Pub Date : 2020-07-01DOI: 10.1109/IAICT50021.2020.9172036
Ahmad Tirta Hutomo, Muhammad Nasrun, C. Setianingsih
The interest and talent test is one of the methods and measurement tools in psychology that can help provide department or career recommendations that suit their interests and potential. Teenagers with an age range of 16–20 years must choose a field for college that suits their interests. Problems arise when they don’t know what majors they are interested. The web-based RMIB test with the Fuzzy method is the answer to that problem. The results of this test inform the user of the type of work that is suitable for them. So that it can help them choose a major for college or career. This application has an accuracy of 96%.
{"title":"Web-Based Psychological Rothwell Miller Interest Blank (RMIB) Test using Fuzzy Method","authors":"Ahmad Tirta Hutomo, Muhammad Nasrun, C. Setianingsih","doi":"10.1109/IAICT50021.2020.9172036","DOIUrl":"https://doi.org/10.1109/IAICT50021.2020.9172036","url":null,"abstract":"The interest and talent test is one of the methods and measurement tools in psychology that can help provide department or career recommendations that suit their interests and potential. Teenagers with an age range of 16–20 years must choose a field for college that suits their interests. Problems arise when they don’t know what majors they are interested. The web-based RMIB test with the Fuzzy method is the answer to that problem. The results of this test inform the user of the type of work that is suitable for them. So that it can help them choose a major for college or career. This application has an accuracy of 96%.","PeriodicalId":433718,"journal":{"name":"2020 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132919470","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 : 2020-07-01DOI: 10.1109/IAICT50021.2020.9172030
Muhtadin, Billy, E. M. Yuniarno, Junaidillah Fadlil, Muchlisin Adi Saputra, I. Purnama, M. Purnomo
Elderly people often forget to put the items they need due to decreased memory. In this study, we developed an Integrated platform assistance robot providing support to elderly people. We developed a robot assistant platform that was equipped with an indoor positioning system that can help the elderly find misplaced items. Deep learning already has good accuracy in detecting the object but requires great computation resources. When applied to devices that have limited computing and memory capabilities such as robots, the computation time becomes slow or not applicable. We built a lightweight CNN that could run on a single board computer. To improve the accuracy of the network, we apply knowledge distillation by using an extensive network (YOLOv3) as a teacher. To increase computational speed, we do it by reducing the number of layers by implementing batch normalization fission. After being tested on the YOLO, knowledge distillation method can be used to increase accuracy, batch normalization fission will increase computation speed. From the experiment results using the VOC dataset on YOLO architecture with MobileNet feature extractor, the knowledge distillation method can increase accuracy by 9.4% from 0.3850 mAP to 0.4215 mAP and batch normalization fission can speeds up the computation time to 100.7% from 8.3 FPS to 16.66 FPS on CPU i7. The Knowledge Distillation successfully increase the model’s accuracy, reducing the model’s size, and batch normalization fusion method can speed up the detection process.
