Abstract:Abstract: Anomalous sound detection is essential for industrial predictive maintenance, as machine failures often originate from subtle acoustic changes during operation. However, high background noise and limitations of…
conventional Convolutional Neural Networks (CNN) reduce detection reliability. This study proposes a 1D-CNN-based anomaly detection framework with multi-view feature fusion and temporal segmentation to enhance detection performance. The approach combines MFCC, Log-Mel Spectrogram, and Chroma STFT features, while temporal segmentation divides audio signals into 5-second segments to better capture transient anomalies. Experiments on the MIMII dataset under varying Signal-to-Noise Ratio (SNR) conditions show that MFCC and Log-Mel fusion achieves the best performance, with 97.90% accuracy and ROC-AUC of 0.9789. The model maintains accuracy above 90% at −6 dB, demonstrating strong robustness in noisy industrial environments.
Keywords: industrial anomaly detection; 1D-CNN; multi-view feature fusion; temporal segmentation; MIMII dataset.
Abstrak: Deteksi anomali suara merupakan komponen penting dalam sistem pemeliharaan prediktif industri, karena kegagalan mesin sering diawali oleh perubahan akustik yang bersifat halus selama proses operasi. Namun, tingkat kebisingan yang tinggi serta keterbatasan arsitektur Convolutional Neural Network (CNN) konvensional dapat menurunkan keandalan deteksi. Penelitian ini bertujuan mengusulkan kerangka deteksi anomali berbasis 1D-CNN yang mengintegrasikan strategi fusi fitur multi-view dan segmentasi temporal untuk meningkatkan kinerja deteksi. Pendekatan yang digunakan menggabungkan fitur MFCC, Log-Mel Spectrogram dan Chroma STFT, sementara teknik temporal splitting membagi sinyal audio menjadi segmen berdurasi 5 detik untuk menangkap anomali yang bersifat sementara. Eksperimen menggunakan dataset MIMII pada berbagai kondisi Signal-to-Noise Ratio (SNR) menunjukkan bahwa kombinasi MFCC dan Log-Mel Spectrogram menghasilkan kinerja terbaik dengan akurasi 97,90% dan ROC-AUC sebesar 0,9789. Model juga mempertahankan akurasi di atas 90% pada kondisi kebisingan ekstrem (−6 dB) yang menunjukkan ketahanan yang baik dalam lingkungan industri yang bising.
Kata kunci: deteksi anomali industri; 1D-CNN; fusi fitur multi-view; segmentasi temporal; dataset MIMII
Abstract:This study aims to apply the Analytic Network Process (ANP) method as a decision support tool in determining the eligibility of education grant recipients in North Sumatra Province. The background of this research arises…
from the large number of grant applicants compared to the available budget, as well as the absence of clear and objective evaluation standards. The ANP method was chosen because it allows the interdependence between assessment criteria such as institutional feasibility, performance and achievement, social and educational impact, and accountability and transparency to be analyzed comprehensively. Data were obtained through interviews, documentation, and observation at the North Sumatra Provincial Education Office. The results of the ANP model show that the criterion with the highest weight is accountability and transparency (0.44), followed by social and educational impact (0.31). Among the three alternatives, community-based education foundations (A2) obtained the highest total weight (0.30), indicating that they are the most eligible recipients of education grants. The implementation of the ANP-based decision support system produces valid and consistent ranking results (CR < 0.1), enabling faster, fairer, and more transparent decision-making. Therefore, the ANP method contributes significantly to improving governance, objectivity, and accountability in the distribution of education grants in North Sumatra Province.
Abstract:Abstract: INET Computer Palembang, as a computer training institution, faces difficulties in understanding participant characteristics due to variations in age, educational background, and chosen course packages. This study…
udy aims to analyze participant criteria and group them based on similarities using the K-Means Clustering algorithm. The data used were historical records of course participants from 2022 to 2025. The research process followed the CRISP-DM stages, starting from data cleaning and transformation, determining the optimal number of clusters using the Elbow Method, to evaluating cluster quality with the Davies-Bouldin Index. The implementation was carried out using Python and the scikit-learn library. The results show that the optimal number of clusters is k=5 with a Sum of Squared Errors (SSE) value of 1064.66 and a Davies-Bouldin Index (DBI) score of 0.820, indicating good cluster quality. The resulting clustering provides a structured profile of participants and demonstrates that K-Means is effective in segmenting course participants. These findings are expected to assist the institution in designing more targeted training programs.
