cover
Contact Name
Firdaus Annas
Contact Email
firdaus@uinbukittinggi.ac.id
Phone
+6285278566869
Journal Mail Official
knowbase.uinbukittinggi@gmail.com
Editorial Address
Data Center Building - Kampus II Universitas Islam Negeri Sjech M. Djamil Djambek Bukittinggi. Jln Gurun Aua Kubang Putih Kecamatan Banuhampu Kabupaten Agam Sumatera Barat Telp. 0752 33136 Fax 0752 22871
Location
Kab. agam,
Sumatera barat
INDONESIA
Knowbase : International Journal of Knowledge in Database
ISSN : 27980758     EISSN : 27977501     DOI : https://www.doi.org/10.30983/knowbase
Core Subject : Science,
Knowbase : International Journal of Knowledge in Database is a peer-reviewed journal that publishes articles which contribute new results in all areas of the database management systems & its applications. The goal of this journal is to bring together researchers and practitioners from academia to focus on understanding Modern developments in this field, and establishing new collaborations in these areas. Authors are solicited to contribute to the journal by submitting articles that illustrate research results that describe significant advances in the areas of Database management systems.
Articles 150 Documents
AS Spatiotemporal Analysis of LSCI Variations in ASEAN Using ANOVA and Cluster Techniques (2017–2022) Setiawan, Ariyono; Antoni Arif Priadi; Abdul Razak Bin Abdul Hadi; Erwin Faller
Knowbase : International Journal of Knowledge in Database Vol. 5 No. 1 (2025): June 2025
Publisher : Universitas Islam Negeri Sjech M. Djamil Djambek Bukittinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30983/knowbase.v5i1.9583

Abstract

This study investigates maritime connectivity performance in ASEAN countries using the Liner Shipping Connectivity Index (LSCI) from 2019 to 2023. It aims to identify significant trends, segment national performance, and provide policy-relevant insights on regional maritime development. The research is grounded in transport connectivity and regional integration theory, emphasizing the role of liner shipping as a critical enabler of trade efficiency and economic cooperation in Southeast Asia. The study employs a quantitative approach using longitudinal LSCI data across ten ASEAN member states. It applies descriptive statistics, linear regression modeling for each country, and clustering through k-means (fastclus) to categorize national maritime connectivity performance. Indonesia records the highest average LSCI (49.28), indicating a consistent lead in regional maritime connectivity. Cambodia demonstrates the strongest upward trend with a significant positive slope (β = 0.98; p < 0.01), followed by Myanmar (β = 0.61; p < 0.05) and Laos (β = 0.58; p < 0.01). Cluster results suggest three distinct groups of countries based on average connectivity levels, highlighting disparities and the need for policy harmonization. The regression models explain up to 94% of the variance in several countries' LSCI growth. The findings support regional policy formulation to strengthen weaker maritime economies and align ASEAN maritime strategies with trade facilitation goals. This study presents a novel integration of trend modeling and cluster segmentation of LSCI data within the ASEAN context. It contributes both theoretically to the study of maritime connectivity metrics and practically to policy and infrastructure development.
Lung X-Ray Image Classification Using DenseNet-169 and Bayesian Optimization Shahira, Fayza; Negara, Benny Sukma
Knowbase : International Journal of Knowledge in Database Vol. 5 No. 1 (2025): June 2025
Publisher : Universitas Islam Negeri Sjech M. Djamil Djambek Bukittinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30983/knowbase.v5i1.9618

