cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Arif Mustofa
Contact Email
disprotek@unisnu.ac.id
Phone
-
Journal Mail Official
disprotek@unisnu.ac.id
Editorial Address
-
Location
Kab. jepara,
Jawa tengah
INDONESIA
Jurnal DISPROTEK
Published by Universitas Islam Nahdlatul Ulama Jepara
ISSN : 25484168     EISSN : 25484168     DOI : -
Core Subject : Science, Education, Engineering,
Civil Engineering, Building, Construction & Architecture Computer Science & IT Electrical & Electronics Engineering Industrial & Manufacturing Engineering Other
Jurnal DISPROTEK e-ISSN 2548-4168 p-ISSN 2088-6500 Jurnal di publikasikan oleh Fakultas Sains dan Teknologi, Universitas Islam Nahdlatul Ulama Cakupan isi jurnal DISPROTEK dalam bidang teknik adalah : teknik elektro, teknik sipil, teknik industri; dalam bidang ilmu komputer adalah : teknik informatika dan sistem informasi serta dalam bidang perikanan adalah : budidaya perairan.
Arjuna Subject : -
Articles 249 Documents
 21   22   23   24   25 
HYBRID RANDOM FOREST ALGORITHM FOR QRIS CROSS-BORDER SENTIMENT CLASSIFICATION USING SMOTE METHOD FOR IMBALANCED DATA Nur Faizin; Nur Aeni Widiastuti; Raden Hadapiningradja Kusumodestoni
Jurnal Disprotek Vol. 17 N0. 2 (2026)
Publisher : Universitas Islam Nahdlatul Ulama Jepara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34001/jdpt.v172.9848

Abstract

The implementation of QRIS Cross-border services has triggered diverse responses on YouTube; however, its analysis is hindered by imbalanced data. This study proposes a Hybrid Machine Learning model combining TF-IDF Bigram for statistical features and Bidirectional Long Short-Term Memory (Bi-LSTM) to capture deep contextual features from informal social media text. This hybrid approach is employed to overcome the limitations of single statistical features in understanding complex semantic meanings in YouTube comments. A total of 5,520 comment data points were divided into 80% training data and 20% testing data using the Stratified Split method. To address majority class bias, the SMOTE technique was applied to the training data before classification using a Random Forest algorithm optimized with 1,200 trees (n_estimators). Experimental results show that the Hybrid Bi-LSTM-Random Forest model with SMOTE achieved an accuracy of 93.48%, outperforming SVM (90.31%) and standard Random Forest (88.95%). The application of SMOTE significantly improved the minority class F1-Score from 0.73 to 0.84, with a precision of 0.96. Substantially, public complaints focused on exchange rate issues and technical glitches. The integration of contextual features and data balancing proved effective in producing an accurate and sensitive model for capturing critical public aspirations for financial regulators.
LOCATION-TAG-BASED DECISION SUPPORT SYSTEM FOR WI-FI ACCESS POINT UPGRADES USING THE SAW METHOD Bryan Noviantara; Supriyono; Diana Laily Fithri
Jurnal Disprotek Vol. 17 N0. 2 (2026)
Publisher : Universitas Islam Nahdlatul Ulama Jepara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34001/jdpt.v172.9900

Abstract

Wi-Fi service quality is an important factor in supporting operations and customer satisfaction at internet service providers. CV Piyuen Net still faces obstacles in determining access points that need to be upgraded because the evaluation process is done manually. This study aims to build a Decision Support System (DSS) to determine access point upgrade priorities using the Simple Additive Weighting (SAW) method. The criteria used include Wi-Fi Signal Strength, Number of Active Users, Bandwidth Usage, Signal Interference Level, Access Point Age, and Network Connection Quality. The system was developed using the Extreme Programming (XP) method and utilizes location tags to facilitate access point identification. The Black Box testing results showed that all system functions ran as required with a 100% success rate, while the SAW method was able to generate objective access point upgrade priority recommendations based on the obtained preference values. Thus, the system can help improve the effectiveness of decision-making and the quality of network services at CV Piyuen Net.
UI/UX DESIGN FOR ARTIFICIAL INTELLIGENCE-INTEGRATED STUDYMATCH APPLICATION USING DESIGN THINKING METHOD Candrika Widya Lestari; Nur Afifah Sari Kharimah; Rizqiyah Al-Syafa'ah; Khalimatul Azkiyah; Indra Kurniawan
Jurnal Disprotek Vol. 17 N0. 2 (2026)
Publisher : Universitas Islam Nahdlatul Ulama Jepara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34001/jdpt.v172.9950