{"title":"Robot Service for Elderly to Find Misplaced Items: A Resource Efficient Implementation on Low-Computational Device","authors":"Muhtadin, Billy, E. M. Yuniarno, Junaidillah Fadlil, Muchlisin Adi Saputra, I. Purnama, M. Purnomo","doi":"10.1109/IAICT50021.2020.9172030","DOIUrl":"https://doi.org/10.1109/IAICT50021.2020.9172030","url":null,"abstract":"Elderly people often forget to put the items they need due to decreased memory. In this study, we developed an Integrated platform assistance robot providing support to elderly people. We developed a robot assistant platform that was equipped with an indoor positioning system that can help the elderly find misplaced items. Deep learning already has good accuracy in detecting the object but requires great computation resources. When applied to devices that have limited computing and memory capabilities such as robots, the computation time becomes slow or not applicable. We built a lightweight CNN that could run on a single board computer. To improve the accuracy of the network, we apply knowledge distillation by using an extensive network (YOLOv3) as a teacher. To increase computational speed, we do it by reducing the number of layers by implementing batch normalization fission. After being tested on the YOLO, knowledge distillation method can be used to increase accuracy, batch normalization fission will increase computation speed. From the experiment results using the VOC dataset on YOLO architecture with MobileNet feature extractor, the knowledge distillation method can increase accuracy by 9.4% from 0.3850 mAP to 0.4215 mAP and batch normalization fission can speeds up the computation time to 100.7% from 8.3 FPS to 16.66 FPS on CPU i7. The Knowledge Distillation successfully increase the model’s accuracy, reducing the model’s size, and batch normalization fusion method can speed up the detection process.","PeriodicalId":433718,"journal":{"name":"2020 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"106 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132268600","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 : 2020-07-01DOI: 10.1109/IAICT50021.2020.9172021
Q. Nasir
Pyhyscial security is becoming a centre of focus in research for securing date transmission over wireless channels. One of the techniques is based on an Antenna subset modulation (ASM). ASM is of a low complexity single directional modulation. ASM is to modulate the radiated signal with a specified symbol rate using an array of switches along the radiation path. As a result of this kind of switching, the signal constellation in the targeted direction will not be distorted while a heavy distortion will affect the signal in the other undesired target directions and cause a random signal constellation in these directions. This research paper paper provides an intensive study of the performance of (ASM) in terms of probability of error and channel secrecy. A statistical model will be derived and their probability of symbol error rate when using different kind of data modulation. The simulation results of this paper show that ASM can be used efficiently for securing the multi-directional kind of transmission .
{"title":"Performance analysis Secure Wireless Communication using Antenna Subset Modulation","authors":"Q. Nasir","doi":"10.1109/IAICT50021.2020.9172021","DOIUrl":"https://doi.org/10.1109/IAICT50021.2020.9172021","url":null,"abstract":"Pyhyscial security is becoming a centre of focus in research for securing date transmission over wireless channels. One of the techniques is based on an Antenna subset modulation (ASM). ASM is of a low complexity single directional modulation. ASM is to modulate the radiated signal with a specified symbol rate using an array of switches along the radiation path. As a result of this kind of switching, the signal constellation in the targeted direction will not be distorted while a heavy distortion will affect the signal in the other undesired target directions and cause a random signal constellation in these directions. This research paper paper provides an intensive study of the performance of (ASM) in terms of probability of error and channel secrecy. A statistical model will be derived and their probability of symbol error rate when using different kind of data modulation. The simulation results of this paper show that ASM can be used efficiently for securing the multi-directional kind of transmission .","PeriodicalId":433718,"journal":{"name":"2020 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133864837","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 : 2020-07-01DOI: 10.1109/IAICT50021.2020.9172015
Sarah Nitalya Bakara, D. Gunawan
A call center is a media that can accommodate customer complaints, including IPTV customers. However, along with the development of IPTV technology, PT Telkom customer complaints through call center 147 are increasing so that call center traffic is also higher, and solutions are needed to reduce the traffic that appears on back end tickets. One of the most common IPTV customer complaints is the difficulty of subscribers to subscribe to additional features provided by the provider. In response to this, we designed a payment system where customers can make payments for many features on a self-care basis based on Application Programming Interface (API), known as Multi- services On-Screen Subscription (MOSS). The API functions as a tool to connect several applications through one interface to simplify the operating system. The payment system designed can be used prepaid or postpaid. It is hoped that the presence of MOSS will improve the Quality of Experience (QoE) because USeeTV customers do not have to waste time contacting call center 147. MOSS also combined with variation of Financial Technologies to support Industry 4.0.