Abstract

The increasing prevalence of lung diseases caused by infections such as Pneumonia and COVID-19 highlights the urgent need for accurate and efficient early detection methods. This study aims to improve the classification performance of chest X-ray images using the DenseNet-169 deep learning architecture, with a focus on hyperparameter optimization through Bayesian Optimization. The dataset used consists of 3,000 chest X-ray images—1,000 each for Normal, Pneumonia, and COVID-19 classes—sourced from Mendeley Data and split with an 80:20 ratio for training and testing. The baseline DenseNet-169 model initially achieved an accuracy of 96.837%, although slight overfitting was observed. By applying Bayesian Optimization, several key hyperparameters—such as learning rate, number of epochs, batch size, and kernel size—were systematically optimized. The optimized model demonstrated an improved accuracy of 97.33%, with the most notable increase in the recall score of the Normal class, which rose by 3.19% to 97%, effectively reducing the false negative rate for healthy cases. In addition, the final model recorded a precision of 99% and a specificity of 99.50% for the COVID-19 class, indicating a strong discriminative capability in identifying critical conditions. Analysis of the training and validation curves showed good convergence, confirming the effectiveness of the optimization in reducing overfitting and enhancing the model's generalization ability. Overall, the results of this study demonstrate that the application of Bayesian Optimization significantly enhances the performance of DenseNet-169 in chest X-ray image classification. The resulting model is more balanced, robust, and reliable, showing great potential for integration into AI-based automated diagnostic systems in the field of respiratory healthcare.
End-to-End Text-to-Speech for Minangkabau Pariaman Dialect Using Variational Autoencoder with Adversarial Learning (VITS) Fakhrezi, Muhammad Dzaki; Yusra; Muhammad Fikry; Pizaini; Suwanto Sanjaya
Knowbase : International Journal of Knowledge in Database Vol. 5 No. 1 (2025): June 2025
Publisher : Universitas Islam Negeri Sjech M. Djamil Djambek Bukittinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30983/knowbase.v5i1.9909

Abstract

Language serves as a medium of human communication to convey ideas, emotions, and information, both orally and in writing. Each language possesses vocabulary and grammar adapted to the local culture. One of the regional languages that enriches Indonesian as the national language is Minangkabau. This language has four main dialects, namely Tanah Datar, Lima Puluh Kota, Agam, and Pesisir. Within the Pesisir dialect, there are several variations, including the Padang Kota, Padang Luar Kota, Painan, Tapan, and Pariaman dialects. This study discusses the application of Text-to-Speech (TTS) technology to the Minangkabau language, specifically the Pariaman dialect, using the Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech (VITS) method. This dialect needs to be preserved to prevent extinction and supported through technological development that broadens its use. The VITS method was chosen because it is capable of producing natural and high-quality speech. The research stages include voice data collection and recording, VITS model training, and speech quality evaluation using the Mean Opinion Score (MOS). The final results show a score of 4.72 out of 5, indicating that the generated speech closely resembles the natural utterances of native speakers. This TTS technology is expected to support the preservation and development of the Minangkabau language in the Pariaman dialect, as well as enhance information accessibility for its speakers.
Design of a Decision Support System to Determine Scholarship Recipients at SMKN 2 Padang Panjang Efandari, Ariati; Hari Antoni Musril; Sarwo Derta; Muhammad Iqbal Haikal bin Samia’an
Knowbase : International Journal of Knowledge in Database Vol. 5 No. 1 (2025): June 2025
Publisher : Universitas Islam Negeri Sjech M. Djamil Djambek Bukittinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30983/knowbase.v5i1.10044

Abstract

This research is based on field findings through observations and interviews at SMKN 2 Padang Panjang, which revealed that the process of managing school fee relief scholarship acceptance data is still done manually. This condition causes slow data input processes, slows down administration, and increases the potential for errors in processing student data. Thus, the main focus of this research is to create a valid, practical and effective SPK design in determining scholarship acceptance. This research is a type of Research and Development (R&D) research, using the Analytical Hierarchy Process (AHP) method and the Agile development model. Based on the results of the validity test with 3 lecturers, the system obtained a score of 0.86, indicating a very high level of validity. The practicality test with 3 teachers obtained a score of 0.97, indicating that the system is easy to use. Meanwhile, the results of the effectiveness test with 22 students obtained a score of 0.87, indicating that this system is effective in supporting the scholarship recipient selection process. Unlike previous studies that generally only apply one decision-making method or use conventional development models, this study integrates AHP with an Agile approach to produce a system that is more accurate, practical, and adaptive to school needs. With these achievements, the developed decision support system is worthy of being used as a reliable and efficient tool in determining scholarship recipients at SMKN 2 Padang Panjang.  
Named Entity Recognition for Uncovering Clinical and Emotional Entities from Breast Cancer Patient Interviews Alias, Norma; Sundari, Agus
Knowbase : International Journal of Knowledge in Database Vol. 5 No. 1 (2025): June 2025
Publisher : Universitas Islam Negeri Sjech M. Djamil Djambek Bukittinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30983/knowbase.v5i1.10192

