Pub Date : 2024-07-19DOI: 10.33395/sinkron.v8i3.13809
Alwidahyani Sipahutar, Ibnu Rasyid Munthe, Angga Putra Juledi
The development of online business in Indonesia is now very rapid, with the process being done by ordering goods through resellers or distributors using one of the social media. Item purchases are made based on product information, prices, discounts and inventory quantities using a decision model. In the sales process, Toko Serbu Aek Batu usually releases several different items to be offered to the market at different prices, but not all items are in high demand. Multiple linear regression is an analysis that describes the relationship between dependent variables and factors that affect more than one independent variable. The purpose of this study is to analyze sales trends using a linear regression method using rapidminer. The results of this study are prediction calculations using manual calculations with rapidminer the same results, predicting the price desired by buyers using a linear regression algorithm with the original price is not much different and rapidminer is very accurate to be used in predicting sales trends at the price desired by customers, so that sellers can pay more attention to things that are very influential in the sales process.
目前，印度尼西亚的在线业务发展非常迅速，其流程是通过转售商或分销商利用其中一种社交媒体订购商品。根据产品信息、价格、折扣和库存数量，利用决策模型进行商品采购。在销售过程中，Toko Serbu Aek Batu 通常会发布几种不同的商品，以不同的价格提供给市场，但并不是所有商品都很抢手。多元线性回归是一种描述因变量与影响一个以上自变量的因素之间关系的分析。本研究的目的是利用 rapidminer 的线性回归方法分析销售趋势。本研究的结果是使用人工计算的预测计算结果与 rapidminer 的结果相同，使用线性回归算法预测买家期望的价格与原始价格相差不大，而且 rapidminer 非常准确，可用于预测客户期望价格的销售趋势，这样卖家就可以更加关注在销售过程中非常有影响力的事情。
{"title":"Sales Trend Analysis With Machine Learning Linear Regression Algorithm Method","authors":"Alwidahyani Sipahutar, Ibnu Rasyid Munthe, Angga Putra Juledi","doi":"10.33395/sinkron.v8i3.13809","DOIUrl":"https://doi.org/10.33395/sinkron.v8i3.13809","url":null,"abstract":"The development of online business in Indonesia is now very rapid, with the process being done by ordering goods through resellers or distributors using one of the social media. Item purchases are made based on product information, prices, discounts and inventory quantities using a decision model. In the sales process, Toko Serbu Aek Batu usually releases several different items to be offered to the market at different prices, but not all items are in high demand. Multiple linear regression is an analysis that describes the relationship between dependent variables and factors that affect more than one independent variable. The purpose of this study is to analyze sales trends using a linear regression method using rapidminer. The results of this study are prediction calculations using manual calculations with rapidminer the same results, predicting the price desired by buyers using a linear regression algorithm with the original price is not much different and rapidminer is very accurate to be used in predicting sales trends at the price desired by customers, so that sellers can pay more attention to things that are very influential in the sales process.","PeriodicalId":34046,"journal":{"name":"Sinkron","volume":" 583","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141823652","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}
A trading business is a business that operates in the sales sector with the aim of obtaining maximum profits through sales activities. To be able to sell efficiently, a prediction system is needed, so that there is no excess or shortage of inventory and the sales process can run smoothly. Human limitations in solving prediction problems without using tools that apply prediction methods are one of the obstacles in finding the right prediction value. Therefore, we need a prediction system that can help find accurate and fast values. So the problem formulation is how to design and build a sales prediction system using exponential smoothing and linear regression methods, then compare the two and find out which method is the best, both of which use periodic data prediction models. The data collection method used is secondary data from previous research and journals, as well as combining library study methods, namely information obtained from books, references and scientific works related to predictions. The tool used to build applications is MS-Visual Studio 2010 and WEB based system
贸易企业是在销售领域开展业务的企业，目的是通过销售活动获取最大利润。为了能够有效地进行销售，需要有一个预测系统，这样才不会出现库存过剩或短缺的情况，销售过程才能顺利进行。在不使用应用预测方法的工具的情况下，人类在解决预测问题上的局限性是找到正确预测值的障碍之一。因此，我们需要一个预测系统，帮助我们准确、快速地找到预测值。因此，问题的提出是如何使用指数平滑法和线性回归法设计和建立一个销售预测系统，然后比较这两种方法，找出哪种方法最好，这两种方法都使用周期性数据预测模型。使用的数据收集方法是从以前的研究和期刊中获取二手数据，以及结合图书馆学习方法，即从与预测相关的书籍、参考文献和科学著作中获取信息。用于构建应用程序的工具是 MS-Visual Studio 2010 和基于 WEB 的系统
{"title":"Comparison Of Exponesial Smoothing With Linear Regression Predicting Amount Of Goods Sales","authors":"Erwin Panggabean, Anita Sindar Ros Maryana Sinaga, J. Sagala, Alya Sophia Ramadhan, Alpon Josua","doi":"10.33395/sinkron.v8i3.13811","DOIUrl":"https://doi.org/10.33395/sinkron.v8i3.13811","url":null,"abstract":"A trading business is a business that operates in the sales sector with the aim of obtaining maximum profits through sales activities. To be able to sell efficiently, a prediction system is needed, so that there is no excess or shortage of inventory and the sales process can run smoothly. Human limitations in solving prediction problems without using tools that apply prediction methods are one of the obstacles in finding the right prediction value. Therefore, we need a prediction system that can help find accurate and fast values. So the problem formulation is how to design and build a sales prediction system using exponential smoothing and linear regression methods, then compare the two and find out which method is the best, both of which use periodic data prediction models. The data collection method used is secondary data from previous research and journals, as well as combining library study methods, namely information obtained from books, references and scientific works related to predictions. The tool used to build applications is MS-Visual Studio 2010 and WEB based system","PeriodicalId":34046,"journal":{"name":"Sinkron","volume":" 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141827431","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}
