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
Abstract:This study aimed to compare the performance of machine learning algorithms and user experience in predicting students’ academic achievement. The research is motivated by the need for prediction systems that are not only…
y highly accurate but also easily interpretable by users. The proposed methodology involved the implementation of two algorithms, namely Decision Tree and Random Forest, using an academic dataset that included grade point average, attendance, and assessment scores. Model performance was evaluated using accuracy, precision, recall, and F1-score, while user experience was assessed through the System Usability Scale (SUS) based on a simple user interface. The findings revealed that Random Forest achieved higher predictive accuracy, whereas Decision Tree provided better interpretability and ease of understanding for users. These results indicated a trade-off between model performance and user experience, suggesting that algorithm selection should consider both aspects in order to develop an effective and user-friendly academic prediction system
Abstract:Abstract: The development of information technology has begun to enter the world of education, especially universities, one of which is the academic information system because with this system it greatly influences the learning…
earning process and also in the delivery of information. A web-based academic information system is very adequate, but there are several obstacles such as in learning that does not require a laptop device, it will be very disruptive if the implementation of attendance and others is done on a mobile phone but with a web view. So this research aims to design a mobile-based UI/UX academic information system application with the hope that it can be an alternative in accessing the use of academic information systems for lecturers and students can also be accessed anytime and anywhere through mobile phones with a comfortable display. This study also tested the UI/UX design prototype to assess its feasibility. This test uses the system usability scale (SUS) method with a convident interval validation of 95% to determine the lower and upper limits of the SUS value. For the final score of SUS obtained was 78.75, and in the 95% CI test a Lower CI of 66.27 was produced, and for the Upper CI of 91.23 so that it was given a grade of B. It can be concluded that the design developed in this study is worthy of further development.
Keywords: academic information systems; design thinking; system usability scale
Abstrak: Perkembangan teknologi informasi sudah mulai masuk kedalam dunia pendidikan terutama perguruan tinggi, salah satunya sistem informasi akademik karena dengan adanya sistem ini sangat mempengarusi proses pembelajaran dan juga dalam penyampaian informasi. Sistem informasi akademik berbasis web sudah sangat memadai namun ada beberapa kendala seperti dalam pembelajaran yang tidak memerlukan perangkat laptop akan sangat menganggu jika pelaksanaan absensi dan lainya dilakukan pada ponsel tapi dengan tampilan web. Sehingga penelitian ini bertujuan untuk merancang UI/UX aplikasi sistem informasi akademik berbasis mobile dengan harapan dapat menjadi alternatif dalam akses penggunaan sistem informasi akademik bagi dosen dan mahasiswa juga dapat diakses kapan saja dan dimana saja melalui ponsel dengan tampilan yang nyaman. Penelitian ini juga melakukan pengujian terhadap prototype desain UI/UX untuk menilai kelayakannya. Pengujian ini menggunaka metode system usability scale (SUS) dengan validasi convident interval 95% untuk mengetahui batas bawah dan batas atas nilai SUS. Untuk nilai akhir SUS yang didapatkan adalah 78,75, dan dalam pengujian CI 95 % dihasilkan CI Lower 66,27, dan untuk CI Upper 91,23 Sehingga mendapat grade B. Dapat disumpulkan bahwa desain yang dikembangkan dalam penelitian ini layak untuk dikembangkan lebih lanjut.
Kata kunci: sistem informasi akademik; desain thinking; system usability scale
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.
Abstract:Abstract: Mental health issues, particularly depression among young adult university students, are often detected late due to stigma and reluctance to seek medical consultation. The objective of this study is to develop…
an early screening model employing machine learning techniques, specifically the random forest algorithm, on a dataset of 268 students (aged 17-29 years; consisting of 98 males and 170 females) within a multicultural educational setting. The principal challenges associated with this dataset are class imbalance and the potential for data leakage from clinical scores. This study implements a rigorous feature selection approach that involves the elimination of depression score features and the utilization of the Synthetic Minority Over-sampling Technique (SMOTE) to balance the training data distribution. Furthermore, a Threshold Tuning strategy is employed to prioritize detection sensitivity (Recall). The findings indicate that reducing the decision threshold to an optimal value of 0.25 led to a substantial enhancement in the recall value, increasing it from 36% (baseline) to 77%. A feature importance analysis was conducted, the results of which indicated that Total Social Connectedness (ToSC) is the most dominant predictor. In summary, the present study corroborates the notion that optimizing sensitivity through threshold tuning is of paramount importance for medical screening. Furthermore, social isolation factors emerge as more significant indicators of depression risk than demographic attributes.
