Pub Date : 2024-07-01DOI: 10.11591/ijeecs.v35.i1.pp102-112
A. Krismanto, Radimas Putra Muhammad Davi Labib, H. Setiadi, Abraham Lomi, Muhammad Abdillah
Solar tracker widely maximizes solar energy harvesting by maintaining a perpendicular relative position between the sun and the solar panel. Single and dual-axis solar tracker controllers are the most control mechanisms that are widely implemented. The single-axis solar tracker (SAST) is preferable between those two control mechanisms due to economic and simpler control algorithm features. Many control algorithms have been proposed to improve the performance of SAST. The conventional proportional integral derivative (PID) controller has major limitations mainly corresponding to slower response. Moreover, it cannot handle the uncertainties of the sunlight. To overcome the problem, type 2-fuzzy logic control (T2-FLC) is proposed. The single-axis solar tracker controller based on T2-FLC is applied in Arduino and implemented in the hardware environment. It was monitored that the T2-FLC provides much better responses than the conventional controllers in terms of better dynamic response and more efficiency in harvesting solar energy.
{"title":"Hardware implementation of type-2 fuzzy logic control for single axis solar tracker","authors":"A. Krismanto, Radimas Putra Muhammad Davi Labib, H. Setiadi, Abraham Lomi, Muhammad Abdillah","doi":"10.11591/ijeecs.v35.i1.pp102-112","DOIUrl":"https://doi.org/10.11591/ijeecs.v35.i1.pp102-112","url":null,"abstract":"Solar tracker widely maximizes solar energy harvesting by maintaining a perpendicular relative position between the sun and the solar panel. Single and dual-axis solar tracker controllers are the most control mechanisms that are widely implemented. The single-axis solar tracker (SAST) is preferable between those two control mechanisms due to economic and simpler control algorithm features. Many control algorithms have been proposed to improve the performance of SAST. The conventional proportional integral derivative (PID) controller has major limitations mainly corresponding to slower response. Moreover, it cannot handle the uncertainties of the sunlight. To overcome the problem, type 2-fuzzy logic control (T2-FLC) is proposed. The single-axis solar tracker controller based on T2-FLC is applied in Arduino and implemented in the hardware environment. It was monitored that the T2-FLC provides much better responses than the conventional controllers in terms of better dynamic response and more efficiency in harvesting solar energy.","PeriodicalId":13480,"journal":{"name":"Indonesian Journal of Electrical Engineering and Computer Science","volume":"34 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141716101","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 : 2024-07-01DOI: 10.11591/ijeecs.v35.i1.pp301-309
Likitha Gongalla, Monali Bordoloi
Tea, a commonly consumed beverage, is susceptible to being sold in adulterated or expired forms by third-party vendors. Hyperspectral imaging across different wavelength bands has proven to precisely assess the diverse types of tea and their corresponding financial gains. This study aims to employ a deep learning methodology in conjunction with hyperspectral imaging for efficiently classifying tea leaves. A novel approach is proposed, wherein a waveband convolutional neural network is utilized to generate hyper spectral images of tea leaf samples with enhanced resolution. The model known as optimized-convolutional neural network-random forest O- (ConvNet-RF) demonstrated exceptional performance, achieving high accuracy, impressive recall, F1 score, and notable sensitivity rate, outperforming existing alternative methods. The tea leaf types, namely green, yellow, and black, were accurately identified using a combination of the random forest (RF) model and the O-ConvNet-RF model. The tree-based classification method for the identification of tea leaves demonstrated superior performance as compared to alternative machine learning models. In general, this study presents a successful methodology for the classification of tea leaves, with potential implications for consumer processing and distributor profit analysis.
