Pub Date : 2024-06-01DOI: 10.11591/ijai.v13.i2.pp1888-1899
Jide Kehinde Adeniyi, S. A. Ajagbe, A. Adeniyi, H. Aworinde, P. Falola, M. Adigun
Large volumes of information are generated daily, making it challenging to manage such information. This is due to redundancy and the type of data available, most of which needs to be more structured and increases the amount of search time. Text summarization systems are considered a real solution to this vast amount of data because they are used for document compression and reduction. Text summarization keeps the relevant information and eliminates the text's non-relevant parts. This study uses two types of summarizers: Extractive Text summarizers and Abstractive text summarizers. The Text Rank Algorithm was used to implement the Extractive summarizer, while Bi-directional Recurrent Neural Network (RNN) was used to implement the Abstractive text summarizer. To improve the quality of summaries produced, word embedding was also used. For the evaluation of the summarizers, the ROUGE evaluation system was used. ROUGE contrasts summaries created by hand versus those created automatically. ROUGE examination of the produced summary revealed the superiority of human-produced summaries over those generated automatically. For this paper, a summarizer was implemented as a Web Application. The average ROUGE recall score ranging from 30.00 to 60.00 for abstractive summarizer and 0.75 to 0.82 for extractive text showed an encouraging result.
{"title":"EASESUM: an online abstractive and extractive text summarizer using deep learning technique","authors":"Jide Kehinde Adeniyi, S. A. Ajagbe, A. Adeniyi, H. Aworinde, P. Falola, M. Adigun","doi":"10.11591/ijai.v13.i2.pp1888-1899","DOIUrl":"https://doi.org/10.11591/ijai.v13.i2.pp1888-1899","url":null,"abstract":"<div align=\"center\"><table width=\"590\" border=\"1\" cellspacing=\"0\" cellpadding=\"0\"><tbody><tr><td valign=\"top\" width=\"387\"><p class=\"CM12\">Large volumes of information are generated daily, making it challenging to manage such information. This is due to redundancy and the type of data available, most of which needs to be more structured and increases the amount of search time. Text summarization systems are considered a real solution to this vast amount of data because they are used for document compression and reduction. Text summarization keeps the relevant information and eliminates the text's non-relevant parts. This study uses two types of summarizers: Extractive Text summarizers and Abstractive text summarizers. The Text Rank Algorithm was used to implement the Extractive summarizer, while Bi-directional Recurrent Neural Network (RNN) was used to implement the Abstractive text summarizer. To improve the quality of summaries produced, word embedding was also used. For the evaluation of the summarizers, the ROUGE evaluation system was used. ROUGE contrasts summaries created by hand versus those created automatically. ROUGE examination of the produced summary revealed the superiority of human-produced summaries over those generated automatically. For this paper, a summarizer was implemented as a Web Application. The average ROUGE recall score ranging from 30.00 to 60.00 for abstractive summarizer and 0.75 to 0.82 for extractive text showed an encouraging result.</p></td></tr></tbody></table></div>","PeriodicalId":507934,"journal":{"name":"IAES International Journal of Artificial Intelligence (IJ-AI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141235321","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.pp1214-1226
E. Imandeka, A. Hidayanto, Mufti Mahmud
The rapid rise of intelligent technology, particularly in government, is igniting a new phase of the industrial revolution around the world. As governmental entities, prisons oversee upholding social order and lowering current crime. The concept of the smart prison has not received much attention but is gaining traction. The goal of this research is to conduct a literature review to identify current prison technologies and to analyse the challenges associated with implementing smart prisons using the preferred reporting items for systematic reviews and meta-analyses (PRISMA) protocol. Nine credible publishers were looked up between October 2022 and December 2022. The initial search yielded 362 articles, of which 25 were included in the final phase. This research provides the current state of prison according to technology-organization-environment (TOE). Some challenges arise in the context of TOE, such as the high cost of smart technology, inadequate technology design, poor management, ineffective service, overcrowding, ageing facilities, increasing violence, disease spread, and ethical problems. This study also classifies smart prison technology based on the internet of things (IoT) architecture layer. By providing the first comprehensive review on smart prison technology, this study makes an essential contribution to the subject of prisons.
