Article Per Year (5 Year)
p-Index From 2021 - 2026
0.61
P-Index
This Author published in this journals
All Journal CommIT (Communication & Information Technology) Jurnal Telematika Jurnal Teknik Informatika (JUTIF) Engineering Science Letter Jurnal INFOTEL
Martina, Inge
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Engineering Industrial & Manufacturing Engineering Materials Science & Nanotechnology

Published : 10 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 10 Documents
Search

 1 
Implementation of Structured Object-Oriented Formal Language for Warehouse Management System Afifudi, Irfin; Martina, Inge
CommIT (Communication and Information Technology) Journal Vol 14, No 1 (2020): CommIT Vol. 14 No. 1 Tahun 2020
Publisher : Bina Nusantara University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21512/commit.v14i1.5942

Abstract

Designing process is inseparable from software development. Like other software development processes, designing process faces many problems, such as improper and ambiguous specifications. These problems may be overcome by applying formal engineering methods. One of which is Structured Object-Oriented Formal Language (SOFL). The analysis and formation of the design and implementation of SOFL are carried out as a solution to the problem. The application of SOFL is divided into three parts according to SOFL rules, namely informal specification, semi-formal specification, and formal specification. The design and implementation are measured and tested using rigorous review and maintainability index. This research uses a warehouse management system, a safety-critical system, as a case study. Rigorous analysis shows that SOFL in warehouse management system increases the maintainability index of 56.94%. It means that it is easier to develop.
Implementation of Structured Object-Oriented Formal Language for Warehouse Management System Irfin Afifudin; Inge Martina
CommIT (Communication and Information Technology) Journal Vol. 14 No. 1 (2020): CommIT Journal
Publisher : Bina Nusantara University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21512/commit.v14i1.5942

Abstract

Designing process is inseparable from software development. Like other software development processes, designing process faces many problems, such as improper and ambiguous specifications. These problems may be overcome by applying formal engineering methods. One of which is Structured Object-Oriented Formal Language (SOFL). The analysis and formation of the design and implementation of SOFL are carried out as a solution to the problem. The application of SOFL is divided into three parts according to SOFL rules, namely informal specification, semi-formal specification, and formal specification. The design and implementation are measured and tested using rigorous review and maintainability index. This research uses a warehouse management system, a safety-critical system, as a case study. Rigorous analysis shows that SOFL in warehouse management system increases the maintainability index of 56.94%. It means that it is easier to develop.
PENERAPAN ALGORITMA GENETIKA DENGAN CROSSOVER CUT AND SPLICE DALAM OPTIMASI ROUTING JARINGAN Martina, Inge
Jurnal Telematika Vol. 7 No. 1 (2011)
Publisher : Yayasan Petra Harapan Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61769/telematika.v7i1.50

Abstract

Routing jaringan adalah pemilihan jalur dalam jaringan yang dipakai untuk mengirimkan data. Di dalam jaringan komputer, data akan dikirimkan dari sumbernya ke tujuan akhir melalui titik-titik perantara. Jalur yang dilalui akan mempengaruhi kecepatan pengiriman (delay) dan banyaknya paket data yang hilang. Pencarian routing jaringan adalah masalah pencarian jalur terpendek (shortest path). Paper ini bertujuan untuk mengusulkan sebuah algoritma untuk pencarian routing jaringan dengan algoritma genetika yang memakai crossover cut and splice.. Network routing is the process of selecting paths in a network along which to send data. In computer network, the data will be sent from the source toward the ultimate destination through intermediate nodes. The path will influence the transmission speed (delay) and data packet losses. Network routing finding can be classified as shortest path problem. This paper proposes an algorithm for finding network routing by adapting genetic algorithm with cut and splice crossover.
Sistem Wawancara Virtual untuk Penerimaan Mahasiswa Jurusan Teknik Informatika di ITHB dengan Metode Natural Language Processing Hartanto, Harry; Liong, The Houw; Martina, Inge
Jurnal Telematika Vol. 8 No. 1 (2013)
Publisher : Yayasan Petra Harapan Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61769/telematika.v8i1.69

