Article Per Year (5 Year)
p-Index From 2020 - 2025
0.817
P-Index
This Author published in this journals
All Journal Jurnal Ilmiah Teknologi dan Rekayasa Prosiding KOMMIT Jurnal Teknologi Informasi dan Ilmu Komputer Angkasa: Jurnal Ilmiah Bidang Teknologi Journal of Applied Data Sciences
Sulistyo Puspitodjati
Universitas Gunadarma
Automotive Engineering Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering Engineering Industrial & Manufacturing Engineering Materials Science & Nanotechnology

Published : 5 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 5 Documents
Search

 1 
SISTEM PENGENALAN EKSPRESIWAJAH BERDASARKAN CITRA WAJAH MENGGUNAKAN METODE EIGENFACE DAN NEAREST FEATURE LINE Puspitodjati, Sulistyo
Prosiding KOMMIT 2012
Publisher : Prosiding KOMMIT

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

Abstract

Suatu citra terdiri dari berbagai informasi yang membuatnya dapat dikenali.Informasi tersebut diperlukan dalam proses pengenalan citra. Salah satu metode untuk mengekstrakciri-ciri suatu citra adalah metodeEigenface.Metode Eigenface menggunakan Transformasi Karhounen-Loeve atau PCA untuk mentransformasikan suatu citra berdimensi besar ke dimensi yang lebih kecil di dalam ruang eigen. Sistem Pengenalan Ekspresi Wajah 2 Dimensi dengan Menggunakan Metode Eigenface dan Nearest Feature Line ini bertujuan mengenali berbagaivariasi ekspresi wajah. Metode pengenalan yangdigunakan adalah Nearest Feature Line (NFL) yang melakukan generalisasi ciri-cirisuatu citra dengan membentuk garis ciri (feature line) antara titik-titik ciri dari citra yang bersangkutan. Garis ini akan merangkap lebih banyak perubahan antara titik-titik ciri tersebut, sehingga metode ini dapatmengenali citra dengan variasi ciri yang tidakterdapat pada citra pelatihan. Citra wajah yang telah direduksi dengan menggunakanmetode Eigenface akan menjadi masukan bagiNearest Feature Line untuk melakukan klasifikasi ekspresi berdasarkan nilaithreshold. Uji coba metodedilakukan dengan menggunakan 75 buah sampel Citra Pelatihan yang dibagi ke dalam 3 kelas ekspresi;Tertawa, Senyum, dan Netral. Kemudian 30 buah sampel CitraPengujian –masing-masing 10 untuk setiap kelas ekspresi – digunakan untukmengukur presentasikeberhasilan metode ini. Dari total 105 citra yang digunakan, didapatkan presentasikeberhasilan yang bervariasi, yaitu 70%untuk kelasekspresi Tertawa, 60%untuk kelas ekspresi Senyum, dan 50%untuk kelas ekspresi Netral.
FORECASTING MONTHLY NAUTICAL CHART TIME SERIES OF JAVA AREA USING ARIMA METHOD (Case study: Primkopal Pushidrosal Sales Units) Benny Rushadi; Sulistyo Puspitodjati
Angkasa: Jurnal Ilmiah Bidang Teknologi Vol 12, No 1 (2020): Mei
Publisher : Institut Teknologi Dirgantara Adisutjipto

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (195.072 KB) | DOI: 10.28989/angkasa.v12i1.581

Abstract

Nautical chart is a sea map made from paper and has a function to safety of navigation at sea as it provides vital information such as configuration of the coastline, depth of the sea, seabed nature, hazardous location, height and navigation aids. Sailing at sea and on the waters are not always safe as many navigational hazards threaten at any time, therefore the role of nautical charts is essential. Inaccuracy in estimating the number of nautical chart production has affected the amount of stockpiles in the warehouse, this is very inefficient for sales unit of Primkopal Pushidrosal. Consequently, the making of an appropriate forecasting model to predict the amount of stock in the coming period is expected to overcome these problems. The data which had been used in this research is Indonesian nautical chart sales  from January 2012 to March 2019 in the Java area  for 87 periods from January 2012 to March 2019 to predict the number of product requests for the coming 8 periods from April to November 2019, as the most densely sea traffic hence nautical charts in this area are the most utilized. The quantitative analysis of the model uses the Integrated Moving Average Autoregressive (ARIMA) method approach where the stages are from identification of model, estimation of parameter and diagnostic tests, because this method is good enough to predict short-term periods and is suitable for predicting the magnitude of any variable in time series data. Processing data uses Minitab 17 software and the results of the research showed that 87 of these periods where the data has not been stationer against mean, so it must be differentiated level 1 in order to be stationary and the ARIMA model is ARIMA(0,1,1) by equation  Xt = - 0.551 + Xt − 1 - 0.85et– 1.
ANALISIS KESADARAN MASYARAKAT MENGENAI ISU STUNTING PADA TWITTER MENGGUNAKAN ANALISIS JEJARING SOSIAL Ernastuti Ernastuti; Sulistyo Puspitodjati; D. L. Crispina Pardede; Henny Widowati Farida
Jurnal Ilmiah Teknologi dan Rekayasa Vol 28, No 1 (2023)
Publisher : Universitas Gunadarma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35760/tr.2023.v28i1.8329

