cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Jati Sasongko Wibowo
Contact Email
jatisw@edu.unisbank.ac.id
Phone
+6281325297663
Journal Mail Official
dinamik@edu.unisbank.ac.id
Editorial Address
Jl. Tri Lomba Juang No. 1 Semarang
Location
Kota semarang,
Jawa tengah
INDONESIA
Dinamik
Published by Universitas Stikubank
ISSN : 08549524     EISSN : 26231786     DOI : 10.35315/dinamik.v28i1
Core Subject : Science,
Computer Science & IT
The Jurnal DINAMIK aims to: Promote a comprehensive approach to informatics engineering and management incorporating viewpoints of different applications (computer graphics, computer networks and security, computer vision, computational intelligence, databases, big data, IT project management, and other fields relevant to information technology. Encourage scientists, practicing engineers, and others to conduct research and similar activities.
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 505 Documents
 44   45   46   47   48 
Penerapan Metode Decision Tree dan Naïve Bayes pada Kasus Kriminalitas di Lampung Khadafi, Muhammad; Yudhistira, Aditia
Dinamik Vol 31 No 1 (2026)
Publisher : Universitas Stikubank

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35315/dinamik.v31i1.10411

Abstract

Crime, an unlawful act that contradicts ethics and norms, has now become a primary factor for the police in Lampung province. This presents a challenge for the police institution in predicting high crime rates. However, there are still many crimes that have not become the main focus of problem-solving at the Lampung Regional Police.This research aims to identify the types and criminal acts of crime with the highest recorded incidence in a crime dataset by performing classification using the Naïve Bayes algorithm. The data was obtained from investigators at the Directorate of General Criminal Investigation of the Lampung Regional Police, with a total of 12,034 JTP (Total Criminal Acts) and 7,518 PTP (Crime Resolution) data points for each type of crime, distributed across the Regional Police, City Police, and District Police throughout Lampung province. The classification process using the Naïve Bayes algorithm reveals the relationship between the work unit (Satker) and the type of crime handled, thereby identifying crime patterns based on the location where they are handled. The results of the research, which involved converting numerical data into binomial (binary) form using the "Numerical to Binominal" feature in Rapid miner, show that the analysis and modeling process, especially in algorithms like Naïve Bayes or decision trees, is more effective when using data in a binary format. Thus, the initial dataset can be visualized in the form of a , with the size of the text varying according to the level of each high-incidence crime; the larger the text, the more frequently or significantly the crime occurred or was reported. The application of this method can help in identifying patterns, dominant trends, and areas of focus for more targeted law enforcement efforts or crime prevention policies.
Analisis Efektifitas Komunikasi Publik Pemerintah Ptov. Lampung Melalui Media Sosial Menggunakan Metode Regresi Logistik Saputri, Bella; Satria, Muhammad Najib Dwi
Dinamik Vol 31 No 1 (2026)
Publisher : Universitas Stikubank

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35315/dinamik.v31i1.10413

Abstract

Social media has become a strategic tool for the government to disseminate public information quickly, interactively, and efficiently in the digital era. The Lampung Provincial Government utilizes various social media platforms such as Facebook, Instagram, and TikTok to support public communication activities. This study aims to analyze the effectiveness of public communication by measuring the level of activity of Regional Apparatus Organization (OPD) social media accounts using the logistic regression method. Data were collected through web scraping techniques on the official OPD social media accounts and then processed using a quantitative approach. The results show that the level of social media activity influences the effectiveness of public communication and the transparency of government information. These findings are expected to serve as a basis for local governments in designing public communication strategies that are more optimal and adaptive to developments in digital technology.
Penerapan Algoritma Naïve Bayes untuk Prediksi Minat Siswa Melanjutkan Studi ke Perguruan Tinggi Al-Kasidmi, Afif; Megawaty, Dyah Ayu
Dinamik Vol 31 No 1 (2026)
Publisher : Universitas Stikubank

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35315/dinamik.v31i1.10416

Abstract

This study aims to analyze the factors that influence students' interest in continuing their education to college using a machine learning approach. Data was collected through an online questionnaire completed by 727 students between July 27 and August 22, 2025, covering 23 variables consisting of respondent identity (gender, grade level, major) as well as internal and external factors such as parental support, learning motivation, and preferred type of college. The data preparation stage was carried out through column cleaning, deletion of empty data, encoding of categorical variables, and division of the dataset into 80% training data and 20% test data. The Naive Bayes algorithm of the CategoricalNB type was used because it was suitable for the categorical nature of the data. The evaluation results showed that the model was able to predict student interest with 96% accuracy. For the class of students interested in continuing their studies, the precision, recall, and F1-score values were above 0.95, while the performance in the class of students who were not interested was slightly lower due to the smaller amount of data. These findings show that Naive Bayes is proven to be effective and reliable in classifying students' interest in continuing their studies and can be the basis for decision-making in designing more targeted educational strategies.
Perbandingan Hasil Aspect-Based Sentiment Analysis pada Ulasan Google Review Restoran Sunda di Bogor Menggunakan Fine-Tuning IndoBERT Latifah, Siti; Erfina, Adhitia; Warman, Cecep
Dinamik Vol 31 No 1 (2026)
Publisher : Universitas Stikubank

