Pub Date : 2021-04-01DOI: 10.1109/ICEAST52143.2021.9426262
U. Jansri, N. Chirakalwasan, Busarakum Chaitusaney, Supasuta Busayakanon, Thamonwan Khongjui, S. Tretriluxana
Sleep apnea, a sleep-disordered breathing (SDB), is defined as repeatedly intermittent cessation of breathing during sleep. It causes various life-threatening diseases. The American Academy of Sleep Medicine (AASM) releases the manual for sleep data scoring. Patients with SDB are prescribed to be monitored at the sleep clinic where several physiological data are recorded, called polysomnogram (PSG). The massive PSG data must be scored by the well-trained expert before being diagnosed by the physician. Our research is to use the Artificial Intelligence (AI) in sleep data scoring, particularly in respiratory events detection. Three ready-made Convolution Neural Networks (CNN); AlexNet, ResNet-50, and VGG-16, with transfer learning were applied to classify 5 overnight PSG data from Chulalongkorn hospital. Our preliminary results showed that all networks provide higher classification result in European Data Format (EDF) than in the text (ASCII) formats (71% vs 54%). The ResNet-50 model structure performed better than the other two networks on both data formats. As expected, the visualized (EDF) data is better than the unconditioned (ASCII) data. Our future development is modifying learning model to increase the scoring performance from more recruited PSG data.
睡眠呼吸暂停是一种睡眠呼吸障碍(SDB)，被定义为睡眠中反复间歇性呼吸停止。它会导致各种危及生命的疾病。美国睡眠医学学会(AASM)发布了睡眠数据评分手册。患有SDB的患者需要在睡眠诊所接受监测，并记录多项生理数据，称为多导睡眠图(PSG)。大量的PSG数据必须由训练有素的专家评分，然后才能由医生诊断。我们的研究是在睡眠数据评分中使用人工智能(AI)，特别是在呼吸事件检测中。三个现成的卷积神经网络(CNN);应用AlexNet、ResNet-50和VGG-16结合迁移学习对来自朱拉隆功医院的5个夜间PSG数据进行分类。我们的初步结果表明，所有网络在欧洲数据格式(EDF)下提供的分类结果比在文本(ASCII)格式下提供的分类结果更高(71% vs 54%)。ResNet-50模型结构在两种数据格式上的表现都优于其他两种网络。正如预期的那样，可视化(EDF)数据优于无条件(ASCII)数据。我们未来的发展是修改学习模型，从更多招募的PSG数据中提高评分性能。
{"title":"Automatic Sleep Data Scoring by Artificial Intelligence: A Pilot Study in Thai Population","authors":"U. Jansri, N. Chirakalwasan, Busarakum Chaitusaney, Supasuta Busayakanon, Thamonwan Khongjui, S. Tretriluxana","doi":"10.1109/ICEAST52143.2021.9426262","DOIUrl":"https://doi.org/10.1109/ICEAST52143.2021.9426262","url":null,"abstract":"Sleep apnea, a sleep-disordered breathing (SDB), is defined as repeatedly intermittent cessation of breathing during sleep. It causes various life-threatening diseases. The American Academy of Sleep Medicine (AASM) releases the manual for sleep data scoring. Patients with SDB are prescribed to be monitored at the sleep clinic where several physiological data are recorded, called polysomnogram (PSG). The massive PSG data must be scored by the well-trained expert before being diagnosed by the physician. Our research is to use the Artificial Intelligence (AI) in sleep data scoring, particularly in respiratory events detection. Three ready-made Convolution Neural Networks (CNN); AlexNet, ResNet-50, and VGG-16, with transfer learning were applied to classify 5 overnight PSG data from Chulalongkorn hospital. Our preliminary results showed that all networks provide higher classification result in European Data Format (EDF) than in the text (ASCII) formats (71% vs 54%). The ResNet-50 model structure performed better than the other two networks on both data formats. As expected, the visualized (EDF) data is better than the unconditioned (ASCII) data. Our future development is modifying learning model to increase the scoring performance from more recruited PSG data.","PeriodicalId":416531,"journal":{"name":"2021 7th International Conference on Engineering, Applied Sciences and Technology (ICEAST)","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133534766","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 : 2021-04-01DOI: 10.1109/ICEAST52143.2021.9426310
C. Srinilta, Sivakorn Kanharattanachai
Classification performance depends highly on data distribution. In real life, data often come imbalanced where one class is found more often than others. SMOTE-based algorithms are usually used to handle the class imbalance problem. One key parameter that algorithms in SMOTE family require is k-the number of nearest neighbors with respect to a certain data point. K that fits the dataset the most gives the optimum performance. This paper proposes an approach to suggest a value of the parameter k using Natural Neighbor algorithm. Datasets are made balanced by four SMOTE-based algorithms–standard SMOTE, Safe-Level-SMOTE, ModifiedSMOTE and Weighted-SMOTE. The F-measure and Recall matrices are used to evaluate classification performance of a Support Vector Machine classifier running against six datasets with different imbalance ratios. The results show that, the average classification performance achieved by the proposed k’s is closer to the optimum when compared with the performance given by the default value of k.
