cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Agus Tedyyana
Contact Email
agustedyyana@polbeng.ac.id
Phone
+6285289866666
Journal Mail Official
jurnaoinformatika@polbeng.ac.id
Editorial Address
Jl. Bathin alam, Sungai Alam Bengkalis-Riau 28711
Location
Kab. bengkalis,
Riau
INDONESIA
INOVTEK Polbeng - Seri Informatika
Published by Politeknik Negeri Bengkalis
ISSN : 25279866     EISSN : -     DOI : https://doi.org/10.35314
Core Subject : Science,
Computer Science & IT
The Journal of Innovation and Technology (INOVTEK Polbeng—Seri Informatika) is a distinguished publication hosted by the State Polytechnic of Bengkalis. Dedicated to advancing the field of informatics, this scientific research journal serves as a vital platform for academics, researchers, and practitioners to disseminate their insightful findings and theoretical developments. Scope and Focus: INOVTEK Polbeng - Seri Informatika focuses on a broad spectrum of topics within informatics, including but not limited to Web and Mobile Computing, Image Processing, Machine Learning, Artificial Intelligence (AI), Intelligent Systems, Information Systems, Databases, Decision Support Systems (DSS), IT Project Management, Geographic Information Systems, Information Technology, Computer Networks and Security, and Wireless Sensor Networks. By covering such a wide range of subjects, the journal ensures its relevance to a diverse readership interested in both the practical and theoretical aspects of informatics.
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 543 Documents
 41   42   43   44   45 
Optimization of Biobert Model for Medical Entity Recognition Through Bilstm and CNN-Char Integration Abu Salam; Gilang Djati Prinantyo
Journal of Innovation and Technology Polbeng Series on Informatics (INOVTEK Polbeng - Seri Informatika) Vol. 10 No. 2 (2025): July
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/bypwas91

Abstract

Biomedical Named Entity Recognition (NER) is essential for extracting structured information from medical texts. However, existing models like BioBERT face challenges when dealing with complex biomedical entities, particularly those with intricate morphological structures. This research enhances the BioBERT model by integrating BiLSTM and character-level CNN (CNN-Char), aiming to improve the recognition of Chemical and Disease entities. The proposed models were trained and evaluated on the BC5CDR dataset sourced from the official BioCreative V CDR Corpus. The modified model achieved an F1-score of 0.8678, indicating a significant improvement compared to the standard BioBERT model, which scored 0.8597. This increase is primarily observed in the recognition of complex entity structures, particularly those requiring character-level representation. Despite this improvement, the model is limited to Chemical and Disease entities and may not generalise to other biomedical categories. Future work should focus on expanding the entity types and exploring other model architectures, such as SciBERT or BioALBERT, to further enhance performance
Design and Construction of Employee Recruitment System Application using Profile Matching Method M. Azmi Mahendra; Maulana Firmansyah; Gandung Triyono
Journal of Innovation and Technology Polbeng Series on Informatics (INOVTEK Polbeng - Seri Informatika) Vol. 10 No. 2 (2025): July
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/xvzgjq78

Abstract

The employee recruitment process is one of the important aspects of human resource management, which ensures a match between company needs and available candidates. This research aims to design an E-Recruitment system based on Profile Matching to improve efficiency and accuracy in the employee selection process at PT XYZ. The research methods used include literature study, observation, and interviews with the HRD team. System development follows the SDLC waterfall model, which includes planning, analysis, design, implementation, and testing stages. In this case study, we use data samples from 5 applicants. For the criteria used, there are 3 criteria, namely administration, interview results, and skills/expertise. The results showed that the developed system was able to automate the selection process, reduce administrative burden, and increase objectivity in candidate selection. In conclusion, the implementation of Profile Matching-based E-Recruitment can optimise the recruitment process, but still needs to be combined with other selection methods to get a more comprehensive picture of candidates.
Operational Evaluation of the Document and Archive Management Application at Disdukcapil Salatiga using the EUCS Method Florensia Fransisca Florensia; Frederik Samuel Papilaya
Journal of Innovation and Technology Polbeng Series on Informatics (INOVTEK Polbeng - Seri Informatika) Vol. 10 No. 2 (2025): July
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/w3yzfr51