Breast cancer is a serious medical condition and a leading cause of death among women. Early and accurate diagnosis is crucial for improving patient outcomes. This study explores the use of Convolutional Neural Networks (CNNs) with Transfer Learning using DenseNet121 and ResNet50 models to enhance breast cancer classification via mammography. Transfer Learning enables CNN models to leverage knowledge learned from larger datasets such as ImageNet to improve performance on specific breast cancer datasets. The dataset comprised medical images with three breast variations: benign, malignant, and normal, totaling 531 data points. Data was split with a 70% training and 30% validation ratio. Two CNN models, AlexNet and ResNet50, were evaluated to compare their performance in classifying these breast cancer types. The experimental results show that AlexNet achieved a training accuracy of 98.01%, while ResNet50 achieved 64.07%. AlexNet demonstrated superior performance in identifying complex patterns in mammography images, resulting in more accurate classification of different breast cancer types. These findings highlight the potential of deep learning applications to support more precise and effective medical diagnostics for breast cancer. This research contributes significantly to the development of AI technologies in healthcare aimed at improving early detection of breast cancer. The implications of this study could expand our understanding of Transfer Learning applications in medical contexts, driving further advancements in this field to enhance patient care and prognosis
{"title":"Classification of Breast Cancer with Transfer Learning on Convolutional Neural Network Models","authors":"Bayu Angga Wijaya, Mesrawati Hulu, Resel Resel, Nestina Halawa, Angki Angkota Tarigan","doi":"10.33395/sinkron.v8i3.13792","DOIUrl":"https://doi.org/10.33395/sinkron.v8i3.13792","url":null,"abstract":"Breast cancer is a serious medical condition and a leading cause of death among women. Early and accurate diagnosis is crucial for improving patient outcomes. This study explores the use of Convolutional Neural Networks (CNNs) with Transfer Learning using DenseNet121 and ResNet50 models to enhance breast cancer classification via mammography. Transfer Learning enables CNN models to leverage knowledge learned from larger datasets such as ImageNet to improve performance on specific breast cancer datasets. The dataset comprised medical images with three breast variations: benign, malignant, and normal, totaling 531 data points. Data was split with a 70% training and 30% validation ratio. Two CNN models, AlexNet and ResNet50, were evaluated to compare their performance in classifying these breast cancer types. The experimental results show that AlexNet achieved a training accuracy of 98.01%, while ResNet50 achieved 64.07%. AlexNet demonstrated superior performance in identifying complex patterns in mammography images, resulting in more accurate classification of different breast cancer types. These findings highlight the potential of deep learning applications to support more precise and effective medical diagnostics for breast cancer. This research contributes significantly to the development of AI technologies in healthcare aimed at improving early detection of breast cancer. The implications of this study could expand our understanding of Transfer Learning applications in medical contexts, driving further advancements in this field to enhance patient care and prognosis","PeriodicalId":34046,"journal":{"name":"Sinkron","volume":" 13","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141825923","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}
Every school needs teachers who have good competence to educate students to become outstanding students. Getting teachers who have good competence is certainly not an easy thing, it must be a very strict selection process. This research aims to help determine teachers who are eligible to be accepted at IT Al Munadi Private Elementary School Medan by using the TOPSIS method. The selection consists of 5 criteria, namely education, microteaching, teaching experience, tahsin and memorization of the Koran. The TOPSIS method is widely used for Multi Attribute Decision Making (MADM) decision making. The TOPSIS method is used as a ranking to see teachers who have competencies that are worthy of acceptance. Based on the results of the TOPSIS calculation where there are 6 alternatives that have been determined, the results obtained are G6 in the first place with a preference value of 2.82, 2nd place with a preference value of 2.48, 3rd place with a preference value of 2.09, 4th place with a preference value of 1.72, 5th place with a preference value of 1.67, while the 6th place is G1 with a preference value of 1.00. It is hoped that the decision support system using TOPSIS can help schools in determining teachers who have good competence so as to produce outstanding students.
