ejournal.nusamandiri.ac.id (STMIK Nusa Mandiri)
Not a member yet
1504 research outputs found
Sort by
SYSTEMATIC LITERATURE REVIEW ON ARTIFICIAL INTELLIGENCE IN INDONESIA’S PUBLIC SECTOR: REIMAGINING DIGITAL GOVERNMENT
Get PDFThis study conducts a Systematic Literature Review (SLR) to critically examine the application of Artificial Intelligence (AI) in e-government within the Indonesian public sector. Addressing the limited empirical research and fragmented understanding of AI adoption in Indonesia’s digital governance landscape, this review analyzes 22 peer reviewed articles published between 2021 and 2025 from reputable databases including Scopus, IEEE, ACM Digital Library, SpringerLink, and Emerald Insight. The review identifies adaptability and innovation, ethical consideration, collaboration and partnership as the most frequently cited critical success factors. Meanwhile, the top three recurring challenges are lack of awareness, skill & expertise, policy or legal uncertainty, resistance to change. To address these challenges, the study proposes a multi dimensional AI implementation strategy focusing on strengthening digital infrastructure, developing human capital through sustained capacity building, formulating clear and accountable AI governance policies, and fostering inclusive, cross sectoral stakeholder engagement. This study offers novel insights by mapping AI related factors into the Technology,Organization, Environment (TOE) framework and synthesizing practical, context-specific recommendations for Indonesian policymakers seeking to build an adaptive, inclusive, and sustainable AI based e-government ecosyste
QUANTUM-ASSISTED FEATURE SELECTION FOR IMPROVING PREDICTION MODEL ACCURACY ON LARGE AND IMBALANCED DATASETS
Get PDFOne of the biggest obstacles to creating precise machine learning models is choosing representative and pertinent characteristics from big, unbalanced datasets. While too many features raise the risk of overfitting and computational expense, class imbalance frequently results in decreased accuracy and bias. The Simulated Annealing technique is used in this study to tackle a Quadratic Unconstrained Binary Optimization (QUBO) problem that is formulated as a quantum-assisted feature selection method to handle these problems. The technique seeks to reduce inter-feature redundancy and the number of selected features. There are 102,487 samples in the majority class and 11,239 in the minority class, totaling 28 characteristics in the experimental dataset. Nine ideal features were found during the feature selection method (12, 14, 15, 22, 23, 24, 25, 27, and 28). Ten-fold cross-validation was used to assess a Random Forest Classifier that was trained using an 80:20 split. With precision, recall, f1-score, and accuracy all hitting 1.00, the suggested QUBO+SMOTE method demonstrated exceptional performance. Comparatively, QUBO without SMOTE performed worse with accuracy 0.95 and minority-class f1-score of only 0.71, whereas a traditional Recursive Feature Elimination (RFE) approach obtained accuracy 0.97 with minority-class f1-score of 0.94. These findings indicate that QUBO can reduce dimensionality and address class imbalance which requires its integration with SMOTE. This study demonstrates how quantum computing can enhance the effectiveness and efficiency of machine learning, especially for large-scale imbalanced dataset
PENDAMPINGAN UMKM BATIK LASEM MELALUI INOVASI CANTING CAP DAN DIGITAL MARKETING
Get PDFUMKM Batik Tulis Lasem is one of the superior product MSMEs in Rembang Regency. The partners in this service are 2 MSMEs engaged in batik, namely Real Asto Batik and Safila Batik. The problems of both partners are the lack of product innovation and the lack of current marketing techniques. The purpose of this service is to increase partners' knowledge and skills regarding stamped batik techniques and digital marketing. In addition, the purpose of this service is to improve the management and productivity of partners in the lasem batik business. The methods in this service are socialisation, training and mentoring, technology application and evaluation. The results of the service showed that the skills and knowledge of the partners' stamping techniques and digital marketing increased with a percentage of 44% increasing very high, 54% stated high. In addition, the results of the programme evaluation also showed that the performance of the service team was very good. This programme became one of the programmes that had a positive impact on partners in particular, and in general, improving the economy and tourism of Rembang through textile and fashion products
PEMELIHARAAN DAN PENAMBAHAN DAYA PEMBANGKIT LISTRIK TENAGA SURYA PADA LAHAN PERTANIAN KELOMPOK TANI D’RANGRANG DEPOK