{"title":"Smart prison technology and challenges: a systematic literature reviews","authors":"E. Imandeka, A. Hidayanto, Mufti Mahmud","doi":"10.11591/ijai.v13.i2.pp1214-1226","DOIUrl":"https://doi.org/10.11591/ijai.v13.i2.pp1214-1226","url":null,"abstract":"The rapid rise of intelligent technology, particularly in government, is igniting a new phase of the industrial revolution around the world. As governmental entities, prisons oversee upholding social order and lowering current crime. The concept of the smart prison has not received much attention but is gaining traction. The goal of this research is to conduct a literature review to identify current prison technologies and to analyse the challenges associated with implementing smart prisons using the preferred reporting items for systematic reviews and meta-analyses (PRISMA) protocol. Nine credible publishers were looked up between October 2022 and December 2022. The initial search yielded 362 articles, of which 25 were included in the final phase. This research provides the current state of prison according to technology-organization-environment (TOE). Some challenges arise in the context of TOE, such as the high cost of smart technology, inadequate technology design, poor management, ineffective service, overcrowding, ageing facilities, increasing violence, disease spread, and ethical problems. This study also classifies smart prison technology based on the internet of things (IoT) architecture layer. By providing the first comprehensive review on smart prison technology, this study makes an essential contribution to the subject of prisons.","PeriodicalId":507934,"journal":{"name":"IAES International Journal of Artificial Intelligence (IJ-AI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141231268","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.pp1348-1357
Sushant Mangasuli, Mahesh Kaluti
Climate change poses several environmental threats like floods to urban environment; thus, effective and reliable communication of emergency information is needed during massive breakdown of network infrastructure. This paper presents a mobile adhoc network (MANETs) based effective information such as calls, image, and videos communication system that is compatible with current 3GPP and 5G communication network. Here in maintaining connectivity the information is communicated between different MANET nodes in a multi-hop manner. However, designing radio propagation is challenging considering higher local emergency request congestion at different terrain with varying speed of users. The current radio propagation model is designed without considering the effect of line-of-sight between communicating device and are not adaptive to different environment considering urban disaster management environment. This paper develops an adaptive radio propagation (ARP) model namely expressway, city and semiurban. Then, in reducing congestion and improving network performance efficiency the work introduced an adaptive medium access control (AMAC) protocol. The MAC incorporates a dynamic network controller (DNC) to optimize the contention window size in dynamic manner according to current traffic demands. The AMAC protocol achieves much improved throughput with lesser packet loss in comparison with existing MAC (EMAC) model considering different radio propagation model introduced in this work.
{"title":"Adaptive radio propagation model for maximizing performance efficiency in smart city disaster management application","authors":"Sushant Mangasuli, Mahesh Kaluti","doi":"10.11591/ijai.v13.i2.pp1348-1357","DOIUrl":"https://doi.org/10.11591/ijai.v13.i2.pp1348-1357","url":null,"abstract":"Climate change poses several environmental threats like floods to urban environment; thus, effective and reliable communication of emergency information is needed during massive breakdown of network infrastructure. This paper presents a mobile adhoc network (MANETs) based effective information such as calls, image, and videos communication system that is compatible with current 3GPP and 5G communication network. Here in maintaining connectivity the information is communicated between different MANET nodes in a multi-hop manner. However, designing radio propagation is challenging considering higher local emergency request congestion at different terrain with varying speed of users. The current radio propagation model is designed without considering the effect of line-of-sight between communicating device and are not adaptive to different environment considering urban disaster management environment. This paper develops an adaptive radio propagation (ARP) model namely expressway, city and semiurban. Then, in reducing congestion and improving network performance efficiency the work introduced an adaptive medium access control (AMAC) protocol. The MAC incorporates a dynamic network controller (DNC) to optimize the contention window size in dynamic manner according to current traffic demands. The AMAC protocol achieves much improved throughput with lesser packet loss in comparison with existing MAC (EMAC) model considering different radio propagation model introduced in this work.","PeriodicalId":507934,"journal":{"name":"IAES International Journal of Artificial Intelligence (IJ-AI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141229054","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.pp2212-2225
S. Nurdiati, Endar Hasafah Nugrahani, F. Bukhari, M. Najib, Denny Muliawan Sebastian, Putri Afia Nur Fallahi
Hotspots as indicators of forest fires capable of quickly monitoring large areas are often predicted using various machine learning methods. However, there is still little research that analyzes the sensitivity and feature importance of each predictor that forms a machine learning prediction model. This study evaluates and compares several machine learning methods to predict hotspots in Kalimantan. Using the most accurate machine learning model, each climate factor used as a predictor is analyzed for its sensitivity and feature importance. Some of the machine learning methods used include random forest, gradient boosting, Bayesian regression, and artificial neural networks. Meanwhile, several measures of sensitivity and feature importance used are variance-based, density-based, and distribution-based sensitivity indices, as well as permutation and Shapley feature importance. Evaluation of the ML model concluded that the Bayesian linear regression model outperformed other ML models, based on RMSE and explained variance score. Meanwhile, tree-based models, such as random forest and gradient boosting, are indicative of overfit. Based on the results of sensitivity analysis and feature importance, the number of dry days is the most important feature for the Bayesian linear regression model in predicting the number of hotspots in Kalimantan.
