Article Per Year (5 Year)
p-Index From 2020 - 2025
2.024
P-Index
This Author published in this journals
All Journal IAES International Journal of Artificial Intelligence (IJ-AI) Majalah Ilmiah Teknologi Elektro JOIV : International Journal on Informatics Visualization Informatika EDUKASI
Rukmi Sari Hartati
Teknik Elektro Unud
Religion Humanities Chemical Engineering, Chemistry & Bioengineering Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering Library & Information Science Other

Published : 13 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 13 Documents
Search

 1   2 
Sistem Pelaporan dan Monitoring Data Limbah Pada Dinas Lingkungan Hidup dan Kebersihan Kabupaten Badung Wijaya, Anak Agung Ngurah Mahendra; Hartati, Rukmi Sari; Divayana, Yoga
Jurnal Teknologi Elektro Vol 22 No 2 (2023): (Juli - Desember) Majalah Ilmiah Teknologi Elektro
Publisher : Program Studi Magister Teknik Elektro Universitas Udayana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/MITE.2023.v22i02.P04

Abstract

In the waste reporting process is still done manually, so the hotel is required to come to the Badung Regency Environment and Hygiene Office and then submit the report. These activities cause the reporting process to require a long duration and the progress of the report cannot be monitored by the hotel. The formulation of the problem in this study is how to report and monitor waste data from hotels quickly using the Waste Data Reporting and Monitoring System. The purpose of this research is to help hotels, especially in Badung district, in providing waste reporting quickly. In making this system, the design concept goes through the stages of data collection, Cross Functional Flowchart, Context Diagram, Level 0 Data Flow Diagram, Entity Relationship Diagram, Conceptual Database and Interface Design. And then implement it with Hypertext Preprocessor Programming (PHP), Bootstrap Framework, MySQL.
IoT Berbasis NodeMCU ESP8266 Sebagai Decision Support System Pengelolaan Energi Gedung Telkomsel Renon Hardiansyah, Amien Harist; Kumara, I Nyoman Satya; Hartati, Rukmi Sari
Jurnal Teknologi Elektro Vol 23 No 1 (2024): (Januari - Juni ) Majalah Ilmiah Teknologi Elektro
Publisher : Program Studi Magister Teknik Elektro Universitas Udayana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/MITE.2024.v23i01.P11

Abstract

The Telkomsel Renon Building serves as the regional telecommunications service office for the Bali and Nusa Tenggara area, covering an area of 5072 m2 with a PLN power capacity of 555 kVA. PT Telkom is committed to reducing energy consumption by implementing ISO 50001 energy management. Despite this, the use of 14 smart meters is still manually conducted, leading to a lack of real-time energy usage information. PLN data indicates an average energy consumption from 2017 to 2023 of 628.271 kWh, with an average annual cost of Rp. 696.915.017. Factors such as electrical equipment, room size, activities within, and building insulation affect the building's energy consumption. Inappropriate activities relative to room capacity can lead to energy wastage. One solution proposed for accurately monitoring energy usage in real-time involves the development of an Internet of Things (IoT) based application using Blynk. IoT is implemented in large meeting rooms with Central Split Duct AC and small meeting rooms with Split Wall AC. Measurement results indicate significantly higher energy consumption in large meeting rooms, reaching 4207.83 kWh, compared to only 467.06 kWh in small meeting rooms for similar activities. Discussions with users of small meeting rooms revealed their comfort and successful achievement of meeting objectives. By utilizing small meeting rooms, energy consumption can be reduced by up to 88.9%. Based on these findings, recommendations for room usage SOPs have been formulated for the Telkomsel Renon Building to realize energy-efficient practices towards green building standards. Keywords: Energy Management; Green Building; Internet of Things; Smart Meter.
Analisis Efisiensi Energi antara Lampu LED dan Lampu Konvensional (Studi kasus: Pada Hotel Cap Karoso) Pramono, Lukito; Linawati, Linawati; Hartati, Rukmi Sari
Jurnal Teknologi Elektro Vol 22 No 2 (2023): (Juli - Desember) Majalah Ilmiah Teknologi Elektro
Publisher : Program Studi Magister Teknik Elektro Universitas Udayana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/MITE.2023.v22i02.P10

