Garuda - Garba Rujukan Digital

Klasifikasi Usia Berdasarkan Citra Wajah Menggunakan Algoritma Artificial Neural Network dan Gabor Filter Sudirman Melangi
Jambura Journal of Electrical and Electronics Engineering Vol 2, No 2 (2020): Juli - Desember 2020
Publisher : Teknik Elektro - Universitas Negeri Gorontalo

Pengklasifikasian kelompok usia dibangun berdasarkan ciri-ciri dari fitur wajah. klasifikasi usia berdasarkan citra wajah perlu dilakukan dengan lebih akurat agar dapat berguna dalam sistem pengenalan usia manusia. Beberapa kesulitan dalam pengenalan wajah yang sering muncul karena variabilitas wajah seperti ekspresi, penuaan, variasi kumis dan sebagainya. Metode filter gabor dikenal sebagai detektor ciri yang sukses serta memiliki kemampuan mengeliminasi parameter variabilitas wajah yang pada metode lainnya sering menggangggu dalam proses pengenalan. Dengan menggunakan metode Gabor filter yang terbukti handal digunakan untuk memecahkan masalah agar pengenalan usia berdasarkan wajah dapat dilakukan dengan lebih akurat. Hasil penelitian menunjukkan bahwa penerapan metode Gabor Filter dan Artificial Neural Network pada masalah pengenalan usia berdasarkan citra wajah berhasil mendapatkan akurasi yaitu sebesar 83% dengan menggunakan pengujian Confusion Matrix. Dengan demikian penerapan metode Gabor Filter dan Artificial Neural Network pada masalah pengenalan usia berdasarkan citra wajah cukup akurat, dan dapat diimplementasikan. Kata kunci: Klasifikasi Usia, Wajah, ANN, Gabor Filter. Classification of age groups is built on the characteristics of facial features. Age classifications based on facial images need to be done more accurately in order to be useful in the human age recognition system. Some difficulties in facial recognition that often arise due to facial variability such as expression, aging, mustache variations and so on. Gabor filter method is known as a successful feature detector and has the ability to eliminate facial variability parameters which in other methods often interfere in the recognition process. By using the Gabor filter method which is proven to be reliable it is used to solve problems so that face recognition based on faces can be done more accurately. The results showed that the application of the Gabor Filter and Artificial Neural Network method on the problem of age recognition based on face images managed to get an accuracy of 83% using the Confusion Matrix test. Thus the application of the Gabor Filter and Artificial Neural Network method to the problem of age recognition based on face images is quite accurate, and can be implemented.Keywords: Age Classification, Face, ANN, Gabor Filter

Sistem Monitoring Informasi Kualitas dan Kekeruhan Air Tambak Berbasis Internet of Things Sudirman Melangi; Muhammad Asri; Stephan Adriansyah Hulukati
Jambura Journal of Electrical and Electronics Engineering Vol 4, No 1 (2022): Januari - Juni 2022
Publisher : Teknik Elektro - Universitas Negeri Gorontalo

Terjadinya perubahan keadaan air tambak yang tidak dapat diprediksi, yang disebabkan oleh suhu, kandungan atau unsur-unsur yang terlarut dalam air tambak dapat mempengaruhi mutu dari hasil budidaya tambak, dan petani tidak dapat memantau terus-menerus perubahan keadaan air tambak mereka secara langsung, maka dibuatlah penelitian ini dengan tujuan membuat sistem monitoring untuk menginformasikan kualitas dan kekeruhan air pada tambak dengan konsep Internet of Things (IoT) dengan menampilkan secara realtime nilai kualitas dan kekeruhan air menggunakan Smartphone. Obyek pengujian berasal dari dua sampel air tambak yang berbeda dan satu air sumur sebagai pembanding. Metode pada sistem monitoring menggunakan dua sensor agar lebih akurat dalam melihat kondisi air tambak, sensor TDS meter untuk mendeteksi kualitas air dan sensor SEN0189 untuk mendeteksi kekeruhan air, kemudian data sensor dikirim menggunakan konsep IoT dimana mikrokontroler NodeMCU sebagai penerima data sensor bertindak sebagai pengirim informasi keadaan air secara online ke Smartphone menggunakan aplikasi Blynk. Dari hasil pengujian sistem monitoring pada aplikasi Blynk dapat menampilkan grafik dari data kualitas air dalam satuan ppm dan data kekeruhan air dalam satuan mg/l, rata-rata sensor mendapatkan data untuk kedua sampel air tambak dengan nilai yang tinggi, sedangkan sampel air sumur lebih rendah.Unpredictable changes in pond water conditions caused by temperature, content, or dissolved elements in pond water can affect the quality of freshwater aquaculture. As farmers are not able to continuously monitor changes in the state of their pond water directly, this study was made with the aim of creating a monitoring system to inform pond water quality and turbidity with the Internet of Things (IoT) concept, by displaying in real-time the quality and turbidity values using a smartphone. The objects of the test were taken from two different pond water samples and one well water for comparison. The method used in the monitoring system is two sensors, in order to increase the accuracy in observing the condition of pond water, where the TDS meter sensor was used to detect water quality, and the SEN0189 sensor was to detect water turbidity. The sensor data was sent using the IoT concept, where the NodeMCU microcontroller as the sensor data receiver sends information on the condition of the water to the Smartphone using the Blynk application. The results of the monitoring system test on the Blynk application can display the graph of water quality data in ppm units and water turbidity data in mg/l units, where the average sensor receives data for both pond water samples with high values, while well water samples are lower.

