Kasmira Kasmira
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Kasmira Kasmira has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Purnawansyah Purnawansyah
Universitas Muslim Indonesia
2 shared publications - Abdul Rachman Manga'
Universitas Negei Malang, universitas Muslim Indonesia
1 shared publication - Anik Nur Handayani
Universitas Negeri Malang
1 shared publication - Benny Leonard Enrico Panggabean
Universitas Muslim Indonesia
1 shared publication - Heru Wahyu Herwanto
Universitas Negeri Malang
1 shared publication - La Saiman
Universitas Muslim Indonesia
1 shared publication
Latest Publications
- Open Access
- 7 April 2023
- Published by Universitas Muslim Indonesia in ILKOM Jurnal Ilmiah
- Vol. 15 (1) , 186-192
Analysis of the Ensemble Method Classifier's Performance on Handwritten Arabic Characters Dataset
Arabic character handwriting is one of the patterns and characteristics of each person's writing. This characteristic makes Arabic writing more challenging if the letter recognition process is based on a dataset of Arabic scripts. This Arabic script has been presented in a dataset totaling 16800, each representing a class of hijaiyah letters starting from alif to yes, consisting of 600 data for each class. The accuracy of the data used can be increased using the ensemble method. By using multiple algorithms at simultaneously, the ensemble technique can raise the level or result of a score in machine learning. This study's primary goal is to evaluate the ensemble method classifier's performance on datasets of handwritten Arabic characters. The classifier uses the ensemble method by applying the proposed soft voting to provide a multiclass classification of three machine learning algorithms, namely, SVM, Random Forest, and Decision Tree for classification. This research process produces an accuracy value for the voting classifier of 0.988 and several other SVM algorithms with an accuracy of 0.103, a random forest with an accuracy of 1.0, and a decision tree with an accuracy of 0.134. The test results used the confusion matrix evaluation model, including accuracy, precision, recall, and f1-score of 0.99.
- 7 April 2023
- Published by Universitas Muslim Indonesia in ILKOM Jurnal Ilmiah
- Vol. 15 (1) , 186-192
Open AccessAnalysis of the Ensemble Method Classifier's Performance on Handwritten Arabic Characters Dataset
Arabic character handwriting is one of the patterns and characteristics of each person's writing. This characteristic makes Arabic writing more challenging if the letter recognition process is based on a dataset of Arabic scripts. This Arabic script has been presented in a dataset totaling 16800, each representing a class of hijaiyah letters starting from alif to yes, consisting of 600 data for each class. The accuracy of the data used can be increased using the ensemble method. By using multiple algorithms at simultaneously, the ensemble technique can raise the level or result of a score in machine learning. This study's primary goal is to evaluate the ensemble method classifier's performance on datasets of handwritten Arabic characters. The classifier uses the ensemble method by applying the proposed soft voting to provide a multiclass classification of three machine learning algorithms, namely, SVM, Random Forest, and Decision Tree for classification. This research process produces an accuracy value for the voting classifier of 0.988 and several other SVM algorithms with an accuracy of 0.103, a random forest with an accuracy of 1.0, and a decision tree with an accuracy of 0.134. The test results used the confusion matrix evaluation model, including accuracy, precision, recall, and f1-score of 0.99.
- Open Access
- 19 December 2022
- Published by Universitas Muslim Indonesia in ILKOM Jurnal Ilmiah
- Vol. 14 (3) , 314-322
The development of Web-based information system using quick UDP internet connection
The Academic Information System (xSIA) is built to its users to manage Study Program modules, including student academic grades. xSIA applying the Moodle Learning Management System (LMS) was developed by implementing Quick UDP Internet Connection (QUIC) technology with the HTTP/3 protocol which can demonstrate protocol transaction speed performance. The design of information systems and databases employs the Convention Over Configuration paradigm. The Prototyping Model is used to graphically represent the workflow of the system with an experimental research design. System modeling utilizes Unified Modeling Language (UML) tools, Data Base Management System (DBMS) using PostgreSQL, and UDP ports as a means of data communication. The implementation of Quick UDP Internet Connection (QUIC) on the xSIA moodle LMS is effective for real-time communications that do not require conditions to open, maintain, or terminate connections as in streaming video conference. It is also optimal because the UDP data is transferred individually and checked for its integrity upon arrival. When a video streaming transaction last 02:36 seconds with a file size of 4.1mb, there is a significant difference of 100.98ms in the waiting time to first byte (ttfb).
- 19 December 2022
- Published by Universitas Muslim Indonesia in ILKOM Jurnal Ilmiah
- Vol. 14 (3) , 314-322
Open AccessThe development of Web-based information system using quick UDP internet connection
The Academic Information System (xSIA) is built to its users to manage Study Program modules, including student academic grades. xSIA applying the Moodle Learning Management System (LMS) was developed by implementing Quick UDP Internet Connection (QUIC) technology with the HTTP/3 protocol which can demonstrate protocol transaction speed performance. The design of information systems and databases employs the Convention Over Configuration paradigm. The Prototyping Model is used to graphically represent the workflow of the system with an experimental research design. System modeling utilizes Unified Modeling Language (UML) tools, Data Base Management System (DBMS) using PostgreSQL, and UDP ports as a means of data communication. The implementation of Quick UDP Internet Connection (QUIC) on the xSIA moodle LMS is effective for real-time communications that do not require conditions to open, maintain, or terminate connections as in streaming video conference. It is also optimal because the UDP data is transferred individually and checked for its integrity upon arrival. When a video streaming transaction last 02:36 seconds with a file size of 4.1mb, there is a significant difference of 100.98ms in the waiting time to first byte (ttfb).
- Open Access
- 30 July 2021
- Published by Universitas Muslim Indonesia in Ilmu Komputer untuk Masyarakat
- Vol. 2 (1) , 49-54
Bimbingan Teknis Pemanfaatan xSIA untuk Pelaporan Akademik Siswa di SDN No. 133 Kabupaten Takalar
Bimbingan Teknis Pemanfaatan xSIA untuk Pelaporan Akademik Siswa di SDN No. 133 Kabupaten Takalar
- 30 July 2021
- Published by Universitas Muslim Indonesia in Ilmu Komputer untuk Masyarakat
- Vol. 2 (1) , 49-54
Open AccessBimbingan Teknis Pemanfaatan xSIA untuk Pelaporan Akademik Siswa di SDN No. 133 Kabupaten Takalar
Bimbingan Teknis Pemanfaatan xSIA untuk Pelaporan Akademik Siswa di SDN No. 133 Kabupaten Takalar