Abstract

The development of digital educational technology has led to the emergence of various digital learning platforms that support more flexible and accessible learning. However, most existing platforms primarily provide learning materials and do not fully support students' collaborative learning needs. This study aims to design the UI/UX of the StudyMatch mobile application as a collaborative learning platform using the Design Thinking method. The design process consists of five stages: Empathize, Define, Ideate, Prototype, and Test, to identify user needs and develop a user-centered solution. The StudyMatch application is designed with features such as tutor search, study partner search, study groups, and learning notes. In addition, this study proposes the SmartMatch AI feature as an AI-assisted recommendation feature to support tutor and study partner recommendations in future development. The prototype was evaluated using the System Usability Scale (SUS) with 20 respondents and achieved an average score of 70.5, which falls into the Good category. These findings indicate that the proposed UI/UX design has good usability and is acceptable to users. Overall, the implementation of the Design Thinking method resulted in a UI/UX design that addresses user needs and provides a foundation for the future development of collaborative learning applications.
PCC CEMENT DEMAND FORECASTING USING SINGLE EXPONENTIAL SMOOTHING METHOD AT PT SEMEN TONASA Atik Febriani; Muh Ikhwanul Ahkam Febriani; Gunawan Mohammad
Jurnal Disprotek Vol. 17 N0. 2 (2026)
Publisher : Universitas Islam Nahdlatul Ulama Jepara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34001/jdpt.v172.9972

Abstract

Employee productivity is a strategic factor in enhancing an organization's operational efficiency and competitiveness. However, human resource management in many companies remains suboptimal, particularly regarding the development of human capital quality that supports productivity. This study aims to analyze the impact of education, work experience, and job training as dimensions of human capital on the productivity of PT XYZ employees. Unlike previous studies that tended to examine human capital aspects in isolation or within specific organizational contexts, this research integrates these three dimensions into a single model to provide a more comprehensive understanding of the factors driving productivity within the study's scope. The selection of these three dimensions is grounded in Human Capital Theory, which views education as the foundation of knowledge, work experience as the accumulation of practical competence, and training as a mechanism for continuous competence development. A quantitative approach was employed, utilizing a survey of 150 respondents selected through purposive sampling. Data were collected via Likert-scale questionnaires and analyzed using multiple linear regression in SPSS. The results indicate that education (β = 0.241; p < 0.05), work experience (β = 0.356; p < 0.05), and job training (β = 0.418; p < 0.05) all have a positive and significant effect on work productivity. Collectively, the three variables exert a significant influence, with an Adjusted R-squared value of 0.682. Job training emerged as the factor making the largest contribution. These findings underscore the importance of integrated human capital development strategies in boosting organizational productivity and competitiveness.
SUPPLY CHAIN ANALYSIS, INVENTORY CONTROL, AND INFORMATION SYSTEM DESIGN FOR FRESH FRUIT RETAIL MSMEs Atik Febriani; Muhammad Rizki Pambudi; Rui Almer Guritno; Kuntoro Bayu Pringgondani; Muhammad Vicky Maulana
Jurnal Disprotek Vol. 17 N0. 2 (2026)
Publisher : Universitas Islam Nahdlatul Ulama Jepara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34001/jdpt.v172.9981

