Pub Date : 2021-04-28DOI: 10.1109/AIMS52415.2021.9466054
M. Marwan, Muhammad Dihyah Marwan, M. Anshar, J. Jamal, Aksan Aksan, A. Apollo
The current paper presents is to manage/control the electricity peak demand. In this scheme, the consumer will be able to manage the use of electrical energy for some appliances using innovative technology. In order to achieve the aim of this research, a time of use program was applied under the demand side response model. In this research there are three demand scenarios have been formulated to demonstrated the result of the simulation. An economic model was developed to define the electricity peak demand. As a result, the electricity peak demand can be minimized, such as: 450 MWh (scenario-1), 460 MWh (scenario-2) and 480 MWh (scenario-3). In addition, the New South Wales electricity market was chosen for the case study.
{"title":"Applied TOU program to control electricity peak demand under demand side response model","authors":"M. Marwan, Muhammad Dihyah Marwan, M. Anshar, J. Jamal, Aksan Aksan, A. Apollo","doi":"10.1109/AIMS52415.2021.9466054","DOIUrl":"https://doi.org/10.1109/AIMS52415.2021.9466054","url":null,"abstract":"The current paper presents is to manage/control the electricity peak demand. In this scheme, the consumer will be able to manage the use of electrical energy for some appliances using innovative technology. In order to achieve the aim of this research, a time of use program was applied under the demand side response model. In this research there are three demand scenarios have been formulated to demonstrated the result of the simulation. An economic model was developed to define the electricity peak demand. As a result, the electricity peak demand can be minimized, such as: 450 MWh (scenario-1), 460 MWh (scenario-2) and 480 MWh (scenario-3). In addition, the New South Wales electricity market was chosen for the case study.","PeriodicalId":299121,"journal":{"name":"2021 International Conference on Artificial Intelligence and Mechatronics Systems (AIMS)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127638857","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 : 2021-04-28DOI: 10.1109/AIMS52415.2021.9466012
Aziz Fajar, Dwi Wahyu Santoso, Zico Ritonda Bahen, R. Sarno, C. Fatichah
This paper introduces an automatic colorization of 3D volumetric medical image based on brain Computed Tomography (CT) scan images. This volumetric 3D images are generated from Digital Imaging and Communications in Medicine (DICOM) images. This research renders the DICOM images to volumetric images using ray marching method. Then automatically colorized each brain parts by computing the transfer function based on the value of grayscale to compared to tissue density. Our proposed method focused on the value which color each parts of the brain as well as the use of ray marching algorithm to show colorized result in 3D.
{"title":"Color Mapping for Volume Rendering Using Digital Imaging and Communications in Medicine Images","authors":"Aziz Fajar, Dwi Wahyu Santoso, Zico Ritonda Bahen, R. Sarno, C. Fatichah","doi":"10.1109/AIMS52415.2021.9466012","DOIUrl":"https://doi.org/10.1109/AIMS52415.2021.9466012","url":null,"abstract":"This paper introduces an automatic colorization of 3D volumetric medical image based on brain Computed Tomography (CT) scan images. This volumetric 3D images are generated from Digital Imaging and Communications in Medicine (DICOM) images. This research renders the DICOM images to volumetric images using ray marching method. Then automatically colorized each brain parts by computing the transfer function based on the value of grayscale to compared to tissue density. Our proposed method focused on the value which color each parts of the brain as well as the use of ray marching algorithm to show colorized result in 3D.","PeriodicalId":299121,"journal":{"name":"2021 International Conference on Artificial Intelligence and Mechatronics Systems (AIMS)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124637746","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 : 2021-04-28DOI: 10.1109/AIMS52415.2021.9466023
S. Tahir, M. Khan, Mubashir Rasool, Nauman Naseer
Some areas in Pakistan are still without excess to electricity and have no utility grid structure. Recently they are using diesel generators with fuel to fulfill their requirements. To overcome these problems, renewable energy technologies are capable of providing the electrical demand in those areas which have a shortage of electricity. Native renewable energy resources (RES) in remote areas can be utilized to establish a hybrid energy system that meets the electrical supplies of the community. This paper study a hybrid renewable energy system (HRES) based on solar, wind, and diesel resources to meet different industrial needs of the selected area. Industrial Estate Gadoon (District Swabi), Khyber Pakhtunkhwa, Pakistan is selected as a project site where there is a continuous need for a reliable energy resource throughout the year. The HOMER optimization software is utilized to design and analyze the system with estimated load requirements and existing energy resources. Optimization of the hybrid renewable energy system (HRES) has been done by selecting the best components and cheap, efficient, reliable, and cost-effective alternative energy systems. The system proposed comes out to have a very low cost of energy (i.e., 0.0655 $ /kWh). Sensitivity analysis of the proposed system shows that with an increase of 10% in wind speed, COE, and the total operating cost are reduced. This HRES proposed in the study can prove its efficiency and reliability at any place with the same system conditions.