{"title":"Decision Support System Using the TOPSIS Method in New Teacher Selection","authors":"Dedek Indra Gunawan Hts, Efani Desi, Siti Aliyah, Fitri Pranita Nasution, Ulfah Indriani, Firman Edi","doi":"10.33395/sinkron.v8i3.13751","DOIUrl":"https://doi.org/10.33395/sinkron.v8i3.13751","url":null,"abstract":"Every school needs teachers who have good competence to educate students to become outstanding students. Getting teachers who have good competence is certainly not an easy thing, it must be a very strict selection process. This research aims to help determine teachers who are eligible to be accepted at IT Al Munadi Private Elementary School Medan by using the TOPSIS method. The selection consists of 5 criteria, namely education, microteaching, teaching experience, tahsin and memorization of the Koran. The TOPSIS method is widely used for Multi Attribute Decision Making (MADM) decision making. The TOPSIS method is used as a ranking to see teachers who have competencies that are worthy of acceptance. Based on the results of the TOPSIS calculation where there are 6 alternatives that have been determined, the results obtained are G6 in the first place with a preference value of 2.82, 2nd place with a preference value of 2.48, 3rd place with a preference value of 2.09, 4th place with a preference value of 1.72, 5th place with a preference value of 1.67, while the 6th place is G1 with a preference value of 1.00. It is hoped that the decision support system using TOPSIS can help schools in determining teachers who have good competence so as to produce outstanding students.","PeriodicalId":34046,"journal":{"name":"Sinkron","volume":" 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141831597","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 : 2024-07-15DOI: 10.33395/sinkron.v8i3.13798
Muhammad Ariq Muthi, Putu Harry Gunawan
Traffic congestion has become one of the main problems that occur in big cities around the world. Traffic congestion also has a negative impact if not handled seriously. Traffic congestion occurs because there is a buildup of vehicle volume that exceeds the capacity of the road. The efficiency and quality of living in cities can be negatively impacted by traffic congestion, which can also result in higher fuel consumption, pollution, and delays. There needs to be a method that can overcome and identify this. Therefore, by classifying sounds, this research aims to reduce traffic congestion. The author uses deep learning with the Convolutional Neural Network (CNN) method as the algorithm model. The model employs Mel-Frequency Cepstral Coefficients (MFCC) as the primary feature extraction technique to capture the essential characteristics of the audio signals. This research is expected to be able to classify traffic congestion sounds with good accuracy, so it can be used as a solution to overcome traffic congestion. Experiments were conducted using a training dataset, and for testing, the road sound dataset has been collected at traffic light intersections. To evaluate the proposed method, the implementation showed promising results, achieving an accuracy of 97.62% on the training data and 88.19% on the test data in classifying traffic congestion sounds.