Keywords: clustering; data mining; elbow method; k-means; computer course
Abstract:Abstract: Medan Aviation Polytechnic is one of the campuses under the ministry of transportation which has a major in telecommunication and air navigation engineering in Indonesia. Based on field surveys, an Analog to Digital…
gital Converter (ADC) practicum kit is needed to improve the ability of cadets. Based on this background, this study aims to design and simulate two ADC circuits, each of which is compiled by the integrated circuit (IC) ADC0804 and IC ADC0809 respectively. Three statistical formulas, namely mean error (ME), standard deviation error (SDE), and root mean square error (RMSE) are used to measure the performance of the two ADC circuits. Both ADC circuits are simulated using a Proteus 8.11 Simulator with 255 analog input voltages. Based on the result of the study, it is known that the ADC circuit compiled by IC ADC0809 is more accurate than the ADC circuit compiled by IC ADC0804. This is evidenced by a smaller error value, which is based on the simulation results of the ME, SDE, and RMSE values were 0.4210, 0.3410, and 0.5110, respectively. And, based on the measurement results, it has ME, SDE, RMSE respectively, namely 0.8510, 0.8110, and 0.9310.
Keywords: ADC; Proteus 8.11 Simulator; IC ADC0804; IC ADC0809; ME; SDE; RMSE
Abstrak: Politeknik Penerbangan Medan adalah salah satu kampus di bawah Kementerian Perhubungan yang memiliki jurusan teknik telekomunikasi dan navigasi udara di Indonesia. Berdasarkan survei di lapangan, kit praktikum konverter analog ke digital diperlukan untuk meningkatkan kemampuat taruna. Berdasarkan latar belakang tersebut, penelitian ini bertujuan merancang dan mensimulasi dua rangkaian ADC yang masing-masing disusun oleh IC ADC0804 dan IC ADC0809. Tiga formula statistik, yaitu mean error (ME), standard deviation error (SDE), and root mean square error (RMSE) digunakan untuk mengukur kinerja kedua rangkaian ADC tersebut. Kedua rangkaian ADC tersebut disimulasi menggunakan Simulator Proteus 8.11 dengan 255 tegangan masukan analog. Berdasarkan hasil penelitian diketahui bahwa rangkaian ADC yang disusun oleh IC ADC0809 lebih akurat dibandingkan dengan rangkaian ADC yang disusun oleh IC ADC0804. Hal tersebut dibuktikan dengan nilai kesalahan yang lebih kecil, yaitu berdasarkan hasil simulasi memiliki ME, SDE, RMSE masing-masing adalah 0,4210, 0,3410 dan 0,5110. Dan berdasarkan hasil pengukuran memiliki ME, SDE, dan RMSE masing-masing adalah 0,8510, 0,8110, dan 0,9310.
Kata kunci: ADC; Simulator Proteus 8.11; IC ADC0804; IC ADC0809; ME; SDE; RMSE
Abstract:Abstract: The background of this research is that some of the risks of using technology that are classified as dangerous are often ignored by users of the monitoring system for learning activities at private universities…
so that there are several obstacles such as not being able to open the system because the system is hacked by irresponsible parties, the computer network used is often disrupted so that hampers the operational process, and the level of computer security is still relatively weak. This study aims to measure the likelihood of threats and risk impacts on the teaching and learning activity monitoring system and to provide recommendations for risk control of security problems that could become a threat that causes losses to universities. The framework used as a tool to measure the level of threat and risk impact is to use the NIST Special Publication 800-30r-1 framework. The framework of the NIST Special Publication 800-30r-1 has nine phases in carrying out risk assessments, namely introduction of system characteristics, recognition of threats, recognition of vulnerabilities, analysis of handling systems, determining likelihood, determining impact, risk determination, recommending control and determination of results. There are six risk assessment systems for monitoring learning activities at private universities, two of which are high so they are classified as very dangerous and the rest are moderate. The results of this study are used as a reference in making risk control standard documents as a form of improving the quality of a private university.