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35315/dinamik.v31i1.10417

Abstract

Penelitian ini dilakukan untuk menganalisis dan membandingkan sentimen pelanggan terhadap lima restoran Sunda di Kota Bogor menggunakan metode Aspect-Based Sentiment Analysis (ABSA) berbasis Fine-Tuning IndoBERT. Ulasan pelanggan di platform digital seperti Google Review berpengaruh besar terhadap citra dan keputusan konsumen, sementara jumlah ulasan yang besar sulit dijelaskan secara manual. Data penelitian diperoleh dari 3.232 ulasan Google Review dan diproses menjadi 3.010 data yang dikelompokkan berdasarkan lima aspek utama, yaitu makanan, pelayanan, harga, suasana, dan fasilitas. Metode Fine-Tuning IndoBERT digunakan untuk mengklasifikasikan sentimen positif, netral, dan negatif, dengan evaluasi melalui metrik akurasi, presisi, recall, dan F1-score. Hasil menunjukkan bahwa model memiliki performa sangat baik dengan akurasi tertinggi sebesar 97,51% pada aspek pelayanan dan terendah 92,52% pada aspek makanan, serta nilai F1-score makro di atas 0,91. Analisis menunjukkan bahwa Bumi Aki unggul pada aspek makanan dan fasilitas, Saung Abah pada pelayanan, Saung Kuring pada harga, dan Gumati pada suasana. Hasil penelitian ini menunjukkan bahwa Fine-Tuning IndoBERT efektif dalam memahami opini pelanggan berbahasa Indonesia dan dapat menjadi acuan bagi pelaku usaha kuliner dalam meningkatkan kualitas layanan.
IMPLEMENTASI METASPLOIT FRAMEWORK DAN NMAP UNTUK DETEKSI AWAL SERANGAN PADA KEAMANAN WEB Agshari, M. Faisal; Amarudin, Amarudin
Dinamik Vol 31 No 1 (2026)
Publisher : Universitas Stikubank

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35315/dinamik.v31i1.10420

Abstract

Web security is an important aspect in maintaining data integrity and confidentiality in the digital age, where cyber threats are increasingly complex and difficult to detect. This research was conducted because there are still many web systems that are vulnerable to attacks due to weak early detection of security gaps. For this reason, this study implements a combination of Nmap and Metasploit Framework as the main tools in proactively detecting and testing system vulnerabilities. The research method was carried out in three stages, namely data collection by scanning the network using Nmap to identify open ports and services, selecting the appropriate testing tools, and controlled exploitation using Metasploit on the Metasploitable2 test system. The results of the study show that Nmap is capable of mapping the attack surface in detail, while Metasploit can validate the scan results through exploitation of vulnerable services such as vsftpd 2.3.4, which successfully provided root access to the target system. The combination of these two tools has proven to be effective in conducting systematic, fast, and accurate early detection of attacks, so that it can be used as a preventive measure to improve web security from potential cyber threats.
Evaluasi Sistem Surat Keterangan Pendamping Ijazah (SKPI) Universitas Semarang Melalui Audit Dengan COBIT 2019 Fokus Pada Domain DSS dan MEA Aryanti, Diva Eka; Handayani, Titis
Dinamik Vol 31 No 1 (2026)
Publisher : Universitas Stikubank

