Pub Date : 2023-06-01DOI: 10.1109/IS3C57901.2023.00070
J. Chiang, Yi-Yan Lin
In this study, the indium-zinc-oxide(IZO) thin mms were deposited on silicon substrates by r.f. sputtering. The IZO/Si sensing structure was used as a disposable sensor head and connected to the gate terminal of MOSFET. The IZO extended-gate field-effect transistor (EGFET) sensing structure and the Ag/AgCl reference electrode were immersed into the different buffer solutions (pH=1,3,5,7,9,11). Afterward, the current-voltage (I-V) characteristics curves and the pH sensitivity were measured and analyzed. According to the experimental results, the pH sensitivity of the IZO EGFET was obtained at approximately 52 mV/pH, and the pH-sensing response is linear (~1). The superior sensing properties of IZO pH-EGFET can be applied to detecting the $H^{+}-$ion concentrations.
{"title":"Deposited Indium-Zinc-Oxide Thin Film by RF Sputtering for pH-Sensing Application","authors":"J. Chiang, Yi-Yan Lin","doi":"10.1109/IS3C57901.2023.00070","DOIUrl":"https://doi.org/10.1109/IS3C57901.2023.00070","url":null,"abstract":"In this study, the indium-zinc-oxide(IZO) thin mms were deposited on silicon substrates by r.f. sputtering. The IZO/Si sensing structure was used as a disposable sensor head and connected to the gate terminal of MOSFET. The IZO extended-gate field-effect transistor (EGFET) sensing structure and the Ag/AgCl reference electrode were immersed into the different buffer solutions (pH=1,3,5,7,9,11). Afterward, the current-voltage (I-V) characteristics curves and the pH sensitivity were measured and analyzed. According to the experimental results, the pH sensitivity of the IZO EGFET was obtained at approximately 52 mV/pH, and the pH-sensing response is linear (~1). The superior sensing properties of IZO pH-EGFET can be applied to detecting the $H^{+}-$ion concentrations.","PeriodicalId":142483,"journal":{"name":"2023 Sixth International Symposium on Computer, Consumer and Control (IS3C)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134446357","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 : 2023-06-01DOI: 10.1109/IS3C57901.2023.00064
Jiun-Hung Lin, Chita Chen, Yung-Tsung Cheng
In recent years, Taiwan has faced the challenge of an aging society, and long-term care has become a pressing issue. In this study, a long-term care monitoring system was developed using LoRa wireless communication technology, which is remote, low-power, and low-cost. The system automatically performs daily physiological measurements through a portable physiological sensor to reduce the workload of healthcare workers and improve the quality of care. The system automatically performs daily physiological measurements through a portable physiological sensor to reduce the workload of healthcare workers and improve the quality of care. In the future, the system can be combined with cloud servers and related application development to provide a convenient, complete, real-time and low-cost long-term care monitoring system for patients and their families, medical institutions and care providers.
{"title":"Application of IoT Technology in Healthcare: A Case Study of LoRa Technology","authors":"Jiun-Hung Lin, Chita Chen, Yung-Tsung Cheng","doi":"10.1109/IS3C57901.2023.00064","DOIUrl":"https://doi.org/10.1109/IS3C57901.2023.00064","url":null,"abstract":"In recent years, Taiwan has faced the challenge of an aging society, and long-term care has become a pressing issue. In this study, a long-term care monitoring system was developed using LoRa wireless communication technology, which is remote, low-power, and low-cost. The system automatically performs daily physiological measurements through a portable physiological sensor to reduce the workload of healthcare workers and improve the quality of care. The system automatically performs daily physiological measurements through a portable physiological sensor to reduce the workload of healthcare workers and improve the quality of care. In the future, the system can be combined with cloud servers and related application development to provide a convenient, complete, real-time and low-cost long-term care monitoring system for patients and their families, medical institutions and care providers.","PeriodicalId":142483,"journal":{"name":"2023 Sixth International Symposium on Computer, Consumer and Control (IS3C)","volume":"261 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133929002","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 : 2023-06-01DOI: 10.1109/IS3C57901.2023.00036
Hung-Kuang Chen
The level-of-detail (LOD) technique has been proved to be an effective technique in balancing the rendering efficiency and fidelity demands in the interactive 3D computer graphics applications. Among previously proposed geometric LOD techniques, the discrete, or static, LOD technique is the most adopted representation in real-time 3D graphics applications such as the virtual reality (VR) and 3D computer game. According to previous works, the discrete LOD representations usually suffers from the “popping effect” causing visual disturbance when switching LOD meshes; to cope with this, techniques such as geo-morphing and LOD blending were proposed. However, they either require additional efforts in converting underlying mesh representation or consume additional storage space or transmission cost. In this paper, we have proposed a novel LOD representation based on the concept of sharing a common vertex buffer among the various LOD meshes of a model. The novel LOD representation, called Common Vertex Buffer LOD, denoted as CVB-LOD, has the benefits of saving transmission and storage costs, lower mesh loading latency that effectively reduces the popping effect in switching LOD meshes.