Abstract

Institut Teknologi Harapan Bangsa khususnya jurusan Teknik Informatika memiliki sistem penerimaan mahasiswa baru dengan metode wawancara secara langsung oleh kepala departemen. Metode natural language processing, adalah metode yang memproses input teks menjadi kata-kata kunci jawaban user. Proses-proses yang terlibat adalah stemming, parsing, dan scoring. Stemming adalah proses untuk mencari kata dasar. Sistem sudah mempunyai kumpulan kata dasar yang dikenali dan disimpan di dalam lexicon. Hasil stemming akan diberi atribut yang berupa bobot dan tipe kata. Proses selanjutnya adalah parsing yaitu merangkai kata-kata dasar menjadi struktur kalimat. Parsing seperti ini disebut bottom-way parsing. Proses terakhir adalah scoring yaitu menghitung bobot dan menilai jawaban user. Hasil akhir dari sistem adalah mengkalkulasikan semua nilai dari setiap jawaban dan menampilkan total skor dari user tersebut. Institut Teknologi Harapan Bangsa majoring in Informatics Engineering in particular has a new admission system by doing direct interview by the head of department. Natural Language Processing is a method for processing the input text into the user answer keywords. Processes involved are stemming, parsing and scoring. Stemming is a process for finding base form of the word. System already has dictionary of known words that called lexicon. The result of stemming will be given attributes that consist of weight and type of the word. The next process is parsing that will build those base words into sentence structure. Such parsing is so called bottom-way parsing. The final proccess is scoring that will calculate the score of the user answer. The end result of the system is to calculate all the values of each answer and display  the total score of that user.
Optimasi Penjadwalan Landasan Pacu untuk Keberangkatan Menggunakan Algoritma Genetika Pontolaeng, Hanna Ribkah; Martina, Inge
Jurnal Telematika Vol. 9 No. 2 (2014)
Publisher : Yayasan Petra Harapan Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61769/telematika.v9i2.88

Abstract

Saat ini penjadwalan landasan pacu (runway) menggunakan metode “First In First Out” (FIFO) oleh petugas Air Traffic Control (ATC). Penjadwalan FIFO hanya memperhatikan waktu kedatangan, tidak memperhatikan delay yang sudah dialami pesawat. Penjadwalan dengan algoritma genetika (GA) akan mengoptimasi waktu tunggu dengan mempertimbangkan delay yang sudah terjadi. Algoritma genetika memiliki beberapa operator, yaitu persilangan (crossover), mutasi, seleksi, dan evaluasi fitness. Penelitian ini menggunakan operator swap mutation dan truncation selection. Hasil dari GA akan dibandingkan dengan hasil penjadwalan FIFO.
Penggunaan Correlation-Based Similarity untuk Sistem Rekomendasi Tanpa Rating Yulian, Hans; Martina, Inge
Jurnal Telematika Vol. 10 No. 1 (2015)
Publisher : Yayasan Petra Harapan Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61769/telematika.v10i1.121

Abstract

Sistem rekomendasi adalah sebuah sistem yang menjadi sebuah kebutuhan banyak perusahaan saat ini, terutama perusahaan yang menjual produk dan melakukan aktivitasnya melalui media web. Rating yang telah diberikan oleh seorang pengguna akan digunakan sebagai referensi untuk menentukan rekomendasi untuk pengguna tersebut serta orang lain yang memiliki karakteristik yang mirip. Terkadang sistem rekomendasi tidak menggunakan rating, tetapi berdasarkan sejarah pembelian/pemakaian. Correlation-based similarity adalah sebuah algoritma yang dapat digunakan untuk mendapatkan nilai kemiripan antar dua obyek yang berbeda. Kemiripan dihitung berdasar rating yang diberikan oleh pengguna. Seorang pengguna dikatakan mirip dengan pengguna lain berdasarkan nilai threshold yang ditentukan. Kadang sulit untuk mendapatkan rating maka diperlukan sistem rekomendasi tanpa rating. Rumus correlation-based similarity perlu dioptimasi untuk sistem rekomendasi tanpa rating.Recommender system is needed by many companies, mainly for companies that selling products and services in web. User ratings are used as recommendation references for user himself or for another users having similar characteristics. Sometimes recommender system doesn’t use rating, but based on buying/using history. Correlation-based similarity is an algorithm that can be used for getting similarity value between two different objects. Similarity is calculated based on user ratings. Sometimes it is difficult to get rating, so that it is needed a recommender system without user input. Correlation-based similarity formula must be optimized for recommender system without rating.
Penerapan Algoritma Genetika pada Optimalisasi Tim Pengerja Musik Gereja Rengku, Alwin; Martina, Inge
Jurnal Telematika Vol. 11 No. 2 (2016)
Publisher : Yayasan Petra Harapan Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61769/telematika.v11i2.148

