Pub Date : 2022-12-22DOI: 10.1109/ISMODE56940.2022.10180999
Yuri Pamungkas, Yahya Rais
Innovations in robotics have been widely used and developed to facilitate various lines of human life. Robots are often designed to have human-like abilities (such as by implanting hearing abilities). However, many challenges need to be overcome in the application process. One of them is related to sound localization (determination of the sound source direction). Research related to sound localization has indeed been carried out by many researchers before. However, previous research still tends to use a lot of array microphones for the sound localization process, and the delay in sound detection still needs to be considered. Therefore, we are trying to build a real-time sound source localization system using the Interaural Time Difference Method. In this study, two array microphones were used for sound source detection, and a DSP board (TMS320C6713) was used for data processing so that this system could detect sound sources quickly and accurately. Based on the test results, this system can detect the source and direction of sound in real-time. It can be seen from the value of the detection delay, which ranges from 3. 05-27.08ms. In addition, the system can also predict sound direction quite well even though at measurement angles of more than -80° and 80°, there is still an estimation error (around 3.61% - 4.76%). Meanwhile, at angles of measurement less than -80° and 80°, the accuracy of the estimation of the direction of sound reaches 100%.
{"title":"Implementation of Real-Time Sound Source Localization using TMS320C6713 Board with Interaural Time Difference Method","authors":"Yuri Pamungkas, Yahya Rais","doi":"10.1109/ISMODE56940.2022.10180999","DOIUrl":"https://doi.org/10.1109/ISMODE56940.2022.10180999","url":null,"abstract":"Innovations in robotics have been widely used and developed to facilitate various lines of human life. Robots are often designed to have human-like abilities (such as by implanting hearing abilities). However, many challenges need to be overcome in the application process. One of them is related to sound localization (determination of the sound source direction). Research related to sound localization has indeed been carried out by many researchers before. However, previous research still tends to use a lot of array microphones for the sound localization process, and the delay in sound detection still needs to be considered. Therefore, we are trying to build a real-time sound source localization system using the Interaural Time Difference Method. In this study, two array microphones were used for sound source detection, and a DSP board (TMS320C6713) was used for data processing so that this system could detect sound sources quickly and accurately. Based on the test results, this system can detect the source and direction of sound in real-time. It can be seen from the value of the detection delay, which ranges from 3. 05-27.08ms. In addition, the system can also predict sound direction quite well even though at measurement angles of more than -80° and 80°, there is still an estimation error (around 3.61% - 4.76%). Meanwhile, at angles of measurement less than -80° and 80°, the accuracy of the estimation of the direction of sound reaches 100%.","PeriodicalId":335247,"journal":{"name":"2022 2nd International Seminar on Machine Learning, Optimization, and Data Science (ISMODE)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115372709","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 : 2022-12-22DOI: 10.1109/ISMODE56940.2022.10180916
Wanvy Arifha Saputra, Inayatul Ulya Ahyati, A. Yunanto, Syamsudin Noor, A. N. Asyikin, Dimas Fanny Hebrasianto Permadi
Rubber trees can be said to be mature by having a trunk circumference of more than 45 cm at the height of 130 cm from the ground. It influences the use of digital imagery to determine the classification of “mature rubber trees” and “immature rubber trees”. The challenge in the image of rubber trees is that they have similar colour characteristics between tree trunks and the ground, and multi-object rubber trees in one picture. We propose a method using the gray-level co-occurrence matrix (GLCM) and geometric shape for the classification of Rubber Tree Maturity. GLCM is used to measure neighbouring pixels with grey intensity, distance, and angle in solving the first characteristic problem. Geometric shapes used to solve the second characteristic problem with the help of determining a region of interest (ROI). The research results show that the proposed method was successfully carried out with the strongest evidence on the support vector machine (SVM), namely 0.800 f1-score, 0.778 precision and 0.824 recall.
