Abstract:One of the impacts of the Covid-19 Pandemic is the change of learning process in elementary schools from offline learning to online learning. The results of the observations at Al-Khoiriyyah islamic elementary school show…
w that partners still had difficulties in utilizing information technology facilities besides there was also a decrease in the enthusiasm of teachers and students in the learning process. The community service team offers solutions by providing training related to interactive learning media and the utilization of technology using the wordwall application. The wordwall application can attract the enthusiasm of teachers and students in the learning process by utilizing various features. This training was attended by 8 participants located at UHW Perbanas on June 24, 2022. The methods used were discussion, independent practice, and evaluation obtained from filling out the pre-test and post-test. The results of the training and mentoring show that 100% of the training participants are able to use wordwalls. The learning media using this wordwall had a significant effect and this was shown by the practical results of each participant who successfully completed the tasks given by the community service team which is 8 participants successfully made a quiz using the wordwall application.
Abstract:Abstract: Sinar Jaya store is a store that sells fire extinguishers in Medan city. In majority, this store still serves transactions by accepting customer to the store directly. Since the COVID-19 pandemic has lasted for…
so long, this store has begun to explore technology by utilizing Instagram as social media and having a website which can be accessed via www.sinarjayamedan.com as a medium to introduce the store, market the products digitally and increase business legitimacy. However, existing web pages must be optimized further to improve the ability of Toko Sinar Jaya in response to marketing needs. The measurement results using 2 (two) Search Engine Optimization (SEO) measurement websites show an average score of 61,5 out of a scale of 100. Thus, this community service activity is aimed at increasing this SEO score. SEO activities are carried out by using the on-page SEO method on existing web pages and continued with Content Management training for off-page SEO implementation. On-page SEO is carried out with activities including the installation of the Yoast SEO plugin, keyword research, visibility and permalink settings, Google Search Console, Google Analytics, sitemap generator and schema markup. The SEO score then increased significantly from 61,5 to 74,5.
Keywords: inbound marketing; micro, small and medium enterprise; search engine optimization (SEO)
Abstrak: Toko Sinar Jaya merupakan toko yang menjual alat-alat pemadam kebakaran di kota Medan. Secara mayoritas, toko ini masih melayani transaksi langsung dengan menerima kedatangan pelanggan ke toko. Sejak pandemi COVID-19 yang berlangsung telah begitu lama, toko ini mulai mengeksplorasi teknologi dengan memanfaatkan media sosial Instagram dan memiliki website yang bisa diakses lewat www.sinarjayamedan.com sebagai media untuk memperkenalkan toko, memasarkan produk secara digital dan meningkatkan legitimasi bisnis. Namun demikian, laman web yang ada harus dioptimalkan lagi untuk lebih meningkatkan kemampuan Toko Sinar Jaya dalam menjawab kebutuhan pemasaran. Hasil pengukuran menggunakan 2 (dua) website pengukuran Search Engine Optimization (SEO) masih menunjukkan rata-rata skor 61,5 dari skala 100. Kegiatan pengabdian kepada masyarakat ini ditujukan untuk meningkatkan skor SEO ini. Kegiatan SEO dilakukan secara on-page terhadap laman web dan dilanjutkan dengan pelatihan Content Management untuk implementasi SEO secara off-page. SEO on-page dilakukan dengan kegiatan meliputi Instalasi plugin Yoast SEO, keyword research, visibility and permalink setting, Google Search Console, Google Analytics, sitemap generator dan schema markup. Skor SEO kemudian meningkat dengan cukup signifikan dari angka 61,5 menjadi 74,5.
Kata kunci: inbound marketing; search engine optimization (SEO); usaha mikro, kecil dan menengah (UMKM)
Abstract:Abstrak: Computer technology more and more influential in the management of office space at the moment. It is characterized by the more easy it is bureaucracy, the study of grammar of the easy access to information from…
one point to another. Of course, computer technology will not be such a big contribution to the development of the management of the Government if the role of human resources is not optimized. With respect to the development of computer technology, until now has been a significant development occurred in several areas in regard of the IT application in management offices. Contradictory with the above example, there are still many areas that still have not had the courage or good faith to apply IT in the management of this Office for various reasons. In fact, the IT deployment in government management office management in particular can be a motivation for employees to improve productivity of work.
