ITB Journal
Not a member yet
5999 research outputs found
Sort by
Penyesuaian Konsep Identitas Sosial pada Korpus Ujaran Kebencian, Pendekatan Komputasional Linguistik
Full text linkThe identification of hate speech must be accompanied by the identification of social identity concepts. This study aims to provide an alternative corpus with text metadata and social identity based on relevant laws that are designed to be implemented in machine learning. Two key questions are addressed: what social identity semantic domains are realized in the corpus, and what are the accuracy measurement results from the corpus? To achieve these aims, the study adopts a mixed-methods approach: qualitative for the first question and quantitative for the second. This research falls under the broader umbrella of computational linguistics, utilizing semantic domain theory and natural language processing. The first approach shows that the corpus only contributes five out of nine formulated domains, dominated by negative (uncategorized), religion, and ethnicity. The second approach indicates suboptimal conditions in the annotation distribution of the corpus, despite an average accuracy rate of over 80%. This condition limits the model’s ability to generalize beyond the information within the corpus, especially regarding social identity categories that are not fully represented. This study differs from previous ones by focusing on data categorization based on more up-to-date legal sources. Future research could elaborate on this work by incorporating new language use concepts aligned with the corpus's original goal to detect hate speech.Identifikasi ujaran kebencian harus dibarengi dengan identifikasi konsep identitas sosial. Penelitian ini berupaya memberikan korpus alternatif dengan metadata teks dan identitas sosial berdasarkan hukum terkait. Untuk itu terdapat dua pertanyaan yang perlu di jawab, yaitu apa saja domain semantik identitas sosial yang terealisasi dalam korpus serta bagaimana hasil pengujian dari korpus tersebut. Dengan tujuan tersebut, penelitian ini mengadopsi metode penelitian campuran, yaitu kualitatif untuk pertanyaan pertama dan kuantitatif untuk pertanyaan kedua. Payung besar penelitian ini adalah Linguistik Komputasional yang memanfaatkan teori Domain Semantik dan perhitungan algoritma pembelajaran mesin. Teori tersebut digunakan untuk memproses data korpus ujaran kebencian sebagai luaran dari penelitian sebelumnya yang tersedia secara open-source. Hasil analisis memproyeksikan adanya kondisi yang kurang layak dari segi distribusi anotasi pada korpus, walaupun luaran pengujian akurasi memunculkan angka rata-rata di atas 80%. Kondisi ini mengakibatkan model mesin memiliki kemampuan terbatas hanya pada informasi di dalam korpus saja, sedangkan terdapat kategori identitas sosial yang pengetahuannya tidak termuat dalam korpus. Penelitian ini membedakan dengan penelitian sebelumnya dengan berfokus pada kategorisasi data berdasarkan sumber hukum terkait yang lebih mutakhir. Luaran penelitian dapat dilanjutkan dengan penambahan konsep penggunaan bahasa baru yang sesuai dengan tujuan awal korpus, yaitu mendeteksi ujaran kebencia
Palu City MSME Strategy to Face Data Leakage Risks and Digital Transformation Safely and Efficiently
No full textThe gap in digital technology adoption for operational purposes poses a significant barrier to the growth of MSMEs, particularly in Palu City. According to data from the central statistics agency or BPS-Statistics Indonesia of Central Sulawesi (2022/2023), only 13.42% of MSMEs utilize digital technology in their business activities. This study aims to identify the main obstacles in the digital transformation process of MSMEs by integrating the diffusion of innovation (DOI) theory and the technology acceptance model (TAM), as well as Islamic values and local cultural perspectives. Employing a qualitative case study approach, data sources include in-depth interviews with MSME actors in Palu City and related official documents. The data were analyzed using thematic analysis. The findings indicate that technological complexity, limited availability of skilled personnel, low digital literacy, and concerns about data breaches are the primary inhibiting factors. Local traditions such as nogae (cooperation) and cross-sector collaboration are identified as potential accelerators for promoting inclusive digital technology adoption. This study contributes theoretically by integrating sociocultural approaches into technology adoption models and by advocating for sustainable digital education strategies and collaborative cross-sector policies. The findings provide a foundation for formulating adaptive digital transformation strategies for MSMEs tailored to the local context.Studi ini meneliti tantangan MSM di Kota Palu dalam mengadopsi teknologi digital, terutama