{"title":"Gray-Level Co-Occurrence Matrix and Geometric Shape for Classification of Rubber Tree Maturity","authors":"Wanvy Arifha Saputra, Inayatul Ulya Ahyati, A. Yunanto, Syamsudin Noor, A. N. Asyikin, Dimas Fanny Hebrasianto Permadi","doi":"10.1109/ISMODE56940.2022.10180916","DOIUrl":"https://doi.org/10.1109/ISMODE56940.2022.10180916","url":null,"abstract":"Rubber trees can be said to be mature by having a trunk circumference of more than 45 cm at the height of 130 cm from the ground. It influences the use of digital imagery to determine the classification of “mature rubber trees” and “immature rubber trees”. The challenge in the image of rubber trees is that they have similar colour characteristics between tree trunks and the ground, and multi-object rubber trees in one picture. We propose a method using the gray-level co-occurrence matrix (GLCM) and geometric shape for the classification of Rubber Tree Maturity. GLCM is used to measure neighbouring pixels with grey intensity, distance, and angle in solving the first characteristic problem. Geometric shapes used to solve the second characteristic problem with the help of determining a region of interest (ROI). The research results show that the proposed method was successfully carried out with the strongest evidence on the support vector machine (SVM), namely 0.800 f1-score, 0.778 precision and 0.824 recall.","PeriodicalId":335247,"journal":{"name":"2022 2nd International Seminar on Machine Learning, Optimization, and Data Science (ISMODE)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123461358","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 : 2022-12-22DOI: 10.1109/ISMODE56940.2022.10180983
Hamdy Nur Saidy, A. A. Ilham, Syafaruddin
There have been several studies on the scheduling mechanism in cloud manufacture in on-factory manufacturing situations. However, scheduling mechanism in cloud manufacture in an off-factory situation (field cloud manufacturing) has not been widely studied. Even though there are many manufacturing tasks that need to be implemented using field manufacturing scheme. So in this study, a research on scheduling problems in field cloud manufacture system was carried out. The research process begins with creating a model for scheduling problem in field cloud manufacture. This model is designed by analyzing the workflow of field cloud manufacture system. Then by analyzing the assumptions and limitations contained in the field manufacturing scheme, the encoding and decoding methods of the scheduling model and the parameters used to measure the performance of the proposed solutions can be determined. After that, the Elitist Genetic Algorithm (EGA) and Elitist Ant Colony optimization (EACO) were applied to the scheduling problem model to carry out the process of finding optimal scheduling solutions. The results of this study showed that the Elitist Genetic Algorithm (EGA) and Elitist Ant Colony optimization (EACO) can be used to optimize the scheduling problem in field cloud manufacturing and the overall improvement of the optimized schedule scheme is improved by 40,3% by EGA and 3S,7S% by EACO. It can be seen that EGA and EACO suitable for optimizing the problems with large solution spaces like scheduling in field cloud manufacturing. But this study also shows that the performance of EGA is far superior both in terms of the value of the resulting fitness schedule and in terms of the time consumed to produce the schedule compared to EACO.