Abstract

This study aims to develop a Named Entity Recognition (NER) system capable of identifying clinical and emotional entities within interview transcripts of breast cancer patients. The corpus was manually annotated using the BIO scheme across seven main entity categories: Social Support (Dukungan Sosial), Medical Actions (Tindakan Medis), Diagnosis, Negative Emotions (Emosi Negatif), Positive Emotions (Emosi Positif), Symptoms (Gejala), and Spiritual. The annotation process was followed by the implementation of a rule-based method supported by entity dictionaries and word normalization, and the model was evaluated using precision, recall, and F1-score metrics. The analysis results revealed that Dukungan Sosial was the most dominant entity with 347 occurrences, followed by Tindakan Medis and Diagnosis. The rule-based NER model achieved an F1-score of 0.50 for the Diagnosis entity, although its performance on emotional and social entities remained low due to data imbalance. These findings highlight the importance of integrating clinical and emotional aspects in natural language processing to gain a more comprehensive understanding of patient narratives. The proposed approach has potential applications in healthcare text mining for detecting emotional experiences and medical contexts, and it can be further enhanced through the integration of transformer-based models such as IndoBERT to improve entity recognition accuracy.
Optimizing Futsal Field Reservation Through FCFS Queueing Algorithm in a Web-Based Booking Platform Annas, Firdaus
Knowbase : International Journal of Knowledge in Database Vol. 3 No. 2 (2023): December 2023
Publisher : Universitas Islam Negeri Sjech M. Djamil Djambek Bukittinggi

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

Abstract

Advancements in information technology have accelerated the demand for digital systems capable of supporting efficient service management and data processing. Within futsal facility operations, the increasing number of users highlights the need for an automated and reliable field reservation mechanism. Traditional booking practices, which require customers to visit the venue directly to check availability and make reservations, are inefficient, time-consuming, and susceptible to scheduling conflicts. This study proposes a web-based futsal field reservation system that integrates the First-Come, First-Served (FCFS) queueing algorithm to manage booking order. The FCFS algorithm, commonly applied in computing and resource scheduling, processes reservation requests strictly based on arrival time, thereby ensuring fairness and preventing overlapping bookings. The implementation of FCFS within the reservation workflow enables systematic scheduling, minimizes manual errors, and enhances user convenience. Experimental results indicate that the proposed system significantly improves booking efficiency and provides a more transparent, reliable, and organized reservation experience for both customers and futsal operators
Implementation of the C4.5 Algorithm to Build A Prediction Model for Student Success in Database Courses Nanda Pratama Alfyandri; Hari Antoni Musril; Sarwo Derta
Knowbase : International Journal of Knowledge in Database Vol. 5 No. 2 (2025): December 2025
Publisher : Universitas Islam Negeri Sjech M. Djamil Djambek Bukittinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30983/knowbase.v5i2.10083

Abstract

This study aims to implement the C4.5 algorithm to build a model for predicting student success in database system courses in the Informatics and Computer Engineering Education study program at UIN Sjech M. Djamil Djambek Bukittinggi. Using the Knowledge Discovery in Database (KDD) approach, this study includes the stages of data selection, cleaning, transformation, modeling, and evaluation. Secondary data from the academic information system of students enrolled from 2018 to 2023 included 1,177 entries, which after cleaning resulted in 1,030 valid data. Predictor attributes consisted of academic factors such as Algorithm Logic scores, 1st semester Grade Point Average (GPA), attendance, and credit load, as well as non-academic factors such as gender and UKT (Tuition Fee Category). The target variable was student success status. Modeling was performed using Altair RapidMiner 2025 software with the C4.5 algorithm, resulting in a decision tree model. Evaluation showed an accuracy of 82.10%, recall of 69.58%, and precision of 62.51%, indicating the algorithm's effectiveness in classifying students as potentially successful or unsuccessful. This model identifies the most influential attributes, both academic and non-academic, on student success. Overall, the application of the C4.5 algorithm supports Educational Data Mining (EDM) in higher education, helping study programs improve the quality of learning and the effectiveness of data-based academic interventions.
Analysis of Drug Inventory Patterns Using the K-Means Algorithm Setiadi, Dedi; Gusmaliza, Debi
Knowbase : International Journal of Knowledge in Database Vol. 5 No. 2 (2025): December 2025
Publisher : Universitas Islam Negeri Sjech M. Djamil Djambek Bukittinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30983/knowbase.v5i2.10420