Keywords : Computer technology, management offices, government
Abstrak: Teknologi Komputer semakin banyak berperan dalam manajemen perkantoran saat ini. Hal ini ditandai dengan semakin mudahnya birokrasi tata persuratan, semakin mudahnya akses informasi dari satu titik ke titik lainnya. Tentu saja, teknologi komputer tidak akan sedemikian besar kontribusinya bagi perkembangan manajemen pemerintahan jika peran sumber daya manusia tidak dioptimalkan. Sehubungan dengan perkembangan teknologi komputer, hingga saat ini telah terjadi perkembangan yang signifikan di beberapa daerah dalam kaitan aplikasi TI dalam Manajemen Perkantoran. Kontradiktif dengan kalimat di atas, masih banyak pula daerah perkantoran didesa yang masih belum memiliki keberanian atau itikad baik untuk mengaplikasikan TI dalam manajemen perkantoran ini dengan berbagai alasan. Padahal, pengaplikasian TI dalam manajemen pemerintahan khususnya manajemen perkantoran dapat menjadi motivasi bagi pegawai untuk meningkatkan produktivitas kerjanya.
Kata Kunci: teknologi komputer, manajemen perkantoran, pemerintahan
Abstract:Abstract: The increasing use of the Maxim ride-hailing application in Manokwari highlights the need to understand the factors influencing user acceptance and satisfaction. However, the growing number of users does not necessarily…
cessarily reflect a high level of technology acceptance and user satisfaction. This study aims to examine the effects of performance expectancy, effort expectancy, facilitating conditions, and habit on behavioral intention, as well as the effect of behavioral intention on user satisfaction among Maxim users in Manokwari. A quantitative approach based on the Unified Theory of Acceptance and Use of Technology 2 (UTAUT2) was employed. Data were collected through questionnaires using a purposive sampling technique from 156 valid respondents and analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM) with SmartPLS 4.0. The results show that performance expectancy (β = 0.343, p < 0.001), effort expectancy (β = 0.191, p = 0.002), facilitating conditions (β = 0.142, p = 0.029), and habit (β = 0.359, p < 0.001) positively and significantly influence behavioral intention. Furthermore, behavioral intention positively and significantly affects user satisfaction (β = 0.771, p < 0.001). These findings confirm the applicability of the UTAUT2 model and provide practical insights for Maxim management and application developers to improve service quality and user satisfaction.
Keywords: behavioral intention; effort expectancy; facilitating conditions; habit; performance expectancy; user satisfaction.
Abstrak: Meningkatnya penggunaan aplikasi transportasi daring Maxim di Manokwari mendorong perlunya memahami faktor-faktor yang memengaruhi penerimaan teknologi dan kepuasan pengguna. Namun, peningkatan jumlah pengguna belum tentu mencerminkan tingginya tingkat penerimaan teknologi dan kepuasan pengguna. Penelitian ini bertujuan menganalisis pengaruh performance expectancy, effort expectancy, facilitating conditions, dan habit terhadap behavioral intention, serta pengaruh behavioral intention terhadap user satisfaction pada pengguna aplikasi Maxim di Manokwari. Penelitian ini menggunakan pendekatan kuantitatif berdasarkan model Unified Theory of Acceptance and Use of Technology 2 (UTAUT2). Data dikumpulkan melalui kuesioner menggunakan teknik purposive sampling terhadap 156 responden dan dianalisis menggunakan Partial Least Squares Structural Equation Modeling (PLS-SEM) dengan SmartPLS 4.0. Hasil penelitian menunjukkan bahwa performance expectancy (β = 0,343; p < 0,001), effort expectancy (β = 0,191; p = 0,002), facilitating conditions (β = 0,142; p = 0,029), dan habit (β = 0,359; p < 0,001) berpengaruh positif dan signifikan terhadap behavioral intention. Selanjutnya, behavioral intention berpengaruh positif dan signifikan terhadap user satisfaction (β = 0,771; p < 0,001). Temuan ini menegaskan penerapan model UTAUT2 serta memberikan masukan bagi manajemen Maxim dan pengembang aplikasi untuk meningkatkan kualitas layanan dan kepuasan pengguna.
Kata kunci: behavioral intention; effort expectancy; facilitating conditions; habit; performance expectancy; user satisfaction.