{"title":"Elitist Genetic Algorithm and Elitist Ant Colony Optimization on Resource Scheduling in Field Cloud Manufacturing","authors":"Hamdy Nur Saidy, A. A. Ilham, Syafaruddin","doi":"10.1109/ISMODE56940.2022.10180983","DOIUrl":"https://doi.org/10.1109/ISMODE56940.2022.10180983","url":null,"abstract":"There have been several studies on the scheduling mechanism in cloud manufacture in on-factory manufacturing situations. However, scheduling mechanism in cloud manufacture in an off-factory situation (field cloud manufacturing) has not been widely studied. Even though there are many manufacturing tasks that need to be implemented using field manufacturing scheme. So in this study, a research on scheduling problems in field cloud manufacture system was carried out. The research process begins with creating a model for scheduling problem in field cloud manufacture. This model is designed by analyzing the workflow of field cloud manufacture system. Then by analyzing the assumptions and limitations contained in the field manufacturing scheme, the encoding and decoding methods of the scheduling model and the parameters used to measure the performance of the proposed solutions can be determined. After that, the Elitist Genetic Algorithm (EGA) and Elitist Ant Colony optimization (EACO) were applied to the scheduling problem model to carry out the process of finding optimal scheduling solutions. The results of this study showed that the Elitist Genetic Algorithm (EGA) and Elitist Ant Colony optimization (EACO) can be used to optimize the scheduling problem in field cloud manufacturing and the overall improvement of the optimized schedule scheme is improved by 40,3% by EGA and 3S,7S% by EACO. It can be seen that EGA and EACO suitable for optimizing the problems with large solution spaces like scheduling in field cloud manufacturing. But this study also shows that the performance of EGA is far superior both in terms of the value of the resulting fitness schedule and in terms of the time consumed to produce the schedule compared to EACO.","PeriodicalId":335247,"journal":{"name":"2022 2nd International Seminar on Machine Learning, Optimization, and Data Science (ISMODE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130652103","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 : 2022-12-22DOI: 10.1109/ISMODE56940.2022.10181004
Muluken Regas Eressa, Hakim Badis, R. Langar, Dorian Grosso
For machine learning algorithms the availability of huge data offers ample opportunity to learn and infer educated generalizations. However, for gaussian process the size of the data presents a challenge for their wider application in the areas of big data domain. Various approaches have been suggested to ensure scalability and computational efficiency. Such as, the kernel approximation and the variational inference are few notable mentions. This paper proposes a random sparse Gaussian approximation method based on a stochastic column sampling. It employs frequency analysis to select subsets of points that would generalize the observed data. Then, applies sparsity and sampling without replacement strategy when building the model. The predictive performance of the model is evaluated using the Variational Gaussian Process (VGA) as a benchmark. We run a Monte Carlo type model building and evaluation scheme using the mean square error (MSE) and R2 score as quality metrics. An ensemble of models were trained and evaluated for different sampling sizes under the same setting. The experiments have shown that the RSGA, on average is 10 times faster and offer better predictive performance compared to VGA. In addition, the RSGA offers a robust response to changes in kernel type compared to the VGA. Hence, for a fast optimal kernel estimation and big data analysis, the RSGA can give an alternative route to model building and inference.
{"title":"Random Sparse Approximation for a Fast and Scalable Gaussian Process","authors":"Muluken Regas Eressa, Hakim Badis, R. Langar, Dorian Grosso","doi":"10.1109/ISMODE56940.2022.10181004","DOIUrl":"https://doi.org/10.1109/ISMODE56940.2022.10181004","url":null,"abstract":"For machine learning algorithms the availability of huge data offers ample opportunity to learn and infer educated generalizations. However, for gaussian process the size of the data presents a challenge for their wider application in the areas of big data domain. Various approaches have been suggested to ensure scalability and computational efficiency. Such as, the kernel approximation and the variational inference are few notable mentions. This paper proposes a random sparse Gaussian approximation method based on a stochastic column sampling. It employs frequency analysis to select subsets of points that would generalize the observed data. Then, applies sparsity and sampling without replacement strategy when building the model. The predictive performance of the model is evaluated using the Variational Gaussian Process (VGA) as a benchmark. We run a Monte Carlo type model building and evaluation scheme using the mean square error (MSE) and R2 score as quality metrics. An ensemble of models were trained and evaluated for different sampling sizes under the same setting. The experiments have shown that the RSGA, on average is 10 times faster and offer better predictive performance compared to VGA. In addition, the RSGA offers a robust response to changes in kernel type compared to the VGA. Hence, for a fast optimal kernel estimation and big data analysis, the RSGA can give an alternative route to model building and inference.","PeriodicalId":335247,"journal":{"name":"2022 2nd International Seminar on Machine Learning, Optimization, and Data Science (ISMODE)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134230076","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 : 2022-12-22DOI: 10.1109/ISMODE56940.2022.10180933
Muhammad Abdillah Rahmat, Indrabayu, A. Achmad, Ejah Umraeni Salam, Muhammad Fadhil Bin Bahrunnida
Several stages will be carried out in developing an intelligent transportation system, including building stereo vision by utilizing two cameras with stereo performance. Before vehicle object detection, vehicle distance and speed detection are implemented in the user’s vehicle by using cameras. Camera calibration is a process that should be noticed in computer vision. The calibration process is usually carried out if the camera is to be used to estimate the camera’s distance to a particular object. The camera stereo calibration system has been carried out and successfully implemented to detect vehicle distance and relative speed of vehicles on autonomous cars. OpenCV with c920 stRealm pro and c922 stRealm pro cameras is used to implement stereo vision on the camera. Optimal calibration conditions were obtained on a chessboard pattern measuring 3 cm with a distance between the lenses of 9.8 cm and shooting ranges from 0.5 cm. The optimal conditions were obtained based on the RMSE value of 0.4932.