{"title":"Common Vertex Buffer LOD: A Novel Discrete LOD Approach to Reducing Load Latency","authors":"Hung-Kuang Chen","doi":"10.1109/IS3C57901.2023.00036","DOIUrl":"https://doi.org/10.1109/IS3C57901.2023.00036","url":null,"abstract":"The level-of-detail (LOD) technique has been proved to be an effective technique in balancing the rendering efficiency and fidelity demands in the interactive 3D computer graphics applications. Among previously proposed geometric LOD techniques, the discrete, or static, LOD technique is the most adopted representation in real-time 3D graphics applications such as the virtual reality (VR) and 3D computer game. According to previous works, the discrete LOD representations usually suffers from the “popping effect” causing visual disturbance when switching LOD meshes; to cope with this, techniques such as geo-morphing and LOD blending were proposed. However, they either require additional efforts in converting underlying mesh representation or consume additional storage space or transmission cost. In this paper, we have proposed a novel LOD representation based on the concept of sharing a common vertex buffer among the various LOD meshes of a model. The novel LOD representation, called Common Vertex Buffer LOD, denoted as CVB-LOD, has the benefits of saving transmission and storage costs, lower mesh loading latency that effectively reduces the popping effect in switching LOD meshes.","PeriodicalId":142483,"journal":{"name":"2023 Sixth International Symposium on Computer, Consumer and Control (IS3C)","volume":"140 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131591561","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 : 2023-06-01DOI: 10.1109/IS3C57901.2023.00048
Mark Philip M. Sy, Rufo I. Marasigan, E. Festijo
Blockchain is a specific Distributed Ledger Technology (DLT) that is an emerging technology currently disrupting various fields. The aim of this paper is to explore ways to harness the advantages of blockchain while being implemented to existing systems. A permissioned blockchain can be established through Hyperledger Fabric (HLF) that utilizes ledgers that are interacted upon by a chaincode. An HLF network was established to investigate the custom chaincode. The scenario of the project was grounded on the functions performed in a web-based property inventory management system that uses a centralized database. The chaincode in the project was written using JavaScript and Node.js was used to create the whole chaincode source. A channel was built between the nodes of the blockchain where the chaincode was deployed. Subsequently, to open a gateway to the network, multiple Representational State Transfer (RST) Application Programming Interface (API) were created. Several gateway endpoints were tested through Insomnia, a cross-platform API client for RST. The tests performed employed various request methods (GET, POST, PUT, and DELETE) which resulted in evidence that the custom chaincode is fully functional and adheres to the OpenAPI specification. The paper concludes that it is highly feasible and advantageous to integrate a blockchain into an existing Web 2.0 system. Most functions and business logic in existing traditional systems can be reflected in a chaincode with proper planning and execution. In the future, other aspects of the blockchain network will be explored further.
