Pub Date : 2024-07-01DOI: 10.11591/ijeecs.v35.i1.pp156-164
R. N. Amarnath, Gurumoorthi Gurulakshmanan
Gradient boosting machines harnesses the inherent capabilities of decision trees and meticulously corrects their errors in a sequential fashion, culminating in remarkably precise predictions. Word2Vec, a prominent word embedding technique, occupies a pivotal role in natural language processing (NLP) tasks. Its proficiency lies in capturing intricate semantic relationships among words, thereby facilitating applications such as sentiment analysis, document classification, and machine translation to discern subtle nuances present in textual data. Bayesian networks introduce probabilistic modeling capabilities, predominantly in contexts marked by uncertainty. Their versatile applications encompass risk assessment, fault diagnosis, and recommendation systems. Gated recurrent units (GRU), a variant of recurrent neural networks, emerges as a formidable asset in modeling sequential data. Both training and testing are crucial to the success of an intrusion detection system (IDS). During the training phase, several models are created, each of which can recognize typical from anomalous patterns within a given dataset. To acquire passwords and credit card details, "phishing" usually entails impersonating a trusted company. Predictions of student performance on academic tasks are improved by hyper parameter optimization of the gradient boosting regression tree using the grid search approach.
{"title":"Cloud-based machine learning algorithms for anomalies detection","authors":"R. N. Amarnath, Gurumoorthi Gurulakshmanan","doi":"10.11591/ijeecs.v35.i1.pp156-164","DOIUrl":"https://doi.org/10.11591/ijeecs.v35.i1.pp156-164","url":null,"abstract":"Gradient boosting machines harnesses the inherent capabilities of decision trees and meticulously corrects their errors in a sequential fashion, culminating in remarkably precise predictions. Word2Vec, a prominent word embedding technique, occupies a pivotal role in natural language processing (NLP) tasks. Its proficiency lies in capturing intricate semantic relationships among words, thereby facilitating applications such as sentiment analysis, document classification, and machine translation to discern subtle nuances present in textual data. Bayesian networks introduce probabilistic modeling capabilities, predominantly in contexts marked by uncertainty. Their versatile applications encompass risk assessment, fault diagnosis, and recommendation systems. Gated recurrent units (GRU), a variant of recurrent neural networks, emerges as a formidable asset in modeling sequential data. Both training and testing are crucial to the success of an intrusion detection system (IDS). During the training phase, several models are created, each of which can recognize typical from anomalous patterns within a given dataset. To acquire passwords and credit card details, \"phishing\" usually entails impersonating a trusted company. Predictions of student performance on academic tasks are improved by hyper parameter optimization of the gradient boosting regression tree using the grid search approach.","PeriodicalId":13480,"journal":{"name":"Indonesian Journal of Electrical Engineering and Computer Science","volume":"135 36","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141714153","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.pp631-641
Mohamed Halim, Abdelmajid Tahiri, Yassir El Ghzizal, N. Adadi, D. Chenouni
Service-oriented computing (SOC) provides a new framework for designing distributed web applications and software in a flexible, scalable, and cost-effective manner. Its use is widespread to efficiently integrate existing Web services and create high value-added applications. This model, proven in various fields such as e-commerce, also shows significant advantages in the field of e-learning. This approach highlights the discovery and use of Web services listed in specialized directories. In fact, this paper proposes a framework for exploring web services associated with education. This approach is based on the application of a matching algorithm to select the services best suited to the needs of users of the online learning system, as well as the ontology of the e-learning domain and the semantic descriptions of the web services via web ontology language for web services (OWL-S).