{"title":"Payment System Innovation Package Add on IPTV Using Multi-services on Screen Subscription (MOSS) Case Study UseeTV","authors":"Sarah Nitalya Bakara, D. Gunawan","doi":"10.1109/IAICT50021.2020.9172015","DOIUrl":"https://doi.org/10.1109/IAICT50021.2020.9172015","url":null,"abstract":"A call center is a media that can accommodate customer complaints, including IPTV customers. However, along with the development of IPTV technology, PT Telkom customer complaints through call center 147 are increasing so that call center traffic is also higher, and solutions are needed to reduce the traffic that appears on back end tickets. One of the most common IPTV customer complaints is the difficulty of subscribers to subscribe to additional features provided by the provider. In response to this, we designed a payment system where customers can make payments for many features on a self-care basis based on Application Programming Interface (API), known as Multi- services On-Screen Subscription (MOSS). The API functions as a tool to connect several applications through one interface to simplify the operating system. The payment system designed can be used prepaid or postpaid. It is hoped that the presence of MOSS will improve the Quality of Experience (QoE) because USeeTV customers do not have to waste time contacting call center 147. MOSS also combined with variation of Financial Technologies to support Industry 4.0.","PeriodicalId":433718,"journal":{"name":"2020 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133224756","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 : 2020-07-01DOI: 10.1109/IAICT50021.2020.9172013
Dennisa Aliffa Nursafitri, U. Usman, M. Maulana
Motorized vehicles user, especially those who use the four wheels, who often pass the Jakarta-Cikampek toll road, may often have difficulty connecting to their cellular operator network services, which may be due to the density of users and the influence of the condition of the area which is classified as open space. Along with the increase of users passing through the Cikampek Toll Road, the construction of the overpass on the Jakarta-Cikampek route was held as a form of anticipation of traffic congestion. With this condition, the number of devices requiring network services in the area will also increase. Therefore, in this research will carry out network planning for the Cikampek elevated toll area. Network planning in this research will carry out by conducting capacity planning and coverage planning. The data that will be used for the planning will be base on Cikampek toll users, also the population of the cities around Cikampek elevated toll route. Then, from the data obtained will be use for calculations in coverage and capacity planning for the elevated toll that is being built. With this planning, it is known the minimum site of 8 to fulfilled the service to fulfilled the need of the users. By doing the simulation using Atoll software, was measure the quality of the network from the planning. With the SINR average of 8.23 dB, throughput average of 31.99 Mbps, and BLER average of 0,01%.
{"title":"Long Term Evolution (LTE) Network Planning in Jakarta-Cikampek Elevated Toll","authors":"Dennisa Aliffa Nursafitri, U. Usman, M. Maulana","doi":"10.1109/IAICT50021.2020.9172013","DOIUrl":"https://doi.org/10.1109/IAICT50021.2020.9172013","url":null,"abstract":"Motorized vehicles user, especially those who use the four wheels, who often pass the Jakarta-Cikampek toll road, may often have difficulty connecting to their cellular operator network services, which may be due to the density of users and the influence of the condition of the area which is classified as open space. Along with the increase of users passing through the Cikampek Toll Road, the construction of the overpass on the Jakarta-Cikampek route was held as a form of anticipation of traffic congestion. With this condition, the number of devices requiring network services in the area will also increase. Therefore, in this research will carry out network planning for the Cikampek elevated toll area. Network planning in this research will carry out by conducting capacity planning and coverage planning. The data that will be used for the planning will be base on Cikampek toll users, also the population of the cities around Cikampek elevated toll route. Then, from the data obtained will be use for calculations in coverage and capacity planning for the elevated toll that is being built. With this planning, it is known the minimum site of 8 to fulfilled the service to fulfilled the need of the users. By doing the simulation using Atoll software, was measure the quality of the network from the planning. With the SINR average of 8.23 dB, throughput average of 31.99 Mbps, and BLER average of 0,01%.","PeriodicalId":433718,"journal":{"name":"2020 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129847276","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 : 2020-07-01DOI: 10.1109/IAICT50021.2020.9172027
Midde Venkata Siva, E. P. Jayakumar
Scaling on the image is to be performed if the resolution of the target device and source device is not the same. Image interpolation is obtaining the unknown pixel from the known pixels. Bilinear interpolation is a commonly used interpolation technique for scaling the image because of its low complexity. Blurring effects on the scaled image due to bilinear interpolation is reduced by adding spatial sharp filter as a prefilter. To preserve the losses of edges, adaptive edge detection is used. In this paper, an approximated algorithm and its low-cost VLSI architecture is proposed for edge enhanced image scaling. Quality of the scaled images are evaluated and found to be good and comparable to that of the existing image scaling methods. The proposed architecture requires less area when compared to the existing architectures which can scale images without compromising the quality.