Abstract

Gereja memiliki sejumlah pengerja musik yang dijadwalkan setiap pekan secara bergilir pada lokasi yang berbeda-beda. Pengerja terpisah kedalam beberapa kelompok, selain itu pengerja juga memiliki tingkat kemampuan yang berbeda-beda, sehingga solusi optimasi harus bisa menghasilkan susunan tim yang memenuhi ketentuan. Tidak hanya pengerja, setiap lokasi juga memiliki tingkatan karakteristik yang berbeda sehingga sebagian lokasi membutuhkan konfigurasi tim yang khusus. Algoritma genetika digunakan dengan menjadikan pengerja sebagai alel, waktu ibadah dalam setiap lokasi sebagai gen, dan alokasi pengerja pada setiap waktu ibadah dalam setiap lokasi sebagai kromosom. Setiap kromosom mewakili sebuah solusi. Kromosom akan melewati sejumlah tahapan seleksi, persilangan, dan mutasi, sehingga pada akhirnya dihasilkan sejumlah alternatif solusi terbaik. Solusi terbaik dipilih berdasarkan nilai fitness kromosom yang lebih mendekati 0, yang dalam hal ini berarti sangat optimal. Populasi akan mengalami regenerasi sejumlah ukuran generasi yang ditetapkan. Proses regenerasi akan berakhir jika fitness kromosom terbaik tidak mengalami perubahan selama jumlah generasi yang ditetapkan juga. Rata-rata generasi yang dibutuhkan untuk menghasilkan solusi dari 200 pengerja pada 9 lokasi adalah 12, dengan probabilitas persilangan 0,167 dan probabilitas mutasi 0,125.  A church generally employs some music servants whom scheduled every week sequentially to some distributed locations. Each of them is divided into several different groups. They also have different level of expertise, so then the optimization solution should propose a desired team configuration. Every location has their own characteristic level, so it may require special team configuration. Genetic algorithm define servant as allele, service time slot in each location as gene, and servant allocation to each location as chromosome. Each chromosome proposed an alternative solution. Chromosome will be processed through some selection, crossover, and motation steps, so then the best solution will be acquired. Best solution will be chosen from a chromosome that has fitness value near to 0, which means it is the most optimum solution. Population will be regenerated as long as the provided generation size. The regeneration process will be terminated if the best chromosome fitness does not change in a provided generation count. The average required generation to acquire solution from 200 servants in 9 locations is 12, with the crossover probability of 0.167 and mutation probability of 0.125. 
A Proposed Quality Improvement of Delivery Services at PT Pos Indonesia Using Importance-Performance Analysis and Kano Model Silitonga, Roland Y. H.; Tindaon, Phila Delphia; Indriati, Ellen; Martina, Inge
Engineering Science Letter Vol. 3 No. 02 (2024): Engineering Science Letter
Publisher : The Indonesian Institute of Science and Technology Research