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35315/dinamik.v31i1.10262

Abstract

Penelitian ini bertujuan untuk mengevaluasi Sistem Surat Keterangan Pendamping Ijazah (SKPI) di Universitas Semarang melalui audit dengan menggunakan kerangka kerja COBIT 2019, dengan fokus pada domain Deliver, Service and Support (DSS) dan Monitor, Evaluate and Assess (MEA). SKPI berfungsi sebagai dokumen resmi yang memberikan informasi tambahan mengenai kompetensi lulusan di luar nilai akademik (ijazah), sehingga penting untuk memastikan kualitas dan relevansinya dengan kebutuhan industri. Metodologi yang digunakan dalam penelitian ini meliputi pengumpulan data primer melalui observasi, wawancara, dan kuesioner, serta data sekunder dari literatur terkait. Hasil penelitian menunjukkan bahwa tingkat kapabilitas pada sub-domain DSS dan MEA berada pada level 4 yang dilabeli sebagai terkelola, dengan nilai rata-rata masing-masing 3,73 untuk DSS dan 3,85 untuk MEA. Meskipun demikian, terdapat sejumlah rekomendasi untuk meningkatkan nilai Maturity Level sistem, dengan GAP masing-masing sebesar 1,07 untuk DSS dan 1,04 untuk MEA. Rekomendasi yang disampaikan meliputi peningkatan kompetensi petugas teknis, pengembangan aplikasi mobile, dan sosialisasi prosedur penyajian SKPI secara digital. Dengan adanya rekomendasi tersebut, diharapkan dapat memberikan masukan positif dalam pengelolaan SKPI di Universitas Semarang dan meningkatkan daya saing lulusan di pasar kerja.Kata Kunci: Audit Sistem, Maturity Level, Rekomendasi, Deliver, Service and Support (DSS), Monitor, Evaluate and Assess (MEA)
Perbandingan Kinerja Model Klasifikasi dalam Memprediksi Intensi Pembelian Pengunjung E-Commerce Eniyati, Sri; Noor Santi, Rina Candra; Yulianton, Heribertus; Sunardi, Sunardi; Sulastri, Sulastri; Sugiyamta, Sugiyamta
Dinamik Vol 30 No 2 (2025)
Publisher : Universitas Stikubank

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35315/dinamik.v30i2.10593

Abstract

This study aims to analyze and compare the performance of the Naive Bayes, K-Nearest Neighbors (KNN), and Decision Tree algorithms in predicting the purchase intention of e-commerce visitors using the Online Shoppers Purchasing Intention Dataset, which consists of 12,330 records and 18 variables, with the Revenue variable serving as the classification target. The preprocessing stage involved transforming categorical and boolean variables into numerical form, standardizing features using StandardScaler, and splitting the dataset into 80 percent training data and 20 percent testing data. Model evaluation was conducted using accuracy, precision, recall, F1-score, and ROC-AUC metrics, and was further strengthened by 10-fold cross-validation to obtain more stable results. The findings indicate that KNN achieved the highest accuracy of 0.866180, while Naive Bayes produced the highest recall value of 0.690998 and the highest ROC-AUC value of 0.821696. Meanwhile, Decision Tree demonstrated relatively balanced performance with an accuracy of 0.857259 and an F1-score of 0.571776, whereas the cross-validation results identified KNN as the model with the highest average accuracy of 0.8770. These findings suggest that the selection of a classification model for purchase intention prediction cannot rely solely on a single evaluation metric, as each algorithm possesses different strengths. Therefore, a comparative approach among algorithms can help determine the most suitable model for supporting consumer behavior analysis on e-commerce platforms.
Klasifikasi Tipe Pokémon Berdasarkan Statistik Tempur Menggunakan Algoritma Random Forest Nugroho Kumala Destianto; Yohanes Simarmata; Nurul Hidayanah; Icha Winadya Permadani; Heni Sulistiani
Dinamik Vol 31 No 2 (2026)
Publisher : Universitas Stikubank

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35315/dinamik.v31i2.10395

Abstract

This study aims to classify Pokémon types based on battle statistics using the Random Forest algorithm. The dataset used comes from the file pokemon_bw.csv, which contains information such as Pokédex number, name, type, abilities, and battle stat values (HP, Attack, Defense, Special Attack, Special Defense, Speed). Data preprocessing was carried out to clean and prepare the data, including primary type extraction, label encoding, feature selection, and feature standardization. After that, the dataset was split into training and testing data with an 80:20 ratio. The classification model was built using Random Forest with 100 decision trees and evaluated using accuracy, classification report, confusion matrix, and multiclass ROC Curve metrics. The results show that the model achieved an accuracy of 64.8%, with the best performance in the 'rock', 'steel', and 'dragon' classes, while the 'flying' and 'ghost' classes were still difficult to classify accurately. Confusion matrix. It shows that some types have quite significant misclassification errors, such as 'ground' which is often predicted as 'grass' and 'rock' which is often misclassified as 'steel'. ROC Curve evaluation also proves that most classes have an AUC above 0.80, indicating the model's ability to distinguish between classes. With this approach, this study provides an initial analysis of the potential for predicting Pokémon types based on battle statistics, which can be further developed through handling class imbalances or using other ensemble techniques.
Model Kolaborasi Chatbot dan Manusia dengan Mekanisme Handoff berbasis Trigger untuk Optimalisasi Layanan Pelanggan UMKM di Era Digital Dimas Adi Wicaksono; Heru Yulianto; Aji Priyambodo
Dinamik Vol 31 No 2 (2026)
Publisher : Universitas Stikubank