{"title":"Hyperledger-Operated Blockchain Integration: Writing, Deploying and Testing Custom Chaincode","authors":"Mark Philip M. Sy, Rufo I. Marasigan, E. Festijo","doi":"10.1109/IS3C57901.2023.00048","DOIUrl":"https://doi.org/10.1109/IS3C57901.2023.00048","url":null,"abstract":"Blockchain is a specific Distributed Ledger Technology (DLT) that is an emerging technology currently disrupting various fields. The aim of this paper is to explore ways to harness the advantages of blockchain while being implemented to existing systems. A permissioned blockchain can be established through Hyperledger Fabric (HLF) that utilizes ledgers that are interacted upon by a chaincode. An HLF network was established to investigate the custom chaincode. The scenario of the project was grounded on the functions performed in a web-based property inventory management system that uses a centralized database. The chaincode in the project was written using JavaScript and Node.js was used to create the whole chaincode source. A channel was built between the nodes of the blockchain where the chaincode was deployed. Subsequently, to open a gateway to the network, multiple Representational State Transfer (RST) Application Programming Interface (API) were created. Several gateway endpoints were tested through Insomnia, a cross-platform API client for RST. The tests performed employed various request methods (GET, POST, PUT, and DELETE) which resulted in evidence that the custom chaincode is fully functional and adheres to the OpenAPI specification. The paper concludes that it is highly feasible and advantageous to integrate a blockchain into an existing Web 2.0 system. Most functions and business logic in existing traditional systems can be reflected in a chaincode with proper planning and execution. In the future, other aspects of the blockchain network will be explored further.","PeriodicalId":142483,"journal":{"name":"2023 Sixth International Symposium on Computer, Consumer and Control (IS3C)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130929322","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 : 2023-06-01DOI: 10.1109/IS3C57901.2023.00107
Yuan-Pei Chen, Qing-Cheng Long, Hao-Jen Wang, Shih-Sian Tang, Chia-Yen Lee
The primary objective of this study is to investigate and propose a reliable and accurate method for segmenting Diabetic Foot Ulcers (DFU) wounds. DFU is a prevalent complication among diabetic patients that can have severe consequences if not promptly addressed. However, the segmentation of DFU wounds poses a complex challenge due to variations in symptom color, size, and contrast, which can vary depending on the severity of the condition. Furthermore, challenges such as image noise, lighting and contrast variations, and labeling difficulties further complicate the taskTaking advantage of the rapid advancements in deep learning and its application to image segmentation, this study introduces a robust DFU segmentation model based on deep learning techniques. The proposed model aims to achieve accurate and precise segmentation of DFU wounds, addressing the aforementioned challenges..To assess the effectiveness of our segmentation strategy, we evaluated its performance using the public database of the 2022 DFU Segmentation Challenge. The results obtained demonstrate that our model achieves an average Dice coefficient of 83.44%, a substantial improvement compared to the average Dice coefficient of 72.87% achieved by other participants. These results serve as compelling evidence that our segmentation method successfully achieves high-precision segmentation of DFU wounds.
{"title":"A Deep Learning-Based Segmentation Strategy for Diabetic Foot Ulcers: Combining the Strengths of HarDNet-MSEG and SAM Models","authors":"Yuan-Pei Chen, Qing-Cheng Long, Hao-Jen Wang, Shih-Sian Tang, Chia-Yen Lee","doi":"10.1109/IS3C57901.2023.00107","DOIUrl":"https://doi.org/10.1109/IS3C57901.2023.00107","url":null,"abstract":"The primary objective of this study is to investigate and propose a reliable and accurate method for segmenting Diabetic Foot Ulcers (DFU) wounds. DFU is a prevalent complication among diabetic patients that can have severe consequences if not promptly addressed. However, the segmentation of DFU wounds poses a complex challenge due to variations in symptom color, size, and contrast, which can vary depending on the severity of the condition. Furthermore, challenges such as image noise, lighting and contrast variations, and labeling difficulties further complicate the taskTaking advantage of the rapid advancements in deep learning and its application to image segmentation, this study introduces a robust DFU segmentation model based on deep learning techniques. The proposed model aims to achieve accurate and