mengenai risiko seperti kebocoran data dan serangan dunia maya. Ini mengidentifikasi kesenjangan dalam mengadopsi teknologi digital untuk tujuan operasional dan mengeksplorasi solusi untuk mempercepat transformasi digital yang aman dan efisien. Menggunakan metode kualitatif dengan pendekatan studi kasus, penelitian ini mengumpulkan data melalui wawancara mendalam dengan aktor UMKM, dokumen resmi dari Biro Statistik Pusat (BPS), data dari Kantor Koperasi dan MSM, dan dokumen terkait. Analisis tematik digunakan untuk mengungkap pola dan tema dalam data. Temuan menunjukkan bahwa hanya sejumlah kecil MSM di Kota Palu mengadopsi dan secara strategis menggunakan teknologi digital. Hambatan utama termasuk kompleksitas teknologi, kurangnya profesional yang terampil, akses terbatas ke modal, dan kekhawatiran tentang keamanan data. Namun, nilai -nilai budaya lokal, seperti tradisi "nogae" dalam masyarakat Kaili, dapat mendukung transformasi digital yang lebih inklusif dan berkelanjutan. Studi ini menyoroti perlunya program literasi digital yang berkelanjutan, meningkatkan kolaborasi lintas sektoral antara pemerintah, sektor swasta, dan lembaga keuangan, dan peningkatan infrastruktur digital untuk mengatasi tantangan ini secara efektif
A Vaccination and Isolation Strategy Based on an Adaptive Sliding Mode Control Design for the COVID-19 Virus (Omicron Variant) in Jakarta, Indonesia
Full text linkThe Omicron variant, identified as B.1.1.529, has been recognized as a variant of concern (VOC) by the World Health Organization (WHO), necessitating continuous monitoring and a proactive response. This study develops a mathematical model to analyze the spread of COVID-19 mutations, considering a population that, despite vaccination, remains susceptible to infection. The model also accounts for key epidemiological factors, including the incubation period, quarantine measures, and various intervention strategies. This study focuses on the epidemiological conditions in Jakarta Province, where the highest number of Omicron cases in Indonesia has been recorded. Real-world epidemiological data related to Omicron in Jakarta were collected between February 6, 2022, and May 6, 2022. Model parameters were estimated using genetic algorithm optimization. A significant challenge in epidemic modeling is the uncertainty of parameters, which can substantially affect the effectiveness of control measures. To address this challenge, an adaptive sliding mode control approach is introduced, allowing dynamic adjustments to parameter variations without requiring precise parameter estimation. This approach maintains system stability by enforcing a predefined sliding surface, making it inherently robust against uncertainties. The main goal of this approach is to gradually minimize infections attributed to the initial COVID-19 strain and the Omicron variant, while simultaneously decreasing the count of susceptible individuals by ensuring the system follows a specified reference trajectory. Additionally, an adaptive mechanism is implemented to account for unknown variations in the system using the Lyapunov stability theorem. Numerical simulations illustrate that adaptive sliding mode control significantly improves epidemic management, reducing infections by 92.8% for the original strain and by 96.87% for the Omicron variant when compared to an uncontrolled scenario. Furthermore, the basic reproduction number (R0) is lowered by 85.92%, confirming the efficiency of adaptive sliding mode control in mitigating the outbreak. Moreover, this study incorporates a cost-effectiveness analysis to assess the viability of various vaccination and isolation strategies. The findings contribute to epidemiological research by offering valuable insights for policymakers in designing effective and resilient intervention strategies for epidemic management
Studi Tentang Mental Imagery: Pengaruh Mental Imagery Terhadap Performa Olahraga dan Pemulihan Cedera Pada Atlet Menggunakan Analisis Bibliometrik
No full textThis study aims to examine the impact of mental imagery on sports performance and injury recovery in athletes through bibliometric analysis. The study utilizes data from the Scopus database to analyze the annual publication trends, most cited articles, prolific journals, frequently occurring keywords, and emerging research trends related to mental imagery. A total of 131 articles published between 1977 and 2024 were analyzed using VOSviewer, RStudio, and Scopus to visualize the data. The findings of this study indicate that mental imagery has a significant effect on enhancing athletic performance, both through the improvement of motor skills and injury recovery. The results provide new insights into research trends, gaps, and the future direction of mental imagery studies in sports, serving as a valuable reference for further research.
