Claim Missing Document
Check
Articles

Found 18 Documents
Search

Tinjauan Penerapan Kecerdasan Buatan Dalam Keamanan Jaringan: Tantangan Dan Prospek Masa Depan Simanjuntak, Ebrika Nadia; Irmayani, Deci; Nasution, Fitri Aini
Jurnal Media Informatika Vol. 5 No. 2 (2024): Jurnal Media Informatika
Publisher : Jurnal Media Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Penerapan kecerdasan buatan (Artificial Intelligence/AI) dalam keamanan jaringan telah menjadi topik yang semakin penting dalam beberapa tahun terakhir. Artikel ini meninjau berbagai aspek terkait penggunaan AI untuk meningkatkan keamanan jaringan, termasuk tantangan yang dihadapi dan prospek masa depan. AI memiliki potensi besar untuk mengidentifikasi dan merespons ancaman keamanan secara lebih cepat dan efisien dibandingkan dengan metode konvensional. Dengan menggunakan teknik pembelajaran mesin (machine learning) dan pemrosesan bahasa alami (natural language processing), AI dapat menganalisis pola data yang kompleks dan mendeteksi anomali yang mungkin menunjukkan adanya serangan. Meskipun demikian, penerapan AI dalam keamanan jaringan tidaklah tanpa tantangan. Salah satu tantangan utama adalah kebutuhan akan data yang besar dan berkualitas tinggi untuk melatih model AI. Selain itu, serangan terhadap sistem AI, seperti adversarial attacks, juga merupakan ancaman signifikan yang perlu diatasi. Ketergantungan pada AI juga menimbulkan masalah etika dan privasi, terutama terkait dengan pengumpulan dan penggunaan data pribadi. Di masa depan, AI diprediksi akan memainkan peran yang semakin penting dalam keamanan jaringan. Pengembangan teknologi AI yang lebih canggih diharapkan dapat mengatasi beberapa tantangan yang ada saat ini, seperti peningkatan kemampuan deteksi dan mitigasi serangan. Kolaborasi antara ahli AI dan pakar keamanan jaringan juga akan menjadi kunci untuk menciptakan sistem keamanan yang lebih robust dan adaptiff. Secara keseluruhan, tinjauan ini menunjukkan bahwa meskipun ada banyak tantangan yang harus dihadapi, potensi AI untuk meningkatkan keamanan jaringan sangat besar. Dengan penelitian dan pengembangan yang tepat, AI dapat menjadi alat yang sangat efektif dalam melindungi jaringan dari berbagai ancaman, sekaligus membuka peluang baru untuk inovasi di bidang keamanan siber. Potensi prospek masa depan dalam integrasi AI dengan keamanan jaringan sangat menjanjikan, namun memerlukan pendekatan yang hati-hati dan bertanggung jawab untuk memaksimalkan manfaatnya sambil meminimalkan risiko yang mungkin timbul
Analisis Minat Konsumen Terhadap Produk Makanan Pada Mie Gacoan Menggunakan Algoritma Decision Tree (Studi Kasus Mie Gacoan Rantau Prapat) Harahap, Ismalya Wahyuni; Nasution, Fitri Aini; Yanris, Gomal Juni
Journal of Computer Science and Information System(JCoInS) Vol 6, No 3: JCoInS | 2025
Publisher : Universitas Labuhanbatu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36987/jcoins.v6i3.7973

Abstract

This study was conducted to analyze consumer interest in Mie Gacoan Rantau Prapat using a Decision Tree-based classification method. This analysis aims to determine the most influential factors in determining consumer interest in the food product. The theoretical basis used is the concept of data mining with classification techniques, where Decision Tree was chosen because of its ability to produce easy-to-understand models. In addition, theories regarding model evaluation such as accuracy, precision, and recall are also used to measure the performance of the built classification. This research methodology includes collecting data from 100 consumer entries which are then divided using the Split Data feature in RapidMiner with a ratio of 60:40, resulting in 40 training data and 60 testing data. The classification process is carried out using the Decision Tree algorithm, while evaluation is carried out with the performance operator to assess the model results. The classification results show that cleanliness is a major factor in determining consumer interest, where the number of consumers in the Interest category is more dominant than the No Interest category. The model evaluation yielded an accuracy of 73.33% with a precision of 73.47% in the Interested class and 72.73% in the Not Interested class, as well as a recall of 92.31% in the Interested class and 38.10% in the Not Interested class. In conclusion, the classification model developed is able to provide a picture of consumer interest patterns with a fairly good level of accuracy. These results can be a strategic reference for Mie Gacoan to improve service quality and cleanliness as the main factors determining consumer interest.
Pengembangan Sistem Informasi Akademik Berbasis Web Sebagai Sistem Pengolahan Nilai Siswa di SMK Muhammadiyah 03 Aek Kanopan Menggunakan Metode Research And Development Priyanti, Priyanti; Harahap, Syaiful Zuhri; Nasution, Fitri Aini; Suryadi, Sudi
Journal of Computer Science and Information System(JCoInS) Vol 6, No 3: JCoInS | 2025
Publisher : Universitas Labuhanbatu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36987/jcoins.v6i3.7878