Abstract

This study aims to formulate inventory-control policies and a simple information-system design for a fresh-fruit retail micro, small, and medium enterprise by using supply-chain mapping and retail activities as the operational diagnostic basis. A case study was conducted at Krisbi Buah Purwokerto through observation, interviews, supply-chain and value-chain mapping, supplier-relationship analysis, safety-stock and reorder-point calculations, and an as-is/to-be information-system gap analysis. Four products were purposively selected to represent differences in sourcing origin, chain length, demand rate, and shelf life. The results show that apples have the longest supply chain through import and distributor routes, whereas mangoes have a shorter chain but higher seasonal dependence. Procurement, inventory recording, sales, and reporting remain fragmented, preventing demand information from consistently supporting purchasing decisions. Mango is the principal fast-moving product, with estimated demand of 28.6 kg/day. Using a 95% service-level target, a daily demand standard deviation of 5 kg, and a two-day lead time, the recommended safety stock is 12 kg and the reorder point is 70 kg. The proposed Google Sheets prototype comprises six connected modules covering suppliers, procurement, inventory, sales, dashboards, and monthly reports. The study contributes an integrated link between supply-chain characteristics, inventory policies, and low-cost information-system requirements for micro-retailers. The design remains conceptual and requires user testing and post-implementation performance evaluation.
CLASSIFICATION OF STAFFING ADEQUACY LEVELS IN EACH SECTION IN SOKO DISTRICT USING THE NAÏVE BAYES METHOD Dede Latifah; Sholihul Ibad; Ahnaf Febriyan Fachri
Jurnal Disprotek Vol. 17 N0. 2 (2026)
Publisher : Universitas Islam Nahdlatul Ulama Jepara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34001/jdpt.v172.10039

Abstract

Advances in information technology have encouraged the use of data mining to support decision-making, particularly in the government sector. Soko District faces challenges in objectively assessing employee needs because the assessment is still carried out manually, resulting in uneven employee distribution. This study aims to classify the level of employee sufficiency using the Naïve Bayes method with a quantitative approach supported by observation, interview, and documentation data. The analyzed data consisted of 7 datasets representing each section in Soko District, analyzed based on the attributes of employee number and workload. Testing was carried out through manual calculations and validated using RapidMiner. The results showed that most of the data were categorized as Insufficient with a posterior probability value higher than the Sufficient category. Testing using RapidMiner produced an accuracy rate of 50%, indicating that the model was able to classify some of the data but still faced challenges in identifying optimal patterns. The Naïve Bayes method can be used to categorize the level of employee sufficiency and provide an initial overview to support more objective and data-driven decision-making.
IMPLEMENTATION OF CODING FOR CHANGE TRAINING TO ENHANCE PROGRAMMING SKILLS AND ARTIFICIAL INTELLIGENCE LITERACY AMONG HIGH SCHOOL STUDENTS Purwati; Sofia Ulfah; A. Faiq Abror; Nila Ayu Kusuma Wardani; Nur Ahmad Budi Yulianto
Jurnal Disprotek Vol. 17 N0. 2 (2026)
Publisher : Universitas Islam Nahdlatul Ulama Jepara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34001/jdpt.v172.10054

Abstract

The rapid advancement of digital technology and Artificial Intelligence (AI) requires students to develop programming skills, computational thinking, and digital literacy to meet the demands of the twenty-first century. However, programming instruction at the secondary school level remains predominantly theoretical, providing limited opportunities for hands-on practice and AI literacy development. This study aims to analyze the implementation of the Coding for Change training program in improving programming skills and Artificial Intelligence literacy among students at SMA Negeri 1 Nalumsari Jepara. A qualitative descriptive approach was employed in this study. Data were collected through classroom observations, documentation, and participants’ reflections throughout the training activities. Data analysis followed the interactive model of Miles, Huberman, and Saldaña, including data reduction, data display, and conclusion drawing. The findings indicate that the implementation of learning by doing and Project-Based Learning effectively improved students’ understanding of fundamental Python programming concepts, their ability to complete simple programming projects, and their awareness of Artificial Intelligence applications in creative activities. Participants demonstrated high engagement during the training and successfully implemented programming concepts through Google Colab and AI-assisted design using Canva AI. Furthermore, integrating programming instruction with AI literacy created a more contextual learning experience, enhanced students’ learning motivation, strengthened computational thinking skills, and improved their readiness to face digital transformation. This study contributes to the development of project-based Informatics learning models aligned with twenty-first-century competencies and provides an alternative framework for community engagement programs aimed at strengthening students’ digital competencies.
THE INFLUENCE OF EXTRINSIC MOTIVATION, PERSONALITY, AND COMMUNICATION ON EMPLOYEE PERFORMANCE AT PT. SOLO BETON SRAGEN Ratna Sekar Ayu; Yunita Primasanti; Agung Widiyanto Fajar S.
Jurnal Disprotek Vol. 17 N0. 2 (2026)
Publisher : Universitas Islam Nahdlatul Ulama Jepara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34001/jdpt.v172.10079

