Garuda - Garba Rujukan Digital

PENGENDALI POINTER DENGAN GAZE TRACKING MENGGUNAKAN METODE HAAR CLASSIFIER SEBAGAI ALAT BANTU PRESENTASI (EYE POINTER) Satriyanto, Edi; Ardilla, Fernando; Agustriany Lubis, Risa Indah
Jurnal Matematika Sains dan Teknologi Vol 11 No 2 (2010)
Publisher : LPPM Universitas Terbuka

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

The application that builded in this research is a pointer controller using eye movement (eye pointer). This application is one of image processing applications, where the users just have to move their eye to control the computer pointer. This eye pointer is expected able to assist the usage of manual pointer during the presentation. Since the title of this research is using gaze tracking that follow the eye movement, so that is important to detect the center of the pupil. To track the gaze, it is necessary to detect the center of the pupil if the eye image is from the input camera. The gaze tracking is detected using the three-step hierarchy system. First, motion detection, object (eye) detection, and then pupil detection. For motion detection, the used method is identify the movement by dynamic compare the pixel ago by current pixel at t time. The eye region is detected using the Haar-Like Feature Classifier, where the sistem must be trained first to get the cascade classifier that allow the sistem to detect the object in each frame that captured by camera. The center of pupil is detect using integral projection.The final step is mapping the position of center of pupil to the screen of monitor using comparison scale between eye resolution with screen resolution. When detecting the eye gaze on the screen, the information (the distance and angle between eyes and a screen) is necessary to compute pointing coordinates on the screen. In this research, the accuracy of this application is equal to 80% at eye movement with speed 1-2 second. And the optimum mean value is between 5 and 10. The optimum distance of user and the webcam is 40 cm from webcam.

VIRTUAL POINTER UNTUK IDENTIFIKASI ISYARAT TANGAN SEBAGAI PENGENDALI GERAKAN ROBOT SECARA REAL-TIME Irawan, M. Isa; Satriyanto, Edi
Jurnal Informatika Vol 9, No 1 (2008): MAY 2008
Publisher : Institute of Research and Community Outreach - Petra Christian University

Many previous researches have been done in relation to human-robot interface, which is an interaction between human and robot using hand gesture. Hand gesture that is used in this research is a moving hand gesture with pointing position. The most important factor to identify hand gesture is the ability to differentiate hands with other objects based on the skin colour. A method to detect hand skin colour is using Fuzzy C-Means (FCM) which can refine a cluster centre and the membership value of each data iteratively by minimizing objective function. Hence, the cluster centre moves to the correct location. Recognition result with moving detection method was able to detect the movement of a moving object 91.07944% in 1 second. Skin detection using FCM was able to segment skin colour and not the skin in real time with the successful rate 90.2834%. The successful rate of the hand gesture pattern identification using rule base is 86.67%. The successful rate of virtual hand writing using LVQ artificial neural network as a command for controlling a robot is 79.2%. Abstract in Bahasa Indonesia : Banyak penelitian sebelumnya berrhubungan dengan human robot interface, interaksi manusia dengan robot menggunakan isyarat tangan sebagai bahasa tubuh manusia. Isyarat tangan yang digunakan dalam penelitian ini adalah isyarat tangan bergerak yang berposisi menunjuk untuk identifikasi isyarat tangan, faktor yang paling penting adalah kemampuan membedakan tangan dengan obyek lain berdasarkan warna kulitnya. Metode untuk mendeteksi warna kulit tangan adalah Fuzzy C-Means (FCM) yang memiliki kemampuan memperbaiki pusat cluster dan nilai keanggotaan tiap data secara berulang dengan meminimumkan fungsi obyektif, sehingga pusat cluster akan bergerak menuju lokasi yang tepat. Hasil pengenalan dengan metode moving detection, mampu mendeteksi pergerakan obyek bergerak. secara baik sebesar 91.07944% dalam 1 detik. obyek Skin detection dengan Fuzzy C-Means (FCM) mampu melakukan segmentasi warna kulit dan bukan kulit secara real-time dengan tingkat keberhasilan. 90.2834% Identifikasi pola isyarat tangan dengan rule base tingkat keberhasilannya 86.67%. Identifikasi hasil virtual hand writing menggunakan jaringan syaraf tiruan metode LVQ sebagai perintah untuk mengendalikan robot tingkat keberhasilannya mencapai 79.2%. Kata Kunci : virtual pointer , Fuzzy C-Mean (FCM), jaringan syaraf tiruan LVQ

PENGENDALI POINTER DENGAN GAZE TRACKING MENGGUNAKAN METODE HAAR CLASSIFIER SEBAGAI ALAT BANTU PRESENTASI (EYE POINTER) Edi Satriyanto; Fernando Ardilla; Risa Indah Agustriany Lubis
Jurnal Matematika Sains dan Teknologi Vol. 11 No. 2 (2010)
Publisher : LPPM Universitas Terbuka