Abstract

Efficient population administration services require information systems that effectively support staff performance. This study aims to evaluate user satisfaction with the internal application used by the Salatiga Civil Registry Office (Disdukcapil) using the End User Computing Satisfaction (EUCS) method. Data were collected through questionnaires distributed to 10 respondents from two different job functions (service counter and archive), and analysed using descriptive statistics and the Mann-Whitney test. The results show that user satisfaction scores were generally high (ranging from 3.9 to 4.3), with no statistically significant differences in perceptions based on job function or duration of system use (p > 0.05). This suggests that the application is widely accepted among users. However, limitations such as a small sample size and lack of personalised features may affect the generalizability of the findings. The study recommends improving interface design and increasing system flexibility to better align with operational needs. Future research should involve a larger number of respondents and consider evaluating additional technical aspects, such as data security and system integration.
User Experience Analysis on Facebook Marketplace Pekanbaru using User Experience Questioner Method Raihan Mukti; Megawati; Angraini; Mona Fronita
Journal of Innovation and Technology Polbeng Series on Informatics (INOVTEK Polbeng - Seri Informatika) Vol. 10 No. 2 (2025): July
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/r0qp2735

Abstract

The integration of e-commerce features into social media platforms has created unique user experience challenges, particularly in localized buying and selling communities. This study evaluates the user experience of Facebook Marketplace within the Pekanbaru Jual Beli Online (PJBO) community using the User Experience Questionnaire (UEQ) method. Through a quantitative approach with 400 active users selected via simple random sampling, this research reveals significant user experience gaps in a platform that accommodates over 136,000 members. The results demonstrate that four core UX dimensions fall below industry benchmarks: attractiveness (0.85), clarity (0.81), efficiency (0.82), and dependability (0.79), all with narrow confidence intervals (±0.14-0.18), indicating consistent user dissatisfaction across these dimensions. While stimulation (0.80) achieved "good" ratings and novelty (0.78) scored "above average," the overall UX profile reveals a platform that provides adequate innovative features but struggles with fundamental usability aspects. This study contributes to UX literature by examining the unique intersection of social network-based e-commerce in localized Indonesian markets, and provides platform developers with actionable recommendations to enhance system navigation, transaction efficiency, and trust mechanisms. However, this study employs only the UEQ method and does not extend to a more comprehensive evaluation, such as assessing system effectiveness and application interface performance.
Comparison of K-Means++ and Agglomerative Hierarchical Methods in Clustering Healthcare Workers Citra Tjipta Nur Handayani; Melkior N. N. Sitokdana
Journal of Innovation and Technology Polbeng Series on Informatics (INOVTEK Polbeng - Seri Informatika) Vol. 10 No. 2 (2025): July
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/pcbrs043

Abstract

As an archipelagic country, Indonesia faces disparities in the distribution of healthcare workers, influenced by its diverse geographical conditions. These disparities impact the equitable access to healthcare services across the country. This study aims to compare the effectiveness of two clustering methods, namely K-Means++ and Agglomerative Hierarchical Clustering, using secondary data from Statistics Indonesia (BPS) on the Number of Healthcare Workers by Province in 2023, covering 38 provinces and 13 categories of healthcare professions.The evaluation was conducted using three metrics: Silhouette Score to measure cluster cohesion, Davies-Bouldin Index to assess inter-cluster separation, and Calinski-Harabasz Index to compare inter-cluster variance. The results show that Agglomerative Hierarchical outperformed K-Means++ in Silhouette Score (0.550) and Davies-Bouldin Index (0.457), while K-Means++ performed better in the Calinski-Harabasz Index (63.630). A 2D PCA visualization further illustrates the structural differences between the clusters formed by each method. These findings provide insights into selecting the most appropriate clustering method for analyzing the distribution of healthcare workers and can support data-driven decision-making by policymakers
Performance Comparison Of BERT Metrics and Classical Machine Learning Models (SVM,Naive Bayes) for Sentiment Analysis Adib Ulinuha El Majid; Reflan Nuari
Journal of Innovation and Technology Polbeng Series on Informatics (INOVTEK Polbeng - Seri Informatika) Vol. 10 No. 2 (2025): July
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/wmh3rg23