{"title":"Proposal for an e-learning system model based on the invocation and semantic discovery of web services","authors":"Mohamed Halim, Abdelmajid Tahiri, Yassir El Ghzizal, N. Adadi, D. Chenouni","doi":"10.11591/ijeecs.v35.i1.pp631-641","DOIUrl":"https://doi.org/10.11591/ijeecs.v35.i1.pp631-641","url":null,"abstract":"Service-oriented computing (SOC) provides a new framework for designing distributed web applications and software in a flexible, scalable, and cost-effective manner. Its use is widespread to efficiently integrate existing Web services and create high value-added applications. This model, proven in various fields such as e-commerce, also shows significant advantages in the field of e-learning. This approach highlights the discovery and use of Web services listed in specialized directories. In fact, this paper proposes a framework for exploring web services associated with education. This approach is based on the application of a matching algorithm to select the services best suited to the needs of users of the online learning system, as well as the ontology of the e-learning domain and the semantic descriptions of the web services via web ontology language for web services (OWL-S).","PeriodicalId":13480,"journal":{"name":"Indonesian Journal of Electrical Engineering and Computer Science","volume":"22 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141715298","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.pp255-262
Mohamed Taj Bennani, Abdelali Zbakh, Mohamed El Far, Mohamed Lamrini, Outman El Hichami, Khalid El Fahssi, Hassan Satori
In the last years, The CMOS was developed and miniaturized rapidly, which, made sensors very fast, small and accurate. Hence, the creation of wireless sensor network (WSN) which are a network of nodes that exchange the data between them until it reaches the sink (base station). It is responsible for treating the data and transfer them to other servers linked to the internet for further treatment or storage. Therefore, everything related to WSN is a big topic of research for scientific community, especially transferring scalar data. In fact, many factors enter into account when it comes to send data like a radio, range of transmission, energy consumption and routing protocol. Routing protocols are very important in transferring data. They also have a big impact on energy consumption by nodes. Many categories of routing protocols exist: planning and level routing. Each type has its strength and weakness points. So, using a routing protocol in high-density environments is very challenging in energy consumption and data delivery. In addition, since level routing protocols like Leach are known for their energy efficiency. We choose three level routing protocol (Leach, MLD-Leach and MRE-Leach) to put them in a harsh environment to test their energy consumption and data transferring. We found that MLD-Leach has better energy consumption and data delivery.
{"title":"Comparing Leach protocol and its descendants on transferring scalar data","authors":"Mohamed Taj Bennani, Abdelali Zbakh, Mohamed El Far, Mohamed Lamrini, Outman El Hichami, Khalid El Fahssi, Hassan Satori","doi":"10.11591/ijeecs.v35.i1.pp255-262","DOIUrl":"https://doi.org/10.11591/ijeecs.v35.i1.pp255-262","url":null,"abstract":"In the last years, The CMOS was developed and miniaturized rapidly, which, made sensors very fast, small and accurate. Hence, the creation of wireless sensor network (WSN) which are a network of nodes that exchange the data between them until it reaches the sink (base station). It is responsible for treating the data and transfer them to other servers linked to the internet for further treatment or storage. Therefore, everything related to WSN is a big topic of research for scientific community, especially transferring scalar data. In fact, many factors enter into account when it comes to send data like a radio, range of transmission, energy consumption and routing protocol. Routing protocols are very important in transferring data. They also have a big impact on energy consumption by nodes. Many categories of routing protocols exist: planning and level routing. Each type has its strength and weakness points. So, using a routing protocol in high-density environments is very challenging in energy consumption and data delivery. In addition, since level routing protocols like Leach are known for their energy efficiency. We choose three level routing protocol (Leach, MLD-Leach and MRE-Leach) to put them in a harsh environment to test their energy consumption and data transferring. We found that MLD-Leach has better energy consumption and data delivery.","PeriodicalId":13480,"journal":{"name":"Indonesian Journal of Electrical Engineering and Computer Science","volume":"21 13","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141704006","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/ijeecs.v34.i3.pp1879-1892
Stepan Vyazigin, Madina Mansurova, Victor Malyshkin, Aygul Shaykhulova
This study examines a modified approach to optimizing the performance of support vector machine (SVM)-type multicomputer systems through a distinct type of caching method that allocates space in the random access memory (RAM) of a computing node for caching pages. The article extensively describes research on enhancing the performance of the SVM system through memory page caching in RAM at the hardware level by implementing the SVM system based on field-programmable gate arrays (FPGA). A systematic comparative evaluation highlights a discernible enhancement in system performance relative to systems not equipped with the revised caching algorithm. These findings could prove instrumental for subsequent studies focused on optimizing the performance of SVM systems, providing empirical data to inform future investigations and potential applications in multicomputer system performance enhancement.
