Garuda - Garba Rujukan Digital

PENENTUAN TREN MODE JENIS KAYU HUTAN ALAM DENGAN ALGORITMA APRIORI ., Jupriyanto
IKRAITH-INFORMATIKA Vol 1 No 2 (2017): IKRAITH-INFORMATIKA vol 1 Nomor 2 Bulan November 2017
Publisher : Fakultas Teknik Universitas Persada Indonesia YAI

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (217.657 KB)

Subdit Peredaran Hasil Hutan adalah salah satu Subdit di bawah Kementrian Lingkungan Hidup dan Kehutanan yangbertanggung jawab terhadap peredaran hasil hutan yang ada di Indonesia. Subdit akan mencatat transaksi SKSKB (SuratKeterangan Sah Kayu Bulat) / DKB (Daftar Kayu Bulat) dari TPK (Tempat Penampungan Kayu) 1 ke TPK yang lain.Teknik data mining telah di terapkan dalam mengatasi permasalahan yang ada, adalah algoritma apriori untuk mendapatkaninformasi tentang asosiasi antar jenis kayu dari laporan transaksi SKSKB / DKB. Hasil pengolahan akan membantu dalambentuk rekomendasi pemenuhan stok kayu di TPK. Juga akan lebih mudah menempatkan posisi kayu yang menjadi trendalam transaksi SKSKB / DKB, sehingga dapat dengan mudah di lihat dan di jangkau pada saat proses pengangkutan. Hasil pengolahan data mining juga akan membantu dalam hal promosi penjulan kayu dalam hal paket potongan harga. Dari data transaksi SKSKB / DKB yang ada di wilayah Provinsi Kalimantan Timur selama periode bulan April 2017, denganmenggunakan teknik data mining algoritma apriori dapat diambil kesimpulan bahwa data mining dapat diimplementasikandengan menggunakan database SKSKB/DKB karena dapat menemukan kecenderungan pola kombinasi itemsets (jeniskayu), pola kombinasi yang paling tinggi supportnya adalah pola kombinasi pengiriman jenis kayu Meranti Kuning makaakan mengirim jenis kayu Meranti Merah.

COMPARATIVE ANALYSIS OF THE K-NEAREST NEIGHBOR ALGORITHM ON VARIOUS INTRUSION DETECTION DATASETS Andri Agung Riyadi; Fachri Amsury; Irwansyah Saputra; Tiska Pattiasina; Jupriyanto Jupriyanto
Jurnal Riset Informatika Vol 4 No 1 (2021): Period of December 2021
Publisher : Kresnamedia Publisher

Security in computer networks can be vulnerable, this is because we have weaknesses in making security policies, weak computer system configurations, or software bugs. Intrusion detection is a mechanism for securing computer networks by detecting, preventing, and blocking illegal attempts to access confidential information. The IDS mechanism is designed to protect the system and reduce the impact of damage from any attack on a computer network for violating computer security policies including availability, confidentiality, and integrity. Data mining techniques have been used to obtain useful knowledge from the use of IDS datasets. Some IDS datasets that are commonly used are Full KDD, Corrected KDD99, NSL-KDD, 10% KDD, UNSW-NB15, Caida, ADFA Windows, and UNM have been used to get the accuracy rate using the k-Nearest Neighbors algorithm (k-NN). The latest IDS dataset provided by the Canadian Institute of Cybersecurity contains most of the latest attack scenarios named the CICIDS2017 dataset. A preliminary experiment shows that the approach using the k-NN method on the CICIDS2017 dataset successfully produces the highest average value of intrusion detection accuracy than other IDS datasets.