Abstract

Web-based academic information system is an effective solution to manage the value of students at SMK Muhammadiyah 03 AEK Kanopan. This study aims to develop and evaluate the feasibility of the system using Research and Development methods. The developed system is designed to address challenges in the current value processing process, such as efficiency, accuracy, and data accessibility. In system development, the methodology used includes needs analysis, system design, implementation, and testing. Needs analysis is conducted to identify important features that must be present in the system, such as value input, final value calculation, report generation, and access for teachers, students, and administrative staff. After that, the system is designed with an intuitive interface and powerful functionality. The results of this study indicate that the web-based academic information system developed is very feasible to be used as a value processing system at SMK Muhammadiyah 03 AEK Kanopan. This feasibility is supported by evaluations from various stakeholders, including teachers and administrative staff, who assess this system can improve efficiency, reduce errors, and facilitate access to value information. Thus, this system is expected to be a reliable tool to support the teaching and learning process in the school.
Analisis Dampak Implementasi Sistem Informasi Manajemen Pada Efisiensi Proses Bisnis Kedai Kopi "Sahoeta Kopi" Wonosari Menggunakan Metode K Means Ardian, Aldi; Suryadi, Sudi; Nasution, Fitri Aini; Bangun, Budianto
Journal of Computer Science and Information System(JCoInS) Vol 6, No 3: JCoInS | 2025
Publisher : Universitas Labuhanbatu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36987/jcoins.v6i3.7974

Abstract

This study aims to perform clustering analysis on consumer data coffee shop “Sahoeta coffee” by using the method of K-Means clustering in RapidMiner Studio. The Data used include attributes of Consumer age, number of purchases per day, income per day, and capital per day. The clustering process divides the data into five different clusters, each with different characteristics in terms of purchases and revenue. The clustering results showed that Cluster 0 contained consumers with older age and more frequent shopping, while Cluster 1 contained younger consumers with lower purchases. Clusters 2, 3, and 4 show a pattern of consumers with higher incomes and capital, indicating that they have greater purchasing power. Visualization of clustering results provides a clear picture of consumer segments that can be used to design more specific marketing strategies.
Penerapan Data Mining Untuk Memprediksi Prestasi Akademik Siswa SMKS IT Shah Hamidun Majid Menggunakan Algoritma Decision Tree Sahbana, Ahmad; Nasution, Fitri Aini; Ritonga, Ali Akbar; Suryadi, Sudi
Journal of Computer Science and Information System(JCoInS) Vol 6, No 3: JCoInS | 2025
Publisher : Universitas Labuhanbatu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36987/jcoins.v6i3.7939

Abstract

Education is the main foundation in the development of superior human resources, especially in the digital era that demands the use of Information Technology. One of the main challenges is how schools are able to effectively manage and analyze academic data. Data mining comes as a solution in extracting hidden information from educational data so that it can support strategic decision making. This study focuses on the application of Decision Tree algorithm in predicting student academic achievement in SMKs It Shah Hamidun Majid. The Decision Tree algorithm was chosen because it is easy to understand and is able to provide accurate classification based on various variables, such as attendance, grades, and student background. By utilizing academic data for the 2023/2024 school year, this study is expected to produce predictive models that help schools identify factors that affect student achievement, provide personalized coaching recommendations, and support data-based policies. The results of this study are expected to be a real contribution in the development of academic information systems that are adaptive, inclusive, and oriented to improving the quality of education at the private vocational school level.
Analisis Sentimen Pelayanan Pembayaran Pajak Menggunakan Metode Algoritma Naïve Bayes Pada Kantor Badan Pendapatan Daerah Labuhanbatu Utara Dengan Menggunakan RapidMiner Purba, Mhd. Rafly; Harahap, Syaiful Zuhri; Nasution, Fitri Aini; Bangun, Budianto
Journal of Computer Science and Information System(JCoInS) Vol 6, No 3: JCoInS | 2025
Publisher : Universitas Labuhanbatu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36987/jcoins.v6i3.7959

