Claim Missing Document
Check
Articles

Found 39 Documents
Search

PERBANDINGAN METODE KLASIFIKASI SUPPORT VECTOR MACHINE DAN NAÏVE BAYES PADA ANALISIS SENTIMEN KENDARAAN LISTRIK Ni Wayan Ernawati; I Nyoman Satya Kumara; Widyadi Setiawan
Jurnal SPEKTRUM Vol 10 No 3 (2023): Jurnal SPEKTRUM
Publisher : Program Studi Teknik Elektro UNUD

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/SPEKTRUM.2023.v10.i03.p12

Abstract

Electric vehicles are one of the solutions that can be used to deal with the problem of greenhouse gas emissions. Switching to electric vehicles can be an effective solution because electric vehicles have many advantages. However, the acceptance of electric vehicles in Indonesia depends on the opinions or sentiments given by the community. Sentiment analysis can provide a specific picture of how the sentiment or opinion given by the Indonesian people towards electric vehicles. The sentiment analysis process is carried out using the Python programming language. This research compares SVM and Naïve Bayes methods in sentiment analysis in terms of accuracy and time efficiency. A total of 717 data were used as test data and SVM correctly classified 150 negative data, 152 neutral data, and 277 positive data. Meanwhile, Naïve Bayes correctly classified 166 negative data, 143 neutral data, and 282 positive data. training time required for the SVM method is 37.42 seconds while Naïve Bayes is 0.10 seconds. Naïve Bayes is the best method in this study because of its high accuracy and fast training time.
Ship Trajectory Extraction Using Python Vessel Tracking Interpolation Method Setiawan, Widyadi; Linawati, Linawati; Widyantara, I Made Oka; Wiharta, Dewa Made; Asri, Sri Andriati
PIKSEL : Penelitian Ilmu Komputer Sistem Embedded and Logic Vol. 12 No. 2 (2024): September 2024
Publisher : LPPM Universitas Islam 45 Bekasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33558/piksel.v12i2.9567

Abstract

A deep understanding of ship trajectory movements has essential implications for maritime applications, including navigation, monitoring, and marine traffic analysis. Efficient and accurate extraction techniques are necessary to extract valuable information from ship trajectory data. One commonly used approach is the interpolation method, which allows the reconstruction of smooth trajectories from recorded data points. This research is focused on analyzing the extraction of ship trajectories using the interpolation method provided by the Python Vessel Tracking (PyVT) library. This method allows interpolation of ship trajectory data based on various algorithms available in the library. This research aims to evaluate the effectiveness and accuracy of interpolation methods from PyVT in reconstructing ship trajectories from incomplete or disturbed data. Within this research's framework, several test scenarios were implemented to examine different types of ship trajectory data, including data with missing points and speed variations. Evaluation metrics RMSE (root mean Squared Error), which includes reconstruction accuracy, will be utilized from the interpolation algorithm in PyVT.
ANALISIS KUALITAS JARINGAN PADA LAYANAN INDIHOME UNTUK GAME ONLINE Dove Gandaria, Aaron Gerry Ian; Sudiarta, Pande Ketut; Setiawan, Widyadi
Jurnal SPEKTRUM Vol 11 No 1 (2024): Jurnal SPEKTRUM
Publisher : Program Studi Teknik Elektro UNUD

