Claim Missing Document
Check
Articles

Found 28 Documents
Search

Penggunaan Metode Speech Processing Untuk Optimasi Peforma Aplikasi NLP Dalam Penerjemah Bahasa Minang Dengan Indonesia Berbasis Android Fadhilah, Raihan Fajar; Aldisa, Rima Tamara
Kesatria : Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen) Vol 5, No 3 (2024): Edisi Juli
Publisher : LPPM STIKOM Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/kesatria.v5i3.461

Abstract

This research examines the use of Speech Processing techniques in an Android-based translation app aimed at improving Natural Language Processing (NLP) for translating between Minang and Indonesian. The Minang language, spoken in West Sumatra, Indonesia, features complex linguistic structures, idiomatic phrases, and specialized vocabulary that challenge automated translation systems. These linguistic attributes make it hard for traditional NLP algorithms to accurately translate the language. To overcome these issues, the app incorporates sophisticated Speech Processing methods to accurately recognize and convert spoken Minang into text for NLP analysis. The NLP component then interprets and translates this text into Indonesian while preserving the Minang language's nuances. The app's evaluation shows significant progress in translation accuracy, especially with simple and common phrases. Nonetheless, it still struggles with intricate sentence structures, dialectal differences, and culturally specific terms unique to Minang. The study highlights the need for customized technological solutions that accommodate the intricacies of regional languages like Minang. Such advancements are essential not only for enhancing communication in multilingual contexts but also for the digital preservation and promotion of indigenous languages in a globalized world.
Sistem Informasi Laboratorium Dengan Metode Joint Application Design (JAD) Berbasis Website (Kasus: Laboratorium Artificial Intelligence Universitas Nasional) Aldisa, Rima Tamara; Wahyuddin, Mohammad Iwan
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 6, No 1 (2022): EDISI MARET
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/j-sakti.v6i1.468

Abstract

Data processing is a routine thing needed by organizations that must be developed properly in order to produce accurate information. Therefore, it is necessary to have a system to perform this task quickly and precisely, namely a computer with superior data processing in processing, storing, presenting, and analyzing so that the results are accurate and fast. Artificial Intelligence Computer Laboratory of the Faculty of Communication and Information Technology at the National University designed an Information System using the Joint Application Design (JAD) method as the first step or system design flow as a means to perform manual administrators or special systems in making reports related to data processing and inventory. The results of the design or system will be made based on the Website.
Aplikasi Pengolahan Data Penjualan Pembangkit Listrik Tenaga Surya Menggunakan Model View Controler Berbasis Framework Codelgniter Dan White Box Testing Rafli, R; Fauziah, F; Aldisa, Rima Tamara
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 5, No 2 (2021): EDISI SEPTEMBER
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/j-sakti.v5i2.367

Abstract

Solar power plants are engaged in providing services and selling solar cells. The design of the sales data processing application uses a database and generates archiving data reports on the sales data report maker. To meet the needs of inputting sales data, there is a special section that handles the admin section, the cashier section, but this work system already uses a web-based data processing application. The method used in data processing applications is in the form of observation, interviews, and documentation. While the application design method uses document flow charts, data flow diagrams, and use cases. Supporting software in making data processing applications using the php database programming language used mysql. The design of the product sales data application produces a database design, namely the goods data and sales table. Black box test results show the features in the application run accordingly and the white box test results in the login menu generate the same region and path value of 7 for the value of Cyclomatic Complexity=7 , Region=7 and Independent Path=7, meaning that the logic used in the program code is appropriate and running and in accordance with the research objectives that the input process of stock goods and transactions can be done optimally.
Perancangan User Experience Aplikasi Lapor Vaksin Kelurahan Menggunakan Metode UCD (User Centered Design) Putra, Gifari Yudiya; Andrianingsih, Andrianingsih; Aldisa, Rima Tamara
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 6, No 1 (2022): EDISI MARET
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/j-sakti.v6i1.457

Abstract

Urban village is an administrative division of the area under the auspices of the sub-district formed by the sub-district government to assist the implementation of the government in development and society. With the current Covid situation, the kelurahan has an important role to help the government accelerate to implement the program evenly. The problem faced by the community is the lack of information on where and when there is a vaccination schedule. Therefore, in order applications that provide information about vaccines. Based on this problem, the authors conducted testing on 302 respondents using the User Centered Design method and the application of the usability method by prioritizing three aspects with the results, namely learmability, efficiency, and staisfacation. User success rate is 91.10%, time-based efficiency is 0.061794869 and system usability scale is 61.42. the existence of this vaccine report application was built to make it easier for sub-districts to record who has not implemented the vaccine and provide notifications about the nearest mass vaccination program
Penerapan Metode Support Vector Machine Dalam Memprediksi Prediksi Cuaca Rifqi, Muhammad Naufal; Aldisa, Rima Tamara
Journal of Computer System and Informatics (JoSYC) Vol 5 No 2 (2024): February 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v5i2.4961

