Lukman Syafie

Authors

Azis, Huzain; Nirmala; Syafie, Lukman; Herman; Fattah Farniwati; Hasanuddin,Tasrif, Faculty Of Computer Science, Universitas Muslim Indonesia, Makassar, Indonesia

Abstract

This investigation constitutes a noteworthy progression in the advancement of more sophisticated and precise botanical image analysis. The primary objective of this inquiry is to confront the difficulties associated with the categorization of Calendula and Coreopsis flowers through the application of diverse segmentation techniques and classification algorithms. In this experiment, we employed the Canny edge detection, thresholding, mean shift, and Otsu methods to process flower images before applying Naïve Bayes, K-Nearest Neighbors, Support Vector Machine, and Decision Tree algorithms for classification. Enhanced comprehension of the integration of distinct segmentation techniques with varied classification algorithms is attained. We scrutinized accuracy, precision, recall, and F1 measure across diverse segmentation scenarios to assess the efficacy of these algorithms. Our principal discoveries consistently affirm that the Decision Tree algorithm attains the utmost accuracy levels in flower classification when coupled with mean shift segmentation, underscoring its noteworthy proficiency in this endeavor. The pivotal role of an optimal amalgamation of segmentation techniques and classification algorithms in augmenting flower recognition is underscored, thereby charting the course for subsequent investigations into the integration of diverse segmentation methods with advanced classification algorithms. This study's outcomes wield a favorable influence on the domain of botany and image analysis at large, offering support to researchers and scientists in achieving a more precise understanding and classification of plant species.

Related SDGs

Authors

Satra, Ramdan; Syafie, Lukman, Universitas Muslim Indonesia

Abstract

Nowadays, Information technology is rapidly developing including computer network technology. One technology that plays an important role in the field of computer networks is server virtualization. Server virtualization technology will be highly supportive of IT development in an organization considering the potential for a processor with more than one core in a server that can be utilized to run applications and services simultaneously using virtualization techniques on a computer server. The application of server virtualization technology will increase efficiency and optimize the utilization of more than one core processor. The implementation of server virtualization will also save on electricity costs because it uses only one or fewer servers. This study performs a comparison analysis of server virtualization using Kernel-based Virtual Machine (KVM) and Linux Container (LXC) on PROXMOX. Based on the results obtained, it can be concluded that the performance of the LXC-based virtual servers is superior to KVM either in terms of running server time, time duration of virtual servers creation, or the usage of hardware resources. The implementation of LXC-based virtual servers is highly recommended to be implemented in the local network of an organization.

Related SDGs

Authors

Syafie, Lukman; Satra, Ramdan; Azis, Huzain, Universitas Muslim Indonesia

Abstract

Hybrid learning model is the combination of onsite learning and online learning model. Hybrid learning model is an interesting issue in order to balance the drastically change of learning model to the learning model of ICT-based. This study was analyze the effectiveness of hybrid learning model on the student. The test were carried out before and after the learning model applied. The data was picked up from the questionnaire. The sample consisted of 40 students. By using statistical analysis, we obtain that the average difference between the pre-test and post-test scores was -29.03175. In the t-test, Ho: pre-test=post-test gives a T value=-33,890 with 39 degrees of freedom. The p-value for the two-tailed test is 0.000 less than=0.05. It was proved that the average pre-test and post-test scores are significantly different. It means the application of the hybrid model learning is effective. The implication of research is to encourage the use of e-learning technology to improve academic learning outcomes.