{"title":"Application of Natural Neighbor-based Algorithm on Oversampling SMOTE Algorithms","authors":"C. Srinilta, Sivakorn Kanharattanachai","doi":"10.1109/ICEAST52143.2021.9426310","DOIUrl":"https://doi.org/10.1109/ICEAST52143.2021.9426310","url":null,"abstract":"Classification performance depends highly on data distribution. In real life, data often come imbalanced where one class is found more often than others. SMOTE-based algorithms are usually used to handle the class imbalance problem. One key parameter that algorithms in SMOTE family require is k-the number of nearest neighbors with respect to a certain data point. K that fits the dataset the most gives the optimum performance. This paper proposes an approach to suggest a value of the parameter k using Natural Neighbor algorithm. Datasets are made balanced by four SMOTE-based algorithms–standard SMOTE, Safe-Level-SMOTE, ModifiedSMOTE and Weighted-SMOTE. The F-measure and Recall matrices are used to evaluate classification performance of a Support Vector Machine classifier running against six datasets with different imbalance ratios. The results show that, the average classification performance achieved by the proposed k’s is closer to the optimum when compared with the performance given by the default value of k.","PeriodicalId":416531,"journal":{"name":"2021 7th International Conference on Engineering, Applied Sciences and Technology (ICEAST)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130925040","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 : 2021-04-01DOI: 10.1109/ICEAST52143.2021.9426280
Natchanon Wanthong, K. Ohyama
This paper proposes an excitation angle condition capable creating high generation efficiency for a switched reluctance generator (SRG) with low loss. This paper examines high power generation efficiency by reducing copper loss in 12/8 switched reluctance generators operated at various speeds within a wind power generation system. For this purpose, excited current waveforms and excitation angles capable of reducing the copper loss are considered. The current waveforms that appear in the duration of the excitation stage are classified into three types. The copper loss and energy conversion loop that depend on the excitation current waveforms are also analyzed. Furthermore, the correlations between the excitation condition and power generation efficiency, copper loss, excited current waveforms and energy conversion loop are considered. Finally, the excitation conditions which reduce copper loss and improve the power generation efficiency at various speeds are summarized.