Abstract

LED lamps are an example of an efficiency method compared to conventional lamps because of their higher energy efficiency. In this research, a comparative analysis of electrical efficiency was carried out between LED lamps and conventional lamps. This research collected data from a number of lamps used in a comparative study of LED lamps and conventional lamps at the Cap Karoso Hotel and were tested under the same conditions. The types of LED lights used are recessed downlights, track lights, pendant lights and wall scones. While the types of conventional lamps used are incandescent, halogen, fluorescent and HID. Comparisons and calculations were made in terms of watt energy and electricity costs. Based on these parameters, it can be seen the energy produced and the costs required from both types of LED lamps and conventional lamps. Based on calculations and comparisons of the two types of lamps used, it is calculated that LED lamps can save energy and cost savings by 27%.
Analisis Penentuan Respons Twitter sebagai Media Komunikasi dan Informasi Pemerintah Berbasis Metode Rabin-Karp Sari, Luh Ayu Diah Fernita; Sastra, Nyoman Putra Putra; Hartati, Rukmi Sari
Jurnal Teknologi Elektro Vol 22 No 2 (2023): (Juli - Desember) Majalah Ilmiah Teknologi Elektro
Publisher : Program Studi Magister Teknik Elektro Universitas Udayana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/MITE.2023.v22i02.P15

Abstract

Social media in this digital era, especially Twitter, has an important role in the interaction between government and society. Given the wide variety of activities within government circles, the task of monitoring and responding to messages is complex and time-consuming. Therefore, this study aims to develop an effective approach in determining the appropriate response from the government to people's tweets. This study proposes using a combination of the Rabin-Karp method to quickly determine relevant responses. The Rabin-Karp method, known for its efficiency in pattern matching, is used to match tweets to a set of tweets that have already been given a response. Furthermore, the Word2Vec technique is used to improve understanding of the meaning of the text. The use of the Rabin-Karp method with the addition of the Word2Vec method shows that the response accuracy rate is 74.55%. The results of this study also show that the lower the K-Gram value, the higher the similarity value, and vice versa. These results are expected to contribute in the context of government that is responsive to societal issues discussed on Twitter.
Kemandirian Energi Listrik di Pasar Seni Kuta dengan menggunakan Sistem PLTS Wiranatha, I Dewa Gde Bayu; Hartati, Rukmi Sari; Setiawan, I Nyoman
Jurnal Teknologi Elektro Vol 23 No 1 (2024): (Januari - Juni ) Majalah Ilmiah Teknologi Elektro
Publisher : Program Studi Magister Teknik Elektro Universitas Udayana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/MITE.2024.v23i01.P17

Abstract

The Kuta Art Market, is a modern market that was recently revitalized in 2023. The building has renewable energy potential of PLTS on the roof area, when this potential can be exploited then the electricity consumption of the Kuta Art Market Building is no longer supplied by conventional power plants (PLN) but will enjoy clean energy of autonomous plants such as PLTS. The aim of this study is to identify the potential for generating electricity on the roof of the Kuta Art Market, determine the capacity of the battery as a reserve source of energy and the value of the investment. The research steps of this thesis calculate the solar energy potential in the area of the Kuta Art Market by using PVsyst software, collect the load profile of the Kuta Art Market. The next step is to compute the capacity of the PLTS - inverter then determine the battery capacity required according to the load profile of the Kuta Art Market and then determines the investment cost to build the solar power plant on the rooftop of the Kuta Art Market as well as to evaluate the potential cost savings that can be achieved by using solar energy as a primary resource. The total roof area of the Kuta Art Market is 780,455 m2 with energy potential of 166,23 kW. Based on the design results, PLTS will be built with a capacity of 61,6 kWp, with total battery capacity 3200 Ah. Total investment of Rp. 1,162,938.563 is required for the construction of PLTS, a payback period of 15 years 8 months, NPV of Rp. 204,439.887,26 and IRR of 8,06%. Based on the values above, it indicates that the PLTS project on the roof of the Kuta Art Market building is feasible to carry out.
Analisa Indeks Keandalan pada Pembangkit Listrik Tenaga Mesin Gas (PLTMG) MPP Flores Kapu, Joannes Mario Graciano; Jasa, Lie; Hartati, Rukmi Sari
Jurnal Teknologi Elektro Vol 23 No 1 (2024): (Januari - Juni ) Majalah Ilmiah Teknologi Elektro
Publisher : Program Studi Magister Teknik Elektro Universitas Udayana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/MITE.2024.v23i01.P13