热点作为能够快速监测大面积森林火灾的指标，通常使用各种机器学习方法进行预测。然而，对构成机器学习预测模型的每个预测因子的灵敏度和特征重要性进行分析的研究仍然很少。本研究评估并比较了几种机器学习方法，以预测加里曼丹的热点地区。使用最准确的机器学习模型，对用作预测因子的每个气候因子的敏感性和特征重要性进行分析。使用的机器学习方法包括随机森林、梯度提升、贝叶斯回归和人工神经网络。同时，还使用了基于方差、基于密度和基于分布的灵敏度指数，以及置换和 Shapley 特征重要性等灵敏度和特征重要性度量方法。对 ML 模型进行评估后得出结论，根据 RMSE 和解释方差得分，贝叶斯线性回归模型优于其他 ML 模型。同时，基于树的模型，如随机森林和梯度提升模型，都有过拟合的迹象。根据灵敏度分析和特征重要性的结果，干旱天数是贝叶斯线性回归模型预测加里曼丹热点数量的最重要特征。
{"title":"Sensitivity and feature importance of climate factors and evaluation of different machine learning models for predicting fire hotspots in Kalimantan, Indonesia","authors":"S. Nurdiati, Endar Hasafah Nugrahani, F. Bukhari, M. Najib, Denny Muliawan Sebastian, Putri Afia Nur Fallahi","doi":"10.11591/ijai.v13.i2.pp2212-2225","DOIUrl":"https://doi.org/10.11591/ijai.v13.i2.pp2212-2225","url":null,"abstract":"Hotspots as indicators of forest fires capable of quickly monitoring large areas are often predicted using various machine learning methods. However, there is still little research that analyzes the sensitivity and feature importance of each predictor that forms a machine learning prediction model. This study evaluates and compares several machine learning methods to predict hotspots in Kalimantan. Using the most accurate machine learning model, each climate factor used as a predictor is analyzed for its sensitivity and feature importance. Some of the machine learning methods used include random forest, gradient boosting, Bayesian regression, and artificial neural networks. Meanwhile, several measures of sensitivity and feature importance used are variance-based, density-based, and distribution-based sensitivity indices, as well as permutation and Shapley feature importance. Evaluation of the ML model concluded that the Bayesian linear regression model outperformed other ML models, based on RMSE and explained variance score. Meanwhile, tree-based models, such as random forest and gradient boosting, are indicative of overfit. Based on the results of sensitivity analysis and feature importance, the number of dry days is the most important feature for the Bayesian linear regression model in predicting the number of hotspots in Kalimantan.","PeriodicalId":507934,"journal":{"name":"IAES International Journal of Artificial Intelligence (IJ-AI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141231224","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.pp2247-2253
Leena Chawla, Vijay Kumar, Arti Saxena
Information theoretic learning plays a very important role in adaption learning systems. Many non-parametric entropy estimators have been proposed by the researchers. This work explores kernel density estimation based on Tsallis entropy. Firstly, it has been proved that for linearly independent samples and for equal samples, Tsallis-estimator is consistent for the PDF and minimum respectively. Also, it is investigated that Tsallis-estimator is smooth for differentiable, symmetric, and unimodal kernel function. Further, important properties of Tsallis-estimator such as scaling and invariance for both single and joint entropy estimation have been proved. The objective of the work is to understand the mathematics behind the underlying concept.