{"title":"Effect of the Excitation Conditions on the Power Generation Efficiency of a Switched Reluctance Generator","authors":"Natchanon Wanthong, K. Ohyama","doi":"10.1109/ICEAST52143.2021.9426280","DOIUrl":"https://doi.org/10.1109/ICEAST52143.2021.9426280","url":null,"abstract":"This paper proposes an excitation angle condition capable creating high generation efficiency for a switched reluctance generator (SRG) with low loss. This paper examines high power generation efficiency by reducing copper loss in 12/8 switched reluctance generators operated at various speeds within a wind power generation system. For this purpose, excited current waveforms and excitation angles capable of reducing the copper loss are considered. The current waveforms that appear in the duration of the excitation stage are classified into three types. The copper loss and energy conversion loop that depend on the excitation current waveforms are also analyzed. Furthermore, the correlations between the excitation condition and power generation efficiency, copper loss, excited current waveforms and energy conversion loop are considered. Finally, the excitation conditions which reduce copper loss and improve the power generation efficiency at various speeds are summarized.","PeriodicalId":416531,"journal":{"name":"2021 7th International Conference on Engineering, Applied Sciences and Technology (ICEAST)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128463561","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 : 2021-04-01DOI: 10.1109/ICEAST52143.2021.9426252
N. Atiwongsangthong
This research presents the effect of the constant current density on nanoporous silicon formation by double tank electrochemical etching cell without coating aluminum on the backside of silicon wafer. In this paper, the constant current density is increased from 10 mA/cm2 to 25 mA/cm2 during the anodization process by using hydrofluoric acid and ethanol at ratio 4:1 and the etching time are 10 minute. Gravimetric and Photoluminescence measurement were performed to investigate the porosity and the uniform distribution of nanoporous silicon layer respectively. The result shows that the porosity of nanoporous silicon layer was increased when the constant current density increased. The range of the porosity 46% to 80% and it is dependent on constant current density. The photoluminescence measurement with irradiate ultraviolet light on the surface of samples it was observed that hight uniformity of photoluminescence intensity. Indicates that the nanoporous silicon surface are more uniform distribution. This research discovers that the constant current density has large effect on the porosity of nanoporous silicon layer. Results show good improvement the nanoporous silicon formation by double tank electrochemical etching cell without coating aluminum on the backside of silicon.
{"title":"The Study of Porosity and Photoluminescence Properties of Nanoporous Silicon Layer Under Anodization Current Density Formation by Double Tank Electrochemical Etching Cell","authors":"N. Atiwongsangthong","doi":"10.1109/ICEAST52143.2021.9426252","DOIUrl":"https://doi.org/10.1109/ICEAST52143.2021.9426252","url":null,"abstract":"This research presents the effect of the constant current density on nanoporous silicon formation by double tank electrochemical etching cell without coating aluminum on the backside of silicon wafer. In this paper, the constant current density is increased from 10 mA/cm2 to 25 mA/cm2 during the anodization process by using hydrofluoric acid and ethanol at ratio 4:1 and the etching time are 10 minute. Gravimetric and Photoluminescence measurement were performed to investigate the porosity and the uniform distribution of nanoporous silicon layer respectively. The result shows that the porosity of nanoporous silicon layer was increased when the constant current density increased. The range of the porosity 46% to 80% and it is dependent on constant current density. The photoluminescence measurement with irradiate ultraviolet light on the surface of samples it was observed that hight uniformity of photoluminescence intensity. Indicates that the nanoporous silicon surface are more uniform distribution. This research discovers that the constant current density has large effect on the porosity of nanoporous silicon layer. Results show good improvement the nanoporous silicon formation by double tank electrochemical etching cell without coating aluminum on the backside of silicon.","PeriodicalId":416531,"journal":{"name":"2021 7th International Conference on Engineering, Applied Sciences and Technology (ICEAST)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117153088","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 : 2021-04-01DOI: 10.1109/ICEAST52143.2021.9426281
Wandee Aunsa-Ard, T. Pobkrut, T. Kerdcharoen, S. Siyang, Nathamanee Prombaingoen
This paper describes the development and application of our electronic nose (e-nose) machine and algorithms for monitoring of malodor emission. Malodor emission from livestock farms have been known as a significant source of odor nuisance resulting in increased complaints and environmental issues. E-nose technology has provided solutions to variety of these odorous problems with identification of the odor source and real-time monitoring of odor diffusion into the environment. This lab-developed electronic nose system consists of eight metal oxide semiconductor (MOX) gas sensors as sensing materials, including a humidity sensor and a temperature sensor. The gas sensors were specifically selected for the main volatile compounds emitted from the livestock farms. Principal Component Analysis (PCA) was used as classification algorithms combined with data analysis techniques, which enable the recognition of different odor samples. In this work, five commercial poultry farms were selected for odor monitoring using the in-lab developed e-nose machine. The field experiments were conducted at various sites in the farms such as chicken houses, manure storage, biogas facilities, downwind points and in nearby villages. Odor concentrations were mainly detected behind the poultry house fan (Max. 11 odor unit). In addition, the malodor sources have been investigated with the e-nose in each poultry farm. High concentrations of malodor were identified in the poultry farms with poor manure handling system and poor building management. In conclusion, the e-nose technology has the potential of providing monitoring capabilities for livestock and agricultural industries. The use of e-nose device is recommended to apply in the livestock farms to reduce neighbourhood complaints and risk on workers’ health and safety.
