Pub Date : 2023-07-13DOI: 10.1109/IAICT59002.2023.10205595
Mikho J Pelingon, Valenzuela Franco Carlos, M. L. Guico, J. K. Galicia
Calamansi has been declared as one of the most important fruit growing crops in the Philippines. However, due to certain bacteria, it is susceptible to certain diseases affecting its harvest rate. This paper aims to effectively monitor the state of the calamansi at its healthy state and at its diseased state. Specifically, it classifies diseases such as Citrus Canker, Citrus Scab, and Citrus Browning by utilizing existing image processing techniques for disease detection of different fruits and determining which algorithm is most apt for this application in terms of precision, accuracy and recall. Techniques such as K-Means Clustering, utilization of an Artificial Neural Network (ANN), feature extraction through GLCM along with the usage of a minimum distance classifier, a Support Vector Machine (SVM) classifier and other techniques and/or their combinations were explored and measured. The researchers performed two kinds of tests: 1×1 comparison and merged comparison. For the 1×1 comparison, making use of GrabCut, color feature extraction, and SVM produced the best overall results, with an overall average of 98% for precision, 95% for accuracy, 91% for recall, and 94% for F-score. Adaptive Gaussian Filtering along with texture feature extraction and SVM was the most accurate for detecting calamansi fruits with citrus canker and citrus scab. Overall, the two methods acquired the same average accuracy of 61%
{"title":"Application of Image Recognition Algorithms in the Detection of Philippine Lime Diseases","authors":"Mikho J Pelingon, Valenzuela Franco Carlos, M. L. Guico, J. K. Galicia","doi":"10.1109/IAICT59002.2023.10205595","DOIUrl":"https://doi.org/10.1109/IAICT59002.2023.10205595","url":null,"abstract":"Calamansi has been declared as one of the most important fruit growing crops in the Philippines. However, due to certain bacteria, it is susceptible to certain diseases affecting its harvest rate. This paper aims to effectively monitor the state of the calamansi at its healthy state and at its diseased state. Specifically, it classifies diseases such as Citrus Canker, Citrus Scab, and Citrus Browning by utilizing existing image processing techniques for disease detection of different fruits and determining which algorithm is most apt for this application in terms of precision, accuracy and recall. Techniques such as K-Means Clustering, utilization of an Artificial Neural Network (ANN), feature extraction through GLCM along with the usage of a minimum distance classifier, a Support Vector Machine (SVM) classifier and other techniques and/or their combinations were explored and measured. The researchers performed two kinds of tests: 1×1 comparison and merged comparison. For the 1×1 comparison, making use of GrabCut, color feature extraction, and SVM produced the best overall results, with an overall average of 98% for precision, 95% for accuracy, 91% for recall, and 94% for F-score. Adaptive Gaussian Filtering along with texture feature extraction and SVM was the most accurate for detecting calamansi fruits with citrus canker and citrus scab. Overall, the two methods acquired the same average accuracy of 61%","PeriodicalId":339796,"journal":{"name":"2023 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127833633","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 : 2023-07-13DOI: 10.1109/IAICT59002.2023.10205656
O. Vasilevskyi, V. Didych, O. Zabula, V. Sarana, E. Popovici
Evaluating the measurement accuracy of sensors is one of the most important tasks in the development of support systems for Industry 4.0. The study of accuracy is proposed to be carried out using measurement models by expanding them into a Taylor series. From the components of the Taylor series, equations are obtained that describe the sensitivity, additive and multiplicative errors of the measuring instrument. A mathematical model is also proposed that allows you to recalculate the multiplicative and additive errors of the measuring instrument into the uncertainty. The proposed metrological models are tested on the example of the expansion of the transformation equation, which describes the operation of the means for measuring the activity of ions. In absolute units of measurement of ion activity, the multiplicative and additive errors are 0.047pX each in the measurement range from 0.2 to 7.5pX. Using proposed mathematical model for converting these errors into uncertainty, we obtained the standard type B uncertainty, which is 0.064pX.