{"title":"Deep Learning Approach for Traffic Congestion Sound Classification using Circular Neural Networks","authors":"Muhammad Ariq Muthi, Putu Harry Gunawan","doi":"10.33395/sinkron.v8i3.13798","DOIUrl":"https://doi.org/10.33395/sinkron.v8i3.13798","url":null,"abstract":"Traffic congestion has become one of the main problems that occur in big cities around the world. Traffic congestion also has a negative impact if not handled seriously. Traffic congestion occurs because there is a buildup of vehicle volume that exceeds the capacity of the road. The efficiency and quality of living in cities can be negatively impacted by traffic congestion, which can also result in higher fuel consumption, pollution, and delays. There needs to be a method that can overcome and identify this. Therefore, by classifying sounds, this research aims to reduce traffic congestion. The author uses deep learning with the Convolutional Neural Network (CNN) method as the algorithm model. The model employs Mel-Frequency Cepstral Coefficients (MFCC) as the primary feature extraction technique to capture the essential characteristics of the audio signals. This research is expected to be able to classify traffic congestion sounds with good accuracy, so it can be used as a solution to overcome traffic congestion. Experiments were conducted using a training dataset, and for testing, the road sound dataset has been collected at traffic light intersections. To evaluate the proposed method, the implementation showed promising results, achieving an accuracy of 97.62% on the training data and 88.19% on the test data in classifying traffic congestion sounds.","PeriodicalId":34046,"journal":{"name":"Sinkron","volume":" 17","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141833467","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}
This study developed a Convolutional Neural Network (CNN) model as one of artificial intelligence method to detect trucks experiencing over-dimension and over-loading (ODOL). The primary goal of this research is to enhance the efficiency of truck monitoring, reduce road infrastructure damage, and support the sustainability of transportation using artificial intelligence approaches. The model was trained using a dataset consisting of ODOL and non-ODOL truck images, and successfully achieved a testing accuracy of 94.23%. The confusion matrix analysis demonstrated the model's ability to classify trucks with high precision. Additional testing on truck images not included in the training or testing dataset showed the model's potential for good generalization.
{"title":"A CNN Model for ODOL Truck Detection","authors":"Nurul Afifah Arifuddin, Kharisma Wiati Gusti, Rifka Dwi Amalia","doi":"10.33395/sinkron.v8i3.13780","DOIUrl":"https://doi.org/10.33395/sinkron.v8i3.13780","url":null,"abstract":"This study developed a Convolutional Neural Network (CNN) model as one of artificial intelligence method to detect trucks experiencing over-dimension and over-loading (ODOL). The primary goal of this research is to enhance the efficiency of truck monitoring, reduce road infrastructure damage, and support the sustainability of transportation using artificial intelligence approaches. The model was trained using a dataset consisting of ODOL and non-ODOL truck images, and successfully achieved a testing accuracy of 94.23%. The confusion matrix analysis demonstrated the model's ability to classify trucks with high precision. Additional testing on truck images not included in the training or testing dataset showed the model's potential for good generalization.","PeriodicalId":34046,"journal":{"name":"Sinkron","volume":" 10","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141833278","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 : 2024-07-10DOI: 10.33395/sinkron.v8i3.13729
Yudhistira Yudhistira, A. S. Talita
Disruptions to banking services can negatively affect customer trust and happiness, thus affecting the bank's reputation in the eyes of the public. Analysis of sentiment expressed on social media is very important because it can provide a direct picture of individual perceptions and responses in real time. This research aims to analyze public sentiment towards disruptions in Bank Syariah Indonesia (BSI) services through social media using the Naive Bayes algorithm. Through this analysis, the research seeks to understand the pattern of public responses and perceptions of BSI disruptions and evaluate the performance of the Naive Bayes algorithm in classifying sentiment on related tweet data. The data used came from specific social media platforms, where sentiment analysis was conducted by categorizing the data into positive, negative, and neutral categories. The research findings show that the sentiment analysis of the community towards BSI service disruptions through X social media platforms shows a diverse pattern of responses and perceptions. This finding recorded 525 data points with negative sentiment, 325 data points with neutral sentiment, and 141 data points with positive sentiment. The research also compared the performance of the Naive Bayes algorithm with the Google Cloud Natural Language API, which showed an accuracy rate of 81.03%. This research provides valuable insights for Bank Syariah Indonesia in understanding public perception of BSI services on social media.