信息论学习在自适应学习系统中扮演着非常重要的角色。研究人员提出了许多非参数熵估计器。本研究探讨了基于 Tsallis 熵的核密度估计。首先，研究证明，对于线性独立样本和相等样本，Tsallis 估计器分别与 PDF 和最小值一致。此外，还研究了 Tsallis-estimator 对于可微分、对称和单模态核函数是平滑的。此外，研究还证明了 Tsallis-estimator 的重要特性，如单个熵估计和联合熵估计的缩放性和不变性。这项工作的目的是理解基本概念背后的数学。
{"title":"Kernel density estimation of Tsalli’s entropy with applications in adaptive system training","authors":"Leena Chawla, Vijay Kumar, Arti Saxena","doi":"10.11591/ijai.v13.i2.pp2247-2253","DOIUrl":"https://doi.org/10.11591/ijai.v13.i2.pp2247-2253","url":null,"abstract":"Information theoretic learning plays a very important role in adaption learning systems. Many non-parametric entropy estimators have been proposed by the researchers. This work explores kernel density estimation based on Tsallis entropy. Firstly, it has been proved that for linearly independent samples and for equal samples, Tsallis-estimator is consistent for the PDF and minimum respectively. Also, it is investigated that Tsallis-estimator is smooth for differentiable, symmetric, and unimodal kernel function. Further, important properties of Tsallis-estimator such as scaling and invariance for both single and joint entropy estimation have been proved. The objective of the work is to understand the mathematics behind the underlying concept.","PeriodicalId":507934,"journal":{"name":"IAES International Journal of Artificial Intelligence (IJ-AI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141231446","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.pp1380-1387
Khaldun G. Al-Moghrabi, Ali M. Al-Ghonmein
Technology, such as blockchain, has emerged as a promising solution for addressing the challenges of e-commerce decision-making. In this study, we explore the potential benefits of integrating blockchain technology into e-commerce and its role in supporting decision-making in e-commerce. We also examine blockchain’s benefits in terms of enhanced security, transparency, and efficiency for e-commerce platforms. Furthermore, the study discusses the challenges of implementing blockchain for e-commerce, including scalability, integration, regulatory frameworks, user experience, privacy, interoperability, and sustainability. By analyzing these challenges, the study provides valuable insights for future research and development efforts to facilitate a seamless adoption of blockchain technology in e-commerce decisions. Blockchain technology holds the potential to transform an e-commerce ecosystem by overcoming these challenges and unlocking its transformative potential.
{"title":"Harnessing the power of blockchain technology to support decision-making in e-commerce processes","authors":"Khaldun G. Al-Moghrabi, Ali M. Al-Ghonmein","doi":"10.11591/ijai.v13.i2.pp1380-1387","DOIUrl":"https://doi.org/10.11591/ijai.v13.i2.pp1380-1387","url":null,"abstract":"Technology, such as blockchain, has emerged as a promising solution for addressing the challenges of e-commerce decision-making. In this study, we explore the potential benefits of integrating blockchain technology into e-commerce and its role in supporting decision-making in e-commerce. We also examine blockchain’s benefits in terms of enhanced security, transparency, and efficiency for e-commerce platforms. Furthermore, the study discusses the challenges of implementing blockchain for e-commerce, including scalability, integration, regulatory frameworks, user experience, privacy, interoperability, and sustainability. By analyzing these challenges, the study provides valuable insights for future research and development efforts to facilitate a seamless adoption of blockchain technology in e-commerce decisions. Blockchain technology holds the potential to transform an e-commerce ecosystem by overcoming these challenges and unlocking its transformative potential.","PeriodicalId":507934,"journal":{"name":"IAES International Journal of Artificial Intelligence (IJ-AI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141233513","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.pp2236-2246
Mohammed El Assad, Said Nouh, Imrane Chemseddine Idrissi, Seddiq El Kasmi Alaoui, Bouchaib Aylaj, M. Azzouazi
Error-correcting codes are used to partially or completely correct errors as much as possible, while ensuring high transmission speeds. Several Machine Learning (ML) models such as Logistic Regression and Decision tree have been applied to correct transmission errors. Among the most powerful ML techniques are aggregation methods which have yielded to excellent results in many areas of research. It is this excellence that has prompted us to consider their application for the hard decoding problem. In this sense, we have successfully designed, tested and validated our proposed EL-BoostDec decoder (hard decision decoder based on Ensemble Learning - Boosting technique) which is based on computing of the syndrome of the received word and on using Ensemble Learning techniques to find the corresponding corrigible error. The obtained results with EL-BoostDec are very encouraging in terms of the binary error rate (BER) that it offers. Practically EL-BoostDec has succeed to correct 100% of errors that have weights less than or equal to the correction capacity of studied codes. The comparison of EL-BoostDec with many competitors proves its power. A study of parameters which impact on EL-BoostDec performances has been established to obtain a good BER with minimum run time complexity.
