Pub Date : 2023-02-16DOI: 10.1109/ICCoSITE57641.2023.10127697
Wisudantyo Wahyu Priambodo, H. Wijanto, N. Adriansyah
The main problem faced by cellular operators in Indonesia is the cost of infrastructure investment which is very expensiv. Thus, a sharing infrastructure scheme is needed between cellular operators to reduce the Capex and Opex. In this thesis, the author will examine the feasibility of a 5G infrastructure core sharing (CN sharing) scheme for cellular operators in Indonesia using two aspects, namely technology and economy. From the technological aspect, the writer will analyze the capacity and coverage approach. The economic aspect is carried out to test the business feasibility of this RAN-frequency sharing scheme from the cellular operator's point of view. The research will be conducted in 2 types of areas, urban area (Banjarmasin City) and suburban area (Banjarbaru City) for 7 years ahead (2022-2028). Based on capacity and coverage planning, Banjarmasin city need 84 gNodeB and Banjarbaru city need 71 gNodeB. The results of the study show that the implementation of the RAN-spectrum sharing scheme can reduce Capex costs 50-67%. The most feasible scenario to be implemented from economical point of view is sharing 3 operators for economic parameter Net Present Value, Internal Rate of Return and Payback Period. Sensitivity Analysis show that the most sensitive parameter is Opex and the least sensitive parameter is interest rate.
{"title":"Techno-Economics Analysis Of RAN-Spectrum Sharing Scheme Use Sensitivity Analysis Method","authors":"Wisudantyo Wahyu Priambodo, H. Wijanto, N. Adriansyah","doi":"10.1109/ICCoSITE57641.2023.10127697","DOIUrl":"https://doi.org/10.1109/ICCoSITE57641.2023.10127697","url":null,"abstract":"The main problem faced by cellular operators in Indonesia is the cost of infrastructure investment which is very expensiv. Thus, a sharing infrastructure scheme is needed between cellular operators to reduce the Capex and Opex. In this thesis, the author will examine the feasibility of a 5G infrastructure core sharing (CN sharing) scheme for cellular operators in Indonesia using two aspects, namely technology and economy. From the technological aspect, the writer will analyze the capacity and coverage approach. The economic aspect is carried out to test the business feasibility of this RAN-frequency sharing scheme from the cellular operator's point of view. The research will be conducted in 2 types of areas, urban area (Banjarmasin City) and suburban area (Banjarbaru City) for 7 years ahead (2022-2028). Based on capacity and coverage planning, Banjarmasin city need 84 gNodeB and Banjarbaru city need 71 gNodeB. The results of the study show that the implementation of the RAN-spectrum sharing scheme can reduce Capex costs 50-67%. The most feasible scenario to be implemented from economical point of view is sharing 3 operators for economic parameter Net Present Value, Internal Rate of Return and Payback Period. Sensitivity Analysis show that the most sensitive parameter is Opex and the least sensitive parameter is interest rate.","PeriodicalId":256184,"journal":{"name":"2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115911872","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 : 2023-02-16DOI: 10.1109/ICCoSITE57641.2023.10127753
Daniel Anando Wangean, Sinjiru Setyawan, F. I. Maulana, Gusti Pangestu, C. Huda
Face recognition is a technology that is widely used in security systems. In a door security system, facial recognition can be used to open the door simply by recognizing the face of the door owner. This study aims to develop a real-time facial recognition system for smart locking doors using Haar Cascade and OpenCV LBPH Face Recognizer. The purpose of this project is creating security system to limit people who can access a room. The Haar Cascade method is used to detect faces in images, while the OpenCV LBPH Face Recognizer is used to recognize detected faces. This system was developed using the Python programming language and the OpenCV library. The test results show that this system can detect and recognize faces with an accuracy of 62.7% with our dataset and can be improved by adding more datasets and using deep learning algorithms to train the recognizer model. Thus, the developed real-time facial recognition system can be used as a smart locking door security solution with high accuracy.