{"title":"Random access memory page caching: a strategy for enhancing shared virtual memory multicomputer systems performance","authors":"Stepan Vyazigin, Madina Mansurova, Victor Malyshkin, Aygul Shaykhulova","doi":"10.11591/ijeecs.v34.i3.pp1879-1892","DOIUrl":"https://doi.org/10.11591/ijeecs.v34.i3.pp1879-1892","url":null,"abstract":"This study examines a modified approach to optimizing the performance of support vector machine (SVM)-type multicomputer systems through a distinct type of caching method that allocates space in the random access memory (RAM) of a computing node for caching pages. The article extensively describes research on enhancing the performance of the SVM system through memory page caching in RAM at the hardware level by implementing the SVM system based on field-programmable gate arrays (FPGA). A systematic comparative evaluation highlights a discernible enhancement in system performance relative to systems not equipped with the revised caching algorithm. These findings could prove instrumental for subsequent studies focused on optimizing the performance of SVM systems, providing empirical data to inform future investigations and potential applications in multicomputer system performance enhancement.","PeriodicalId":13480,"journal":{"name":"Indonesian Journal of Electrical Engineering and Computer Science","volume":"15 20","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141233431","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/ijeecs.v34.i3.pp1953-1964
D. Baigereyev, S. Kasenov, L. Temirbekova
This research is devoted to the development of a geographic information system (GIS) for the analysis of geological data. It presents two specialized software modules designed to solve complex geological problems related to potential progress to disturbed masses and magnetotelluric sounding. These modules are integrated into the QGIS environment, offering efficient data processing and analysis capabilities, contributing to a deeper understanding of geological structures. The study presents a mathematical model for the problem of magnetotelluric sounding (MTS) and the continuation of potentials towards the perturbed masses, demonstrating numerical results using the developed algorithm. To confirm the accuracy of the model, a comparative analysis was carried out with empirical data for various chemical elements, which showed high accuracy, especially at shallow depths, with an error rate of less than 2%. In addition, the study highlights the importance of powerful GIS for the analysis and interpretation of geological data, including geochemical, geophysical and remote sensing information. The advanced functionality of QGIS simplifies data processing and visualization, which makes it an invaluable tool for geologists and researchers.
{"title":"Empowering geological data analysis with specialized software GIS modules","authors":"D. Baigereyev, S. Kasenov, L. Temirbekova","doi":"10.11591/ijeecs.v34.i3.pp1953-1964","DOIUrl":"https://doi.org/10.11591/ijeecs.v34.i3.pp1953-1964","url":null,"abstract":"This research is devoted to the development of a geographic information system (GIS) for the analysis of geological data. It presents two specialized software modules designed to solve complex geological problems related to potential progress to disturbed masses and magnetotelluric sounding. These modules are integrated into the QGIS environment, offering efficient data processing and analysis capabilities, contributing to a deeper understanding of geological structures. The study presents a mathematical model for the problem of magnetotelluric sounding (MTS) and the continuation of potentials towards the perturbed masses, demonstrating numerical results using the developed algorithm. To confirm the accuracy of the model, a comparative analysis was carried out with empirical data for various chemical elements, which showed high accuracy, especially at shallow depths, with an error rate of less than 2%. In addition, the study highlights the importance of powerful GIS for the analysis and interpretation of geological data, including geochemical, geophysical and remote sensing information. The advanced functionality of QGIS simplifies data processing and visualization, which makes it an invaluable tool for geologists and researchers.","PeriodicalId":13480,"journal":{"name":"Indonesian Journal of Electrical Engineering and Computer Science","volume":"17 11","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141229962","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/ijeecs.v34.i3.pp1944-1952