COMPARATIVE ANALYSIS OF THE K-NEAREST NEIGHBOR ALGORITHM ON VARIOUS INTRUSION DETECTION DATASETS Andri Agung Riyadi; Fachri Amsury; Irwansyah Saputra; Tiska Pattiasina; Jupriyanto Jupriyanto
Jurnal Riset Informatika Vol 4 No 1 (2021): Period of December 2021
Publisher : Kresnamedia Publisher

Security in computer networks can be vulnerable, this is because we have weaknesses in making security policies, weak computer system configurations, or software bugs. Intrusion detection is a mechanism for securing computer networks by detecting, preventing, and blocking illegal attempts to access confidential information. The IDS mechanism is designed to protect the system and reduce the impact of damage from any attack on a computer network for violating computer security policies including availability, confidentiality, and integrity. Data mining techniques have been used to obtain useful knowledge from the use of IDS datasets. Some IDS datasets that are commonly used are Full KDD, Corrected KDD99, NSL-KDD, 10% KDD, UNSW-NB15, Caida, ADFA Windows, and UNM have been used to get the accuracy rate using the k-Nearest Neighbors algorithm (k-NN). The latest IDS dataset provided by the Canadian Institute of Cybersecurity contains most of the latest attack scenarios named the CICIDS2017 dataset. A preliminary experiment shows that the approach using the k-NN method on the CICIDS2017 dataset successfully produces the highest average value of intrusion detection accuracy than other IDS datasets.

Prediksi Stok IT’s Clean Detergent Cair Di CV Satu Titik Nol Menggunakan Metode Double Exponential Smoothing Jupriyanto; Hernawati
Jurnal Teknologi Informasi dan Komunikasi Vol 14 No 2 (2021): Oktober
Publisher : STMIK SUBANG

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47561/a.v14i2.218

The prediction process is important for the company in the formulation of the company's strategy in the future. Therefore, a precise prediction method is needed by the company to be able to maximize the estimation of future sales. The Double Exponential Smoothing method is a popular method used in privacy because it has good performance. This method has parameter values and has a large influence on the results of predictions. This method uses data compilation that shows trends. Exponential smoothing in the presence of a trend such as a simple transmitter such as two components must be updated every period - its level and trend. Level is an estimate that is smoothed from the data value at the end of each period. A trend is a smoothed estimate of average growth. The purpose of this design produces a prediction method that is appropriate and applicable in the company to facilitate sales activities in the company. With the right prediction method, it is expected that the company can make efficient all the resources needed by the company.

COMPARATIVE ANALYSIS OF THE K-NEAREST NEIGHBOR ALGORITHM ON VARIOUS INTRUSION DETECTION DATASETS Andri Agung Riyadi; Fachri Amsury; Tiska Pattiasina; Jupriyanto Jupriyanto
Jurnal Riset Informatika Vol. 4 No. 1 (2021): December 2021
Publisher : Kresnamedia Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34288/jri.v4i1.147

Because we have flaws in developing security rules, inadequate computer system settings, or software defects, security in computer networks can be vulnerable. Intrusion detection is a computer network security method that detects, prevents, and blocks unauthorized access to confidential information. The IDS method is intended to defend the system and minimize the harm caused by any attack on a computer network that violates computer security policies such as availability, confidentiality, and integrity. Data mining techniques were utilized to extract relevant information from IDS databases. The following are some of the most widely utilized IDS datasets NSL-KDD, 10% KDD, Full KDD, Corrected KDD99, UNSW-NB15, ADFA Windows, Caida, dan UNM have been used to get the accuracy rate using the k-Nearest Neighbors algorithm (k-NN). The latest IDS dataset provided by the Canadian Institute of Cybersecurity contains most of the latest attack scenarios named the CICIDS2017 dataset. Preliminary experiment shows that the approach using the k-NN method on the CICIDS2017 dataset successfully produces the highest average value of intrusion detection accuracy than other IDS datasets.

