Garuda - Garba Rujukan Digital

Analisis Wacana Kritis Model Teun A. Van Djik terhadap Kasus Korupsi pada Media Online detik.News Sari, Arini Vika; Pariyasto, Sofyan; Marpaung, Muhammad Sahrijal
Adjektiva: Educational Languages and Literature Studies Vol. 7 No. 2 (2024)
Publisher : Universitas Mulawarman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30872/adjektiva.v7i2.4098

Penelitian ini bertujuan untuk menganalisis wacana dari teks berita mengenai kasus korupsi yang terdapat pada media online detik.News menggunakan analisis wacana kritis. Penelitian ini merupakan penelitian kualitatif deskriptif. Data yang digunakan adalah teks berita pada detik.News dengan judul Penyuap Gubernur Malut Abdul Gani Kasuba di Kasus Korupsi Segera Diadili yang diterbitkan 4 Maret 2024. Teknik analisis data dilakukan dengan baca dan catat. Instrumen penelitian adalah peneliti sendiri dengan menggunakan analisis wacana kritis model Teun A. Van Dijk. Teknik analisis data dilakukan dengan reduksi data, penyajian data, dan penarikan kesimpulan. Hasil penelitian menunjukkan bahwa teks berita mengenai kasus korupsi pada media online detik.News menggunakan struktur makro, superstruktur dan struktur mikro. Pada struktur mikro, topik dan subtopik sesuai dengan tema berita. Pada bagian superstruktur terdapat judul, situasi dan komentar yang terstruktur dan saling mendukung. Sedangkan pada struktur mikro ditemukan koherensi, kata ganti dan retoris. Dengan menggunakan analisis wacana kritis menggunakan model Teun A. Van Dijk ini kita dapat mengetahui kasus korupsi yang ada di media online detik.News yang penulisnya memiliki ideologi untuk memberikan informasi kepada pembaca atau masyarakat dengan sebenar-benarnya.

Lung X-ray Image Similarity Analysis Using RGB Pixel Comparison Method Pariyasto, Sofyan; ., Suryani; Warongan, Vicky Arfeni; Sari, Arini Vika; Widiyanto, Wahyu Wijaya
Journal of Applied Informatics and Computing Vol. 9 No. 1 (2025): February 2025
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v9i1.8776

The high death rate caused by pneumonia and Covid-19 is still quite high. Based on data released by WHO, 14% of deaths in children under 5 years old are caused by pneumonia. One of the processes carried out to help the diagnosis process is to look at lung images using X-Ray images. To obtain information about normal lung X-Ray images, Pneumonia and Covid-19, calculations are carried out using the color difference in each pixel of the X-ray image. The calculation process will provide output in the form of numbers in units of 0 to 100. This is done to facilitate the process of identifying the similarity of each X-Ray image being compared. The research stages are carried out with stages starting from adjusting the image size, then by breaking down the pixel values of the two images being compared and the process of calculating the difference in value from each pixel with the same coordinates. After calculating a combination of 30,000 combinations using 300 x-ray images, the results obtained in the form of the level of similarity between normal x-ray images and pneumonia x-ray images are the highest with a similarity percentage of 80.06%. The combination of normal images and pneumonia images is 10,000 combinations using 100 normal x-ray images and 100 pneumonia x-ray images. Normal x-ray images and covid x-ray images have a similarity of 79.18%. The combination of normal images and covid images is 10,000 combinations. The combination uses 100 normal x-ray images and 100 covid x-ray images. Pneumonia x-ray images and covid x-ray images have the lowest similarity level of 78.87%. The combination of pneumonia x-ray images and covid x-ray images is 10,000 combinations. The data used in the combination are 100 pneumonia images and 100 covid images. From the test results, the information obtained was that Accuracy was worth 0.54, Precision was worth 0.54, Recall was worth 0.59 and F1-score was worth 0.56.

ANALISIS ONTOLOGIS PERFORMA METODE EUCLIDEAN, MANHATTAN, DAN MINKOWSKI UNTUK IDENTIFIKASI KEMIRIPAN CITRA Pariyasto, Sofyan
JOURNAL OF SCIENCE AND SOCIAL RESEARCH Vol 8, No 1 (2025): February 2025
Publisher : Smart Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54314/jssr.v8i1.2480