{"title":"Stereo Camera Calibration For Autonomous Car Applications","authors":"Muhammad Abdillah Rahmat, Indrabayu, A. Achmad, Ejah Umraeni Salam, Muhammad Fadhil Bin Bahrunnida","doi":"10.1109/ISMODE56940.2022.10180933","DOIUrl":"https://doi.org/10.1109/ISMODE56940.2022.10180933","url":null,"abstract":"Several stages will be carried out in developing an intelligent transportation system, including building stereo vision by utilizing two cameras with stereo performance. Before vehicle object detection, vehicle distance and speed detection are implemented in the user’s vehicle by using cameras. Camera calibration is a process that should be noticed in computer vision. The calibration process is usually carried out if the camera is to be used to estimate the camera’s distance to a particular object. The camera stereo calibration system has been carried out and successfully implemented to detect vehicle distance and relative speed of vehicles on autonomous cars. OpenCV with c920 stRealm pro and c922 stRealm pro cameras is used to implement stereo vision on the camera. Optimal calibration conditions were obtained on a chessboard pattern measuring 3 cm with a distance between the lenses of 9.8 cm and shooting ranges from 0.5 cm. The optimal conditions were obtained based on the RMSE value of 0.4932.","PeriodicalId":335247,"journal":{"name":"2022 2nd International Seminar on Machine Learning, Optimization, and Data Science (ISMODE)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133907309","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 : 2022-12-22DOI: 10.1109/ISMODE56940.2022.10181005
M. Djalal, I. Robandi
To improve the generator’s performance, additional equipment is needed, mainly if oscillations occur outside the excitation control of the generator. PSS will increase the stability limit by providing damping for generator oscillations. PSS damping means that the PSS will produce an electric torque component that is in phase with the change in speed. However, the use of PSS has many errors, especially conventional PSS. The desired value is different from the measured PSS output value. This is due to shaft motion components such as lateral shaft run out or torsional oscillations. In this study, the Dual Input Power System Stabilizer (DIPSS) equipment was used to reduce signal noise on the generator in the Sulselrabar system. With optimal DIPSS parameters, optimal system performance is obtained. An intelligent optimization technique based on the Mayfly optimization Algorithm (MOA) is used to get the correct parameters. MOA is used to find the correct parameters and get the system’s minimum damping. Then the placement of DIPSS is based on the participation factor method of each generator. This study uses a case study of the addition of a load on the Sengkang generator. From the test results, system performance increases with the installation of DIPSS MOA. The increase in system performance can be seen from the speed and angle response of the generator rotor, which produces minimal overshoot oscillations and fast settling time when a disturbance occurs. In addition, the increase in system performance can also be seen from the negative system eigenvalues.
