Abstract:The increased integration of operational technology (OT), Internet of Things (IoT), and business IT systems has allowed sophisticated attackers to circumvent isolated security features and launch cross-platform assaults.…
Current fragmented techniques, with discrete detectors monitoring Modbus, Kubernetes, MQTT, or other domain-specific protocols, cannot handle cross-system risks. These methodologies overlook 68% of multi-vector marketing that uses both physical and digital channels. This study introduces a transfer learning architecture to integrate detection capabilities by correlating threats across protocols, devices, and settings. The architecture generates a unified feature space that extracts behavioral semantics from industrial control system logs, cloud telemetry, network traffic, and device-level signals to produce protocol-agnostic threat representations. Adversarial domain adaptation and semantic graph embeddings enable cross-domain knowledge transfer with minimum retraining. Security teams may now discover kill chains like infected cloud containers preceding illegal PLC command execution every 23 minutes. Validated against real-world attack datasets from water treatment facilities (OT) and cloud infrastructure (IT), the system achieved 93.4% cross-platform attack recall, a 41.3 percentage point improvement over prior methodologies. It reduced OT data labeling by 89% and false positives by 93.5%. This paradigm shift transforms threat correlation from a reactive, domain-specific process to adaptive intelligence, boosting resilience for critical infrastructure, industrial ecosystems, and smart environments facing cyber-physical hazards. The framework's practical validation in energy, industry, and vital infrastructure shows its importance in protecting an increasingly linked world.
Abstract:Inflation is a fundamental measure of macroeconomic stability that negatively impacts the nation's economy and affects many other macroeconomic variables. Thus, in this study, the major objective was based on modeling and…
d forecasting inflation in Ethiopia and its components using a VAR model. The analysis was based on annual data from 1992 to 2021, encompassing 30 years. The results indicated that all five series were non-stationary at the level but stationary after their first differencing at a 5% level of significance. Johansen's cointegration tests were conducted. The results indicated the presence of at least one co-integration relationship between the variables. The Vector Error Correction Model (VECM) was fitted to model short run and long run relationships among inflation and other macro-econometric series such as GDP growth, government expenditure, money supply, and imports, and the result indicated that the coefficient of error correction term is negative (-0.279), which indicated that the fitted VECM model continues to move toward long run equilibrium and converges. Granger causality tests were employed to explore potential causal relationships. Impulse response analysis and variance decomposition were used to determine the short-run interactions among the variables. Finally, using the fitted model, out-of-sample forecasts were produced, yielding forecasted plots and values for the endogenous variables. According to the forecasted inflation rates for the next five years, prices are projected to decrease by approximately 18.0% in 2022, 6.8% in 2023, and then increase by approximately 8.3% in 2024. Subsequently, prices are expected to decrease by approximately 2% in 2025 and 5% in 2026 over the specified time periods.
Abstract:The purpose of this study is to analyze the effect of the Federal Funds Rate before and during the Covid-19 pandemic on economic stability in five developing countries in the Southeast Asian region which are members of an…
n economic and geopolitical organization, namely the Association of Southeast Nations (ASEAN) to see short-term relationships. and long-term during that period. The indicators of economic stability used are the benchmark interest rate for deposits, the reference interest rate for loans, the balance of payments which includes exports and imports, inflation, exchange rates, and the money supply. In this study, the method used was the quantitative method and the data obtained was secondary data sourced from International Financial Statistics (IFS) from January 2015 to December 2022 which used the Vector Error Correction Model (VECM) approach in the Eviews 9 application. The results found indicated that in the long run, the existence of FFR volatility has a positive effect on the Deposit and Export Reference Rates. While those that have a negative effect are Loan Reference Rates, Imports, Exchange Rate Inflation, and Money Supply. In the short term, the existence of the FFR interest rate has a positive effect on the Reference Rates for Deposits, Imports, and Inflation. While those that have a negative effect are Loan Reference Rates, Exports, Exchange Rates, and Money Supply
Abstract:Penggunaan dompet digital yang terus meningkat menghasilkan banyak ulasan pengguna yang dapat dimanfaatkan untuk mengevaluasi kualitas layanan. Penelitian ini bertujuan meningkatkan akurasi klasifikasi sentimen pengguna…
dompet digital menggunakan metode Stacking Ensemble Machine Learning yang mengombinasikan Support Vector Machine (SVM), Multinomial Naïve Bayes (MNB), dan AdaBoost dengan Logistic Regression sebagai meta-learner. Data ulasan diproses melalui tahapan text preprocessing meliputi case folding, cleaning, tokenizing, stopword removal, stemming, dan pembobotan fitur menggunakan TF-IDF. Penyeimbangan data dilakukan dengan SMOTE, sedangkan evaluasi model menggunakan 5-Fold Cross-Validation. Hasil penelitian menunjukkan bahwa model Stacking Ensemble memperoleh akurasi rata-rata 80,55%, lebih tinggi dibandingkan algoritma dasar. Evaluasi menggunakan Confusion Matrix, Classification Report, dan ROC Curve juga menunjukkan peningkatan nilai precision, recall, F1-score, dan kemampuan diskriminasi model. Hasil ini menunjukkan bahwa pendekatan Stacking Ensemble Machine Learning efektif untuk meningkatkan akurasi klasifikasi sentimen pengguna dompet digital serta mendukung evaluasi kualitas layanan berbasis opini pengguna.