Praveen Kumar, Mira Rakhimzhanova, S. Rawat, Alibek Orynbek, Vikas Kamra
Since the outbreak, the novel coronavirus (COVID-19) has infected more than 180 million people and has taken a toll of 3.91 million lives globally as of June 2021. This virus causes symptoms like fever, cold, and fatigue, and can develop into Pneumonia which can be detected using chest X-rays (CXRs). Therefore, early detection of COVID-19 can help get early medical attention. However, a sudden rise in the number of cases in many countries caused by COVID waves increases the burden on their testing facilities. As a result, they sometimes fail to perform enough testing to contain the spread. This work proposes a deep learning model to detect COVID-19 and Pneumonia based on CXRs. The dataset for our COVID model contains a total of 3,400 CXRs images of COVID-19 patients and 3,400 normal CXRs. The dataset for our Pneumonia model contains 1,300 CXR images of Pneumonia patients and 1,300 normal CXRs. We use convolutional neural network provided by TensorFlow to build our model, which gave 94.17% and 93.55% accuracy for COVID model and Pneumonia model, respectively. Finally, we deployed our model on the web and added a web tracker, which gives us the cases, deaths, and recoveries state-wise and nationwide.
{"title":"Deep learning based COVID and Pneumonia detection using chest X-ray","authors":"Praveen Kumar, Mira Rakhimzhanova, S. Rawat, Alibek Orynbek, Vikas Kamra","doi":"10.11591/ijeecs.v34.i3.pp1944-1952","DOIUrl":"https://doi.org/10.11591/ijeecs.v34.i3.pp1944-1952","url":null,"abstract":"Since the outbreak, the novel coronavirus (COVID-19) has infected more than 180 million people and has taken a toll of 3.91 million lives globally as of June 2021. This virus causes symptoms like fever, cold, and fatigue, and can develop into Pneumonia which can be detected using chest X-rays (CXRs). Therefore, early detection of COVID-19 can help get early medical attention. However, a sudden rise in the number of cases in many countries caused by COVID waves increases the burden on their testing facilities. As a result, they sometimes fail to perform enough testing to contain the spread. This work proposes a deep learning model to detect COVID-19 and Pneumonia based on CXRs. The dataset for our COVID model contains a total of 3,400 CXRs images of COVID-19 patients and 3,400 normal CXRs. The dataset for our Pneumonia model contains 1,300 CXR images of Pneumonia patients and 1,300 normal CXRs. We use convolutional neural network provided by TensorFlow to build our model, which gave 94.17% and 93.55% accuracy for COVID model and Pneumonia model, respectively. Finally, we deployed our model on the web and added a web tracker, which gives us the cases, deaths, and recoveries state-wise and nationwide.","PeriodicalId":13480,"journal":{"name":"Indonesian Journal of Electrical Engineering and Computer Science","volume":"59 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141231621","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/ijeecs.v34.i3.pp1410-1419
Dwayne Jensen Reddy, Ian Joseph Lazarus
This study investigated the fabrication and characterization of CH3NH3PbI3 based perovskite solar cells (PSCs) using the one-step spin coating technique under ambient conditions, eliminating the need for expensive glovebox and thermal evaporation equipment. The perovskite layer was annealed at 65 °C for 30 seconds and 100 °C for 30 seconds, 1 and 2 minutes. The scanning electron microscope (SEM) images show a smooth and uniform surface coverage for the ETL and CH3NH3PbI3 layers. SEM results also show an average grain size of 397 nm for CH3NH3PbI3 and an average particle size of ~17 nm for TiO2 was confirmed by transmission electron microscopy (TEM). X-ray diffraction (XRD) results confirmed the formation of tetragonal perovskite (CH3NH3PbI3) phase with high crystallinity with a crystallite size of 19.99 nm for the samples annealed for 30 seconds at 65 °C and 1 min at 100 °C. FTIR results also confirmed the presence of anatase TiO2 at wavenumber 438 cm-1 and the formation of the adduct of Pb2 with dimethyl sulfoxide (DMSO) and MAI is confirmed at 1,015 cm-1 . From the Tauc plot the bandgap energy of TiO2 and Perovskite layers was determined to be 3.52 eV and 2.06 eV respectively. An open-circuit voltage was 0.9057 V and short circuit current density was 12.2185 mA/cm2 with a fill factor of 48.05 and power conversion efficiency (PCE) of 5.199%.