Abstract:Abstract: The advancement of smart agriculture has become a promising solution to increase food productivity and land use efficiency in urban environments. This research aims to develop an Artificial Intelligence (AI)-based…
sed vertical hydroponic farming system integrated with LED grow light technology and catfish aquaponics. The proposed system combines vertical hydroponics and aquaponics to optimize plant growth and water utilization. Internet of Things technology enables real-time environmental monitoring through an Arduino Uno microcontroller integrated with LDR, soil moisture, pH, and NPK sensors. The obtained sensor data is processed using the Mamdani Fuzzy Logic algorithm, which performs fuzzification, rule inference, aggregation, and defuzzification to generate adaptive control decisions for irrigation, nutrient circulation, and LED grow light intensity. This research uses the Research and Development (R&D) method through prototype development and performance evaluation for 30 days using spinach (Amaranthus spp.) and mustard greens (Brassica juncea) as test plants. Experimental results showed that the developed system successfully maintained stable environmental conditions, with soil moisture ranging between 69–72%, a pH value between 6.4 and 6.6, and optimal nutrient availability. Plant growth increased significantly. The integration of IoT, AI and aquaponics improves cultivation efficiency, enabling environmental control as a smart and sustainable solution for urban agriculture.
Keywords: artificial intelligence; aquaponic; hydroponic; LED grow light; vertical farming
Abstract: Kemajuan pertanian cerdas telah menjadi solusi yang menjanjikan untuk meningkatkan produktivitas pangan dan efisiensi penggunaan lahan di lingkungan perkotaan. Penelitian ini bertujuan untuk mengembangkan sistem pertanian hidroponik vertikal berbasis Kecerdasan Buatan (AI) yang terintegrasi dengan teknologi lampu tumbuh LED dan aquaponik ikan lele. Sistem yang diusulkan menggabungkan hidroponik vertikal dan aquaponik untuk mengoptimalkan pertumbuhan tanaman dan pemanfaatan air. Teknologi Internet of Things memungkinkan pemantauan lingkungan secara real-time melalui mikrokontroler arduino uno yang terintegrasi dengan sensor LDR, kelembaban tanah, pH, dan NPK. Data sensor yang diperoleh diproses menggunakan algoritma Logika Fuzzy Mamdani, yang melakukan fuzzifikasi, inferensi aturan, agregasi, dan defuzzifikasi untuk menghasilkan keputusan kontrol adaptif untuk irigasi, sirkulasi nutrisi, dan intensitas lampu tumbuh LED. Penelitian ini menggunakan metode Pengembangan (R&D) melalui pengembangan prototipe dan evaluasi kinerja selama 30 hari menggunakan bayam (Amaranthus spp.) dan sawi hijau (Brassica juncea) sebagai tanaman uji. Hasil eksperimen menunjukkan bahwa sistem yang dikembangkan berhasil mempertahankan kondisi lingkungan yang stabil, dengan kelembaban tanah berkisar antara 69–72%, nilai pH antara 6,4 dan 6,6, dan ketersediaan nutrisi yang optimal. Pertumbuhan tanaman meningkat secara signifikan. Integrasi IoT, AI dan aquaponik meningkatkan efisiensi budidaya, untuk pengendalian lingkungan sebagai solusi cerdas dan berkelanjutan untuk pertanian perkotaan.
Keywords: aquaponik; kecerdasan buatan; hidroponik; lampu tumbuh LED; pertanian vertikal
Abstract:Abstract: Digital technology has expanded the usage of mobile apps like M-Tix for movie ticket booking. The success of an app depends on its features, user experience, and technical acceptability. The User Experience Questionnaire…
stionnaire (UEQ) and Technology acceptability Model (TAM) will be used to examine how user experience affects technology acceptability and M-Tix application usage in Manokwari Regency. Quantitative methods were used with 149 respondents. SmartPLS 4 was used to analyse data using PLS-SEM. Researchers found that Hedonic Quality positively impacts Perceived Usefulness (β=0.288; p=0.005). Pragmatic Quality significantly impacts Perceived Ease of Use (β=0.651; p<0.001) and Usefulness (β=0.372; p=0.002). Additionally, Perceived Ease of Use (β=0.180; p=0.043) and Usefulness (β=0.453; p<0.001) favourably impact Behavioural Intention. However, Perceived Ease of Use does not substantially impact Perceived Usefulness (β=0.105; p=0.265). These data show that user experience is crucial to technological adoption and M-Tix application usage.
Keywords: m-tix; PLS-SEM; technology acceptance model (TAM); user experience; user experience questionnaire (UEQ).