{"title":"An Optimized Off-grid Renewable Micro-Grid Design and Feasibility Analysis for Remote Industries of Gadoon Swabi (Pakistan)","authors":"S. Tahir, M. Khan, Mubashir Rasool, Nauman Naseer","doi":"10.1109/AIMS52415.2021.9466023","DOIUrl":"https://doi.org/10.1109/AIMS52415.2021.9466023","url":null,"abstract":"Some areas in Pakistan are still without excess to electricity and have no utility grid structure. Recently they are using diesel generators with fuel to fulfill their requirements. To overcome these problems, renewable energy technologies are capable of providing the electrical demand in those areas which have a shortage of electricity. Native renewable energy resources (RES) in remote areas can be utilized to establish a hybrid energy system that meets the electrical supplies of the community. This paper study a hybrid renewable energy system (HRES) based on solar, wind, and diesel resources to meet different industrial needs of the selected area. Industrial Estate Gadoon (District Swabi), Khyber Pakhtunkhwa, Pakistan is selected as a project site where there is a continuous need for a reliable energy resource throughout the year. The HOMER optimization software is utilized to design and analyze the system with estimated load requirements and existing energy resources. Optimization of the hybrid renewable energy system (HRES) has been done by selecting the best components and cheap, efficient, reliable, and cost-effective alternative energy systems. The system proposed comes out to have a very low cost of energy (i.e., 0.0655 $ /kWh). Sensitivity analysis of the proposed system shows that with an increase of 10% in wind speed, COE, and the total operating cost are reduced. This HRES proposed in the study can prove its efficiency and reliability at any place with the same system conditions.","PeriodicalId":299121,"journal":{"name":"2021 International Conference on Artificial Intelligence and Mechatronics Systems (AIMS)","volume":"287 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122657638","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 : 2021-04-28DOI: 10.1109/AIMS52415.2021.9466030
Fikri Rida Pebriansyah, P. Turnip, N. S. Syafei, A. Trisanto, A. Turnip
Cardiovascular disease (CVD) is a disease caused by malfunctioning of the heart and blood vessels. Arrhythmias are a type of cardiovascular disease. Arrhythmia can be detected by reading the patient's electrocardiogram (ECG) data. A system is needed that can read the user's electrocardiogram data frequently and detect when an arrhythmic occurs. Therefore, it is necessary to create an interface that can visualize data both from ECG data and detection results by machine learning. The design method of this system is divided into 7 stages, namely: designing the user flow diagram, designing the model and controller, designing the entity-relationship diagram (ERD), designing the use case diagram, creating API specification, realizing the system, and testing the features. Data collection on the client side was carried out by testing conducted by the Google Chrome browser version 86.0.4240.198 and Apache JMeter 5.4.1. Based on the model that has been created and tested, it can be concluded that a web application has been successfully created to facilitate interaction between users and doctors on ECG data and the results of the user's ECG classification. These features have tested and have a functional percentage of 100%. On the server-side, the average CPU usage value were 86.27% for PHP, 4.77% for MariaDB, and 0.28% for Nginx. The average value of memory usage were 173.6 MB for PHP, 87.33 MB for MariaDB, and 7.90 MB for Nginx. Then, on the client-side, the more users who open the application at the same time, the value of the error ratio and response time would also increase. The system could handle 100 requests per second successfully, so application can handle 8,640,000 requests per day on the tested hardware specification.