Keywords: data mining; depression; imbalanced data; random forest; smote; threshold tuning
Abstrak: Masalah kesehatan mental, khususnya depresi di kalangan mahasiswa dewasa muda, sering terdeteksi terlambat akibat stigma dan enggan mencari konsultasi medis. Tujuan studi ini adalah mengembangkan model skrining dini menggunakan teknik machine learning, khususnya algoritma random forest, pada dataset 268 mahasiswa (usia 17-29 tahun; terdiri dari 98 laki-laki dan 170 perempuan) dalam lingkungan pendidikan multikultural. Tantangan utama yang terkait dengan dataset ini adalah ketidakseimbangan kelas dan potensi kebocoran data dari skor klinis. Studi ini menerapkan pendekatan seleksi fitur yang ketat, yang melibatkan eliminasi fitur skor depresi dan penggunaan Teknik Over-sampling Minoritas Sintetis (SMOTE) untuk menyeimbangkan distribusi data pelatihan. Selain itu, strategi Penyesuaian Ambang Batas diterapkan untuk memprioritaskan sensitivitas deteksi (Recall). Hasil penelitian menunjukkan bahwa mengurangi ambang batas keputusan ke nilai optimal 0,25 menyebabkan peningkatan signifikan dalam nilai recall, dari 36% (dasar) menjadi 77%. Analisis pentingnya fitur dilakukan, hasilnya menunjukkan bahwa Total Social Connectedness (ToSC) adalah prediktor yang paling dominan. Secara ringkas, studi ini membenarkan bahwa mengoptimalkan sensitivitas melalui penyesuaian ambang batas sangat penting untuk skrining medis. Selain itu, faktor isolasi sosial muncul sebagai indikator risiko depresi yang lebih signifikan daripada atribut demografis.
Kata kunci: penambangan data; depresi; data tidak seimbang; hutan acak; smote; penyesuaian ambang batas
Abstract:Abstract: The election of the Student Council President is an important process in building a democratic, responsible, and integrity-based leadership culture in the school environment. In addition, through the main discussion…
ssion in this study aims to optimize the selection process for candidates for Student Council President at SMP Negeri 11 Tanjung Balai through the implementation of a Decision Support System (DSS) based on the MOORA (Multi-Objective Optimization on the Basis of Ratio Analysis) method. The MOORA method is used to normalize values, weight criteria, and calculate optimization values to produce the best alternative ranking. Data were obtained through observation, interviews with school officials, and literature studies. The results of the study indicate that the MOORA method is able to provide objective and transparent ranking results, where M. Asril Sitorus Pane obtained the highest score of 0.347 (Rank 1), followed by M. Rian with a score of 0.333 (Rank 2). The implementation of this system is expected to be able to provide recommendations for the best candidates regularly and accurately, so that it can support fairer and more accountable decision-making in the next Student Council President election.
Keywords: decision support system; osis chairman election; MOORA; SMP negeri 11 tanjung balai.
Abstrak: Pemilihan Ketua OSIS merupakan proses penting dalam membangun budaya kepemimpinan yang demokratis, bertanggung jawab dan berintegritas di lingkungan sekolah. Selain itu, melalui pokok pembahasan pada penelitian ini bertujuan untuk dapat mengoptimalkan proses seleksi calon Ketua OSIS di SMP Negeri 11 Tanjung Balai melalui penerapan Sistem Pendukung Keputusan berbasis metode MOORA (Multi-Objective Optimization on the Basis of Ratio Analysis). Metode MOORA digunakan agar dapat melakukan normalisasi nilai, pembobotan kriteria serta perhitungan nilai optimasi guna menghasilkan peringkat alternatif terbaik. Data diperoleh melalui observasi, wawancara dengan pihak sekolah serta dan studi kepustakaan. Hasil penelitian menunjukkan bahwa metode MOORA mampu memberikan hasil peringkat yang objektif dan transparan, yang dimana M. Asril Sitorus Pane memperoleh nilai tertinggi sebesar 0,347 (Peringkat 1), diikuti oleh M. Rian dengan nilai 0,333 (Peringkat 2). Penerapan sistem ini diharapkan mampu memberikan rekomendasi kandidat terbaik secara sistematis dan akurat, sehingga dapat mendukung pengambilan keputusan yang lebih adil dan akuntabel dalam pemilihan Ketua OSIS selanjutnya.
Kata kunci: MOORA; pemilihan ketua osis; sistem pendukung keputusan; SMP negeri 11 tanjung balai.
Abstract:Abstract: Rehabilitation programs are essential in correctional systems to equip inmates with the skills and behavioral readiness required for social reintegration. However, rehabilitation program assignment in many correctional…
ectional institutions remains dependent on manual and subjective assessments, which may result in inconsistent decisions. This study develops a Random Forest–based prediction system to support objective and data-driven rehabilitation program determination. A quantitative approach was applied using historical inmate data from January 2023 to January 2025, comprising 2,023 records. The research process included data preprocessing, an 80:20 training–testing split, model training, and performance evaluation using accuracy, precision, recall, and F1-score metrics. The results show that the model achieved an accuracy of 86.17% during training in Google Colab and 68.83% when deployed within the application system. This performance gap reflects real-world deployment and computational constraints rather than model failure. The proposed system provides consistent and objective rehabilitation program recommendations, thereby supporting more effective rehabilitation planning and decision-making in correctional institutions.
