Claim Missing Document
Check
Articles

Found 7 Documents
Search

Saran Aksi Saham Dengan Pendekatan Fundamental Dan Teknikal Menggunakan Metode Learning Vector Quantization Neural Network Inggrayana, I Made Gery; Widodo, Wahyu; Hermanto, Luky Agus
INTEGER: Journal of Information Technology Vol 1, No 2 (2016): September 2016
Publisher : Fakultas Teknologi Informasi Institut Teknologi Adhi Tama Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (618.66 KB) | DOI: 10.31284/j.integer.2016.v1i2.60

Abstract

Stock is one instrument that is traded in the capital market. Investment in the form of shares can also offer enormous profit, even though it is highly risky in the investment especially on weekly stock trade.; Based on this reason, a system is developed to help take action in transactions whether to buy, sell or hold the stock. This analysis system uses technical and fundamental approach by applying Learning Vector Quantization (LVQ). This research uses five inputs taken from technical analysis, namely: Open Price, High Price, Low Price, Close Price, and Volume. One more input from the fundamental approach is Last Price. This system test indicated 72% accuracy on the transaction actions.
Klasifikasi Kualitas Pisau Potong Tembakau (CUT CELL) Menggunakan Metode Radial Basis Function (RBF) Apriyanto, Fungki; Sujono, Hari Agus; Hermanto, Luky Agus
INTEGER: Journal of Information Technology Vol 1, No 2 (2016): September 2016
Publisher : Fakultas Teknologi Informasi Institut Teknologi Adhi Tama Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (548.559 KB) | DOI: 10.31284/j.integer.2016.v1i2.62

Abstract

Indonesia is one of countries that produces several types of tobacco. Almost 80% tobacco produces is used of cigarette industry. Tobacco leaves slicing into small cuts is one of the process of cigarette production. The cutting process of tobacco requires Cut Cell which is able to cut tobacco into small pieces. Contol is required in the process of making cut cell to set the quality of the blade. The quality control often has problem in determining the Cut Cell quality. The problem is the length of time needed in determining the quality. In this fast paced era, the Quality Control is demanded to be able to determine the cut cell quality quickly and accurately. To support this need from the Quality Control, a system that can be used to determine the cut cell quality which has fast output result. The research process is started with collecting the system needs, followed by system designing, then system making, and system test. The system designing is initiated by preparing the test data and training data which are going to be used for the making and testing of the system. RADIAL BASIS FUNCTION consist of several calculation processes. The first  process is the process of center search of each variable using K-MEANS method. Aftar the center is found, the deviation standard of each variable is calculated. The second process is setting the GAUSSIAN matrix of every group found. The third process is the process of new weight and bias values search by doing pseudo-inverse GAUSSIAN matrix multiplication. The forth process is classification in which this process sets out the classication result by multiplying the value of GAUSSIAN matrix and new weight and bias applying network output formula. The experiment done to 75 experiment data which are compared to manual data as the reference result 12 different data, thus it can be concluded that the accuracy level of this system is 84 %.
Prakiraan Tinggi Gelombang Air Laut Menggunakan Data Mining Hermanto, Luky Agus
Jurnal IPTEK Vol 22, No 1 (2018)
Publisher : LPPM Institut Teknologi Adhi Tama Surabaya (ITATS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (754.731 KB) | DOI: 10.31284/j.iptek.2018.v22i1.232