{"title":"Design of Arrhythmia Early Detection Interface Using Laravel Framework","authors":"Fikri Rida Pebriansyah, P. Turnip, N. S. Syafei, A. Trisanto, A. Turnip","doi":"10.1109/AIMS52415.2021.9466030","DOIUrl":"https://doi.org/10.1109/AIMS52415.2021.9466030","url":null,"abstract":"Cardiovascular disease (CVD) is a disease caused by malfunctioning of the heart and blood vessels. Arrhythmias are a type of cardiovascular disease. Arrhythmia can be detected by reading the patient's electrocardiogram (ECG) data. A system is needed that can read the user's electrocardiogram data frequently and detect when an arrhythmic occurs. Therefore, it is necessary to create an interface that can visualize data both from ECG data and detection results by machine learning. The design method of this system is divided into 7 stages, namely: designing the user flow diagram, designing the model and controller, designing the entity-relationship diagram (ERD), designing the use case diagram, creating API specification, realizing the system, and testing the features. Data collection on the client side was carried out by testing conducted by the Google Chrome browser version 86.0.4240.198 and Apache JMeter 5.4.1. Based on the model that has been created and tested, it can be concluded that a web application has been successfully created to facilitate interaction between users and doctors on ECG data and the results of the user's ECG classification. These features have tested and have a functional percentage of 100%. On the server-side, the average CPU usage value were 86.27% for PHP, 4.77% for MariaDB, and 0.28% for Nginx. The average value of memory usage were 173.6 MB for PHP, 87.33 MB for MariaDB, and 7.90 MB for Nginx. Then, on the client-side, the more users who open the application at the same time, the value of the error ratio and response time would also increase. The system could handle 100 requests per second successfully, so application can handle 8,640,000 requests per day on the tested hardware specification.","PeriodicalId":299121,"journal":{"name":"2021 International Conference on Artificial Intelligence and Mechatronics Systems (AIMS)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115069145","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}
The use of fossil fuels for power plant produces emissions that pollute the environment. It takes environmentally friendly energy, one of which is solar energy. The electrical energy produced by solar panels is influenced by the value of solar irradiation, so that the power generated by solar panels fluctuates. PV solar output is optimized using a modified Maximum Power Point Tracking (MPPT) algorithm using Grey Wolf Optimization (GWO). However, the overvoltage can be caused by the maximum power that the PV generates. This paper proposed the modification of the Maximum Power Point Tracking algorithm using Grey Wolf Optimization for Constant Power Generation of photovoltaic systems. This method prepares MPPT mode and CPG mode to handle solar PV conditions. When the output power of the PV is less than the limit power, the MPPT mode is active. Meanwhile, if the output power of the solar panel exceeds the limit power, the CPG mode is active. Used SEPIC converter for MPPT-CPG control. The simulation results of the proposed control method show that the output voltage response does not exceed the value of 24 V with the largest error value of 1.48% which has been verified using various radiation and reference power.
{"title":"A Modified Maximum Power Point Tracking Algorithm Using Grey Wolf Optimization for Constant Power Generation of Photovoltaic System","authors":"Fernanda Roikhul Hasan, Eka Prasetyono, Epyk Sunarno","doi":"10.1109/AIMS52415.2021.9466050","DOIUrl":"https://doi.org/10.1109/AIMS52415.2021.9466050","url":null,"abstract":"The use of fossil fuels for power plant produces emissions that pollute the environment. It takes environmentally friendly energy, one of which is solar energy. The electrical energy produced by solar panels is influenced by the value of solar irradiation, so that the power generated by solar panels fluctuates. PV solar output is optimized using a modified Maximum Power Point Tracking (MPPT) algorithm using Grey Wolf Optimization (GWO). However, the overvoltage can be caused by the maximum power that the PV generates. This paper proposed the modification of the Maximum Power Point Tracking algorithm using Grey Wolf Optimization for Constant Power Generation of photovoltaic systems. This method prepares MPPT mode and CPG mode to handle solar PV conditions. When the output power of the PV is less than the limit power, the MPPT mode is active. Meanwhile, if the output power of the solar panel exceeds the limit power, the CPG mode is active. Used SEPIC converter for MPPT-CPG control. The simulation results of the proposed control method show that the output voltage response does not exceed the value of 24 V with the largest error value of 1.48% which has been verified using various radiation and reference power.","PeriodicalId":299121,"journal":{"name":"2021 International Conference on Artificial Intelligence and Mechatronics Systems (AIMS)","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126386797","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 : 2021-04-28DOI: 10.1109/AIMS52415.2021.9466014
Achmad Zulfajri Syaharuddin, Z. Zainuddin, Andani
Building an approach system that is able to serve various types of traffic signs is a challenge. The important stages in handling an object are finding objects, dividing them into several categories, and marking objects with bounding boxes. However, in reality, monitoring traffic signs objects is quite difficult because it is based on various factors such as; other closed objects, driving times, or traffic sign conditions. This study aims to measure the level of precision in monitoring traffic signs (detection speed of 4–6 frames per second) from video recording (single camera) using the Faster Region based Convolutional Neural Network (Faster R-CNN) algorithm. The traffic sign detection system uses the Faster R-CNN algorithm with Inception v2 model which is implemented in the TensorFlow API framework. The Faster R-CNN consists of 2 different modules. The first module is a deep convolutional neural network which functions to build the area to be detected, which is called the Regional Proposal Network (RPN), and the second module is the Fast R-CNN detector which functions to use the previously proposed area. This system is one unit, a detection network based on the results of the manufacture and testing of a traffic sign detection system based on the Faster R-CNN method, so it can be shown that there is no difference in the results of detection of traffic signs in day and night conditions. Where the precision testing for detection of traffic signs during the day and at night is 100%.