Abstract

Sentiment analysis is one of the important methods in understanding public opinion from large amounts of text, such as product reviews or user comments. Many studies have shown that the BERT (BiDirectional Encoder Representations from Transformers) model has advantages over classical machine learning models such as Support Vector Machine (SVM) and Naïve Bayes. However, there are still few studies that systematically compare the performance of the two on datasets from various topics and languages, especially those with imbalanced label distributions. This study compares four BERT variants (bert-base-uncased, distilbert-base-uncased, indobert-base-uncased, and distilbert-base-indonesian) with two classical models using three datasets of IMDb 50K (English), Amazon Food Reviews (English), and Gojek App Review (Indonesian). The classical model uses the TF-IDF vectorisation method, while the BERT model is optimised through a further training process (fine-tuning) with a layer freezing technique. The evaluation is carried out using accuracy, precision, recall, and F1-score. The results show that the BERT model excels on English data, while on imbalanced Indonesian data, SVM and Naïve Bayes produce higher F1-score results. These findings indicate that the selection of the right model must be adjusted to the characteristics of the data used.
Website-Based Management and Financial Information System using Prototyping Method at GITJ Puncel Church Yehezkiel Febri Kurniawan; Aditya Akbar Riadi; Evanita
Journal of Innovation and Technology Polbeng Series on Informatics (INOVTEK Polbeng - Seri Informatika) Vol. 10 No. 2 (2025): July
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/p9rvkh62

Abstract

This study aims to design and implement a web-based information system to manage ministry and financial activities at GITJ Puncel Church, focusing on improving data accuracy, reporting transparency, and operational efficiency. The system was developed using the Prototyping method with an iterative approach, while data were collected through observations, structured interviews with church administrators, and document analysis. The system was built using PHP with the Laravel framework and MySQL database, and tested using the Black Box Testing method. This research addresses gaps in previous studies that did not effectively integrate ministry management features with financial administration, nor evaluate the quantitative impact on operational efficiency. The results show that the system successfully reduced financial recording time from 3–4 hours to 30 minutes (an 87.5% efficiency improvement), decreased recording errors from 15% to 2% (an 86.7% reduction in error rate), and enhanced reporting transparency through an automatic PDF export feature. Testing confirmed that all system functionalities operated 100% according to specifications. The study's limitations include its scope being limited to a single church with 150 congregants, a three-month implementation period, and no evaluation of long-term impacts on congregation participation. Overall, this research contributes a model for integrating ministry and financial systems for small to mid-sized religious organizations, and offers a framework for evaluating the effectiveness of web-based information systems in non-profit contexts.
Comparison of VGG16 and VGG19 Models in the Classification of Down Syndrome in the European Region with Transfer Learning Excel Bima Evansyah; Christian Sri Kusuma Aditya
Journal of Innovation and Technology Polbeng Series on Informatics (INOVTEK Polbeng - Seri Informatika) Vol. 10 No. 2 (2025): July
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/pz35e881

