UPN (Universitas Pembangunan Nasional) Veteran Yogyakarta: Portal Journals
Not a member yet
5715 research outputs found
Sort by
Implementation of Natural Language Processing with Deep Learning on Chatbot UKT (Uang Kuliah Tunggal) University
Full text linkTujuan: Penelitian yang dilakukan adalah membuat chatbot yang mampu mengklasifikasikan teks soal berdasarkan maksud/label secara lebih tepat, dan membantu memudahkan pelajar dalam memperoleh informasi tambahan terkait layanan UKT (Uang Kuliah Tunggal) dan biaya pendidikan. Chatbot ini mampu mengatasi keterbatasan yang dialami oleh Tata Usaha Fakultas Teknik (TU FT) Universitas Tidar, seperti human delay dalam merespon email atau live chat, keterbatasan jam layanan (office hour), dan keterbatasan informasi pada website kampus. Chatbot dikembangkan menggunakan pendekatan Natural Language Processing (NLP) dan algoritma Deep Learning BiDirectional Long Short-Term Memory (BiLSTM). Hasil sistem chatbot diintegrasikan ke dalam aplikasi Telegram untuk melihat tingkat kepuasan pengguna setelah berinteraksi.Desain/metodologi/pendekatan: Proses penelitian ini diawali dengan pengumpulan dataset berupa pertanyaan dan jawaban yang telah diberi tag atau label dalam format file JSON. Dataset tersebut dilakukan proses normalisasi teks atau preprocessing Natural Language Processing (NLP), dimana pada tahap ini dilakukan lower case atau case lipat, penghapusan tanda baca, penghapusan spasi berlebih, stopword dan stemming dengan perpustakaan Sastrawi, tokenisasi, dan padding. Selanjutnya dilakukan proses split dataset dengan Bagi 80% pelatihan 20% pengujian, sebelum diolah menjadi fitur ekstraksi, menggunakan FastText untuk penyematan kata. Selanjutnya dilakukan proses klasifikasi teks pertanyaan dengan model BiDirectional Long Short-Term Memory (BiLSTM) dan dilanjutkan evaluasi dengan matriks konvergensi. Tahap terakhir, yaitu integrasi chatbot ke dalam bot Telegram, kemudian dilakukan pengujian pengguna terhadap chatbot dan pengukuran tingkat kepuasan dengan metode Customer Satisfaction Score (CSAT).Temuan/Hasil: Model akurasi klasifikasi menghasilkan nilai sebesar 96,05% dan pengujian pengguna dengan penerapan metode Customer Satisfaction Score (CSAT) memberikan tingkat kepuasan rata-rata pada rentang 4 (Puas) dan 5 (Sangat Puas) dengan hasil sebesar 88,86% berdasarkan poin-poin berikut \u27Kepuasan terhadap jawaban yang diberikan\u27, \u27Pemahaman pertanyaan dan jawaban mudah dipahami\u27, dan \u27Kinerja sesuai harapan\u27.Orisinalitas/nilai/keadaan terkini: Penelitian tentang klasifikasi teks pertanyaan pada chatbot dengan pendekatan Natural Language Processing (NLP) dan model BiDirectional Long Short-Term Memory (BiLSTM) untuk menangani permasalahan pertanyaan jawab layanan UKT (Uang Kuliah Tunggal) dan biaya pendidikan Fakultas Teknik Universitas Tidar belum pernah dilakukan sebelumnya
Combination of supply chain operation reference and analytical hierarchy process methods in measuring supply chain management performance in the metal industry
Full text linkThe metal manufacturing industry\u27s supply chain faces problems with inaccurate sales demand analysis, with a 9% discrepancy between forecasted and actual demand. Production activity times are 23% inconsistent with established plans. Shipments of goods are inconsistent with sales orders, preventing the metal company from achieving its delivery targets. This study aims to analyze supply chain performance measurements and provide suggestions for improvements to the results of these measurements. This research method combines the Supply Chain Operation Reference (SCOR) and Analytical Hierarchy Process (AHP) methods. This study identified 17 selected performance indicators and prioritized attributes, namely reliability, responsiveness, and agility. The results of data processing through performance indicator weighting yielded a total SCM performance score of 90.90, with 5 performance indicators requiring improvement. Therefore, the proposed improvements focus more on these 5 dominant indicators. The contribution of this study to the analysis of SCOR and AHP performance measurements is that companies are expected to maximize their supply chains, thereby increasing industrial productivity and gaining a competitive advantage.