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/SPEKTRUM.2024.v11.i01.p26

Abstract

The use and utilization of the Internet network is not only limited to its use for internet needs for social media but also for entertainment such as playing games such as the online game Valorant. The need for good network quality is very necessary to be able to play Valorant well. The purpose of this research is to determine the network quality of internet service provided by Indihome as one of the internet service providers (ISP) in Indonesia when playing the online game Valorant. With measurements using LAN cables and wireless at a speed of 50 Mbps using 2 laptop devices with the Indihome network. Measuring only the Delay and Packet Loss parameters using the Wireshark application, as well as measuring the Throughput parameters for the bandwidth requirements of the Valorant online game using the Netlimiter application for 4 weeks on Mondays and Wednesdays on weekdays and also weekends. The results of this test are the highest values of delay and packet loss for cable use, namely 6.81 ms and 0.285% and the highest values of delay and packet loss for wireless use, namely 6.15 ms and 0.548%. Where in testing the Quality of Service (QoS) value of the Indihome network when using cable and wireless, namely delay and packet loss, it shows good values compared to the TIPHON standard.
PROTOTYPE SISTEM PELEPASAN BEBAN BERBASIS INTERNET OF THINGS PADA SISTEM PENYIMPANAN ENERGI GEDUNG TEKNIK ELEKTRO UDAYANA Sungkono, Gilberth; Dyana Arjana, I Gd.; Setiawan, Widyadi; Maharta Pemayun, A.A Gd.
Jurnal SPEKTRUM Vol 11 No 2 (2024): Jurnal SPEKTRUM
Publisher : Program Studi Teknik Elektro UNUD

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Solar power plants (PLTS) and wind power plants (PLTB) are plants that utilize renewable energy sources Solar Power Plants and Wind Power Plants that work with an off-grid system will of course utilize batteries to store the energy that has been produced. This research aims to display a prototype that functions as a load shedding system for energy storage. The load shedding control system for microcontroller-based energy storage is designed so that the loading system according to the level of load vitality can be controlled automatically by the system so that manual control is not required. The microcontroller will provide output to the SSR relay will function as a release and connection for the electrical line. This research found results where the use of a load shedding system in energy storage can increase the duration of life of priority load lamps compared to other load classes.
SOLUSI ALTERNATIF PENYAMPAIAN INFORMASI DENGAN TOLERANSI WAKTU TUNDA UNTUK PENGGUNA LAYANAN KOMUNIKASI DATA PADA PEDESTRIAN NETWORK Vina Yuliani, Ni Putu; Permata Sari, Indah Ayu; Indra ER, Ngurah; Setiawan, Widyadi
Jurnal SPEKTRUM Vol 10 No 4 (2023): Jurnal SPEKTRUM
Publisher : Program Studi Teknik Elektro UNUD

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/SPEKTRUM.2023.v10.i04.p8

Abstract

This research aims to evaluate the performance of routing patterns in opportunistic networks for transmitting time-tolerant information, such as product prices and store coordinates in the Kuta, Badung area by using pedestrians as intermediaries and recipients of information. Two basic routing patterns, epidemic and spray and wait, are simulated using The ONE Simulator into two scenarios including a scenario of increasing average pedestrian density and a scenario of increasing buffer size. The simulation results show that in the scenario of increasing the average pedestrian density, the epidemic routing has a higher delivery probability and lower average latency than the spray and wait routing, but the spray and wait routing has a lower overhead ratio value. In the scenario of increasing buffer size, the spray and wait routing has a higher delivery probability and lower average latency at smaller buffer sizes. Meanwhile, the epidemic routing pattern produces a higher delivery probability and lower average latency at a larger buffer size, although with a difference that is not too significant.
SISTEM REKOMENDASI TEMPAT WISATA DI BALI MENGGUNAKAN IMDB WEIGTED RATING DAN CHATBOT Oktafiana Susanti, Baiq Dwinda; Setiawan, Widyadi; Indra ER, Ngurah
Jurnal SPEKTRUM Vol 10 No 4 (2023): Jurnal SPEKTRUM
Publisher : Program Studi Teknik Elektro UNUD

