Articles
<![CDATA[MODEL BIDIRECTIONAL LSTM UNTUK PEMROSESAN SEKUENSIAL DATA TEKS SPAM ]]>
<![CDATA[Siringoringo, Rimbun]]>;
<![CDATA[Jamaluddin, Jamaluddin]]>;
<![CDATA[Perangin-angin, Resianta]]>;
<![CDATA[Harianja, Eva Julia Gunawati]]>;
<![CDATA[Lumbantoruan, Gortap]]>;
<![CDATA[Purba, Eviyanti Novita]]>
<![CDATA[ METHOMIKA: Jurnal Manajemen Informatika & Komputerisasi Akuntansi Vol. 7 No. 2 (2023): METHOMIKA: Jurnal Manajemen Informatika & Komputersisasi Akuntansi ]]>
Publisher : <![CDATA[Universitas Methodist Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.46880/jmika.Vol7No2.pp265-271
<![CDATA[This study examines the LSTM-based model for processing spam in text data. Spam poses several dangers and risks, both for individuals and organizations. Spam can be a nuisance that hampers both individual and organizational productivity. Much spam contains fraudulent or phishing attempts to obtain sensitive information. Spam detection using deep learning involves the utilization of algorithms and deep neural network models to accurately classify messages as either spam or not spam. Typically, spam detection systems use a combination of these methods to improve the accuracy of identifying spam messages. This study applies the Bi-LSTM deep learning model to sequentially process text (sequencing). The performance of the model is determined based on the loss and accuracy. The data used are the Spam SMS and Spam Email datasets. The test results show that the Bi-LSTM model demonstrates better performance on all tested datasets. Bi-LSTM is able to capture textual patterns from both the context and the text itself, as it can combine information from both directions. The test results prove that the Bi-LSTM model is more effective in text comprehension. So we need to use Snort to maintain network security. Snort is a useful software for observing activity in a computer network. Snort can be used as a lightweight Network Intrusion Detection System (NIDS). Detection is carried out based on the rules that have been described by the administrator in the directory rules contained in the configuration file. Snort can analyze real time alerts, where the mechanism for entering alerts can be in the form of a user syslog, file or through a database. So we can detect attacks on computer networks early.]]>
<![CDATA[Sistem Informasi Pemesanan Makanan/Minuman pada Coffee Hitam Putih Berbasis Web ]]>
<![CDATA[Sinaga, Nillasari]]>;
<![CDATA[Nainggolan, Rena]]>;
<![CDATA[Harianja, Eva Julia Gunawati]]>
<![CDATA[ TAMIKA: Jurnal Tugas Akhir Manajemen Informatika & Komputerisasi Akuntansi Vol 5 No 1 (2025): TAMIKA: Jurnal Tugas Akhir Manajemen Informatika & Komputerisasi Akuntansi ]]>
Publisher : <![CDATA[Universitas Methodist Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.46880/tamika.Vol5No1.pp61-66
<![CDATA[Currently, Coffee Hitam Putih still uses manual recording. Manual order recording is less efficient in terms of time and cost. So, to realize consumer satisfaction in ordering food, a food/beverage ordering information system on web-based Coffee Hitam Putih was created. This information system provides a list of food menus, prices, descriptions, and availability. This information system makes it easier for the management of Coffee Hitam Putih to provide effective and efficient services. It can produce fast, precise and accurate information because it uses a database. The methods used in data collection are: a. Literature method, which is a method of collecting data with the help of books from the library or documents and reports related to this research. b. The observation method, which is observing the running system directly on the object to be studied, in order to provide clear and precise information about the process and activities related to ordering menus at Coffee Hitam Putih. c. Interview method, namely conducting questions and answers directly with the manager of Coffee Hitam Putih. The advantage of this technological development is that it is very helpful for people's daily activities. The existence and role of information technology in all sectors of life have an impact on the economic, social, and cultural aspects of human beings.]]>