Feature-based classification of sugarcane quality using the K-nearest neighbor algorithm
Full text linkThe rapid advancement of artificial intelligence has enabled practical, data-driven approaches to agricultural quality assessment. However, many existing methods rely on complex sensor systems that are costly and difficult to deploy in the field. This study proposes a lightweight and interpretable K-Nearest Neighbor (KNN) model for non-destructive evaluation of sugarcane milling feasibility using five easily measurable physical attributes: relative distance ratio, internode length, mean diameter, circumference, and weight per centimeter. Samples with Brix less than 16 are categorized as not feasible for milling, while Brix equal to or greater than 16 are classified as possible. A dataset of 1,889 Bululawang samples collected in Malang, East Java, Indonesia, was evaluated across twenty-two scenarios that varied the train-test split, normalization method, distance metric, and neighborhood size. The optimal configuration, consisting of an 80:20 split, Standard normalization, the Minkowski distance metric, and k=75, achieved an accuracy of 78%. The findings confirm that physical measurements can serve as effective predictors of sugarcane quality and support data-driven inspection and sustainable resource utilization in line with SDGs 2, 9, and 12
PEMANFAATAN MULSA ORGANIK DAN APLIKASI PGPR TERHADAP PERTUMBUHAN, HASIL, DAN KUALITAS BUNGA POTONG KRISAN (Dendranthema grandiflora Tzvelev)
Full text linkABSTRAK
Hasil dan kualitas bunga yang diproduksi petani memengaruhi harga jual bunga potong krisan. Penelitian ini bertujuan untuk mengetahui pengaruh berbagai jenis mulsa organik dan konsentrasi Plant Growth Promoting Rhizobacteria (PGPR), terhadap pertumbuhan, hasil, dan kualitas tanaman krisan. Penelitian menggunakan percobaan lapangan Rancangan Acak Kelompok Lengkap (RAKL) dengan metode faktorial (3 x 3) + 1. Faktor pertama yaitu jenis mulsa organik (jerami padi, batang pisang, dan rumput gajah) dan faktor kedua yaitu konsentrasi PGPR (25, 50, dan 75 mL/L). Kontrol menggunakan mulsa plastik hitam perak (MPHP), tanpa pemberian PGPR. Analisis dilakukan menggunakan Sidik Ragam (ANOVA) dan dilanjutkan dengan uji DMRT pada taraf 5%. Uji kontras ortogonal digunakan untuk membandingkan antara perlakuan dan kontrol. Hasil penelitian menunjukkan kombinasi perlakuan lebih efektif dari kontrol, pada parameter waktu kemunculan bunga, volume akar, jumlah bunga per tanaman, dan diameter bunga. Terdapat interaksi pada parameter tinggi tanaman umur 56 HST, panjang petiol, dan jumlah bunga per tanaman. Perlakuan mulsa organik jerami padi memberikan hasil paling efektif pada parameter jumlah daun umur 28 HST dan jumlah tangkai bercabang. Konsentrasi PGPR 75 mL/L, memberikan hasil paling efektif pada parameter tinggi tanaman 42 HST, jumlah daun umur 28 HST, diameter batang, volume akar, dan jumlah tangkai bercabang. Kombinasi perlakuan yang menunjukkan hasil terbaik adalah mulsa organik jerami padi dengan konsentrasi PGPR 75 mL/L
IDENTIFIKASI SECARA MORFOLOGI DAN MORFOMETRI NEMATODA ENTOMOPATOGEN PADA LAHAN PERTANAMAN JAGUNG DI KABUPATEN GUNUNGKIDUL
Full text linkCorn productivity often declines due topest attacks, but can be controlled through the use of biological agents such asentomopathogenic nematodes (EPN). This study aims to explore andidentify EPN in corn fields in Gunungkidul Regency morphologically and morphometrically. Soil samples were taken in five districts, namely Wonosari, Playen, Patuk, Karangmojo, and Semanu. NEP trapping was carried out using Tenebrio molitor larvae, then isolatedusing the white head tray method and observed morphologically and morphometrically using a microscope. The results showed that the highest NEP population NEP population was found in Playen Subdistrict (462.67 NEP/5 ml) and the lowest in Patuk Subdistrict (7.33 NEP/5 ml). Population variation is thought to be influenced by differences in soil texture and cultivation systems. Based on the morphological and morphometric characteristics of the NEP found in Gunungkidul corn fields, they were identifiedas Heterorhabditis indica, with a body length ranging from 438.77–501.9 µm. These findings indicate the potential of H. indica as a biological agentin pest control in corn farming ecosystems in the Gunungkidul.