{"title":"Development of Real-Time Face Recognition for Smart Door Lock Security System using Haar Cascade and OpenCV LBPH Face Recognizer","authors":"Daniel Anando Wangean, Sinjiru Setyawan, F. I. Maulana, Gusti Pangestu, C. Huda","doi":"10.1109/ICCoSITE57641.2023.10127753","DOIUrl":"https://doi.org/10.1109/ICCoSITE57641.2023.10127753","url":null,"abstract":"Face recognition is a technology that is widely used in security systems. In a door security system, facial recognition can be used to open the door simply by recognizing the face of the door owner. This study aims to develop a real-time facial recognition system for smart locking doors using Haar Cascade and OpenCV LBPH Face Recognizer. The purpose of this project is creating security system to limit people who can access a room. The Haar Cascade method is used to detect faces in images, while the OpenCV LBPH Face Recognizer is used to recognize detected faces. This system was developed using the Python programming language and the OpenCV library. The test results show that this system can detect and recognize faces with an accuracy of 62.7% with our dataset and can be improved by adding more datasets and using deep learning algorithms to train the recognizer model. Thus, the developed real-time facial recognition system can be used as a smart locking door security solution with high accuracy.","PeriodicalId":256184,"journal":{"name":"2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124174101","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 : 2023-02-16DOI: 10.1109/ICCoSITE57641.2023.10127679
Indri Tri Julianto, D. Kurniadi, Fakhrun Mahda Khoiriyyah
Non-Fungible Tokens (NFTs) experienced a peak of popularity in Indonesia through content created and sold by an account at OpenSea called Ghozali Everyday in early 2022. Ghozali reportedly earned ± Rp. 1.3 billion from the content he has created. This sparked the curiosity of the Indonesian people to imitate what Ghozali Everyday did in the hope of getting similar benefits. The market price of NFTs is the same as stock prices, which will fluctuate depending on the price of the cryptocurrency because these NFTs can generally be purchased with the cryptocurrency, namely Ethereum. This research was conducted to predict the price of NFTs using the Data Mining Prediction Algorithm. Five algorithms are compared to find the best algorithm: Deep Learning, Linear Regression, Neural Networks, Support Vector Machines, and Generalized Linear Model. The methodology used is Knowledge Discovery in Databases. The NFTs price dataset is taken from the page coinmarketcap.com from 16 November 2021 to 16 November 2022. The results show that the best Data Mining Prediction Algorithm is a Neural Network with a value of The lowest Root Mean Square Error (RMSE) compared to other algorithms, namely 83.617 +/- 18.853 (micro average: 85.590 +/- 0.000). After the Neural Network is used in the Dataset, the graph results show no significant difference between the Closing Price and the Predicted Price.
{"title":"Price Prediction of Non-Fungible Tokens (NFTs) using Data Mining Prediction Algorithm","authors":"Indri Tri Julianto, D. Kurniadi, Fakhrun Mahda Khoiriyyah","doi":"10.1109/ICCoSITE57641.2023.10127679","DOIUrl":"https://doi.org/10.1109/ICCoSITE57641.2023.10127679","url":null,"abstract":"Non-Fungible Tokens (NFTs) experienced a peak of popularity in Indonesia through content created and sold by an account at OpenSea called Ghozali Everyday in early 2022. Ghozali reportedly earned ± Rp. 1.3 billion from the content he has created. This sparked the curiosity of the Indonesian people to imitate what Ghozali Everyday did in the hope of getting similar benefits. The market price of NFTs is the same as stock prices, which will fluctuate depending on the price of the cryptocurrency because these NFTs can generally be purchased with the cryptocurrency, namely Ethereum. This research was conducted to predict the price of NFTs using the Data Mining Prediction Algorithm. Five algorithms are compared to find the best algorithm: Deep Learning, Linear Regression, Neural Networks, Support Vector Machines, and Generalized Linear Model. The methodology used is Knowledge Discovery in Databases. The NFTs price dataset is taken from the page coinmarketcap.com from 16 November 2021 to 16 November 2022. The results show that the best Data Mining Prediction Algorithm is a Neural Network with a value of The lowest Root Mean Square Error (RMSE) compared to other algorithms, namely 83.617 +/- 18.853 (micro average: 85.590 +/- 0.000). After the Neural Network is used in the Dataset, the graph results show no significant difference between the Closing Price and the Predicted Price.","PeriodicalId":256184,"journal":{"name":"2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE)","volume":"5 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116789870","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 : 2023-02-16DOI: 10.1109/ICCoSITE57641.2023.10127798
Devi Fajar Wati, F. Renaldi, I. Santikarama
Health agencies have actively implemented electronic medical records (EMR) on paper-based medical records. Currently, EMR is not very informative for extracting useful information or for tracking the patient disease. Hidden patterns that can be removed through data mining can help practitioners understand discreet relationships, such as inpatient categorization. Categorizing patients in determining groups in hospitals is very helpful for medical personnel in understanding work and actions to provide the right decisions and fast in taking action. However, there are several challenges in categorizing patients using data mining, one of which is selecting methods for the right cluster results according to the data used. Although there have been many studies that discuss the categorization of patients, no one has addressed the categorization of dynamic patients, especially in medical records. We consider this an important issue because, in medical records, there are similarities between one data and another, which causes one patient data to fall into two categories and affects health practitioner decision making. These challenges can be overcome using dynamic patient categorization. After implementation, we do an accuracy test. The test is done using Silhouette, Sum Squared Error, and Duns Fuzziness Coefficients. The result is that the accuracy is close to 85.2%. Identifying the types of diseases that become cluster labels is a good future work to do.