Customer Profilling for Precision Marketing using RFM Method, K-MEANS algorithm and Decision Tree Budilaksono, Sularso; Jupriyanto, Jupriyanto; Suwarno, M.Anno; Suwartane, I Gede Agus; Azhari, Lukman; Fauzi, Achmad; Mahpud, Mahpud; Mariana, Novita; Effendi, Maya Syafriana
Sinkron : jurnal dan penelitian teknik informatika Vol. 5 No. 2B (2021): Article Research October 2021
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v6i1.11225

Precision marketing is the companys ability to offer products specifically made to customers. This decision can give the company the ability to attract customers to always buy continuously. This study presents a trend model for accurately predicting monthly supply quantities / The method used in the first stage is the RFM (Recency, Frequency, Monetary) method for selecting attributes to group customers into different groups. The output of the first stage is clustered using the K-Means Algorithm. The output of clustering is then classified using the Decision Tree and compared with the K Nearest Neighbor method. The dataset that is processed is sales data from Syifamart As-Syifa Boarding School in Subang with 351,158 rows of data. The clustering process produces 4 optimal clusters. The four clusters are then classified using the Decision Tree algorithm to determine the potential and non-potential characteristics of each customer.

Customer Profilling for Precision Marketing using RFM Method, K-MEANS algorithm and Decision Tree Budilaksono, Sularso; Jupriyanto, Jupriyanto; Suwarno, M.Anno; Suwartane, I Gede Agus; Azhari, Lukman; Fauzi, Achmad; Mahpud, Mahpud; Mariana, Novita; Effendi, Maya Syafriana
Sinkron : jurnal dan penelitian teknik informatika Vol. 5 No. 2B (2021): Article Research October 2021
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v6i1.11225

Precision marketing is the companys ability to offer products specifically made to customers. This decision can give the company the ability to attract customers to always buy continuously. This study presents a trend model for accurately predicting monthly supply quantities / The method used in the first stage is the RFM (Recency, Frequency, Monetary) method for selecting attributes to group customers into different groups. The output of the first stage is clustered using the K-Means Algorithm. The output of clustering is then classified using the Decision Tree and compared with the K Nearest Neighbor method. The dataset that is processed is sales data from Syifamart As-Syifa Boarding School in Subang with 351,158 rows of data. The clustering process produces 4 optimal clusters. The four clusters are then classified using the Decision Tree algorithm to determine the potential and non-potential characteristics of each customer.

KERANGKA PENGAMBILAN KEPUTUSAN UNTUK PEMASARAN PRESISI MENGGUNAKAN METODE RFM, ALGORITMA K-MEANS DAN DECISION TREE Jupriyanto, Jupriyanto; Nurlela, Siti
Jurnal Pilar Nusa Mandiri Vol 15 No 2 (2019): Pilar Nusa Mandiri : Journal of Computing and Information System Periode Septemb
Publisher : LPPM Universitas Nusa Mandiri

Pemasaran presisi memberikan kemampuan pada perusahaan untuk menawarkan produk-produk yang dibuat secara khusus kepada pelanggan dan memberikan kemampuan kepada perusahaan untuk menarik minat pelanggan dengan pesan-pesan pemasaran yang dibuat secara khusus. Penelitian ini menyajikan kerangka kerja pengambilan keputusan baru menggunakan teknik data mining. Pertama, penelitian ini menyajikan model tren untuk memprediksi secara akurat kuantitas pasokan bulanan; kedua, menggunakan model RFM (Recency,Frequency, Monetary) untuk memilih atribut untuk mengelompokkan pelanggan ke dalam kelompok sesuai history transaksi belanjanya; ketiga, menggunakan Algoritma K-Means untuk membuat clustering pelanggan berdasarkan data RFM masing-masing pelanggan, keempat, menggunakan Decision Tree untuk mengidentifikasi nilai atribut penting untuk membedakan kelompok pelanggan yang berbeda; dan akhirnya, dari proses data mining yang peneliti lakukan menciptakan berbagai strategi penawaran yang menargetkan setiap cluster pelanggan. Data penjualan dari Syifamart di Subang Jawa Barat, dikumpulkan dan digunakan dalam studi kasus untuk menggambarkan bagaimana mengimplementasikan kerangka yang diusulkan. Dari penelitian yang telah dilakukan menunjukan bahwa proses data mining dari history transaksi penjualan 351,158 rows, dengan agregasi berdasarkan pelanggan menggunakan metode RFM dan diekstraksi dengan menggunakan algoritma clustering k-means membentuk 4 (empat) cluster optimal. Keempat (empat) cluster tersebut diklasifikasikan dengan menggunakan algoritma decision tree sehingga Syifamart dapat mengetahui mana pelanggan potensial dan mana pelanggan yang tidak potensial. Untuk ketersediaan pasokan stok, manajemen memprediksi kebutuhan persediaan produk dengan menggunakan metode tren dimana stok di bulan selanjutnya di prediksi dengan menggunkana history penjualan di bulan sebelumnya.