{"title":"Developing and using measurement models to assess accuracy: using the example of measurements of the activity of ions","authors":"O. Vasilevskyi, V. Didych, O. Zabula, V. Sarana, E. Popovici","doi":"10.1109/IAICT59002.2023.10205656","DOIUrl":"https://doi.org/10.1109/IAICT59002.2023.10205656","url":null,"abstract":"Evaluating the measurement accuracy of sensors is one of the most important tasks in the development of support systems for Industry 4.0. The study of accuracy is proposed to be carried out using measurement models by expanding them into a Taylor series. From the components of the Taylor series, equations are obtained that describe the sensitivity, additive and multiplicative errors of the measuring instrument. A mathematical model is also proposed that allows you to recalculate the multiplicative and additive errors of the measuring instrument into the uncertainty. The proposed metrological models are tested on the example of the expansion of the transformation equation, which describes the operation of the means for measuring the activity of ions. In absolute units of measurement of ion activity, the multiplicative and additive errors are 0.047pX each in the measurement range from 0.2 to 7.5pX. Using proposed mathematical model for converting these errors into uncertainty, we obtained the standard type B uncertainty, which is 0.064pX.","PeriodicalId":339796,"journal":{"name":"2023 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"129 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123292964","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 : 2023-07-13DOI: 10.1109/IAICT59002.2023.10205624
Itsnanta Muhammad Fauzan, D. Gunawan
Post-merger between MNO-1 and MNO-2 become new entity ‘MNO-M’, there are some obligations from government: It is required to make a frequency band return of $2 times 5$ MHz at 2.1 GHz, adding new sites for services until 2025, and to improve its Quality of Service (QoS). On top of those obligations, during the network consolidation, there are some challenges such as big network infrastructure complexity from MNO-1 & MNO-2, network consolidation must be done on the live network which potentially impact to customer experience, and many 3G sites which require to be sunset as part of government compliance. The method that is used in this paper is by analysis secondary data from MNO-M and review of scientific literature as supporting reference. The strategy to be able to face the challenges by building a platform and tool that will provide end-to-end visibility to multi-operator networks. This paper introduces a new digital operation concept and solution named DIAMON (Digital Intelligence Automation Multi-Operator Network). DIAMON integrates all of Network Elements (NEs) multi-vendor end-to-end and provides full visibility for network operations management (network monitoring, performance management, service quality, and customer experience management). A strong digital operation platform and tool through DIAMON is also very important to support the multi-operator network to face network consolidation challenges and provide excellence operational services in Indonesia.
{"title":"Network Consolidation Challenges After MNO-1 & MNO-2 Merger and Strategy for Operational Excellence in Indonesia Using DIAMON","authors":"Itsnanta Muhammad Fauzan, D. Gunawan","doi":"10.1109/IAICT59002.2023.10205624","DOIUrl":"https://doi.org/10.1109/IAICT59002.2023.10205624","url":null,"abstract":"Post-merger between MNO-1 and MNO-2 become new entity ‘MNO-M’, there are some obligations from government: It is required to make a frequency band return of $2 times 5$ MHz at 2.1 GHz, adding new sites for services until 2025, and to improve its Quality of Service (QoS). On top of those obligations, during the network consolidation, there are some challenges such as big network infrastructure complexity from MNO-1 & MNO-2, network consolidation must be done on the live network which potentially impact to customer experience, and many 3G sites which require to be sunset as part of government compliance. The method that is used in this paper is by analysis secondary data from MNO-M and review of scientific literature as supporting reference. The strategy to be able to face the challenges by building a platform and tool that will provide end-to-end visibility to multi-operator networks. This paper introduces a new digital operation concept and solution named DIAMON (Digital Intelligence Automation Multi-Operator Network). DIAMON integrates all of Network Elements (NEs) multi-vendor end-to-end and provides full visibility for network operations management (network monitoring, performance management, service quality, and customer experience management). A strong digital operation platform and tool through DIAMON is also very important to support the multi-operator network to face network consolidation challenges and provide excellence operational services in Indonesia.","PeriodicalId":339796,"journal":{"name":"2023 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"376 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123410550","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 : 2023-07-13DOI: 10.1109/IAICT59002.2023.10205740
K. S. Shanthini, S. N. George, S. George, B. Devassy
Hyperspectral imaging offers the capacity to quickly and noninvasively monitor a food product’s physical, chemical and morphological properties. Specim IQ is a handheld push broom camera with basic data handling and data analysis capabilities within the camera software. However, the recordings of the Specim IQ camera showed a line pattern (stripes) that was evident in all images. Stripes significantly reduce the visual quality of the images and lower the results of further processing. Hence an efficient destriping model is developed, which specifically addresses this issue. The proposed model uses a spatial gradient term to analyze the directional characteristics and group sparsity to describe the structural characteristics of the stripe component. In addition to this, a spatial spectral total variation regularization is used to ensure piecewise smoothness in the spatial and spectral domains and to remove Gaussian noise. The ensuing optimisation problem is solved using the alternating direction method of multipliers (ADMM). The proposed method is tested in real stripe noise environments, and the findings demonstrate that it outperforms some of the best approaches in terms of visual quality and quantitative evaluations. When compared with the other approaches, the proposed method attained the highest noise reduction (NR) and lowest mean relative deviation (MRD) values (NR=1.67, MRD=1.02%).