{"title":"Hyperspectral image construction in different spectral bands of tea leafs for identifying the tea type using O-ConvNet-RF model","authors":"Likitha Gongalla, Monali Bordoloi","doi":"10.11591/ijeecs.v35.i1.pp301-309","DOIUrl":"https://doi.org/10.11591/ijeecs.v35.i1.pp301-309","url":null,"abstract":"Tea, a commonly consumed beverage, is susceptible to being sold in adulterated or expired forms by third-party vendors. Hyperspectral imaging across different wavelength bands has proven to precisely assess the diverse types of tea and their corresponding financial gains. This study aims to employ a deep learning methodology in conjunction with hyperspectral imaging for efficiently classifying tea leaves. A novel approach is proposed, wherein a waveband convolutional neural network is utilized to generate hyper spectral images of tea leaf samples with enhanced resolution. The model known as optimized-convolutional neural network-random forest O- (ConvNet-RF) demonstrated exceptional performance, achieving high accuracy, impressive recall, F1 score, and notable sensitivity rate, outperforming existing alternative methods. The tea leaf types, namely green, yellow, and black, were accurately identified using a combination of the random forest (RF) model and the O-ConvNet-RF model. The tree-based classification method for the identification of tea leaves demonstrated superior performance as compared to alternative machine learning models. In general, this study presents a successful methodology for the classification of tea leaves, with potential implications for consumer processing and distributor profit analysis.","PeriodicalId":13480,"journal":{"name":"Indonesian Journal of Electrical Engineering and Computer Science","volume":"17 9","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141698451","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 : 2024-07-01DOI: 10.11591/ijeecs.v35.i1.pp62-69
Gusti Made, Ngurah Desnanjaya, I. Made, Aditya Nugraha
Blood pressure is an important cardiovascular health indicator, with normal values set by the WHO at 140 mmHg for systole and 90 mmHg for diastole. Excess of these values indicates hypertension, which increases the risk of serious medical complications. This research developed an internet of things (IoT)-based blood pressure monitoring device, which facilitates digital blood pressure measurement and data transmission to widely accessible applications and websites. The device uses an MPX5050GP pressure sensor, Arduino Nano, and NodeMCU ESP32, as well as other components programmed using the Arduino IDE. Test results obtained from 10 subjects, the device showed an average difference in systole of 7.9 mmHg and diastole of 5.4 mmHg. This complies with recognized accuracy standards of a maximum error of 10 mmHg and indicates that the device operates effectively with the designed concept.
{"title":"Real-time monitoring system for blood pressure monitoring based on internet of things","authors":"Gusti Made, Ngurah Desnanjaya, I. Made, Aditya Nugraha","doi":"10.11591/ijeecs.v35.i1.pp62-69","DOIUrl":"https://doi.org/10.11591/ijeecs.v35.i1.pp62-69","url":null,"abstract":"Blood pressure is an important cardiovascular health indicator, with normal values set by the WHO at 140 mmHg for systole and 90 mmHg for diastole. Excess of these values indicates hypertension, which increases the risk of serious medical complications. This research developed an internet of things (IoT)-based blood pressure monitoring device, which facilitates digital blood pressure measurement and data transmission to widely accessible applications and websites. The device uses an MPX5050GP pressure sensor, Arduino Nano, and NodeMCU ESP32, as well as other components programmed using the Arduino IDE. Test results obtained from 10 subjects, the device showed an average difference in systole of 7.9 mmHg and diastole of 5.4 mmHg. This complies with recognized accuracy standards of a maximum error of 10 mmHg and indicates that the device operates effectively with the designed concept.","PeriodicalId":13480,"journal":{"name":"Indonesian Journal of Electrical Engineering and Computer Science","volume":"283 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141711423","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 : 2024-07-01DOI: 10.11591/ijeecs.v35.i1.pp520-541
Usman Tariq, Irfan Ahmed, Muhammad Attique Khan, Ali Kashif Bashir
Deep learning (DL) is increasingly recognized for its effectiveness in analyzing and forecasting complex economic systems, particularly in the context of Pakistan's evolving economy. This paper investigates DL's transformative role in managing and interpreting increasing volumes of intricate economic data, leading to more nuanced insights. DL models show a marked improvement in predictive accuracy and depth over traditional methods across various economic domains and policymaking scenarios. Applications include demand forecasting, risk evaluation, market trend analysis, and resource allocation optimization. These processes utilize extensive datasets and advanced algorithms to identify patterns that traditional methods cannot detect. Nonetheless, DL's broader application in economic research faces challenges like limited data availability, complexity of economic interactions, interpretability of model outputs, and significant computational power requirements. The paper outlines strategies to overcome these barriers, such as enhancing model interpretability, employing federated learning for better data privacy, and integrating behavioral and social economic theories. It concludes by stressing the importance of targeted research and ethical considerations in maximizing DL's impact on economic insights and innovation, particularly in Pakistan and globally.