{"title":"Dynamic Patient Categorization Based on Medical Records Using Fuzzy C-Means Clustering Technique","authors":"Devi Fajar Wati, F. Renaldi, I. Santikarama","doi":"10.1109/ICCoSITE57641.2023.10127798","DOIUrl":"https://doi.org/10.1109/ICCoSITE57641.2023.10127798","url":null,"abstract":"Health agencies have actively implemented electronic medical records (EMR) on paper-based medical records. Currently, EMR is not very informative for extracting useful information or for tracking the patient disease. Hidden patterns that can be removed through data mining can help practitioners understand discreet relationships, such as inpatient categorization. Categorizing patients in determining groups in hospitals is very helpful for medical personnel in understanding work and actions to provide the right decisions and fast in taking action. However, there are several challenges in categorizing patients using data mining, one of which is selecting methods for the right cluster results according to the data used. Although there have been many studies that discuss the categorization of patients, no one has addressed the categorization of dynamic patients, especially in medical records. We consider this an important issue because, in medical records, there are similarities between one data and another, which causes one patient data to fall into two categories and affects health practitioner decision making. These challenges can be overcome using dynamic patient categorization. After implementation, we do an accuracy test. The test is done using Silhouette, Sum Squared Error, and Duns Fuzziness Coefficients. The result is that the accuracy is close to 85.2%. Identifying the types of diseases that become cluster labels is a good future work to do.","PeriodicalId":256184,"journal":{"name":"2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129811311","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 : 2023-02-16DOI: 10.1109/ICCoSITE57641.2023.10127780
Melisah Melisah, Muhathir Muhathir
Spices are biological resources that have long played a very important role in everyday life. Spices have characteristics, shapes, and colors that are almost similar and it is difficult to distinguish one spice from another. To assist in recognizing the characteristics of existing spices, the author tries to do research with the title. "Spices Classification Using the K-Nearest Neighbor (K-NN) Method and Using Histogram Oriented Gradient Feature Extraction. The method used in this study is the K-Nearest Neighbor and uses the Histogram Of Oriented Gradient feature extraction. In this study, the dataset used was 2250 image samples and divided into two categories, namely training data and testing data with a ratio of 80%: 20%. The results of this study indicate that the most optimal testing distance formula, namely the Manhattan distance formula, obtained an average accuracy of 87%, 87% precision, 87% recall, 87% f1 score, 87% Fbeta score, and 77% Jaccard score. These results indicate that feature extraction greatly influences the number of types in extracting information, the Histogram of Oriented Gradient works optimally when the number of types extracted is small and not optimal when used in a large number of classification types.