Abstract

Energi listrik ialah kebutuhan penting yang semakin berkembang setiap tahunnya. Memastikan distribusi tenaga listrik yang andal, aman dan ramah lingkungan sangat penting untuk memenuhi kebutuhan pelanggan sesuai dengan standart yang ditetapkan. Untuk menilai kemampuan pembangkit listrik dalam memenuhi kebutuhan listrik, diperlukan adanya indeks keandalan pembangkit listrik. Riset ini bertujuan untuk menilai indeks keandalan pada Pembangkit Listrik Tenaga Mesin Gas (PLTMG) MPP Flores. Nilai indeks LOLP (Loss Of Load Probability) dimanfaatkan untuk melakukan perhitungan. Pada penelitian ini dalam mencari indeks keandalan suatu sistem pembangkitan, mengacu pada dalam SPLN : 68-1A : 1986 yaitu untuk sistem Jawa-Bali adalah 3 hari per tahun dan untuk sistem diluar Jawa-Bali adalah 3,5-5 hari per tahun. Berdasarkan hasil penelitian nilai LOLP dari PLTMG MPP Flores pada tahun 2022 adalah sebesar 4,5295 hari/tahun dan berdasarkan SPLN : 68-1A:1986, maka dari itu nilai Loss Of Load Probability (LOLP) pada PLTMG MPP Flores dikatakan andal karena sudah memenuhi standar. Kata Kunci— LOLP; Keandalan; PLTMG.
Rancang Bangun Simulator Smart Home Berbasis IoT Dengan Sumber Daya PLTS Servinus, Servinus; Kumara, I Nyoman Satya; Hartati, Rukmi Sari
Jurnal Teknologi Elektro Vol 23 No 1 (2024): (Januari - Juni ) Majalah Ilmiah Teknologi Elektro
Publisher : Program Studi Magister Teknik Elektro Universitas Udayana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/MITE.2024.v23i01.P10

Abstract

Electrical energy is one of the basic needs to support daily life. Renewable energy sources are an alternative that can be used as a source of electrical energy, one example is solar energy. This research aims to be able to create a control and monitoring system for electrical equipment loads based on the Internet of Things, to be able to simulate this tool as a test the system as a whole, starting from the power source to the devices to be controlled. The simulation results in the design show monitoring of load (charger smartphones) and then the system can control it by disconnecting the power source by an automatic relay which is connected to the Esp-Wroom32 via a WiFi network so that the system can run according to the user's needs. Keywords - Smart Home; Energy Consumption Intensity; System Monitoring; Smart Control; Esp-Wroom32.
Classification of Tri Pramana learning activities in virtual reality environment using convolutional neural network Sindu, I Gede Partha; Sudarma, Made; Hartati, Rukmi Sari; Gunantara, Nyoman
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 13, No 3: September 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v13.i3.pp2840-2853

Abstract

Tri Pramana as the local genius of Balinese society, is now adopted in the education system. This adaptation results in a Learning Cycle Model which essentially consists of three classes namely Sabda Pramana (theoretical study), Pratyaksa Pramana (direct observation), and Anumana Pramana (practicum). In learning activities, it is difficult for educators to fully observe individuals to find out the most suitable learning model. Through Virtual Environment Technology, educators can observe students more freely through the recording of students' activities. However, in its implementation, manual analysis requires large resources. Deep Learning approach based on Convolutional Neural Network (CNN) is able to automate this analysis process through the classification ability of the image of the recorded learner activity. To produce a robust CNN model, this research compares four of the most commonly used architectures, namely ResNet-50, MobileNetV2, InceptionV3, and Xception. Each architecture is tuned using a combination of learning rate and batch size. Through a 512 x 512 resolution dataset with 70% training subset (4,541 images), 20% validation (1,296 images), and 10% test (652 images), the best ResNet model is obtained with a learning rate configuration of 1e-3 and batch size 64 with an accuracy of 99.39%, precision of 99.37%, and recall of 99.42%.
Rancang Bangun Purwarupa Monitoring Arus Bocor Pada Kabel Grounding Trafo Incoming 20 KV di Gardu Induk Nusa Dua Berbasis Internet Of Things Saputra, Dharma Bagus; Pradana, Aditya; Togatorop, Josua Febrian; Jasa, Lie; Hartati, Rukmi Sari
Jurnal Informatika Vol 12, No 3: INFORMATIKA
Publisher : Fakultas Sains & Teknologi, Universitas Labuhanbatu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36987/informatika.v12i3.5998

