Garuda - Garba Rujukan Digital

Article Per Year (5 Year)

All

Techno Nusa Mandiri : Journal of Computing and Information Technology

techno
Website

Published by Universitas Nusa Mandiri

ISSN : 19782136 EISSN : 2527676X DOI : -

Core Subject : Science,

Computer Science & IT

Jurnal TECHNO Nusa Mandiri, merupakan Jurnal yang diterbitkan oleh Pusat Penelitian Pengabdian Masyarakat (PPPM) STMIK Nusa Mandiri Jakarta. Jurnal TECHNO Nusa Mandiri, berawal diperuntukan menampung paper-paper ilmiah yang dibuat oleh dosen-dosen program studi Teknik Informatika.

Arjuna Subject : -

Articles 279 Documents

24 25 26 27 28

AUTONOMOUS AND EXPLAINABLE DETECTION OF SUSPICIOUS BEHAVIORS IN CONNECTED VEHICLE ENVIRONMENTS THROUGH MULTI-SENSOR VISION Gihonia Abraham, Senghor; Mabela Makengo Matendo, Rostin; Masakuna, Felicien; Muluba Mfumudimbu Lireh, Celeste; Muhala Luhepa, Blaise
Jurnal Techno Nusa Mandiri Vol. 23 No. 1 (2026): Techno Nusa Mandiri : Journal of Computing and Information Technology Period o
Publisher : Lembaga Penelitian dan Pengabdian Pada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/4z0rn547

The safety of connected and autonomous vehicles requires intelligent systems capable of detecting suspicious behaviors in real time while providing clear explanations to human operators. This paper presents an innovative framework for the autonomous and explainable detection of suspicious activities around connected vehicles, combining multi-sensor vision, multi-agent reinforcement learning (MARL), and explainable artificial intelligence (XAI). The system relies on lightweight deep learning models (YOLO-tiny, MobileNet) for perception, along with spatio-temporal reasoning to identify abnormal events such as prolonged parking, restricted area crossings, or the placement of suspicious objects. Cooperative decision-making between vehicles and roadside units (RSUs) is managed through MARL. In parallel, an XAI module generates visual and textual explanations to enhance transparency and user trust. The framework has been implemented and evaluated in simulation (CARLA, SUMO/Veins) and on embedded platforms (Jetson Nano/Orin). Results demonstrate an F1-score of 0.91, real-time performance at 7.5 FPS, and a 40% reduction in false positives, confirming the robustness of the proposed system for the cyber-physical security of intelligent transportation systems.

PERFORMANCE ANALYSIS OF K-NN AND SVM IN DIGITAL IMAGE-BASED TEA LEAF DISEASE CLASSIFICATION Zer, P.P.P.A.N.W.Fikrul Ilmi R.H; Damanik, Abdi Rahim; Zer, P.A.M. Zidane R.W.P.P
Jurnal Techno Nusa Mandiri Vol. 23 No. 1 (2026): Techno Nusa Mandiri : Journal of Computing and Information Technology Period o
Publisher : Lembaga Penelitian dan Pengabdian Pada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/js2snb70

Tea is a commodity with high economic value, but it is susceptible to diseases such as Brown Blight, Red Rust, and Red Spider Mite. The manual identification process currently relies on visual observation, which is time-consuming and prone to error. This research aims to analyze the performance of K-NN and SVM algorithms in classifying tea leaf diseases based on digital images. This research utilized a perfectly balanced dataset of 5,000 images. The research methodology involves image preprocessing and classification using 5-Fold, 10-Fold, and 20-Fold Cross-Validation. The results demonstrate that the SVM algorithm consistently outperforms K-NN across all testing scenarios. Specifically, SVM achieved its highest accuracy of 96.6% using 20-Fold Cross-Validation, whereas the highest accuracy for K-NN was 96.1%. The research concludes that SVM provides superior sensitivity and accuracy for identifying tea leaf diseases, offering a viable solution for automated detection systems in the plantation sector