{"title":"Analyzing Public Sentiment Towards BSI Service Disruptions Through X: Naïve Bayes Algorithm","authors":"Yudhistira Yudhistira, A. S. Talita","doi":"10.33395/sinkron.v8i3.13729","DOIUrl":"https://doi.org/10.33395/sinkron.v8i3.13729","url":null,"abstract":"Disruptions to banking services can negatively affect customer trust and happiness, thus affecting the bank's reputation in the eyes of the public. Analysis of sentiment expressed on social media is very important because it can provide a direct picture of individual perceptions and responses in real time. This research aims to analyze public sentiment towards disruptions in Bank Syariah Indonesia (BSI) services through social media using the Naive Bayes algorithm. Through this analysis, the research seeks to understand the pattern of public responses and perceptions of BSI disruptions and evaluate the performance of the Naive Bayes algorithm in classifying sentiment on related tweet data. The data used came from specific social media platforms, where sentiment analysis was conducted by categorizing the data into positive, negative, and neutral categories. The research findings show that the sentiment analysis of the community towards BSI service disruptions through X social media platforms shows a diverse pattern of responses and perceptions. This finding recorded 525 data points with negative sentiment, 325 data points with neutral sentiment, and 141 data points with positive sentiment. The research also compared the performance of the Naive Bayes algorithm with the Google Cloud Natural Language API, which showed an accuracy rate of 81.03%. This research provides valuable insights for Bank Syariah Indonesia in understanding public perception of BSI services on social media.","PeriodicalId":34046,"journal":{"name":"Sinkron","volume":"56 S269","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141835290","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 : 2024-07-10DOI: 10.33395/sinkron.v8i3.13707
Novi Hendri Adi, Arina Luthfini Lubis, Ali Basriadi, Ika Parma Dewi, Yera Wahda Wahdi
In computer network learning, there is still little use of media which has an impact on students' understanding of device material and computer network topology. Augmented Reality (AR) based learning media can answer these problems by providing dynamic visualization and interactive simulations. The research objective is that AR applications can be used to help visualize abstract concepts for understanding and structure of an object model. The development method used is MDLC (Multimedia Development Life Cycle) which consists of six stages, namely concept, design, material collecting, assembly, testing, and distribution. The results of the AR application research show that the value of the learning media application in terms of material is declared valid at 0.85 and in terms of design it is declared valid at 0.86. The AR application was also stated to be very practical, this can be seen from the responses of lecturers and students with the practicality of the learning media application being 87% as seen from ease, motivation, attractiveness, and usefulness. From the results of this research, the AR learning media application is very practical to apply to students, especially in computer networking courses.
{"title":"Augmented Reality Learning Media Application In Computer Networking Courses","authors":"Novi Hendri Adi, Arina Luthfini Lubis, Ali Basriadi, Ika Parma Dewi, Yera Wahda Wahdi","doi":"10.33395/sinkron.v8i3.13707","DOIUrl":"https://doi.org/10.33395/sinkron.v8i3.13707","url":null,"abstract":"In computer network learning, there is still little use of media which has an impact on students' understanding of device material and computer network topology. Augmented Reality (AR) based learning media can answer these problems by providing dynamic visualization and interactive simulations. The research objective is that AR applications can be used to help visualize abstract concepts for understanding and structure of an object model. The development method used is MDLC (Multimedia Development Life Cycle) which consists of six stages, namely concept, design, material collecting, assembly, testing, and distribution. The results of the AR application research show that the value of the learning media application in terms of material is declared valid at 0.85 and in terms of design it is declared valid at 0.86. The AR application was also stated to be very practical, this can be seen from the responses of lecturers and students with the practicality of the learning media application being 87% as seen from ease, motivation, attractiveness, and usefulness. From the results of this research, the AR learning media application is very practical to apply to students, especially in computer networking courses. \u0000 ","PeriodicalId":34046,"journal":{"name":"Sinkron","volume":"21 s39","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141835458","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 : 2024-07-10DOI: 10.33395/sinkron.v8i3.13750
Fajar Riskiyono, Deni Mahdiana
University also has responsibility for the period of study taken by students in accordance with the level of education taken. The prediction of student study duration is designed to support the study program in guiding students to graduate on time. In this problem, data mining techniques can be applied to make predictions, namely by using the Random Forest classification method. The stages used in this study are data collecting, namely collecting student data, the data selection stage of 300 students with 5 (five) input data attributes including personal data (gender, age, marital status, job status) and academic data (grade) and 1 (one) attribute as an output containing choices about on time and late. The next stage is preprocessing with the aim of eliminating duplication, noise, and missing values, the stage of data transformation by normalizing age attributes (young and old), grade (large and small). Then the data split stage 3 times, namely 50/50, 40/60, and 30/60, the modeling stage with random forest, and finally, the evaluation stage by analyzing the confusion matrix consisting of accuracy, precision, and recall. The results of the study show that the proposed model can do well with predictions, that is, with the same results for all three data splits. The test value is 100% accuracy, 100% recall, and 100% precision. With this value, the success rate for predicting the timeliness of student graduation will be more accurate