Abstract

Stunting, menurut WHO, merupakan masalah bagi suatu negara jika nilai prevelansinya di atas 20%. Indonesia, dalam nilai prevalensi termasuk tinggi, sempat menduduki tertinggi ke-tiga di dunia. Walau nilai prevalensi stunting di Indonesia membaik, namun masih di atas standar WHO tersebut. Pemerintah sudah merumuskan dan mengambil keputusan untuk memperkecil nilai stunting ini, salah satunya adalah meningkatkan kepedulian masyarakat tentang bahaya stunting. Penelitian ini melakukan analisa keterlibatan masyarakat melalui pendekatan analisa jaringan sosial untuk melihat sejauh mana masyarakat terlibat melalui ukuran modularitas dan sentralitas jaringan sosial melalui scraping data media sosial Twitter. Hasil penelitian berupa topik utama yang dibahas berkenaan stunting, dan statistik jaringan masyarakat yang membicarakan stunting di Twitter.
Enhancing Sharia Stock Price Forecasting using a Hybrid ARIMA-LSTM with Locally Weighted Scatterplot Smoothing Regression Approach Gunaryati, Aris; Mutiara, Achmad Benny; Puspitodjati, Sulistyo
Journal of Applied Data Sciences Vol 6, No 1: JANUARY 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i1.514

Abstract

Predicting Sharia stock prices is complex because it has high volatility and non-linear data patterns. To improve the accuracy of the forecast, the right technique is needed according to the existing data pattern. One of the techniques currently developing is integrating (hybrid) two forecasting models. This study proposes a hybrid autoregressive integrated moving average (ARIMA) and long short-term memory (LSTM) model with the locally weighted scatterplot smoothing (lowess) linear regression technique. This model is designed by creating a linear regression between the actual value and the predicted results of the ARIMA and LSTM models using the Lowess technique. The dataset used here is the closing stock prices of four Indonesian Islamic banking companies. The hybrid ARIMA-LSTM model with lowess linear regression significantly outperforms the individual ARIMA and LSTM models because it produces better performance metrics, namely mean square error (MSE), root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE), for training and testing datasets. The proposed hybrid model effectively reduces noise, and the model can capture complex patterns in the Sharia stock price dataset, and the prediction results are more accurate. The accuracy values for training data and data testing datasets were respectively 97.6% and 98.3% (BANK. JK), 98.3% and 98.2% (BRIS. JK), 99.4% and 99.5% (BTPN. JK), and 97.7% and 99.3% (PNBS. JK).
Penentuan Jarak Karakter Pemain dengan Karakter Bukan Pemain yang Harus Mengikuti Pemain pada Pengembangan Game Simulasi Mitigasi Bencana Erupsi Gunung Widowati, Henny; Widhowati, Rachma Putri; Puspitodjati, Sulistyo; Pardede, D.L. Crispina
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 7 No 2: April 2020
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jtiik.2020702633

Abstract

Game simulasi sering melibatkan karakter pemain (player character) dan karakter bukan pemain (non player character) (KBP/NPC), sebagaimana pada game simulasi mitigasi bencana erupsi gunung yang sedang dikembangkan. Salah satu bentuk interaksi antara karakter pemain dengan KBP adalah KBP harus mengikuti karakter pemain. Pemrograman agar KBP mengikuti pemain, perlu menentukan jarak sejauh apa sehingga KBP secara otomatis mengikuti pemain. Penentuan jarak antara karakter pemain dengan KBP  menjadi bahasan dalam makalah ini. Jarak dihitung secara matematis menggunakan konsep pitagoras, dan dengan pertimbangan estetika visual. Salah satu unsur visual yang dipertimbangkan adalah bentuk, baik KBP maupun bentuk karakter pemain. Jarak yang merupakan hasil perhitungan digunakan sebagai batasan untuk menganimasi (menggerakkan) KBP mengikuti karakter pemain. Animasi KBP, yaitu karakter berupa sapi dan manusia mengikuti pemain adalah bagian dari pengembangan game simulasi mitigasi bencana erupsi gunung berapi. Pengujian dengan membuat karakter pemain dan collider yang ada pada KBP bertumbukan atau bersentuhan berhasil membuat KBP bisa mengikuti karakter pemain sesuai dengan jarak yang ditentukan, dan berhasil mencapai tujuan. AbstractSimulation games often involve player characters and non-player characters (NPC), as in the mountain eruption disaster mitigation simulation game developed. One form of interaction between player characters and NPC is that NPC must follow the player character. Programming so that NPC follows players requires determining the distance so that NPC automatically follows the player. Determination of the distance between player characters (players) and non-player character objects (NPC) is discussed in this paper. The distance is measured mathematically using the pythagorean concept and visual aesthetics consideration. One visual element considered is the shape, both NPC and the player's own shape. The resulting distance is used as boundary to animate (move) NPC following the player's character. NPC's animation: the character of cows and humans following players is part of the development of mitigation simulation games for volcanic eruptions. The test, by making the player character and the collider on the NPC collide,  succeeded in making the NPC follows the player character according to the specified distance, and succeeded in achieving the goal.
Co-Authors Achmad Benny Mutiara Aris Gunaryati, Aris Benny Rushadi D. L. Crispina Pardede D. Lucia Crispina Pardede Ernastuti Ernastuti Henny Widowati Henny Widowati Farida Widhowati, Rachma Putri