{"title":"Deep learning for economic transformation: a parametric review","authors":"Usman Tariq, Irfan Ahmed, Muhammad Attique Khan, Ali Kashif Bashir","doi":"10.11591/ijeecs.v35.i1.pp520-541","DOIUrl":"https://doi.org/10.11591/ijeecs.v35.i1.pp520-541","url":null,"abstract":"Deep learning (DL) is increasingly recognized for its effectiveness in analyzing and forecasting complex economic systems, particularly in the context of Pakistan's evolving economy. This paper investigates DL's transformative role in managing and interpreting increasing volumes of intricate economic data, leading to more nuanced insights. DL models show a marked improvement in predictive accuracy and depth over traditional methods across various economic domains and policymaking scenarios. Applications include demand forecasting, risk evaluation, market trend analysis, and resource allocation optimization. These processes utilize extensive datasets and advanced algorithms to identify patterns that traditional methods cannot detect. Nonetheless, DL's broader application in economic research faces challenges like limited data availability, complexity of economic interactions, interpretability of model outputs, and significant computational power requirements. The paper outlines strategies to overcome these barriers, such as enhancing model interpretability, employing federated learning for better data privacy, and integrating behavioral and social economic theories. It concludes by stressing the importance of targeted research and ethical considerations in maximizing DL's impact on economic insights and innovation, particularly in Pakistan and globally.","PeriodicalId":13480,"journal":{"name":"Indonesian Journal of Electrical Engineering and Computer Science","volume":"101 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141713583","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 : 2024-07-01DOI: 10.11591/ijeecs.v35.i1.pp203-212
Eva Shayo, Abdi T. Abdalla, A. Mwambela, Tole Sutikno
In recent years, long-range wide-area networks (LoRaWAN) have gained much attention as low-power wide-area networks. LoRaWAN uses ALOHA as the medium access control protocol, where the end devices transmit data randomly and retransmit it up to eight times if collisions occur. ALOHA is not energy efficient and works perfectly for a smaller network. Several techniques, including the use of synchronization and scheduling schemes, to deal with the limitations imposed by ALOHA in LoRaWAN have been reported in the literature. However, the existing synchronization and scheduling algorithms transmit synchronization messages randomly using one super frame with fixed time slots that accommodate devices using different spreading factors, which limit the LoRaWAN network's scalability. This work proposes a slotted synchronization mechanism for transmitting synchronization requests to the gateway. The performance of the slotted synchronization was evaluated through simulation using packet delivery ratio (PDR) and energy efficiency as the performance parameters. The results indicate that when the number of devices in the network increases, a time-slotted synchronization consumes less energy, on average, by about 0.2 mAh. The use of a slotted synchronization can improve the energy efficiency of the end devices as collisions are completely avoided, achieving a PDR of 100%.