{"title":"Dual Input Power System Stabilizer in Sulselrabar System Based on Mayfly Optimization Algorithm","authors":"M. Djalal, I. Robandi","doi":"10.1109/ISMODE56940.2022.10181005","DOIUrl":"https://doi.org/10.1109/ISMODE56940.2022.10181005","url":null,"abstract":"To improve the generator’s performance, additional equipment is needed, mainly if oscillations occur outside the excitation control of the generator. PSS will increase the stability limit by providing damping for generator oscillations. PSS damping means that the PSS will produce an electric torque component that is in phase with the change in speed. However, the use of PSS has many errors, especially conventional PSS. The desired value is different from the measured PSS output value. This is due to shaft motion components such as lateral shaft run out or torsional oscillations. In this study, the Dual Input Power System Stabilizer (DIPSS) equipment was used to reduce signal noise on the generator in the Sulselrabar system. With optimal DIPSS parameters, optimal system performance is obtained. An intelligent optimization technique based on the Mayfly optimization Algorithm (MOA) is used to get the correct parameters. MOA is used to find the correct parameters and get the system’s minimum damping. Then the placement of DIPSS is based on the participation factor method of each generator. This study uses a case study of the addition of a load on the Sengkang generator. From the test results, system performance increases with the installation of DIPSS MOA. The increase in system performance can be seen from the speed and angle response of the generator rotor, which produces minimal overshoot oscillations and fast settling time when a disturbance occurs. In addition, the increase in system performance can also be seen from the negative system eigenvalues.","PeriodicalId":335247,"journal":{"name":"2022 2nd International Seminar on Machine Learning, Optimization, and Data Science (ISMODE)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125475104","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 : 2022-12-22DOI: 10.1109/ISMODE56940.2022.10181002
H. Saragi, Iswanti Sihaloho, W. Siagian, R. Pardede, Santi Agustina Manalu
Electric power is one of the basic human needs. To fulfil the consumer’s power requirement, the electricity supplier and provider need an economical and reliable distribution system. Nowadays, a transformer has been installed in the power distribution system, and if it is moved, it will need a high replacement cost. Therefore, the development of the power distribution system will not change the existing transformer location. However, the current transformer capacity does not adequate to provide the electricity requirement; therefore, newly placed transformers are required to support and provide the needs. This research aims to determine the optimal combination of existing and newly placed transformers to provide a reliable and economical power system. The reliable power distribution system is gained from the shortest power connection distance and low power loss distribution system. The most economical power system is gained by finding the transformation location that produces the lowest cost for power distribution installation, system installation, and lowest transformer losses. The optimal condition is calculated by a genetic algorithm respecting the voltage limit regulation. The result combines existing transformers and newly placed transformers in PT. PLN (PERSERO) Rayon Dolok Masihul Sumatera Utara is the transformer coordinate and capacity, the transformer load combination, and the minimum investment cost.
电力是人类的基本需求之一。为了满足用户的用电需求，电力供应商和供应商需要一个经济可靠的配电系统。如今，配电系统中已经安装了变压器，如果将其移动，则需要很高的更换成本。因此，配电系统的发展不会改变现有变压器的位置。但是，当前变压器的容量不足以提供用电需求;因此，新放置的变压器需要支持和提供需求。本研究旨在确定现有变压器和新变压器的最佳组合，以提供可靠和经济的电力系统。可靠的配电系统是指接线距离短、损耗小的配电系统。寻找配电安装成本、系统安装成本和变压器损耗最低的变电站位置，从而获得最经济的电力系统。采用遗传算法计算了电压极限调节的最优条件。结合PT. PLN (PERSERO) Rayon Dolok Masihul sumata Utara现有变压器和新放置变压器的结果是变压器坐标和容量，变压器负载组合，以及最小投资成本。
{"title":"Combination of Existing Transformer and Newly Placed Transformer for Optimal Electric Power Distribution System","authors":"H. Saragi, Iswanti Sihaloho, W. Siagian, R. Pardede, Santi Agustina Manalu","doi":"10.1109/ISMODE56940.2022.10181002","DOIUrl":"https://doi.org/10.1109/ISMODE56940.2022.10181002","url":null,"abstract":"Electric power is one of the basic human needs. To fulfil the consumer’s power requirement, the electricity supplier and provider need an economical and reliable distribution system. Nowadays, a transformer has been installed in the power distribution system, and if it is moved, it will need a high replacement cost. Therefore, the development of the power distribution system will not change the existing transformer location. However, the current transformer capacity does not adequate to provide the electricity requirement; therefore, newly placed transformers are required to support and provide the needs. This research aims to determine the optimal combination of existing and newly placed transformers to provide a reliable and economical power system. The reliable power distribution system is