precise segmentation of DFU wounds, addressing the aforementioned challenges..To assess the effectiveness of our segmentation strategy, we evaluated its performance using the public database of the 2022 DFU Segmentation Challenge. The results obtained demonstrate that our model achieves an average Dice coefficient of 83.44%, a substantial improvement compared to the average Dice coefficient of 72.87% achieved by other participants. These results serve as compelling evidence that our segmentation method successfully achieves high-precision segmentation of DFU wounds.","PeriodicalId":142483,"journal":{"name":"2023 Sixth International Symposium on Computer, Consumer and Control (IS3C)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132184205","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 : 2023-06-01DOI: 10.1109/IS3C57901.2023.00097
Kai-Zheng Zhong, J. Chen
Industrial development is gradually transforming towards intelligent autonomy by the development trend of Industry 4.0. The mechanical system fault diagnosis by using prevention techniques is urgent and necessary. Thus, various abnormal diagnosis and prediction technologies based on AI (Artificial Intelligence) are extensively proposed in this paper. Moreover, it is using of Acoustic Information ML (Machine learning) systems to collect acoustic information, which can in-depth acknowledge system health and prevent system failures. The system is developed from acoustic data based on a data-driven ML system. By the way, it is including vibration signals and acoustic images gathered from machinery. This developed system uses a deep learning model to analyze and combine input acoustic feature data. Besides, there is a diagnosis model developed with AI learning methods that can be used for decision-making problems of various goals. The system can be widely used in many aspects, especially in monitoring machine status and product quality with a high degree of identification. The application of AI architecture plus the adaptation of ML scheme are employed to satisfy the requirements of the following practical operations. For example, the factory automation, error diagnosis and prediction of motor failure of automatic factory equipment, and even automatic feedback system after abnormal sound detection. Once the aforementioned scenario is combined with EC (edge computing) migration module can inspire innovative design concepts. Through the collaboration of practical technology, such as acoustics analysis, AI, EC, electromagnetics, communications, and other theoretical basis subjects, it is convenient for flexible changes made in response to the trend of Edge operation. Especially, it can be formed as a unique customized system. In addition, this paper investigates the embedded system in the application of smart speakers as a basis. Then it is jointing with audio recording (motor audio emission) to establish an ML model which is trained by the audio emission data. There a DSP system on the arm-4mf chip is adopted to complete the complex calculation of audio signal conversion digital, which is able to completely facilitate the judgment of audio signal emission from a specific motor. In this paper, the results from the build framework illustrate the accuracy of audio judgment can reach 85%, but the accuracy of judgment for motor audio emission still cannot reach 20% at the current stage. There are also many possible problems encountered in the research. Eventually, this paper provides an analysis method to accomplish the goal of solving judgment misalignment of the motor axis. The method is based on TinyML (Tiny machine learning) techniques so that the field of IoT can move toward the direction of smart energy saving. This article believes that the AIOT (AI Internet of Thing) in the future of AI popularization is bound to affect and change people’s lifestyles
在工业4.0的发展趋势下，工业发展正逐步向智能自主方向转变。应用预防技术对机械系统进行故障诊断是迫切而必要的。因此，本文广泛提出了各种基于AI(人工智能)的异常诊断和预测技术。此外，利用声学信息ML (Acoustic Information Machine learning)系统收集声学信息，可以深入了解系统的健康状况，防止系统故障。该系统是基于数据驱动的ML系统从声学数据开发的。顺便说一下，它包括振动信号和从机械上收集的声学图像。该系统采用深度学习模型对输入的声学特征数据进行分析和组合。此外，利用人工智能学习方法开发了诊断模型，可用于各种目标的决策问题。该系统可广泛应用于许多方面，特别是在监控机器状态和产品质量方面具有很高的辨识度。采用AI架构的应用和ML方案的适配来满足以下实际操作的需求。例如工厂自动化，对自动化工厂设备的电机故障进行错误诊断和预测，甚至是异常声音检测后的自动反馈系统。一旦将上述场景与EC(边缘计算)迁移模块相结合，就可以激发创新的设计概念。通过声学分析、AI、EC、电磁学、通信等理论基础学科等实用技术的协同，便于针对Edge运营的趋势做出灵活的改变。特别是，它可以形成一个独特的定制系统。此外，本文还研究了嵌入式系统在智能音箱中的应用作为基础。然后结合音频记录(电机音频发射)建立机器学习模型，利用音频发射数据进行训练。arm-4mf芯片上采用DSP系统完成音频信号转换数字的复杂计算，能够完全方便判断特定电机发出的音频信号。本文构建框架的结果表明，音频判断的准确率可以达到85%，但现阶段对电机音频发射的判断准确率仍达不到20%。在研究中也可能遇到很多问题。最后，本文提供了一种分析方法，以达到解决电机轴线判断偏差的目的。该方法基于TinyML(微型机器学习)技术，使物联网领域朝着智能节能的方向发展。本文认为AIOT (AI物联网)在AI普及的未来，势必会影响和改变人们的生活方式。
