Article Per Year (5 Year)
p-Index From 2020 - 2025
1.835
P-Index
This Author published in this journals
All Journal POSITIF JURNAL NASIONAL TEKNIK ELEKTRO Sinkron : Jurnal dan Penelitian Teknik Informatika Journal of Applied Data Sciences Indonesian Journal of Engagement, Community Services, Empowerment and Development (IJECSED) Jurnal Pengabdian Multidisiplin Indonesia Jurnal Sistem Komputer Asia Jurnal ilmiah teknologi informasi Asia
Sunu Jatmika, Sunu
Unknown Affiliation
Arts Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Social Sciences Other

Published : 15 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 15 Documents
Search

 1   2 
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%.
Rice Plants Disease Identification Using Deep Learning with Convolutional Neural Network Method Jatmika, Sunu; Saputra, Danang Eka
Sinkron : jurnal dan penelitian teknik informatika Vol. 6 No. 3 (2022): Article Research Volume 6 Number 3, July 2022
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v7i3.11540

Abstract

Indonesia is an agricultural country where most of the population grows rice and most farmers cannot detect early if there is a pest attack on rice plants . This research discuss about deep learning implementation to classify or identify diseases in rice leaves using mobile application. This system will make users easily to diagnose diseases by displaying diagnostic results in the form of the name of the disease along with its taxonomy, disease description and drug recommendations for disease solutions. There are four classes of leaves used in this research, including healthy leaves, leaf blight, brown spot and potassium deficiency. The design of the model uses two approaches, one of them are modeling convolutional neural network from the scratch and modeling with transfer learning using inception v3 architecture. Both models will go through training process to produce a model that is ready to be used for classification. In application testing, a comparison is made between two models. From the tests that have been carried out, it is concluded that the system with model made using transfer learning approach, produce good accuracy with an accuracy of 90%. Meanwhile the System with the other model gain an accuracy of 62%. So when the data used in research are extremely low, it is best to use transfer learning as an approach to design a mode.
Cognition-Based Document Matching Within the Chatbot Modeling Framework Jatmika, Sunu; Patmanthara, Syaad; Wibawa, Aji Prasetya; Kurniawan, Fachrul
Journal of Applied Data Sciences Vol 5, No 2: MAY 2024
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v5i2.209

Abstract

The aim of the study is to examine cognitive methods for document matching in a chatbot modeling framework by utilizing Euclidean Distance, Cosine Similarity, and BERT methodologies. Five primary indications are used to carry out evaluation in testing: document matching accuracy, document matching execution time, document search efficiency, consistency of document matching results, and the quality of the document representation in the matrix. Document matching accuracy is evaluated by precision; document matching execution time is measured from the beginning to the end of the document matching process; document search efficiency is measured through evaluation of execution time and matching accuracy; the consistency of document matching results is assessed by comparing method results when tested against the same or similar queries and the quality of document representation is assessed based on the method's ability to represent documents in a matrix or vector. The test findings offer a comprehensive understanding of how well the three approaches operate and exhibit their capacity to address the unique requirements of chatbot users. These results may contribute to the advancement of language technology applications, making it possible for chatbots to deliver pertinent information more rapidly and precisely. There are 1,755 labeled question samples in the dataset, which were split up into two sets: 60% for training (1,053 pieces), and 40% for testing (702 samples) to evaluate the model's performance. The test results show the accuracy of the three methods based on five measured evaluation indications, namely Euclidean Distance 0,45%, Cosine similarity 0,59%, and BERT 0,91%.  By comprehending the benefits and drawbacks of each approach, this research strengthens contributions to the growth of chatbot systems to better serve user demands and opens the door for the creation of more complex human-machine interaction solutions.
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.
MQTT Broker Optimization: Comparative Analysis of Round Robin and Least Response Time Arifin, Samsul; Nugraha, Alfian Wahyu; Mukti, Fransiska Sisilia; Jatmika, Sunu
JURNAL NASIONAL TEKNIK ELEKTRO Vol 13, No 3: November 2024
Publisher : Jurusan Teknik Elektro Universitas Andalas