Get PDFThe Drangrang farmer group’s agricultural garden, located at RT10 RW03, Tirtajaya Village, Sukmajaya District, Depok, covers an area of approximately 1,500 m². The land is used to cultivate vegetables and crops such as corn, peanuts, and cucumbers. Electricity for agricultural operations is supplied by a Solar Power Plant (PLTS) with an initial capacity of 100 Wp. However, along with land expansion and increased load demand, the existing PLTS system could no longer meet energy needs, requiring a capacity upgrade. This community service activity aimed to provide technical assistance for the installation of additional solar panels to increase the PLTS capacity and fulfill electricity requirements for lighting and water pumps. The method included equipment procurement, system assembly in the garden area, and PLTS testing. The activity was carried out by lecturers and students from the Department of Electrical Engineering, Gunadarma University. The stages consisted of design, installation, testing, and measurement. The upgraded PLTS system now provides 200 Wp, capable of supplying four lighting points and one 160 W water pump. The additional capacity ensures a safer and more continuous power supply, supporting improved agricultural productivity and operational efficiency of the farmer group
PENGUATAN EKONOMI LOKAL MELALUI DIGITALISASI UMKM PEREMPUAN: STUDI KASUS KELOMPOK TANI WANITA DESA SIDODADI
Get PDFStrengthening the local economy through the active role of the Women Farmers Group (KTW) by improving digital marketing technology skills is an effective strategy for developing rural MSMEs. Sidodadi Village in Malang Regency has several key agricultural commodities such as bananas, cassava, and corn, which are mostly processed and marketed by women’s MSME groups. However, several challenges remain, including limited institutional management capacity, lack of knowledge about digital marketing technology, and restricted market access, making it difficult for MSMEs to compete. This community service aims to assist the Women Farmers Group in improving institutional management capacity and digital marketing skills through training and mentoring activities. The program was conducted in Sidodadi Village using survey, socialization, and training methods, followed by evaluation. The evaluation results show that participants were enthusiastic, actively involved, and demonstrated improved understanding and skills in using digital marketing tools. The activity successfully encouraged the group to optimize digital marketing for the sustainable growth of rural MSMEs. Therefore, this service is expected to increase the efficiency of agricultural product marketing and positively impact community welfare and income
PENERAPAN WEBSITE PROMOSI WISATA AIR TLAGA PESONA DI DESA TLAGAYASA BERBASIS WORDPRESS
Get PDFTlagayasa Village, located in Bobotsari Sub-district, Purbalingga Regency, Central Java, is situated about 30 km from the Department of Physics, Faculty of Mathematics and Natural Sciences, UNSOED. Based on interviews with village officials, a water tourism destination with various attractions is currently being developed. However, despite progress in physical facilities, plans for proper tourism promotional media remain unprepared. The village government, in coordination with the Faculty of Mathematics and Natural Sciences, UNSOED, identified limited knowledge of promotional strategies and the absence of a digital database as major challenges. To address this issue, village officials requested assistance in developing online promotional media. Considering the rapid advancement of information technology, digital platforms play a crucial role in supporting tourism promotion. Through community service activities, several stages were implemented, including socialization, training, mentoring, and evaluation. The initial stage involved data collection and website development using WordPress, followed by training for BUMDes Tlaga Pesona managers. Mentoring was then conducted to enable them to manage the website independently. Evaluation results showed that the website improved the managers’ digital literacy, sense of ownership, and responsibility for sustainable tourism promotion. This program demonstrates the tangible benefits of academic–community collaboration and provides a replicable model for technology-based tourism development in rural areas
PELATIHAN PENULISAN BUKU REFERENSI BAGI GURU SEKOLAH DASAR SEBAGAI UPAYA PENINGKATAN BUDAYA LITERASI
Get PDFThe dynamic development of the education sector requires teachers who are highly motivated and skilled in adapting to technological advancements. One effective strategy for elementary school teachers is to develop engaging, student-centered, and environmentally contextual learning materials. To support this, higher education institutions play a vital role in offering direction, encouragement, and mentoring through community service programs. This initiative aimed to enhance the competencies of teachers at SD Arjowinangun 2 and SDN Polehan 5 in Malang City by equipping them with the skills and independence to write reference books that support classroom learning. The program combined independent mentoring and classical in-school training, implemented over three months, with a two-day intensive session on August 7–8, 2024, followed by post-training mentoring. Teachers received detailed guidance on drafting, structuring, and publishing reference books. Throughout the sessions, participants engaged in active discussions to address challenges in the writing process. As a result, teachers successfully produced reference books tailored to the needs of their students, contributing to the availability of contextual learning resources and the overall improvement of instructional quality in elementary education in SD Arjowinangun 2 and SDN Polehan 5 in Malang City in supporting the learning process