Keywords: mental imagery, sports performance, injury recovery, athletes, bibliometric analysis.Penelitian ini bertujuan untuk meninjau pengaruh mental imagery terhadap performa olahraga dan pemulihan cedera pada atlet melalui analisis bibliometrik. Studi ini menggunakan data dari basis Scopus untuk menganalisis perkembangan publikasi tahunan, artikel yang paling banyak dikutip, jurnal produktif, kata kunci yang sering muncul, serta tren penelitian yang sedang dieksplorasi terkait mental imagery. Sebanyak 131 artikel yang diterbitkan dalam rentang waktu 1977 hingga 2024 dianalisis menggunakan perangkat VOSviewer, RStudio, dan Scopus untuk memvisualisasikan data. Hasil temuan penelitian ini menunjukkan bahwa mental imagery memiliki pengaruh signifikan terhadap peningkatan performa atlet, baik melalui peningkatan keterampilan motorik maupun pemulihan cedera. Hasil penelitian ini memberikan wawasan baru mengenai tren, kesenjangan penelitian, serta arah pengembangan studi mental imagery dalam konteks olahraga, yang dapat menjadi referensi bagi penelitian lanjutan di masa depan
CUSTOM, IMMIGRATION AND QUARANTINE (CIQ) DALAM MENDUKUNG PENYELENGGARAAN EVENT WISATA BISNIS/MICE DI INDONESIA: Tinjauan terhadap Tindakan Karantina Tumbuhan untuk Kebutuhan Pameran
Full text linkThe Business Tourism Industry or better known as MICE (Meeting, Incentive, Convention and Exhibition) is considered significant in driving the national economy. According to data from the Indonesian Ministry of Tourism and Creative Economy in 2023, the contribution of the MICE sector to the national tourism industry is around 30 (thirty) percent. Not only developing in organizing international meetings/conferences such as the G20 Summit or ASEAN SUMMIT, the organization of international exhibitions in Indonesia is also growing significantly. Government support for increasing the organization of international exhibitions is given in the form of policies that encourage the smooth implementation of exhibition activities, one of which is the policy related to CIQ (Custom, Immigration and Quarantine) which can make it easier for tourists/goods/animals/exhibition plants to enter and leave Indonesia. This study will focus on analyzing plant quarantine measures in organizing exhibition activities where the purpose of these plants is as exhibition goods/participated as participants/exhibitors in plant exhibitions. Sending plants from abroad into Indonesia for exhibition purposes requires specific and detailed procedures administratively and technically operationally. The methods used in this study are observation, interviews and literature studies. The output of this study is a systematic and comprehensive description of quarantine procedures and actions on plants intended for exhibition purposes.Industri Pariwisata Bisnis atau lebih dikenal dengan sebutan MICE (Meeting, Incentive, Convention and Exhibition) dinilai signifikan dalam menggerakkan perekonomian nasional. Menurut data dari Kemenparekraf RI pada tahun 2023, kontribusi sektor MICE terhadap industri pariwisata nasional ada di angka kurang lebih 30 (tiga puluh) persen. Tidak hanya berkembang pada penyelenggaraan pertemuan internasional/ konferensi seperti KTT G20 atau ASEAN SUMMIT, penyelenggaraan pameran internasional di Indonesia juga berkembang signifikan. Dukungan pemerintah terhadap peningkatan penyelenggaraan pameran internasional diberikan dalam bentuk kebijakan-kebijakan yang mendorong kelancaran penyelenggaraan kegiatan pameran, salah satunya adalah kebijakan yang terkait dengan CIQ (Custom, Immigration, dan Quarantine) yang dapat mempermudah wisatawan/barang/hewan/tumbuhan pameran untuk dapat masuk dan keluar wilayah Indonesia. Penelitian ini akan berfokus menganalisis tindakan karantina tumbuhan dalam penyelenggaraan kegiatan pameran, dimana tujuan peruntukan tumbuhan ini adalah sebagai barang pameran yang diikutsertakan sebagai peserta/exhibitor dalam pameran tumbuhan. Pengiriman tumbuhan dari luar negeri ke dalam wilayah Indonesia untuk keperluan pameran perlu melalui prosedur yang spesifik dan detail secara administratif dan teknis operasional. Metode yang digunakan dalam penelitian ini adalah observasi, wawancara, dan studi literatur. Luaran penelitian ini adalah gambaran sistematis dan komprehensif prosedur dan tindakan karantina pada tumbuhan yang diperuntukkan sebagai keperluan pameran