Abstract

Melakukan prakiraan cuaca memerlukan banyak komponen data cuaca, record dalam jumlah yang besar, serta kemampuan pelaku prakiraan. Keadaan ini mengakibatkan keakuratan dan kecepatan prakiraan menjadi kurang terpenuhi ketika kesimpulan diambil. Untuk mengatasi masalah tersebut, dilakukan penelitian pemodelan prediksi menggunakan teknik yang ada dalam konsep penambangan data, association rule, klasifikasi, serta Random Forest. Penelitian ini menggunakan data dari stasiun pengamatan maritim Cilacap mulai Agustus 2012 sampai dengan Agustus 2016. Data tersebut terdiri atas tanggal, waktu, kecepatan angin, arah angin, arah arus, kecepatan arus, arah gelombang, dan kecepatan gelombang. Data pengujian adalah sebagian data yang diambil secara acak dari keseluruhan data yang digunakan. Dari pengujian model, didapatkan bahwa Association Rule menghasilkan akurasi 79%, sedangkan Classification Tree menghasilkan akurasi 88%.
Aplikasi Findgo-ITATS Berbasis Android Dengan Algoritma SURF Untuk Menampilkan Informasi Lokasi Di ITATS Hapsari, Rinci Kembang; Sulaiman, Nur; Hermanto, Luky Agus
INTEGER: Journal of Information Technology Vol 1, No 1 (2016): Maret 2016
Publisher : Fakultas Teknologi Informasi Institut Teknologi Adhi Tama Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (469.141 KB) | DOI: 10.31284/j.integer.2016.v1i1.57

Abstract

Institut Teknologi Adhi Tama Surabaya (ITATS) is an institute that has relatively wide territory and complicated building arrangement for outsiders especially related to identification of buildings that they want to visit. To overcome this problem, an android based application that can be used to gain information related to those buildings, locations of places or important places in real-time is required. Augmented Reality (AR) is the appropriate technology to display environment and locations information at ITATS in real-time. The implementation of Augmented Reality technology on android based smartphones using Speeded Up Robust Features (SURF) can identify pictures continuously and has proper identification speed. Speeded Up Robust Features (SURF) is an algorithm that has been commonly applied in correspondence matching because it is faster than Scale Invariant Feature Transform (SIFT) and has appropriate and accurate performance maintenance. In designing this application, there are three main stages that should be considered, namely: initialization, tracking marker, and object rendering. Initialization is the stage where images that becomes the database is preliminary processed with Speeded Up Robust Features (SURF) algorithm and  the preparation of the displayed information on the users’ smartphones. The second is tracking marker, smartphone camera takes pictures continuously while processing every inputted image applying Speeded Up Robust Features (SURF) and conducting matching process of images in the database. The final stage, after a match is found, this application displays the text information which corresponds with the matching result. The reliability of this system in recognizing locations at ITATS is 81.66% and average time required is 2.333 seconds.
Ant Colony Optimization Pada Klasifikasi Mangga Gadung Dan Mangga Manalagi Liantoni, Febri; Hermanto, Luky Agus
Prosiding Seminar Nasional Sains dan Teknologi Terapan Peningkatan Teknologi Terapan di Industri dan Infrastruktur untuk Kemajuan Bangsa
Publisher : Institut Teknologi Adhi Tama Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (383.951 KB)

Abstract

Examples of types of mango that can be used for food is mango gadung and mango manalagi. In this study taken the topic of the classification of mango gadung and mango manalagi. The process of introduction of mango leaves of gadung and mango manalagi is done based on image edge detection of mango leaf structure. In the process of edge detection is used ant colony optimization (ACO) method that replaces conventional detection. Application of ant colony optimization method successfully optimizes the result of edge detection of a mango leaf bone structure. This is demonstrated by the detection of bony edges of leaf bone structure and more detail than using Roberts or Sobel edge detection. The result of classification test using k-nearest neighbor method got 67,5% accuracy.
EVALUASI SKENARIO KOORDINASI SUPPLY CHAIN UNTUK MODEL PRICING DAN KEPUTUSAN ORDER/DELIVERY Yuliawati, Evi; Hermanto, Luky Agus
Jurnal Teknologi Vol 7 No 2 (2014): Jurnal Teknologi
Publisher : Jurnal Teknologi, Fakultas Teknologi Industri, Institut Sains & Teknologi AKPRIND Yogyakarta