{"title":"Implementation of Random Forest Algorithm for Graduation Prediction","authors":"Fajar Riskiyono, Deni Mahdiana","doi":"10.33395/sinkron.v8i3.13750","DOIUrl":"https://doi.org/10.33395/sinkron.v8i3.13750","url":null,"abstract":"University also has responsibility for the period of study taken by students in accordance with the level of education taken. The prediction of student study duration is designed to support the study program in guiding students to graduate on time. In this problem, data mining techniques can be applied to make predictions, namely by using the Random Forest classification method. The stages used in this study are data collecting, namely collecting student data, the data selection stage of 300 students with 5 (five) input data attributes including personal data (gender, age, marital status, job status) and academic data (grade) and 1 (one) attribute as an output containing choices about on time and late. The next stage is preprocessing with the aim of eliminating duplication, noise, and missing values, the stage of data transformation by normalizing age attributes (young and old), grade (large and small). Then the data split stage 3 times, namely 50/50, 40/60, and 30/60, the modeling stage with random forest, and finally, the evaluation stage by analyzing the confusion matrix consisting of accuracy, precision, and recall. The results of the study show that the proposed model can do well with predictions, that is, with the same results for all three data splits. The test value is 100% accuracy, 100% recall, and 100% precision. With this value, the success rate for predicting the timeliness of student graduation will be more accurate","PeriodicalId":34046,"journal":{"name":"Sinkron","volume":"91 12","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141835558","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 : 2024-07-08DOI: 10.33395/sinkron.v8i3.13815
Hazrul Anshari Ulvi, Muhammad Ikhsan
International relations affect the economic growth of each country, which can affect the economic growth of each country. As a result, global economic growth is necessary, which means that the global economy has a greater capacity to produce goods and services. Exports and imports are very important to drive economic growth. but if exports and imports are not balanced, it will have a bad impact if the value of imports is greater than exports, export prices abroad will definitely fall. An analysis comparing export and import categories is needed to determine which goods are most imported and exported in Indonesia in 2021-2023. This study uses a quantitative methodology and machine learning methods, namely k-means and k-medoids algorithms. These two methods will be compared to determine which is the most effective for export and import data of goods in Indonesia in 2021-2023. The results of the study were obtained by K-Means more effectively in handling data on the grouping of exports and imports of goods in Indonesia in 2021-2023. The dataset shows the results of the evaluation of K-Means using DBI of 0.59, while the results of the evaluation using K-Medoids show a result of 1.7868. Because the evaluation value of K-Means has low computing performance compared to K-Medoids. The largest amount of the value and weight of exports and imports of goods in Indonesia is in C1 where in the HS code [27], namely Mineral fuels with a total export value of goods in 2021 to 2023 of 134,999,470,522 US$ and a total import value of 113,714,568,740 US$. Meanwhile, the total export weight of goods from 2021 to 2023 in mineral fuel goods is 1,505,006,250,327 Kg or around 1,658,985,413 tons and the total import weight is 186,446,782,134 Kg or around 205,522,397 tons.
{"title":"Comparison of K-Means and K-Medoids Clustering Algorithms for Export and Import Grouping of Goods in Indonesia","authors":"Hazrul Anshari Ulvi, Muhammad Ikhsan","doi":"10.33395/sinkron.v8i3.13815","DOIUrl":"https://doi.org/10.33395/sinkron.v8i3.13815","url":null,"abstract":"International relations affect the economic growth of each country, which can affect the economic growth of each country. As a result, global economic growth is necessary, which means that the global economy has a greater capacity to produce goods and services. Exports and imports are very important to drive economic growth. but if exports and imports are not balanced, it will have a bad impact if the value of imports is greater than exports, export prices abroad will definitely fall. An analysis comparing export and import categories is needed to determine which goods are most imported and exported in Indonesia in 2021-2023. This study uses a quantitative methodology and machine learning methods, namely k-means and k-medoids algorithms. These two methods will be compared to determine which is the most effective for export and import data of goods in Indonesia in 2021-2023. The results of the study were obtained by K-Means more effectively in handling data on the grouping of exports and imports of goods in Indonesia in 2021-2023. The dataset shows the results of the evaluation of K-Means using DBI of 0.59, while the results of the evaluation using K-Medoids show a result of 1.7868. Because the evaluation value of K-Means has low computing performance compared to K-Medoids. The largest amount of the value and weight of exports and imports of goods in Indonesia is in C1 where in the HS code [27], namely Mineral fuels with a total export value of goods in 2021 to 2023 of 134,999,470,522 US$ and a total import value of 113,714,568,740 US$. Meanwhile, the total export weight of goods from 2021 to 2023 in mineral fuel goods is 1,505,006,250,327 Kg or around 1,658,985,413 tons and the total import weight is 186,446,782,134 Kg or around 205,522,397 tons.","PeriodicalId":34046,"journal":{"name":"Sinkron","volume":"12 19","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141836364","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：