{"title":"Stripe Removal from Hyperspectral Food Images acquired by Handheld Camera using ℓ2,1 Norm Minimization and SSTV Regularization","authors":"K. S. Shanthini, S. N. George, S. George, B. Devassy","doi":"10.1109/IAICT59002.2023.10205740","DOIUrl":"https://doi.org/10.1109/IAICT59002.2023.10205740","url":null,"abstract":"Hyperspectral imaging offers the capacity to quickly and noninvasively monitor a food product’s physical, chemical and morphological properties. Specim IQ is a handheld push broom camera with basic data handling and data analysis capabilities within the camera software. However, the recordings of the Specim IQ camera showed a line pattern (stripes) that was evident in all images. Stripes significantly reduce the visual quality of the images and lower the results of further processing. Hence an efficient destriping model is developed, which specifically addresses this issue. The proposed model uses a spatial gradient term to analyze the directional characteristics and group sparsity to describe the structural characteristics of the stripe component. In addition to this, a spatial spectral total variation regularization is used to ensure piecewise smoothness in the spatial and spectral domains and to remove Gaussian noise. The ensuing optimisation problem is solved using the alternating direction method of multipliers (ADMM). The proposed method is tested in real stripe noise environments, and the findings demonstrate that it outperforms some of the best approaches in terms of visual quality and quantitative evaluations. When compared with the other approaches, the proposed method attained the highest noise reduction (NR) and lowest mean relative deviation (MRD) values (NR=1.67, MRD=1.02%).","PeriodicalId":339796,"journal":{"name":"2023 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"131 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121709242","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 : 2023-07-13DOI: 10.1109/IAICT59002.2023.10205862
Rehan Mohammed, Vu Le, D. Creighton, Anwar Hosen
Machine learning algorithms are widely used in data-driven predictive maintenance to address prognostics of the condition of lithium-ion batteries over their cycle life. However, selecting relevant features remains a critical issue when predicting the remaining useful life (RUL) of these batteries using data-driven approaches. This issue can significantly affect the performance of machine learning algorithms and lead to time loss. In this paper, we investigate the effectiveness of two feature selection techniques that use the Recursive Feature Elimination (RFE) method for predicting the RUL of fast-charged lithium-ion batteries. We use the RFE-LASSO and RFE-XGB methods for feature selection and the Elastic Net and Relevance Vector Regression models for RUL prediction. Experimental results using Nature Energy’s battery dataset show that the RFEXGB feature selection method can provide stable prediction performance using 33 or more features. Furthermore, when integrated with the Elastic Net model, RFE-XGB achieves the lowest prediction error at a train-test split of 80%-20%.