Abstract

Down syndrome detection by utilizing facial images as the main data has been widely developed through deep learning approaches, especially Convulutional Neural Network (CNN). However, most studies only classify the disorder without paying attention to regional factors. This has limited the effectiveness of the model in the classification of Down syndrome, especially in populations in European regions that have different morphological characteristics. This study examines the performance of two pretrained CNN models, namely VGG16 and VGG19, in classifying facial images of children from Europe who are divided into 2 categories of Down Syndrome and Healthy. The dataset used in the study consists of 1,543 images from the Down syndrome class 671 images and the Healthy class 872 images. It was then expanded to 1570 images to balance the data between both Down syndrome and Healthy classes. The evaluation results of this research by applying augmentation show that the VGG16 model has superior performance compared to VGG19, with accuracy reaching 94%. Meanwhile, the VGG19 model obtained an accuracy of 90%. This difference shows that the VGG16 model has a more stable performance in detecting both categories with a better balance between precision and recall. This research is limited to European children's image data and still does not exist for ethnic teenagers or the elderly. This provides a basis for the development of facial image-based early detection systems, particularly for clinical applications or early screening in areas with similar populations.
Utilization of Satellite Imagery and GIS for Mapping Potential Anchovy Fishing Areas in East Lampung Rifki Arif Rifki; Chairani Chairani; Sriyanto Sriyanto
Journal of Innovation and Technology Polbeng Series on Informatics (INOVTEK Polbeng - Seri Informatika) Vol. 10 No. 2 (2025): July
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/t4fqfq25

Abstract

This study utilises Aqua MODIS satellite imagery from January to December 2023 to analyse Sea Surface Temperature (SST) and chlorophyll-a as primary indicators in mapping Potential Fishing Zones (PFZ) for anchovy in East Lampung. Images were filtered based on minimal cloud cover and seasonal completeness using Level 3 daily data with 1 km resolution. The spatial analysis was conducted using Geographic Information Systems (GIS) to identify areas with SST between 29–31°C and chlorophyll-a concentrations above 0.2 mg/m³, which are considered optimal for anchovy habitat. The results show dynamic seasonal shifts in fishing zones influenced by oceanographic conditions. Compared to previous studies, this research provides more detailed seasonal maps and incorporates local fishing data to strengthen relevance. Despite limitations in temporal continuity due to cloud coverage, the approach demonstrates potential for efficient and sustainable fisheries management in Lampung.
Schizophrenia Classification using Fuzzy K-Nearest Neighbour on Patient Data from RSJD Dr. Amino Gondohutomo Ozagastra Caluella Prambudi; Ajib Susanto; Christy Atika Sari
Journal of Innovation and Technology Polbeng Series on Informatics (INOVTEK Polbeng - Seri Informatika) Vol. 10 No. 2 (2025): July
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/t2mfvf14

Abstract

Schizophrenia is a complex mental disorder with overlapping symptoms, making subtype diagnosis uncertain. This study aims to develop an automated classification method for schizophrenia subtypes using the Fuzzy K-Nearest Neighbour (FKNN) algorithm, which effectively handles uncertainty in medical data. The dataset includes 300 patients from RSJD Dr. Amino Gondohutomo, Central Java, aged 18–60 years, with balanced gender distribution. Four subtypes—paranoid, catatonic, hebephrenic, and undifferentiated—were classified. Symptom and demographic data were encoded and normalised using min-max scaling. The model was trained using k = 5 and evaluated via 10-fold cross-validation. The results achieved 94% accuracy with high precision and recall across all classes. However, limitations include a relatively small and single-source dataset and the lack of ROC/AUC analysis. These findings suggest that FKNN has strong potential as a data-driven decision support system for schizophrenia diagnosis, suitable for integration into psychiatric hospital information systems. Future research should explore oversampling techniques such as SMOTE and threshold tuning to improve model sensitivity.

Page 43 of 55 | Total Record : 543

 41   42   43   44   45 

Filter by Year

2024 2026


Reset
Filter By Issues
All Issue Vol. 11 No. 3 (2026): August (Inpress) Vol. 11 No. 2 (2026): May Vol. 11 No. 1 (2026): February Vol. 10 No. 3 (2025): November Vol. 10 No. 2 (2025): July Vol. 10 No. 1 (2025): March Vol. 9 No. 2 (2024): November