Pub Date : 2021-04-01DOI: 10.1109/ICEAST52143.2021.9426250
Dhanachai Pinitsava, P. Surinlert, Worapan Kusakunniran
Shrimp is a sensitive creature and cannibalism. When shrimp die because of some factor in the water, for example, the temperature suddenly changed. Shrimp will start the cannibalization process. Farmers need to understand the ecological process to avoid this situation. Water management is one of them, and water quality properties take the main role of it. If farmers know the water’s current and future situations, it could help them handle unexpected/unforeseen situations. In this research, forecasting water quality values by using Monte Carlo Tree Search (MCTS) is proposed. Salinity, pH, Dissolved Oxygen, Temperature was collected by IoT Arduino based device with Solar cell as a power source and sent data using NB-IoT module. Linear interpolation was manipulated raw data for creating a new dataset of every 30 minutes. The data was given a grade from 1 to 5. MCTS forecast value by cutting the outliner in the selection phase. After selecting the node, expand the selected node, simulate the node until found the target node, give a score, and calculate and update the score back to the beginning node. The result is the route from the beginning node to the target node that has the highest score. The device can float on the water and work all day all night. The data collected from the device does not cover the entire pond’s water quality because there is one device in the large area of shrimp ponds. The MCTS can forecast the water quality in the small area around the device. When the farmer knows the water’s future situation will help them reduce the risk of losing the shrimp.
{"title":"Water Quality Forecasting in Shrimp Cultures based on Monte Carlo Tree Search","authors":"Dhanachai Pinitsava, P. Surinlert, Worapan Kusakunniran","doi":"10.1109/ICEAST52143.2021.9426250","DOIUrl":"https://doi.org/10.1109/ICEAST52143.2021.9426250","url":null,"abstract":"Shrimp is a sensitive creature and cannibalism. When shrimp die because of some factor in the water, for example, the temperature suddenly changed. Shrimp will start the cannibalization process. Farmers need to understand the ecological process to avoid this situation. Water management is one of them, and water quality properties take the main role of it. If farmers know the water’s current and future situations, it could help them handle unexpected/unforeseen situations. In this research, forecasting water quality values by using Monte Carlo Tree Search (MCTS) is proposed. Salinity, pH, Dissolved Oxygen, Temperature was collected by IoT Arduino based device with Solar cell as a power source and sent data using NB-IoT module. Linear interpolation was manipulated raw data for creating a new dataset of every 30 minutes. The data was given a grade from 1 to 5. MCTS forecast value by cutting the outliner in the selection phase. After selecting the node, expand the selected node, simulate the node until found the target node, give a score, and calculate and update the score back to the beginning node. The result is the route from the beginning node to the target node that has the highest score. The device can float on the water and work all day all night. The data collected from the device does not cover the entire pond’s water quality because there is one device in the large area of shrimp ponds. The MCTS can forecast the water quality in the small area around the device. When the farmer knows the water’s future situation will help them reduce the risk of losing the shrimp.","PeriodicalId":416531,"journal":{"name":"2021 7th International Conference on Engineering, Applied Sciences and Technology (ICEAST)","volume":"323 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":"116777770","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/ICEAST52143.2021.9426297
Chuthitep Sukhawit, B. Burapattanasiri, U. Torteanchai, S. Lerkvaranyu, B. Knobnob, M. Kumngern
This paper presents a new electronically tunable differential difference current conveyor (DDCC) using operational transconductance amplifiers (OTAs). Unlike conventional DDCC, the proposed DDCC offers current gain between z- and x-terminal that can be controlled electronically by bias currents. The DDCC-based OTA can be investigated both simulation and experiment tests. The proposed DDCC is used to implement a quadrature oscillator to confirm workability.