Related SDGs

Authors

Sumi, Amin Siddiq; Purnawansyah; Syafie, Lukman, Fakultas Ilmu Komputer Universitas Muslim Indonesia Makassar, Indonesia

Abstract

Kebutuhan untuk menemukan informasi yang berguna dan cepat dalam suatu data yang besar sangat dibutuhkan. Karena kompleksitas data yang begitu banyak maka diperlukan suatu metode atau cara untuk dapat mencari suatu informasi yang diperlukan. Untuk melakukan pencarian sebuah data atau informasi tidak terlepas dari pencocokan string dimana dari hasil pencocokan inilah akan ditemukan pola kalimat yang dicari. Dalam penelitian ini membahas tentang penerapan algoritma brute force dalam melakukan pencocokan sebuah string. Algoritma ini melakukan pencocokan string dengan menggeser satu persatu pattern dan menyesuaikannya dengan teks hingga antara pattern dan teks memiliki pola yang sama. Hasil analisis dari penelitian ini berupa uji coba pencocokan string dengan algoritma brute force dengan studi kasus menggunakan mesin pencarian (search engine) dengan bahasa pemrograman PHP untuk pencocokan string.

Related SDGs

Authors

Purnawansyah; Syafie, Lukman; Herdianti, Universitas Muslim Indonesia

Abstract

Shallots are one of the most widely produced crops in Enrekang Regency. The obstacle in cultivation is the presence of disease in the plant which can reduce production yields. We can recognize this disease from the spots on the leaves because these spots have unique color and texture characteristics. The aim of this research is to determine the results of the classification of shallot plant diseases which focuses on purple spot and moler disease. The classification algorithms used are CNN and SVM with RBF, linear, sigmoid and polynomial kernels. The feature extraction method used is Gray Level Co-occurance Matrix (GLCM). The analysis was carried out using 320 datasets with 2 classes, namely, purple spot disease and moler disease, each class has 160 datasets. The test results show that the CNN and SVM methods with RBF, linear and polynomial kernels get accuracy, precision, recall and F1 scores of 100% respectively. Meanwhile, the SVM method on the sigmoid kernel using texture feature extraction with the GLCM method states that the accuracy value is 75%, precision 75%, recall 73% and F1-Score 74%. So these results state that the Sigmoid method using GLCM feature extraction has the lowest value among other methods

Related SDGs

Authors

Satra, Ramdan; Syafie, Lukman, Universitas Muslim Indonesia, Makassar, Indonesia; Nidhom, Ahmad Mursyidun, National University of Malaya

Abstract

One of the problems in providing infrastructure is the lack of interest in managing infrastructure. AWS Lambda is a FaaS (Function as a Service) service that allows users to run code automatically in an environment managed by Amazon Web Services. In this study, the method used is to collect data on code execution time at various input sizes, then perform an analysis of the factors that affect execution time. Furthermore, optimization is carried out by selecting the appropriate memory size and proper coding techniques to improve performance. The results show that optimizing memory size and coding can improve code execution time performance by up to 30%, depending on the type of service used. This can help AWS Lambda users improve code performance and save on operational costs.

Related SDGs

Authors

Azis, Huzain; Nasrullah, Departement of Computer Science, Universitas Muslim Indonesia, Makassar, Indonesia; Abdullah Munaisyah; Ismail, Suriana, Malaysian Institute of Information Technology, Universiti Kuala Lumpur, Kuala Lumpur, Malaysia; Purnawansyah; Syafie, Lukman, , Departement of Computer Science, Universitas Muslim Indonesia, Makassar, Indonesia

Abstract

The use of Unmanned Aerial Vehicles (UAVs) in aerial imaging is expanding rapidly, particularly in traffic monitoring and intelligent transportation systems. Detecting small and occluded vehicles in aerial images poses significant challenges due to varying resolutions and obstructions like buildings or trees. This study seeks to enhance vehicle detection accuracy by improving You Only Look Once (YOLO) models, with a focus on small and occluded object detection. Utilizing the COWC-M dataset and advanced data augmentation techniques such as Mosaic Augmentation, this research evaluates multiple YOLO variants. The YOLOv8-L model achieved the highest mAP50 score of 0.9899, demonstrating superior detection accuracy for small objects. Additionally, the YOLOv10-L model outperformed others with the best mAP50–95 score of 0.8715, indicating strong results across different intersection-over-union (IoU) ranges. Compared to YOLO-RTUAV, which achieved an mAP50 of 0.9353, the newer YOLO models provide significant improvements in both precision and recall. These findings contribute to the development of highly efficient, real-time vehicle detection systems suitable for large-scale surveillance applications in complex environments.