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1479.979 KB)

The application that builded in this research is a pointer controller using eye movement (eye pointer). This application is one of image processing applications, where the users just have to move their eye to control the computer pointer. This eye pointer is expected able to assist the usage of manual pointer during the presentation. Since the title of this research is using gaze tracking that follow the eye movement, so that is important to detect the center of the pupil. To track the gaze, it is necessary to detect the center of the pupil if the eye image is from the input camera. The gaze tracking is detected using the three-step hierarchy system. First, motion detection, object (eye) detection, and then pupil detection. For motion detection, the used method is identify the movement by dynamic compare the pixel ago by current pixel at t time. The eye region is detected using the Haar-Like Feature Classifier, where the sistem must be trained first to get the cascade classifier that allow the sistem to detect the object in each frame that captured by camera. The center of pupil is detect using integral projection.The final step is mapping the position of center of pupil to the screen of monitor using comparison scale between eye resolution with screen resolution. When detecting the eye gaze on the screen, the information (the distance and angle between eyes and a screen) is necessary to compute pointing coordinates on the screen. In this research, the accuracy of this application is equal to 80% at eye movement with speed 1-2 second. And the optimum mean value is between 5 and 10. The optimum distance of user and the webcam is 40 cm from webcam.

Aplikasi Analisis Manajemen Resiko Untuk Membantu Pengambilan Keputusan Menggunakan Metode Decision Table Berbasis Web (Studi Kasus SMKN 1 Jenangan Ponorogo) Dihin Muriyatmoko; Edi Satriyanto; Eru Puspita
Fountain of Informatics Journal Vol 1, No 2 (2016): November
Publisher : Universitas Darussalam Gontor

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21111/fij.v1i2.671

Decision making by considering is very important in an institution. Generally, in choosing a solution of the problem is only take from a meeting, discussion or vote among the leader of each division. But it usually needs more time if the problems are the repetitive and less measurable, then it takes an application so that decision-making to be effective, efficient, systematic and measurable. This application use decision table method to classifies each risk by considering the scale of likelihood and consequence, then of both these parameters will be taken risk management matrix that will determine the best solution. This application not absolutely and only help to give the recommendation with the minimum value, so on each solution and risk have a value and the test results of the respondents indicated that the application is able to assist institutions in decision-making as much as 50 percent.

APPLICATION OF MULTISTAGE CLUSTERING FOR MAPPING ECONOMIC POTENTIAL IN EAST JAVA PROVINCE Ronny Susetyoko; Edi Satriyanto; Alfi Fadliana; Muhammad Syahfitra
Jurnal Ilmiah Kursor Vol 12 No 1 (2023)
Publisher : Universitas Trunojoyo Madura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21107/kursor.v12i01.325

This study aims to map the economic potential in East Java Province based on GRDP according to business field category. Multistage clustering is a method developed for outlier data and datasets with large variance. Multistage clustering is a combination of Ordering Points to Identify the Clustering Structure (OPTICS) and K-Means. The first stage was grouped using OPTICS. The outlier data resulting from the clustering stage is used as a dataset in the second stage using K-Means. The performance of this method is compared with several other methods, namely: K-Means, DBSCAN – K-Means, Agglomerative, Fuzzy C-Means (FCM), Possibilistic C-Means (PCM), and Fuzzy Possibilistic C-Means (FPCM) based on the characteristics of the Silhouette score and Davies-Bouldin score. Multistage clustering was chosen as the best method with a Silhouette score of 0.442 and Davies-Bouldin score of 0.388. With the Elbow method and the two metrics, the optimum number of clusters is 8 clusters. The results of this mapping method, the City of Surabaya forms a separate cluster which has the highest economic potential in 15 categories of business fields. Next Gresik, Pasuruan, Sidoarjo, and Probolinggo have the second highest economic potential with 10 categories of business fields ranking in the top 3.

Improved Fuzzy Possibilistic C-Means using Artificial Bee Colony for Clustering New Student’s Financial Capability to Determine Tuition Level Satriyanto, Edi; Surya Wardhani, Ni Wayan; Anam, Syaiful; Mahmudy, Wayan Firdaus
JOIV : International Journal on Informatics Visualization Vol 8, No 4 (2024)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.8.4.3087