<![CDATA[UTILITY VECTORS TO FUZZY PREFERENCE RELATION DENGAN METODE SIMPLE ADDITIVE WEIGHTING (SAW) DALAM PENENTUAN POSISI KERJA KARYAWAN ]]>
<![CDATA[Harianja, Eva Julia Gunawati]]>;
<![CDATA[Ketaren, Eliasta]]>
<![CDATA[ Jurnal TIMES Vol 5 No 1 (2016) ]]>
Publisher : <![CDATA[STMIK TIME ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (323.743 KB)
|
DOI: 10.51351/jtm.5.1.2016480
<![CDATA[Penempatan kerja bukanlah masalah sederhana, sebab kesalahan penempatan dapat mempengaruhi operasi perusahaan. Masalah utama yang dihadapi dalam menyeleksi karyawan adalah masih kurangnya ketepatan dan kecepatan proses penilaian kinerja masing-masing karyawan guna memenuhi posisi tertentu. Penilaian kinerja karyawan yang didasarkan pada kriteria-kriteria tersebut sering kali menjadi masalah dalam proses pengambilan keputusan. Untuk mengekspresikan preferensi pengambil keputusan pada alternatif yang paling diinginkan, dapat dilakukan dengan transformasi format preferensi Utility Vectors to Fuzzy Preference Relation. Selanjutnya memilih metode SAW untuk menentukan nilai bobot untuk setiap atribut, yang dilanjutkan dengan proses perangkingan untuk menyeleksi alternatif terbaik, dalam hal ini adalah alternatif yang cocok untuk menentukan posisi kerja karyawan yang sesuai dengan kriteria-kriteria yang telah ditentukan. Dengan metode ini diharapkan penilaian akan lebih tepat dan akurat karena didasarkan pada nilai kriteria dan bobot yang telah ditentukan.]]>
<![CDATA[Pendekatan Level Data untuk Menangani Ketidakseimbangan Data Menggunakan Algoritma K-Nearest Neighbor ]]>
<![CDATA[Perangin-angin, Resianta]]>;
<![CDATA[Harianja, Eva Julia Gunawati]]>;
<![CDATA[Jaya, Indra Kelana]]>
<![CDATA[ Jurnal TIMES Vol 9 No 1 (2020) ]]>
Publisher : <![CDATA[STMIK TIME ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (302.889 KB)
|
DOI: 10.51351/jtm.9.1.2020615
<![CDATA[Dalam penelitian ini digunakan dataset yang memiliki tingkat ketidakseimbangan yang berbeda beda mulai dari 16.40, 8.60, 2.06, 2.78, 1.87, tentu hal ini dapat menurunkan kinerja algoritma klasifikasi. Secara umum ketidakseimbangan kelas dapat ditangani dengan dua pendekatan, yaitu level data dan level algoritma. Pendekatan level data ditujukan untuk memperbaiki keseimbangan kelas, sedangkan pendekatan level algoritma ditujukan untuk memperbaiki algoritma atau menggabungkan (ensemble) pengklasifikasi agar lebih konduktif terhadap kelas minoritas. Pada penelitian ini diusulkan pendekatan level data dengan resampling, yaitu random oversampling (ROS), dan random undersampling (RUS), Pengklasifikasi yang digunakan adalah k-near neighbors. Hasil penelitian menunjukkan bahwa model ROS+KNN dan RUS+KNN didapat dengan selisih G-Means sebesar 13% dan F-Measure 2,08%, dari, hal ini menunjutkan bahwa RUS+KNN dan ROS+KNN bisa meningkatkan akurasi dari G-Mean dan F-Measure namun tidak memiliki perbedaan yang signifikan.]]>
<![CDATA[Comparison Detection Edge Lines Algoritma Canny dan Sobel ]]>
<![CDATA[Perangin-angin, Resianta]]>;
<![CDATA[Harianja, Eva Julia Gunawati]]>
<![CDATA[ Jurnal TIMES Vol 8 No 2 (2019) ]]>
Publisher : <![CDATA[STMIK TIME ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (321.095 KB)
|
DOI: 10.51351/jtm.8.2.2019616