Abstract: Information about algorithm performance is one of the reasons for this research. Choosing an algorithm that suits your needs will certainly increase the effectiveness of the computational process. The ontology in this study focuses on finding information about the comparison of the performance of the Euclidean, Manhattan, and Minkowski methods. In the research process, testing was carried out using a dataset consisting of 1,000 images. From the dataset used, there are ten categories, namely African Tribes, Beaches, Buildings, Buses, Dinosaurs, Elephants, Flowers, Horses, Mountains, and Food. Each category consists of 100 images. The study was conducted by comparing the performance of each method to identify image similarities. From the results of the study, information was obtained on the average execution time to perform computations from each method, namely Euclidean 0.55 seconds, Manhattan 0.56 seconds, and Minkowski 0.58 seconds. Then the average memory usage for the computational process of each method, namely Euclidean 2.29 MB, Manhattan 2.28 MB, and Minkowski 2.22 MB. The peak memory usage during the computation process of each method is Euclidean 3.60 MB, Manhattan 3.59 MB, and Minkowski 2.39 MB. Euclidean distance offers the speed of the computation process but requires the highest resources. Minkowski distance offers low resource usage but the computation process becomes slow. Keywords: Euclidean Method, Manhattan, Minkowski, Image Similarity Identification. Abstrak: Informasi mengenai performa algoritma menjadi salah satu alasan dilakukan penelitian ini. Pemilihan algoritma yang sesuai dengan kubutuhan tentu akan meningkatkan efektifitas dalam proses komputasi. Ontologi dalam penelitian ini fokus dalam mencari keberadaan informasi mengenai perbandingan performa metode Metode Euclidean, Manhattan, dan Minkowski. Dalam proses penelitian dilakukan pengujian dengan menggunakan dataset yang terdiri dari 1.000 citra. Dari dataset yang digunakan terdapat sepuluh kategori yaitu Suku Afrika, Pantai, Bangunan, Bus, Dinosaurus, Gajah, Bunga, Kuda, Gunung, dan Makanan. Setiap kategori terdiri dari 100 citra. Penelitian dilakukan dengan membandingkan kinerja masing-masing metode metode untuk melakukan identifikasi kemiripan citra. Dari hasil penelitian didaptkan informasi rata-rata waktu eksekusi untuk melakukan komputasi dari tiap-tiap metode yaitu Euclidean 0.55 detik , Manhattan 0.56 detik, dan Minkowski 0.58 detik. Kemudian rata-rata penggunaan memori untuk proses komputasi dari masing-msing metode yaitu Euclidean 2.29 MB, Manhattan 2.28 MB, dan Minkowski 2.22 MB. Puncak penggunaan memori saat melakukan proses komputasi dari masing-masing metode yaitu Euclidean 3.60 MB, Manhattan 3.59 MB, dan Minkowski 2.39 MB. Eculidean distance menawarkan kecepatan proses komputasi namun membutuhkan resource paling tinggi. minkowski distance menawarkan penggunaan resource yang rendah namun proses komputasi menjadi lambat. Kata kunci: Metode Euclidean, Manhattan, Minkowski, Identifikasi Kemiripan Citra

OPTIMALISASI KLASIFIKASI CITRA MEDIS MENGGUNAKAN CNN DAN ADAM OPTIMIZER DENGAN PARAMATER MINIMUM Pariyasto, Sofyan; Warongan, Vicky Arfeni; Suryani, Suryani
JOURNAL OF SCIENCE AND SOCIAL RESEARCH Vol 8, No 1 (2025): February 2025
Publisher : Smart Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54314/jssr.v8i1.2515