{"title":"Fabrication and characterization of methylammonium lead iodide-based perovskite solar cells under ambient conditions","authors":"Dwayne Jensen Reddy, Ian Joseph Lazarus","doi":"10.11591/ijeecs.v34.i3.pp1410-1419","DOIUrl":"https://doi.org/10.11591/ijeecs.v34.i3.pp1410-1419","url":null,"abstract":"<p>This study investigated the fabrication and characterization of CH<sub>3</sub>NH<sub>3</sub>PbI<sub>3</sub> based perovskite solar cells (PSCs) using the one-step spin coating technique under ambient conditions, eliminating the need for expensive glovebox and thermal evaporation equipment. The perovskite layer was annealed at 65 °C for 30 seconds and 100 °C for 30 seconds, 1 and 2 minutes. The scanning electron microscope (SEM) images show a smooth and uniform surface coverage for the ETL and CH<sub>3</sub>NH<sub>3</sub>PbI<sub>3</sub> layers. SEM results also show an average grain size of 397 nm for CH<sub>3</sub>NH<sub>3</sub>PbI<sub>3</sub> and an average particle size of ~17 nm for TiO<sub>2</sub> was confirmed by transmission electron microscopy (TEM). X-ray diffraction (XRD) results confirmed the formation of tetragonal perovskite (CH<sub>3</sub>NH<sub>3</sub>PbI<sub>3</sub>) phase with high crystallinity with a crystallite size of 19.99 nm for the samples annealed for 30 seconds at 65 °C and 1 min at 100 °C. FTIR results also confirmed the presence of anatase TiO2 at wavenumber 438 cm<sup>-1</sup> and the formation of the adduct of Pb<sub>2</sub> with dimethyl sulfoxide (DMSO) and MAI is confirmed at 1,015 cm<sup>-1</sup> . From the Tauc plot the bandgap energy of TiO2 and Perovskite layers was determined to be 3.52 eV and 2.06 eV respectively. An open-circuit voltage was 0.9057 V and short circuit current density was 12.2185 mA/cm<sup>2</sup> with a fill factor of 48.05 and power conversion efficiency (PCE) of 5.199%.</p>","PeriodicalId":13480,"journal":{"name":"Indonesian Journal of Electrical Engineering and Computer Science","volume":"20 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141231764","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/ijeecs.v34.i3.pp1935-1943
Orlando Iparraguirre-Villanueva, Josemaria Gonzales-Huaman, Jose Machuca-Solano, John Ruiz-Alvarado
Employee safety is paramount in the manufacturing industry to ensure their well-being and protection. Technological advancements, particularly convolutional neural networks (CNN), have significantly enhanced this safety aspect by facilitating object detection and recognition. This project aims to utilize CNN technology to detect personal protective equipment and implement a safety implement detection system. The CNN architecture with the YOLOv5x model was employed to train a dataset. Dataset videos were converted into frames, with resolution scale adjustments made during the data collection phase. Subsequently, the dataset was labeled, underwent data cleaning, and label and bounding box revisions. The results revealed significant metrics in safety equipment detection in industrial settings. Helmet precision reached 91%, with a recall of 74%. Goggles achieved 85% precision and an 87% recall. Mask absence recorded 92% precision and an 89% recall. The YOLOv5x model exhibited commendable performance, showcasing its robust ability to accurately locate and detect objects. In conclusion, the utilization of a CNN-based safety equipment detection system, such as YOLOv5x, has yielded substantial improvements in both speed and accuracy. These findings lay a solid foundation for future industrial security applications aimed at safeguarding workers, fostering responsible workplace behavior, and optimizing the utilization of information technology resources.