Abstrak: Teknologi digital telah memperluas penggunaan aplikasi seluler seperti M-Tix untuk pemesanan tiket film. Keberhasilan suatu aplikasi bergantung pada fitur-fiturnya, pengalaman pengguna, dan penerimaan teknis. Kuesioner Pengalaman Pengguna (UEQ) dan Model Penerimaan Teknologi (TAM) akan digunakan untuk meneliti bagaimana pengalaman pengguna memengaruhi penerimaan teknologi dan penggunaan aplikasi M-Tix di Kabupaten Manokwari. Metode kuantitatif digunakan dengan 149 responden. SmartPLS 4 digunakan untuk menganalisis data menggunakan PLS-SEM. Peneliti menemukan bahwa Kualitas Hedonik berdampak positif pada Kegunaan yang Dirasakan (β=0,288; p=0,005). Kualitas Pragmatis berdampak signifikan pada Kemudahan Penggunaan yang Dirasakan (β=0,651; p<0,001) dan Kegunaan (β=0,372; p=0,002). Selain itu, Kemudahan Penggunaan yang Dirasakan (β=0,180; p=0,043) dan Kegunaan (β=0,453; p<0,001) berdampak positif terhadap Niat Perilaku. Namun, Kemudahan Penggunaan yang Dirasakan tidak berdampak signifikan terhadap Kegunaan yang Dirasakan (β=0,105; p=0,265). Data ini menunjukkan bahwa pengalaman pengguna sangat penting untuk adopsi teknologi dan penggunaan aplikasi M-Tix.
Kata kunci: m-tix; PLS-SEM; technology acceptance model (TAM); user experience; user experience questionnaire (UEQ).
Abstract:Abstract: Choosing the right elementary school is a crucial milestone for a child's future. However, the large number of school options in Asahan Regency with diverse criteria such as accreditation, facilities, fees, curriculum,…
riculum, and accessibility often makes it difficult for parents. Decision-making tends to be based on subjective word-of-mouth recommendations, which risks triggering bias. This research aims to develop an adaptive and objective web-based elementary school selection Decision Support System (DSS) framework to minimize such bias. The system is designed using a hybrid model that combines the Simple Multi-Attribute Rating Technique (SMART) method as a dynamic criteria weighting engine based on parents' preferences, and the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) method to rank ten alternative schools. System testing was conducted through black-box testing functionality and empirical accuracy testing using Spearman Rank Correlation involving 40 respondents. The black-box testing results confirmed that all main system operations ran perfectly with a 100% success rate. Validity testing demonstrated very high accuracy, with a Spearman correlation coefficient of 0.89, demonstrating significant alignment between the system's recommendations and actual choices on the ground. Thus, the SMART-TOPSIS framework has proven reliable as a data-driven approach to helping parents choose the best elementary school.
Keywords: decision support system; elementary school; SMART; TOPSIS
Abstrak: Memilih sekolah dasar yang tepat merupakan tonggak awal krusial bagi masa depan anak. Namun, banyaknya pilihan sekolah di Kabupaten Asahan dengan keberagaman kriteria seperti akreditasi, fasilitas, biaya, kurikulum, dan aksesibilitas sering kali menyulitkan orang tua. Pengambilan keputusan pun cenderung didasarkan pada rekomendasi subjektif dari mulut ke mulut, yang berisiko memicu bias. Penelitian ini bertujuan mengembangkan kerangka kerja Sistem Pendukung Keputusan (SPK) pemilihan sekolah dasar berbasis web yang adaptif dan objektif guna meminimalkan bias tersebut. Sistem dirancang menggunakan model hibrida yang mengombinasikan metode *Simple Multi-Attribute Rating Technique* (SMART) sebagai mesin pembobotan kriteria dinamis sesuai preferensi orang tua, serta metode *Technique for Order of Preference by Similarity to Ideal Solution* (TOPSIS) untuk memeringkat sepuluh sekolah alternatif. Pengujian sistem dilakukan melalui uji fungsionalitas *black-box testing* dan uji akurasi empiris menggunakan Korelasi Peringkat Spearman dengan melibatkan 40 responden. Hasil *black-box testing* mengonfirmasi seluruh operasi utama sistem berjalan sempurna dengan tingkat keberhasilan 100%. Uji validitas menunjukkan akurasi sangat tinggi dengan koefisien korelasi Spearman sebesar 0,89, membuktikan keselarasan signifikan antara rekomendasi sistem dan pilihan nyata di lapangan. Dengan demikian, kerangka SMART-TOPSIS ini terbukti andal sebagai pendekatan berbasis data untuk membantu orang tua memilih sekolah dasar terbaik.