{"title":"Approximated algorithm and low cost VLSI architecture for edge enhanced image scaling","authors":"Midde Venkata Siva, E. P. Jayakumar","doi":"10.1109/IAICT50021.2020.9172027","DOIUrl":"https://doi.org/10.1109/IAICT50021.2020.9172027","url":null,"abstract":"Scaling on the image is to be performed if the resolution of the target device and source device is not the same. Image interpolation is obtaining the unknown pixel from the known pixels. Bilinear interpolation is a commonly used interpolation technique for scaling the image because of its low complexity. Blurring effects on the scaled image due to bilinear interpolation is reduced by adding spatial sharp filter as a prefilter. To preserve the losses of edges, adaptive edge detection is used. In this paper, an approximated algorithm and its low-cost VLSI architecture is proposed for edge enhanced image scaling. Quality of the scaled images are evaluated and found to be good and comparable to that of the existing image scaling methods. The proposed architecture requires less area when compared to the existing architectures which can scale images without compromising the quality.","PeriodicalId":433718,"journal":{"name":"2020 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131008084","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 : 2020-07-01DOI: 10.1109/IAICT50021.2020.9172023
Prita Dewi Mariyam, Vivi G. Anggraini, Adis Alifiawan, C. Apriono
In telecommunication industries, the radio frequency spectrum is a limited natural resource that should be managed and utilized effectively and efficiently. One critical issue is operators possibly assigned in uncontiguous spectrum allocations that may affect their optimum services. This paper proposes the process and analysis of a refarming application process to rearrange radio frequency in the 800 and 900 MHz bands to become contiguous bands for Indonesia telecommunication systems. The systems performances are analyzed in two main parameters in telecommunication industries, namely the dropcall and Standalone Dedicated Control Channel (SDCCH) success rate. The refarming process results dropcall and SDSR average of less than 1% and greater than 95%, respectively. This value is influenced by the signal’s quality in each cluster, weather, and geographical conditions. Also, an analysis of the timing of refarming was carried out in each cluster, and the results of the CDF regression is close to the two-order polynomial regression. The mobile network operators that have had contiguous frequency allocation can upgrade their network and deliver better user experience with a higher mobile broadband capacity.