<![CDATA[Deteksi tepi adalah pendekatan paling umum yang digunakan untuk mendeteksi tingkat abu-abu diskontinuitas. Ini karena titik atau garis yang terisolasi tidak terlalu sering dijumpai dalam aplikasi praktis. Idealnya, teknik yang digunakan untuk mendeteksi diskontinuitas hanya menghasilkan satu piksel yang terletak di wilayah batas. Salah satu teknik pengolahan citra yang digunakan adalah deteksi tepi. Deteksi tepi sering terjadi pada pengolahan citra digital karena merupakan salah satu langkah awal dalam segmentasi citra yang bertujuan untuk mempresentasikan objek yang terdapat pada citra. Deteksi tepi berfungsi untuk mengidentifikasi batas-batas suatu objek dengan latar belakang yang tumpang tindih. Oleh karena itu, ketika garis besar gambar dapat diidentifikasi secara akurat, semua objek dapat ditemukan dan properti dasar seperti luas, bentuk, dan ukuran objek dapat diukur. Ada beberapa jenis metode deteksi tepi yang dapat digunakan untuk mendeteksi garis besar suatu citra, seperti algoritma Sobel, Prewitt, Canny dan homogenitas. Masing-masing metode tersebut memiliki kelebihan dan kekurangannya masing-masing. Dalam penelitian ini akan diambil dua algoritma yaitu algoritma Canny dan Sobel. Berdasarkan kekuatan dan kelemahan kedua metode tersebut akan dilakukan analisis terhadap kedua metode tersebut untuk melihat hasil pendeteksian yang keduanya akan digunakan sebagai pembanding. Dilihat dari hasil yang didapat dari algoritma deteksi tepi Canny dan Sobel secara jelas terlihat lebih baik algoritma cannya pada hasil pendekteksian tepi, dimana algoritma Canny mempunyai hasil yang lebih halus dan lebih spesifik mendekteksi garis tepi suatu objek citra. Sedangkan algoritma pendektesian garis tepi sobel masih meregang pada daerah yang tidak berbatasan. Dilihat dari struktur hasil pendeteksian algoritma Canny lebih baik daripada algoritma Sobel.]]>
<![CDATA[SISTEM PENDUKUNG KEPUTUSAN PEMBERIAN BANTUAN SEMBAKO BAGI JEMAAT GEREJA HKI TERDAMPAK COVID-19 MENGGUNAKAN METODE TOPSIS STUDI KASUS: HKI RESORT SIGALINGGING ]]>
<![CDATA[Harianja, Eva Julia Gunawati]]>;
<![CDATA[Lumbantoruan, Gortap]]>;
<![CDATA[Nainggolan, Rena]]>
<![CDATA[ Jurnal TIMES Vol 10 No 2 (2021): Jurnal TIMES ]]>
Publisher : <![CDATA[STMIK TIME ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (513.431 KB)
|
DOI: 10.51351/jtm.10.2.2021662
<![CDATA[Berbagai sektor kehidupan manusia yang terdampak Covid-19 secara khusus dapat dirasakan pada sektor perekonomian, seperti yang dialami oleh masyarakat Indonesia saat ini. Pemerintah maupun berbagai pihak lainnya berupaya meringankan beban masyarakat yang terdampak Covid-19 dengan menyelenggarakan berbagai program bantuan, seperti halnya penyaluran sembako kepada masyarakat. Gereja Huria Kristen Indonesia (HKI), khususnya Resort Sigalingging juga turut mengambil peran dengan menyalurkan bantuan sembako bagi warga jemaatnya yang terdampak Covid-19. Sebagai penyelenggara penyalur bantuan tersebut, diharapkan Gereja HKI lebih selektif dalam proses penyeleksian calon penerima bantuan agar penyaluran bantuan tepat pada sasarannya. Penentuan warga jemaat Gereja HKI sebagai calon penerima bantuan sembako yang terdampak Covid-19 didasarkan pada kriteria-kriteria tertentu sering kali menjadi masalah dalam proses pengambilan keputusan. Untuk mengekspresikan preferensi pengambil keputusan pada alternatif yang paling diinginkan, dapat dilakukan dengan menerapkan Technique For Order Preference by Similarity to Ideal Solution (TOPSIS). Metode TOPSIS akan di kombinasikan dengan logika fuzzy untuk menentukan nilai bobot pada setiap atribut kriteria, yang dilanjutkan dengan proses perangkingan untuk menyeleksi alternatif terbaik, dalam hal ini adalah alternatif yang valid sebagai penerima bantuan yang sesuai dengan kriteria. Dengan metode ini diharapkan proses penilaian akan lebih tepat dan akurat karena didasarkan pada nilai kriteria dan bobot yang telah ditentukan.]]>
<![CDATA[Logic Test Educational Game for Children Based on Multimedia ]]>