{"title":"Experimental Applying Acoustic Emission to Fault Diagnosis and Prediction of Autonomous Devices","authors":"Kai-Zheng Zhong, J. Chen","doi":"10.1109/IS3C57901.2023.00097","DOIUrl":"https://doi.org/10.1109/IS3C57901.2023.00097","url":null,"abstract":"Industrial development is gradually transforming towards intelligent autonomy by the development trend of Industry 4.0. The mechanical system fault diagnosis by using prevention techniques is urgent and necessary. Thus, various abnormal diagnosis and prediction technologies based on AI (Artificial Intelligence) are extensively proposed in this paper. Moreover, it is using of Acoustic Information ML (Machine learning) systems to collect acoustic information, which can in-depth acknowledge system health and prevent system failures. The system is developed from acoustic data based on a data-driven ML system. By the way, it is including vibration signals and acoustic images gathered from machinery. This developed system uses a deep learning model to analyze and combine input acoustic feature data. Besides, there is a diagnosis model developed with AI learning methods that can be used for decision-making problems of various goals. The system can be widely used in many aspects, especially in monitoring machine status and product quality with a high degree of identification. The application of AI architecture plus the adaptation of ML scheme are employed to satisfy the requirements of the following practical operations. For example, the factory automation, error diagnosis and prediction of motor failure of automatic factory equipment, and even automatic feedback system after abnormal sound detection. Once the aforementioned scenario is combined with EC (edge computing) migration module can inspire innovative design concepts. Through the collaboration of practical technology, such as acoustics analysis, AI, EC, electromagnetics, communications, and other theoretical basis subjects, it is convenient for flexible changes made in response to the trend of Edge operation. Especially, it can be formed as a unique customized system. In addition, this paper investigates the embedded system in the application of smart speakers as a basis. Then it is jointing with audio recording (motor audio emission) to establish an ML model which is trained by the audio emission data. There a DSP system on the arm-4mf chip is adopted to complete the complex calculation of audio signal conversion digital, which is able to completely facilitate the judgment of audio signal emission from a specific motor. In this paper, the results from the build framework illustrate the accuracy of audio judgment can reach 85%, but the accuracy of judgment for motor audio emission still cannot reach 20% at the current stage. There are also many possible problems encountered in the research. Eventually, this paper provides an analysis method to accomplish the goal of solving judgment misalignment of the motor axis. The method is based on TinyML (Tiny machine learning) techniques so that the field of IoT can move toward the direction of smart energy saving. This article believes that the AIOT (AI Internet of Thing) in the future of AI popularization is bound to affect and change people’s lifestyles","PeriodicalId":142483,"journal":{"name":"2023 Sixth International Symposium on Computer, Consumer and Control (IS3C)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132271181","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 : 2023-06-01DOI: 10.1109/IS3C57901.2023.00018
Fityanul Akhyar, I. Wijayanto, Sofia Saidah, M. Khadafi, Rika Jesicha, Nabilla Anggraini, Ghanes Mahesa Aditya, Aldilano Bella Marlintha, Isack Farady, Chih-Yang Lin
Anthropometric detection tasks play a crucial role in medical and military recruitment processes as they help identify abnormalities that could otherwise be missed. Presently, these measurements are carried out manually using markers, which is a time-consuming process and prone to errors. This paper presents a computer vision-based system for detecting shoulder and knee abnormalities by automatically measuring shoulder tilt and knee distance to observe the knock-knees and bowlegs condition. The proposed system employs deep learning and BlazePose landmark estimation to accurately identify anomalies in the shoulders and legs. The Atan and Dist theoretical basis is applied for shoulder tilt and knee distance measurements, respectively. The proposed system can measure shoulder tilt and knee distance with an error rate of less than 10%. The automation of these measurements reduces the time required for examination and eliminates subjectivity and potential errors associated with manual measurements. Therefore, the proposed system has the potential to revolutionize shoulder and knee abnormality examinations by offering more accurate and efficient diagnoses.