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25077/jnte.v13n3.1260.2024

Abstract

Optimizing MQTT broker performance is crucial for maintaining efficient message routing in IoT systems, especially under varying workloads and QoS levels. This study compares the Round Robin (RR) and Least Response Time (LRT) algorithms to evaluate their performance across QoS levels 0, 1, and 2 and client loads ranging from 500 to 2,500 clients. Using Apache JMeter, key metrics such as CPU usage, throughput, delay, jitter, and response time were assessed. LRT was found to excel in enhancing response time and reducing delay, particularly under high client loads and in applications requiring minimal latency. However, this comes at the cost of higher CPU usage under heavy loads. In contrast, RR demonstrated optimal performance in maintaining balanced CPU utilization and predictable performance, though with slightly higher response times. Both algorithms demonstrated linear scalability in throughput, confirming their ability to handle increasing workloads without bottlenecks. These findings offer practical guidance for IoT developers: in latency-sensitive environments such as industrial automation, LRT is preferable due to its low-latency benefits, while RR is better suited for resource-constrained IoT systems like environmental monitoring, where stability and even load distribution are prioritized. The trade-offs identified provide valuable insights for selecting appropriate algorithms based on specific application requirements.
WORKSHOP PENDAMPINGAN BISNIS TEKNOLOGI CERDAS “SMART TRASH BIN” DESA KESAMBEN, KECAMATAN NGAJUM, MALANG, INDONESIA Dura, Justita; Cahyaningtyas, Fadilla; Yogatama, Ahmad Nizar; Bukhori, Mohammad; Hanif, Rifki; Aqromi , Nur Lailatul; Afiyah, Siti Nurul; Riska, Suastika Yulia; Farokah, Lia; Arifin, Jaenal; Islamiyah, Mufidatul; Arifin, Samsul; Jatmika, Sunu
Indonesian Journal of Engagement, Community Services, Empowerment and Development Vol. 4 No. 3 (2024): Indonesian Journal of Engagement, Community Services, Empowerment and Developme
Publisher : Yayasan Education and Social Center

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53067/ijecsed.v4i3.169

Abstract

Kesamben Village, Ngajum District, Malang Regency faces serious problems in waste management that have an impact on the environment and public health. This community service program aims to introduce "Smart Trash Bin" technology as an innovative solution in improving the efficiency and effectiveness of waste management in the village. This technology uses automatic sensors that allow people to dispose of garbage without touching the trash can, making it more hygienic and comfortable. Early results show high enthusiasm from the public for this technology, which can be seen from active participation in socialization, training, and question and answer sessions. The application of this technology has also succeeded in improving environmental cleanliness and reducing health risks. However, some challenges such as high implementation costs and difficulties in technology adaptation still need to be overcome through adequate financial support and ongoing training. With collaboration between the government, local communities, and related parties, this program has great potential to become a model in the application of smart technology for sustainable waste management in other regions.
Aplikasi Monitoring Lokasi Anak Menggunakan Location Based Service Dengan History Tracking Lokasi Berbasis Android Baharuddin, Shofi; Jatmika, Sunu
JURNAL SISTEM KOMPUTER ASIA Vol 2 No 2 (2024): JISKOMSIA - Volume 2, Nomor 2, Tahun 2024
Publisher : Institut Tekonologi dan Binisi Asia Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32815/jiskomsia.v2i2.74

Abstract

This study discusses the problems of every parent because they have many activities or activities that cannot be avoided. This busyness reduces the supervision and monitoring of their children, making parent worry about the whereabouts of their child’s location. Because at the stage of growth and development of children aged 10 to 18 year they tend to be more interested in exploring things around them. Increased supervision and monitoring of children is needed without reducing children’s freedom to learn and explore their environment. For this reason, an application system is needed that can make it easier for parents to supervise and monitor the location of their children. One alternative way that allows monitoring of location presence and good accuracy is to use Location Based Service with location tracking history. Location Based Service is an information service that can be accessed using mobile devices through the internet and cellular networks that utilize the capabilities of location pointers (maps) on mobile devices. In measuring position, latitude and longtitude are used to determine geographic location. With a note the application must be planted on the smartphone of parents and children. This study produces an Android-based application that is used for monitoring the location of children using Location Based Service with location tracking history with the aim of displaying the child’s location and also tracking location history that can be accessed via the parent’s smartphone.
Co-Authors Aisyah, Firda Aji Prasetya Wibawa Al Zahwa, Naviza Yulia Amrullah Mudzakkir, Amrullah Aqromi , Nur Lailatul Baharuddin, Shofi BUKHORI, MOHAMMAD Burhanudin, Dimas Eka Saputra, Danang Fachrul Kurniawan Fadilla Cahyaningtyas Farokah, Lia fatiby, ubay Fransiska Sisilia Mukti Hanif, Rifki Indra Andiko, Indra Indriastuti, Maria Theresia Jaenal Arifin Justita Dura Mufidatul Islamiyah, Mufidatul Muhammad Idris Nugraha, Alfian Wahyu Nur Lailatul Aqromi Samsul Arifin Saputra, Danang Eka Siti Nurul Afiyah Suastika Yulia Riska Syaad Patmanthara Tri Prasetyo, Broto Poernomo Tri Prasetyo, Broto Poernomo Tria Aprilianto, Tria Wafdulloh, Gibran Adna Yogatama, Ahmad Nizar