{"title":"Feature Selection for Cycle Life Prediction of Fast-Charged Lithium-ion Batteries","authors":"Rehan Mohammed, Vu Le, D. Creighton, Anwar Hosen","doi":"10.1109/IAICT59002.2023.10205862","DOIUrl":"https://doi.org/10.1109/IAICT59002.2023.10205862","url":null,"abstract":"Machine learning algorithms are widely used in data-driven predictive maintenance to address prognostics of the condition of lithium-ion batteries over their cycle life. However, selecting relevant features remains a critical issue when predicting the remaining useful life (RUL) of these batteries using data-driven approaches. This issue can significantly affect the performance of machine learning algorithms and lead to time loss. In this paper, we investigate the effectiveness of two feature selection techniques that use the Recursive Feature Elimination (RFE) method for predicting the RUL of fast-charged lithium-ion batteries. We use the RFE-LASSO and RFE-XGB methods for feature selection and the Elastic Net and Relevance Vector Regression models for RUL prediction. Experimental results using Nature Energy’s battery dataset show that the RFEXGB feature selection method can provide stable prediction performance using 33 or more features. Furthermore, when integrated with the Elastic Net model, RFE-XGB achieves the lowest prediction error at a train-test split of 80%-20%.","PeriodicalId":339796,"journal":{"name":"2023 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122452125","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 : 2023-07-13DOI: 10.1109/IAICT59002.2023.10205863
Yit Hong Choo, Vu Le, Michael Johnstone, Doug Creighton, Himanshu Jindal, Kevin Tan
In line with Industry 4.0, various advanced technologies such as sensors, automation, and artificial intelligence (AI) methods have been leveraged to enhance maintenance processes in the rolling stock industry. In particular, AI techniques are useful for optimising maintenance scheduling and planning tasks for rolling stocks. This study focuses on the use of a metaheuristic method, namely an enhanced multi-objective Harris’ Hawk optimiser (MO-HHO), for optimising competing objectives based on data obtained from a railway maintenance company. The results of MO-HHO are evaluated and compared with those from other competing models. The findings demonstrate the usefulness of MO-HHO in tackling multi-objective train maintenance scheduling tasks in practical environments.
{"title":"Optimisation of Multi-objective Rolling Stock Maintenance Scheduling with Harris’ Hawk Optimiser","authors":"Yit Hong Choo, Vu Le, Michael Johnstone, Doug Creighton, Himanshu Jindal, Kevin Tan","doi":"10.1109/IAICT59002.2023.10205863","DOIUrl":"https://doi.org/10.1109/IAICT59002.2023.10205863","url":null,"abstract":"In line with Industry 4.0, various advanced technologies such as sensors, automation, and artificial intelligence (AI) methods have been leveraged to enhance maintenance processes in the rolling stock industry. In particular, AI techniques are useful for optimising maintenance scheduling and planning tasks for rolling stocks. This study focuses on the use of a metaheuristic method, namely an enhanced multi-objective Harris’ Hawk optimiser (MO-HHO), for optimising competing objectives based on data obtained from a railway maintenance company. The results of MO-HHO are evaluated and compared with those from other competing models. The findings demonstrate the usefulness of MO-HHO in tackling multi-objective train maintenance scheduling tasks in practical environments.","PeriodicalId":339796,"journal":{"name":"2023 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126751218","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 : 2023-07-13DOI: 10.1109/IAICT59002.2023.10205875
Jiann-Liang Chen, Bagus Tri Atmaja, Candra Ahmadi, Jian-Chang Hsu
In the digital era, internet reliance has transformed daily life, potentially exposing security vulnerabilities. In addition, the proliferation of network devices has increased the risk of cyber-attacks, posing threats to individuals and organizations. This study develops a predictive system for Security Functional Requirements (SFRs) and Evaluation Assurance Level (EAL) using machine learning based on the ISO/IEC15408 Common Criteria for Information Technology Security Certification (EUCC), a global ICT product evaluation framework. Utilizing an XML parser, ElementTree, the research focuses on the Common Criteria as the security target and analyzes two datasets: SFRs and EAL. The decision tree algorithm yields an EAL prediction model with 100% accuracy. A random forest algorithm generates an SFR prediction model with 65% accuracy. The lower accuracy is attributed to diverse device specifications. An Expert system manages multiple cases to predict the EAL level. The study also produces a Security Target document with EAL and SFRs predictions, facilitated by a PySide6-developed user interface that integrates the prediction system. This research significantly enhances ICT security, providing a robust tool for improving ICT product security and offering valuable insights for manufacturers and developers through the high accuracy of the EAL prediction model and comprehensive analysis of the SFR dataset