CITRA DESTINASI DAN MINAT BERKUNJUNG KEMBALI : ANALISIS MODERASI KEPUASAN WISATAWAN
Get PDFThis study stems from the phenomenon of Gua Kristal’s remarkable tourism potential, yet the level of revisit intention remains relatively low. The purpose of this research is to analyze the influence of destination image on revisit intention by considering tourist satisfaction as a moderating variable. A quantitative approach was employed with the population consisting of all visitors to Gua Kristal. The sampling technique used was incidental sampling, resulting in 120 respondents. Data were collected through a questionnaire using a 5 point Likert scale, and analyzed using regression and Moderated Regression Analysis (MRA). The findings reveal that destination image has a significant effect on revisit intention, and tourist satisfaction is able to strengthen this influence. The implications highlight the importance for destination managers to maintain a positive image through cleanliness, safety, facilities, and effective promotion strategies. Moreover, tourist satisfaction must be prioritized by providing friendly services, adequate facilities, and enjoyable experiences, thereby enhancing visitors’ revisit intention.Penelitian ini berangkat dari fenomena potensi wisata Gua Kristal yang sangat menarik, namun tingkat kunjungan ulang wisatawan masih rendah. Tujuan penelitian adalah untuk menganalisis pengaruh citra destinasi terhadap minat berkunjung kembali dengan memasukkan kepuasan wisatawan sebagai variabel moderasi. Metode yang digunakan adalah pendekatan kuantitatif dengan populasi seluruh wisatawan Gua Kristal. Teknik pengambilan sampel dilakukan secara incidental sampling dan diperoleh 120 responden. Instrumen penelitian berupa kuesioner dengan skala Likert 1–5, sementara analisis data menggunakan analisis regresi sederhana dan Moderated Regression Analysis (MRA). Hasil penelitian menunjukkan bahwa citra destinasi berpengaruh signifikan terhadap minat berkunjung kembali, serta kepuasan wisatawan mampu memperkuat pengaruh citra destinasi tersebut. Implikasi penelitian menegaskan pentingnya pengelola destinasi menjaga citra melalui aspek kebersihan, keamanan, fasilitas, dan strategi promosi yang tepat. Selain itu, kepuasan wisatawan harus menjadi prioritas utama dengan memberikan layanan ramah, fasilitas yang memadai, dan pengalaman yang menyenangkan, sehingga dapat meningkatkan minat wisatawan untuk kembali berkunjung.
 
APPLYING K-MEANS CLUSTERING FOR GROUPING PAPUA’S DISTRICTS BASED ON POVERTY INDICATORS ANALYSIS
Get PDFIn the context of Indonesia's resource-rich development, poverty remains a major challenge, especially in Papua Province which has the highest poverty rate. Although Papua is rich in resources such as minerals, tropical forests, and biodiversity, challenges such as economic inequality, lack of infrastructure, and social conflict hinder economic and social progress. This research aims to implement the K-Means Clustering algorithm to cluster districts/cities in Papua based on poverty indicators, including the percentage of poor people, poverty line, average years of schooling, human development index, poverty depth index, poverty severity index, unemployment rate, and per capita expenditure. The research methodology includes data collection from the Central Statistical Agency (BPS), data processing through cleaning and transformation stages, and application of K-Means Clustering to determine the optimal cluster using the elbow method and silhouette score. The results show that the districts/cities in Papua can be grouped into two main clusters: C0, which indicates high poverty rates and C1, which indicates low poverty rates. This research is expected to provide a strategic foundation for the government to design more focused and effective development policies in reducing poverty in Papua
COMBINATION OF LEARNING VECTOR QUANTIZATION AND LINEAR DISCRIMINANT ANALYSIS FOR TEA LEAF DISEASE CLASSIFICATION
Get PDFTea farming, one of the key pillars of Indonesia's economy, faces productivity challenges due to diseases affecting tea leaves. Manual identification of tea leaf diseases requires significant time and cost, making an automated solution necessary. This research develops an innovative model for classifying tea leaf diseases by synergizing Learning Vector Quantization (LVQ) and Linear Discriminant Analysis (LDA). By leveraging LVQ’s prototype-based classification and LDA’s dimensionality reduction, the model ensures accurate and efficient disease identification. During preprocessing, tea leaf images were converted to the CIELAB color space to enhance segmentation using Otsu’s Thresholding. Features such as Mean Color and texture attributes based on Gray Level Co-occurrence Matrix (GLCM) were extracted, reduced via LDA, and classified using LVQ. Tested on five tea leaf disease classes, the model achieved 94.1% accuracy. This performance underscores its potential to significantly assist farmers in early detection and management of tea leaf diseases, while also providing researchers with a robust tool for advancing agricultural technology