SENTISTRENGTH-BASED SENTIMENT ANALYSIS TO UNDERSTAND THE LOYALTY AND SHOPPING INTERESTS OF DIGITAL BUSINESS MARKETPLACE Astuti, Widi; Firasari, Elly; Cahyani, F. Lia Dwi; Sarasati, Fajar; Septian, Rendi
Jurnal Techno Nusa Mandiri Vol. 23 No. 1 (2026): Techno Nusa Mandiri : Journal of Computing and Information Technology Period o
Publisher : Lembaga Penelitian dan Pengabdian Pada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/z9qneg62

In Indonesia's dynamic digital economy, customer reviews on marketplace platforms like TikTok Shop, Shopee, and Tokopedia are strategic assets for understanding consumer loyalty and online shopping interest. However, extracting information from thousands of informal reviews presents a significant challenge for rapid business decision-making. This study aims to implement an automated sentiment analysis system by comparing three major machine learning algorithms: Logistic Regression (LR), Naive Bayes (NB), and K-Nearest Neighbors (KNN), utilizing the sentiment strength feature of the Indonesian SentiStrength method. The research dataset consists of 881 reviews collected through crawling techniques and subjected to text preprocessing stages including case folding, cleaning, tokenization, stemming, and stop word removal. Automatic labeling using SentiStrength resulted in a sentiment distribution consisting of Neutral (41.9%), Positive (40.2%), and Negative (17.9%). The data was then divided into training and test data to evaluate the performance of the three algorithms. Experimental results show that all three models performed very reliably in classifying customer opinions. Based on an evaluation using the Classification Report, K-Nearest Neighbors (KNN) provided the most optimal results with an accuracy rate of 99%, followed by Naive Bayes with 96% accuracy, and Logistic Regression with 94%. The high performance of these three models demonstrates that using SentiStrength sentiment scores as input features is highly effective in minimizing language ambiguity. Managerially, this research contributes to digital business practitioners' ability to monitor public perception in real-time to formulate more responsive marketing strategies and maintain customer retention in the marketplace ecosystem

OPTIMIZING TOMATO STORAGE-TIME USING SUPPORT VECTOR MACHINE ALGORITHM TO IMPROVE QUALITY AND REDUCE WASTE Rahmat; Sunardi; Fitriani; Andi Saenong; Muhammad Rusdi Rahman; Herman Heriadi; Hernawati
Jurnal Techno Nusa Mandiri Vol. 23 No. 1 (2026): Techno Nusa Mandiri : Journal of Computing and Information Technology Period o
Publisher : Lembaga Penelitian dan Pengabdian Pada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/6kt3mn85

Tomatoes are an agricultural commodity that is susceptible to spoilage, with a limited shelf life if not stored under optimal conditions. Optimizing tomato storage time is very important for improving product quality and reducing waste in distribution. This study aims to implement the Support Vector Machine (SVM) algorithm in predicting the optimal storage time for tomatoes, taking into account environmental factors such as temperature and humidity, as well as tomato ripeness. The dataset used consists of tomato images taken at various ripeness levels, as well as environmental data during storage. The SVM model was trained to classify tomato ripeness conditions and predict the optimal storage duration before significant quality deterioration occurs. The results of the study show that the SVM model has high accuracy in classifying tomato ripeness and can be used to predict the optimal storage time, which in turn can extend the shelf life of tomatoes and reduce crop waste. This research contributes to more efficient and sustainable tomato post-harvest management.

INTEGRATED DIGITAL LAUNDRY APPLICATION FOR MSMES: END-TO-END OPERATIONS AND REMOTE MONITORING Joharini; Kursehi Falgenti; Intan Saesaria; Hanief Fathul Bahri Ahmad; Mohamad Prastya
Jurnal Techno Nusa Mandiri Vol. 23 No. 1 (2026): Techno Nusa Mandiri : Journal of Computing and Information Technology Period o
Publisher : Lembaga Penelitian dan Pengabdian Pada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/j0e97093