{"title":"A modification of the Distance Formula on the K-Nearest Neighbor Method is Examined in Order to Categorize Spices from Photo Using the Histogram of Oriented Gradient *","authors":"Melisah Melisah, Muhathir Muhathir","doi":"10.1109/ICCoSITE57641.2023.10127780","DOIUrl":"https://doi.org/10.1109/ICCoSITE57641.2023.10127780","url":null,"abstract":"Spices are biological resources that have long played a very important role in everyday life. Spices have characteristics, shapes, and colors that are almost similar and it is difficult to distinguish one spice from another. To assist in recognizing the characteristics of existing spices, the author tries to do research with the title. \"Spices Classification Using the K-Nearest Neighbor (K-NN) Method and Using Histogram Oriented Gradient Feature Extraction. The method used in this study is the K-Nearest Neighbor and uses the Histogram Of Oriented Gradient feature extraction. In this study, the dataset used was 2250 image samples and divided into two categories, namely training data and testing data with a ratio of 80%: 20%. The results of this study indicate that the most optimal testing distance formula, namely the Manhattan distance formula, obtained an average accuracy of 87%, 87% precision, 87% recall, 87% f1 score, 87% Fbeta score, and 77% Jaccard score. These results indicate that feature extraction greatly influences the number of types in extracting information, the Histogram of Oriented Gradient works optimally when the number of types extracted is small and not optimal when used in a large number of classification types.","PeriodicalId":256184,"journal":{"name":"2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE)","volume":"17 10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127220272","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 : 2023-02-16DOI: 10.1109/ICCoSITE57641.2023.10127818
Febriyani Baharu, Faizal Arya Samman, Y. Yusran
The use of brushless DC motors will increase with the transition of conventional vehicle motors to electric vehicles (Electric Vehicles). The purpose of this study is to produce control that can maintain and increase the stability of motor rotation at changing or non-linear loads. It then performs testing of the created model. The control method used is PID. The control that is suitable for use in cases like this is the PID (Proportional Integral Derivative) control system. The best Kp, Ki, and Kd values obtained based on trial and error, and the values obtained are Kp = 1.1, Ki = 0.2, and Kd = 0.8. The response to distractions gets better and the response to speed variations gets better. In addition, the speed of the simulation results can follow the change in the speed reference with a slight overshoot in each transition of the speed value. The resulting system responds with a settling time value of 0.0035 s and a large overshoot with a value of 1.9%.
{"title":"Performance Evaluation Brushless DC Motor System With Variable Loads","authors":"Febriyani Baharu, Faizal Arya Samman, Y. Yusran","doi":"10.1109/ICCoSITE57641.2023.10127818","DOIUrl":"https://doi.org/10.1109/ICCoSITE57641.2023.10127818","url":null,"abstract":"The use of brushless DC motors will increase with the transition of conventional vehicle motors to electric vehicles (Electric Vehicles). The purpose of this study is to produce control that can maintain and increase the stability of motor rotation at changing or non-linear loads. It then performs testing of the created model. The control method used is PID. The control that is suitable for use in cases like this is the PID (Proportional Integral Derivative) control system. The best Kp, Ki, and Kd values obtained based on trial and error, and the values obtained are Kp = 1.1, Ki = 0.2, and Kd = 0.8. The response to distractions gets better and the response to speed variations gets better. In addition, the speed of the simulation results can follow the change in the speed reference with a slight overshoot in each transition of the speed value. The resulting system responds with a settling time value of 0.0035 s and a large overshoot with a value of 1.9%.","PeriodicalId":256184,"journal":{"name":"2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130609402","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 : 2023-02-16DOI: 10.1109/ICCoSITE57641.2023.10127852
Fitri Nuraeni, D. Kurniadi, Gisna Fauzian Dermawan
The limited quota of recipients of the Kartu Indonesia Pintar Kuliah (KIP-K) causes the host universities to select applicants to get students who are eligible to receive KIP-K based on academic achievement, non-academic achievements, and family economic conditions. However, after the lectures started, some students who received KIP-K lacked discipline in undergoing lecture procedures and experienced a decrease in their achievement index (IP). Therefore, it is necessary to explore knowledge about the characteristics of KIP-K recipient students by conducting clustering modeling. So, in this study, clustering modeling was carried out on student data receiving KIP-K at a university by applying the Cross-Industry Standard Process for Data Mining (CRIPS-DM) method and the k-means clustering algorithm. This study chooses a clustering model with a value of k=2, which has the smallest Davies Bouldine index (DBI) value of 0.35. This clustering resulted in 2 clusters where student characteristics showed significant differences in the attributes of the distance from home to the campus location and relatively minor fluctuations in IP from the first semester to the fourth semester. From mapping the characteristics of KIP-K recipient students, knowledge can be used as material for higher education decisions in selecting KIP-K registrants to minimize the future academic problems of KIP-K recipient students.