{"title":"Electronically Tunable Differential Difference Current Conveyor Using OTAs","authors":"Chuthitep Sukhawit, B. Burapattanasiri, U. Torteanchai, S. Lerkvaranyu, B. Knobnob, M. Kumngern","doi":"10.1109/ICEAST52143.2021.9426297","DOIUrl":"https://doi.org/10.1109/ICEAST52143.2021.9426297","url":null,"abstract":"This paper presents a new electronically tunable differential difference current conveyor (DDCC) using operational transconductance amplifiers (OTAs). Unlike conventional DDCC, the proposed DDCC offers current gain between z- and x-terminal that can be controlled electronically by bias currents. The DDCC-based OTA can be investigated both simulation and experiment tests. The proposed DDCC is used to implement a quadrature oscillator to confirm workability.","PeriodicalId":416531,"journal":{"name":"2021 7th International Conference on Engineering, Applied Sciences and Technology (ICEAST)","volume":"30 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":"122642875","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/iceast52143.2021.9426286
C. Jinjakam, Tipakorn Thanawanarat, Korn Isaranimitr
Engineering drawing is one of the important fundamental subjects in the engineering course that requires imagination and artistic skill for understanding. Engineering student needs to practice a lot of exercises to understand three-dimensions representation and its two dimensional orthographic in top view, front view and side view. However, some students cannot understand 3D objects by just only paper and pencil. This process makes them feel bored to practice. Therefore, they cannot understand well and might have a long-term issue. Therefore, this paper proposes virtual reality 3D games as a learning media by using Oculus Rift and Oculus Touch. The objective of this game is to help students or people who have a previously mentioned problem to improve their skills. This game will increase the enjoyment of learning and possibly motivate them to educate the understanding of 3D objects and their visual dimensions. In this game, the player must match 3D objects with orthographic projections and create the object by themselves to match an orthographic projection. A player can register and check their improvement from history score and time spent. The goal of this virtual reality learning game is to motivate the player to practice with happiness. The experimental results showed players used shorter time and had got higher accuracy when continue playing. Post-questionnaire results shown they feel most enjoying when creating 3D virtual reality objects by themselves. Moreover, the results could imply students below grade C+ in Engineering Drawing subject may have problems with 3D objects that were cut into triangular in prismatic shapes, and students below grade D+ may have problems with dashed and solid lines.
{"title":"Virtual Reality Game for Visual Dimension Understanding","authors":"C. Jinjakam, Tipakorn Thanawanarat, Korn Isaranimitr","doi":"10.1109/iceast52143.2021.9426286","DOIUrl":"https://doi.org/10.1109/iceast52143.2021.9426286","url":null,"abstract":"Engineering drawing is one of the important fundamental subjects in the engineering course that requires imagination and artistic skill for understanding. Engineering student needs to practice a lot of exercises to understand three-dimensions representation and its two dimensional orthographic in top view, front view and side view. However, some students cannot understand 3D objects by just only paper and pencil. This process makes them feel bored to practice. Therefore, they cannot understand well and might have a long-term issue. Therefore, this paper proposes virtual reality 3D games as a learning media by using Oculus Rift and Oculus Touch. The objective of this game is to help students or people who have a previously mentioned problem to improve their skills. This game will increase the enjoyment of learning and possibly motivate them to educate the understanding of 3D objects and their visual dimensions. In this game, the player must match 3D objects with orthographic projections and create the object by themselves to match an orthographic projection. A player can register and check their improvement from history score and time spent. The goal of this virtual reality learning game is to motivate the player to practice with happiness. The experimental results showed players used shorter time and had got higher accuracy when continue playing. Post-questionnaire results shown they feel most enjoying when creating 3D virtual reality objects by themselves. Moreover, the results could imply students below grade C+ in Engineering Drawing subject may have problems with 3D objects that were cut into triangular in prismatic shapes, and students below grade D+ may have problems with dashed and solid lines.","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":"123570398","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/ICEAST52143.2021.9426287
Saran Khotmanee, U. Pinsopon
Thailand 2015 Alternative Energy Development Plan (AEDP2015) stated that renewable energy should take part in the gross energy consumption for 30% by the year 2036. The plan also targeted compressed biogas to replace refined petroleum for a daily use 4,800 tons, as well as the biogas produced from waste to be the source for a 600 MW electricity power generation. To understand how close the biogas production status is up to the plan, the biogas production potential in Thailand 2019 was investigated, and is presented in this paper. The biogas production potential was considered from 3 sectors: industrial plants, livestock, and agricultural plants. The industrial plants with high organic content of waste were considered in the study. They are ethanol, starch, palm oil, rubber, food and alcoholic beverage plants. Livestock investigated in this study are cattle, buffaloes, pigs and chickens. Top 6 most cultivated agricultural plants were considered: rice, corn, sugarcane, cassava, palm and pineapple. Only business units with significant production potential yields were included in the potential study. The biogas productivity status in the year 2019 was also surveyed. The biogas production potential in Thailand 2019 was estimated to be 22,827 million m3, higher than the planned demand of 8,124 million m3 in the year 2036 due to the AEDP2015 plan. However, the productivity status was found to be 816 million m3, only 10% of the planned value in the year 2036. Continual supports from the government are needed in order that the biogas productivity could meet the targeted demand in the year 2036.