<![CDATA[Ndruru, Yufita Friska]]>;
<![CDATA[Jamaluddin, Jamaluddin]]>;
<![CDATA[Simamora, Roni Jhonson]]>;
<![CDATA[Harianja, Eva Julia Gunawati]]>
<![CDATA[ Journal of Computer Science and Research (JoCoSiR) Vol. 2 No. 1 (2024): Jan: CNN and Artificial ]]>
Publisher : <![CDATA[Asosiasi Perguruan Tinggi Informatika dan Ilmu Komputer (APTIKOM) Provinsi Sumatera Utara ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.65126/jocosir.v2i1.21
<![CDATA[Along with the development of information technology, the rapid use of technology as a learning media is very good to apply. Many ways can be done to improve the quality of education. This research was conducted by creating an interactive learning media product in the form of a logic test educational game where students are required to learn to solve existing logic problems. The multimedia-based logic test educational game for children is designed to develop children's logic, measure intelligence levels, and become an alternative means of fostering students' interest in learning. The research method used is the method of literature study, interviews, and observations, the stages of analysis and definition of needs, the stages of system and software design, the stages of implementation, and unit testing. The appearance of educational games is designed to be attractive, which is accompanied by images and quizzes that improve student memory and provide new experiences for students. The implementation of this educational game has been carried out on students of SD Negeri 060934 and the results show the enthusiasm level of the students towards the educational game used.]]>
<![CDATA[MODEL BIDIRECTIONAL LSTM UNTUK PEMROSESAN SEKUENSIAL DATA TEKS SPAM ]]>
<![CDATA[Siringoringo, Rimbun]]>;
<![CDATA[Jamaluddin, Jamaluddin]]>;
<![CDATA[Perangin-angin, Resianta]]>;
<![CDATA[Harianja, Eva Julia Gunawati]]>;
<![CDATA[Lumbantoruan, Gortap]]>;
<![CDATA[Purba, Eviyanti Novita]]>
<![CDATA[ METHOMIKA: Jurnal Manajemen Informatika & Komputerisasi Akuntansi Vol. 7 No. 2 (2023): METHOMIKA: Jurnal Manajemen Informatika & Komputersisasi Akuntansi ]]>
Publisher : <![CDATA[Universitas Methodist Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.46880/jmika.Vol7No2.pp265-271
<![CDATA[This study examines the LSTM-based model for processing spam in text data. Spam poses several dangers and risks, both for individuals and organizations. Spam can be a nuisance that hampers both individual and organizational productivity. Much spam contains fraudulent or phishing attempts to obtain sensitive information. Spam detection using deep learning involves the utilization of algorithms and deep neural network models to accurately classify messages as either spam or not spam. Typically, spam detection systems use a combination of these methods to improve the accuracy of identifying spam messages. This study applies the Bi-LSTM deep learning model to sequentially process text (sequencing). The performance of the model is determined based on the loss and accuracy. The data used are the Spam SMS and Spam Email datasets. The test results show that the Bi-LSTM model demonstrates better performance on all tested datasets. Bi-LSTM is able to capture textual patterns from both the context and the text itself, as it can combine information from both directions. The test results prove that the Bi-LSTM model is more effective in text comprehension. So we need to use Snort to maintain network security. Snort is a useful software for observing activity in a computer network. Snort can be used as a lightweight Network Intrusion Detection System (NIDS). Detection is carried out based on the rules that have been described by the administrator in the directory rules contained in the configuration file. Snort can analyze real time alerts, where the mechanism for entering alerts can be in the form of a user syslog, file or through a database. So we can detect attacks on computer networks early.]]>