{"title":"Development of Intelligent Electronic Nose for Livestock Industries","authors":"Wandee Aunsa-Ard, T. Pobkrut, T. Kerdcharoen, S. Siyang, Nathamanee Prombaingoen","doi":"10.1109/ICEAST52143.2021.9426281","DOIUrl":"https://doi.org/10.1109/ICEAST52143.2021.9426281","url":null,"abstract":"This paper describes the development and application of our electronic nose (e-nose) machine and algorithms for monitoring of malodor emission. Malodor emission from livestock farms have been known as a significant source of odor nuisance resulting in increased complaints and environmental issues. E-nose technology has provided solutions to variety of these odorous problems with identification of the odor source and real-time monitoring of odor diffusion into the environment. This lab-developed electronic nose system consists of eight metal oxide semiconductor (MOX) gas sensors as sensing materials, including a humidity sensor and a temperature sensor. The gas sensors were specifically selected for the main volatile compounds emitted from the livestock farms. Principal Component Analysis (PCA) was used as classification algorithms combined with data analysis techniques, which enable the recognition of different odor samples. In this work, five commercial poultry farms were selected for odor monitoring using the in-lab developed e-nose machine. The field experiments were conducted at various sites in the farms such as chicken houses, manure storage, biogas facilities, downwind points and in nearby villages. Odor concentrations were mainly detected behind the poultry house fan (Max. 11 odor unit). In addition, the malodor sources have been investigated with the e-nose in each poultry farm. High concentrations of malodor were identified in the poultry farms with poor manure handling system and poor building management. In conclusion, the e-nose technology has the potential of providing monitoring capabilities for livestock and agricultural industries. The use of e-nose device is recommended to apply in the livestock farms to reduce neighbourhood complaints and risk on workers’ health and safety.","PeriodicalId":416531,"journal":{"name":"2021 7th International Conference on Engineering, Applied Sciences and Technology (ICEAST)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125294014","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 : 2021-04-01DOI: 10.1109/ICEAST52143.2021.9426298
K. Thungsook, S. Promwong, N. Pattanadech
This paper explains and demonstrates how to measured high-frequency signals in a distribution transformer. The high-frequency signals tend to suffer attenuation while propagating within a transformer to a detection device. In order to understand the propagation and attenuation characteristics of the high-frequency signals within the transformer, the highfrequency signal simulation in the transformer is essential. In this research, the reflection and the attenuation characteristics of high-frequency signals amplitudes as well as the frequency components of the high frequency while propagation through transformer winding and a core of transformer were examined both in the time domain and frequency domain measurement. The detail of high-frequency signals, including methods of detection device and material properties, are described in this paper. The infallibility of the experiment results was also evaluated.
