Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : Internet of Things and Artificial Intelligence Journal

Wireless Network Service Quality Analysis at Kefamenanu 1 State Vocational School using QoS Methods Silla , Intan Nubriyanti; Rema, Yasinta Oktaviana Legu; Fallo, Kristoforus
Internet of Things and Artificial Intelligence Journal Vol. 4 No. 4 (2024): Volume 4 Issue 4, 2024 [November]
Publisher : Association for Scientific Computing, Electronics, and Engineering (ASCEE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31763/iota.v4i4.812

Abstract

Indonesia is one of the largest archipelagic countries in the world, one of the challenges is that the existing internet network is not optimal and should be evenly distributed throughout Indonesia. This article is one of the efforts to increase the capacity and use of the internet, especially to support the education process which should be evenly distributed in various regions in Indonesia, not only in Java but also in areas outside Java. especially in East Nusa Tenggara. NTT is one of the areas discussed in this article, specifically at Kefamenanu 1 State Vocational School. This article puts forward some essential aspects in the development and installation of the internet in this school, including using the right measurements of Quality of Service (QoS). QoS includes many things such as Throughput, Bandwidth, Packet Loss, and other parameters that are essential in building and analyzing internet networks that have a wide scope, especially for the Education level. Vocational High Schools are not only expected to be able to use the internet but also build, design, install, and perform detailed analysis on the internet network they build. Two essential networks must be able to be installed, i.e., a Wireless Network and Local Area Network.
Prediction of New Customer Segmentation Classification Using Artificial Intelligence Project Cycle Orange Data Mining Kosat , Fransiska Febriyanti; Rema, Yasinta Oktaviana Legu; Ullu, Hevi Herlina
Internet of Things and Artificial Intelligence Journal Vol. 4 No. 4 (2024): Volume 4 Issue 4, 2024 [November]
Publisher : Association for Scientific Computing, Electronics, and Engineering (ASCEE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31763/iota.v4i4.813

Abstract

This research aims to predict the right segmentation group or classification of new customers to become a classification comparison data carried out by the sales team to determine the strategy used to enter the market, whether it can be said to be feasible or not. This article discusses the basis of the method used, i.e., Machine Learning, discussed in detail about Artificial Intelligence (AI). Also discusses what is Classification, Segmentation, Data Mining, Neural Networks, Naive Bayes, Decision Trees, Random Forest (RF), and Support Vector Machine (SVM). This article discusses comprehensively the method used, and the development of Modeling, in the results and analysis section, comprehensively shows the prediction analysis of new customer segmentation classification, algorithm performance results of several methods, and distributions analysis. With the percentage prediction of new potential customer segmentation using the Neural Network method, the percentage prediction of Segmentation A is 25.21%, the percentage prediction of Segmentation B is 21.77%, the percentage prediction of Segmentation C is 23.49%, the percentage prediction of Segmentation D is 29.53%. The percentage of segmentation that has been calculated by the company is the percentage of Segmentation A of 32.13%, the percentage of Segmentation B of 20.89%, the percentage of Segmentation C of 17.69%, and the percentage of prediction of Segmentation D of 29.29%.