Abstract

Weather is a natural that has a big impact on humans. Information about weather predictions is really needed by humans, especially in the city of Medan. This information is very useful for knowing weather events around us. Data mining is a process of collecting important information from large data, so that it can help make decisions and make accurate predictions. So researchers are interested in conducting research in predicting the weather in the city of Medan using the Support Vector Machine (SVM) method as a solution for predicting the weather in the city of Medan. The application of data mining using the SVM method helps produce precise accuracy for weather based on predetermined criteria. This method is suitable for weather predictions because it is able to provide clear and accurate assessments with weather predictions of 54.55%.
Penerapan Sistem Pendukung Keputusan Metode ROC dan ARAS dalam Seleksi Tim Kreatif Industri Sholeha, Puspa Ayu; Aldisa, Rima Tamara
Journal of Information System Research (JOSH) Vol 5 No 2 (2024): Januari 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v5i2.4752

Abstract

The process of selecting creative team members in the creative industry poses complex challenges. While aspects of formal and technical qualifications can often be clearly measured, elements such as creativity, innovation, and cultural fit are subjective factors that are difficult to measure objectively. Conventional selection methods are often not able to fully incorporate these qualitative aspects, which sometimes results in less precise or less than ideal evaluations. The criteria used in the selection of creative industry teams are portfolio, experience, innovation, technical skills, and collaboration. This emphasizes the need for research and development of more sophisticated and scalable selection methods in the context of the creative industry. The use of a Decision Support System (DSS) is the main focus for handling the problem. applying the ROC (Rank Order Centroid) method, which is utilized to give weight values to the selection criteria, and ARAS (Additive Ratio Assessment), which is utilized to provide the results of creative team selection decisions in the creative industry. The results of the study show that Lolly gets the highest score, which is 1.00000, and is selected as the most suitable creative team for the creative industry.
Perbandingan Algoritma K-Means dan K-Medoids Dalam Pengelompokan Kelas Untuk Mahasiswa Baru Program Magister Faran, Jhiro; Aldisa, Rima Tamara
Journal of Information System Research (JOSH) Vol 5 No 2 (2024): Januari 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v5i2.4753

Abstract

This research discusses a comparison of two grouping algorithms, namely K-Means and K-Medoids, in the context of class grouping for new master's program students. Choosing the right clustering algorithm can help universities optimize resource allocation and maximize student learning experiences. K-Means is a popular clustering algorithm, which works by dividing data into a number of homogeneous groups based on the distance between data points and the cluster center. Meanwhile, K-Medoids is a variation of K-Means that uses actual data points as a cluster representation, which makes it more resistant to outliers. This research involves a dataset of new master's program students which includes various attributes, such as entrance exam scores, educational background, and major preferences. The comparison results between K-Means and K-Medoids were carried out by considering clustering evaluation metrics such as SSE (Sum of Squared Errors) and Silhouette Score. Experimental results show that the performance of K-Means and K-Medoids differs depending on the characteristics of the dataset. K-Means tends to produce more homogeneous groups, but is more sensitive to outliers. In contrast, K-Medoids tend to be more stable in dealing with outliers, but may produce less homogeneous groups. Therefore, the selection of an appropriate clustering algorithm should be based on the specific goals and characteristics of the new master's program student population. This research provides valuable insight for colleges in planning the allocation of classes, mentors, and other resources for new students. The right decisions in class grouping can increase student retention, learning satisfaction, and academic success. In addition, this research also stimulates further discussion in combining different clustering methods to achieve more optimal results in grouping classes of new master's program students.
Penerapan Metode Multi Objective Optimization on The Basis of Ratio Analysis (MOORA) dalam Penentuan Pembimbing Skripsi Terbaik Nasution, Aisah Amini; Aldisa, Rima Tamara; Mesran, Mesran; Fadillah, Rizkah
Journal of Information System Research (JOSH) Vol 5 No 2 (2024): Januari 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v5i2.4803

Abstract

The first step in thesis preparation involves titling and selecting a supervisor. Choosing the best supervisors aims to enhance both lecturers' enthusiasm and the quality of student guidance. To identify the most suitable lecturer, thorough consideration and a decision-support system are essential. In this research, the authors employed the Multi-Objective Optimization on the Basis of Ratio Analysis (MOORA) method as a technique integrated into the decision support system. This method aids in determining attribute weight values and the ranking process, ultimately selecting the most favorable supervisor from various available options. From the results of the application of the MOORA method in knowing the best thesis supervisor, namely on alternative A8 with a value of 0.3288 on behalf of Marigan Sianturi, SE, and M.kom,