Micro, Small, and Medium Enterprises (MSMEs), particularly in service sectors such as laundry businesses, often rely on fragmented and manual operational practices, resulting in inefficiencies and limited managerial visibility. Existing digital laundry applications typically support isolated functionalities and lack end-to-end integration. This study proposes and evaluates an integrated digital laundry application that supports end-to-end operations and remote business monitoring for MSMEs. The research adopts a Design Science Research (DSR) approach combined with Agile-based development. A functional prototype was implemented using Flutter-based mobile applications for customers and staff, along with a web-based dashboard for business owners. The system integrates customer booking, operational workflows, digital payments, automated financial recording, and real-time monitoring within a unified platform. Evaluation was conducted through functional testing, System Usability Scale (SUS) assessment, and business impact analysis involving 10 participants. The system achieved a SUS score of 78.5, indicating good usability. In addition, transaction errors were reduced by approximately 70%, and service processing time improved by 47%. These results demonstrate that the proposed system enhances operational efficiency, financial transparency, and managerial control. This study contributes an empirically validated, domain-specific digital artifact that operationalizes digital transformation and technopreneurship concepts in MSMEs

K-MEANS CLUSTERING OF INDONESIAN BANKING STOCKS USING FINANCIAL RATIOS Fajar Rizki Aditiya; Nina Sulistiyowati; Siska
Jurnal Techno Nusa Mandiri Vol. 23 No. 1 (2026): Techno Nusa Mandiri : Journal of Computing and Information Technology Period o
Publisher : Lembaga Penelitian dan Pengabdian Pada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/dfsypr32

This study aims to classify banking sector issuers listed on the Indonesia Stock Exchange based on financial ratios, namely Return on Assets (ROA), Return on Equity (ROE), and Loan to Deposit Ratio (LDR), to assist investors in analyzing financial performance and making more objective investment decisions. The method used in this study is Knowledge Discovery in Databases (KDD) with the K-Means clustering algorithm. The dataset was obtained from the annual financial reports of 25 banking issuers for the period 2022–2024. The research stages consist of data selection, data cleaning, data transformation, data mining, and interpretation/evaluation. In the transformation stage, the average values of ROA, ROE, and LDR were calculated and normalized using the Min-Max method. The optimal number of clusters was determined using the Elbow method, while cluster quality was evaluated using the Silhouette Coefficient. The results indicate that the optimal number of clusters is three with a Silhouette Coefficient value of 0.5946. The clustering results consist of a dominant cluster containing 22 issuers with relatively stable financial performance, a second cluster consisting of two issuers characterized by higher lending activity and relatively higher risk, and a third cluster containing one issuer with significantly lower financial performance. These findings reveal latent patterns among banking issuers that may not be easily identified through conventional ratio analysis and provide a clearer structural overview of banking sector performance to support investment evaluation. These insights provide a clearer structural overview of the banking sector and may assist investors in identifying banks with comparable financial risk and performance profiles.

MODEL FOR DETERMINING CANDIDATES FOR VILLAGE SOCIAL ASSISTANCE USING THE AHP–MOORA METHOD Hardian Oktavianto; Dodik Aris Setiawan; Guruh Wijaya; Zainul Arifin; Henny Wahyu Sulistyo
Jurnal Techno Nusa Mandiri Vol. 23 No. 1 (2026): Techno Nusa Mandiri : Journal of Computing and Information Technology Period o
Publisher : Lembaga Penelitian dan Pengabdian Pada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/rp2qkd88

Social assistance programs at the village level are one of the government's efforts to reduce poverty and improve community welfare. However, in practice, the process of determining eligible beneficiaries is often carried out manually, which may lead to subjectivity, inaccurate targeting, and a lack of transparency in decision-making. This study aims to develop a decision support system that assists village administrators in determining priority candidates for social assistance in a more objective and systematic manner. The proposed approach integrates the Analytical Hierarchy Process (AHP) and the Multi-Objective Optimization on the Basis of Ratio Analysis (MOORA) methods. The AHP method is used to determine the weight of each criterion through pairwise comparison matrices and consistency testing. Subsequently, the MOORA method is applied to normalize the decision matrix, calculate preference values, and rank the alternatives. The results show that AHP-MOORA can generate a priority ranking of potential social assistance beneficiaries. The calculated weights for the criteria respectively are Kepemilikan Tanah: 0.5579 (highest importance), Kondisi Rumah: 0.2633, Pekerjaan: 0.1219, Penghasilan: 0.0569 (lowest importance) and the value of CR is 0.0654, which is less than 0.1, indicating that the criteria weights are consistent. The ranking based on AHP-MOORA show significant differences than the earlier dataset. Based on sensitivity analysis, the high correlation values in all sensitivity tests show that the ranking results remain consistent. Furthermore, the system improves transparency and consistency in the decision-making process.

