Article Per Year (5 Year)
p-Index From 2021 - 2026
2.765
P-Index
This Author published in this journals
All Journal Jurnal Informatika dan Teknik Elektro Terapan SemanTIK : Teknik Informasi Communications in Science and Technology JISICOM (Journal of Information System, Infomatics and Computing) Indonesian Journal of Electrical Engineering and Computer Science Jurnal Sains Teknologi dan Sistem Informasi Jurnal Pengabdian Masyarakat Ilmu Terapan (JPMIT) JPNM : Jurnal Pustaka Nusantara Multidisiplin
Sajiah, Adha Mashur
Unknown Affiliation
Religion Agriculture, Biological Sciences & Forestry Humanities Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Social Sciences

Published : 18 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 18 Documents
Search

 1   2 
WHAT DO USERS WRITE IN ONE FILE CABINET DATABASES: AN ANALYSIS BASED ON TEXT MINING Ransi, Natalis; Surimi, La; Nangi, Jumadil; Sajiah, Adha Mashur; Arman, Arman; Cahyono, Edi
SemanTIK : Teknik Informasi Vol 7, No 1 (2021): semanTIK
Publisher : Informatics Engineering Department of Halu Oleo University

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (535.822 KB) | DOI: 10.55679/semantik.v7i1.15263

Abstract

One file cabinet adalah sistem terintegrasi yang salah satu fungsinya untuk merekam catatan kerja (logbook) dosen dan tenaga kependidikan di Universitas Halu Oleo. Dalam logbook, setiap hari kerja dosen dan tenaga kependidikan menuliskan deskripsi kerja yang telah mereka lakukan dalam sistem database. Artikel ini membahas analisis kumpulan kata-kata yang dituliskan oleh dosen dan tenaga kependidikan pada logbook mereka. Metode yang digunakan adalah penambangan teks kata-kata (text mining). Hasil analisis diperlukan oleh pimpinan (top managers) Universitas Halu Oleo dalam memperoleh gambaran global kinerja dosen dan tenaga kependidikan. Informasi ini penting untuk menentukan kebijakan dalam pengembangan sumber daya manusia.Kata kunci; Database, Logbook, One File Cabinet, Sumber Daya Manusia, Text Mining
Interval type-2 fuzzy logic system for diagnosis coronary artery disease Sajiah, Adha Mashur; Setiawan, Noor Akhmad; Wahyunggoro, Oyas
Communications in Science and Technology Vol 1 No 2 (2016)
Publisher : Komunitas Ilmuwan dan Profesional Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21924/cst.1.2.2016.26

Abstract

Coronary artery disease (CAD) is a disease that has been the deadliest disease in Indonesia. The ratio of cardiologists over potential patients is not appropriate either. Intelligent system which can help doctors or patients for cheap and efficient diagnosing CAD is needed. Medical record data, acquisition of cardiologist knowledge and computing technology can be utilized for developing fuzzy logic based intelligent system. Type-1 fuzzy logic system (T1 FLS) has been widely used in various fields. T1 FS has limitation in representing and modelling uncertainty and minimize the impact. Whereas, type-2 fuzzy set (T2 FS) was also introduced as fuzzy set that can model uncertainty more sophisticated. T2 FLS does have a higher degree of freedom when modeling uncertainty but it is quite difficult to make the membership function. An interval T2 FS is a T2 FS in which the membership grade on third dimension is the same everywhere so it is simpler than T2 FS. This paper aims to clarify the better capability of IT2 FLS over T1 FLS on the development of CAD diagnosis system. Rules and membership function were formulated with the help of fuzzy c-means. This study illustrated the causes of CAD risk factors, fuzzification, type reduction and defuzzification. The resulted system was tested with percentage split method (50%-50%) to produce training data and testing data. This test is performed ten times with random seed to separate the data set. The resulted system generates an average of 73.78% accuracy, 71.94% sensitivity and 76.52% specificity.
PERBANDINGAN JARAK EUCLIDEAN, CITYBLOCK, MINKOWSKI, CANBERRA, DAN CHEBYSHEV DALAM SISTEM TEMU KEMBALI CITRA BATIK Muchtar, Mutmainnah; Zainuddin, Noorhasanah; Sajiah, Adha Mashur; Ningsi, Nurfitria; Pasrun, Yuwanda Purnamasari
Jurnal Informatika dan Teknik Elektro Terapan Vol 12, No 3S1 (2024)
Publisher : Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/jitet.v12i3S1.5324

