika, I. Kadek, Arta Wiguna","doi":"10.11591/ijai.v13.i2.pp1388-1397","DOIUrl":"https://doi.org/10.11591/ijai.v13.i2.pp1388-1397","url":null,"abstract":"This study aimed to show the user interface design form of the context-input-process-product (CIPP) evaluation application based on weighted product as a measuring tool for the effectiveness level of blended learning in health colleges. This research approach was development research. The development model used was Borg and Gall. It focused on the design stage, initial trials, and revisions. The initial test of the user interface design involved 32 respondents. The tool for conducting it was in the form of a questionnaire, which contains 16 questions. The research was at the health colleges in Buleleng Regency. The data analysis technique of the initial test results was quantitative descriptive. It compared the percentage level of user interface design quality from the weighted product-based CIPP evaluation application with a quality standard which referred to a five scale. The results of this study indicated that the quality of the user interface design was relatively good. The research result’s impact on educational evaluation was new knowledge for pedagogic evaluators in maximizing the development of digital-based evaluation tools by integrating the decision support system method (weighted product) with the educational evaluation model (CIPP model).","PeriodicalId":507934,"journal":{"name":"IAES International Journal of Artificial Intelligence (IJ-AI)","volume":"18 22","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141233412","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}
Pub Date : 2024-06-01DOI: 10.11591/ijai.v13.i2.pp1450-1458
Hanaa M. Mushgil, Khairiyah Saeed Abduljabbar, Baydaa Mohammad Mushgil
This abstract focuses on the significance of wireless body area networks (WBANs) as a cutting-edge and self-governing technology, which has garnered substantial attention from researchers. The central challenge faced by WBANs revolves around upholding quality of service (QoS) within rapidly evolving sectors like healthcare. The intricate task of managing diverse traffic types with limited resources further compounds this challenge. Particularly in medical WBANs, the prioritization of vital data is crucial to ensure prompt delivery of critical information. Given the stringent requirements of these systems, any data loss or delays are untenable, necessitating the implementation of intelligent algorithms. These algorithms play a pivotal role in expediting diagnosis and treatment processes during medical emergencies. This study introduces an innovative protocol termed collaborative binary Naive Bayes decision tree (CBNBDT) designed to enhance packet classification and transmission prioritization. Through the utilization of this protocol, incoming packets are categorized based on their respective classes, enabling subsequent prioritization. Thorough simulations have demonstrated the superior performance of the proposed CBNBDT protocol compared to baseline approaches.
{"title":"A novel fusion-based approach for the classification of packets in wireless body area networks","authors":"Hanaa M. Mushgil, Khairiyah Saeed Abduljabbar, Baydaa Mohammad Mushgil","doi":"10.11591/ijai.v13.i2.pp1450-1458","DOIUrl":"https://doi.org/10.11591/ijai.v13.i2.pp1450-1458","url":null,"abstract":"This abstract focuses on the significance of wireless body area networks (WBANs) as a cutting-edge and self-governing technology, which has garnered substantial attention from researchers. The central challenge faced by WBANs revolves around upholding quality of service (QoS) within rapidly evolving sectors like healthcare. The intricate task of managing diverse traffic types with limited resources further compounds this challenge. Particularly in medical WBANs, the prioritization of vital data is crucial to ensure prompt delivery of critical information. Given the stringent requirements of these systems, any data loss or delays are untenable, necessitating the implementation of intelligent algorithms. These algorithms play a pivotal role in expediting diagnosis and treatment processes during medical emergencies. This study introduces an innovative protocol termed collaborative binary Naive Bayes decision tree (CBNBDT) designed to enhance packet classification and transmission prioritization. Through the utilization of this protocol, incoming packets are categorized based on their respective classes, enabling subsequent prioritization. Thorough simulations have demonstrated the superior performance of the proposed CBNBDT protocol compared to baseline approaches.","PeriodicalId":507934,"journal":{"name":"IAES International Journal of Artificial Intelligence (IJ-AI)","volume":"14 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141235307","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}
A number of weaknesses were demonstrated in the E-learning platforms during the Covid-19 pandemic despite the efforts invested. This has negatively influenced learners' motivation and consequently their performance. With the proliferation of technology and the revolution of information and communication technologies (ICT), learning objects have become new epitomes widely used, accessible, and implemented with educational resources and technological support. The integration of learning objects into E-learning has enhanced educational progress, but during critical periods, it is crucial to ensure pedagogical continuity and learner motivation. Based on this observation, we will propose architecture of a personalized learning object model in the context of an adaptive hypermedia learning system (AHS). The objective of our model is to increase the motivation factor which is a determining element in the success of E-learning, our model aims to improve the performance of the learners in order to avoid the abounding of learning and to promote the attendance of the learners. This will be useful later for any design or development of learning objects in hypermedia learning systems that are adaptive to the needs of the learners and in line with their preferences and profiles throughout the learning process offered by the system.
