Articles
<![CDATA[Klasifikasi Citra Alat Musik Marakas, Gitar, dan Drum Menggunakan Metode K-Means dan GLCM ]]>
<![CDATA[salim, alfajri]]>;
<![CDATA[Ramadhanu, Agung]]>
<![CDATA[ Jurnal Teknologi Dan Sistem Informasi Bisnis Vol 7 No 4 (2025): Oktober 2025 ]]>
Publisher : <![CDATA[Prodi Sistem Informasi Universitas Dharma Andalas ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.47233/jteksis.v7i4.2265
<![CDATA[The development of digital image processing technology enables automatic object identification with high accuracy. This study aims to classify images of musical instruments, namely maracas, guitars, and drums, using a combination of K-Means-based color segmentation and Gray Level Co-Occurrence Matrix (GLCM) feature extraction. The process begins with converting RGB images into the Lab color space, followed by object segmentation using the K-Means clustering algorithm to separate the main object from the background. Subsequently, shape features (metric, eccentricity) and texture features (contrast, correlation, energy, homogeneity) are extracted using GLCM. The extracted features are then compared with a feature database using a distance-based approach to determine the object class. Experimental results show that the system can successfully recognize maracas, guitar, and drum images with a satisfactory accuracy level. This research demonstrates that the combination of K-Means and GLCM methods can serve as an effective approach for musical instrument image classification and has the potential to be further developed for object recognition in other fields]]>
<![CDATA[PENINGKATAN METODE MEDIAN FILTER UNTUK IDENTIFIKASI DAN AKURASI JENIS PISANG EMAS DAN PISANG KAPAS ]]>
<![CDATA[Chan, Fajri Rinaldi]]>;
<![CDATA[Yanti, Rahma]]>;
<![CDATA[Ramadhanu, Agung]]>
<![CDATA[ JOISIE (Journal Of Information Systems And Informatics Engineering) Vol 8 No 2 (2024) ]]>
Publisher : <![CDATA[Institut Bisnis dan Teknologi Pelita Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.35145/joisie.v8i2.4767
<![CDATA[Pengembangan teknologi dalam bidang pertanian telah membawa dampak signifikan, terutama dalam proses identifikasi dan klasifikasi hasil pertanian. Salah satu inovasi yang berpotensi meningkatkan efisiensi ini adalah teknologi pengolahan citra digital. Pisang, sebagai komoditas pertanian yang penting di Indonesia, memerlukan akurasi tinggi dalam klasifikasi, khususnya dalam membedakan jenis-jenis seperti Pisang Emas dan Pisang Kapas yang memiliki karakteristik visual mirip. Untuk itu, penelitian ini fokus pada peningkatan metode pengolahan citra untuk membedakan kedua jenis pisang tersebut. Metode yang digunakan adalah Median Filter, yang efektif mengurangi noise pada citra, namun terbukti kurang akurat dalam kasus dengan kemiripan visual tinggi. Penelitian ini bertujuan untuk mengembangkan dan menguji metode Median Filter yang ditingkatkan untuk meningkatkan akurasi dalam identifikasi jenis Pisang Emas dan Pisang Kapas. Hasil penelitian menunjukkan bahwa dengan peningkatan tersebut, tingkat akurasi identifikasi meningkat secara signifikan, mencapai 98% pada 35 citra yang diuji. Temuan ini membuka potensi untuk penerapan teknologi pengolahan citra dalam sistem klasifikasi otomatis di sektor pertanian, terutama dalam memastikan kualitas dan efisiensi distribusi produk pertanian.]]>
<![CDATA[Implementasi Algoritma K-Means Pada Pengolahan Citra Untuk Deteksi Bentuk Dan Material Gelas ]]>
<![CDATA[putri, kamila amaliah]]>;
<![CDATA[Ramadhanu, Agung]]>
<![CDATA[ Jurnal Teknologi Dan Sistem Informasi Bisnis Vol 7 No 4 (2025): Oktober 2025 ]]>
Publisher : <![CDATA[Prodi Sistem Informasi Universitas Dharma Andalas ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.47233/jteksis.v7i4.2267
<![CDATA[Digital image processing is a branch of computer science that plays a significant role in automating object identification processes. This study presents the implementation of the K-Means Clustering algorithm for detecting the shape and material of drinking glasses based on digital images. The research methodology involves several stages, including image data collection, color space conversion from RGB to Lab, image segmentation using K-Means Clustering, and feature extraction of shape and texture. The K-Means algorithm is employed to cluster image pixels into multiple groups according to color similarity and texture patterns, thereby enabling the classification of glasses based on their material (glass, plastic, or clay) and shape. The experimental results demonstrate that the proposed method achieves a high level of accuracy in object identification and can be effectively implemented within a Matlab-based system. Consequently, this approach offers a potential solution for the automation of drinking container identification in various industrial and research applications.]]>
<![CDATA[Hybrid Data Mining with the Combination of K-Means Algorithm and C4.5 to Predict Student Achievement ]]>
<![CDATA[Ramadhanu, Agung]]>;
<![CDATA[Defit, Sarjon]]>;
<![CDATA[Kareem, Shahab Wahhab]]>
<![CDATA[ International Journal of Artificial Intelligence Research Vol 5, No 2 (2021): December 2021 ]]>