Kata kunci: sekolah dasar; sistem pendukung keputusan; SMART; TOPSIS
Abstract:Abstract: Query performance is a critical factor in managing large-scale databases. One of the most widely used optimization techniques is indexing. This study aims to analyze the impact of indexing on query performance…
in PostgreSQL, compare the effectiveness of B-Tree and Hash indexes, and evaluate their influence on query planner decisions. A quantitative experimental approach was employed using the TPC-H benchmark dataset at scale factors SF0.1, SF1, and SF10. Experiments were conducted using EXPLAIN ANALYZE on exact match, range, and join queries under three conditions: without indexing, with B-Tree indexing, and with Hash indexing. The results demonstrate that indexing significantly improves query performance. For exact match queries on the SF10 dataset, execution time decreased from 93.36 ms without indexing to 0.034 ms using B-Tree and 0.045 ms using Hash indexes. For join queries, execution time was reduced from 857.77 ms to 0.180 ms using B-Tree and 0.079 ms using Hash indexes. B-Tree showed consistent performance across different query types, while Hash achieved the best results for equality-based queries. Furthermore, index usage influenced query planner decisions in selecting more efficient execution strategies. These findings indicate that appropriate index selection can substantially improve data access efficiency in PostgreSQL.
Keywords: b-tree index; hash index; PostgreSQL; query optimization; query planner
Abstrak: Performa query merupakan faktor penting dalam pengelolaan basis data berskala besar. Salah satu teknik optimasi yang umum digunakan adalah indexing. Penelitian ini bertujuan menganalisis pengaruh penggunaan indexing terhadap performa query pada PostgreSQL, membandingkan efektivitas B-Tree dan Hash index, serta mengevaluasi pengaruhnya terhadap keputusan query planner. Penelitian menggunakan metode eksperimen kuantitatif dengan dataset benchmark TPC-H pada skala SF0.1, SF1, dan SF10. Pengujian dilakukan menggunakan EXPLAIN ANALYZE pada exact match query, range query, dan join query dalam kondisi tanpa index, menggunakan B-Tree index, dan Hash index. Hasil penelitian menunjukkan bahwa indexing meningkatkan performa query secara signifikan. Pada exact match query dataset SF10, execution time menurun dari 93,36 ms tanpa index menjadi 0,034 ms menggunakan B-Tree dan 0,045 ms menggunakan Hash index. Pada join query, execution time berkurang dari 857,77 ms menjadi 0,180 ms menggunakan B-Tree dan 0,079 ms menggunakan Hash index. B-Tree menunjukkan performa yang konsisten pada berbagai jenis query, sedangkan Hash index memberikan performa terbaik pada query berbasis equality. Selain itu, penggunaan index memengaruhi keputusan query planner dalam memilih strategi eksekusi yang lebih efisien. Hasil penelitian menunjukkan bahwa pemilihan metode indexing yang tepat dapat meningkatkan efisiensi akses data pada PostgreSQL
Kata kunci: b-tree index; hash index; optimasi query; PostgreSQL; query planner
Abstract:Abstract: Existing IoT anomaly detection studies have achieved high classification performance, but most focus on accuracy and F1-score without explicitly controlling the false positive rate (FPR). In addition, many approaches…
oaches rely on a single detection perspective, limiting their operational reliability. To address this gap, this study proposes a hybrid anomaly detection framework integrating Long Short-Term Memory (LSTM), Shannon entropy, and autoencoder reconstruction error. Shannon entropy is incorporated as an additional feature, while LSTM and the autoencoder capture temporal and reconstruction characteristics. The resulting hybrid representation is processed by a constraint-based threshold selection mechanism that enforces FPR . Experiments on the TON-IoT and Edge-IIoTset datasets achieved average F1-scores of 0.9250 and 0.9934, while maintaining average FPR values of 0.0091 and 0.0714, respectively. Analysis of entropy distributions showed consistent differences between normal and anomalous traffic across both datasets, indicating that Shannon entropy provides discriminative information for anomaly detection. These results demonstrate strong detection performance with controlled false alarms, while ablation studies confirm the significant contribution of Shannon entropy to overall model performance.