gained from the shortest power connection distance and low power loss distribution system. The most economical power system is gained by finding the transformation location that produces the lowest cost for power distribution installation, system installation, and lowest transformer losses. The optimal condition is calculated by a genetic algorithm respecting the voltage limit regulation. The result combines existing transformers and newly placed transformers in PT. PLN (PERSERO) Rayon Dolok Masihul Sumatera Utara is the transformer coordinate and capacity, the transformer load combination, and the minimum investment cost.","PeriodicalId":335247,"journal":{"name":"2022 2nd International Seminar on Machine Learning, Optimization, and Data Science (ISMODE)","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129296352","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 : 2022-12-22DOI: 10.1109/ISMODE56940.2022.10180907
Andi Nurkholis, Styawati, Vega Purwayoga, Hen Hen Lukmana, Agung Prihandono, Wawan Koswara
Rainfall has an essential role in human life, including the agricultural aspect. By knowing the estimated intensity of rainfall that will fall in an area at a particular time, we can determine a good planting period for commodities that require rainfall prediction. This study aims to produce a rainfall prediction model using the C5.0 Algorithm on the Bogor Regency daily weather dataset in the previous five years (2017 - 2021). The dataset is divided into two categories, namely nine explanatory factors (date, month, minimum temperature, maximum temperature, average temperature, average humidity, sun exposure, maximum wind speed, and average wind speed) and one target class rainfall category (low, medium, and high). The best model variation was generated using a 5-fold CV, which resulted in five model partitions with a total accuracy of 86.33% in the training data and 84.22% in the test data. The resultant rules include 72 attributes, two partitions pick the average humidity as root node, and the remaining three choose the average temperature. The model rules produce rainfall prediction information that can assist in determining the best cultivation time for an agricultural commodity to increase yield productivity.
{"title":"Analysis of Weather Data for Rainfall Prediction using C5.0 Decision Tree Algorithm","authors":"Andi Nurkholis, Styawati, Vega Purwayoga, Hen Hen Lukmana, Agung Prihandono, Wawan Koswara","doi":"10.1109/ISMODE56940.2022.10180907","DOIUrl":"https://doi.org/10.1109/ISMODE56940.2022.10180907","url":null,"abstract":"Rainfall has an essential role in human life, including the agricultural aspect. By knowing the estimated intensity of rainfall that will fall in an area at a particular time, we can determine a good planting period for commodities that require rainfall prediction. This study aims to produce a rainfall prediction model using the C5.0 Algorithm on the Bogor Regency daily weather dataset in the previous five years (2017 - 2021). The dataset is divided into two categories, namely nine explanatory factors (date, month, minimum temperature, maximum temperature, average temperature, average humidity, sun exposure, maximum wind speed, and average wind speed) and one target class rainfall category (low, medium, and high). The best model variation was generated using a 5-fold CV, which resulted in five model partitions with a total accuracy of 86.33% in the training data and 84.22% in the test data. The resultant rules include 72 attributes, two partitions pick the average humidity as root node, and the remaining three choose the average temperature. The model rules produce rainfall prediction information that can assist in determining the best cultivation time for an agricultural commodity to increase yield productivity.","PeriodicalId":335247,"journal":{"name":"2022 2nd International Seminar on Machine Learning, Optimization, and Data Science (ISMODE)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115329801","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 : 2022-12-22DOI: 10.1109/ISMODE56940.2022.10180425
Nicola Bastianello, L. Badia
Future smart cities are expected to have efficient control of vehicular traffic to provide satisfactory mobility and transportation of people and goods. Reliable and efficient control schedule design for signalized intersections is needed to alleviate vehicular congestions and improve the overall road network management. In the present paper, we propose an approach based on game theory to design a decentralized intersection traffic controller, able to adaptively react to changing traffic conditions and minimize the waiting time of the cars in queue. We adopt a Bayesian dynamic game framework, which is able to improve the existing state of the art alternatives by reducing the amount of data exchanged from monitoring roadside units. Moreover, we also introduce a tunable sharing factor that is a design element available to the traffic planner controlling the priority of access and allowing for prioritization. Finally, the proposed solution is extensively evaluated via simulation in different scenarios.