Outliers in the dataset will affect the quality of the cluster, so a good clustering method is needed. Based on the Mahalanobis distance method, it is known that the research dataset has outliers. Clustering methods that are often used for this type of data are Fuzzy C-means (FCM), Possibilistic C-means (PCM), and Fuzzy Possibilistic C-means (FPCM). This study aims to develop a clustering method that is more robust to outliers by using the Artificial Bee Colony (ABC) algorithm to minimize the objective function of FPCM. This study produces a new algorithm called Artificial Bee Colony Fuzzy Possibilistic C-Means (ABCFPCM) so that the resulting clusters are not easily trapped in the local optimum. This study also provides cluster centroid initialization using K-Means++ to improve cluster quality. ABCFPCM performs best because it significantly increases the Silhouette value and the Between Sum Squares (BSS) and Total Sum Squares (TSS) ratio. ABCFPCM performance provides the best cluster quality of 72.16% based on the BSS/TSS ratio, FPCM of 70.71%, and FCM K-Means++ of 68.14%. K-Means++ in the cluster method does not affect cluster performance except for FCM, where cluster quality is slightly increased. The centroid results of 8 clusters as the best performance of ABCFPCM are used to determine the tuition rate level. The impact of this study is to improve the quality of FPCM performance because it is no longer trapped in a local optimum at the cluster centroid.

Perbandingan Kinerja ARIMAX dan Fuzzy Time Series Multi Factor pada Peramalan Data Nilai Tukar USD Tsabita, Rania Hana; Susetyoko, Ronny; Satriyanto, Edi
Jurnal Infomedia: Teknik Informatika, Multimedia, dan Jaringan Vol 10, No 1 (2025): Jurnal Infomedia
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jim.v10i1.6865

Penelitian ini membandingkan metode ARIMAX dan Fuzzy Time Series Multi Factor dalam meramalkan nilai tukar USD untuk mendukung pencapaian SDG 8. Data yang digunakan mencakup nilai tukar USD, inflasi, dan ekspor migas Indonesia selama periode 2019–2024, dengan enam variasi panjang data pelatihan. Evaluasi kinerja model dilakukan menggunakan metrik Mean Absolute Percentage Error (MAPE). Hasil penelitian menunjukkan bahwa metode ARIMAX With Dummy menghasilkan akurasi terbaik dengan nilai MAPE terendah sebesar 2,32% pada rasio data latih dan uji 60:9. Model ini juga menunjukkan pengaruh signifikan dari panjang data terhadap akurasi prediksi. Hasil menunjukkan bahwa model ini paling optimal dan signifikan dalam meningkatkan akurasi peramalan indikator ekonomi.

Implementasi Aplikasi Chatbot Informasi Pelayanan Kelurahan Keputih, Surabaya Edelani, Renovita; Satriyanto, Edi; Nadhori, Isbat Uzzin; Susetyoko, Ronny; Barakbah, Aliridho; Karlita, Tita; Muliawati, Tri Hadiah; Fadliana, Alfi; Maulana, Wahyu Ikbal; Insani, Fawzan; Fauzi Nafi'Ubadah, Kriza; Haikal Yuniarta Krisgianto, Ricko; Saputra, Muhammad Krisnanda Vilovan; Ridho, Bistiana Syafina; Ni'Ma, Najma Akmalina; Damayanti, Anita; Febrianto, Ardiansyah Indra; Alde, Muhammad Riski
El-Mujtama: Jurnal Pengabdian Masyarakat Vol. 5 No. 2 (2025): El-Mujtama: Jurnal Pengabdian Masyarakat
Publisher : Intitut Agama Islam Nasional Laa Roiba Bogor

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47467/elmujtama.v5i2.6272

In today's era of digital transformation, the government, particularly Kelurahan Keputih, is aware of the community's need for information regarding the management of kependudukan and non-kependudukan documents. Given their busy lifestyles, residents require a medium to access information related to these matters. This service information is needed to improve bureaucratic efficiency, accelerate information access, and reduce the burden of manual administrative work. Therefore, researchers have developed an AI-based Intelligent Chatbot application using Large Language Modeling (LLM) technology to assist both employees and residents of Kelurahan Keputih in obtaining information related to the management of kependudukan and non-kependudukan services. The implementation of this Chatbot utilizes the Hugging Face library and the LangChain model, one of the Llama models developed by Meta. This Kelurahan Keputih Service Information Chatbot application is named "BambuBot". This application benefits the residents of Keputih by providing them with interactive, comprehensive, and easily accessible information regarding services for managing kependudukan and non-kependudukan documents, as well as platforms for processing these documents.

