Claim Missing Document
Check
Articles

Found 5 Documents
Search
Journal : POSITIF

Implementasi Teks Mining Untuk Klasifikasi Buku Berdasarkan Dewey Decimal Clasification (Ddc) Di Perpustakaan Stmik Asia Malang Berbasis Vektor Space Model Jatmika, Sunu; Indriastuti, Maria Theresia; Wafdulloh, Gibran Adna
POSITIF : Jurnal Sistem dan Teknologi Informasi Vol 4 No 2 (2018): POSITIF : Jurnal Sistem dan Teknologi Informasi
Publisher : P3M Politeknik Negeri Banjarmasin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31961/positif.v4i2.567

Abstract

ASIA University Library has a problem in the grouping of new books in large numbers, because the DDC is a parameter for the grouping of the book has not been entered into the library information system, so that when the librarian input some books, they should be viewed DDC before entering into the system and it was very reducing the work time efficiently. Those problems can be solved by adding the new intelligent system in the application, namely the pre-processing algorithms that has tokenizing phase, filtering, and stemming use Nazief Andriani and then compared to find similarities documents or title with Vector Space Model algorithm. From the test that results using the algorithm above, eventually the system could resolve the problems in the library of ASIA that is this system has a recall value by 63% and the value of Precision by 72%. These results meet on the effectiveness of information retrieval system that the accuracy of a value is at least 50%.
Analisis Antrian Model Multi Channel - Single Phase Dan Optimalisasi Layanan Akademik (Studi Kasus Pada STMIK ASIA Malang) Jatmika, Sunu; Tri Prasetyo, Broto Poernomo
POSITIF : Jurnal Sistem dan Teknologi Informasi Vol 3 No 1 (2017): POSITIF - Jurnal Sistem dan Teknologi Informasi
Publisher : P3M Politeknik Negeri Banjarmasin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31961/positif.v3i1.396

Abstract

Antrian merupakan hal penting dalam manajemen operasi. Sistem antrian bisa diketemukan pada sektor industri maupun sektor jasa. Antrian bisa barisan orang atau barang yang menunggu untuk dilayani dan meninggalkan barisan setelah dilayani. Tujuan dari penelitian ini adalah untuk mengukur tingkat kepuasan pelayanan yang diberikan perguruan tinggi sehubungan dengan berapa cepat pemenuhan kebutuhan mahasiswa dibidang akademik. Hasil menunjukkan bahwa model jenis antrian pelayanan akademik yang digunakan di STMIK ASIA Malang adalah jenis antrian model Multi Channel - Singel Phase dengan menerapkan disiplin antrian yaitu First In – First Out (FIFO) . Pola kedatangan mahasiswa mengikuti distribusi poisson dengan nilai 15 mahasiswa/jam dan pola pelayanan berdistribusi eksponential dengan nilai rata-rata 17 mahasiswa/jam. Dari pengujian didapatkan tingkat intensitas pelayanan 88% sedangkan 12% untuk istirahat, jumlah rata-rata mahasiswa yang dalam sistem 7.5, jumlah mahasiswa yang menunggu dalam antrian untuk dilayani 6.6, waktu yang digunakan mahasiswa selama dalam sistem (menunggu untuk dilayani) 15 menit, waktu yang diharapkan oleh setiap mahasiswa untuk menunggu dalam antrian 13.4 menit. Jumlah optimal pegawai dalam memberikan pelayanan terhadap mahasiswa adalah dengan melakukan penambahan 1-2 pegawai, maka waktu tunggu dalam sistem yang awalnya 30 menit menjadi 10 menit dan waktu tunggu dalam antrian yang awalnya 13.4 menit menjadi 5.38 menit.
EKSTRAKSI FITUR UNTUK MENGIDENTIFIKASI MARGA TANAMAN MENGGUNAKAN ALGORITMA BACKPROPAGATION Jatmika, Sunu; Aprilianto, Tria; Idris, Muhammad
POSITIF : Jurnal Sistem dan Teknologi Informasi Vol 6 No 1 (2020): Positif : Jurnal Sistem dan Teknologi Informasi
Publisher : P3M Politeknik Negeri Banjarmasin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31961/positif.v6i1.907