Abstract

Batik is a highly valuable cultural heritage in Indonesia, showcasing a rich diversity of motifs with deep meaning and aesthetics. To enhance the accessibility and utilization of batik collections, an efficient image retrieval system is essential. This study compares distance measurement methods in a batik image retrieval system: Euclidean, Cityblock, Minkowski, Canberra, and Chebyshev, using a combination of color and texture features. The dataset comprises 50 types of batik images. The results show that the Cityblock method achieves the highest Mean Average Precision (MAP) of 97.71, followed by Canberra with MAP 96.87. The Euclidean method also performs well with a MAP of 94.56, while Minkowski and Chebyshev have lower MAP values of 92.93 and 90.89, respectively. Chebyshev experiences the largest MAP drop when images are rotated (5.98), while Cityblock demonstrates the best resistance to rotation with the smallest MAP drop (1.51). This research successfully developed a Content-Based Image Retrieval (CBIR) system with a GUI in MATLAB and suggests integrating the latest image processing and machine learning techniques for further enhancement.
Penerapan Hadoop untuk Analisis Sentimen Berbasis Big Data pada Ulasan Aplikasi Transportasi Online Putri Angraini Aziz; Nur Ilahi, Syaban Barokah; Sumiarni Moka; Sajiah, Adha Mashur
SATESI: Jurnal Sains Teknologi dan Sistem Informasi Vol. 5 No. 1 (2025): April 2025
Publisher : Yayasan Pendidikan Penelitian Pengabdian ALGERO

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54259/satesi.v5i1.4051

Abstract

The rapid growth of application-based transportation services in Indonesia has generated a large volume of user reviews that contain essential information for service development. However, significant challenges arise in processing and analyzing data on a large scale. This study utilizes Hadoop and Apache Spark technology to conduct sentiment analysis on online transportation application reviews, focusing on Gojek user reviews. The dataset comprises 1.880.112  reviews obtained from Kaggle and Google Play Store. The research method includes data preprocessing using distributed computing with Hadoop and Spark, followed by sentiment labeling based on user ratings. The sentiment analysis model used is Logistic Regression, with hyperparameter tuning through Cross Validation. The evaluation results show a model accuracy of 80%, demonstrating the model's capability in effectively classifying sentiments, supported by PySpark implementation which enables efficient training and evaluation processes despite working with large-scale datasets. Text visualization in the form of a word cloud reveals that negative sentiment is often associated with app performance and digital wallet issues, while neutral sentiment focuses more on driver services. On the other hand, positive sentiment highlights user satisfaction with the overall service. The findings of this study demonstrate the effectiveness of Hadoop in large-scale sentiment analysis processing and provide valuable insights for improving online transportation services.
PENERAPAN HADOOP DALAM ANALISIS SENTIMEN ULASAN PENGGUNA DI PLATFROM ECCOMERCE Kasim, Nurdian; Ardini, Ni Luh Ica; Muharramah, Alfi Zahrah; Hikma, Hikma; Al Qadri, Muhammad Vannes; Rosalina, Rosalina; Asriyani, Wa Ode; Eviriawan, Eviriawan; Sajiah, Adha Mashur
Journal of Information System, Informatics and Computing Vol 9 No 1 (2025): JISICOM (June 2025)
Publisher : Sekolah Tinggi Manajemen Informatika dan Komputer Jayakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52362/jisicom.v9i1.1784