{"title":"Model for motivating learners with personalized learning objects in a hypermedia adaptive learning system","authors":"Chelliq Ikram, Anoir Lamya, Erradi Mohamed, Khaldi Mohamed","doi":"10.11591/ijai.v13.i2.pp1282-1293","DOIUrl":"https://doi.org/10.11591/ijai.v13.i2.pp1282-1293","url":null,"abstract":"A number of weaknesses were demonstrated in the E-learning platforms during the Covid-19 pandemic despite the efforts invested. This has negatively influenced learners' motivation and consequently their performance. With the proliferation of technology and the revolution of information and communication technologies (ICT), learning objects have become new epitomes widely used, accessible, and implemented with educational resources and technological support. The integration of learning objects into E-learning has enhanced educational progress, but during critical periods, it is crucial to ensure pedagogical continuity and learner motivation. Based on this observation, we will propose architecture of a personalized learning object model in the context of an adaptive hypermedia learning system (AHS). The objective of our model is to increase the motivation factor which is a determining element in the success of E-learning, our model aims to improve the performance of the learners in order to avoid the abounding of learning and to promote the attendance of the learners. This will be useful later for any design or development of learning objects in hypermedia learning systems that are adaptive to the needs of the learners and in line with their preferences and profiles throughout the learning process offered by the system. ","PeriodicalId":507934,"journal":{"name":"IAES International Journal of Artificial Intelligence (IJ-AI)","volume":"8 38","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141230837","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}
Pub Date : 2024-06-01DOI: 10.11591/ijai.v13.i2.pp1358-1370
Shiva Shankar Reddy, Vuddagiri MNSSVKR. Gupta, Lokavarapu V. Srinivas, Chigurupati Ravi Swaroop
Finding relevant content and extracting information from images is highly significant. Still, it may be challenging to do so because of changes within the textual contents, such as typefaces, size, line orientation, sophisticated backgrounds in images, and non-uniform illuminations. Despite these challenges, extracting content from captured images is still very important. Proficient textual content image recognition abilities extract text from the images to get over these issues. Despite the availability of several optical character recognition (OCR) techniques, this issue has yet to be resolved. Captured images with text are a rich source of information that should be presented so that viewers may make informed decisions. Because of this, it has become a complicated process to extract the text from an image because the text might be of poor quality, has a variety of fonts and styles, and occasionally have a complicated backdrop, among other things. Several approaches have been tried. However, finding a solution remains challenging. The maximally stable external regions (MSER) approach is developed to identify the text region in a picture. MSER is utilized to elevate the plain regions outside the text and non-text areas using geometric features and stroke width variation qualities.