{"title":"A Study on Biogas Production Potential in Thailand 2019","authors":"Saran Khotmanee, U. Pinsopon","doi":"10.1109/ICEAST52143.2021.9426287","DOIUrl":"https://doi.org/10.1109/ICEAST52143.2021.9426287","url":null,"abstract":"Thailand 2015 Alternative Energy Development Plan (AEDP2015) stated that renewable energy should take part in the gross energy consumption for 30% by the year 2036. The plan also targeted compressed biogas to replace refined petroleum for a daily use 4,800 tons, as well as the biogas produced from waste to be the source for a 600 MW electricity power generation. To understand how close the biogas production status is up to the plan, the biogas production potential in Thailand 2019 was investigated, and is presented in this paper. The biogas production potential was considered from 3 sectors: industrial plants, livestock, and agricultural plants. The industrial plants with high organic content of waste were considered in the study. They are ethanol, starch, palm oil, rubber, food and alcoholic beverage plants. Livestock investigated in this study are cattle, buffaloes, pigs and chickens. Top 6 most cultivated agricultural plants were considered: rice, corn, sugarcane, cassava, palm and pineapple. Only business units with significant production potential yields were included in the potential study. The biogas productivity status in the year 2019 was also surveyed. The biogas production potential in Thailand 2019 was estimated to be 22,827 million m3, higher than the planned demand of 8,124 million m3 in the year 2036 due to the AEDP2015 plan. However, the productivity status was found to be 816 million m3, only 10% of the planned value in the year 2036. Continual supports from the government are needed in order that the biogas productivity could meet the targeted demand in the year 2036.","PeriodicalId":416531,"journal":{"name":"2021 7th International Conference on Engineering, Applied Sciences and Technology (ICEAST)","volume":"36 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":"127604734","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/ICEAST52143.2021.9426283
Kanut Tangtisanon, Kiatnarong Tongprasert
It is widely accepted that a crucial part of learning is practicing. This is also true for computer programming courses. Students develop advanced skills and understand what they have learned better through practice. The more they practice, the more skillful they become. However, with hundreds of students in a class, an instructor may not be able to check the outcomes of student practice thoroughly nor give sufficient and timely feedback on practice to each student. An easily accessible learning platform plays an important role in dealing with this issue.Nowadays, since the internet can be accessed by anyone, a web application as a learning platform was expected to be able to play this role. Therefore, we developed a web application. It was intended for any student in any computer programming course: it was used by students in a programming course in King Mongkut’s Institute of Technology Ladkrabang, Thailand, since 2017. No prior programming knowledge was required for students to use the application. The programming course had 10 chapters and one examination. In each chapter, students were required to code five programs on a PC in the programming laboratory and to submit the source files by uploading them via the web interface. The outputs of the submitted programs from all students were collected in a few seconds rather than minutes. If a submitted program was correct, proper scores were assigned. If not, the student’s wrong source code was displayed on the application page together with test cases both of sample and students, and the student could examine effortlessly the incorrect part of his or her source code. Later, the student could modify the original source code and resubmit it, until the student has arrived at the correct code. This strategy was less stressful on students, because they could keep working on assignments at their own time and pace, until they were successful. Throughout the course with 789 students in the first semester of academic year 2020, the web application platform handled over 70,000 submissions of source code, beyond the capability of a human instructor. This large number of submissions indicated that the students had more time, opportunity and will to edit their source code thoroughly with this platform. Moreover, the students seemed to enjoy their attempts to overcome the programming challenge with this platform.