Keywords : morphology, morphometry, population, Tenebrio molitor, white head trayProduktivitas jagung sering menurun akibat serangan hama, namun dapat dikendalikan melalui pemanfaatan agen hayati seperti nematoda entomopatogen (NEP). Penelitian ini bertujuan mengeksplorasi dan mengidentifikasi NEP pada lahan pertanaman jagung di Kabupaten Gunungkidul secara morfologi dan morfometri. Pengambilan sampel tanah dilakukan pada lima kecamatan, yaitu Wonosari, Playen, Patuk, Karangmojo, dan Semanu. Pemerangkapan NEP dilakukan menggunakan larva Tenebrio molitor, kemudian diisolasi dengan metode white head tray dan diamati secara morfologi dan morfometri menggunakan mikroskop. Hasil penelitian menunjukkan bahwa populasi NEP tertinggi ditemukan di Kecamatan Playen (462,67 NEP/5 ml) dan terendah di Kecamatan Patuk (7,33 NEP/5 ml). Variasi populasi diduga dipengaruhi oleh perbedaan tekstur tanah dan sistem budidaya. Berdasarkan karakter morfologi dan morfometri NEP yang ditemukan di lahan jagung Gunungkidul diidentifikasi sebagai Heterorhabditis indica, dengan panjang tubuh berkisar antara 438,77–501,9 µm. Temuan ini menunjukkan potensi H. indica sebagai agen hayati dalam pengendalian hama di ekosistem pertanian jagung di wilayah Gunungkidul.
Kata kunci : morfologi, morfometri, populasi, Tenebrio molitor, white head tray
 
Scrutinizing Crop production from Ayamaru Timur District, Maybrat-Southwest Papua Province; Land-Use and Agribusiness Cycles’ Potential
Full text linkUnderstanding the land-use potential in Ayamaru Timur District, Maybrat-Southwest Papua Province provides insights into optimizing agricultural activities to boost local economies and ensure sustainable development in the region. The aims of study are to explore the land-use potential and agribusiness cycles in Ayamaru Timur District by analysing physiographic characteristics, soil types, and existing land utilization patterns, the research identifies opportunities and challenges for optimizing agricultural productivity. Methods employed are field observation in on land-uses of farming land and surveys by interviewing key farmers using open structural questionnaire. Samples of soils then analysed in the Soil Laboratory of Agriculture Faculty, Papua University for further syntheses. Parameters measured are physiographic of lands, soil types and suitability, crop types and actual and potential suitability, types of crops including production and productivities, revenue, cost and added to this income generation. Major challenges are recorded for future policy development. Data presented by statistical descriptives and tabulations. The finding revealed that land suitable ranges from marginal to moderately suitable. Potential land-uses are agroforestry crops, food crops, and plantation crops. Non-agricultural land (1%), followed by agroforestry crops, food and plantation crops are actually useable by farmers. Crops grown are tubers, vegetables, non-tuber crops and legumes. Revenues earned firstly from vegetables (IDR 1,890,476), followed by tuber crops (IDR 926,506), Nuts (IDR 486,170), and non-tubers (IDR 420,000). In conclusion, vegetables, tuber and non-tuber crops, including legumes have potential for agricultural development
Household Livelihood Strategies Following the Decline of Shrimp Pond Productivity in Bumi Dipasena, Tulang Bawang, Indonesia
Full text linkBumi Dipasena in Tulang Bawang Regency, Lampung Province, was once the largest shrimp farming area in Southeast Asia and played a major role in Indonesia’s shrimp exports. Since the early 2000s, shrimp pond productivity has declined due to institutional conflicts, infrastructure degradation, limited access to capital, and unstable production systems, resulting in reduced household income and economic pressure on local communities. This study aims to identify and analyze household livelihood strategies following the decline of shrimp pond productivity in Bumi Dipasena. The research employs a qualitative descriptive approach based on secondary data, utilizing official statistics, government reports, scientific