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35315/dinamik.v31i2.10398

Abstract

The development of artificial intelligence (AI) technology has changed the paradigm of customer service by introducing Chatbots as a solution to improve service efficiency and availability. However, in the context of micro, small, and medium enterprises (MSMEs), limited resources and the complexity of customer interactions require a hybrid approach that integrates Chatbots with human agents. This study designed a model for collaboration between Chatbots and humans with a trigger-based handoff mechanism that enables automatic transitions based on measurable indicators, such as negative sentiment, complex questions, and explicit customer requests. Using a simulation approach on 5,000 customer conversations, this study found that the hybrid model was able to increase the Customer Satisfaction Score (CSAT) from 3.6 to 4.2, reduce completion time from 6.2 minutes to 3.8 minutes, and increase customer loyalty from 52% to 68%. The implementation roadmap is structured in three levels (beginner, intermediate, advanced) to suit the varying digital capabilities of SMEs. This research contributes to the literature on human-AI collaboration and omnichannel customer experience, and offers an applicable framework for SMEs to accelerate the digital transformation of customer service.
IMPLEMENTASI SEGMENTASI WARNA HSV UNTUK IDENTIFIKASI KARAT PADA MATERIAL LOGAM Muhammad Bagus Bintang Timur; Royansyah Royansyah; Dewi Kusumaningsih
Dinamik Vol 31 No 2 (2026)
Publisher : Universitas Stikubank

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35315/dinamik.v31i2.10403

Abstract

Corrosion on metal surfaces poses significant risks to structural durability and operational safety in industrial environments. Manual detection is often time-consuming and prone to errors, especially under inconsistent lighting. This research addresses the challenge by implementing a color-based segmentation technique using the HSV (Hue, Saturation, Value) color space. The input images undergo preprocessing and conversion from RGB to HSV to enhance color differentiation. A defined range of HSV values, corresponding to typical rust tones, is used to generate binary masks that highlight corroded regions. The algorithm is built using the OpenCV library to support real-time analysis. A series of test images with varying illumination and corrosion patterns were analyzed to assess the method’s effectiveness. The results confirm that the HSV-based segmentation accurately separates rusted areas from unaffected surfaces, maintaining reliable performance under diverse conditions. The proposed approach offers a lightweight and efficient tool for early rust detection, supporting preventive maintenance strategies in industrial inspection workflows.

Page 46 of 51 | Total Record : 505

 44   45   46   47   48 

Filter by Year

2002 2026


Reset
Filter By Issues
All Issue Vol 31 No 2 (2026) Vol 31 No 1 (2026) Vol 30 No 2 (2025) Vol 30 No 1 (2025) Vol 29 No 2 (2024) Vol 29 No 1 (2024) Vol 28 No 2 (2023) Vol 28 No 1 (2023) Vol 27 No 2 (2022) Vol 27 No 1 (2022) Vol 26 No 2 (2021) Vol 26 No 1 (2021) Vol 25 No 2 (2020) Vol 25 No 1 (2020) Vol 24 No 2 (2019) Vol 24 No 1 (2019) Vol 23 No 2 (2018) Vol 23 No 1 (2018) Vol 22 No 2 (2017) Vol 22 No 1 (2017) Vol 21 No 2 (2016) Vol 21 No 1 (2016) Vol 20 No 2 (2015) Vol 20 No 1 (2015) Vol 19 No 2 (2014) Vol 19 No 1 (2014) Vol 18 No 2 (2013) Vol 18 No 1 (2013) Vol 17 No 2 (2012) Vol 17 No 1 (2012) Vol 16 No 2 (2011) Vol 16 No 1 (2011) Vol 15 No 2 (2010) Vol 15 No 1 (2010) Vol 14 No 2 (2009) Vol 14 No 1 (2009) Vol 13 No 2 (2008) Vol 13 No 1 (2008) Vol 12 No 2 (2007) Vol 12 No 1 (2007) Vol 11 No 2 (2006) Vol 11 No 1 (2006) Vol 10 No 3 (2005) Vol 10 No 2 (2005) Vol 10 No 1 (2005) Vol 9 No 2 (2004) Vol 8 No 2 (2003) Vol 8 No 1 (2003) Vol 7 No 2 (2002) Vol 7 No 1 (2002) More Issue