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

Abstract

Model pricing dan keputusan order/delivery merupakan model yang menggabungkan aktivitas penentuan harga (pricing) dan penentuan jumlah unit produk yang harus di order dan delivery. Model gabungan ini akan memaksimalkan keuntungan yang diperoleh oleh supply chain, yaitu melalui peningkatan pendapatan dan meminimalkan biaya yang terlibat seperti biaya pembelian, biaya pemesanan dan biaya handling. Pada penelitian ini akan dikembangkan model matematik pada 2 (dua) skenario yang berbeda, yang menggambarkan karakteristik sistem pada sebuah ritel modern di Surabaya. Pada skenario pertama adalah implementasi model pricing dan keputusan order/delivery pada supply chain ritel modern tanpa koordinasi, dimana pelaku bisnis yang terlibat yaitu DC-Ritel dan Distributor, akan menetapkan keuntungannya masing-masing tanpa mempedulikan keuntungan supply chain secara keseluruhan. Sedangkan pada skenario yang kedua akan dihitung keuntungan model pada skema koordinasi supply chain, yaitu koordinasi antara DC-Ritel-Distributor. Evaluasi model pricing dan keputusan order/delivery dilakukan pada dua skenario tersebut. Nilai-nilai yang digunakan sebagai parameter model diukur dari dua skenario untuk melihat besarnya pendapatan dan biaya-biaya yang dibutuhkan. Dengan menggunakan parameter sebagai ukuran kuantitatif model, skenario koordinasi supply chain dapat menghasilkan keuntungan yang lebih besar dibandingkan dengan skenario tanpa koordinasi.
Pengembangan Metode Ant Colony Optimization Pada Klasifikasi Tanaman Mangga Menggunakan K-Nearest Neighbor Liantoni, Febri; Hermanto, Luky Agus
Jurnal Buana Informatika Vol 8, No 4 (2017): Jurnal Buana Informatika Volume 8 Nomor 4 Oktober 2017
Publisher : Universitas Atma Jaya Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (345.249 KB) | DOI: 10.24002/jbi.v8i4.1443

Abstract

Abstract. Leaf is one important part of a plant normally used to classify the types of plants. The introduction process of mango leaves of mangung and manalagi mango is done based on the leaf edge image detection. In this research the conventional edge detection process was replaced by ant colony optimization method. It is aimed to optimize the result of edge detection of mango leaf midrib and veins image. The application of ant colony optimization method successfully optimizes the result of edge detection of a mango leaf midrib and veins structure. This is demonstrated by the detection of bony edges of the leaf structure which is thicker and more detailed than using a conventional edge detection. Classification testing using k-nearest neighbor method obtained 66.67% accuracy.Keywords: edge detection, ant colony optimization, classification, k-nearest neighbor.Abstrak. Pengembangan Metode Ant Colony Optimization Pada Klasifikasi Tanaman Mangga Menggunakan K-Nearest Neighbor. Daun merupakan salah satu bagian penting dari tanaman yang biasanya digunakan untuk proses klasifikasi jenis tanaman. Proses pengenalan daun mangga gadung dan mangga manalagi dilakukan berdasarkan deteksi tepi citra struktur tulang daun. Pada penelitian ini proses deteksi tepi konvensional digantikan dengan metode ant colony optimization. Hal ini bertujuan untuk optimasi hasil deteksi tepi citra tulang daun mangga. Penerapan metode ant colony optimization berhasil mengoptimalkan hasil deteksi tepi struktur tulang daun mangga. Hal ini ditunjukkan berdasarkan dari hasil deteksi tepi citra struktur tulang daun yang lebih tebal dan lebih detail dibandingkan menggunakan deteksi tepi konvensional. Pengujian klasifikasi dengan metode k-nearest neighbor didapatkan nilai akurasi sebesar 66,67%.Kata Kunci: deteksi tepi, ant colony optimization, klasifikasi, k-nearest neighbor.