Keywords: Monitoring System; NIST Spesial Publication 800-30r1; Risk Assessment.
Abstrak: Latarbelakang penelitian ini adalah resiko penggunaan teknologi yang tergolong berbahaya sering tidak dihiraukan oleh pengguna sistem monitoring kegiatan belajar pada perguruan tinggi swasta sehingga terjadi beberapa kendala seperti tidak bisa membuka sistem karena sistem diretas oleh pihak yang tidak bertanggung jawab, jaringan komputer yang digunakan sering terganggu sehingga menghambat proses operasional, serta tingkat keamanan komputer yang masih tergolong lemah. Penelitian ini mempunyai tujuan yaitu mengukur seberapa besar kemungkinan terjadi ancaman dan dampak resiko terhadap sistem monitoring kegiatan belajar mengajar serta memberikan rekomendasi pengendalian resiko dari permasalahan keamanan yang bisa menjadi suatu ancaman yang menimbulkan kerugian pada perguruan tinggi. Framework yang digunakan sebagai alat untuk mengukur tingkat ancaman dan dampak resiko adalah menggunakan kerangka kerja NIST Special Publication 800-30r-1. Kerangka kerja NIST Special Publication 800-30r-1 ini mempunyai sembilan fase dalam melakukan penilaian resiko yaitu pengenalan karakteristik sistem, pengenalan ancaman, pengenalan kerentanan, analisis penanganan sistem, menentukan kemungkinan terjadi (likelihood), menentukan dampak (impact), risk determination, merekomendasikan pengendalian dan penetapan hasil. Penilaian resiko sistem monitoring kegiatan belajar pada perguruan tinggi swasta ada enam resiko yang dua diantaranya termasuk tinggi sehingga digolongkan sangat berbahaya dan selebihnya termasuk sedang. Hasil dari penelitian ini digunakan sebagai acuan dalam pembuatan dokumen standar pengendalian resiko sebagai bentuk peningkatan mutu suatu perguruan tinggi swasta.
Kata kunci: NIST Spesial Publication 800-30r; Penilaian Resiko; Sistem Monitoring
Abstract:This study investigates the role of the internet in bridging language gaps and enhancing English as a Foreign Language (EFL) instruction within Solo's multilingual context. The focus is on how internet resources aid students…
ents in navigating between Bahasa Jawa, Bahasa Indonesia, and English, reflecting the multilingual dynamics of EFL classrooms. Utilizing a qualitative approach, semi-structured interviews were conducted with students from grade XII public senior high schools in Solo, Central Java. The findings reveal that the internet plays a significant role in facilitating language learning by providing access to diverse resources and interactive platforms. It is reported that internet tools help them create more engaging and culturally relevant lessons, which cater to the multilingual backgrounds of the students. Students highlighted that online resources offer immediate feedback, diverse learning materials, and opportunities for practicing English in real-world contexts, which are crucial for mastering a foreign language. Moreover, the study shows that the internet supports students in developing digital literacy skills, which are essential for effective language learning in the 21st century. The use of internet-based learning tools helps students seamlessly transition between languages, enhancing their overall language proficiency and confidence in using English. This research underscores the importance of integrating internet resources in EFL education to address the unique linguistic needs of students in multilingual settings. Future studies should explore the long-term impacts of internet use on language acquisition and its potential integration with traditional teaching methods to create a more holistic and effective EFL learning environment.