{"title":"Refarming Performance Analysis of Mobile Broadband System in Indonesia","authors":"Prita Dewi Mariyam, Vivi G. Anggraini, Adis Alifiawan, C. Apriono","doi":"10.1109/IAICT50021.2020.9172023","DOIUrl":"https://doi.org/10.1109/IAICT50021.2020.9172023","url":null,"abstract":"In telecommunication industries, the radio frequency spectrum is a limited natural resource that should be managed and utilized effectively and efficiently. One critical issue is operators possibly assigned in uncontiguous spectrum allocations that may affect their optimum services. This paper proposes the process and analysis of a refarming application process to rearrange radio frequency in the 800 and 900 MHz bands to become contiguous bands for Indonesia telecommunication systems. The systems performances are analyzed in two main parameters in telecommunication industries, namely the dropcall and Standalone Dedicated Control Channel (SDCCH) success rate. The refarming process results dropcall and SDSR average of less than 1% and greater than 95%, respectively. This value is influenced by the signal’s quality in each cluster, weather, and geographical conditions. Also, an analysis of the timing of refarming was carried out in each cluster, and the results of the CDF regression is close to the two-order polynomial regression. The mobile network operators that have had contiguous frequency allocation can upgrade their network and deliver better user experience with a higher mobile broadband capacity.","PeriodicalId":433718,"journal":{"name":"2020 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"166 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113988875","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 : 2020-07-01DOI: 10.1109/IAICT50021.2020.9172009
Clinton Elian Gandana, J. D. K. Disu, Hongzhi Xie, Lixu Gu
The main objective paper is to make an empirical analysis of the effect of various unstated spatial goal constraints on reinforcement learning policy for the “reacher” task in the Robotic Scrub Nurse (RSN) application. This “reacher” task is an essential part of the RSN manipulation task, such as the task of picking, grasping, or placing the surgical instruments. This paper provides our experimental results and the evaluation of the “reacher” task under different spatial goal constraints. We researched the effect of this unstated assumption on a reinforcement learning (RL) algorithm: Soft-Actor Critic with Hindsight Experience Replay (SAC+HER). We used the 7-DoF robotic arm to evaluate this state-of-the-art deep RL algorithm. We performed our experiments in a virtual environment while training the robotic arm to reach the random target points. The implementation of this RL algorithm showed a robust performance, which is measured by reward values and success rates. We observed, these reinforcement learning assumptions, particularly the unstated spatial goal constraints, can affect the performance of the RL agent. The important aspect of the “reacher” task and the development of reinforcement learning applications in medical robotics is one of the main motivations behind this research objective.
{"title":"Analyzing Different Unstated Goal Constraints on Reinforcement Learning Algorithm for Reacher Task in the Robotic Scrub Nurse Application","authors":"Clinton Elian Gandana, J. D. K. Disu, Hongzhi Xie, Lixu Gu","doi":"10.1109/IAICT50021.2020.9172009","DOIUrl":"https://doi.org/10.1109/IAICT50021.2020.9172009","url":null,"abstract":"The main objective paper is to make an empirical analysis of the effect of various unstated spatial goal constraints on reinforcement learning policy for the “reacher” task in the Robotic Scrub Nurse (RSN) application. This “reacher” task is an essential part of the RSN manipulation task, such as the task of picking, grasping, or placing the surgical instruments. This paper provides our experimental results and the evaluation of the “reacher” task under different spatial goal constraints. We researched the effect of this unstated assumption on a reinforcement learning (RL) algorithm: Soft-Actor Critic with Hindsight Experience Replay (SAC+HER). We used the 7-DoF robotic arm to evaluate this state-of-the-art deep RL algorithm. We performed our experiments in a virtual environment while training the robotic arm to reach the random target points. The implementation of this RL algorithm showed a robust performance, which is measured by reward values and success rates. We observed, these reinforcement learning assumptions, particularly the unstated spatial goal constraints, can affect the performance of the RL agent. The important aspect of the “reacher” task and the development of reinforcement learning applications in medical robotics is one of the main motivations behind this research objective.","PeriodicalId":433718,"journal":{"name":"2020 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115710037","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 : 2020-07-01DOI: 10.1109/IAICT50021.2020.9172033
Bern Jonathan, P. Putra, Y. Ruldeviyani
Female Daily is a beauty platform that has social media application share users’ experiences of beauty by posting images and text in a post. Female Daily has terms of condition to not use the platform for selling in their post. Somehow, users of Female Daily sometimes use the platform for selling beauty products. Post of users in Female Daily records in Female Daily databases. In that data, there are imbalanced data about users’ posts that banned (minority class) and post that admin does not ban because it does not contain selling products (majority class). SMOTE and Tomek are techniques for handling imbalanced data by over-sampling and under-sampling techniques repeatedly to manage the data into balance. In this study, we want to evaluate the imbalanced data text in Female Daily using SMOTE, Tomek, and SMOTE-Tomek. Predicting algorithms that we will use are Support Vector Machine (SVM) and Logistic Regression (LR) using transform vector TF-IDF to evaluate the best methods to predict the users selling products on Female Daily. The results of this study show us the effect of SMOTE, Tomek, and SMOTE-Tomek to Precision-Recall in people selling products (majority class) is effects not quite high and also reducing the Precision-Recall, but for people selling products (minority class) is positives improvement. The highest results combination each metrics are; G-Mean combination SMOTE-Tomek with SVM, Precision to minority class combination of SMOTE with SVM, Recall to minority class combination of SMOTE with LR. Experimental results on this study indicate the usefulness of the using SMOTE or SMOTE-Tomek approach.