Related SDGs

Authors

Satra, Ramdan; Syafie, Lukman, Universitas Muslim Indonesia

Abstract

Smk Latanro Enrekang merupakan salah satu sekolah kejuruan yang berada di kota Enrekang. Saat ini ada beberapa guru dan siswa yang memanfaatkan jaringan internet dari sekolah. Namun manajemen bandwidth di sekolah ini belum dapat digunakan secara optimal dalam mencukupi kebutuhan pengguna, dimana ketika banyaknya pengguna akses internet pada saat jam belajar dan kepentingan administrasi akan menyebabkan penggunaan banwdwith menjadi lambat. Salah satu cara untuk mengurangi penurunan performansi adalah dengan mengatur pembagian bandwidth antar pengguna dengan tepat. Penelitian ini bertujuan untuk mengukur performansi jaringan di SMK Latanro Enrekang dengan metode Per Connection Queue (PCQ) dan Hierarchical Token Bucket (HTB) serta menganalisa parameter pengukuran performansi jaringan dengan menggunakan Quality of Service (QoS). Hasil penelitian menunjukkan nilai rata-rata throughput dengan metode PCQ 1,2 Mbps dengan kategori TIPHON “Bagus” serta nilai rata-rata throughput dengan metode HTB 1,0 Mbps dengan kategori TIPHON “Bagus”, nilai rata-rata packet loss dengan metode PCQ 0,3% dengan kategori TIPHON “Sangat Bagus” serta nilai rata-rata packet loss dengan metode HTB 0,3% dengan kategori TIPHON “Sangat Bagus” dan nilai rata-rata delay dengan metode PCQ 6.42 ms dengan kategori TIPHON “Sangat Bagus” serta nilai rata-rata delay dengan metode HTB 5.92 ms dengan kategoriTIPHON “Sangat Bagus”

Related SDGs

Authors

Purnawansyah; Herdianti; Widyawati, Dewi, Universitas Muslim Indonesia

Abstract

Tanaman herbal menunjukkan variasi berbagai ukuran dan bentuk yang berbeda untuk setiap jenis. Penelitian ini bertujuan untuk mengklasifikasikan citra daun dari daun katuk (Sauropus Androgynus) dan daun kelor (Moringa). Dalam penelitian ini digunakan Gray Level Co-Occurrence Matrix (GLCM) untuk mengektraksi fitur contrast, correlation, homogeneity, dissimilarity, dan Angular Second Moment (ASM). Adapun pada klasifikasi diterapkan metode Convolutional Neural Network (CNN) dan Naïve Bayes dengan kernel Gaussian, multinomial, dan Bernoulli. Jumlah citra yang digunakan dalam riset ini adalah 480 citra, dengan perincian 80% untuk data training dan 20% sebagai data testing. Berdasarkan hasil pengujian dan perbandingan yang telah dilakukan didapatkan kesimpulan bahwa penerapan metode CNN tanpa ekstraksi fitur terbukti lebih efisien dalam proses klasifikasi citra daun herbal, dengan nilai precision, recall, f1-score dan accuracy mencapai 98% pada situasi cahaya terang

Related SDGs

Authors

Syafie, Lukman; Azis, Huzain; Admojo, Fadhilah Tangguh, Universiti Kuala Lumpur, 50250 Kuala Lumpur, Malaysia