Abstract:This study investigates the relationship between teenage pregnancy and future maternal mental health by using qualitative methods and relying on literature review as the main data source. The background of this study is…
based on the importance of a deeper understanding of the impact of teenage pregnancy on maternal mental health, given the high prevalence of teenage pregnancy in Indonesia and its long-term negative impact. The purpose of this study is to investigate the factors that support or hinder the mental health of mothers who experience teenage pregnancy, and to present key findings from the relevant literature in this context. The research method used was a qualitative analysis of relevant literature studies found through systematic searches in academic databases and scientific journals. This approach allowed us to explore the findings of various studies and gain an in-depth understanding of the phenomenon under study. The main results of this study show that teenage pregnancy has a significant impact on the mother's future mental health, including an increased risk of depression, anxiety and postnatal stress. Factors such as social support, access to mental health services, and economic conditions play an important role in determining the mother's future mental health. The conclusion of this study is that efforts to improve future maternal mental health should be a priority in public policy and clinical practice. A holistic approach that takes into account the various factors that influence maternal mental health, as well as cross-sectoral cooperation, is needed to create a supportive environment for adolescent mothers to achieve optimal mental well-being.
Abstract:Based on the background of the problem that has been explained by the researcher, it has been clarified into several problems as follows: 1. There are still many female students who ignore or underestimate the lessons of…
moral aqidah 2. The ongoing learning process is less interesting so that students feel bored quickly. 3. Only some students understand the explanation given by the teacher. 4. Lack of student activity (question and answer) when learning takes place. 5. There are still many students who are reluctant to pay attention to the teacher explaining the material. The research method used by the author is quantitative research. The population in this study was all 30 students in class IX M at MTs Darunnajah 2 Cipining. This shows that student learning outcomes in the subject of moral aqidah have a very high level. Based on the research results, there is a significant positive influence of the use of learning media on student learning outcomes in the moral aqidah subject at MTs Darunnajah 2 Cipining Bogor. This is proven by the calculation results of the equation Y 140.383 + 0.219 In the table for testing the significance of the regression line equation from the 5th column regression row, namely Fcount (b/a) 1.407, and p-value 0.245 > 0.05, so that H0 is accepted, it can be concluded that the regressions of Y and X are significant. The correlation coefficient value obtained r_xy 0.219 < r_table 0.374 is included in the weak correlation because it is in the value range 0.20-0.39. The results of the coefficient of determination show that visual learning media (print) has an influence of 4.8% on student learning outcomes, while 95.2% is influenced by other factors.
Abstract:This study investigates the influence of Accounting Knowledge and Education on the quality of MSME financial reports, focusing on the moderating role of SAK EMKM Socialization (Indonesian Financial Accounting Standards for…
or Micro, Small, and Medium Enterprises). Using survey data collected from MSME operators, the research reveals that accounting knowledge has a strong positive relationship with financial reporting quality. Education also plays a positive but weaker role, suggesting significant potential for improvement. The study finds that the socialization of SAK EMKM significantly improves the quality of MSME financial reports but does not moderate the relationship between either accounting knowledge or education and financial report quality. These findings suggest that education and accounting knowledge are fundamental in improving MSME financial reporting practices, while SAK EMKM socialization is more effective for MSMEs with limited financial literacy. This research highlights the need for tailored training programs and socialization efforts to address the specific needs of MSMEs, ensuring that all operators, regardless of educational background, can produce high-quality financial reports in line with established standards.
Abstract:This research is designed to examine how students use both denotative and connotative meanings in their everyday utterances within the campus environment. In daily communication, students do not rely solely on literal meanings;…
anings; instead, their language often conveys implied messages shaped by context, cultural background, and patterns of social interaction. To explore this phenomenon, the study applies a qualitative descriptive approach, focusing on naturally occurring conversations among students in various campus settings. Data were collected through careful observation and documentation of students’ spoken interactions, allowing for an in-depth understanding of how meaning is constructed in real-life situations. The results indicate that students actively employ both denotative and connotative meanings in their speech. However, connotative meanings appear more dominant, particularly in informal contexts such as casual conversations with peers. This tendency highlights the role of language as a flexible and dynamic tool for expression. Furthermore, the frequent use of connotative language demonstrates students’ creativity in conveying ideas, emotions, and attitudes. It also reflects how language functions as a marker of social identity, helping students build relationships and express group belonging within the academic community.