Claim Missing Document
Check
Articles

Found 3 Documents
Search
Journal : Jupiter

Analisis Tingkat Kematangan Tata Kelola Teknologi Informasi Menggunakan Kerangka Kerja COBIT5 Deri Haryanto; Didi Supriyadi; Yudha Saintika
JUPITER (Jurnal Penelitian Ilmu dan Teknologi Komputer) Vol 13 No 2 (2021): JUPITER Edisi Oktober 2021
Publisher : Teknik Komputer Politeknik Negeri Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5281/3364.jupiter.2021.10

Abstract

Kesuksesan tata kelola sebuah organisasi merujuk pada sejauh mana tingkat kematangan tata kelola TI dilakukan. Penyelenggaraaan Pemerintah dalam meningkatkan pelayanan publik (public service) memerlukan tata kelola yang baik (Good Governance). Implementasi Good Governance akan menjamin transparansi, efisiensi, dan efektifitas penyelenggaraan pemerintah. Dinas Komunikasi dan Informatika Kabupaten Banyumas merupakan institusi pemerintahan yang saat ini berupaya untuk mewujudkan smartcity Banyumas. Saat ini Dinas Komunikasi dan informatika Banyumas masih mengalami beberapa kendala pada pelaksanan Tata kelola TI antara lain: Penerapan teknologi Big Data, Internet Of Things, maupun Artificial intelligence, serta belum adanya kebijakan yang mengatur mengenai kolaborasi dan transparansi data. Hal ini menjadi kendala dalam upaya mewujudkan smart city serta membutuhkan strategi dalam pemanfaatan TIK untuk mengatasi kendala-kendala tersebut. Untuk dapat mengatasi kendala – kendala tersebut perlu diketahui terlebih dahulu kondisi kematangan pemanfaatan teknologi informasi saat ini (as is). Penelitian ini menggunakan framework COBIT5 (Control Objectives for Information and Related Technology) yaitu untuk mengukur tingkat kematangan tata kelola teknologi infromasi Dinas Komunikasi dan Informatika Kabupaten Banyumas. Sub Domain yang digunakan pada penlitian ini adalah EDM01, EDM05, APO01, APO02, APO03, APO04, DSS01, DSS02, dan MEA01. Hasil analisis tingkat kematatangan secara keseluruhan berada pada level 4 (Predictable proccess) dengan target pengelolaan TI berada pada level 5 (optimizing).
Enterprise Architecture Desa Menggunakan Framework TOGAF ADM Sekar Aninditya Sugi Ananda; S. Thya Safitri; Didi Supriyadi
JUPITER (Jurnal Penelitian Ilmu dan Teknologi Komputer) Vol 13 No 2 (2021): JUPITER Edisi Oktober 2021
Publisher : Teknik Komputer Politeknik Negeri Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5281/3473.jupiter.2021.10

Abstract

Sudagaran Village is one of the villages that has implemented Information Technology (IT) to support business processes and village government operations. One of the business processes that utilize IT is a letter request service, using the SMARD application. However, in the business process for the letter application, the community must come to the Village Hall to collect the required documents and fill out the letter application form. This process is considered less effective. So that the village government expects the planning and development of a better and more effective information system, which can be accessed by the community starting from collecting files, filling out forms to receiving/downloading letters without having to go to the Village Hall. An enterprise architecture is needed for the design of the Sudagaran Village information system, which is focused on the business processes of 5 types of mail services, namely Letter of Introduction, Certificate of Population Move, Cover Letter of SKCK, Certificate of Underprivileged, and Business Certificate using TOGAF ADM. This study uses 6 stages of TOGAF ADM, namely the Preliminary Phase to Phase E – Opportunities & Solutions because it focuses on planning. This study resulted in an EA document containing business artifacts, data, applications, and technology made using Sparx, which can be used as a guide for Sudagaran Village to support the smart village concept in Banyumas Regency.
Komparasi Metode Machine Learning dan Deep Learning untuk Deteksi Emosi pada Text di Sosial Media Rona Nisa Sofia Amriza; Didi Supriyadi
JUPITER (Jurnal Penelitian Ilmu dan Teknologi Komputer) Vol 13 No 2 (2021): JUPITER Edisi Oktober 2021
Publisher : Teknik Komputer Politeknik Negeri Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5281/3603.jupiter.2021.10

Abstract

Emotion Detection is the process of human emotions recognition, it extracting emotions such as happy, sad, and angry, which are obtained from human natural language. Linguistic Style has a wide range, emotional representations occur to millions of people and makes it difficult to infer a person's emotion in a concrete way. Multilabel datasets are also a challenge to deal in emotion detection. Therefore, an in-depth study of the appropriate method for emotional detection is needed. This study performs a comparative analysis between machine learning methods and deep learning methods. The machine learning methods used are Naïve Bayes, Random Forest, SVM, Gradient Boosting and Logistic Regression. The deep learning methods used in this study include LSTM, CNN, MLP, GRU and RNN. This research discovered that Deep learning has a better performance than machine learning, it seen from the accuracy values ​​of LSTM, CNN, MLP, GRU and RNN which exceed the accuracy values ​​of Naïve Bayes, SVM, Logistic Regression, Gradient Boosting and Random Forest.