{"title":"Security Document Generation for Common Criteria Using Machine Learning and Rule-based Expert System","authors":"Jiann-Liang Chen, Bagus Tri Atmaja, Candra Ahmadi, Jian-Chang Hsu","doi":"10.1109/IAICT59002.2023.10205875","DOIUrl":"https://doi.org/10.1109/IAICT59002.2023.10205875","url":null,"abstract":"In the digital era, internet reliance has transformed daily life, potentially exposing security vulnerabilities. In addition, the proliferation of network devices has increased the risk of cyber-attacks, posing threats to individuals and organizations. This study develops a predictive system for Security Functional Requirements (SFRs) and Evaluation Assurance Level (EAL) using machine learning based on the ISO/IEC15408 Common Criteria for Information Technology Security Certification (EUCC), a global ICT product evaluation framework. Utilizing an XML parser, ElementTree, the research focuses on the Common Criteria as the security target and analyzes two datasets: SFRs and EAL. The decision tree algorithm yields an EAL prediction model with 100% accuracy. A random forest algorithm generates an SFR prediction model with 65% accuracy. The lower accuracy is attributed to diverse device specifications. An Expert system manages multiple cases to predict the EAL level. The study also produces a Security Target document with EAL and SFRs predictions, facilitated by a PySide6-developed user interface that integrates the prediction system. This research significantly enhances ICT security, providing a robust tool for improving ICT product security and offering valuable insights for manufacturers and developers through the high accuracy of the EAL prediction model and comprehensive analysis of the SFR dataset","PeriodicalId":339796,"journal":{"name":"2023 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125829406","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 : 2023-07-13DOI: 10.1109/IAICT59002.2023.10205635
Abdel F. Chabi, Matheus Fontinele de Aguiar, Jordan Kalliure S. Carvalho, Vivianne de Aquino Rodrigues, João Vitor Da S. Campos, Bruna Maira Da S. Fonseca, J. O. D. Sousa
In recent years, Voice over IP (VoIP) call feature has become increasingly accessible to customers due to advancements in internet services and the emergence of voice call applications. However, identifying the variables that impact Voice over Long-Term Evolution (VoLTE) performance, particularly in quantifying end-user experience in the field and the effects of radio conditions and IP impairments on voice quality as measured by the Mean Opinion Score (MOS), presents challenges for carriers. MOS is a widely used metric for evaluating voice quality, and there is a significant commitment from both mobile device manufacturers and carriers to ensure superior voice quality during voice calls. To this end, MOS experiments are performed to evaluate the reliability of VoLTE calls, which is currently the best approach for measuring voice quality. In this study, we present MOS experimentation results in laboratory environments to homologate 146 different smartphone models. As results, we highlight the challenges associated with MOS testing in VoLTE calls under controlled conditions and discuss the primary issues found and how they were addressed. These experimental analyses offer substantial opportunities for enhancing the design and operation of audio quality during VoLTE calls and detail potentially improvements for 5GVoNR calls.
{"title":"Voice Quality Experience Evaluation: MOS Laboratory Test and Spectrum Analysis of Failures in VoLTE Calls","authors":"Abdel F. Chabi, Matheus Fontinele de Aguiar, Jordan Kalliure S. Carvalho, Vivianne de Aquino Rodrigues, João Vitor Da S. Campos, Bruna Maira Da S. Fonseca, J. O. D. Sousa","doi":"10.1109/IAICT59002.2023.10205635","DOIUrl":"https://doi.org/10.1109/IAICT59002.2023.10205635","url":null,"abstract":"In recent years, Voice over IP (VoIP) call feature has become increasingly accessible to customers due to advancements in internet services and the emergence of voice call applications. However, identifying the variables that impact Voice over Long-Term Evolution (VoLTE) performance, particularly in quantifying end-user experience in the field and the effects of radio conditions and IP impairments on voice quality as measured by the Mean Opinion Score (MOS), presents challenges for carriers. MOS is a widely used metric for evaluating voice quality, and there is a significant commitment from both mobile device manufacturers and carriers to ensure superior voice quality during voice calls. To this end, MOS experiments are performed to evaluate the reliability of VoLTE calls, which is currently the best approach for measuring voice quality. In this study, we present MOS experimentation results in laboratory environments to homologate 146 different smartphone models. As results, we highlight the challenges associated with MOS testing in VoLTE calls under controlled conditions and discuss the primary issues found and how they were addressed. These experimental analyses offer substantial opportunities for enhancing the design and operation of audio quality during VoLTE calls and detail potentially improvements for 5GVoNR calls.","PeriodicalId":339796,"journal":{"name":"2023 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125804579","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 : 2023-07-13DOI: 10.1109/IAICT59002.2023.10205620
Abdulaziz Almaleh
The management of mental health issues in the workplace has always been a significant and challenging task, especially for professionals. Despite the evidence of the detrimental effects of preventable mental health disorders and stress in the workplace, many organizations have not taken enough preventative measures. To address this issue, data were collected from the OSMI website, which aims to raise awareness of mental illness in the workplace. The collected data was label encoded to improve prediction accuracy. Various machine learning techniques were applied to the data to develop a model to help individuals with mental health issues create a healthier work environment. Our proposed approach involved the implementation of classification algorithms, including Random Forest, Logistic Regression, Support Vector Machine, Adaboost, and Gradient Boosting, to obtain the highest accuracy possible.