The rapid growth of digital wallet usage has generated a large volume of user reviews that can be utilized to evaluate service quality. This study aims to improve the accuracy of digital wallet user sentiment classification using a Stacking Ensemble Machine Learning approach that combines Support Vector Machine (SVM), Multinomial Naïve Bayes (MNB), and AdaBoost with Logistic Regression as the meta-learner. User reviews were processed through text preprocessing stages, including case folding, text cleaning, tokenization, stopword removal, stemming, and TF-IDF feature weighting. Synthetic Minority Over-sampling Technique (SMOTE) was employed to address class imbalance, while model performance was evaluated using 5-Fold Cross-Validation. The experimental results show that the proposed Stacking Ensemble model achieved an average accuracy of 80.55%, outperforming the individual base learners. Furthermore, evaluations based on the Confusion Matrix, Classification Report, and Receiver Operating Characteristic (ROC) Curve demonstrated improvements in precision, recall, F1-score, and the model's discriminative capability. These findings indicate that the proposed Stacking Ensemble Machine Learning approach is effective in improving the accuracy of digital wallet user sentiment classification and can serve as a reliable tool for supporting service quality evaluation based on user opinions.
Abstract:This socialization activity aimed to introduce the use of CorelDRAW as a graphic editing tool among university students. CorelDRAW was chosen because it is easy to use, flexible, and supports various design needs such as…
logo creation, posters, flyers, and visual illustrations. The activity was conducted using a descriptive qualitative approach with a participatory method, where students not only received material but also practiced directly. The program involved 12 students and took place at Universitas Pangeran Antasari. The results showed that most participants understood the material well, particularly in recognizing the interface and basic vector drawing techniques. This activity proved to be helpful in improving students' communicative visual design skills to support both academic and organizational purposes.
Abstract:This research is a quasi-experimental study conducted to improve students' mathematical problem-solving abilities, one of which is through the use of the Self-Directed Learning (SDL) instructional model. The objectives of…
f this study are to determine (a) the learning process using the Self-Directed Learning model; (b) the difference in improvement of students' mathematical problem-solving abilities between those using the Self-Directed Learning model and those receiving conventional (expository) instruction; and (c) students' attitudes toward mathematics learning using the Self-Directed Learning model. Data were collected using research instruments including tests in the form of mathematical problem-solving ability questions and non-tests such as student response questionnaires toward learning using the Self-Directed Learning model. This study was conducted at MAN 1 Gorontalo, with class X IPA-1 as the experimental class and class X IPA-2 as the control class, focusing on vector material. Based on the research results and n-gain data analysis, it was found that: (a) the description of the teacher and student learning process on quadrilateral vector material using the Self-Directed Learning model falls into the good category; (b) the improvement in mathematical problem-solving ability of students who received learning with the Self-Directed Learning model showed a moderate increase. Meanwhile, the improvement in mathematical problem-solving ability of students who received conventional learning showed a low increase. Therefore, there is a difference in the improvement of mathematical problem-solving ability between students using the Self-Directed Learning model and those using conventional learning; (c) most students who received learning using the Self-Directed Learning model responded positively to mathematics learning using this model.