Abstract

Failure of the grounding isolation on the 20 kV transformer incoming cable, resulting in leakage current. The leakage current on the grounding cable can change periodically, so an accurate and real-time monitoring system is required to protect the power transformer equipment and facilitate responsive handling. Therefore, an Internet of Things-based monitoring device is needed that can detect the magnitude of the leakage current present on the 20 kV secondary side of the transformer using an ESP8266 microcontroller and Arduino UNO R3 as the brain of the monitoring system, which controls and processes data from the input to output components. The SCT-013 current sensor is used to measure the AC current on the transformer incoming 20 kV grounding cable without requiring cable cutting, and the Arduino IDE is used to configure the program on the ESP8266 microcontroller to work according to the desired configuration. The results of the prototype testing using the ESP826 and Arduino UNO R3 microcontrollers and the SCT-013 current sensor have shown that the system can work well and the monitoring has been successfully implemented with real-time current monitoring using the Thinkspeak and Blynk platforms. The testing also proved that the SCT-013 current monitoring device can provide a comparison of the test results and measurements with a Tang Ampere, and the data obtained shows that the real-time SCT-013 current monitoring device is accurate, with an average reading error of less than 3% from the SCT-013 non-linearity specification, with a total reading error percentage of 2.0%. Additionally, the current monitoring device is precise, with the lowest standard deviation value of 0.046.
Multi Task Deep Learning with Transformer Encoder Decoder for Semantic Segmentation Indah, Komang Ayu Triana; Darma Putra, I Ketut Gede; Sudarma, Made; Hartati, Rukmi Sari
JOIV : International Journal on Informatics Visualization Vol 9, No 1 (2025)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.9.1.1978

Abstract

Visual understanding is one of the core elements of computer vision consisting of image classification, object detection, and segmentation. The system applies a multilayer process to obtain complex image and video understanding using deep learning methods to convert the images to text. Therefore, this study aimed to extract video in the form of frames followed by the application of Transformer and Inception V3 architectures to the image captioning process. The synchronization was based on Multi-task Deep Learning method developed by combining Convolutional Neural Network (CNN) system in the image area, Recurrent Neural Network (RNN) with Long Short-Term Memory (LSTM) in the sentence area, Caption Content Network (CCN), and Relational Network Context (RCN). Moreover, Transformer Encoder-Decoder architecture was used in the process of labeling and determining the relationships between objects. The results of the image-to-text conversion process were determined by comparing prospective translated text with one or more references. This was achieved using accuracy and loss validation tables to provide graphical comparisons between the number of epochs and losses. The test results showed that the validation data accuracy was 70.166% while the loss was 22,648% and this showed more epoch iterations led to greater validation accuracy.Keywords— Visual Understanding, Transformer, Encoder, Decoder
Co-Authors Aditya Pradana, Aditya Agus Aan Jiwa Permana Dewa Made Wiharta Hardiansyah, Amien Harist Helmawati Helmawati I GAN Subawa, I GAN I ketut Gede Darma Putra I Made Agus Putrawan, I Made Agus I Made Sukarsa I Made Widiartha I N Satya Kumara I Nyoman Gunantara I Nyoman Setiawan I Nyoman Suprapta Winaya Kapu, Joannes Mario Graciano Komang Ayu Triana Indah Lie Jasa Linawati Linawati Luh Gede Astuti Made Sudarma Marzuki Marzuki Miftahul Huda Nyoman Putra Sastra Pramono, Lukito Putu Lokantara Saputra, Dharma Bagus Sari, Luh Ayu Diah Fernita Servinus, Servinus Sindu, I Gede Partha Togatorop, Josua Febrian Wijaya, Anak Agung Ngurah Mahendra Wiranatha, I Dewa Gde Bayu Yoga Divayana