Keywords: false positive rate; hybrid deep learning; Internet of Things; network anomaly detection; Shannon entropy
Abstrak: Penelitian deteksi anomali Internet of Things (IoT) telah menunjukkan performa klasifikasi yang tinggi, namun sebagian besar masih berfokus pada accuracy dan F1-score tanpa mengendalikan false positive rate (FPR) secara eksplisit. Selain itu, banyak pendekatan hanya memanfaatkan satu perspektif deteksi sehingga reliabilitas operasionalnya masih terbatas. Untuk mengatasi kesenjangan tersebut, penelitian ini mengusulkan kerangka deteksi anomali hybrid yang mengintegrasikan Long Short-Term Memory (LSTM), Shannon entropy, dan autoencoder reconstruction error. Shannon entropy digunakan sebagai fitur tambahan, sedangkan LSTM dan autoencoder menangkap karakteristik temporal dan deviasi rekonstruksi. Representasi hybrid yang dihasilkan kemudian diproses melalui mekanisme constraint-based threshold selection dengan batas FPR . Hasil pengujian pada dataset TON-IoT dan Edge-IIoTset menghasilkan F1-score rata-rata sebesar 0,9250 dan 0,9934, dengan FPR rata-rata sebesar 0,0091 dan 0,0714. Perbedaan nilai entropy yang konsisten antara trafik normal dan anomali pada kedua dataset menunjukkan bahwa Shannon entropy menyediakan informasi diskriminatif untuk deteksi anomali. Hasil tersebut menunjukkan performa deteksi yang kuat dengan false alarm yang terkendali, sementara studi ablasi mengonfirmasi kontribusi signifikan Shannon entropy terhadap performa model.
Kata kunci: deteksi anomali jaringan; false positive rate; hybrid deep learning; Internet of Things; Shannon entropy
Abstract:Abstract: Manual meeting documentation risks losing important information due to cognitive fatigue. Although automated summarization models have evolved, integrated end-to-end systems for Indonesian spoken language remain…
n highly limited. This study aims to design and evaluate an end-to-end automated meeting summarization architecture that directly integrates Automatic Speech Recognition (ASR) via OpenAI Whisper for transcription and the IndoT5 language model for abstractive summarization. IndoT5 was fine-tuned using a dataset of 486 Indonesian spoken language transcript pairs. Testing was conducted on a CPU infrastructure using MP4, MP3, and WAV formats. Results show the optimal fine-tuning configuration significantly improved accuracy, achieving ROUGE-1 (0.4167), ROUGE-2 (0.1973), and ROUGE-L (0.2701) scores. Computationally, the system achieved a Real-Time Factor below 1, processing data faster than the actual recording duration. Conclusively, integrating Whisper and IndoT5 shows potential in producing coherent meeting summaries with lightweight computational overhead, making it viable for local infrastructure implementation to ensure data privacy.
Keywords: abstractive summarization; ASR; end-to-end pipeline; IndoT5; real-time factor
Abstrak: Dokumentasi rapat manual rentan menghilangkan informasi penting akibat keterbatasan kognitif. Meskipun model peringkas otomatis telah berkembang, implementasi sistem terintegrasi (end-to-end) khusus percakapan lisan berbahasa Indonesia masih sangat terbatas. Penelitian ini bertujuan merancang dan mengevaluasi arsitektur peringkas rapat otomatis end-to-end yang mengintegrasikan langsung Automatic Speech Recognition (ASR) melalui OpenAI Whisper untuk transkripsi dan model bahasa IndoT5 untuk peringkasan abstraktif. Adaptasi domain dilakukan melalui fine-tuning IndoT5 menggunakan 486 pasang dataset transkrip lisan berbahasa Indonesia. Pengujian pada infrastruktur CPU menggunakan format MP4, MP3, dan WAV. Hasil pengujian menunjukkan konfigurasi fine-tuning optimal berhasil meningkatkan akurasi, dengan skor ROUGE-1 (0,4167), ROUGE-2 (0,1973), dan ROUGE-L (0,2701). Sistem mendemonstrasikan efisiensi komputasi dengan nilai Real-Time Factor di bawah 1, mengindikasikan waktu pemrosesan lebih cepat dari durasi rekaman asli. Kesimpulannya, integrasi Whisper dan IndoT5 menunjukkan potensi dalam menghasilkan ringkasan yang koheren dengan beban komputasi ringan, sehingga layak diimplementasikan pada infrastruktur lokal organisasi untuk menjaga privasi data.
Kata kunci: ASR; end-to-end pipeline; IndoT5; peringkasan abstraktif; real-time factor