Abstract:Tujuan penelitian ini adalah untuk mengetahui cara menganalisis sentimen dari ulasan pengguna pada game Roblox dan untuk mengetahui hasil perbandingan performa klasifikasi dengan menggunakan metode Support Vector Machine…
Dan Naive Bayes dalam menganalisis sentimen ulasan pengguna pada game Roblox. Data yang digunakan pada penelitian ini berjumlah sebanyak 10000 record data ulasan yang di ambil pada tanggal 15 Juni 2024. Hasil yang di peroleh dalam menganalisis sentimen data ulasan pada aplikasi Roblox cenderung mendapatkan sentimen positif dengan persentase 65,06% sedangkan untuk sentimen negatif dengan persentase 34,94%. Support Vector Machine merupakan algoritma terbaik dalam menganalisis sentimen data ulasan pada aplikasi Roblox dengan tingkat akurasi yang paling tinggi pada perbandingan data 90:10 yaitu 90 %, untuk precision, recall, dan f1-score yang dihasilkan pada sentimen positif yaitu 88%, 85%, dan 86%, sedangkan pada sentimen negatif adalah 91%, 93%, dan 92%. Algoritma Naïve Bayes mendapatkan tingkat akurasi yang paling tinggi pada perbandingan data 90:10 yaitu 72,4%, untuk precision, recall, dan f1-score yang dihasilkan pada sentimen positif yaitu 88%, 34%, dan 49%, sedangkan pada sentimen negatif adalah 70%, 97%, dan 81%.
Abstract:In order to increase community participation in preventing the spread of mosquito-borne diseases, education for the community needs to be carried out through counseling. Tanggamus Regency is one of the areas in Lampung where…
here DHF occurred, where from January to June 2024 there were 227 cases. To increase public knowledge in Banjar Agung Udik Village, Pugung District, Tanggamus Regency regarding phytotelmata as a breeding ground for mosquitoes, this counseling was carried out. Counseling was carried out using the pretest, lecture and discussion methods, and practicum. The results of the counseling showed that most participants knew that DBD and malaria were transmitted by mosquitoes, but not all knew the name of the vector species. Participants knew where mosquitoes perched at home and how to avoid mosquito bites. Participants also know mosquito breeding places, but are new to phytotelmata in this counseling. The practicum carried out by participants successfully identified six plant species that were proven to be phytotelmata. Thus, it can be concluded that this counseling has succeeded in providing knowledge to the community about the potential of phytotelmata as a source of mosquito-borne diseases.
Keywords: Phytotelmata; Mosquito Borne Diseases; Mosquito Breeding Places; Mosquitoes Bite.
Dalam rangka meningkatkan peran serta masyarakat dalam mencegah penyebaran penyakit tukar nyamuk itulah pendidikan kepada masyarakat perlu perlu dilakukan melalui penyuluhan. Kabupaten Tanggamus adalah salah satu daerah di Lampung yang kejadian DBD-nya dimana sejak Januari hingga Juni 2024 ada 227 kasus. Untuk meningkatkan pengetahuan masyarakat di Desa Banjar Agung Udik, Kecamatan Pugung, Kabupaten Tanggamus terhadap fitotelmata sebagai tempat perindukan nyamuk maka penyuluhan ini dilakukan. Penyuluhan dilakukan dengan metode pretes, ceramah dan diskusi, serta praktikum. Hasil penyuluhan didapatkan bahwa sebagian besar peserta tahu bahwa DBD dan malaria ditularkan nyamuk, tetapi tidak semua tahu nama spesies namuk vektornya. Peserta tahu tempat hinggap nyamuk di rumah dan juga tahu cara menghindarkan diri dari gigitan nyamuk. Peserta juga tahu tempat-tempat berkembang biak nyamuk, tetapi baru mengenal fitotelmata dalam penyuluhan ini. Praktikum yang dilakukan peserta berhasil mengidentifikasi enam spesies tumbuhan yang terbukti menjadi fitotelmata.Dengan demikian dapat disimpulkan bahwa penyuluhan ini berhasil memberkan pengetahuan kepada masyarakat tentang potensi fitotelmata sebagai sumber penyebar penyakit tular nyamuk.
Kata kunci: Fitotelmata; Penyakit Tular Nyamuk; Tempat Perindukan Nymauk; Gigitan Nyamuk.
