Article Per Year (5 Year)
p-Index From 2021 - 2026
1.347
P-Index
This Author published in this journals
All Journal IAES International Journal of Artificial Intelligence (IJ-AI) Ecotrophic, Journal of Environmental Science Jurnal Teknologi Informasi dan Ilmu Komputer Jurnal Elementer (Elektro dan Mesin Terapan) JUTIK : Jurnal Teknologi Informasi dan Komputer Matrix : Jurnal Manajemen Teknologi dan Informatika Jurnal Teknologi Terapan MATRIX : JURNAL MANAJEMEN TEKNOLOGI DAN INFORMATIKA The International Journal of Remote Sensing and Earth Sciences (IJReSES)
I Ketut Swardika
Unknown Affiliation
Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Earth & Planetary Sciences Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Environmental Science Mechanical Engineering Social Sciences

Published : 15 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 15 Documents
Search

 1   2 
Rancang Bangun Penerjemah BISINDO Real-time Berbasis Kamera dan Deep Learning dengan Kendali Suara ESP32 WiFi I Gusti Agung Made Yoga Mahaputra; Putri Alit Widyastuti Santiary; I Ketut Swardika
Jurnal ELEMENTER (Elektro dan Mesin Terapan) Vol 11 No 1 (2025): Jurnal Elektro dan Mesin Terapan (ELEMENTER)
Publisher : Politeknik Caltex Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35143/elementer.v11i1.6578

Abstract

Indonesian Sign Language (BISINDO) serves as the primary means of communication for the deaf community. However, limited public understanding and the lack of practical real-time translation technology remain significant barriers to effective two-way communication. Most prior research has focused on foreign sign languages or relied on sensor-based gloves, which are less flexible for everyday use. This study proposes a real-time BISINDO translation system that converts hand gestures into speech using a camera and an ESP32 microcontroller. The system employs a CNN-LSTM deep learning model implemented in Python to classify gestures representing letters A to J, then wirelessly transmits the classification results to the ESP32, which triggers the corresponding audio output. A custom gesture dataset was collected and enhanced through preprocessing and data augmentation to support model training. Evaluation results demonstrate a classification accuracy of 91.4%, with a precision of 89.7%, recall of 90.5%, and F1-score of 89.9%. The average communication latency was recorded at 3.1 seconds, and the speech output success rate reached 86.7%. The system has proven reliable for real-time automatic gesture-to-speech translation and holds potential for further development as an inclusive communication aid for individuals with hearing impairments in Indonesia. This study serves as an initial foundation for future advancements in assistive communication technologies.
Sistem Pendukung Keputusan Penentuan Lokasi Wisata dengan Metode Topsis Santiary, Putri Alit Widyastuti; Ciptayani, Putu Indah; Saptarini, Ni Gusti Ayu Putu Harry; Swardika, I Ketut
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 5 No 5: Oktober 2018
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (3250.396 KB) | DOI: 10.25126/jtiik.2018551120

Abstract

Bali merupakan salah satu tujuan wisata favorit. Di Bali terdapat banyak lokasi wisata yang menawarkan berbagai kelebihannya masing-masing. Setiap kawasan wisata menawarkan wahana dan keunggulannya masing-masing. Hal ini seringkali menjadikan wisatawan bingung untuk menentukan lokasi wisata, agar mampu memaksimalkan waktu kunjungan, biaya serta kepuasan yang diperoleh. Penelitian ini bertujuan untuk membangun sistem pendukung keputusan (SPK) untuk penentuan lokasi wisata dengan metode TOPSIS dan fuzzy. Metode ini akan memberikan pembobotan kriteria sesuai dengan kondisi/preferensi pengguna, dan kemudian melakukan pengolahan pada data yang bersifat rasa/fuzzy. Metode TOPSIS akan memberikan perankingan alternatif yang menjamin kedekatan dengan kriteria benefit dan menjauhkannya dari kriteria yang bersifat cost. Implementasi sistem dilakukan dengan menggunakan database MySQL dan bahasa PHP. SPK yang dibangun mampu menghasilkan rekomendasi dengan memberikan perankingan lokasi wisata kepada pengguna sesuai preferensinya. Sistem yang dibangun diuji dengan menggunakan 17 alternatif dan 3 kriteria yang terdiri dari 1 kriteria cost dan 2 benefit. Eksperimen yang dilakukan berhasil memberikan perankingan yang berbeda terhadap 15 alternatif dan hanya 2 alternatif dengan ranking yang sama yaitu pada ranking ke-5 dan ke-6 karena skor keduanya sama pada setiap kriteria. AbstractBali is one of the favorite tourist destinations. In Bali there are many tourist destinations that offer their respective advantages. Each tourist area offers its own attraction and advantages. This often makes tourists confused to determine tourist destinations to maximize visit time, costs and satisfaction obtained. This study aims to build a decision support system (DSS) for determining tourist destinations with TOPSIS and fuzzy methods. This method will provide criteria weighting in accordance with the conditions/preferences of the user, and then perform processing on fuzzy data. The TOPSIS method will provide an alternative ranking that guarantees proximity to benefit criteria and keeps them from the cost criteria. System implementation was done using a MySQL database and PHP language. The DSS able to produce recommendation that provides users with a ranking of tourist destinations according to their preferences. The system built was tested using 17 alternatives and 3 criteria consisting of 1 cost criterion and 2 benefi criteria. Experiments carried out successfully gave different ranks to 15 alternatives and only 2 alternatives with the same ranking were ranked 5th and 6th because of both alternatives have the same score at each criterion.
VERTICAL DISTRIBUTION OF CHLOROPHYLL-A BASED ON NEURAL NETWORK TAKAHIRO OSAWA; CHAO FANG ZHAO; NUARSA I WAYAN; I KETUT SWARDIKA; YASUHIRO SUGIMORI
International Journal of Remote Sensing and Earth Sciences Vol. 2 (2005)
Publisher : BRIN