Enhancing Natural Language Inference Performance with Knowledge Graph for COVID-19 Automated Fact-Checking in Indonesian Language
Full text linkAutomated fact-checking is a key strategy to overcome the spread of COVID-19 misinformation on the internet. These systems typically leverage deep learning approaches through natural language inference (NLI) to verify the truthfulness of information based on supporting evidence. However, one challenge that arises in deep learning is performance stagnation due to a lack of knowledge during training. This study proposes using a knowledge graph (KG) as external knowledge to enhance NLI performance for automated COVID-19 fact-checking in the Indonesian language. The proposed model architecture comprises three modules: a fact module, an NLI module, and a classifier module. The fact module processes information from the KG, while the NLI module handles semantic relationships between the given premise and hypothesis. The representation vectors from both modules are concatenated and fed into the classifier module to produce the final result. The model was trained using the generated Indonesian COVID-19 fact-checking dataset and the COVID-19 KG Bahasa Indonesia. Our study demonstrates that incorporating KGs can significantly improve NLI performance in fact-checking, achieving a maximum accuracy of 0.8616. This suggests that KGs are a valuable component for enhancing NLI performance in automated fact-checking
Diachronic Morphological Study In Pontianak City As Waterfront City
Full text linkThis study presented a diachronic analysis of the morphological development of Pontianak City as a waterfront city. The diachronic time frame is based on several old maps, including those made in 1846, 1898, 1942, 1980, and 2020. The objective of this study was to determine the direction and patterns of waterfront city development in terms of road network patterns. Space syntax method was selected because this method analyzes urban morphology through a configuration model and produces spatial patterns in relation to the social character of the residents in the city. Integration analysis was performed to convey the tendency and probability of the next direction of development. The results showed that the direction of the development orientation of Pontianak City underwent some changes over periods, starting from river-oriented to land-oriented due to the construction of ditches and bridges. In fact, the development patterns of Pontianak City caused some urban problems, namely North Pontianak (Area C) became left behind and segregated from the city centre (Area A). Space syntax can predict the development of Pontianak City based on the socio-economic conditions of the community. However, political conditions and policies are unpredictable yet able to change the direction of the city’s development to be guided
Kajian Eksperimental Peningkatan Kinerja Kuat Lentur Sambungan Ordinary dan Extended End Plate
No full textAbstrak