{"title":"Observation Imbalanced Data Text to Predict Users Selling Products on Female Daily with SMOTE, Tomek, and SMOTE-Tomek","authors":"Bern Jonathan, P. Putra, Y. Ruldeviyani","doi":"10.1109/IAICT50021.2020.9172033","DOIUrl":"https://doi.org/10.1109/IAICT50021.2020.9172033","url":null,"abstract":"Female Daily is a beauty platform that has social media application share users’ experiences of beauty by posting images and text in a post. Female Daily has terms of condition to not use the platform for selling in their post. Somehow, users of Female Daily sometimes use the platform for selling beauty products. Post of users in Female Daily records in Female Daily databases. In that data, there are imbalanced data about users’ posts that banned (minority class) and post that admin does not ban because it does not contain selling products (majority class). SMOTE and Tomek are techniques for handling imbalanced data by over-sampling and under-sampling techniques repeatedly to manage the data into balance. In this study, we want to evaluate the imbalanced data text in Female Daily using SMOTE, Tomek, and SMOTE-Tomek. Predicting algorithms that we will use are Support Vector Machine (SVM) and Logistic Regression (LR) using transform vector TF-IDF to evaluate the best methods to predict the users selling products on Female Daily. The results of this study show us the effect of SMOTE, Tomek, and SMOTE-Tomek to Precision-Recall in people selling products (majority class) is effects not quite high and also reducing the Precision-Recall, but for people selling products (minority class) is positives improvement. The highest results combination each metrics are; G-Mean combination SMOTE-Tomek with SVM, Precision to minority class combination of SMOTE with SVM, Recall to minority class combination of SMOTE with LR. Experimental results on this study indicate the usefulness of the using SMOTE or SMOTE-Tomek approach.","PeriodicalId":433718,"journal":{"name":"2020 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"4 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123421460","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 : 2020-07-01DOI: 10.1109/IAICT50021.2020.9172011
M. Skorikov, S. Momen
In this paper, machine learning approaches have been used to predict whether a scientific paper will be accepted in a top-tier AI conferences or not. This shall help authors identify the likelihood of their paper getting accepted in a top-tier AI conference. We have used the PeerRead dataset containing papers collected from major AI conferences that are publicly available. We have achieved an accuracy of 81% using Random Forest classifier. The novelty of the paper lies in accurately predicting whether a scientific paper will be accepted in the top AI conference.
{"title":"Machine learning approach to predicting the acceptance of academic papers","authors":"M. Skorikov, S. Momen","doi":"10.1109/IAICT50021.2020.9172011","DOIUrl":"https://doi.org/10.1109/IAICT50021.2020.9172011","url":null,"abstract":"In this paper, machine learning approaches have been used to predict whether a scientific paper will be accepted in a top-tier AI conferences or not. This shall help authors identify the likelihood of their paper getting accepted in a top-tier AI conference. We have used the PeerRead dataset containing papers collected from major AI conferences that are publicly available. We have achieved an accuracy of 81% using Random Forest classifier. The novelty of the paper lies in accurately predicting whether a scientific paper will be accepted in the top AI conference.","PeriodicalId":433718,"journal":{"name":"2020 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133258950","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：