{"title":"Shoulder and Knee Abnormality Examination Based on Artificial Landmark Estimation","authors":"Fityanul Akhyar, I. Wijayanto, Sofia Saidah, M. Khadafi, Rika Jesicha, Nabilla Anggraini, Ghanes Mahesa Aditya, Aldilano Bella Marlintha, Isack Farady, Chih-Yang Lin","doi":"10.1109/IS3C57901.2023.00018","DOIUrl":"https://doi.org/10.1109/IS3C57901.2023.00018","url":null,"abstract":"Anthropometric detection tasks play a crucial role in medical and military recruitment processes as they help identify abnormalities that could otherwise be missed. Presently, these measurements are carried out manually using markers, which is a time-consuming process and prone to errors. This paper presents a computer vision-based system for detecting shoulder and knee abnormalities by automatically measuring shoulder tilt and knee distance to observe the knock-knees and bowlegs condition. The proposed system employs deep learning and BlazePose landmark estimation to accurately identify anomalies in the shoulders and legs. The Atan and Dist theoretical basis is applied for shoulder tilt and knee distance measurements, respectively. The proposed system can measure shoulder tilt and knee distance with an error rate of less than 10%. The automation of these measurements reduces the time required for examination and eliminates subjectivity and potential errors associated with manual measurements. Therefore, the proposed system has the potential to revolutionize shoulder and knee abnormality examinations by offering more accurate and efficient diagnoses.","PeriodicalId":142483,"journal":{"name":"2023 Sixth International Symposium on Computer, Consumer and Control (IS3C)","volume":"131 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134458683","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 : 2023-06-01DOI: 10.1109/IS3C57901.2023.00042
Yu-Huei Cheng, Po-Yun Chen
In recent years, due to the rapid development of artificial intelligence, many related technologies have been widely used in various fields, including the deep learning-based license plate recognition technology. However, there are still some problems with the deep learning-based license plate recognition technology, such as the inability to process license plate images with low light and dynamic blur. In addition, in real life, due to factors such as the speed of vehicle movement and camera exposure time, license plates often appear blurred, causing difficulties in license plate recognition. Therefore, this study proposes a method for restoring dynamic blur license plates based on Generative Adversarial Network (GAN) technology. Using a dataset of 16,900 original license plates and 25,000 iterations of training, a high-fidelity license plate model was trained and a dataset of 3,000 high-fidelity license plates was randomly generated, with dynamic blur effects added to the high-fidelity license plate dataset. Then, using the structure of the cGAN network in the pix2pix technology, the clear license plate was restored from the dynamic blur license plate. Our model was able to effectively restore 2,873 dynamic blur license plates out of 3,000 license plates with a blur level of 85 or more in the preliminary experiment on the dataset, with a restoration rate of 95.7%. The proposed method is more excellent and adaptable to most physical environments than traditional image processing methods. In the future, we will further improve and optimize the model, and introduce effects such as pollution, exposure, darkness, and obstruction to train a license plate restoration model with multiple functions to meet the increasingly wide-ranging needs of license plate recognition applications.