MACHINE LEARNING SMART PACKAGING PENGIRIMAN TELUR AYAM BERBASIS INTERNET oF THINGS (IoT) MENGGUNAKAN ALGORITMA C.45 DENGAN PLATFORM THINGSPEAK Jupriyanto, Jupriyanto; Putri, Cerafine Delna
Jurnal Teknologi Informasi dan Komunikasi Vol 16 No 2 (2023): Oktober
Publisher : STMIK Subang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47561/a.v16i2.247

In the era of Industry 4.0, the integration of Machine Learning and the Internet of Things (IoT) plays a crucial role in enhancing the efficiency and safety of logistics processes. This research aims to develop a Smart Packaging system for the shipment of chicken eggs utilizing Machine Learning with the C.45 algorithm and IoT-based on the ThingSpeak platform. The system integrates Node-MCU (ESP8266) as the central processing unit, the DHT11 sensor to monitor temperature and humidity within the packaging, the Vibration Sensor SW-420 to detect potential damage to eggs during shipment, and the Unblock Neo6m-V2 GPS Module for real-time location tracking. The C.45 algorithm is employed to process data and make intelligent decisions regarding the condition of the eggs and the shipping environment. Sensor data is collected and transmitted to the ThingSpeak platform through the Wi-Fi connection provided by Node-MCU. The C.45 algorithm is applied to analyze the data, provide predictions regarding egg conditions, and make decisions for further actions during the shipping process. Experiments were conducted to evaluate the system's accuracy using RapidMiner software. The results indicate that the system is capable of predicting egg conditions with a high level of accuracy, enabling responsive actions to situations that may affect egg quality during shipment. The implementation of Machine Learning and IoT technologies in this chicken-egg shipping system is expected to enhance the quality of delivered products, optimize logistical processes, and provide an intelligent solution to ensure the sustainability of the food product supply chain.

IMPLEMENTASI SISTEM PRESENSI BERBASIS IOT (INTERNET OF THINGS) MENGGUNAKAN PLATFORM BLYNK DI SMK CENDIKIA RANCAKALONG Jupriyanto, Jupriyanto; Maulana, Lutfi; Udoyono, Kodar; Permana, Eka
Jurnal Teknologi Informasi dan Komunikasi Vol 17 No 1 (2024): April
Publisher : STMIK Subang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47561/a.v17i1.259

An IoT (Internet of Things) based attendance system using the Blynk Platform with NodeMCU and ESP32-CAM is a teacher attendance management and monitoring system. This system combines Radio Frequency Identification (RFID) technology for time and attendance detection, NodeMCU and ESP32-CAM microcontroller hardware for data processing, and a MySQL database for storage and management of time and attendance data. Using an RFID card, teachers can easily record attendance via a reader connected to the NodeMCU, and the ESP32-CAM provides the ability to capture facial images as an additional verification step. Attendance data is stored in a MySQL database in a structured manner, enabling efficient data management and accurate attendance reporting.

Title

Found 26 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 26 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 26 Documents
Search