Claim Missing Document
Check
Articles

Found 6 Documents
Search
Journal : Kilat

Klasifikasi Sentiment Analysis Pada Komentar Peserta Diklat Menggunakan Metode K-Nearest Neighbor Riki Ruli A. Siregar; Zuhdiyyah Ulfah Siregar; Rakhmat Arianto
KILAT Vol 8 No 1 (2019): KILAT
Publisher : Sekolah Tinggi Teknik - PLN

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (770.029 KB) | DOI: 10.33322/kilat.v8i1.421

Abstract

The process of analyzing and classifying comment data done by reading and sorting one by one negative comments and classifying them one by one using Ms. Excel not effective if the data to be processed in large quantities. Therefore, this study aims to apply sentiment analysis on comment data using K-Nearest Neighbor (KNN) method. The comment data used is the comments of the participants of the training on Udiklat Jakarta filled by each participant who followed the training. Furthermore, the comment data is processed by pre-processing, weighting the word using Term Frequency-Invers Document Frequency, calculating the similarity level between the training data and test data with cosine similarity. The process of applying sentiment analysis is done to determine whether the comment is positive or negative. Furthermore, these comments will be classified into four categories, namely: instructors, materials, facilities and infrastructure. The results of this study resulted in a system that can classify comment data automatically with an accuracy of 94.23%
Metode Weighted Product Pada Penentuan Perjalanan Dinas ( Studi Kasus : Arsip Nasional Republik Indonesia ) Riki Ruli A. Siregar; Anugrah Danny Prasetyo
KILAT Vol 5 No 1 (2016): KILAT
Publisher : Sekolah Tinggi Teknik - PLN

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1348.086 KB) | DOI: 10.33322/kilat.v5i1.681

Abstract

The determination of employee uses an alternative method to produce a decision. Methods for generating decision alternatives for employees who are entitled to travel is the method of Weighted Product. Weighted Methods Product has a consistent pattern in its calculation formula so that the calculation formula kesederhanan remains stubbornly high accuracy to four decimal places. determination of weighting between the criteria of benefit and cost criteria are within the powers of formula distinguishing numbers with positive and negative values ​​so the calculation becomes easier. Simplicity in calculation and the value of high accuracy is needed because the predefined criteria of ten criteria so that the result is very selective. This research was placed as a tool which is used prior to decision-making, for the alternative decision in determining employees in following official travel based on the criteria. This application required for the emergence of budget problems are less, the use of the budget surplus of the budget is predetermined. With this application, is expected to assist in the administration of official travel and provide the first step in saving and adjusting travel budgets in each of its parts.
Sistem Kontrol Pada Penggunaan Energi Listrik Berbasis Android Studi Kasus : Sekolah Menengah Pertama Negeri (SMPN) 7 Pontianak Riki Ruli A. Siregar; Alwi Baraqbah
KILAT Vol 4 No 1 (2015): KILAT
Publisher : Sekolah Tinggi Teknik - PLN

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1016.88 KB) | DOI: 10.33322/kilat.v4i1.700

Abstract

Automation in daily life has now become a necessity which began to be used in all areas, especially in the fields of education, economics, business, and industry. In the field of education , especially in elementary school, junior high school and high school, almost all the schools in Indonesia do electronic equipment settings which should help school personnel work with ease but still in do with the complicated, for example, conventional job still turn on and off the buzzer and lights, open the gates still use human tools, turn on a fan that has not been controlled in the center and many problems are still to be done manually with the help of human hand. In this case there needs to be a system that can manage and monitor the places they live and conduct electricity in a sustainable management. Responding to the issue in this thesis was designed and fabricated an integrated device such as intelligent building control system based on Android that uses a microcontroller, network and webserver in control. By utilizing the wireless connection technology , Raspberry, Arduino is expected to work optimally so as to provide safety and comfort .
Double Exponential Smoothing Berimputasi LOCF Dan Linear Interpolation Dalam Akurasi Peramalan Harga Harian Emas Riki Ruli A. Siregar; Taufik Djatna; Sergius Sarmose Manggara Putra Sarmose Manggara Putra; Irwansyah Saputra
KILAT Vol 10 No 1 (2021): KILAT
Publisher : Sekolah Tinggi Teknik - PLN

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33322/kilat.v10i2.1200

Abstract

Gold is another kind of investment that often experiences price change, mostly every day. Because of its price fluctuation, forecasting is needed to help the investor in investment decision making. But during this Coronavirus Disease 2019 (Covid-19), the gold price is fluctuating extremely than the past 4 years so a better forecasting method approached and analysis technique is needed due to this case. Double Exponential Smoothing method is chosen to forecast this daily gold price. On the other hand, there are so many missing values spreading around the main dataset so the imputation method is needed too, Last Observation Carried Forward (LOCF) and linear interpolation are chosen for imputing the missing values. In this research, the main dataset was split into 3 (three) datasets, which are Precovid-19 (before Covid-19, used only for visualizing the actual fluctuation condition during this pandemic), Incovid-19 (during Covid-19 based on the date where the first Covid-19 case occurred in Indonesia), and Combination (a binding dataset of Pracovid-19 and Incovid-19). Although Incovid-19’s MAPE value is higher than Pracovid-19 and Combination’s MAPE values, in evaluation session showed that Incovid-19’s MAPE of forecast results has the lowest value rather than Combination’s MAPE of forecast results, so the conclusion of this research is Incovid-19 dataset with LOCF imputation is the most adaptive with the actual condition and it is used to forecast the daily gold price until the last period of the main dataset then.
Implementasi Ant Colony Optimization (ACO) pada Sistem Irigasi Lahan Tadah Hujan Abdul Haris; Trisma Juwita; Rosida Nur Aziza; Hengki Sikumbang; Riki Ruli A. Siregar
KILAT Vol 10 No 2 (2021): KILAT
Publisher : Sekolah Tinggi Teknik - PLN

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33322/kilat.v10i2.1518

Abstract

The purpose of this research is to produce an optimal water distribution system for irrigation of rainfed land. The problem with conventional irrigation systems is that the water distribution process cannot be controlled and monitored automatically and in real time. The impact on water distribution becomes ineffective. The implementation of Ant Colony Optimization (ACO) is used in research as a method to determine the location or node based on the pheromone pattern of the soil dryness level at the sprinkler nodes to be distributed by the water flow, taking into account the criteria level on the soil as a trend of probability values ​​and determining the nodes according to the needs in the flow water. The results obtained from this study indicate that the data displayed is the level of dryness of each node, the volume of water in the reservoir, and the flow of water flowing. The ACO test shows the sequence of nodes that will be passed after the optimization process of water distribution in a rainfed irrigation system using the ACO method gets an error value calculated by the MAPE method of 43% so that it gets an accuracy value of 57%.
Integrating LoRa SX178S with GPS Sensor for Free Geolocation Satrio Yudho; Darma Rusjdi; Rizki Pratama Putra; Riki Ruli A. Siregar
KILAT Vol 11 No 1 (2022): KILAT
Publisher : Sekolah Tinggi Teknik - PLN

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33322/kilat.v11i1.1620

Abstract

Global positioning system known as an information which determine position of an object in standard value like Longitude and Altitude. due the trending development of Internet of things and its application, providing services is enable by using cellular networks which in metered connection. LoRa so-called long-range radio communication is one of wireless network sensor infrastructure that have an advantage in longer range operation. integrating LoRa with GPS module is one solution to provide location services with relatively free of cost. in this paper, we present our experiment of LoRa chipset SX76s and GPS module to aim the geolocation information to locate the device location.