{"title":"Decentralized Intersection Control Using Bayesian Game Theory","authors":"Nicola Bastianello, L. Badia","doi":"10.1109/ISMODE56940.2022.10180425","DOIUrl":"https://doi.org/10.1109/ISMODE56940.2022.10180425","url":null,"abstract":"Future smart cities are expected to have efficient control of vehicular traffic to provide satisfactory mobility and transportation of people and goods. Reliable and efficient control schedule design for signalized intersections is needed to alleviate vehicular congestions and improve the overall road network management. In the present paper, we propose an approach based on game theory to design a decentralized intersection traffic controller, able to adaptively react to changing traffic conditions and minimize the waiting time of the cars in queue. We adopt a Bayesian dynamic game framework, which is able to improve the existing state of the art alternatives by reducing the amount of data exchanged from monitoring roadside units. Moreover, we also introduce a tunable sharing factor that is a design element available to the traffic planner controlling the priority of access and allowing for prioritization. Finally, the proposed solution is extensively evaluated via simulation in different scenarios.","PeriodicalId":335247,"journal":{"name":"2022 2nd International Seminar on Machine Learning, Optimization, and Data Science (ISMODE)","volume":"355 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121630040","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 : 2022-12-22DOI: 10.1109/ISMODE56940.2022.10180961
F. W. Wibowo, Wihayati
Using field programmable gate arrays (FPGAs) as a hardware platform still plays a significant role in digital signal processing. It is because the FPGA has a relatively strong influence on the processing speed and task distribution of its components in parallel. This paper aims to design a hardware-based power meter by applying the Goertzel algorithm, in this case, using an FPGA. The FPGA reconfiguration language used in this design is very high-speed integrated circuit hardware description language (VHDL). The design results that have been synthesized are three top-level modules consisting of an analog capture circuit controller, a DSP module that implements the Goertzel algorithm, and a DAC. The analog capture circuit controller module has three input types and nine output types. While DSP modules have four input types and four output types, and DAC modules have four input types and six output types. The design of this power meter produced an average power factor of 0.96.
{"title":"Field Programmable Gate Arrays-Based Design of Electrical Power Measurement using Goertzel Algorithm","authors":"F. W. Wibowo, Wihayati","doi":"10.1109/ISMODE56940.2022.10180961","DOIUrl":"https://doi.org/10.1109/ISMODE56940.2022.10180961","url":null,"abstract":"Using field programmable gate arrays (FPGAs) as a hardware platform still plays a significant role in digital signal processing. It is because the FPGA has a relatively strong influence on the processing speed and task distribution of its components in parallel. This paper aims to design a hardware-based power meter by applying the Goertzel algorithm, in this case, using an FPGA. The FPGA reconfiguration language used in this design is very high-speed integrated circuit hardware description language (VHDL). The design results that have been synthesized are three top-level modules consisting of an analog capture circuit controller, a DSP module that implements the Goertzel algorithm, and a DAC. The analog capture circuit controller module has three input types and nine output types. While DSP modules have four input types and four output types, and DAC modules have four input types and six output types. The design of this power meter produced an average power factor of 0.96.","PeriodicalId":335247,"journal":{"name":"2022 2nd International Seminar on Machine Learning, Optimization, and Data Science (ISMODE)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122053165","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：