Kartu Indonesia Pintar Kuliah (KIP-K)的有限名额导致主办大学根据学术成就、非学术成就和家庭经济条件选择有资格获得KIP-K的申请人。但是，接受KIP-K的部分学生在讲课过程中缺乏纪律，成绩指数(IP)有所下降。因此，有必要通过聚类建模来探索KIP-K受援生的特征知识。因此，本研究采用跨行业数据挖掘标准流程(crics - dm)方法和k-means聚类算法，对某高校接受KIP-K的学生数据进行聚类建模。本研究选择k=2的聚类模型，其Davies Bouldine指数(DBI)值最小，为0.35。通过聚类可以得到2个聚类，在第一学期到第四学期，学生特征在离家到校园的距离属性上存在显著差异，IP波动相对较小。通过绘制KIP-K接收学生的特征，知识可以作为选择KIP-K注册者的高等教育决策的材料，以尽量减少KIP-K接收学生未来的学业问题。
{"title":"Implementation of the K-Means Algorithm for Clustering the Characteristics of Students Receiving Kartu Indonesia Pintar Kuliah (KIP-K)","authors":"Fitri Nuraeni, D. Kurniadi, Gisna Fauzian Dermawan","doi":"10.1109/ICCoSITE57641.2023.10127852","DOIUrl":"https://doi.org/10.1109/ICCoSITE57641.2023.10127852","url":null,"abstract":"The limited quota of recipients of the Kartu Indonesia Pintar Kuliah (KIP-K) causes the host universities to select applicants to get students who are eligible to receive KIP-K based on academic achievement, non-academic achievements, and family economic conditions. However, after the lectures started, some students who received KIP-K lacked discipline in undergoing lecture procedures and experienced a decrease in their achievement index (IP). Therefore, it is necessary to explore knowledge about the characteristics of KIP-K recipient students by conducting clustering modeling. So, in this study, clustering modeling was carried out on student data receiving KIP-K at a university by applying the Cross-Industry Standard Process for Data Mining (CRIPS-DM) method and the k-means clustering algorithm. This study chooses a clustering model with a value of k=2, which has the smallest Davies Bouldine index (DBI) value of 0.35. This clustering resulted in 2 clusters where student characteristics showed significant differences in the attributes of the distance from home to the campus location and relatively minor fluctuations in IP from the first semester to the fourth semester. From mapping the characteristics of KIP-K recipient students, knowledge can be used as material for higher education decisions in selecting KIP-K registrants to minimize the future academic problems of KIP-K recipient students.","PeriodicalId":256184,"journal":{"name":"2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132893003","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 : 2023-02-16DOI: 10.1109/ICCoSITE57641.2023.10127687
Ahmed F. Ashour, M. Fouda
In the future, communication networks such as fifth-generation new radio (5G NR) and sixth-generation (6G) will require large data rates and capacities. As a result, mmWave and terahertz (THz) bands are being employed to meet these demands. Unfortunately, these high-frequency bands are susceptible to high path loss, necessitating the deployment of small cells. This, in turn, calls for the installation of a massive number of base stations to cover the whole area. The sheer number of cells and users in such a setup can lead to interruptions in calls when users switch cells, a process known as handover (HO). This has a negative effect on the quality of service (QoS) and the quality of experience (QoE). Therefore, this survey focuses on exploring and comparing artificial intelligence (AI)-based intelligent HO solutions that can optimize HO in 5G NR and 6G networks.
{"title":"AI-Based Approaches for Handover Optimization in 5G New Radio and 6G Wireless Networks","authors":"Ahmed F. Ashour, M. Fouda","doi":"10.1109/ICCoSITE57641.2023.10127687","DOIUrl":"https://doi.org/10.1109/ICCoSITE57641.2023.10127687","url":null,"abstract":"In the future, communication networks such as fifth-generation new radio (5G NR) and sixth-generation (6G) will require large data rates and capacities. As a result, mmWave and terahertz (THz) bands are being employed to meet these demands. Unfortunately, these high-frequency bands are susceptible to high path loss, necessitating the deployment of small cells. This, in turn, calls for the installation of a massive number of base stations to cover the whole area. The sheer number of cells and users in such a setup can lead to interruptions in calls when users switch cells, a process known as handover (HO). This has a negative effect on the quality of service (QoS) and the quality of experience (QoE). Therefore, this survey focuses on exploring and comparing artificial intelligence (AI)-based intelligent HO solutions that can optimize HO in 5G NR and 6G networks.","PeriodicalId":256184,"journal":{"name":"2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127918542","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 : 2023-02-16DOI: 10.1109/iccosite57641.2023.10127801
Felix Indra Kumiadi, Ajeng Wulandari, S. Arifin
high dimensional data provide a major problem to supervised learning. In identifying high dimensional data, the learning models usually exhibit overfitting and become less understandable. One way to find the ideal features on high-dimensional data implemented feature selection on dataset Feature selection is one of the crucial aspects on data preprocessing step. Several algorithms for feature selection were proposed over the decades such as wrapper method, filter, and embedded method. In this research, we implemented wrapper method with Grey Wolf Optimization. We implemented Grey Wolf Optimization on wrapper method because the algorithm is efficient, simple and had lower computational time. We are also compared Grey Wolf Optimization to other meta-heuristic algorithms such as Particle Swarm Optimization and Genetic Algorithms. The result showed the GWO provide better computational time with the average time from four different dataset was 6.1125s. The accuracy result showed the GWO performed better on Ionosphere dataset.