publications, and credible media sources. Data were analyzed through descriptive qualitative analysis, including data reduction, thematic categorization, and identification of livelihood strategy patterns. The findings show that households respond to the decline by diversifying income into informal sectors, small-scale trade, labor migration, and increased reliance on social networks. These livelihood strategies reflect household-level economic responses to prolonged structural changes after the collapse of shrimp farming as the primary livelihood source. This study contributes to socio-economic and development studies by providing empirical insights into household livelihood reorganization in post-aquaculture decline contexts and offers policy-relevant input for sustainable livelihood support in coastal areas
Tourism Communication: Garuda Indonesia Airline In Improving Its Brand As A Tourism Transportation Service Provider
Full text linkThe development of the tourism sector intersects with other business sectors as it supports the tourism industry. Modern tourism management is a concept that defines tourism as a modern business product consisting of tourist destinations, the creative economy, transportation, hotels, recreation areas, and arts and cultural attractions, packaged in attractive tour packages for potential tourists. Modern tourism destinations are complex and capital-intensive, requiring business management and promotional activities. So, how does Garuda Indonesia enhance its brand as a tourism transportation service provider?
This study aims to examine Tourism Communication: Garuda Indonesia\u27s Brand Enhancement as a Tourism Transportation Service Provider using the concept of tourism transportation communication, which is part of tourism communication studies. The closest discipline to tourism communication is marketing communication.
This study will use a case study with a qualitative approach. Data collection was conducted through interviews, documentation, and observation. Research informants were selected using purposive sampling techniques.
The results of this study indicate that Garuda Indonesia is a tourism transportation service provider. The results show that the factors that determine passengers\u27 choice of flying with Garuda are safety, price (in relation to facilities, service, and affordability), social (face-to-face, virtual, and relationships), comfort (physical and employees), membership (points, lounge, and redemption), and punctuality. Meanwhile, the motives for passengers choosing to fly with Garuda are achievement (punctuality and points), experience (comparison and aircraft), parental recognition, responsibility (family and work), and pleasure (service, physical, and travel)
Digital Health Advocacy: Exploring Instagram\u27s Role in Promoting Public Support for Sugar-Sweetened Beverage Excise
Full text linkThe Instagram account @fyindonesians has emerged as a response to the rising consumption of Sugar-Sweetened Beverages (SSBs) in Indonesia and the lack of comprehensive regulatory instruments to address it. This study examines how @fyindonesians contributes to building public support for implementing an SSB tax as a health policy intervention. Using a qualitative case study design, the analysis is grounded in the Theory of Interactive Media Effects. Data were obtained through semi-structured interviews, complemented by content analysis via the Fanpage Karma application and validated through triangulation. The results indicate that @fyindonesians actively shapes social understanding of health issues through the platform\u27s interactive affordances, utilizing both cue- and action-route mechanisms. The cue route directs initial audience attention through engaging visuals, social metrics, and consistent content style. In contrast, the action route fosters deeper cognitive engagement via interactive features, gradual information processing, and reflection on consumption behavior. These mechanisms jointly enhance user engagement, cultivate positive health attitudes, and encourage support for SSB excise