Abstract

The decline in employee performance at PT. Solo Beton Sragen from 95% in 2023 to 82% in 2024 indicates that human resource management within the company has not been optimal. This study aims to analyze the influence of extrinsic motivation, personality, and communication on employee performance, both partially and simultaneously. Data were collected through observation, interviews, and questionnaires distributed to 39 employees using a saturated sampling technique. The study employed a quantitative descriptive approach with multiple linear regression analysis processed using SPSS 25, including instrument feasibility testing, classical assumption testing, hypothesis testing (t-test and F-test), and the coefficient of determination test. The results show that extrinsic motivation and communication partially have no significant effect on employee performance, while personality has a significant effect and is the most dominant variable. Simultaneously, the three variables significantly affect employee performance, contributing 86.1%. These findings confirm that strengthening employees' personality traits should be a company priority in sustainably improving performance.
IMPLEMENTATION OF SPEECH RECOGNITION FOR SENTIMENT ANALYSIS WITH A VOICE-TO-VOICE PIPELINE USING THE PROTOTYPE METHOD Ummu Khuzaifah; Akhmad Pandhu Wijaya; Arief Hidayat
Jurnal Disprotek Vol. 17 N0. 2 (2026)
Publisher : Universitas Islam Nahdlatul Ulama Jepara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34001/jdpt.v172.10089

Abstract

Human–computer interaction is increasingly evolving toward more natural and efficient voice-based communication. However, most voice assistant systems still separate speech recognition from users’ emotional analysis, resulting in less adaptive interactions. This study aims to design and implement an integrated speech recognition system that combines Speech-to-Text (STT), Support Vector Machine (SVM)-based sentiment analysis, and Text-to-Speech (TTS) within a unified voice-to-voice pipeline. The system was developed using the prototype method to ensure stable and iterative integration among the modules. The STT module utilizes the Google Web Speech API for speech transcription, while sentiment classification employs the SVM algorithm supported by preprocessing stages, including text normalization and spelling correction. The results show that the system operates in real time with a stable response time ranging from 0.6 to 0.9 seconds. Evaluation of the STT module using the Word Error Rate (WER) metric demonstrated optimal performance, achieving a WER of 0 on the test data. In sentiment analysis testing, the prototype method significantly improved system accuracy from 56.00% in the initial prototype to 85.33% in the final prototype through the addition of training data and model refinement. The integration of the three components using the Flask framework resulted in a virtual assistant capable not only of converting speech into text but also of responding adaptively to users’ sentiments through voice. In conclusion, integrating STT, SVM, and TTS into a unified pipeline effectively improves the quality of voice interaction, enabling more communicative and adaptive human–computer interaction.

Page 25 of 25 | Total Record : 249

 21   22   23   24   25 

Filter by Year

2010 2026


Reset
Filter By Issues
All Issue Vol. 17 N0. 2 (2026) Vol. 17 No. 1 (2026) Vol 16, No 2 (2025) Vol 16, No 1 (2025) Vol 15, No 2 (2024) Vol 15, No 1 (2024) Vol 14, No 2 (2023) Vol 14, No 1 (2023) Vol 13, No 2 (2022) Vol 13, No 1 (2022) Vol 12, No 2 (2021) Vol 12, No 1 (2021) Vol 11, No 2 (2020) Vol 11, No 1 (2020) Vol 10, No 2 (2019) Vol 10, No 1 (2019) Vol 9, No 2 (2018) Vol 9, No 2 (2018) Vol 9, No 1 (2018) Vol 8, No 2 (2017) Vol 8, No 1 (2017) Vol 7, No 2 (2016) Vol 7, No 1 (2016) Vol 6, No 2 (2015) Vol 6, No 1 (2015) Vol 5, No 2 (2014) Vol 5, No 1 (2014) Vol 2, No 2 (2011) Vol 1, No 1 (2010) More Issue