{"title":"Multi-Pole Road Sign Detection Based on Faster Region-based Convolutional Neural Network (Faster R-CNN)","authors":"Achmad Zulfajri Syaharuddin, Z. Zainuddin, Andani","doi":"10.1109/AIMS52415.2021.9466014","DOIUrl":"https://doi.org/10.1109/AIMS52415.2021.9466014","url":null,"abstract":"Building an approach system that is able to serve various types of traffic signs is a challenge. The important stages in handling an object are finding objects, dividing them into several categories, and marking objects with bounding boxes. However, in reality, monitoring traffic signs objects is quite difficult because it is based on various factors such as; other closed objects, driving times, or traffic sign conditions. This study aims to measure the level of precision in monitoring traffic signs (detection speed of 4–6 frames per second) from video recording (single camera) using the Faster Region based Convolutional Neural Network (Faster R-CNN) algorithm. The traffic sign detection system uses the Faster R-CNN algorithm with Inception v2 model which is implemented in the TensorFlow API framework. The Faster R-CNN consists of 2 different modules. The first module is a deep convolutional neural network which functions to build the area to be detected, which is called the Regional Proposal Network (RPN), and the second module is the Fast R-CNN detector which functions to use the previously proposed area. This system is one unit, a detection network based on the results of the manufacture and testing of a traffic sign detection system based on the Faster R-CNN method, so it can be shown that there is no difference in the results of detection of traffic signs in day and night conditions. Where the precision testing for detection of traffic signs during the day and at night is 100%.","PeriodicalId":299121,"journal":{"name":"2021 International Conference on Artificial Intelligence and Mechatronics Systems (AIMS)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128432007","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 : 2021-04-28DOI: 10.1109/AIMS52415.2021.9466076
Wilda Hayati, Martinus Ahmad Raif, C. Ginting, Refi Ikhtiari
Persea Americana Mill. (avocado) is the dicotyledonous plant that rich in secondary metabolite compounds such as saponins, alkaloids, terpenoids, and flavonoids. It applies as an antioxidant, anti-inflammatory, anti-lithiasis, and anti-diabetic. This study investigates the wound healing properties of P. americana leaves extract on Mus musculus in gel formulations. Preliminary phytochemical screening had done qualitatively, and antioxidant capacity was evaluated by the DPPH scavenging method. Extract in gel formulation contained various concentration of extracts (1%, 3%, 5%, and 7% v/v) was performed to observed the wound healing activity compared to standard medicine Bioplaceton® on mice. The phytochemical test showed the presence of alkaloids, flavonoids, saponins, and tannins. The result of the DPPH scavenging activity (IC50) of the leaves extract was 8.92 ppm. In wound healing activity, the application of extract P. americana leaves with various concentrations (1%, 3%, 5%, and 7% v/v) in gel formulations showed decreasing of wound length drastically to 0.9, 0.3, 0.2, and 0.7 cm, respectively. Gel-5% extract showed the highest percentage on wound healing, 90%, where gel-1% extract was 55%, gel-3% extract was 85%, and gel-7% extract was 75%. The 5% extract gel formulations showed a significant result similar to Bioplacenton®, with the percentage of wound healing being 90%. It can be concluded that the extract of P. americana leaves could be the potential for natural antioxidant and wound healing sources in the future.