{"title":"Improving industrial security device detection with convolutional neural networks","authors":"Orlando Iparraguirre-Villanueva, Josemaria Gonzales-Huaman, Jose Machuca-Solano, John Ruiz-Alvarado","doi":"10.11591/ijeecs.v34.i3.pp1935-1943","DOIUrl":"https://doi.org/10.11591/ijeecs.v34.i3.pp1935-1943","url":null,"abstract":"Employee safety is paramount in the manufacturing industry to ensure their well-being and protection. Technological advancements, particularly convolutional neural networks (CNN), have significantly enhanced this safety aspect by facilitating object detection and recognition. This project aims to utilize CNN technology to detect personal protective equipment and implement a safety implement detection system. The CNN architecture with the YOLOv5x model was employed to train a dataset. Dataset videos were converted into frames, with resolution scale adjustments made during the data collection phase. Subsequently, the dataset was labeled, underwent data cleaning, and label and bounding box revisions. The results revealed significant metrics in safety equipment detection in industrial settings. Helmet precision reached 91%, with a recall of 74%. Goggles achieved 85% precision and an 87% recall. Mask absence recorded 92% precision and an 89% recall. The YOLOv5x model exhibited commendable performance, showcasing its robust ability to accurately locate and detect objects. In conclusion, the utilization of a CNN-based safety equipment detection system, such as YOLOv5x, has yielded substantial improvements in both speed and accuracy. These findings lay a solid foundation for future industrial security applications aimed at safeguarding workers, fostering responsible workplace behavior, and optimizing the utilization of information technology resources.","PeriodicalId":13480,"journal":{"name":"Indonesian Journal of Electrical Engineering and Computer Science","volume":"70 8","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141230956","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/ijeecs.v34.i3.pp1739-1752
Manjula Kalita, L. Mahanta, A. Das, Mananjay Nath
Cytological evaluation through microscopic image analysis of fine needle aspiration cytology (FNAC) is pivotal in the initial screening of breast cancer. The sensitivity of FNAC as a screening tool relies on both image quality and the pathologist’s expertise. To enhance diagnostic accuracy and alleviate the pathologist’s workload, a computer-aided diagnosis (CAD) system was developed. A comparative study was conducted, assessing twelve candidate pre-trained models. Utilizing a locally gathered FNAC image dataset, three superior models-MobileNet-V2, DenseNet-121, and Inception-V3-were selected based on their training, validation, and testing accuracies. Further, these models underwent evaluation in four transfer learning scenarios to enhance testing accuracy. While the outcomes were promising, they left room for improvement, motivating us to create a novel deep convolutional neural network (CNN). The newly proposed model exhibited robust performance with testing accuracy at 85%. Our research concludes that the most lightweight, high-accuracy model is the one we propose. We’ve integrated it into our user-friendly Android App, “Breast Cancer Detection System,” in TensorFlow Lite format, with cloud database support, showcasing its effectiveness. Implementing an artificial intelligent (AI)-based diagnosis system with a user-friendly interface holds the potential to enhance early breast cancer detection using FNAC.