{"title":"Energy efficient slotted synchronization approach in LoRaWAN","authors":"Eva Shayo, Abdi T. Abdalla, A. Mwambela, Tole Sutikno","doi":"10.11591/ijeecs.v35.i1.pp203-212","DOIUrl":"https://doi.org/10.11591/ijeecs.v35.i1.pp203-212","url":null,"abstract":"In recent years, long-range wide-area networks (LoRaWAN) have gained much attention as low-power wide-area networks. LoRaWAN uses ALOHA as the medium access control protocol, where the end devices transmit data randomly and retransmit it up to eight times if collisions occur. ALOHA is not energy efficient and works perfectly for a smaller network. Several techniques, including the use of synchronization and scheduling schemes, to deal with the limitations imposed by ALOHA in LoRaWAN have been reported in the literature. However, the existing synchronization and scheduling algorithms transmit synchronization messages randomly using one super frame with fixed time slots that accommodate devices using different spreading factors, which limit the LoRaWAN network's scalability. This work proposes a slotted synchronization mechanism for transmitting synchronization requests to the gateway. The performance of the slotted synchronization was evaluated through simulation using packet delivery ratio (PDR) and energy efficiency as the performance parameters. The results indicate that when the number of devices in the network increases, a time-slotted synchronization consumes less energy, on average, by about 0.2 mAh. The use of a slotted synchronization can improve the energy efficiency of the end devices as collisions are completely avoided, achieving a PDR of 100%.","PeriodicalId":13480,"journal":{"name":"Indonesian Journal of Electrical Engineering and Computer Science","volume":"164 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141694921","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 : 2024-07-01DOI: 10.11591/ijeecs.v35.i1.pp78-89
Elber E. Canto-Vivanco, Sebastian Ramos-Cosi, Victor N. Romero-Alva, N. Vargas-Cuentas, A. Roman-Gonzalez
This research aims to address the need for monitoring the behavior of organic and inorganic materials in hypergravity conditions. To fulfill this objective, a container with specific features was designed. The container has a box with a lid, measuring 10×10×10 cm, conforming to the 1U volume of the CubeSat standard. It includes four cylindrical spaces to accommodate the sample wells. The container was 3D printed using polylactic acid (PLA) wire. For the electronic components, four ESP32-CAM modules were utilized, with two programmed to capture and upload photos to the cloud, and the other two programmed to capture and store photos on a micro SD memory card. Additionally, four light emitting diodes (LEDs) were incorporated to illuminate the well spaces. The total weight of the container is 450 grams, and it has a maximum wireless upload distance of 10 meters to the cloud. The storage capacity of the SD memory card determines the number of images that can be saved.
{"title":"Development of a payload for monitoring biological samples in microgravity and hypergravity conditions","authors":"Elber E. Canto-Vivanco, Sebastian Ramos-Cosi, Victor N. Romero-Alva, N. Vargas-Cuentas, A. Roman-Gonzalez","doi":"10.11591/ijeecs.v35.i1.pp78-89","DOIUrl":"https://doi.org/10.11591/ijeecs.v35.i1.pp78-89","url":null,"abstract":"This research aims to address the need for monitoring the behavior of organic and inorganic materials in hypergravity conditions. To fulfill this objective, a container with specific features was designed. The container has a box with a lid, measuring 10×10×10 cm, conforming to the 1U volume of the CubeSat standard. It includes four cylindrical spaces to accommodate the sample wells. The container was 3D printed using polylactic acid (PLA) wire. For the electronic components, four ESP32-CAM modules were utilized, with two programmed to capture and upload photos to the cloud, and the other two programmed to capture and store photos on a micro SD memory card. Additionally, four light emitting diodes (LEDs) were incorporated to illuminate the well spaces. The total weight of the container is 450 grams, and it has a maximum wireless upload distance of 10 meters to the cloud. The storage capacity of the SD memory card determines the number of images that can be saved.","PeriodicalId":13480,"journal":{"name":"Indonesian Journal of Electrical Engineering and Computer Science","volume":"85 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141697509","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 : 2024-07-01DOI: 10.11591/ijeecs.v35.i1.pp655-664
L. N. Amali, Muhammad Rifai Katili, Alif Perdana Sugeha
This paper describes virtual reality (VR) development using a 360-degree panoramic and Leaflet JavaScript (Leaflet JS) to introduce campus buildings in real-time. The campus building of Universitas Negeri Gorontalo (UNG) in Bone Bolango Regency was chosen as a case study. It allows users to navigate and listen to background sound and narration, open the site map interactively, and read brief information about each location. Each panorama contains hotspots that allow users to explore further. All images are combined using a photo-stitching technique to produce a panoramic image. The research method used is the multimedia development life cycle (MDLC), which consists of six stages: concept, design, material collection, assembly, testing, and distribution. Based on the system usability scale (SUS) test, the virtual tour reality website application received feedback from users regarding its usability, satisfaction, and effectiveness, and it is interesting to use this application. The results show that the website application can visualize the campus building environment with various layers of information and can create a very realistic and detailed representation of the campus environment.