{"title":"Feature Selection using Grey Wolf Optimization Algorithm on Light Gradient Boosting Machine","authors":"Felix Indra Kumiadi, Ajeng Wulandari, S. Arifin","doi":"10.1109/iccosite57641.2023.10127801","DOIUrl":"https://doi.org/10.1109/iccosite57641.2023.10127801","url":null,"abstract":"high dimensional data provide a major problem to supervised learning. In identifying high dimensional data, the learning models usually exhibit overfitting and become less understandable. One way to find the ideal features on high-dimensional data implemented feature selection on dataset Feature selection is one of the crucial aspects on data preprocessing step. Several algorithms for feature selection were proposed over the decades such as wrapper method, filter, and embedded method. In this research, we implemented wrapper method with Grey Wolf Optimization. We implemented Grey Wolf Optimization on wrapper method because the algorithm is efficient, simple and had lower computational time. We are also compared Grey Wolf Optimization to other meta-heuristic algorithms such as Particle Swarm Optimization and Genetic Algorithms. The result showed the GWO provide better computational time with the average time from four different dataset was 6.1125s. The accuracy result showed the GWO performed better on Ionosphere dataset.","PeriodicalId":256184,"journal":{"name":"2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE)","volume":"30 11","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120922062","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 : 2023-02-16DOI: 10.1109/ICCoSITE57641.2023.10127787
Ira Safira, Muhathir Muhathir
Spices are biological natural resources that have long been used in human life. Spices are highly valued in the European market due to their flavor, aroma, and delicacy. Spices come in a variety of shapes and sizes, each with its own set of characteristics. Because there are so many different types of spices, many people are unfamiliar with their names and forms. As a result, this study discusses how to classify spices using the Nave Bayes method and the Speeded-up Robust Features feature extraction method. According to the results of the tests conducted in this study, experiments with 5 types of spices produced better results with an accuracy of 77.3%, precision of 77.5%, recall of 77.5%, f1 score of 76.4%, f beta score of 76.8%, and Jaccard score of 63.3%, whereas experiments with 10 types of spices and 15 types of spices produced less than the maximum. The findings revealed that the number of spice species used in extracting information is greatly influenced by feature extraction. Speeded-up Robust features that have been accelerated Feature Extraction works best when the number of spices extracted is small, and it performs poorly when used in a large number of classification types.
{"title":"Analysis of Different Naïve Bayes Methods for Categorizing Spices Through Photo using the Speeded-up Robust Feature","authors":"Ira Safira, Muhathir Muhathir","doi":"10.1109/ICCoSITE57641.2023.10127787","DOIUrl":"https://doi.org/10.1109/ICCoSITE57641.2023.10127787","url":null,"abstract":"Spices are biological natural resources that have long been used in human life. Spices are highly valued in the European market due to their flavor, aroma, and delicacy. Spices come in a variety of shapes and sizes, each with its own set of characteristics. Because there are so many different types of spices, many people are unfamiliar with their names and forms. As a result, this study discusses how to classify spices using the Nave Bayes method and the Speeded-up Robust Features feature extraction method. According to the results of the tests conducted in this study, experiments with 5 types of spices produced better results with an accuracy of 77.3%, precision of 77.5%, recall of 77.5%, f1 score of 76.4%, f beta score of 76.8%, and Jaccard score of 63.3%, whereas experiments with 10 types of spices and 15 types of spices produced less than the maximum. The findings revealed that the number of spice species used in extracting information is greatly influenced by feature extraction. Speeded-up Robust features that have been accelerated Feature Extraction works best when the number of spices extracted is small, and it performs poorly when used in a large number of classification types.","PeriodicalId":256184,"journal":{"name":"2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE)","volume":"92 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120976551","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：