Abstract

Studi ini menyelidiki penggunaan teknologi Hadoop dan algoritma Naive Bayes untuk menganalisis sentimen ulasan pengguna di platform e-commerce. Data yang digunakan berasal dari 391.500 ulasan dari aplikasi Shopee yang dikumpulkan melalui scraping Google Play Store. Implementasi model klasifikasi sentimen, pengumpulan data melalui web scraping, dan pra-pemrosesan data menggunakan PySpark adalah metodologi penelitian. Hasil penelitian menunjukkan bahwa model Naive Bayes dapat mengklasifikasikan perasaan pengguna dengan akurasi 87%. Menurut analisis word cloud, elemen seperti gratis ongkir dan kemudahan penggunaan menjadi pendorong utama sentimen positif. Sementara itu, sentimen negatif didominasi oleh masalah teknis aplikasi dan layanan pelanggan. Penelitian ini menunjukkan bahwa penggunaan Hadoop dan Naive Bayes dalam analisis data ulasan berskala besar saat mengembangkan platform e-commerce adalah efektif.
Ensuring transcript integrity with SHA-3 and digital signature standard: a practical approach Nur Alam, Wa Ode Siti; Sajiah, Adha Mashur; Bahtiar Aksara, La Ode Muhammad; Surimi, La; Ransi, Natalis; Nangi, Jumadil
Indonesian Journal of Electrical Engineering and Computer Science Vol 38, No 3: June 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v38.i3.pp1957-1969

Abstract

Academic transcripts are essential documents in higher education, reflecting students’ academic performance and capabilities. However, the current management of transcript data at Halu Oleo University (UHO) lacks safeguards against unauthorized alterations, compromising their authenticity. This study proposes a method using the secure hash algorithm 3 (SHA-3) and the digital signature standard (DSS) scheme to ensure the integrity of transcript data. A Python-based web module for managing transcripts and a signing program using SHA-3 and DSS were developed and implemented. This method digitally signs transcript files, ensuring that subsequent changes invalidate the current digital signature. Efficiency tests demonstrated an average signing time of 0.242 seconds, indicating a practical and efficient solution. The study’s findings emphasize how SHA-3 and DSS effectively authenticate academic transcript files, preventing unauthorized modifications and safeguarding the integrity of critical educational records. This method presents a robust and efficient solution for educational institutions to strengthen the security and reliability of their academic record management systems.
Penerapan Algoritma You Only Look Once V5 Large (YOLOv5L) dan Tesseract Optical Character Recognition (Tesseract OCR) dalam Deteksi Plat Nomor Kendaraan untuk Cek Status Uji Emisi Kendaraan Zaria, Hashimatul; Sarita, Muh. Ihsan; Sajiah, Adha Mashur
JPNM Jurnal Pustaka Nusantara Multidisiplin Vol. 3 No. 3 (2025): October : Jurnal Pustaka Nusantara Multidisiplin
Publisher : SM Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59945/jpnm.v3i3.736

Abstract

Peningkatan jumlah kendaraan bermotor di kawasan perkotaan, khususnya di Kota Kendari, berpotensi meningkatkan pencemaran udara akibat emisi gas buang kendaraan. Emisi ini mengandung senyawa berbahaya yang berdampak negatif terhadap kesehatan dan lingkungan. Sebagai upaya pengendalian, pemerintah telah menerapkan kebijakan uji emisi. Namun, pelaksanaannya masih terkendala oleh sistem pendataan manual, keterbatasan petugas, lambatnya proses identifikasi kendaraan, serta adanya ketidaksesuaian antara Peraturan Daerah Kota Kendari Nomor 8 Tahun 2015 dan Undang-Undang Nomor 22 Tahun 2009. Perbedaan regulasi ini menghambat optimalisasi pelaksanaan uji emisi oleh perangkat daerah. Penelitian ini bertujuan untuk merancang sistem otomatisasi deteksi status uji emisi kendaraan berbasis computer vision, dengan memanfaatkan algoritma YOLOv5L untuk mendeteksi plat nomor kendaraan, Tesseract OCR dan EasyOCR untuk mengenali karakter pada plat tersebut. Data karakter yang berhasil diekstraksi kemudian akan dicocokkan dengan database uji emisi guna mengetahui riwayat status uji emisi dari kendaraan yang bersangkutan. Pengujian sistem dilakukan dengan dua pendekatan, yaitu pengujian model deteksi dan pengujian algoritma OCR. Hasil pengujian model YOLOv5L menunjukkan bahwa sistem berhasil mendeteksi plat nomor kendaraan dengan nilai Precision sebesar 91%, Recall sebesar 98,1%, AP sebesar 91%, serta mAP (1 kelas), mAP50, dan mAP50-95 masing-masing sebesar 91%. Sementara itu, pengujian algoritma Tesseract OCR dan EasyOCR menghasilkan nilai Accuracy sebesar 0,93 (93%), Precision sebesar 0,95 (95%), Recall sebesar 0,98 (98%), dan F1-Score sebesar 0,96 (96%). Berdasarkan hasil tersebut, sistem dinyatakan layak digunakan karena mampu mendeteksi serta mengenali plat nomor kendaraan dengan baik untuk mendukung pengecekan status uji emisi secara otomatis.
PERBANDINGAN JARAK EUCLIDEAN, CITYBLOCK, MINKOWSKI, CANBERRA, DAN CHEBYSHEV DALAM SISTEM TEMU KEMBALI CITRA BATIK Muchtar, Mutmainnah; Zainuddin, Noorhasanah; Sajiah, Adha Mashur; Ningsi, Nurfitria; Pasrun, Yuwanda Purnamasari
Jurnal Informatika dan Teknik Elektro Terapan Vol. 12 No. 3S1 (2024)
Publisher : Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/jitet.v12i3S1.5324