{"title":"The Reflection and Attenuation of High-Frequency Signals in a Distribution Transformer","authors":"K. Thungsook, S. Promwong, N. Pattanadech","doi":"10.1109/ICEAST52143.2021.9426298","DOIUrl":"https://doi.org/10.1109/ICEAST52143.2021.9426298","url":null,"abstract":"This paper explains and demonstrates how to measured high-frequency signals in a distribution transformer. The high-frequency signals tend to suffer attenuation while propagating within a transformer to a detection device. In order to understand the propagation and attenuation characteristics of the high-frequency signals within the transformer, the highfrequency signal simulation in the transformer is essential. In this research, the reflection and the attenuation characteristics of high-frequency signals amplitudes as well as the frequency components of the high frequency while propagation through transformer winding and a core of transformer were examined both in the time domain and frequency domain measurement. The detail of high-frequency signals, including methods of detection device and material properties, are described in this paper. The infallibility of the experiment results was also evaluated.","PeriodicalId":416531,"journal":{"name":"2021 7th International Conference on Engineering, Applied Sciences and Technology (ICEAST)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125585122","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 : 2021-04-01DOI: 10.1109/ICEAST52143.2021.9426291
T. Asra, Ahmad Setiadi, Mahmud Safudin, Endah Wiji Lestari, Nila Hardi, D. Alamsyah
The kidneys are one of the important organs for humans with various tasks to keep humans healthy. One of them is to remove excess water and toxins from the blood. The chronic kidney is a disease that interferes with kidney function that is progressive and irreversible in which the body’s ability to fail to maintain metabolism and fluid and electrolyte balance resulting in uremia. There have been many studies aimed at predicting chronic kidney disease. In this study, using the C4.5 algorithm as a classification algorithm and by adding the Adaboost algorithm. The results showed that using the algorithm obtained an accuracy value of 95%, 92% precision, and Area Under the Curve by 1. Whereas using the algorithm combined with Adaboost got an accuracy value is precision, and Area Under the Curve by 1. Based on the results accuracy, precision, and Area Under the Curve, it can be seen by using Adaboost in the algorithm can improve the results of accuracy and precision with very good classification, because the Area Under the Curve value is accepted.
肾脏是人体重要器官之一，担负着维持人体健康的各种任务。其中之一是去除血液中多余的水分和毒素。慢性肾脏病是一种进行性和不可逆的干扰肾功能的疾病，在这种疾病中，身体的能力无法维持新陈代谢和液体和电解质的平衡，导致尿毒症。有许多研究旨在预测慢性肾脏疾病。本研究采用C4.5算法作为分类算法，并加入Adaboost算法。结果表明，使用该算法获得的精度值为95%，精度为92%，曲线下面积为1。而结合Adaboost算法得到的精度值为precision，和Area Under the Curve by 1。从结果的准确度、精度和Area Under the Curve可以看出，在算法中使用Adaboost可以很好的提高准确度和精度的结果，因为Area Under the Curve的值是可以接受的。
{"title":"Implementation of AdaBoost Algorithm in Prediction of Chronic Kidney Disease","authors":"T. Asra, Ahmad Setiadi, Mahmud Safudin, Endah Wiji Lestari, Nila Hardi, D. Alamsyah","doi":"10.1109/ICEAST52143.2021.9426291","DOIUrl":"https://doi.org/10.1109/ICEAST52143.2021.9426291","url":null,"abstract":"The kidneys are one of the important organs for humans with various tasks to keep humans healthy. One of them is to remove excess water and toxins from the blood. The chronic kidney is a disease that interferes with kidney function that is progressive and irreversible in which the body’s ability to fail to maintain metabolism and fluid and electrolyte balance resulting in uremia. There have been many studies aimed at predicting chronic kidney disease. In this study, using the C4.5 algorithm as a classification algorithm and by adding the Adaboost algorithm. The results showed that using the algorithm obtained an accuracy value of 95%, 92% precision, and Area Under the Curve by 1. Whereas using the algorithm combined with Adaboost got an accuracy value is precision, and Area Under the Curve by 1. Based on the results accuracy, precision, and Area Under the Curve, it can be seen by using Adaboost in the algorithm can improve the results of accuracy and precision with very good classification, because the Area Under the Curve value is accepted.","PeriodicalId":416531,"journal":{"name":"2021 7th International Conference on Engineering, Applied Sciences and Technology (ICEAST)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133177412","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 : 2021-04-01DOI: 10.1109/ICEAST52143.2021.9426279
C. Jinjakam, Pichamol Phothong, Piyarat Pearodwong, Thana Hongsuwan
Classroom allocation is one of the most important problems of academic management. The new semester may vary on different sizes of the student population, the number of subjects, provided classrooms, and so forth. Over-allocation and under-allocation of the classroom space directly affect the feeling comfortably of students. Furthermore, not only the facilities provided inside the classroom but also the classroom distance affect the quality of teaching and learning of room members. This paper studies classroom allocation in the School of Engineering, King Mongkut’s Institute of Technology, Ladkrabang, Thailand. The main cohort is around 11,310 Thai bachelor students that are studying in 55 Thai courses. These courses have 1,624 subjects. Some departments provide room for their courses, but the main course of the first year and second-year students are managed under the central classroom allocation. Total 128 central classrooms provided in 5 buildings (data on 8 September 2020), which vary on size and number of seats. From traditional manual management to web-based management, user experience design is chosen method to improve the satisfaction of the automatic system. User interviews are applied with the 30s-years experienced staffs in the academic department and physical and environment department in the School of Engineering, KMITL. Cases of lecturers’ scenarios are transferred to the function of the classroom allocation system. Classroom allocation in functions of capacity and location management is proposed in a user- friendly web-based program. Automatic classroom allocation results 203 of 245 subjects use central classroom location similar to the traditional manual arrangement, and 26 subjects are set in the different building from the assigned zone that improve from the traditional management.