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30536/j.ijreses.2005.v2.a1353

Abstract

An algorithm of estimating Vertical distribution of Chlorophyll-a (Chl-a) was evaluated based on Artificial Neural Networks (ANN) method in Hokkaido field in the northwest of Pacific Ocean. The algorithm applied to the data of SeaWiFS on OrbView-2 and AVHRR on NOAA off Hokkaido, has been applied on September 24, 1998 and September 28, 2001. Ocean color sensor provides the information of the photosynthetic pigment concentration for the upper 22% of the euphotic zone. In order to model a primary production in the water column derived from satellite, it is important to obtain the vertical profile of Chl-a distribution, because the maximum value of Chl-a concentration used to lie in the subsurface region. A shifted Gaussian model has been proposed to describe the variation of the chlorophyll-a (Chl-a) profile which consists of four parameters, i.e. background biomass (B0), maximum depth of Chl-a (zm), total biomass in the peak (h), and a measurement of the thickness or vertical scale of the peak (cr). However, these parameters are not easy to be determined directly from satellite data. Therefore, in the present study, an ANN methodology is used. Using in-situ data from 1974 to 1994 around Japan Islands, the above four parameters are calculated to derive the Chl-a concentration, sea surface temperature, mixed layer depth, latitude, longitude, and Julian days. The total of 6983 profiles of Chl-a and temperature are used for ANN. The correlation coefficients of these parameters are 0.79 (B0), 0.73 (h), 0.76 (cr) and 0.79 (zm) respectively. A site called A-linc off Hokkaido is used to evaluate Chl-a concentration in each depth. After comparing with in-situ data and ANN model, the results show good agreement relatively. Therefore, the ANN method is applicable and available tool to estimate primary production and fish resources from the space.
ESTIMATION OF TUNA FISHING GROUND IN LOW LATITUDE REGION USING SEA SURFACE HEIGHT GRADIENT DERIVED FROM SATELLITE ALTIMETRY: APPLICATION TO NORTHEASTERN INDIAN OCEAN Susumu Kanno; Yasuo Furushima; I Wayan Nuarsa; I Ketut Swardika; Atsushi Ono
International Journal of Remote Sensing and Earth Sciences Vol. 3 (2006)
Publisher : BRIN

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30536/j.ijreses.2006.v3.a1209

Abstract

In order to improve the method for prediction of tuna fishing ground, the modification of the analysis about satellite altimeter data was made as trial. In this study, we focused on the satellite altimeter, TOPEX/POSEIDON series, to improve the method of fishing ground prediction. Fishery data were supplied as hook rate by local fishing information around Indonesia and hearing infromation. The gradient of sea surface height is calculated between the neighbor grid which has the maximum gradient. Result showed that the fishery data with hook rate over 0.8 are grouped in a zone from 1.0E-06 of sea prediction of fishing ground quantitatively, but also reasonable accuracy as shown in the change in the standard deviation. This method can be utilized for the effective fishing plan with the resource protection and the economy in the fishing operation in near future.
BIO-OPTICAL CHARACTERISTIC OF CASE-2 COASTAL WATER SUBSTANCES IN INDONESIA COAST I Ketut Swardika
International Journal of Remote Sensing and Earth Sciences Vol. 4 (2007)
Publisher : BRIN

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30536/j.ijreses.2007.v4.a1218

Abstract

The result of our study in the bio-optical characteristic of mixed water substances or referred as water leaving radiance of chlorophyll-a in case-2 water. Apparent optical properties of chlorophyll-a(chl-a) influence by others water constituents eq.particle backscattering, and yellow substances absorption coefficients. We studied varies Chl-a concentration from 0.001 ug/l,-65.0 ug/l, mixed by suspended particle (SS) concentration from 0.01 mg/l-50.0mg/l, and yellow substances absorption coeficients (ay) from 0.001m - 5.0m. We used the simple radiative transfer equation in seawater method to simulate the Normalized water leaving radiance (NLw)of Chl-a with concentration less than 1 ug/l and less influence from other substances similiar to NLw of pure sea water characteristic. This high reflected at blue band. Otherwise, chl-a concentrations more than 1 ug/l, are similiar to the absorption characteristic of Chl-a with flourescene peak at 680 nm. The Cross characteristic (Hinge point) occurs at 530 nm. Higher SS concentration causes NLw characteristic of Chl-a change, where hinge point moves toward the longer wavelength. Higher yellow substance absorption coeficients cause NLw characteristic of Chl-a has strange behavior. To keep the NLw Chl-a characteristic SS concentration should be no more than 1 mg/l, and ay coeficient no more than 0.01m.
Co-Authors Atsushi Ono Budiada, I Made CHAO FANG ZHAO Dewa Ayu Indah Cahya Dewi Harry Saptarini, Ni Gusti Ayu Putu I Gusti Agung Made Yoga Mahaputra I Nyoman Kusuma Wardana I Nyoman Mudiana I Wayan Arthana I Wayan Nuarsa Ida Bagus Irawan Purnama NUARSA I WAYAN Putri Alit Widyastuti Santiary Putu Indah Ciptayani Santiary, Putri Alit Widyastuti Sugirianta, Ida Bagus Ketut Susumu Kanno Takahiro Osawa Widyastuti Santiary, Putri Alit YASUHIRO SUGIMORI Yasuo Furushima