SYSTEMATIC LITERATURE REVIEW OF THE DEVELOPMENT AND RESEARCH DIRECTIONS OF TECHNOLOGY INNOVATION-BASED TECHNOPRENEURSHIP Rifanny Lysara Annastasya; Herbert Siregar
Jurnal Techno Nusa Mandiri Vol. 23 No. 1 (2026): Techno Nusa Mandiri : Journal of Computing and Information Technology Period o
Publisher : Lembaga Penelitian dan Pengabdian Pada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/75s34433

The rapid development of digital technology has positioned technopreneurship as a strategic approach to strengthening innovation-driven economic competitiveness. However, research on technology innovation-based technopreneurship remains fragmented, and a systematic mapping of research trends and success determinants is still limited. This study aims to analyze research themes, identify key success factors, and highlight future research directions in technology innovation-based technopreneurship. The study employs a Systematic Literature Review (SLR) approach following the PRISMA guidelines to ensure transparency and replicability in the article selection process. A structured literature search was systematically conducted using the Scopus database, focusing on publications published between 2022 and 2025. The search, guided by predefined keywords, yielded a total of 200 articles for initial consideration. After applying predefined inclusion and exclusion criteria, a final corpus of five articles was identified and analyzed using a thematic analysis approach. The results reveal several dominant themes, including digital innovation, entrepreneurial capability development, startup ecosystem collaboration, and sustainability-oriented technopreneurship. The findings also indicate that the success of technopreneurship is influenced by the integration of individual competencies, digital leadership, and collaborative innovation ecosystems involving academia, industry, and government. This study contributes by providing a systematic mapping of recent technopreneurship research and identifying thematic patterns that shape technology-driven entrepreneurship in the digital era, offering academic insights and practical implications for strengthening innovation ecosystems.

ANALYSIS OF THE EFFECTIVENESS OF THE SCRUM METHODOLOGY IN AN EMPLOYEE TASK MONITORING APPLICATION Dama Sukma Kusuma Diwirya; Nissa Almira Mayangky
Jurnal Techno Nusa Mandiri Vol. 23 No. 1 (2026): Techno Nusa Mandiri : Journal of Computing and Information Technology Period o
Publisher : Lembaga Penelitian dan Pengabdian Pada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/zqd9tj56

This study evaluates the effectiveness of the Scrum methodology in improving the productivity of IT development teams at PT. Erajaya Swasembada Tbk, focusing on the development of an employee task monitoring application. Using a mixed-methods approach, it combines qualitative insights from interviews and observations with quantitative metrics from Evidence-Based Management (EBM), including Employee Satisfaction, Lead Time, Velocity, and Innovation Rate. The findings show that Scrum significantly enhances team collaboration and transparency, with an average Employee Satisfaction score of 4.19 out of 5 and Velocity exceeding targets in several sprints (e.g., 167.5% in PROD Sprint 7). However, inconsistent Scrum practices and limited inter-team communication remain challenges. This study provides recommendations to optimize Scrum implementation to improve project outcomes.

Page 28 of 28 | Total Record : 279

24 25 26 27 28

Filter by Year

2013 2026

Filter By Issues

Home Page

OAI Link

Editorial Team

Contact

Reviewer

Google Scholar

Contact Name
Frieyadie

Contact Email
Frieyadie

Phone
-

Journal Mail Official
frieyadie@nusamandiri.ac.id

Editorial Address
-

Location
Kota adm. jakarta pusat,

Dki jakarta

INDONESIA

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Home Page

OAI Link

Editorial Team

Contact

Reviewer

Google Scholar

Contact Name Frieyadie

Contact Email Frieyadie

Phone -

Journal Mail Official frieyadie@nusamandiri.ac.id

Editorial Address -

Location Kota adm. jakarta pusat, Dki jakarta INDONESIA

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Contact Name
Frieyadie

Contact Email
Frieyadie

Phone
-

Journal Mail Official
frieyadie@nusamandiri.ac.id

Editorial Address
-

Location
Kota adm. jakarta pusat,

Dki jakarta

INDONESIA