{"title":"Computer Programming Classroom Platform","authors":"Kanut Tangtisanon, Kiatnarong Tongprasert","doi":"10.1109/ICEAST52143.2021.9426283","DOIUrl":"https://doi.org/10.1109/ICEAST52143.2021.9426283","url":null,"abstract":"It is widely accepted that a crucial part of learning is practicing. This is also true for computer programming courses. Students develop advanced skills and understand what they have learned better through practice. The more they practice, the more skillful they become. However, with hundreds of students in a class, an instructor may not be able to check the outcomes of student practice thoroughly nor give sufficient and timely feedback on practice to each student. An easily accessible learning platform plays an important role in dealing with this issue.Nowadays, since the internet can be accessed by anyone, a web application as a learning platform was expected to be able to play this role. Therefore, we developed a web application. It was intended for any student in any computer programming course: it was used by students in a programming course in King Mongkut’s Institute of Technology Ladkrabang, Thailand, since 2017. No prior programming knowledge was required for students to use the application. The programming course had 10 chapters and one examination. In each chapter, students were required to code five programs on a PC in the programming laboratory and to submit the source files by uploading them via the web interface. The outputs of the submitted programs from all students were collected in a few seconds rather than minutes. If a submitted program was correct, proper scores were assigned. If not, the student’s wrong source code was displayed on the application page together with test cases both of sample and students, and the student could examine effortlessly the incorrect part of his or her source code. Later, the student could modify the original source code and resubmit it, until the student has arrived at the correct code. This strategy was less stressful on students, because they could keep working on assignments at their own time and pace, until they were successful. Throughout the course with 789 students in the first semester of academic year 2020, the web application platform handled over 70,000 submissions of source code, beyond the capability of a human instructor. This large number of submissions indicated that the students had more time, opportunity and will to edit their source code thoroughly with this platform. Moreover, the students seemed to enjoy their attempts to overcome the programming challenge with this platform.","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":"130343938","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/ICEAST52143.2021.9426290
K. Qureshi
An optical sensor based on a fiber Bragg grating (FBG) array is proposed to detect the foot plantar pressure in adults. The plantar pressure signals are detected by three FBGs, spliced in the same piece of single-mode fiber (SMF-28), placed on the platform for the dynamic monitoring of gait motion. The male subject suffering from gait disorder experienced a pressure of 0.35 kPa on the rearfoot and a pressure of 0.15 kPa on the lateral forefoot, exhibiting a large pressure imbalance. The proposed scheme based on FBGs sensors shows a pressure sensitivity of 1.466 pm/kPa with an R2 value of 0.998. This study has revealed the feasibility of the proposed system as a useful alternative to other plantar pressure sensing systems. The advantages offered by the reported technique include; high weight tolerance, robustness, and increased sensitivity compared to other approaches reported in the literature.