{"title":"Classroom Allocation System with User Experience Design","authors":"C. Jinjakam, Pichamol Phothong, Piyarat Pearodwong, Thana Hongsuwan","doi":"10.1109/ICEAST52143.2021.9426279","DOIUrl":"https://doi.org/10.1109/ICEAST52143.2021.9426279","url":null,"abstract":"Classroom allocation is one of the most important problems of academic management. The new semester may vary on different sizes of the student population, the number of subjects, provided classrooms, and so forth. Over-allocation and under-allocation of the classroom space directly affect the feeling comfortably of students. Furthermore, not only the facilities provided inside the classroom but also the classroom distance affect the quality of teaching and learning of room members. This paper studies classroom allocation in the School of Engineering, King Mongkut’s Institute of Technology, Ladkrabang, Thailand. The main cohort is around 11,310 Thai bachelor students that are studying in 55 Thai courses. These courses have 1,624 subjects. Some departments provide room for their courses, but the main course of the first year and second-year students are managed under the central classroom allocation. Total 128 central classrooms provided in 5 buildings (data on 8 September 2020), which vary on size and number of seats. From traditional manual management to web-based management, user experience design is chosen method to improve the satisfaction of the automatic system. User interviews are applied with the 30s-years experienced staffs in the academic department and physical and environment department in the School of Engineering, KMITL. Cases of lecturers’ scenarios are transferred to the function of the classroom allocation system. Classroom allocation in functions of capacity and location management is proposed in a user- friendly web-based program. Automatic classroom allocation results 203 of 245 subjects use central classroom location similar to the traditional manual arrangement, and 26 subjects are set in the different building from the assigned zone that improve from the traditional management.","PeriodicalId":416531,"journal":{"name":"2021 7th International Conference on Engineering, Applied Sciences and Technology (ICEAST)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121415197","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 : 2021-04-01DOI: 10.1109/ICEAST52143.2021.9426288
Thanapart Sangkharat, Jomphop La-or
The barcode system is used in various purpose. In industrial sector, barcode is used for identifying product in the manufacturing process. However, the barcode systems in industrial factory requires special barcode reader and the industrial barcode reader is more complicated and expensive than the conventional barcode reader.Recently, all smart phone can be applied for barcode reader application but there is no study how to use the smart phone barcode reader application in industrial factory. Therefore, this study would consider how to use the smart phone for industrial barcode reader system. The Android smart phone was used to develop barcode reader application by cooperating with the barcode reader library and the barcode reader system in manufacturing process was simulated. The barcodes for this experiment were ID barcode and QR code. Moreover, the damaged barcodes were tested in the experiments and each experimental was continue tested nonstop for 24 hours.The result found that smart phone can read ID barcode and QR code. The readable rates of ID barcode (complete and damage barcode) were 100%. The readable rates of QR code at 30 and 50 photos per minute were 92.5% and 85%. Thus, the smart phone has an opportunity to use as ID barcode reader in industrial factory. For QR code, the readable rate result is low. However, there are many advantages to use smart phone for barcode reader such as price, flexibility, easy to use and reinstall. So, it is a challenge to use smart phone for industrial barcode reader.