PANEL DATA REGRESSION MODEL FOR PREDICTING ECONOMIC GROWTH BEFORE AND DURING THE COVID-19 PANDEMIC IN EAST JAVA PROVINCE Susetyoko, Ronny; Satriyanto, Edi; Fadliana, Alfi; Humaira, Fitrah Maharani
BAREKENG: Jurnal Ilmu Matematika dan Terapan Vol 17 No 4 (2023): BAREKENG: Journal of Mathematics and Its Applications
Publisher : PATTIMURA UNIVERSITY

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30598/barekengvol17iss4pp2121-2134

Gross Regional Domestic Product (GRDP) is one of the key indicators to determine the economic condition of a region in a certain period. GRDP at constant prices has a positive and significant effect on economic growth . This study aims to predict economic growth in East Java before and during the Covid-19 pandemic based on the structural components of regional revenue and expenditure budget realization using panel data regression with data sources from the Directorate General of Fiscal Balance. The results of this study, the best model is the Fixed Effect Model (FEM) with R-Squared 0.99991 and Adj. R-Squared 0.99987. MSE, MAD and MAPE values on the training data are 338724.9919, 259.7182 and 0.6296 respectively. While the MSE, MAD and MAPE values in the testing data are 1716324.2736, 445.7959 and 1.0692 respectively. At the 95% confidence level, Locally Generated Revenue (LGR), Transfers to Regional and Village Funds (TRVF), and Other Revenue (OR) are not significant in the model or have little effect. But at the 99.9% confidence level, all factors (cross section) have a very significant effect. This can be interpreted that local wisdom, or the characteristics of each region/city has a major contribution to economic growth.

Sistem Akuaponik untuk Peternakan Lele dan Tanaman Kangkung Hidroponik Berbasis IoT dan Sistem Inferensi Fuzzy Rozie, Fachrul; Syarif, Iwan; Al Rasyid, Muhammad Udin Harun; Satriyanto, Edi
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 8 No 1: Februari 2021
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jtiik.0814025

Akuaponik adalah penggabungan sistem budidaya akuakultur dan hidroponik yang dapat menjadi solusi untuk mengatasi keterbatasan lahan, keterbatasan sumber air serta meningkatkan ketahanan pangan. Pada sistem akuaponik, kualitas air pada budidaya ikan merupakan salah satu syarat utama dalam keberhasilan proses budidaya. Penelitian ini mengkombinasikan peternakan lele dengan penanaman kangkung hidroponik. Kotoran ikan lele dan sisa makanan terakumulasi di air dan dapat menjadi racun bagi ikan lele karena mengandung kadar anomia yang tinggi sehingga sangat berbahaya jika tidak dibuang. Air ini kemudian dialirkan ke tanaman kangkung hidroponik melalui biofilter yang bermanfaat sebagai pengurai air kotor dari kolam menjadi nitrat dan nitrit yang berguna sebagai nutrisi tanaman. Selanjutnya setelah air menjadi bersih dan mempunyai kadar oksigen yang tinggi, air tersebut dialirkan kembali ke kolam ikan lele. Penelitian ini bertujuan untuk mengembangkan sistem cerdas pada budidaya akuaponik dengan memanfaatkan teknologi Internet of Things yang dilengkapi dengan beberapa jenis sensor untuk memantau dan mengendalikan kualitas air dengan menerapkan algoritma Sistem Inferensi Fuzzy / Fuzzy Inference System (FIS) untuk mengatur kecepatan sirkulasi air kolam agar menghemat daya listrik pada pompa. Peralatan ini juga dilengkapi dengan layanan pemberian pakan ikan secara otomatis yang dapat diprogram sesuai kebutuhan. Sistem akuaponik ini dapat dipantau melalui web maupun ponsel pintar berbasis android. Pengujian yang dilakukan terhadap perbandingan keputusan oleh pakar dan sistem FIS pada kecepatan sirkulasi air sistem akuaponik menunjukkan nilai akurasi 83,33%, dan hasil dari pengujian ketepatan alat pemberi pakan yang dibuat secara otomatis terhadap ketepatan pemberian pakan secara manual memiliki nilai akurasi 90,97%. AbstractAquaponics is a combination of aquaculture and hydroponic cultivation systems that can be a solution to overcoming limited land, limited water sources and increasing food security. In the aquaponics system, water quality in fish farming is one of the main requirements in the success of the cultivation process. This research combines catfish farming with hydroponic kale cultivation. Catfish feces and food scraps accumulate in water and can be toxic to catfish because they contain high levels of anomia so it is very dangerous if not disposed of. This water is then flowed to hydroponic kale plants through a biofilter which is useful as decomposing dirty water from the pond into nitrates and nitrites which are useful as plant nutrients. Furthermore, after the water becomes clean and has high oxygen levels, the water is flowed back into the catfish pond. This study aims to develop a smart system in aquaponic cultivation by utilizing Internet of Things technology which is equipped with several types of sensors to monitor and control water quality by applying the Fuzzy Inference System (FIS) algorithm to regulate the speed of pool water circulation in order to save electric power on the pump. This equipment is also equipped with an automatic fish feeding service which can be programmed as needed. This aquaponics system can be monitored via the web or an Android-based smart phone. Tests carried out on the comparison of decisions by experts and the FIS system on the water circulation speed of the aquaponics system show an accuracy value of 83.33%, and the results of testing the accuracy of the feeder that is made automatically against the accuracy of manual feeding have an accuracy value of 90.97% .

Title

Found 11 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 11 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 11 Documents
Search