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56741/esl.v3i02.534

Abstract

PT Pos Indonesia, a courier service company, contends with a notably low market share, as indicated by Top Brand data reflecting market proportions over the past five years in Indonesia. This decline in market share is predominantly attributed to subpar service quality. Hence, there is a pressing need to scrutinize PT Pos Indonesia to enhance its service standards for consumers and discern the service attributes requiring maintenance and prioritized improvement. This study employs the IPA (Importance Performance Analysis) and Kano method, both of which complement each other synergistically. IPA seeks to unearth insights into service factors influencing customer satisfaction and loyalty, while the Kano model categorizes service attributes based on their capacity to meet customer needs effectively. Additionally, the Kano model identifies areas warranting attention or enhancement, which can augment customer satisfaction. The analysis reveals four attributes classified as defenseless strategy points and one attribute deemed a chronic issue through the amalgamation of IPA and Kano model findings, thereby informing decisions to enhance performance.
You Only Look Once v5 and Long Short-Term Memory Implementation for Crowd Anomaly Detection Wardani, Ken Ratri Retno; Chrisandy, Nicholas; Martina, Inge; Heryanto, Hery
Jurnal Teknik Informatika (Jutif) Vol. 6 No. 2 (2025): JUTIF Volume 6, Number 2, April 2025
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2025.6.2.4224

Abstract

In Indonesia, 116,000 traffic accidents and 370,747 workplace accidents occurred in 2023, emphasizing the urgent need for effective surveillance systems for monitoring crowded areas such as public sidewalks, roads, workplaces, and school hallways. This study introduces a novel approach combining You Only Look Once v5 (YOLOv5) and Long Short-Term Memory (LSTM) networks for crowd anomaly detection. Unlike traditional methods, this hybrid framework utilizes YOLOv5 for precise feature extraction from video frames and LSTM to capture temporal dependencies for detecting anomalous behaviors. The dataset used includes scenes from the Crowd Anomaly Detection UML Dataset, consisting of a 1-minute and 11-second video extracted into 852 images. Hyperparameter tuning was conducted for epochs and learning rates in the YOLOv5 model, as well as for epochs and units in the LSTM model. The proposed framework achieved remarkable results, with 98% accuracy, 100% precision, and 86% F1-Score. However, improvements in class distribution within the training data could enhance model performance further. These findings demonstrate the potential of the proposed method for real-world applications in improving public safety and effective anomaly detection. This research proves that the proposed method which uses separate feature extraction method before detecting anomaly provides a better result in crowd anomaly detection.
Rancangan Dasar Sistem Aplikasi Pemantau Lalu Lintas dan Penghitung Kendaraan Berbasis Komputasi Tepi Heryanto, Hery; Hutagalung, Maclaurin; Gamaliel, Yoyok Yusman; Angela, Dina; Pratama, Dionisius; Martina, Inge; Nugroho, Tunggul Arief
JURNAL INFOTEL Vol 16 No 2 (2024): May 2024
Publisher : LPPM INSTITUT TEKNOLOGI TELKOM PURWOKERTO

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20895/infotel.v16i2.1105

Abstract

One of the main issues in Indonesia is congestion. The number of vehicles continues to increase and is less balanced by the development of transportation infrastructure, especially landlines, causing more complex problems. The Indonesian government needs an intelligent application system that can provide knowledge to unravel congestion. The problem is how to perform edge computing to reduce latency so that the highway monitoring application system runs in real time. This research proposes a basic design for a vehicle monitoring application system that can accurately recognize vehicles, count the number of vehicles, and propose an edge computation that brings computation directly to the data source. The dataset is a video of traffic in Bandung, Jakarta, and several other major cities. The images in the dataset consist of 4,890 training images, 467 validation images, and 231 testing images. In the proposed model, the YOLOv5 and YOLOv7 architectures accurately detect and count vehicles. The test results show a mAP value of 99.1% with an IoU threshold of 50%. Other results include a precision value of 96.2% and a recall of 97.7%. The proposed model can accurately monitor vehicles and reduce latency with an edge computing approach.
Co-Authors Afifudi, Irfin Angela, Dina Chrisandy, Nicholas Gamaliel, Yoyok Yusman Hartanto, Harry Hery Heryanto Hutagalung, Maclaurin Indriati, Ellen Irfin Afifudin Ken Ratri Retno Wardani Nugroho, Tunggul Arief Pontolaeng, Hanna Ribkah Pratama, Dionisius Rengku, Alwin Silitonga, Roland Y. H. The Houw Liong Tindaon, Phila Delphia Yulian, Hans