Abstract

Introduction: The preservation of Javanese script as part of Indonesia’s cultural heritage is increasingly urgent in the digital era, especially due to declining literacy among younger generations. This study aims to explore the effectiveness of YOLOv8, an advanced object detection algorithm, for recognizing handwritten Javanese numerals to support efforts in cultural digitization and education. Methods: A dataset of 2,790 handwritten Javanese numerals (0–9) was collected from 93 respondents. Each numeral was manually annotated using bounding boxes via the MakeSense.ai platform. The YOLOv8 model was trained using 80% of the data and validated on the remaining 20%. Training was performed in the PyTorch framework with data augmentation techniques to increase robustness. Model performance was evaluated using precision, recall, F1-score, and mean Average Precision (mAP), along with visualization through confidence curves and confusion matrices. Results: The model achieved a high validation precision of 88.3%, recall of 89.1%, and mAP of 0.88 at IoU 0.90. F1-score peaked at a confidence threshold of 0.89, while certain numerals like 'six' and 'nine' achieved near-perfect detection. Visualizations confirmed the model’s ability to accurately classify and localize characters in both training and unseen data. Minor misclassifications occurred between visually similar numerals. Conclusions: YOLOv8 demonstrates high effectiveness in recognizing handwritten Javanese numerals and holds significant potential for digital heritage preservation. Future work should focus on expanding the dataset, improving generalization under varied conditions, and integrating this model into educational tools and augmented reality applications for interactive learning.

Related SDGs

Authors

Salim, Yulita; Manga', Abdul Rachman; Azis, Huzain; Syafie, Lukman, Universitas Muslim Indonesia

Abstract

Universitas Muslim Indonesia (UMI) has developed several applications for managing the campus's digital information and management systems, both internally and externally. However, several applications were previously created in the development of information system applications at UMI. However, these applications were not well-suited for long-term use due to their complexity and lack of integration. Therefore, UMI aims to create a fully integrated and well-managed campus information system by implementing the concept of microservices. The microservices approach involves dividing large applications into smaller interconnected components. This approach facilitates the management of application systems and enables better integration. Moreover, the microservices approach simplifies system maintenance for application developers, as each application is separated into smaller components

Related SDGs

Authors

Syafie, Lukman, Universiti Kuala Lumpur, 50250 Kuala Lumpur, Malaysia; Rismayanti, Universitas Negeri Malang, Kota Malang, Jawa Timur 65145, Indonesia

Abstract

Benign Prostatic Hyperplasia (BPH) is a prevalent non-cancerous enlargement of the prostate gland in aging men, often requiring early diagnosis to prevent urinary complications and improve patient outcomes. Traditional diagnostic procedures are limited by subjectivity and accessibility, especially in under-resourced regions. This study proposes an automated diagnostic approach using a deep learning model based on DenseNet121 to classify RGB prostate images into BPH and normal categories. A region-specific dataset consisting of 176 labeled RGB images, collected from a clinical facility in Bangladesh, was used to train and evaluate the model. Pre-processingincluded image resizing, normalization, and data augmentation to enhance generalization. Transfer learning was employed to fine-tune the model, which was trained over 10 epochs using the Adam optimizer and cross-entropy loss. The model achieved a best validation accuracy of 94.12%, with a recall of 72.2% for BPH detection, demonstrating its ability to identify pathological patterns in simple imaging modalities. Despite challenges such as dataset size and imbalance, the findings indicate that RGB image-based deep learning models can support clinical diagnosis of BPH in low-resource settings. This work contributes a lightweight, accessible solution for prostate disease screening and provides a foundation for future research on scalable AI-assisted diagnostics

Related SDGs

Authors

Herman; Syafie, Lukman; Irawati; Hayati, Lilis Nur; Harlinda; Universitas Muslim Indonesia, Indonesia

Abstract

Scheduling lectures is not something easy, considering many factors that must be considered. The factors that must be considered are the courses that will be held, the space available, the lecturers, the suitability of the credits with the duration of courses, the availability of lecturers' time, and so on. One algorithm in the field of computer science that can be used in lecture scheduling automation is Genetic Algorithms. Genetic Algorithms can provide the best solution from several solutions in handling scheduling problems and the selksi method used is roulette wheel. This study produces a scheduling system that can work automatically or independently which can produce optimal lecture schedules by applying Genetic Algorithms. Based on the results of testing, the resulting system can schedule lectures correctly and consider the time of lecturers. In this study, the roulette wheel selection method was more effective in producing the best individuals than the rank selection method.