Abstract

Improving the quality of Public Services is a major need in the era of digitalization, including in the local taxation sector related to the sentiment of services provided in tax payments. The purpose of this study was to analyze public sentiment towards tax payment services in the Office of the regional Revenue Agency (Bapenda) Labuhanbatu Utara by applying Naïve Bayes algorithm using Rapid Miner software. Data analysis through text preprocessing, feature selection, and sentiment classification into positive, negative, and neutral categories. The Data obtained consisted of 225 community comments from the SIMPATDA application and 612 tweets with the hashtag #pajakLabura from Twitter, which reflected people's opinions directly. The analysis process is carried out through the stages of text preprocessing, feature selection, to the classification of sentiments into positive, negative, and neutral categories. The results showed that the Naïve Bayes algorithm is able to classify public opinion with a high degree of accuracy and establish similarities/differences in the aspects of service that are most complained about or appreciated by the public. This study also contributes to the development of data-based evaluation system in the scope of public services.
Penerapan Algoritma Random Forest untuk Klasifikasi Tingkat Keparahan Penyakit pada Data Rekam Medis Nasution, Fitri Aini; Juledi, Angga Putra
Journal of Computer Science and Information System(JCoInS) Vol 6, No 3: JCoInS | 2025
Publisher : Universitas Labuhanbatu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36987/jcoins.v6i3.7993

Abstract

Accurate determination of disease severity is an important step in supporting medical decision-making. This study aims to classify the severity of patients’ diseases into three categories—Mild, Moderate, and Severe—using the Random Forest algorithm. The data used were obtained from patients’ medical records containing structured clinical parameters and have undergone a preprocessing stage, including data cleaning, variable transformation, and splitting into training data (80%) and testing data (20%). The test results show that the Random Forest model achieved an accuracy of 74.77%. The best performance was obtained in the Mild class with a recall value of 0.95 and an f1-score of 0.84. The Moderate class achieved a recall of 0.71 and an f1-score of 0.73, while the Severe class showed perfect precision (1.00) but a low recall (0.12), indicating the model’s limited ability to detect cases in this class. The macro average values for precision, recall, and f1-score were 0.83, 0.60, and 0.59 respectively, while the weighted average values were 0.78, 0.75, and 0.71 respectively. These findings indicate that Random Forest can be used to classify disease severity based on medical records with relatively good performance for the majority class, but further optimization—such as data balancing or parameter adjustment—is needed to improve sensitivity toward classes with fewer samples.
Optimisasi Klasterisasi Nilai Ujian Nasional dengan Pendekatan Algoritma K-Means, Elbow, dan Silhouette Lashiyanti, Allbila Rahajeng; Munthe, Ibnu Rasyid; Nasution, Fitri Aini
Jurnal Ilmu Komputer dan Sistem Informasi (JIKOMSI) Vol. 6 No. 1 (2023): Jurnal Ilmu Komputer dan Sistem Informasi (JIKOMSI)
Publisher : Utility Project Solution

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Penelitian ini bertujuan untuk menerapkan algoritma K-Means dalam klasterisasi data nilai Ujian Nasional (UN) dengan pemanfaatan metode optimasi Elbow dan Silhouette. Klasterisasi data nilai UN memiliki potensi untuk mengidentifikasi pola yang ada dalam hasil ujian dan membantu dalam pemahaman lebih lanjut tentang karakteristik kelompok nilai yang berbeda. Dalam penelitian ini, kami menggunakan data nilai UN sebagai input untuk algoritma K-Means. Proses klasterisasi dilakukan dengan mempertimbangkan penggunaan metode optimasi Elbow dan Silhouette. Metode Elbow digunakan untuk menentukan jumlah klaster yang optimal, sementara metode Silhouette digunakan untuk mengevaluasi kualitas klaster yang terbentuk. Hasil penelitian ini menunjukkan bahwa penerapan algoritma K-Means dengan optimasi Elbow dan Silhouette dapat menghasilkan klaster yang relevan dari data nilai UN. Penentuan jumlah klaster menggunakan metode Elbow memberikan indikasi tentang jumlah kelompok nilai yang paling sesuai, sedangkan evaluasi menggunakan metode Silhouette membantu mengukur sejauh mana kelompok-kelompok tersebut terisolasi dan konsisten. Diharapkan bahwa hasil penelitian ini akan memberikan wawasan lebih lanjut tentang penggunaan algoritma K-Means dalam klasterisasi data nilai UN. Penemuan pola dalam klaster nilai UN dapat memberikan informasi berharga bagi lembaga pendidikan dan pengambil keputusan dalam mengembangkan strategi pendidikan yang lebih efektif. Dengan menggabungkan algoritma K-Means dengan metode optimasi Elbow dan Silhouette, penelitian ini memberikan kontribusi pada pemahaman kita tentang bagaimana teknik klasterisasi dapat diterapkan secara efektif dalam analisis data nilai Ujian Nasional. Selain itu, metodologi yang digunakan dalam penelitian ini dapat memiliki implikasi lebih luas dalam analisis data pada berbagai bidang lainnya