{"title":"A new efficient decoder of linear block codes based on ensemble learning models: case of boosting","authors":"Mohammed El Assad, Said Nouh, Imrane Chemseddine Idrissi, Seddiq El Kasmi Alaoui, Bouchaib Aylaj, M. Azzouazi","doi":"10.11591/ijai.v13.i2.pp2236-2246","DOIUrl":"https://doi.org/10.11591/ijai.v13.i2.pp2236-2246","url":null,"abstract":"Error-correcting codes are used to partially or completely correct errors as much as possible, while ensuring high transmission speeds. Several Machine Learning (ML) models such as Logistic Regression and Decision tree have been applied to correct transmission errors. Among the most powerful ML techniques are aggregation methods which have yielded to excellent results in many areas of research. It is this excellence that has prompted us to consider their application for the hard decoding problem. In this sense, we have successfully designed, tested and validated our proposed EL-BoostDec decoder (hard decision decoder based on Ensemble Learning - Boosting technique) which is based on computing of the syndrome of the received word and on using Ensemble Learning techniques to find the corresponding corrigible error. The obtained results with EL-BoostDec are very encouraging in terms of the binary error rate (BER) that it offers. Practically EL-BoostDec has succeed to correct 100% of errors that have weights less than or equal to the correction capacity of studied codes. The comparison of EL-BoostDec with many competitors proves its power. A study of parameters which impact on EL-BoostDec performances has been established to obtain a good BER with minimum run time complexity.","PeriodicalId":507934,"journal":{"name":"IAES International Journal of Artificial Intelligence (IJ-AI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141234394","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.pp1723-1731
M. Maryanto, Philips Philips, Abba Suganda Girsang
Extractive text summarization has been a popular research area for many years. The goal of this task is to generate a compact and coherent summary of a given document, preserving the most important information. However, current extractive summarization methods still face several challenges such as semantic drift, repetition, redundancy, and lack of coherence. A novel approach is presented in this paper to improve the performance of an extractive summarization model based on bidirectional encoder representations from transformers (BERT) by incorporating topic modeling using the BERTopic model. Our method first utilizes BERTopic to identify the dominant topics in a document and then employs a BERT-based deep neural network to extract the most salient sentences related to those topics. Our experiments on the cable news network (CNN)/daily mail dataset demonstrate that our proposed method outperforms state-of-the-art BERT-based extractive summarization models in terms of recall-oriented understudy for gisting evaluation (ROUGE) scores, which resulted in an increase of 32.53% of ROUGE-1, 47.55% of ROUGE-2, and 16.63% of ROUGE-L when compared to baseline BERT-based extractive summarization models. This paper contributes to the field of extractive text summarization, highlights the potential of topic modeling in improving summarization results, and provides a new direction for future research.
{"title":"Hybrid model for extractive single document summarization: utilizing BERTopic and BERT model","authors":"M. Maryanto, Philips Philips, Abba Suganda Girsang","doi":"10.11591/ijai.v13.i2.pp1723-1731","DOIUrl":"https://doi.org/10.11591/ijai.v13.i2.pp1723-1731","url":null,"abstract":"Extractive text summarization has been a popular research area for many years. The goal of this task is to generate a compact and coherent summary of a given document, preserving the most important information. However, current extractive summarization methods still face several challenges such as semantic drift, repetition, redundancy, and lack of coherence. A novel approach is presented in this paper to improve the performance of an extractive summarization model based on bidirectional encoder representations from transformers (BERT) by incorporating topic modeling using the BERTopic model. Our method first utilizes BERTopic to identify the dominant topics in a document and then employs a BERT-based deep neural network to extract the most salient sentences related to those topics. Our experiments on the cable news network (CNN)/daily mail dataset demonstrate that our proposed method outperforms state-of-the-art BERT-based extractive summarization models in terms of recall-oriented understudy for gisting evaluation (ROUGE) scores, which resulted in an increase of 32.53% of ROUGE-1, 47.55% of ROUGE-2, and 16.63% of ROUGE-L when compared to baseline BERT-based extractive summarization models. This paper contributes to the field of extractive text summarization, highlights the potential of topic modeling in improving summarization results, and provides a new direction for future research.","PeriodicalId":507934,"journal":{"name":"IAES International Journal of Artificial Intelligence (IJ-AI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141232092","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.pp2314-2322
Rima Hatoum, Ali Alkhazraji, Z. Ibrahim, Houssein Dhayni, Ihab Sbeity
Healthcare professionals are increasingly interested in predicting diseases before they manifest, as this can prevent more serious health conditions and even save lives. Machine learning techniques are now playing an important role in healthcare, including in the early prediction of diseases based on prior medical knowledge. However, one of the biggest challenges is how to represent medical information in a way that can be processed by machine learning algorithms. Medical histories are often in a format that computers cannot read, so filtering and converting this information into numerical representations is a crucial step. This process has become easier with the advancement of natural language processing techniques. In this paper, we propose three representations of medical information, two of which are based on BioBERT, the latest text representation techniques for the biomedical sector. The efficiency of these representations is tested on the MIMIC-III database, which contains information on 46,520 patients. The focus of the study is on predicting Coronary Artery Disease, and the results demonstrate the effectiveness of the proposed approach. The study highlights the importance of medical history in disease prediction and demonstrates the potential of machine learning techniques to advance healthcare.