{"title":"Detection of Plantar Pressure Using an Optical Technique","authors":"K. Qureshi","doi":"10.1109/ICEAST52143.2021.9426290","DOIUrl":"https://doi.org/10.1109/ICEAST52143.2021.9426290","url":null,"abstract":"An optical sensor based on a fiber Bragg grating (FBG) array is proposed to detect the foot plantar pressure in adults. The plantar pressure signals are detected by three FBGs, spliced in the same piece of single-mode fiber (SMF-28), placed on the platform for the dynamic monitoring of gait motion. The male subject suffering from gait disorder experienced a pressure of 0.35 kPa on the rearfoot and a pressure of 0.15 kPa on the lateral forefoot, exhibiting a large pressure imbalance. The proposed scheme based on FBGs sensors shows a pressure sensitivity of 1.466 pm/kPa with an R2 value of 0.998. This study has revealed the feasibility of the proposed system as a useful alternative to other plantar pressure sensing systems. The advantages offered by the reported technique include; high weight tolerance, robustness, and increased sensitivity compared to other approaches reported in the literature.","PeriodicalId":416531,"journal":{"name":"2021 7th International Conference on Engineering, Applied Sciences and Technology (ICEAST)","volume":"27 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":"133143744","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/ICEAST52143.2021.9426259
Vo Thi Ngoc Chau, N. H. Phung
Early course-level study performance prediction is a significant educational data mining task to forecast the success of each current student in a course using the historical data of the students in the previous same course. This task can be resolved by different machine learning approaches in various educational contexts. However, how easily and effectively a solution is deployed in practice is restricted by many factors. Two main factors that have not yet been discussed simultaneously are incremental mining and interpretability when the task is prolonged course after course. Therefore, in this paper, we propose a novel cumulative increasing kernelized nearest-neighbor bagging method for early course-level study performance prediction. Our method is a lazy learning one with an inherent incremental mining mechanism, defined as an ensemble method. Although it works in a feature space to handle a non-linearly separated data space, interpretability is enabled with instance-based learning and a confidence score of each prediction is further provided for practical applications. Experimental results on several public datasets confirm the effectiveness of our method as compared to other traditional prediction methods and well-known ensemble ones. Its better early predictions can help both students and lecturers make appropriate course changes for students’ ultimate success.
{"title":"A Cumulative Increasing Kemelized Nearest-Neighbor Bagging Method for Early Course-Level Study Performance Prediction","authors":"Vo Thi Ngoc Chau, N. H. Phung","doi":"10.1109/ICEAST52143.2021.9426259","DOIUrl":"https://doi.org/10.1109/ICEAST52143.2021.9426259","url":null,"abstract":"Early course-level study performance prediction is a significant educational data mining task to forecast the success of each current student in a course using the historical data of the students in the previous same course. This task can be resolved by different machine learning approaches in various educational contexts. However, how easily and effectively a solution is deployed in practice is restricted by many factors. Two main factors that have not yet been discussed simultaneously are incremental mining and interpretability when the task is prolonged course after course. Therefore, in this paper, we propose a novel cumulative increasing kernelized nearest-neighbor bagging method for early course-level study performance prediction. Our method is a lazy learning one with an inherent incremental mining mechanism, defined as an ensemble method. Although it works in a feature space to handle a non-linearly separated data space, interpretability is enabled with instance-based learning and a confidence score of each prediction is further provided for practical applications. Experimental results on several public datasets confirm the effectiveness of our method as compared to other traditional prediction methods and well-known ensemble ones. Its better early predictions can help both students and lecturers make appropriate course changes for students’ ultimate success.","PeriodicalId":416531,"journal":{"name":"2021 7th International Conference on Engineering, Applied Sciences and Technology (ICEAST)","volume":"82 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":"122424159","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/ICEAST52143.2021.9426314
Suriya Soisang, Suvit Poomrittigul
In this paper, a new textural feature for solving offline handwritten signature verification is proposed. A new textural features method is developed by combining a Local Binary Patterns (LBP) method and a Gradient Quantization Angle (GQA) method. This proposed method is called Local Binary Patterns with Gradient Quantization Angle (LBPGQA), as developed by heuristic method to improve the precision of verification the offline signature image. The hypothesis for this study is to classify the distinctive handwritten signature individually with the actual signature angle and refraction for enhancing the signature fraud detection. The verification step is achieved by Artificial Neural Network (ANN) classifier and trained on genuine signatures. Furthermore, the test stage is performed on genuine signatures and skilled forgeries. The experiments are conducted on CEDAR datasets. The experimental results show that in the LBPGQA method outperforms classical features such as Histogram of oriented gradients and local binary patterns. Conclusively, this proposed method can verify the individual and distinctive handwritten signature and help to protect the signature fraud by skilled forgeries.