{"title":"Antioxidant and Wound Healing Potential of Persea Americana Mill. Leaves extract","authors":"Wilda Hayati, Martinus Ahmad Raif, C. Ginting, Refi Ikhtiari","doi":"10.1109/AIMS52415.2021.9466076","DOIUrl":"https://doi.org/10.1109/AIMS52415.2021.9466076","url":null,"abstract":"Persea Americana Mill. (avocado) is the dicotyledonous plant that rich in secondary metabolite compounds such as saponins, alkaloids, terpenoids, and flavonoids. It applies as an antioxidant, anti-inflammatory, anti-lithiasis, and anti-diabetic. This study investigates the wound healing properties of P. americana leaves extract on Mus musculus in gel formulations. Preliminary phytochemical screening had done qualitatively, and antioxidant capacity was evaluated by the DPPH scavenging method. Extract in gel formulation contained various concentration of extracts (1%, 3%, 5%, and 7% v/v) was performed to observed the wound healing activity compared to standard medicine Bioplaceton® on mice. The phytochemical test showed the presence of alkaloids, flavonoids, saponins, and tannins. The result of the DPPH scavenging activity (IC50) of the leaves extract was 8.92 ppm. In wound healing activity, the application of extract P. americana leaves with various concentrations (1%, 3%, 5%, and 7% v/v) in gel formulations showed decreasing of wound length drastically to 0.9, 0.3, 0.2, and 0.7 cm, respectively. Gel-5% extract showed the highest percentage on wound healing, 90%, where gel-1% extract was 55%, gel-3% extract was 85%, and gel-7% extract was 75%. The 5% extract gel formulations showed a significant result similar to Bioplacenton®, with the percentage of wound healing being 90%. It can be concluded that the extract of P. americana leaves could be the potential for natural antioxidant and wound healing sources in the future.","PeriodicalId":299121,"journal":{"name":"2021 International Conference on Artificial Intelligence and Mechatronics Systems (AIMS)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126823266","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 : 2021-04-28DOI: 10.1109/AIMS52415.2021.9466086
Muhammad Aryosandi, Eka Prasetyono, D. O. Anggriawan
The use of electrolytic capacitors in the LED driver can affect the lifetime of the LED. But eliminating electrolytic capacitors causes an unstable load power that is unsafe to operate because there are flickers that will cause damage to the eyes. Therefore, there is a need for a bidirectional converter for decoupling power and additional control for setting the switching, so the ability to LED still constant. The control effect uses the Artificial Neural Network (ANN) method to select the switch state on or off in the bidirectional converter. Finally, the result simulations of the output system 92.4 Watt. Useful for verifying the feasibility of the proposed topology and control strategy.
{"title":"Application of Cuk Converter for Capacitor-Less Electrolytic on the Light-Emitting Diode Driver with Artificial Neural Network","authors":"Muhammad Aryosandi, Eka Prasetyono, D. O. Anggriawan","doi":"10.1109/AIMS52415.2021.9466086","DOIUrl":"https://doi.org/10.1109/AIMS52415.2021.9466086","url":null,"abstract":"The use of electrolytic capacitors in the LED driver can affect the lifetime of the LED. But eliminating electrolytic capacitors causes an unstable load power that is unsafe to operate because there are flickers that will cause damage to the eyes. Therefore, there is a need for a bidirectional converter for decoupling power and additional control for setting the switching, so the ability to LED still constant. The control effect uses the Artificial Neural Network (ANN) method to select the switch state on or off in the bidirectional converter. Finally, the result simulations of the output system 92.4 Watt. Useful for verifying the feasibility of the proposed topology and control strategy.","PeriodicalId":299121,"journal":{"name":"2021 International Conference on Artificial Intelligence and Mechatronics Systems (AIMS)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131190445","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 : 2021-04-28DOI: 10.1109/AIMS52415.2021.9466037
M. Widiasri, A. Arifin, N. Suciati, E. Astuti, R. Indraswari
Cone Beam Computed Tomography (CBCT) is a medical imaging technique widely used in dentistry including dental implant planning. To determine the size of the dental implant, it is necessary to detect the alveolar bone at the implant site. In this study, we propose automatic detection of alveolar bone from CBCT images of teeth using the YOLOv3-tiny method. The YOLOv3-tiny network architecture consists of a seven-layer convolution networks and six max-pooling layers in the Darknet-53 network with two output branch scale predictions. CBCT images of teeth obtained from 4 patients consisted of 800 coronal slices of 2D grayscale images, containing 830 alveolar bone annotations. Before the training process, the ground truth image annotation was made in the form of a bounding box on the alveolar bone object. The detection results of the YOLOv3-tiny model were compared with the detection results of the YOLOv3 and YOLOv2-tiny models. The results of the experiment on 640 training images and 160 testing images showed that YOLOv3-tiny outperformed YOLOv2-tiny with mAP of 98.6% and 96.73%, respectively. Meanwhile, shows the same good result as YOLOv3.