Abstract: Research in the field of imaging, especially in medical terms, is expected to have a positive impact on the treatment and diagnosis of diseases in the medical world. Medical image classification is a topic that is often researched, this is indicated by the many national and international journals that discuss this topic. Research on medical image classification using Convolutional Neural Network (CNN) usually focuses on the use of maximum parameters (hyper parameters) to get the best results. However, those that use minimal parameters and the smallest resources are still lacking. Based on the existing problems, it is carried out to obtain optimization in the medical image classification process. The classification of medical images in this study focuses on brain tumor images consisting of three classes, namely meningioma, glioma and pituitary tumor. The approach taken in this study is to use the CNN model and Adaptive Moment Estimation (Adam) Optimizer. The study was conducted by combining the smallest parameters from the Adam Optimizer. The parameters combined are Epoch and Convolution Layer. Where 3 Epoch categories (1,5,10) and 5 convolution layers (1,2,3,4,5) are used. From the tests carried out, the highest accuracy results obtained were 92.8% with epoch parameters of 10 and three convolution layers. Meanwhile, the highest average accuracy was recorded at 90.7% with epoch parameters of 10. The fastest computation time required for model creation was 24.83 seconds, and the lowest CPU resource usage during the model creation process was 16.45%. Keywords: Image Classification, CNN Optimization, Adam Optimizer, Brain Tumor, Minimum Parameters Abstrak: Penelitian dibidang citra khususnya dalam hal medis diharapkan dapat membawa dampak baik bagi penanganan dan diagnosis penyakit dalam dunia medis. Klasifikasi citra medis menjadi topik yang cukup sering diteliti, hal ini ditandai dengan banyaknya jurnal baik nasional maupun internasional yang membahas mengenai topik ini. Penelitian mengenai klasifikasi citra medis menggunakan Convolutional Neural Network (CNN) biasanya berfokus pada penggunaan paramater maksimal (hyper parameter) untuk mendapatkan hasil terbaik. Namun yang menggunakan paramater minimal dan sumber daya terkecil masih belum ada. Berdasarkan permasalahan yang ada maka dilakukan untuk mendapatkan optimalisasi dalam proses kalsifikasi citra medis. Klasifikasi citra medis dalam penelitian ini difokuskan pada citra tumor otak yang terdiri dari tiga kelas yaitu, meningioma, glioma dan pituitary tumor. Pendekatan yang dilakukan dalam penelitian ini adalah menggunakan model CNN dan Adaptive Moment Estimation (Adam) Optimizer. Penelitian dilakukan dengan melakukakn kombinasi paramater terkecil dari Optimizer Adam. Paramater yang dikombinasikan yaitu Epoch dan Lapisan konvolusi. Dimana digunakan 3 kategori Epoch (1,5,10) serta 5 lapisan konvolusi (1,2,3,4,5). Dari pengujian yang dilkaukan didapatkan hasil Akurasi tertinggi yang diperoleh adalah 92,8% dengan parameter epoch 10 dan tiga lapisan konvolusi. Sementara itu, akurasi rata-rata tertinggi tercatat sebesar 90,7% dengan parameter epoch 10. Waktu komputasi tercepat yang diperlukan untuk pembuatan model adalah 24,83 detik, dan penggunaan sumber daya CPU terendah selama proses pembuatan model adalah 16,45%.Kata kunci: Klasifikasi Citra, Optimalisasi CNN, Adam Optimizer, Tumor Otak, Paramater Minimum

PENDIDIKAN KARAKTER ANAK USIA DINI DALAM TINJAUAN ONTOLOGI, EPISTEMOLOGI, DAN AKSIOLOGI Sari, Arini Vika; Pariyasto, Sofyan
MAANA: Jurnal Pendidikan Islam Anak Usia Dini Vol 3 No 1 (2024): April
Publisher : Universitas Islam Darul Ulum

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52166/mjpiaud.v3i1.6988

Tujuan dari penelitian ini adalah untuk meninjau hasil penelitian Gambaran Pendidikan Karakter Anak Usia Dini di Masa Pandemi Covid-19 berdasarkan landasan ontologi, epistemologi, dan aksiologi. Penelitian ini adalah jenis penelitian analisis konten dengan objek Gambaran Pendidikan Karakter Anak Usia Dini di Masa Pandemi Covid-19 tahun 2020. Analisis data dilakukan dengan penafsiran secara deskriptif yang menggunakan tiga langkah, yaitu memahami isi, memisahkan bagian tertentu, dan menganalisis hasil. Hasil penelitian menunjukkan bahwa Gambaran Pendidikan Karakter Anak Usia Dini di Masa Pandemi Covid-19 memiliki landasan ontologi, epistemologi, dan aksiologi. Namun, terdapat bagian-bagian yang tidak dijelaskan dalam penelitian ini yaitu: (1) pemaparan lebih rinci mengenai acuan dalam menentukan nilai-nilai karakter anak usia dini; (2) kurangnya penjelasan dalam instrumen penelitian yang dibuat dalam bentuk tabel; (3) kurangnya penjelasan mengenai rubik penilaian; (4) pada bagian hasil hanya menampilkan kemandirian, kepercayaan diri, dan tanggung jawab, sedangkan di rubik penilaian terdapat 7 aspek dengan 8 indikator.

Evaluasi Kurikulum Sari, Arini Vika; Pariyasto, Sofyan; Simamora, Winri; Syahputra, Ridwan
Jurnal Studi Multidisiplin Qomaruna Vol 2 No 2 (2025): 2025
Publisher : Lembaga Penelitian dan Pengabdian Masyarakat (LPPM), Universitas Qomaruddin, Gresik, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62048/qjms.v2i2.86

Curriculum evaluation is a strategic step in ensuring the quality of education. This article examines various aspects of curriculum evaluation through a literature review of academic sources published between 2020 and 2024. The findings indicate that the most frequently criticized aspects of curriculum implementation include the misalignment of instructional content with students' needs and characteristics, as well as the limited relevance of curriculum content to advances in knowledge and labor market demands. In addition, qualitative evaluation models—such as in-depth interviews and participatory observation—are recommended, as they are capable of capturing dimensions of the learning process that are often overlooked by quantitative approaches. This review highlights the importance of selecting appropriate evaluation models as a foundation for continuous improvement and the development of a curriculum that is more adaptive to change.