Keywords: correctional institutions; inmate rehabilitation programs; machine learning; random Forest; prediction system
Abstrak: Program pembinaan narapidana memiliki peran penting dalam sistem pemasyarakatan untuk membekali warga binaan dengan keterampilan serta kesiapan perilaku dalam proses reintegrasi ke masyarakat. Namun, pada banyak lembaga pemasyarakatan, penentuan program pembinaan masih bergantung pada penilaian manual yang bersifat subjektif, sehingga berpotensi menimbulkan ketidakkonsistenan dalam pengambilan keputusan. Penelitian ini mengembangkan sistem prediksi program pembinaan narapidana berbasis algoritma Random Forest guna mendukung pengambilan keputusan yang objektif dan berbasis data. Pendekatan kuantitatif diterapkan menggunakan data historis narapidana periode Januari 2023 hingga Januari 2025 sebanyak 2.023 data. Tahapan penelitian meliputi prapemrosesan data, pembagian data latih dan uji dengan rasio 80:20, pelatihan model, serta evaluasi performa menggunakan metrik akurasi, precision, recall, dan F1-score. Hasil penelitian menunjukkan bahwa model mencapai akurasi sebesar 86,17% pada tahap pelatihan di Google Colab dan 68,83% saat diimplementasikan pada sistem aplikasi. Perbedaan performa tersebut mencerminkan keterbatasan lingkungan operasional, bukan kegagalan model. Secara keseluruhan, sistem yang dikembangkan mampu memberikan rekomendasi program pembinaan yang lebih objektif dan konsisten, sehingga mendukung perencanaan pembinaan yang lebih efektif.
Kata kunci: mesin pembelajaran; program pembinaan narapidana; random Forest; sistem pemasyarakatan; sistem prediksi
Abstract:Abstract: Academic achievement mapping is an important process in higher education to support effective academic monitoring and guidance. In practice, student grouping is often conducted manually by academic staff using…
simple criteria such as Grade Point Average (GPA) thresholds and subjective judgment, without systematic data analysis. This study aims to apply the Fuzzy C-Means (FCM) clustering algorithm to objectively group students based on their academic achievement levels. The dataset consists of academic records from 179 sixth-semester students of the Computer Science Study Program at Universitas Islam Negeri Sumatera Utara, where 160 eligible students are processed in the FCM calculation. Three variables are used: cumulative GPA, total completed credits, and the total number of low grades (D/E). The FCM algorithm automatically performs the mapping and groups students into three categories, namely excellent, stable, and at-risk students. Cluster quality is evaluated using the Silhouette Score and Davies–Bouldin Index, showing satisfactory clustering performance. The results indicate that the proposed approach provides a data-driven and objective basis for academic decision support.
Keywords: academic achievement; clustering; fuzzy c-means; student
Abstrak: Pemetaan pencapaian akademik mahasiswa merupakan proses penting dalam pendidikan tinggi untuk mendukung pemantauan dan pembinaan akademik yang tepat sasaran. Dalam praktiknya, pengelompokan mahasiswa masih sering dilakukan secara manual oleh pihak akademik berdasarkan kriteria sederhana, seperti batasan Indeks Prestasi Kumulatif (IPK) dan penilaian subjektif, tanpa analisis data yang sistematis. Penelitian ini bertujuan menerapkan algoritma Fuzzy C-Means (FCM) untuk mengelompokkan mahasiswa secara objektif berdasarkan tingkat pencapaian akademik. Data penelitian berasal dari 179 mahasiswa semester enam Program Studi Ilmu Komputer Universitas Islam Negeri Sumatera Utara, dengan 160 mahasiswa memenuhi kriteria dan diproses menggunakan algoritma FCM. Variabel yang digunakan meliputi IPK kumulatif, jumlah SKS yang telah ditempuh, dan total nilai rendah (D/E). Proses pemetaan sepenuhnya dilakukan oleh algoritma FCM dan menghasilkan tiga kategori mahasiswa, yaitu unggul, stabil, dan berisiko. Evaluasi menggunakan Silhouette Score dan Davies–Bouldin Index menunjukkan kualitas pengelompokan yang cukup baik.
Kata kunci: fuzzy c-means; clustering; mahasiswa; pencapaian akademik
Abstract:YouTube has become a major platform for public discourse in Indonesia, yet large-scale sentiment analysis of its comments remains challenging due to dynamic content, informal language, and limited labeled data. This study…
y proposes a Selenium–IndoBERT pipeline for sentiment analysis of Indonesian YouTube comments using a pseudo-labeling approach. Data were collected from ten YouTube videos discussing the One Piece flag phenomenon, yielding 10,842 comments after preprocessing. Selenium was employed to extract comments from dynamic pages, while IndoBERT was fine-tuned on a small manually labeled dataset and used to generate pseudo-labels for unlabeled data. Model performance was evaluated using probabilistic metrics, including Coverage, Expected Calibration Error (ECE), and Brier Score. At a confidence threshold of 0.75, 78.5% of comments received pseudo-labels, with an ECE of 0.095 and a Brier Score of 0.174. Manual validation showed substantial agreement with human annotations (Fleiss’ kappa = 0.72). The results indicate that the proposed pipeline enables scalable and reliable sentiment analysis with minimal manual annotation.