Related SDGs

Authors

Irawati; Syafie, Lukman, Universitas Muslim Indonesia

Abstract

Pada awal bulan Maret 2023 Menkopolhukan, Bapak Mahfud MD menyampaikan bahwasanya adanya dugaan transaksi yang mencurigakan yang terjadi di Kemenkeu berdasarkan dari laporan temuan PPATK kepada Mahfud MD, sontak hal tersebut menjadi sorotan di berbagai media sosial salah satunya Twitter, beragam tweet yang dilontarkan oleh netizen di Twitter, ada yang memberikan tweet positif, negatif, dan juga netral. Pada penelitian ini bertujuan untuk membandingkan metode Naïve Bayes dan SVM dalam analisis sentimen netizen Twitter terhadap isu Kemenkeu. Penelitian ini menunjukkan bahwa sentimen netizen didominasi dengan sentimen negatif kemudian diikuti sentimen positif, dan terakhir sentimen netral. Hasil pengujian klasifikasi terhadap kedua metode tersebut didapatkan dari membagi secara acak dataset menjadi dua bagian yaitu data latih dan data uji dengan rasio 70:30. Setelah dilakukan pengujian ditemukan bahwa Naïve Bayes mendapatkan nilai akurasi sebesar 71,7%, presisi sebesar 55,2%, recall sebesar 45,3%, dan f1-score sebesar 44,8%, sedangkan pada SVM mendapatkan nilai akurasi sebesar 74%, presisi sebesar 87,8%, recall sebesar 49,1%, dan f1-score sebesar 49,8%.

Related SDGs

Authors

Hayati, Lilis Nur; Syafie, Lukman, Universitas Muslim Indonesia

Abstract

Penentuan penilaian kaligrafi terbaik masih dilakukan secara manual (tulis tangan) karena belum adanya sistem penilaian secara berbasis website. Demikian juga belum ada penentuan metode dalam menentukan pengambilan keputusan untuk menentukan kaligrafi terbaik, dimana guru yang mengajar pada mata pelajaran khat sangat membutuhkan sebuah aplikasi atau sistem yang mendukung penilaian kaligrafi terbaik dari para santri di pondok pesantren. Aplikasi atau sistem yang akan dibuat oleh peneliti ini akan menentukan penilaian setiap kriteria-kriteria. Kriteria pada jenis khat itu ditentukan dari kaidah, warna, motif, kerapian, dan nilai estetika. Berdasarkan hal tersebut untuk menentukan kaligrafi terbaik sesuai dengan kriteria yang akan ditentukan, maka penelitian ini menggunakan metode Simple Additive Weighting (SAW). Metode SAW atau yang dikenal penjumlahan terbobot yang merupakan metode yang digunakan untuk mencari nilai bobot pada rating kinerja setiap alternatif pada setiap atribut. Dalam perhitungannya membutuhkan proses normalisasi matriks keputusan ke suatu skala yang akan dibandingkan dengan semua kriteria dari setiap alternative. Dengan adanya analisis penerapan metode SAW untuk pemilihan kaligrafi terbaik, dapat mempermudah, mempercepat serta memberikan hasil rekomendasi yang akurat untuk penilaian kaligrafi terbaik sehingga dapat membantu dalam proses pengambilan keputusan dan menentukan kaligrafi yang terbaik yang dibuat oleh santri. Dengan ini hasil pengujian black box (beta) dari cara perhitungan tersebut diperoleh skor dan pernyataan sebagai berikut: soal nomor 1 = 4,60%, soal nomor 2 = 5,00%, soal nomor 3 = 4,20 %, soal nomor 4 = 4,80%, soal nomor 5 = 4,80%, soal nomor 6 = 4,90%. Maka diperoleh nilai rata-rata 4,71% dengan nilai indeks 78,50% yang termasuk dalam baik