Criminal Acts Against Spanish Tourist Couples: A Critical Discourse Analysis Teun A. Van Dijk Sari, Arini Vika; Pariyasto, Sofyan; Monteres, Arlestito
Journal of Advance in Language, Literature, and Education Vol. 1 No. 2 (2025): Journal of Advance in Language, Literature, and Education, June 2025
Publisher : Lembaga Publikasi Ilmiah Dwipantara

Show Abstract | Download Original | Original Source | Check in Google Scholar

Criminal acts such as assault or rape are things that cannot be tolerated. This research uses qualitative data with descriptive methods. Data collection techniques were carried out through documentation, attention, and notes. As for the analysis method, the approach is based on the Critical Discourse Analysis model of Teun A. Van Dijk. Based on the discourse analysis of the news discourse of Spanish celebrities raped by 7 people in India, 4 suspects were arrested published by CNN Indonesia media, it can be concluded that the news preparation structure has a conceptual framework following Teun A. Van Dijk's theory which includes macro structure, superstructure and micro structure. Microstructure is a dimension of AWK that has the most detailed discussion. The microstructure consists of semantics, which consists of 6 data, syntax has 8 data, and rhetoric consists of 2 data. The level of a person's understanding in conducting discourse analysis on a news discourse can influence the perception to respond to the contents of the news.

Discourse Analysis In Online Newspapers Regarding The Potential Differences In Ramadan Sari, Arini Vika; Pariyasto, Sofyan; Abrar Arief, Mhd.
Alinea: Jurnal Bahasa, Sastra dan Pengajaran Vol. 5 No. 1 (2025): Alinea: Jurnal Bahasa, Sastra, dan Pengajaran
Publisher : Bale Literasi: Lembaga Riset, Pelatihan & Edukasi, Sosial, Publikasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58218/alinea.v5i1.1378

Study This aiming for analyze news about difference date the beginning of Ramadan between the Minister of Religion and Muhammadiyah in the letter online news. Types of research This is study qualitative, with approach specifically using analysis models discourse critical Teun A. Van Dijk. Analysis method This covers stage identification, description, and interpretation to structure text news. Data sources used is article online news from CNN Indonesia March 6, 2024 entitled Potential Difference in Ramadan Start Date, Minister of Religion and Muhammadiyah Speak Up. Data collection techniques used is technique read and take notes. While technique data analysis used covering data reduction, data presentation, and extraction conclusion. Dimension text Van Dijk's approach is differentiated become three, namely structure macro, suprastructure, and structure micro. Structure macro referring to the meaning the whole thing that can under scrutiny from news. Suprastructure pointing to the frame a news, such as introduction to be continued with Contents main, conclusion, and closing. Whereas structure micro referring to the meaning local a news that can dug up from aspect semantics, syntax, and rhetoric. The results of the study This show that the media is more tend prioritize the authority of the Minister of Religion in determine date the beginning of Ramadan, and emphasized the agreement national. From the results analysis can concluded that information provided has fulfil criteria structure Teun A. Van Dijk model text. Analysis discourse critical disclose existence use language that tends to own objective certain with the party considered more Correct or wrong in determine date the beginning of Ramadan.

“PENERAPAN METODE WEIGHTED PRODUCT MENENTUKAN MINAT BELAJAR SISWA PADA PENGOLAHAN DATA APLIKASI MICROSOFT OFFICE EXCEL DI SMK AL RAZI SINAR HARAPAN”. Astuti, Ermayanti; Suryani, Suryani; Sinaga, Alesia Lorenzza; Pariyasto, Sofyan; Nurhayati, Nurhayati
JOURNAL OF SCIENCE AND SOCIAL RESEARCH Vol 8, No 4 (2025): November 2025
Publisher : Smart Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54314/jssr.v8i4.4788