Abstract

Efficient drug inventory management is a critical challenge for the Sandar Angin Community Health Center to ensure the availability of drugs needed by customers without incurring excessive storage costs. Data mining with the K-Means algorithm was used to determine drug inventory more effectively. Drug data for the past year was used as a sample in this study. The Elbow method was used to determine the optimal number of clusters, and the results showed that three clusters were most appropriate for grouping drug sales data. The first cluster consisted of drugs with high and consistent sales, the second cluster included drugs with moderate and fluctuating sales, while the third cluster contained drugs with low and inconsistent sales. The results of this clustering provide clear guidance in drug inventory management. Drugs in the first cluster require larger stocks, the second cluster requires moderate stocks and promotional strategies tailored to the season, while the third cluster requires minimal stocks and regular evaluations to determine the continuation of its supply. The implementation of the K-Means method has proven effective in reducing storage costs, increasing customer satisfaction, and optimizing inventory management. This study concluded that data mining using the K-Means algorithm can help the Sandar Angin Community Health Center make better decisions regarding drug inventory. The results showed that out of a total of 506 drug data sets, 496 fell into cluster 0, or 98% of the data. One drug data set fell into cluster 1, and nine drug data set fell into cluster 2.
Application for Calculation of Islamic Sharia Inheritance Based on Android for Mawaris Fiqh Courses Anwar, Artesia; Darmawati, Gusnita
Knowbase : International Journal of Knowledge in Database Vol. 1 No. 2 (2021): December 2021
Publisher : Universitas Islam Negeri Sjech M. Djamil Djambek Bukittinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30983/ijokid.v1i2.4956

Abstract

This research was motivated by the discovery of problems in terms of calculating inheritance in the Mawaris Fiqh course at the Islamic Family Law Department of IAIN Bukittinggi, the calculation of inheritance in the Maris Fiqh course still uses the manual method, in which lecturers and students still have to calculate using pen and paper how much the number of shares of each person entitled to inheritance rights. The purpose of this research is to design an Android-Based Application for Inheritance Calculation of Islamic Law for Fiqh Mawaris Subject, Islamic Family Law Department, Sharia Faculty IAIN Bukittinggi, which is practical, effective and efficient. The method used in this research is Research and Development, better known as (R&D). 4D Models (Define, Design, Develop, Disseminate). The system development model used is the System Development Life Cycle (SDLC). The model used in this SDLC is the waterfall, namely Communication, Planning, Modeling, Construction, and Development. The programming language used is the PHP programming language. The product test used is the Test of Validity, Test of Effectiveness and Test of Practicality. The system that has been designed has been tested and has been declared valid, effective and practical in its use. The results of the product test that the author did obtain a validity test from 3 experts obtained a value of 0.80 with a valid category, a practicality test from 5 practitioners obtained a value of 0.93 in a very high category, and test effectiveness of 5 appraisers obtained a value of 0.86 effective categories.
Designing a Student Counseling Guidance Information System at SMA Negeri 1 Batang Kapas Using the Codeigniter (CI) Framework Citra, Reka Sabna; Zakir, Supratman
Knowbase : International Journal of Knowledge in Database Vol. 1 No. 1 (2021): June 2021
Publisher : Universitas Islam Negeri Sjech M. Djamil Djambek Bukittinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30983/ijokid.v1i1.4957

Abstract

This research is conducted because of the need for an information system about how each student's learning development and student behavior were needed, so that Counseling Teacher (BK) was needed. Counseling Teacher (BK) SMA Negeri 1 Batang Kapas is a school directly related to student discipline that requires a computerized information system to operate data collection so that it is more optimal. It is carried out because the Counseling Guidance in schools has not used a computerized system in carrying out its work activities, the school still uses a conventional system such as in making attendance reports and archiving student violation data still using a portfolio so it seems that they use a lot of paper, many points of violation are not accumulated because of recording is still manual, so that sanctions are not appropriate and there is no valid and effective database in data management. It is the background for researchers to design a student counseling guidance information system using the CodeIgniter (CI) framework. The methodology used in the research is the type of research and development research commonly called R&D, which is research to create the desired program and test the program's effectiveness. The research model chosen is the 4D version, namely define, design, develop, and disseminate. This model uses the waterfall. Based on the results of the product test, the validity results of several computer experts were 0.91 (very valid), the results of the practicality test of two Counseling Teacher and one homeroom teacher obtained an average result of 0.91, which is very practical, while for the effectiveness test it was obtained value 0.91 (very high).