{"title":"Towards a disease prediction system: BioBERT-based medical profile representation","authors":"Rima Hatoum, Ali Alkhazraji, Z. Ibrahim, Houssein Dhayni, Ihab Sbeity","doi":"10.11591/ijai.v13.i2.pp2314-2322","DOIUrl":"https://doi.org/10.11591/ijai.v13.i2.pp2314-2322","url":null,"abstract":"Healthcare professionals are increasingly interested in predicting diseases before they manifest, as this can prevent more serious health conditions and even save lives. Machine learning techniques are now playing an important role in healthcare, including in the early prediction of diseases based on prior medical knowledge. However, one of the biggest challenges is how to represent medical information in a way that can be processed by machine learning algorithms. Medical histories are often in a format that computers cannot read, so filtering and converting this information into numerical representations is a crucial step. This process has become easier with the advancement of natural language processing techniques. In this paper, we propose three representations of medical information, two of which are based on BioBERT, the latest text representation techniques for the biomedical sector. The efficiency of these representations is tested on the MIMIC-III database, which contains information on 46,520 patients. The focus of the study is on predicting Coronary Artery Disease, and the results demonstrate the effectiveness of the proposed approach. The study highlights the importance of medical history in disease prediction and demonstrates the potential of machine learning techniques to advance healthcare.","PeriodicalId":507934,"journal":{"name":"IAES International Journal of Artificial Intelligence (IJ-AI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141230032","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.pp1619-1624
Surya Prihanto, Nazrul Effendy, Nopriadi Nopriadi
Viruses can be transmitted due to various aspects; one spreads through airborne droplets or the touch of multiple objects. This can occur in any area, including the entrance to the house or access to a room or deposit box. The spread of viruses that cause diseases like Covid-19 has caused many human casualties, and there is still the possibility of similar conditions appearing in the future. Several things need to be done to reduce the chances of spreading disease due to viruses, including developing contactless security support methods. This paper proposes a security system using hand gesture recognition using squeeze and excitation residual networks (SE-ResNet). This research offers a hand gesture recognition system for an automatic door system using SE-ResNet and the residual network (ResNet).
{"title":"Hand gesture-based automatic door security system using squeeze and excitation residual networks","authors":"Surya Prihanto, Nazrul Effendy, Nopriadi Nopriadi","doi":"10.11591/ijai.v13.i2.pp1619-1624","DOIUrl":"https://doi.org/10.11591/ijai.v13.i2.pp1619-1624","url":null,"abstract":"Viruses can be transmitted due to various aspects; one spreads through airborne droplets or the touch of multiple objects. This can occur in any area, including the entrance to the house or access to a room or deposit box. The spread of viruses that cause diseases like Covid-19 has caused many human casualties, and there is still the possibility of similar conditions appearing in the future. Several things need to be done to reduce the chances of spreading disease due to viruses, including developing contactless security support methods. This paper proposes a security system using hand gesture recognition using squeeze and excitation residual networks (SE-ResNet). This research offers a hand gesture recognition system for an automatic door system using SE-ResNet and the residual network (ResNet).","PeriodicalId":507934,"journal":{"name":"IAES International Journal of Artificial Intelligence (IJ-AI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141233312","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}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号