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/SPEKTRUM.2023.v10.i04.p9

Abstract

The Bali government is trying to re-optimize Bali's tourism potential after the Covid-19 pandemic. To improve the Balinese economy which had declined during the Covid-19 pandemic where foreign tourist visits decreased by 99.93%. In 2022, the tourism industry in Bali finally recovered with an increase in foreign tourist visits by 12.23%. The Bali government needs to optimize the number of foreign tourist visits to re-optimize the tourism sector. One way that can be done is to improve digital-based information services to introduce Bali to tourists. Therefore, to assist the Bali provincial government in optimizing the tourism sector, a recommendation system for tourist attractions in Bali called "MELALI" was created by utilizing the IMDb Weighted Rating algorithm and equipped with a chatbot as a customer service. Based on the results of system testing using Root Mean Square Error (RMSE), the result is 0.0126 (close to zero), this shows that the model made has a small error rate, besides that the chatbot feature has also been able to identify keywords and provide output in accordance with the requested keywords. Overall the system is running well.
EARLY WARNING SYSTEM PELEPASAN BEBAN PADA PENYIMPANAN ENERGI GEDUNG DH TEKNIK ELEKTRO Padwita Darma, I Made Angga; Dyana Arjana, I Gede; Setiawan, Widyadi
Jurnal SPEKTRUM Vol 11 No 2 (2024): Jurnal SPEKTRUM
Publisher : Program Studi Teknik Elektro UNUD

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

The aim of this research is to produce a prototype of an Early Warning System (EWS) for load shedding in energy storage based on ESP32. The load shedding system functions as a load manager to ensure that VIP load classes can be supplied for a longer duration. This load shedding system uses a control system from ATmega 328. The load shedding system utilizes the voltage level read on the battery, allowing it to classify loads according to their importance levels. The load classes are divided into four levels: VIP load class, first-class load, second-class load, and third-class load. The Early Warning System (EWS) is used to provide notifications stored on the battery. ATmega 328 will send battery voltage data to ESP32, which will then be sent through the Telegram application. The performance of the EWS in the load shedding system is reviewed in terms of its effectiveness. The object of this research is the automatic sending of load shedding warnings. Data on battery percentage was taken 20 times. When the battery voltage is 5% above the load class cutoff percentage, ATmega328 will send battery voltage data to ESP32. In the experimental results, it was found that when the percentages show 80%, 75%, 55%, 50%, 30%, 25%, and 5%, the EWS works by sending messages to users about which load class will soon be cut off.
Filter Air Kapur untuk Mengurangi Penyakit Batu Ginjal Azra Ariel Azmir; Ni Made Ary Esta Dewi Wirastuti; Widyadi Setiawan; Komang Oka Saputra
ULIL ALBAB : Jurnal Ilmiah Multidisiplin Vol. 1 No. 9: Agustus
Publisher : CV. Ulil Albab Corp

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Air merupakan salah satu sumber utama bagi kehidupan yang tidak bisa terlepas oleh makhluk hidup, namun kualitas sumber daya air mengalami penurunan yang dapat mengakibatkan bahaya bagi seluruh makhluk hidup. Penurunan kualitas sumber daya air terjadi akibat dari pencemaran lingkungan yang di dalamnya mengandung zat-zat berbahaya seperti logam, merkuri, hingga zat kapur yang dapat memicu berbagai penyakit berbahaya seperti salah satunya penyakit batu ginjal. Berdasarkan permasalahan yang ada di buatlah filter air kapur yang bertujuan untuk mengurangi zat kapur pada air sebagai pencegahan dini terhadap penyakit batu ginjal. Alat filter air kapur dapat mengurangi kandungan kapur yang terlarut di dalam air, pada alat ini dirancang beberapa benda seperti terdapatnya batu paras untuk mengurangi kandungan kapur pada air, arang yang berguna untuk mengurangi bau pada air, serta sensor pH untuk mengetahui kualitas air yang tertampung. Diharapkan alat ini dapat membantu masyarakat dalam menangani kandungan air yang terkandung kapur di dalam sumur sehingga terhindar dari penyakit batu ginjal.
Ship Trajectory Prediction Based on Spatial-temporal Data Using Long Short-Term Memory Setiawan, Widyadi; Linawati, Linawati; Widyantara, I Made Oka; Wiharta, Dewa Made; Asri, Sri Andriati; Pawana, I Wayan Adi Juliawan
JOIV : International Journal on Informatics Visualization Vol 9, No 3 (2025)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.9.3.3353