{"title":"New Textural Features for Handwritten Signature Image Verification","authors":"Suriya Soisang, Suvit Poomrittigul","doi":"10.1109/ICEAST52143.2021.9426314","DOIUrl":"https://doi.org/10.1109/ICEAST52143.2021.9426314","url":null,"abstract":"In this paper, a new textural feature for solving offline handwritten signature verification is proposed. A new textural features method is developed by combining a Local Binary Patterns (LBP) method and a Gradient Quantization Angle (GQA) method. This proposed method is called Local Binary Patterns with Gradient Quantization Angle (LBPGQA), as developed by heuristic method to improve the precision of verification the offline signature image. The hypothesis for this study is to classify the distinctive handwritten signature individually with the actual signature angle and refraction for enhancing the signature fraud detection. The verification step is achieved by Artificial Neural Network (ANN) classifier and trained on genuine signatures. Furthermore, the test stage is performed on genuine signatures and skilled forgeries. The experiments are conducted on CEDAR datasets. The experimental results show that in the LBPGQA method outperforms classical features such as Histogram of oriented gradients and local binary patterns. Conclusively, this proposed method can verify the individual and distinctive handwritten signature and help to protect the signature fraud by skilled forgeries.","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":"131115469","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/ICEAST52143.2021.9426302
Patchara Opaspilai, S. Vongbunyong, Arbtip Dheeravongkit
Management of pharmaceutical products is one of the most complicated and labor-intensive issues in hospitals. The complication can lead to a number of serious problems, especially medication errors that affect the treatment process of patient. The management is involved various logistics activities from obtaining products from external suppliers to dispensing to patients. A number of attempts have been made to implement robotics and automation to these processes in order to improve accuracy and performance. In this research, a robot system used to manage the product at the stage before medicine dispensing. Automatic dispensers’ magazines need to be refilled with the products, e.g. medicine boxes. In general, the transportation of medicine from suppliers are in the form of packing case with a lot of boxes inside. In this case, SCARA robot with a vacuum gripper is used to depalletize boxes contained in the packing cases and rearrange them into magazines for further dispensing. The robot is equipped with vision system, so that the system is capable of handling variations of box packaging in term of appearance, size, and placement pattern. Convolutional Neural Network (CNN) has been applied to locate and classify the boxes and the system can treat them properly.
{"title":"Robotic System for Depalletization of Pharmaceutical Products","authors":"Patchara Opaspilai, S. Vongbunyong, Arbtip Dheeravongkit","doi":"10.1109/ICEAST52143.2021.9426302","DOIUrl":"https://doi.org/10.1109/ICEAST52143.2021.9426302","url":null,"abstract":"Management of pharmaceutical products is one of the most complicated and labor-intensive issues in hospitals. The complication can lead to a number of serious problems, especially medication errors that affect the treatment process of patient. The management is involved various logistics activities from obtaining products from external suppliers to dispensing to patients. A number of attempts have been made to implement robotics and automation to these processes in order to improve accuracy and performance. In this research, a robot system used to manage the product at the stage before medicine dispensing. Automatic dispensers’ magazines need to be refilled with the products, e.g. medicine boxes. In general, the transportation of medicine from suppliers are in the form of packing case with a lot of boxes inside. In this case, SCARA robot with a vacuum gripper is used to depalletize boxes contained in the packing cases and rearrange them into magazines for further dispensing. The robot is equipped with vision system, so that the system is capable of handling variations of box packaging in term of appearance, size, and placement pattern. Convolutional Neural Network (CNN) has been applied to locate and classify the boxes and the system can treat them properly.","PeriodicalId":416531,"journal":{"name":"2021 7th International Conference on Engineering, Applied Sciences and Technology (ICEAST)","volume":"49 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":"134532207","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/ICEAST52143.2021.9426262
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}
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：