Sambungan pelat ujung (end plate connection) adalah sambungan semi kaku yang secara umum digunakan untuk menghubungkan balok-kolom. Salah satu alternatif untuk meningkatkan kapasitas lentur sambungan adalah memperluas area sambungan pelat ujung. Namun, upaya yang dilakukan tersebut butuh dievaluasi lebih lanjut. Penelitian ini bertujuan untuk menginvestigasi kuat lentur sambungan pelat ujung dengan memberikan beberapa perkuatan yaitu penambahan area sambungan, pemasangan pengaku pelat badan, dan perpanjangan penyokong di area bawah balok. Untuk mengevaluasi signifikansi perkuatan, benda uji tanpa perkuatan (ordinary end plate connection) digunakan sebagai acuan. Penelitian dilakukan melalui pemberian beban geser yang ditempatkan pada 400 mm dari sambungan dan beban ditingkatkan secara bertahap hingga benda uji gagal. Kajian eksperimental menunjukkan benda uji dengan kombinasi perkuatan berupa penambahan area sambungan dan penambahan pengaku badan memberikan kuat geser dan lentur yang paling baik. Kajian teoritis mengacu ke SNI 03-1729-2020 menunjukkan kuat lentur nominal lebih kecil dibandingkan kuat lentur eksperimental. Hal ini menunjukkan kajian teoritis memberikan kuat lentur lebih konservatif.
Kata-kata Kunci: Sambungan pelat ujung, sambungan ordinary end plate, sambungan extended end plate, kuat lentur, kuat geser, deformasi
Abstract
An end plate connection is a semi-rigid connection used to connect a beam to a column. One alternative to improve the flexural strength is to enlarge the end plate connection area. However, this strengthening approach needs to be more specifically investigated. This study aims to evaluate the flexural strength of the connections by several strengthening methods: enlarging the connection area, installing web stiffeners, and lengthening the haunch at the bottom side of the beam. To examine the significance of strengthening approaches, an un-strengthened specimen (ordinary end plate connection) was considered as the reference. The research work was first carried out by positioning the shear load at a distance of 400 mm from the connection area, and it was gradually increased until the specimens failed. The experimental study also revealed that the specimen strengthened by combining an enlarged connection area and web stiffeners performed the best in terms of shear and flexural strength. The theoretical study referring to the SNI 03-1729-2020 demonstrated the nominal flexural strength, which is smaller than the experimental flexural strength. This behavior showed that the theoretical study provided more conservative flexural strength.
Keywords: End plate connection, ordinary end plate connection, extended end plate connection, flexural strength, shear strength, deformationSambungan pelat ujung (end plate connection) adalah sambungan semi kaku yang secara umum digunakan untuk menghubungkan balok-kolom. Dalam upaya peningkatan kuat lentur sambungan pelat ujung, salah satu alternatif adalah memperluas area sambungan pelat ujung. Namun, upaya yang dilakukan tersebut belum menghasilkan kuat lentur yang optimal. Penelitian ini bertujuan untuk meningkatkan kuat lentur sambungan pelat ujung dengan memberikan beberapa perkuatan yaitu penambahan area sambungan, pemasangan pengaku pelat badan, dan perpanjangan penyokong di area bawah balok. Untuk memverifikasi signifikansi perkuatan, benda uji tanpa perkuatan (ordinary end plate connection) digunakan sebagai acuan. Penelitian dilakukan melalui pemberian beban geser yang ditempatkan pada 400 mm dari sambungan dan beban ditingkatkan secara bertahap hingga benda uji gagal. Kajian eksperimental menunjukkan benda uji dengan kombinasi perkuatan berupa penambahan area sambungan dan penambahan pengaku badan memberikan kuat geser dan lentur yang paling baik. Selain itu, benda uji dengan perkuatan memiliki deformasi yang lebih kecil. Kajian teoritis mengacu ke SNI 03-1729-2020 menunjukkan kuat lentur nominal lebih kecil dibandingkan kuat lentur eksperimental. Hal ini menunjukkan kajian teoritis memberilan kuat lentur lebih konservatif
Mathematical Modelling of Carbon Dioxide Emissions in Agricultural Systems