本文介绍了利用 360 度全景和传单 JavaScript（Leaflet JS）实时介绍校园建筑的虚拟现实（VR）开发。本文选择了位于 Bone Bolango Regency 的戈伦塔洛国立大学（UNG）的校园建筑作为案例研究。它允许用户进行导航，聆听背景声音和旁白，交互式打开网站地图，并阅读每个地点的简要信息。每个全景图都包含热点，用户可以进一步探索。所有图像均采用照片拼接技术合成全景图像。采用的研究方法是多媒体开发生命周期（MDLC），包括六个阶段：概念、设计、材料收集、组装、测试和发布。根据系统可用性量表（SUS）测试，虚拟游览现实网站应用程序在可用性、满意度和有效性方面得到了用户的反馈，用户对使用该应用程序很感兴趣。结果表明，该网站应用程序可以将校园建筑环境的各层信息可视化，并能非常逼真、详细地再现校园环境。
{"title":"Development of virtual tour reality using 360-degree panoramic images and Leaflet JavaScript","authors":"L. N. Amali, Muhammad Rifai Katili, Alif Perdana Sugeha","doi":"10.11591/ijeecs.v35.i1.pp655-664","DOIUrl":"https://doi.org/10.11591/ijeecs.v35.i1.pp655-664","url":null,"abstract":"This paper describes virtual reality (VR) development using a 360-degree panoramic and Leaflet JavaScript (Leaflet JS) to introduce campus buildings in real-time. The campus building of Universitas Negeri Gorontalo (UNG) in Bone Bolango Regency was chosen as a case study. It allows users to navigate and listen to background sound and narration, open the site map interactively, and read brief information about each location. Each panorama contains hotspots that allow users to explore further. All images are combined using a photo-stitching technique to produce a panoramic image. The research method used is the multimedia development life cycle (MDLC), which consists of six stages: concept, design, material collection, assembly, testing, and distribution. Based on the system usability scale (SUS) test, the virtual tour reality website application received feedback from users regarding its usability, satisfaction, and effectiveness, and it is interesting to use this application. The results show that the website application can visualize the campus building environment with various layers of information and can create a very realistic and detailed representation of the campus environment.","PeriodicalId":13480,"journal":{"name":"Indonesian Journal of Electrical Engineering and Computer Science","volume":"13 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141700614","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 : 2024-07-01DOI: 10.11591/ijeecs.v35.i1.pp620-630
Andien Dwi Novika, A. S. Girsang
This study introduces an innovative hyperparameter optimization approach for enhancing multilayer perceptrons (MLP) using the Jaya algorithm. Addressing the crucial role of hyperparameter tuning in MLP’s performance, the Jaya algorithm, inspired by social behavior, emerges as a promising optimization technique without algorithm-specific parameters. Systematic application of Jaya dynamically adjusts hyperparameter values, leading to notable improvements in convergence speeds and model generalization. Quantitatively, the Jaya algorithm consistently achieves convergences at first iteration, faster convergence compared to conventional methods, resulting in 7% higher accuracy levels on several datasets. This research contributes to hyperparameter optimization, offering a practical and effective solution for optimizing MLP in diverse applications, with implications for improved computational efficiency and model performance.