{"title":"A new deep learning model with interface for fine needle aspiration cytology image-based breast cancer detection","authors":"Manjula Kalita, L. Mahanta, A. Das, Mananjay Nath","doi":"10.11591/ijeecs.v34.i3.pp1739-1752","DOIUrl":"https://doi.org/10.11591/ijeecs.v34.i3.pp1739-1752","url":null,"abstract":"Cytological evaluation through microscopic image analysis of fine needle aspiration cytology (FNAC) is pivotal in the initial screening of breast cancer. The sensitivity of FNAC as a screening tool relies on both image quality and the pathologist’s expertise. To enhance diagnostic accuracy and alleviate the pathologist’s workload, a computer-aided diagnosis (CAD) system was developed. A comparative study was conducted, assessing twelve candidate pre-trained models. Utilizing a locally gathered FNAC image dataset, three superior models-MobileNet-V2, DenseNet-121, and Inception-V3-were selected based on their training, validation, and testing accuracies. Further, these models underwent evaluation in four transfer learning scenarios to enhance testing accuracy. While the outcomes were promising, they left room for improvement, motivating us to create a novel deep convolutional neural network (CNN). The newly proposed model exhibited robust performance with testing accuracy at 85%. Our research concludes that the most lightweight, high-accuracy model is the one we propose. We’ve integrated it into our user-friendly Android App, “Breast Cancer Detection System,” in TensorFlow Lite format, with cloud database support, showcasing its effectiveness. Implementing an artificial intelligent (AI)-based diagnosis system with a user-friendly interface holds the potential to enhance early breast cancer detection using FNAC.","PeriodicalId":13480,"journal":{"name":"Indonesian Journal of Electrical Engineering and Computer Science","volume":"33 9","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141232941","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/ijeecs.v34.i3.pp1472-1481
Van-Khoa Pham, Chi-Chia Sun
Static random-access memory (SRAM) technology is utilized in designing cache memory to enhance the processing performance of computer systems. The sense amplifier (SA) circuit, a crucial component of memory design, significantly impacts data access time and power consumption. In comparison to conventional differential sense amplifiers (DSA) designs, latch-based sense amplifiers (LSA) used in memory-based computing platforms have specific requirements, including robust noise resistance in harsh working environments and low power consumption, particularly for internet of thing (IoT) embedded computing applications. However, the performance can be degraded due to various factors that arise during the layout, such as conductor resistance or the development of parasitic capacitance. Therefore, this study employs low-voltage 22 nm UMC CMOS technology for LSA design layout and analyzes the factors influencing design performance post-layout process. Layout design optimization techniques are applied to mitigate the impact of parasitic capacitance on important signal lines such as data line/data line bar (DLL/DLLB). Based on the performance analysis results, it is possible to achieve a reduction in power consumption of up to 15% and a 5% decrease in read delay time by implementing circuit layout LSA design optimization techniques.
{"title":"Analysis of the parasitic capacitance effects on the layout of latch-based sense amplifiers for improving SRAM performance","authors":"Van-Khoa Pham, Chi-Chia Sun","doi":"10.11591/ijeecs.v34.i3.pp1472-1481","DOIUrl":"https://doi.org/10.11591/ijeecs.v34.i3.pp1472-1481","url":null,"abstract":"Static random-access memory (SRAM) technology is utilized in designing cache memory to enhance the processing performance of computer systems. The sense amplifier (SA) circuit, a crucial component of memory design, significantly impacts data access time and power consumption. In comparison to conventional differential sense amplifiers (DSA) designs, latch-based sense amplifiers (LSA) used in memory-based computing platforms have specific requirements, including robust noise resistance in harsh working environments and low power consumption, particularly for internet of thing (IoT) embedded computing applications. However, the performance can be degraded due to various factors that arise during the layout, such as conductor resistance or the development of parasitic capacitance. Therefore, this study employs low-voltage 22 nm UMC CMOS technology for LSA design layout and analyzes the factors influencing design performance post-layout process. Layout design optimization techniques are applied to mitigate the impact of parasitic capacitance on important signal lines such as data line/data line bar (DLL/DLLB). Based on the performance analysis results, it is possible to achieve a reduction in power consumption of up to 15% and a 5% decrease in read delay time by implementing circuit layout LSA design optimization techniques.","PeriodicalId":13480,"journal":{"name":"Indonesian Journal of Electrical Engineering and Computer Science","volume":"24 26","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141233353","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：