Full text linkThis study formulates a dynamic mathematical model to investigate the interplay between human activities and CO2 emissions within the context of agriculture. The model incorporates a system of differential equations describing the interactions among human population growth (H1), human economic activities (H2), atmospheric CO2 concentration (H3), forest biomass density (H4), and vehicle population (H5). Key processes include the effects of deforestation, economic activities, and vehicle emissions on CO2 levels, as well as the mitigating role of forest biomass.The model parameters account for natural growth rates, carrying capacities, and interaction coefficients that represent both the exacerbation and alleviation of CO2 emissions. The delay parameter τ captures the temporal lag in the effects of population growth and deforestation. This framework aims to provide insights into the dynamic interactions and feedback loops influencing CO2 emissions, with a particular emphasis on sustainable practices and policies to mitigate environmental degradation in agricultural contexts
The Understanding Visual Language in Palestine-Israel conflict humanitarian Crowdfunding Campaigns:: The Role of Machine Learning (AWS Rekognition)
No full textIndonesia is widely acknowledged for its significant generosity globally, rooted deeply in cultural inclinations towards charitable activities and donations. This study explores the role of visual language in humanitarian crowdfunding campaigns, focusing on the Palestine-Israel conflict, and highlights the pivotal role of machine learning, specifically AWS Rekognition and Digital Content Analysis, in enhancing these campaigns. It categorizes campaign images into classifications such as superior fundraising activities, success levels, and degrees of poverty porn, leveraging demographic factors and thematic content to enhance campaign effectiveness. The study emphasizes how machine learning facilitates strategic deployment of visual elements—such as optimized shot composition, scale variations, and naturalistic portrayals—to ethically enhance viewer empathy and perception. Insights aim to deepen understanding of machine learning’s crucial role in shaping donor behavior and campaign success, proposing future directions in refining algorithms and ethical guidelines for impactful visual representation in humanitarian contexts.
Keywords: Visual Language, Humanitarian Fundraising, AWS Rekognition, Poverty Porn, Digital content Analysist.
Indonesia dikenal luas atas kedermawanannya yang signifikan secara global, yang berakar kuat pada kecenderungan budaya terhadap kegiatan amal dan donasi. Studi ini mengeksplorasi peran bahasa visual dalam kampanye urun dana kemanusiaan, dengan fokus pada konflik Palestina-Israel, dan menyoroti peran penting pembelajaran mesin, khususnya AWS Rekognition dan Analisis Konten Digital, dalam meningkatkan kampanye ini. Penelitian ini mengkategorikan gambar kampanye ke dalam klasifikasi seperti aktivitas penggalangan dana yang unggul, tingkat keberhasilan, dan tingkat pornografi kemiskinan, dengan memanfaatkan faktor demografis dan konten tematik untuk meningkatkan efektivitas kampanye. Studi ini menekankan bagaimana pembelajaran mesin memfasilitasi penyebaran strategis elemen visual-seperti komposisi pengambilan gambar yang dioptimalkan, variasi skala, dan penggambaran naturalistik-untuk secara etis meningkatkan empati dan persepsi pemirsa. Wawasan bertujuan untuk memperdalam pemahaman tentang peran penting pembelajaran mesin dalam membentuk perilaku donor dan keberhasilan kampanye, mengusulkan arah masa depan dalam menyempurnakan algoritme dan pedoman etika untuk representasi visual yang berdampak dalam konteks kemanusiaan.
Kata kunci: Bahasa Visual, Penggalangan Dana Kemanusiaan, AWS Rekognition, Pornografi Kemiskinan, Analisis Konten Digita