Abstract: Data processing applications are currently highly needed by students at Al Razi Sinar Harapan Private Vocational High School, Medan, Johor, especially in the Pharmacy and Software Engineering majors. A quality school is one that responds to the trust of the community, especially students, in choosing their majors at the third level. This means that the school is able to provide the best guidance and service to students, thus producing a generation of quality students in all aspects. Systems analysis is the decomposition of a complete information system into its component parts with the aim of identifying and evaluating problems, opportunities, obstacles, and expected needs so that improvements can be proposed. Systems analysis is conducted after the system design stage and before the system design stage. The method used in this research activity will be a sampling process complemented by training in the use of Microsoft Excel-based learning applications to make decisions regarding student learning interests in subjects. The results of these decisions can be obtained using the Weighted Product method.One way is to train students in the use of data processing applications, namely Microsoft Excel. It is hoped that this research will provide students with a better understanding of Information and Communication Technology (ICT) by utilizing Microsoft Excel, providing them with hands-on experience and skills in Microsoft Office. This will significantly improve their skills in utilizing information technology and computers, encouraging them to participate in further activities. Keywords: Systems Analysis, Learning Interest, Information and Communication Technology, Weighted Product Method, Microsoft Excel (Data Processing Application). Abstrak: Aplikasi Pengolahan data pada zaman sekarang sangat dibutuhkan oleh siswa dan siswi di Sekolah Menengah Kejuruan Swasta Al Razi Sinar Harapan Medan Johor terutama pada jurusan Farmasi dan Rekayasa Perangkat Lunak. Sekolah yang bermutu adalah yang dapat merespon kepercayaan masyarakat khususnya siswa dalam menentukan jurusan yang dipilih pada tingkat 3, artinya bagaimana pihak sekolah mampu memberikan arahan dan pelayanan yang terbaik bagi para siswa-siswi sehingga menghasilkan generasi yang bermutu dalam segala hal. Analisis sistem adalah penguraian dari suatu sistem informasi yang utuh ke dalam bagian-bagian komponennya dengan maksud untuk mengidentifikasikan dan mengevaluasi permasalahan, kesempatan, hambatan yang terjadi dan kebutuhan yang diharapkan sehingga dapat diusulkan perbaikan. Analisis sistem dilakukan setelah tahap perancangan sistem dan sebelum tahap desain sistem. Adapun metode yang di pakai dalam pelaksanaan kegiatan penelitian ini akan dilakukan dengan proses pengambilan sample yang dilengkapi dengan pelatihan penggunaan aplikasi pembelajaran berbasis Microsoft Excel untuk mengambil keputusan pada minat belajar siswa terhadap mata pelajaran. Hasil dari keputusan tersebut dapat diperoleh keputusan dengan menggunakan metode Weighted Product.Salah satunya adalah dengan melatih kemampuan memanfaatkan aplikasi pengolah data yaitu Microsoft Excel. Diharapkan dengan adanya penelitian tersebut, siswa dan siswi dapat lebih mengetahui tentang penggunaan Teknologi Informasi dan Komunikasi (TIK) dengan memanfaatkan Microsoft Excel sebagai pengalaman dan keterampilan bagi siswa dan siswi dalam penggunaan Microsoft Office. Sehingga memberikan manfaat yang signifikan bagi peningkatan keterampilan siswa dan siswi dalam memanfaatkan teknologi informasi dan komputer, mereka sangat berantusias untuk mengikuti kegiatan lebih lanjut. Kata Kunci: Analisis Sistem, Minat Belajar, Teknologi Informasi dan Komunikasi, Metode Weighted Product, Microsoft Excel (Aplikasi Pengolahan Data).

COMPARATIVE ANALYSIS OF HYPERPARAMETER OPTIMIZATION TECHNIQUES ON LIGHTGBM FOR ASTHMA PREDICTION Azmi, Zulfian; Julita, Rina; Irawati, Novica; Pariyasto, Sofyan; Purwawijaya, Ellanda
JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) Vol. 11 No. 2 (2025): JITK Issue November 2025
Publisher : LPPM Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/jitk.v11i2.7369

This study presents a comparative study of hyperparameter optimization methods applied to the Light Gradient Boosting Machine (LightGBM) algorithm for asthma prediction. Traditional machine learning models often face limitations in accuracy and generalization capabilities due to suboptimal hyperparameter configurations. To address these challenges, this study evaluates and compares four approaches: Default LightGBM, RandomizedSearchCV, Optuna Optimization, and Bayesian Optimization. Experimental results show that Bayesian Optimization provides the best performance with an accuracy of 78%, a precision of 0.7778, a recall of 0.7778, an F1-score of 0.7778, and an ROC-AUC of 0.975. These findings emphasize the importance of selecting an appropriate optimization strategy to improve model performance in clinical prediction tasks. Overall, this study confirms the effectiveness of Bayesian Optimization in improving the predictive capabilities of LightGBM and provides an important contribution to the development of decision support systems in healthcare, particularly in the diagnosis and management of asthma

Title

Found 10 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 10 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 10 Documents
Search