Abstract

Feature extraction is the beginning to be able to classify and interpret images by linking the characteristics of the leaves into a group of clans according to their type. The algorithm used is backpropagation based on shape and color. The formulation of the problem taken is how the use of the backpropagation algorithm can improve the quality of the community in identifying leaf images. The purpose of this study is to make it easier for the general public to recognize plants, especially the family Azadirachta, Swietenia, and Khaya. This study uses data collection techniques in the form of observation, interviews, and documentation. Data analysis is done by entering content into the system. Data will be input into the learning machine obtained from feature extraction and processed with the backpropagation method. System design uses backpropagation algorithm to classify plants through leaf features. This system uses Android Studio and SQLite databases. The results of this study are that of 9 test data there are 8 recognizable data and 1 incorrectly recognized data. The data shows the accuracy of the backpropagation algorithm in facilitating the general public to recognize plants, especially the family Azadirachta, Swietenia, and Khaya is 88.9%. In addition, the results of the questionnaire show that the backpropagation algorithm has 66% application benefits, 76% ease of interaction, and 80% application display. The overall average of the benefits of each aspect is 74.2%.
SISTEM SMART GATE DENGAN MENGGUNAKAN WASTAFEL DAN SENSOR SUHU TOUCHLESS SENSOR BERBASIS FUZYY LOGIC CONTROL Jatmika, Sunu; Aprilianto, Tria; Burhanudin, Dimas
POSITIF : Jurnal Sistem dan Teknologi Informasi Vol 8 No 1 (2022): Positif : Jurnal Sistem dan Teknologi Informasi
Publisher : P3M Politeknik Negeri Banjarmasin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31961/positif.v8i1.1262

Abstract

Health protocol standards are the main standards during the Covid-19 period. Because there is still a lack of public awareness in carrying out the protocol, one of which is that many people do not wash their hands before doing activities or even check body temperature sensors. In offices, whether private or government, tourist attractions, education and other health protocols still use employees, especially to check body temperature and lack of discipline in terms of checking users, so that people stay tipped, it is necessary the development of standard automation technology that must be carried out when the public will enter the office area or students before entering the school area through the gate. In order for the gate to be open, it must go through two standard health protocols, namely hand washing and checking body temperature. If one is not done and the value is not in accordance with the Covid task force standards, the gate will still be closed, for the hand washing process and temperature sensors use This touchless sensor is to reduce the level of risk of direct contact so that it will reduce the level of spread of the covid-19 virus. The results of this study from 50 respondents who tested the smart gate the success rate reached 90% percent success with 2 input parameters, namely through hand washing and body temperature sensors where the data was processed using fuzzy logic control. The method used for testing is using the functional tools/sensors used. While 10% is not successful because of the external light intensity factor when reading the sensor.
PEMANFAATAN METODE TOPIC MODELLING HIERARCHICAL DIRICHLET PROCESS DALAM MENGEVALUASI KUALITAS KONTEN WEBSITE BERDASARKAN ULASAN PENGGUNA Jatmika, Sunu; Mukti, Fransiska Sisilia; Aprilianto, Tria; Al Zahwa, Naviza Yulia
POSITIF : Jurnal Sistem dan Teknologi Informasi Vol 10 No 1 (2024): Positif : Jurnal Sistem dan Teknologi Informasi
Publisher : P3M Politeknik Negeri Banjarmasin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31961/positif.v10i1.2199

Abstract

The evaluation of website content is important to ensure that the presented content aligns with users' needs and preferences. This can be accomplished by analyzing user reviews regarding the website's content. This research leverages the Hierarchical Dirichlet Process (HDP) method to automatically identify primary topics from 32 users' reviews, resulting in three main recurring topics: 'good', 'bug', and 'update'. Using the OSEMN framework, the final evaluation indicates that the 'good' topic exhibits the highest cosine similarity value compared to other topics. This signifies that the positive aspects highlighted in users' reviews regarding the website's content dominate and possess significant similarities among the reviews. These findings offer crucial insights into comprehending user evaluations of website content, serving as a basis for more effective and targeted content improvements moving forward.