{"title":"Machine Learning-Based Forecasting of Mental Health Issues Among Employees in the Workplace","authors":"Abdulaziz Almaleh","doi":"10.1109/IAICT59002.2023.10205620","DOIUrl":"https://doi.org/10.1109/IAICT59002.2023.10205620","url":null,"abstract":"The management of mental health issues in the workplace has always been a significant and challenging task, especially for professionals. Despite the evidence of the detrimental effects of preventable mental health disorders and stress in the workplace, many organizations have not taken enough preventative measures. To address this issue, data were collected from the OSMI website, which aims to raise awareness of mental illness in the workplace. The collected data was label encoded to improve prediction accuracy. Various machine learning techniques were applied to the data to develop a model to help individuals with mental health issues create a healthier work environment. Our proposed approach involved the implementation of classification algorithms, including Random Forest, Logistic Regression, Support Vector Machine, Adaboost, and Gradient Boosting, to obtain the highest accuracy possible.","PeriodicalId":339796,"journal":{"name":"2023 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"17 12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116065933","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 : 2023-07-13DOI: 10.1109/IAICT59002.2023.10205792
Rika Favoria Gusa, Risanuri Hidayat, H. A. Nugroho
Ultrasound imaging is widely used in medical diagnosis because it is non-invasive and free from ionizing radiation. However, ultrasound images have low contrast and contain speckle noise, making diagnosis difficult. Therefore, speckle noise reduction and image contrast enhancement are important prerequisites in ultrasound image processing. Many methods can be used in the ultrasound image pre-processing stage. In this paper, fetal ultrasound images were enhanced in contrast and sharpness using four enhancement methods, namely histogram equalization (HE), contrast limited adaptive histogram equalization (CLAHE), unsharp masking (UM), and maximum local variation-based unsharp masking (MLVUM). These methods were applied to ultrasound images in two ways. Those are without filtering them and by first filtering them using a speckle reducing anisotropic diffusion (SRAD) filter. A comparative analysis was carried out on the performance of the four enhancement methods using the absolute mean brightness error (AMBE), average local contrast (ALC), and average gradient (AG) parameters. The results show that UM and MLVUM work better in increasing the contrast of fetal ultrasound images than HE and CLAHE. Applying the HE, CLAHE, UM, and MLVUM methods without filtering produces ultrasound images with better sharpness and contrast than enhanced images involving filtering but causing speckle noise amplification.
{"title":"Performance Analysis of Enhancement Methods on Fetal Ultrasound Images","authors":"Rika Favoria Gusa, Risanuri Hidayat, H. A. Nugroho","doi":"10.1109/IAICT59002.2023.10205792","DOIUrl":"https://doi.org/10.1109/IAICT59002.2023.10205792","url":null,"abstract":"Ultrasound imaging is widely used in medical diagnosis because it is non-invasive and free from ionizing radiation. However, ultrasound images have low contrast and contain speckle noise, making diagnosis difficult. Therefore, speckle noise reduction and image contrast enhancement are important prerequisites in ultrasound image processing. Many methods can be used in the ultrasound image pre-processing stage. In this paper, fetal ultrasound images were enhanced in contrast and sharpness using four enhancement methods, namely histogram equalization (HE), contrast limited adaptive histogram equalization (CLAHE), unsharp masking (UM), and maximum local variation-based unsharp masking (MLVUM). These methods were applied to ultrasound images in two ways. Those are without filtering them and by first filtering them using a speckle reducing anisotropic diffusion (SRAD) filter. A comparative analysis was carried out on the performance of the four enhancement methods using the absolute mean brightness error (AMBE), average local contrast (ALC), and average gradient (AG) parameters. The results show that UM and MLVUM work better in increasing the contrast of fetal ultrasound images than HE and CLAHE. Applying the HE, CLAHE, UM, and MLVUM methods without filtering produces ultrasound images with better sharpness and contrast than enhanced images involving filtering but causing speckle noise amplification.","PeriodicalId":339796,"journal":{"name":"2023 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"199 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131333231","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：