{"title":"Multi-layer perceptron hyperparameter optimization using Jaya algorithm for disease classification","authors":"Andien Dwi Novika, A. S. Girsang","doi":"10.11591/ijeecs.v35.i1.pp620-630","DOIUrl":"https://doi.org/10.11591/ijeecs.v35.i1.pp620-630","url":null,"abstract":"This study introduces an innovative hyperparameter optimization approach for enhancing multilayer perceptrons (MLP) using the Jaya algorithm. Addressing the crucial role of hyperparameter tuning in MLP’s performance, the Jaya algorithm, inspired by social behavior, emerges as a promising optimization technique without algorithm-specific parameters. Systematic application of Jaya dynamically adjusts hyperparameter values, leading to notable improvements in convergence speeds and model generalization. Quantitatively, the Jaya algorithm consistently achieves convergences at first iteration, faster convergence compared to conventional methods, resulting in 7% higher accuracy levels on several datasets. This research contributes to hyperparameter optimization, offering a practical and effective solution for optimizing MLP in diverse applications, with implications for improved computational efficiency and model performance.","PeriodicalId":13480,"journal":{"name":"Indonesian Journal of Electrical Engineering and Computer Science","volume":"18 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141703003","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 : 2024-07-01DOI: 10.11591/ijeecs.v35.i1.pp542-550
Rabie Madani, Abderrahmane Ez-Zahout, F. Omary
Recommender systems (RS) primarily rely on user feedback as a core foundation for making recommendations. Traditional recommenders predominantly rely on historical data, which often presents challenges due to data scarcity issues. Despite containing a substantial wealth of valuable and comprehensive knowledge, user reviews remain largely overlooked by many existing recommender systems. Within these reviews, there lies an opportunity to extract valuable insights, including user preferences and contextual information, which could be seamlessly integrated into recommender systems to significantly enhance the accuracy of the recommendations they provide. This paper introduces an innovative approach to building context-aware RS, spanning from data extraction to ratings prediction. Our approach revolves around three essential components. The first component involves corpus creation, leveraging Dbpedia as a data source. The second component encompasses a tailored named entity recognition (NER) mechanism for the extraction of contextual data. This NER system harnesses the power of advanced models such as bidirectional encoder representations from transformers (BERT), bidirectional long short term memory (Bi-LSTM), and bidirectional conditional random field (Bi-CRF). The final component introduces a novel variation of factorization machines for the prediction of ratings called contextual factorization machines. Our experimental results showcase robust performance in both the contextual data extraction phase and the ratings prediction phase, surpassing the capabilities of existing state-of-the-art methods. These findings underscore the significant potential of our approach to elevate the quality of recommendations within the realm of context-aware recommender systems.
推荐系统（RS）主要依靠用户反馈作为推荐的核心基础。传统的推荐器主要依赖历史数据，这往往会因数据稀缺问题而带来挑战。尽管用户评论蕴含着大量宝贵而全面的知识，但许多现有的推荐系统在很大程度上仍然忽视了用户评论。在这些评论中，存在着提取宝贵见解的机会，包括用户偏好和上下文信息，这些见解可以无缝集成到推荐系统中，从而大大提高推荐的准确性。本文介绍了一种构建情境感知 RS 的创新方法，涵盖从数据提取到评分预测的各个环节。我们的方法围绕三个基本组成部分展开。第一部分是利用 Dbpedia 作为数据源创建语料库。第二部分包括一个定制的命名实体识别（NER）机制，用于提取上下文数据。该 NER 系统利用了先进模型的力量，如双向变压器编码器表示（BERT）、双向长短期记忆（Bi-LSTM）和双向条件随机场（Bi-CRF）。最后一个部分引入了一种新的因式分解机变体，用于预测评分，称为上下文因式分解机。我们的实验结果表明，情境数据提取阶段和评分预测阶段的性能都很强劲，超过了现有最先进方法的能力。这些发现凸显了我们的方法在提高情境感知推荐系统的推荐质量方面的巨大潜力。
{"title":"Extracting contextual insights from user reviews for recommender systems: a novel method","authors":"Rabie Madani, Abderrahmane Ez-Zahout, F. Omary","doi":"10.11591/ijeecs.v35.i1.pp542-550","DOIUrl":"https://doi.org/10.11591/ijeecs.v35.i1.pp542-550","url":null,"abstract":"Recommender systems (RS) primarily rely on user feedback as a core foundation for making recommendations. Traditional recommenders predominantly rely on historical data, which often presents challenges due to data scarcity issues. Despite containing a substantial wealth of valuable and comprehensive knowledge, user reviews remain largely overlooked by many existing recommender systems. Within these reviews, there