Abstract

The frequent exploitation of shipping lines by passengers increased traffic and exposed it to more significant dangers. Precise predictions for ship trajectory conditions at sea must be available to ensure safe navigation across the oceans. This article presents a trajectory prediction approach based on Long Short-Term Memory (LSTM) neural networks applied to time series Automatic Identification System (AIS) position data, expressed in spatial-temporal form. LSTM is highly suitable for ship trajectory predictions as it can capture long-term dependencies and spatial-temporal patterns existing in AIS data, since LSTM is targeted toward sequential data. The proposed model extracts ship trajectories from AIS data and utilizes an LSTM (Long Short-Term Memory) model to predict future ship movements based on historical patterns. The experiments demonstrate that it is effective in predicting where ships to navigate next, providing a valuable tool for enhancing traffic flow and improving navigation safety. The model with LSTM unit 500, tested on 3,478 ship trajectories, showed a median RMSE prediction error ranging from 0.0720 to 0.0841, with prediction M=8 coordinate a head having the highest error (0.0841) and M=2 and M=9 having the lowest (0.0720); the interquartile range (IQR) spanned from 0.0571 to 0.1006, and M=2 had the most outliers (302) while M=8 had the fewest (171), indicating varying prediction stability across different points. Despite these results, challenges remain in maintaining prediction stability across all points. Further optimization could enhance the model's performance and address these limitations by incorporating more complex spatial-temporal features or hybrid techniques.
Co-Authors A.A Ngurah Amrita Alfian Hadianto Antonius Ibi Weking Ardiansiah Ardiansiah Axel Adamma Diwanda Azra Ariel Azmir Bagus D. Cahyono Desi Ramayanti Dewa Gede Satria Bayu Putra Dewa Made Wiharta Dewa Ngakan Made Barel Dove Gandaria, Aaron Gerry Ian Duman Care Khrisne Dyana Arjana, I Gd. E. Duta Nugraha, I Putu Gede Sastra Utara Gede Sukadarmika Hilmy Jawas I Dewa Gde Bayu Wiranatha I Dewa Gede Aditya Pemayun I Dewa Gede Angga Prastika I G. A. K. Diafari Djuni Hartawan I Gede Dyana Arjana I Gede Dyana Arjana, I Gede I Gede Wiyoga Putra I Gusti Agung Adhi Waskita I Gusti Agung Komang Diafari Djuni Hartawan I Gusti Made Andi Dipayana I Ketut Ariek Astana Adi I Made Arsa Suyadnya I Made Martina Edi Putra I Made Oka Widyantara I N Satya Kumara I Nyoman Budiastra I Nyoman Setiawan I Putu E. Duta Nugraha I Putu Gede Krsna Yudha Dharma I Putu Hardy Sarjana I Putu Weda Suryawan I Wayan Darma Satika Ida Ayu Putu Intania Paramitha1 Ida Bagus A. Swamardika Issabelle M. Merry Jaime Luis da Costa Kevin Philip Komang Oka Saputra Komang Rio Adi Prasetya Limbong, Patrick Andreas Linawati Linawati M. Merry, Issabelle Made R. D. Prabawa Maharta Pemayun, A.A Gd. Maria Gusti Agung Ayu Permata Michael Angelo Vincensio Simon Muhamad Sony Pratama Ngurah Indra ER Ni Kadek Diah Parwati Ni Made Ary Esta Dewi Wirastuti Ni Putu Dina Rahmawati Ni Wayan Ernawati Novadianto Yudha Irawan Nyoman Putra Sastra Oktafiana Susanti, Baiq Dwinda Padwita Darma, I Made Angga Pande Ketut Sudiarta, Pande Ketut Patrick Andreas Limbong Pawana, I Wayan Adi Juliawan Permata Sari, Indah Ayu Philip, Kevin R. D. Prabawa, Made Rendi Gustina Riawanto Tambun Robbani Punggawa Arcapada Rukmi Sari Hartati Satriya Utama Sri Andriani Asri Sri Andriati Asri Sri Andriati Asri Sri Andriati Asri Sri Andriati Asri Sri Andriati Asri, Sri Andriati Sri Dianing Asri Sungkono, Gilberth Tjok Gede Indra Partha Vina Yuliani, Ni Putu Willy Sucipto Willy Susanto