{"title":"Using Generative Adversarial Network Technology for Repairing Dynamically Blurred License Plates","authors":"Yu-Huei Cheng, Po-Yun Chen","doi":"10.1109/IS3C57901.2023.00042","DOIUrl":"https://doi.org/10.1109/IS3C57901.2023.00042","url":null,"abstract":"In recent years, due to the rapid development of artificial intelligence, many related technologies have been widely used in various fields, including the deep learning-based license plate recognition technology. However, there are still some problems with the deep learning-based license plate recognition technology, such as the inability to process license plate images with low light and dynamic blur. In addition, in real life, due to factors such as the speed of vehicle movement and camera exposure time, license plates often appear blurred, causing difficulties in license plate recognition. Therefore, this study proposes a method for restoring dynamic blur license plates based on Generative Adversarial Network (GAN) technology. Using a dataset of 16,900 original license plates and 25,000 iterations of training, a high-fidelity license plate model was trained and a dataset of 3,000 high-fidelity license plates was randomly generated, with dynamic blur effects added to the high-fidelity license plate dataset. Then, using the structure of the cGAN network in the pix2pix technology, the clear license plate was restored from the dynamic blur license plate. Our model was able to effectively restore 2,873 dynamic blur license plates out of 3,000 license plates with a blur level of 85 or more in the preliminary experiment on the dataset, with a restoration rate of 95.7%. The proposed method is more excellent and adaptable to most physical environments than traditional image processing methods. In the future, we will further improve and optimize the model, and introduce effects such as pollution, exposure, darkness, and obstruction to train a license plate restoration model with multiple functions to meet the increasingly wide-ranging needs of license plate recognition applications.","PeriodicalId":142483,"journal":{"name":"2023 Sixth International Symposium on Computer, Consumer and Control (IS3C)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117351182","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}
This study proposes a MEC-integrated 5G Management and Orchestration (5G MANO) platform architecture for Multi-access Edge Computing (MEC) deployment and orchestration. Since network slicing can provide different types of network service requirements, users can provide better service quality by selecting network slicing to interface with the corresponding MEC host. This study designs and integrates the 5G MANO platform with MEC and the 5G core network. Also, the experimental results show that the designed 5G integrated MEC network slicing architecture provides offloading traffic to MEC hosts and can enable MEC app services to obtain higher network throughput.
{"title":"Design of a MEC-integrated 5G MANO Platform","authors":"Hung-Ming Chen, Yung-Feng Lu, Chun-Hung Tsai, Che-Jung Chang","doi":"10.1109/IS3C57901.2023.00063","DOIUrl":"https://doi.org/10.1109/IS3C57901.2023.00063","url":null,"abstract":"This study proposes a MEC-integrated 5G Management and Orchestration (5G MANO) platform architecture for Multi-access Edge Computing (MEC) deployment and orchestration. Since network slicing can provide different types of network service requirements, users can provide better service quality by selecting network slicing to interface with the corresponding MEC host. This study designs and integrates the 5G MANO platform with MEC and the 5G core network. Also, the experimental results show that the designed 5G integrated MEC network slicing architecture provides offloading traffic to MEC hosts and can enable MEC app services to obtain higher network throughput.","PeriodicalId":142483,"journal":{"name":"2023 Sixth International Symposium on Computer, Consumer and Control (IS3C)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122169903","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 : 2023-06-01DOI: 10.1109/IS3C57901.2023.00046
Kuan-Yu Chen, Chin-Hsien Wu, Cheng-Tze Lee
Solid-state drives (SSDs) using NAND flash memory are the popular storage systems and are widely used in consumer and enterprise systems. Due to the erase-before-write characteristic, NAND flash memory requires time-consuming garbage collection that consists of pages copying and block erasing. Moreover, garbage collection will suspend other I/O requests and cause long-tail latency. In this paper, we propose short-term and long-term idle time detectors to exploit the idle time and reduce the long-tail latency by performing garbage collection on idle time. The experimental results show that our method can reduce the long-tail latency in SSDs.
{"title":"Short-Term and Long-Term Idle Time Detectors for Reducing Long-Tail Latency in Solid-State Drives","authors":"Kuan-Yu Chen, Chin-Hsien Wu, Cheng-Tze Lee","doi":"10.1109/IS3C57901.2023.00046","DOIUrl":"https://doi.org/10.1109/IS3C57901.2023.00046","url":null,"abstract":"Solid-state drives (SSDs) using NAND flash memory are the popular storage systems and are widely used in consumer and enterprise systems. Due to the erase-before-write characteristic, NAND flash memory requires time-consuming garbage collection that consists of pages copying and block erasing. Moreover, garbage collection will suspend other I/O requests and cause long-tail latency. In this paper, we propose short-term and long-term idle time detectors to exploit the idle time and reduce the long-tail latency by performing garbage collection on idle time. The experimental results show that our method can reduce the long-tail latency in SSDs.","PeriodicalId":142483,"journal":{"name":"2023 Sixth International Symposium on Computer, Consumer and Control (IS3C)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132961137","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：