<![CDATA[Perancangan Aplikasi Mobile untuk Rekomendasi Kuliner Lokal ]]>
<![CDATA[Efrans Michael Harahap]]>;
<![CDATA[Jamaluddin Jamaluddin]]>;
<![CDATA[Eva Julia Gunawati Harianja]]>;
<![CDATA[Marlyna Infryanty Hutapea]]>;
<![CDATA[Resianta Parangin-angin]]>
<![CDATA[ METHOMIKA: Jurnal Manajemen Informatika & Komputerisasi Akuntansi Vol. 10 No. 1 (2026): METHOMIKA: Jurnal Manajemen Informatika & Komputersisasi Akuntansi ]]>
Publisher : <![CDATA[Universitas Methodist Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.46880/jmika.Vol10No1.pp161-167
<![CDATA[The rapid advancement of information technology has shifted the paradigm of tourism and culinary exploration towards mobile platforms. However, local culinary searches in Medan City are currently still conventional and random. Scattered culinary information across various social media without a comprehensive summary often confuses customers and complicates the promotion of micro-culinary businesses (UMKM) in the digital era. Existing commercial platforms often burden local sellers with high platform taxes. This research aims to design and implement an Android-Based Mobile Application for Local Culinary Recommendations as an effective solution to these problems. This application is built natively using the Java programming language for the Android client side, integrated with a PHP Application Programming Interface (API) and MySQL relational database. The system design involves a Client-Server architecture and includes three distinct access rights: User, Culinary Admin, and Super Admin. Implemented features include dining place search, interactive reviews, ratings, popularity levels based on view counts, and Google Maps API integration for precise culinary navigation routes. The result of this research is a self-managed mobile application that accelerates navigation access for users while assisting business owners in managing their stalls independently, objectively, and expanding their promotional reach without internal transaction fees.]]>
<![CDATA[Perancangan Aplikasi Survey Kepuasan Pada Program Studi D-lll Manajemen Informartika dan Komputerisasi Akuntansi Universitas Methodist Indonesia Berbasis Web ]]>
<![CDATA[Eriska Hottriani Sinurat]]>;
<![CDATA[Jamaluddin Jamaluddin]]>;
<![CDATA[Eva Julia G. Harianja]]>
<![CDATA[ TAMIKA: Jurnal Tugas Akhir Manajemen Informatika & Komputerisasi Akuntansi Vol 4 No 2(SEMNASTIK) (2024): TAMIKA: Jurnal Tugas Akhir Manajemen Informatika & Komputerisasi Akunt ]]>
Publisher : <![CDATA[Universitas Methodist Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.46880/tamika.Vol4No2(SEMNASTIK).pp184-190
<![CDATA[Currently, study program services to students are considered as one of the tools to achieve the competitive advantage of study programs. The purpose of this research is to design a web-based application that can measure student satisfaction in the D-III Management Informatics and Computerized Accounting Study Program at Methodist University of Indonesia. So far, the satisfaction survey has been carried out in a conventional way through Google Form and to recap the incoming data using Ms.Excel. The application design is carried out with a modeling language using UML and the programming used is PHP using the MySQL database. This application is designed to collect data on student satisfaction with academic services, learning processes, student services and facilities and infrastructure. The results of this survey will provide recommendations to the head of the study program on indices that need to be improved and support the study program accreditation process. ]]>