{"title":"Application of Smart Phone for Industrial Barcode Scanner","authors":"Thanapart Sangkharat, Jomphop La-or","doi":"10.1109/ICEAST52143.2021.9426288","DOIUrl":"https://doi.org/10.1109/ICEAST52143.2021.9426288","url":null,"abstract":"The barcode system is used in various purpose. In industrial sector, barcode is used for identifying product in the manufacturing process. However, the barcode systems in industrial factory requires special barcode reader and the industrial barcode reader is more complicated and expensive than the conventional barcode reader.Recently, all smart phone can be applied for barcode reader application but there is no study how to use the smart phone barcode reader application in industrial factory. Therefore, this study would consider how to use the smart phone for industrial barcode reader system. The Android smart phone was used to develop barcode reader application by cooperating with the barcode reader library and the barcode reader system in manufacturing process was simulated. The barcodes for this experiment were ID barcode and QR code. Moreover, the damaged barcodes were tested in the experiments and each experimental was continue tested nonstop for 24 hours.The result found that smart phone can read ID barcode and QR code. The readable rates of ID barcode (complete and damage barcode) were 100%. The readable rates of QR code at 30 and 50 photos per minute were 92.5% and 85%. Thus, the smart phone has an opportunity to use as ID barcode reader in industrial factory. For QR code, the readable rate result is low. However, there are many advantages to use smart phone for barcode reader such as price, flexibility, easy to use and reinstall. So, it is a challenge to use smart phone for industrial barcode reader.","PeriodicalId":416531,"journal":{"name":"2021 7th International Conference on Engineering, Applied Sciences and Technology (ICEAST)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125323700","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 : 2021-04-01DOI: 10.1109/ICEAST52143.2021.9426282
T. Wiangtong, P. Pookaiyaudom, P. Sirisuk
This paper presents the implementation of IoT (Internet of Things) for monitoring and control in the tethered drone PMU (Power Management Unit) system. Traditionally, power source of a drone is from battery which causes the tradeoff between weight and flight time. To overcome this limitation, stationary tethered drones consume energy from a ground energy source thru light weighted power cords. Tethered drones’ benefits are ideally suited for military uses such as border security and surveillance system, where day-night surveillance capabilities are crucial to monitoring perimeters. It can also be used for tactical communication, fast-deployed relay stations. Since a long operation time, monitoring and control power onboard becomes necessary. Using extra cords for communication will increase the airborne weight. This paper presents the exploitation of wireless IoT system for the tethered drone PMU system. It consists of the PMU-ground constantly delivering 4000W power to PMU-air for BLDC motors also various payloads. With additional IoT including Raspberry Pi, NodeMCUs and sensors, users at ground station can monitor voltage and current values in real-time, also can control MOSFET switches connected with loads onboard via PMU touch screen monitor or smart devices.
{"title":"Exploitation of IoTs for PMU in Tethered Drone","authors":"T. Wiangtong, P. Pookaiyaudom, P. Sirisuk","doi":"10.1109/ICEAST52143.2021.9426282","DOIUrl":"https://doi.org/10.1109/ICEAST52143.2021.9426282","url":null,"abstract":"This paper presents the implementation of IoT (Internet of Things) for monitoring and control in the tethered drone PMU (Power Management Unit) system. Traditionally, power source of a drone is from battery which causes the tradeoff between weight and flight time. To overcome this limitation, stationary tethered drones consume energy from a ground energy source thru light weighted power cords. Tethered drones’ benefits are ideally suited for military uses such as border security and surveillance system, where day-night surveillance capabilities are crucial to monitoring perimeters. It can also be used for tactical communication, fast-deployed relay stations. Since a long operation time, monitoring and control power onboard becomes necessary. Using extra cords for communication will increase the airborne weight. This paper presents the exploitation of wireless IoT system for the tethered drone PMU system. It consists of the PMU-ground constantly delivering 4000W power to PMU-air for BLDC motors also various payloads. With additional IoT including Raspberry Pi, NodeMCUs and sensors, users at ground station can monitor voltage and current values in real-time, also can control MOSFET switches connected with loads onboard via PMU touch screen monitor or smart devices.","PeriodicalId":416531,"journal":{"name":"2021 7th International Conference on Engineering, Applied Sciences and Technology (ICEAST)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115113969","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：