{"title":"Methodology for eliminating plain regions from captured images","authors":"Shiva Shankar Reddy, Vuddagiri MNSSVKR. Gupta, Lokavarapu V. Srinivas, Chigurupati Ravi Swaroop","doi":"10.11591/ijai.v13.i2.pp1358-1370","DOIUrl":"https://doi.org/10.11591/ijai.v13.i2.pp1358-1370","url":null,"abstract":"Finding relevant content and extracting information from images is highly significant. Still, it may be challenging to do so because of changes within the textual contents, such as typefaces, size, line orientation, sophisticated backgrounds in images, and non-uniform illuminations. Despite these challenges, extracting content from captured images is still very important. Proficient textual content image recognition abilities extract text from the images to get over these issues. Despite the availability of several optical character recognition (OCR) techniques, this issue has yet to be resolved. Captured images with text are a rich source of information that should be presented so that viewers may make informed decisions. Because of this, it has become a complicated process to extract the text from an image because the text might be of poor quality, has a variety of fonts and styles, and occasionally have a complicated backdrop, among other things. Several approaches have been tried. However, finding a solution remains challenging. The maximally stable external regions (MSER) approach is developed to identify the text region in a picture. MSER is utilized to elevate the plain regions outside the text and non-text areas using geometric features and stroke width variation qualities.","PeriodicalId":507934,"journal":{"name":"IAES International Journal of Artificial Intelligence (IJ-AI)","volume":"4 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141229737","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}
Pub Date : 2024-06-01DOI: 10.11591/ijai.v13.i2.pp1596-1607
Hasna Melani Puspasari, Ilham Zharif Mustaqim, Avita Tri Utami, Rahmad Syalevi, Y. Ruldeviyani
The Indonesian national police (Polri) offer public services through mobile apps: Digital korlantas polri (DigiKorlantas) and samsat digital nasional (SIGNAL). Sentiment analysis gauges public perceptions, serving as a basis for e-government evaluation using user ratings and comments from app stores. Keyword relevance is assessed via feature extraction and Naïve Bayes classification. Thematic analysis is implemented using N-grams methods to identify the factors affecting the effectiveness based on user experiences. The accuracy of the model reaches 81.09% where it indicates a high performance. DigiKorlantas acquires slightly more negative reviews in comparation with positive reviews which are 51% and 49% respectively. In contrast, positive sentiment is dominant on SIGNAL which reach 58%, compared with negative sentiment that in 42%. N-grams reveal similar review patterns for both apps. Some of the solutions are Korlantas Polri should enhance the verification functionality with several techniques such as retinex algorithms or optical character recognition pipeline and increase the capacity of supporting server then releasing an updated version of application to address errors or bugs. This analysis can be alternative evaluation by the Polri to measure the success of the application and find out the continuous improvement of the process and the system.
印度尼西亚国家警察（Polri）通过移动应用程序提供公共服务：Digital korlantas polri (DigiKorlantas) 和 samsat digital nasional (SIGNAL)。情感分析可衡量公众的看法，并利用应用程序商店中的用户评分和评论作为电子政务评估的基础。关键词相关性通过特征提取和奈维贝叶斯分类进行评估。使用 N-grams 方法进行专题分析，根据用户体验确定影响有效性的因素。该模型的准确率达到 81.09%，显示出较高的性能。与正面评论相比，DigiKorlantas 获得的负面评论略多，分别为 51% 和 49%。相比之下，正面评价在 SIGNAL 上占主导地位，达到 58%，而负面评价为 42%。N-grams 显示这两款应用的评论模式相似。一些解决方案是，Korlantas Polri 应使用多种技术（如视网膜算法或光学字符识别管道）增强验证功能，并提高支持服务器的容量，然后发布更新版本的应用程序，以解决错误或漏洞。Polri 可以通过这种分析进行替代评估，以衡量应用程序的成功与否，并发现流程和系统的持续改进之处。
{"title":"Evaluation of Indonesia’s police public service platforms through sentiment and thematic analysis","authors":"Hasna Melani Puspasari, Ilham Zharif Mustaqim, Avita Tri Utami, Rahmad Syalevi, Y. Ruldeviyani","doi":"10.11591/ijai.v13.i2.pp1596-1607","DOIUrl":"https://doi.org/10.11591/ijai.v13.i2.pp1596-1607","url":null,"abstract":"The Indonesian national police (Polri) offer public services through mobile apps: Digital korlantas polri (DigiKorlantas) and samsat digital nasional (SIGNAL). Sentiment analysis gauges public perceptions, serving as a basis for e-government evaluation using user ratings and comments from app stores. Keyword relevance is assessed via feature extraction and Naïve Bayes classification. Thematic analysis is implemented using N-grams methods to identify the factors affecting the effectiveness based on user experiences. The accuracy of the model reaches 81.09% where it indicates a high performance. DigiKorlantas acquires slightly more negative reviews in comparation with positive reviews which are 51% and 49% respectively. In contrast, positive sentiment is dominant on SIGNAL which reach 58%, compared with negative sentiment that in 42%. N-grams reveal similar review patterns for both apps. Some of the solutions are Korlantas Polri should enhance the verification functionality with several techniques such as retinex algorithms or optical character recognition pipeline and increase the capacity of supporting server then releasing an updated version of application to address errors or bugs. This analysis can be alternative evaluation by the Polri to measure the success of the application and find out the continuous improvement of the process and the system.","PeriodicalId":507934,"journal":{"name":"IAES International Journal of Artificial Intelligence (IJ-AI)","volume":"7 8","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141229482","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：