lies an opportunity to extract valuable insights, including user preferences and contextual information, which could be seamlessly integrated into recommender systems to significantly enhance the accuracy of the recommendations they provide. This paper introduces an innovative approach to building context-aware RS, spanning from data extraction to ratings prediction. Our approach revolves around three essential components. The first component involves corpus creation, leveraging Dbpedia as a data source. The second component encompasses a tailored named entity recognition (NER) mechanism for the extraction of contextual data. This NER system harnesses the power of advanced models such as bidirectional encoder representations from transformers (BERT), bidirectional long short term memory (Bi-LSTM), and bidirectional conditional random field (Bi-CRF). The final component introduces a novel variation of factorization machines for the prediction of ratings called contextual factorization machines. Our experimental results showcase robust performance in both the contextual data extraction phase and the ratings prediction phase, surpassing the capabilities of existing state-of-the-art methods. These findings underscore the significant potential of our approach to elevate the quality of recommendations within the realm of context-aware recommender systems.","PeriodicalId":13480,"journal":{"name":"Indonesian Journal of Electrical Engineering and Computer Science","volume":"40 12","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141709788","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 : 2024-07-01DOI: 10.11591/ijeecs.v35.i1.pp583-592
Fikri Budiman, E. Sugiarto, Novi Hendriyanto
Image retrieval methods are currently developing towards big data processing. The literature review is focused on image big data extraction with cultural heritage domain as training and testing datasets. The development of image retrieval process starts from content-based using machine algorithms, deep learning to ontology-based. Image recognition research with cultural heritage domain is conducted because of the importance of preserving and appreciating cultural heritage, in this case, cultural heritage images such as Indonesian Batik are discussed. Batik motif images are Indonesian cultural heritage that has thousands of motifs that are grouped into many classes with a non-linear hyperplane. The problem is focused on processing big data that has many classes. Currently research is evolving into knowledge-based image retrieval using ontologies due to semantic gap constraints. The results of this literature study can be the basis for developing research on the application of appropriate deep learning algorithms so as to utilize the hierarchy of classes and subclasses of image ontologies with cultural heritage domains.
{"title":"Review on integration of ontology and deep learning in cultural heritage image retrieval","authors":"Fikri Budiman, E. Sugiarto, Novi Hendriyanto","doi":"10.11591/ijeecs.v35.i1.pp583-592","DOIUrl":"https://doi.org/10.11591/ijeecs.v35.i1.pp583-592","url":null,"abstract":"Image retrieval methods are currently developing towards big data processing. The literature review is focused on image big data extraction with cultural heritage domain as training and testing datasets. The development of image retrieval process starts from content-based using machine algorithms, deep learning to ontology-based. Image recognition research with cultural heritage domain is conducted because of the importance of preserving and appreciating cultural heritage, in this case, cultural heritage images such as Indonesian Batik are discussed. Batik motif images are Indonesian cultural heritage that has thousands of motifs that are grouped into many classes with a non-linear hyperplane. The problem is focused on processing big data that has many classes. Currently research is evolving into knowledge-based image retrieval using ontologies due to semantic gap constraints. The results of this literature study can be the basis for developing research on the application of appropriate deep learning algorithms so as to utilize the hierarchy of classes and subclasses of image ontologies with cultural heritage domains.","PeriodicalId":13480,"journal":{"name":"Indonesian Journal of Electrical Engineering and Computer Science","volume":"28 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141713890","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：