{"title":"Alveolar Bone Detection from Dental Cone Beam Computed Tomography using YOLOv3-tiny","authors":"M. Widiasri, A. Arifin, N. Suciati, E. Astuti, R. Indraswari","doi":"10.1109/AIMS52415.2021.9466037","DOIUrl":"https://doi.org/10.1109/AIMS52415.2021.9466037","url":null,"abstract":"Cone Beam Computed Tomography (CBCT) is a medical imaging technique widely used in dentistry including dental implant planning. To determine the size of the dental implant, it is necessary to detect the alveolar bone at the implant site. In this study, we propose automatic detection of alveolar bone from CBCT images of teeth using the YOLOv3-tiny method. The YOLOv3-tiny network architecture consists of a seven-layer convolution networks and six max-pooling layers in the Darknet-53 network with two output branch scale predictions. CBCT images of teeth obtained from 4 patients consisted of 800 coronal slices of 2D grayscale images, containing 830 alveolar bone annotations. Before the training process, the ground truth image annotation was made in the form of a bounding box on the alveolar bone object. The detection results of the YOLOv3-tiny model were compared with the detection results of the YOLOv3 and YOLOv2-tiny models. The results of the experiment on 640 training images and 160 testing images showed that YOLOv3-tiny outperformed YOLOv2-tiny with mAP of 98.6% and 96.73%, respectively. Meanwhile, shows the same good result as YOLOv3.","PeriodicalId":299121,"journal":{"name":"2021 International Conference on Artificial Intelligence and Mechatronics Systems (AIMS)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133376833","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 : 2021-04-28DOI: 10.1109/AIMS52415.2021.9466040
Mushliha, A. Bustamam, Arry Yanuar, W. Mangunwardoyo, P. Anki, R. Amalia
Recently, the development of the artificial intelligence approach is a solution for evaluating the effectiveness, analysis, and safety of drug candidates due to a large number of data sets available. One of the approaches to artificial intelligence is deep learning. Deep learning has a significant influence on drug discovery procedures for rational drug development and optimization so that it can affect public health. The discovery of various inhibitors needs reliable models to figure out the side effects of the drug without requiring large costs and long amounts of time. A new way for the treatment of Alzheimer's disease is Acetylcholinesterase inhibitors. The Quantitative Structure-Activity Relationship (QSAR) model is a model used to filter large databases of the compound to figure the biological properties of chemical molecules based on their structure. The modeling that was used in this study was QSAR classification. The QSAR classification model predicted active and inactive compounds in Acetylcholinesterase inhibitors. There were 3809 inhibitors which consisted of 2215 active inhibitors and 1594 inactive inhibitors. They were labeled using fingerprints as descriptors. This study compared the performances of MLP and DNN in the classification. The result of this study showed DNN had better accuracy of 0.841 in classification.
{"title":"Comparison Accuracy of Multi-Layer Perceptron and DNN in QSAR Classification for Acetylcholinesterase Inhibitors","authors":"Mushliha, A. Bustamam, Arry Yanuar, W. Mangunwardoyo, P. Anki, R. Amalia","doi":"10.1109/AIMS52415.2021.9466040","DOIUrl":"https://doi.org/10.1109/AIMS52415.2021.9466040","url":null,"abstract":"Recently, the development of the artificial intelligence approach is a solution for evaluating the effectiveness, analysis, and safety of drug candidates due to a large number of data sets available. One of the approaches to artificial intelligence is deep learning. Deep learning has a significant influence on drug discovery procedures for rational drug development and optimization so that it can affect public health. The discovery of various inhibitors needs reliable models to figure out the side effects of the drug without requiring large costs and long amounts of time. A new way for the treatment of Alzheimer's disease is Acetylcholinesterase inhibitors. The Quantitative Structure-Activity Relationship (QSAR) model is a model used to filter large databases of the compound to figure the biological properties of chemical molecules based on their structure. The modeling that was used in this study was QSAR classification. The QSAR classification model predicted active and inactive compounds in Acetylcholinesterase inhibitors. There were 3809 inhibitors which consisted of 2215 active inhibitors and 1594 inactive inhibitors. They were labeled using fingerprints as descriptors. This study compared the performances of MLP and DNN in the classification. The result of this study showed DNN had better accuracy of 0.841 in classification.","PeriodicalId":299121,"journal":{"name":"2021 International Conference on Artificial Intelligence and Mechatronics Systems (AIMS)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134331961","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：