Related SDGs

Authors

Syafie, Lukman; Herman; As' ad, Ihwana; Universitas Muslim Indonesia

Abstract

This community service program aims to improve digital literacy among elementary school students in Kedah, Malaysia through introducing robotics and Scratch programming. The main issue faced was students' limited exposure to computational thinking and STEM-based learning. Through intensive training provided by Universitas Muslim Indonesia, students from 13 schools were equipped with fundamental skills in visual programming using Scratch and basic robotics concepts. The training was officially opened by the Special Officer to the Minister of Education Malaysia and covered introduction to computational thinking, hands-on Scratch programming, and educational robotics demonstrations. Results showed significant improvement in students' understanding of programming concepts and increased enthusiasm towards technology. Additionally, an educational module was created for continued learning. The program successfully enhanced students' digital literacy and received strong appreciation from school principals who expressed interest in ongoing collaboration for similar activities.

Related SDGs

Authors

Irsana, Muhammad Alif; Fattah, Farniwati; Syafie, Lukman, Universitas Muslim Indonesia, Makassar, Indonesia

Abstract

Sejak 2019, perkuliahan di Fakultas Ilmu Komputer Universitas Muslim Indonesia (FIKOM UMI) didukung oleh sebuah aplikasi Learning Management System berbasis website yang diberi nama Kalam (kalam.umi.ac.id). Seiring berjalannya waktu, respon pengguna terbentuk sehingga mendorong perlunya analisis pengalaman pengguna sebagai dasar pertimbangan dalam perbaikan dan perkembangan lebih lanjut. Penelitian ini bertujuan untuk mengetahui pengalaman pengguna selama menggunakan LMS Kalam. Dimensi yang digunakan sesuai dengan karakteristik LMS Kalam sebagai platform Pendidikan, sehingga ada 5 dimensi yang digunakan yaitu general ux, ease of use, interactivity, engagement, assignment & assessment. Partisipan pada penelitian ini berjumlah 10 orang pengguna LMS Kalam. 50 kurva yang digambarkan partisipan dimana pada masing – masing partisipan menggambarkan 10 kurva. Berdasarkan hasil penelitian ini faktor yang berpengaruh dalam perubahan pengalaman pengguna pada LMS Kalam antara lain adalah tampilan website yang simpel, website mudah digunakan, dan akses Kalam yang sulit Ketika banyak pengguna yang aktif diwaktu yang sama

Related SDGs

Authors

Syafie, Lukman; Purnawansyah; Herman; Awangga, Narendra; Wahyudi, Ifan, Fakultas Ilmu Komputer, Universitas Muslim Indonesia

Abstract

Program pengabdian ini bertujuan meningkatkan keterampilan digital siswa di Sekolah Kebangsaan Syeikh Mohd Idris Al-Marbawi, Malaysia. Masalah utama yang dihadapi sekolah ini adalah kurangnya akses siswa terhadap komputer dan aplikasi dasar seperti Microsoft Word. Melalui pelatihan intensif yang diberikan oleh Universitas Muslim Indonesia, siswa dibekali dengan keterampilan dasar penggunaan komputer dan aplikasi Microsoft Word. Pelatihan mencakup pengenalan perangkat keras dan perangkat lunak, serta praktik penggunaan fitur Microsoft Word, mulai dari dasar hingga fitur lanjutan seperti Word Art dan pengaturan kolom.Hasil dari pelatihan ini menunjukkan peningkatan signifikan pada keterampilan digital siswa sesudah pelatihan. Selain itu, sebagai luaran dari program ini, panduan pengantar komputer yang dapat digunakan oleh siswa secara berkelanjutan. Program ini berhasil meningkatkan literasi digital siswa dan diharapkan dapat menjadi model bagi sekolah-sekolah lain. Tantangan yang dihadapi adalah tingkat pemahaman siswa yang beragam, namun hal ini diatasi dengan sesi pendampingan dan konsultasi intensif.

Related SDGs