Abstract

Batik is a highly valuable cultural heritage in Indonesia, showcasing a rich diversity of motifs with deep meaning and aesthetics. To enhance the accessibility and utilization of batik collections, an efficient image retrieval system is essential. This study compares distance measurement methods in a batik image retrieval system: Euclidean, Cityblock, Minkowski, Canberra, and Chebyshev, using a combination of color and texture features. The dataset comprises 50 types of batik images. The results show that the Cityblock method achieves the highest Mean Average Precision (MAP) of 97.71, followed by Canberra with MAP 96.87. The Euclidean method also performs well with a MAP of 94.56, while Minkowski and Chebyshev have lower MAP values of 92.93 and 90.89, respectively. Chebyshev experiences the largest MAP drop when images are rotated (5.98), while Cityblock demonstrates the best resistance to rotation with the smallest MAP drop (1.51). This research successfully developed a Content-Based Image Retrieval (CBIR) system with a GUI in MATLAB and suggests integrating the latest image processing and machine learning techniques for further enhancement.
Co-Authors Abdul Karim Agustan Agustan, Agustan Aksan, Chaeril Aksara, L. M Fid Al Qadri, Muhammad Vannes Alfian Alfian Ardini, Ni Luh Ica Arman Arman Asriyani, Wa Ode Bahtiar Aksara, La Ode Muhammad Bambang Pramono Budiman, Iin Juliana Edi Cahyono Efendi, Ilham Julian Eviriawan, Eviriawan Golok Jaya, La Ode Muhammad Hikma Hikma, Hikma Ika Purwanti Ningrum, Ika Purwanti Isnawaty Isnawaty, Isnawaty Jaya, Laode Muhammad Golok Jumadil Nangi, Jumadil Karmila Sari Kasim, Nurdian La Aba La Surimi, La LM. Bahtiar Aksara, LM. Bahtiar Makmun, Wa Ode Wahyuni Muh. Ihsan Sarita, Muh. Ihsan Muharramah, Alfi Zahrah Mutmainnah Muchtar Natalis Ransi, Natalis Noor Akhmad Setiawan Noorhasanah Zainuddin Nur Ilahi, Syaban Barokah Nurfitria Ningsi Oyas Wahyunggoro Prajono, Rahmat Pratama, Elko Dedy Purnama, Ika Purwanti Ningrum Putri Angraini Aziz Rosalina Rosalina Sarita, Muhammad Ihsan Shalihah, Rifa'atus Suci Natasiya, Chindy Elfiana Sumiarni Moka Sutardi Sutardi Syahabuddin, Syahabuddin Uniadi Mangidi Wa Ode Siti Nur Alam Yuwanda Purnamasari Pasrun Zaria, Hashimatul