Text To Speech Bahasa Indonesia Menggunakan Synthesizer Concatenation Berbasis Fonem Sudirman Melangi
Jurnal Cosphi Vol 2, No 2 (2018): Agustus-Desember 2018
Publisher : Teknik Elektro - Universitas Ichsan Gorontalo

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (320.214 KB)

Penelitian tentang text-to-speech (TTS) telah dilakukan untuk berbagai bahasa dan untuk beberapa bahasa, hasilnya sangat memuaskan. Namun, beberapa masalah spesifik dalam pengembangan aplikasi TTS belum sepenuhnya terpecahkan. Semua pendekatan yang diusulkan perlu menciptakan sistem TTS yang memiliki kejelasan dan kealamian. Karena alat/platform saat ini tersedia untuk penerapan TTS, sistem yang dapat mengurangi penggunaan memori dan memasukkan kesederhanaan dalam prosesnya diperlukan. Sistem synthesizer gabungan telah terbukti menghasilkan hasil yang memuaskan dalam berbagai bahasa. Dalam penelitian ini, penggabungan synthesizer digunakan dengan kombinasi pendekatan baru yang menggunakan basis data ujaran fonem dasar. Phoneme adalah unit terkecil dalam sebuah ucapan. Penggunaan fonem dapat diharapkan menghasilkan penggunaan memori yang rendah dan proses yang cepat. Selanjutnya, ini masih bisa diharapkan menghasilkan ucapan bahasa Indonesia yang baik. Berdasarkan pengujian dari 45 responden untuk kriteria penilaian intelligibility didapatkan uji MOS = 3,66, penilaian fluidity dengan uji MOS = 3,66 dan naturalness dengan uji MOS = 3,57. Kata kunci: Text-to-Speech, Phoneme, NLP, Synthesizer

Penerapan Algoritma Naïve Bayes Berbasis Backward Elimination Untuk Prediksi Pemesanan Kamar Hotel Haditsah Annur; Sudirman Melangi
Jurnal Ilmiah Ilmu Komputer Banthayo Lo Komputer Vol 1 No 1 (2022): Edisi Mei 2022
Publisher : Teknik Informatika Fakultas Ilmu Komputer Universitas Ichsan Gorontalo

Abstract— Hotel is one of the business entities that have the potential to grow and develop which requires a lot of investment that stands both in the middle of the city and in tourist destination areas. Hotel room reservations can be made by customers before they use the hotel via online media, but the problem that occurs is that customers who have made room bookings can cancel orders for various reasons, so that hoteliers feel a loss because the cancellation can provide opportunities for designers to get these customers. This study uses the Naïve Bayes Algorithm as an algorithm that can produce high accuracy and can process a lot of data, and backward selection as the selection of suitable parameter values to improve accuracy. This study uses 10,000 hotel room customer data with accuracy results using the Naïve Bayes Algorithm of 89.67%, and accuracy results using the Naïve Bayes Algorithm and Backward Elemination Feature Selection of 97.83%. Prediction Results Check-Out, Canceled and No-Show.Keywords: Prediction, Booking Room Hotel, Naïve Bayes, Backward Elemination.

Implementasi Augmented Reality sebagai Pengenalan Benda Bersejarah di Museum Purbakala Popa Eyato Gorontalo Menggunakan Metode Marker Based Tracking Sukayasa, I Nengah; Nasrullah, Asmaul Husnah; Melangi, Sudirman
Jurnal Ilmiah Ilmu Komputer Banthayo Lo Komputer Vol 2 No 2 (2023): November 2023
Publisher : Teknik Informatika Fakultas Ilmu Komputer Universitas Ichsan Gorontalo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37195/balok.v2i2.639

Abstract ; Augmented Reality is a technology that combines 2 or 3--dimensional objects into images on markers and then projects 3D objects directly. AR is very useful as a tourist data media to attract the attention of tourists both domestic and foreign tourists. It also shares different experiences and guidance in mastering each place or tourist attraction visited. In making this application, the unity3D is used by applying the Marker Based Tracking method. This marker method is to detect markers in Augmented Reality applications so that they can display 3D visualizations of historical objects in the Popa Eyato Gorontalo ancient museum. The utilization of Augmented Reality technology in this recognition system can provide an overview of historical objects in the Popa Eyato Gorontalo ancient museum to increase its attractiveness to the public to get to know historical objects in the Popa Eyato Gorontalo ancient museum. Keywords: augmented reality, android, marker-based tracking, Vuforia

Penerapan Metode Regresi Linier Sederhana Untuk Prediksi Jumlah Persediaan Pestisida Annur, Haditsah; Sudirman Melangi; Andri Setiawan
Jurnal Ilmiah Ilmu Komputer Banthayo Lo Komputer Vol 3 No 1 (2024): Mei 2024
Publisher : Teknik Informatika Fakultas Ilmu Komputer Universitas Ichsan Gorontalo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37195/balok.v3i1.863

Abstract - Forecasting is needed to make things easier for CV. Anak Tani predict how much Roger's pesticide supply will be needed in the following month, so that they do not experience the delivery of the amount of Roger's pesticide supply in the following month. The simple linear regression method is a forecasting method that uses two factors so that it can determine maximum results. The problem faced is that there is often a buildup of pesticide 1 liter Roger 480SL inventory CV. Anak Tani. The aim is to find out the results of applying a simple linear regression method to predict the amount of inventory of 1 Liter Roger 480SL pesticide located at CV. Anak Tani. The results obtained by the mean absoluter percentage error (MAPE) were tested with the 2022 data obtained, namely 7.80%, so it can be concluded that this system is effective to use.Key words: Forecasting, Inventory, Pesticide Roger 480sl 1 Liter, Mape

Title

Found 6 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 6 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 6 Documents
Search