Abstract:Program Pengabdian pada Masyarakat (PPM) yang dilaksanakan bertujuan untuk menerapkan multimedia sebagai media pembelajaran. Media pembelajaran yang dibuat adalah film animasi 2D Vector dengan latar cerita bencana alam di…
i Indonesia (tsunami, gunung merapi, dan longsor) dengan nilai-nilai islami di dalamnya. Pemutaran film animasi ini membuat anak-anak menjadi lebih mudah untuk memahami musibah dalam bentuk bencana alam seperti apa dan sikap bagaimana yang perlu diambil sebagai seorang muslim. Anak-anak pun termotivasi senantiasa mengingat doa yang sudah diajarkan di Tempat Pembelajaran Quran (TPQ). Doa-doa tersebut dapat mereka panjatkan ketika terkena musibah, Film animasi ini dibuat dengan tujuan agar anak-anak lebih mudah untuk ditanamkan sikap religius yang perlu diambil ketika mengalami musibah. Sehingga, anak-anak tidak berlarut-larut dalam kesedihan, tidak trauma berkepanjangan, dan dapat bangkit kembali untuk menata masa depan. Film animasi ini juga dapat digunakan oleh guru maupun orang tua untuk memberikan pelajaran untuk membangun sikap religius anak agar anak mampu mengatasi musibah. Peserta sosialisasi terdiri dari anak-anak usia 5 sampai 12 tahun atau dinamakan kelas cabe rawit dengan jumlah siswa sekitar 12 orang per kelas serta 2 guru untuk tiap kelas. Kegiatan sosialisasi diadakan di TPQ Nurul Huda Dumai. Setelah kegiatan diharapkan anak-anak dapat melihat unsur edukasi pembelajaran nilai islami yang ditanamkan pada media film animasi 2D vector yang diperlihatkan.
Kata kunci: animasi 2D vector, film, motion graphic
Abstract:Abstract: The rapid growth of e-commerce mobile applications has generated large volumes of user reviews, making manual sentiment analysis increasingly impractical. This study aims to compare the effectiveness of three machine…
achine learning algorithms Support Vector Machine (SVM), Random Forest, and Naive Bayes for automated sentiment classification of Indonesian-language mobile application reviews. A dataset of 3,000 user reviews from the RupaRupa application on the Google Play Store was collected and preprocessed through normalization, tokenization, stopword removal, and stemming. TF-IDF vectorization was applied for feature extraction, while the Synthetic Minority Over-sampling Technique (SMOTE) was used to address class imbalance across three sentiment categories: positive, negative, and neutral. The results show that SVM achieved the highest accuracy of 90.02%, while Random Forest obtained the best F1-score of 88.08% when sufficient training data were available. Naive Bayes demonstrated relatively stable performance across varying training data sizes. Furthermore, TF-IDF keyword analysis revealed that negative reviews were primarily associated with delivery issues, technical problems, and pricing concerns. These findings demonstrate the effectiveness of machine learning approaches for sentiment classification and provide practical insights for improving mobile application services.
Keywords: sentiment analysis; machine learning; SMOTE; TF-IDF; text classification
Abstrak: Pertumbuhan pesat aplikasi mobile e-commerce telah menghasilkan volume ulasan pengguna yang sangat besar, sehingga analisis sentimen secara manual menjadi semakin tidak praktis. Penelitian ini bertujuan untuk membandingkan efektivitas tiga algoritma machine learning Support Vector Machine (SVM), Random Forest, dan Naive Bayes dalam melakukan klasifikasi sentimen otomatis terhadap ulasan aplikasi mobile berbahasa Indonesia. Dataset yang digunakan terdiri dari 3.000 ulasan pengguna aplikasi RupaRupa yang dikumpulkan dari Google Play Store. Data kemudian diproses melalui tahapan preprocessing yang meliputi normalisasi, tokenisasi, penghapusan stopword, dan stemming. Ekstraksi fitur dilakukan menggunakan metode Term Frequency–Inverse Document Frequency (TF-IDF), sedangkan ketidakseimbangan kelas ditangani menggunakan Synthetic Minority Over-sampling Technique (SMOTE) pada tiga kategori sentimen, yaitu positif, negatif, dan netral. Hasil penelitian menunjukkan bahwa SVM mencapai tingkat akurasi tertinggi sebesar 90,02%, sementara Random Forest memperoleh nilai F1-score terbaik sebesar 88,08% ketika tersedia data pelatihan yang memadai. Naive Bayes menunjukkan performa yang relatif stabil pada berbagai ukuran data pelatihan. Selain itu, analisis kata kunci berbasis TF-IDF mengungkapkan bahwa ulasan negatif terutama berkaitan dengan masalah pengiriman, kendala teknis aplikasi, dan isu harga. Temuan ini menunjukkan bahwa pendekatan machine learning efektif untuk klasifikasi sentimen serta memberikan wawasan yang bermanfaat dalam meningkatkan kualitas layanan aplikasi mobile.
Kata Kunci: analisis sentimen; pembelajaran mesin; SMOTE; TF-IDF; klasifikasi teks.