Publisher : <![CDATA[Universitas Dharma Wacana ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (480.052 KB)
|
DOI: 10.29099/ijair.v6i1.225
<![CDATA[Getting academic achievement is the dream of every student who studies at higher education, especially undergraduate level. Undergraduate students aspire to the highest achievement (champion) at the last achievement of their studies. However, students cannot predict whether these students with the habits that have been done and the current conditions will make them excel or not. Apart from that, of course, students also want to know what factors and conditions influence the achievement the most. The objective to be achieved in this research is how to predict which number of students among them are predicted to excel (champion) at the end of the semester with a combination of the K-Means and C4.5 methods. Besides, the purpose of this study reveals how the K-Means algorithm performs data clustering of student data who will excel or not and how the C4.5 algorithm predicts students who have been grouped. Data processing in this study uses the Rapid Miner software version 9.7.002. The result of this research is that it is easier to group data in numerical form than data in polynomial form. Other results in this study were that out of 100 students, 27 students (27%) were predicted to excel (champions) and 73 (73%) did not achieve (not champions).]]>
<![CDATA[Penerapan Algoritma K-Means Clustering dalam Segmentasi Citra Sayuran: Wortel, Kol, dan Terong Berbasis Matlab ]]>
<![CDATA[atiqah, sri]]>;
<![CDATA[Ramadhanu, Agung]]>
<![CDATA[ Jurnal Sains dan Teknologi (JSIT) Vol. 5 No. 3 (2025): September-Desember ]]>
Publisher : <![CDATA[CV. Information Technology Training Center - Indonesia (ITTC) ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.47233/jsit.v5i3.3622
<![CDATA[The process of identifying vegetable quality faces a major challenge due to its reliance on manual inspection, which istime-consuming, inconsistent, and highly dependent on the observer’s subjectivity. This study aims to examine theapplication of the K-Means Clustering algorithm in the digital image segmentation of three types of vegetables—carrots,cabbages, and eggplants—to evaluate the algorithm’s ability to separate the main object from the background and assessidentification accuracy based on shape and texture features. The research employs an exploratory method with aconceptual prototype approach. The dataset consists of 30 digital images (10 for each vegetable type) obtained throughdirect image acquisition under controlled lighting conditions. All images were processed using MATLAB R2023a andconverted from the RGB color space to the CIELab (Lab) color space* prior to segmentation using the K-Meansalgorithm. After segmentation, shape features (area, perimeter, eccentricity) and texture features based on the Gray LevelCo-occurrence Matrix (GLCM) were extracted. Quantitative analysis was conducted to evaluate the segmentationaccuracy and the effectiveness of object separation. The results show that the K-Means algorithm successfully separatedthe main objects from the background with 100% accuracy and high consistency. This approach is considered feasible asan initial model for an automatic identification system for agricultural commodities based on digital imagery, withpotential for further development through dataset expansion and comparison with other algorithms.]]>
<![CDATA[Implementasi Image Processing untuk Klasifikasi Citra Sapi, Gajah, dan Iguana dengan K-Means ]]>
<![CDATA[Maharani, Filsha Rifi]]>;
<![CDATA[Ramadhanu, Agung]]>
<![CDATA[ Jurnal Sains dan Teknologi (JSIT) Vol. 5 No. 3 (2025): September-Desember ]]>
Publisher : <![CDATA[CV. Information Technology Training Center - Indonesia (ITTC) ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.47233/jsit.v5i3.3626
<![CDATA[The rapid technological developments have made significant contributions in various fields, but the main problem faced in animal research and conservation is the limitations of manual identification methods that are time-consuming and prone to human error. In addition, visual differences between species often cause difficulties in the process of accurately classifying animal images. This study aims to develop an automatic classification system based on the K-Means Clustering method in identifying three animal species, namely cattle (Bos taurus), elephants (Loxodonta africana and Elephas maximus), and iguanas (Iguanidae). The research method includes several main stages, namely image acquisition, preprocessing by converting RGB to LAB color space, image segmentation using the K-Means Clustering algorithm, and extraction of shape and texture features with Eccentricity, Energy, and Homogeneity parameters. The dataset used consists of 30 images, 10 for each species. The results were analyzed using a confusion matrix to measure the level of classification accuracy. The results showed that the system was able to classify all images with an accuracy level of 100% without any misclassification between classes. Confusion matrix analysis reinforced these findings by demonstrating fully correct identification for all samples. These findings demonstrate the effectiveness of the K-Means Clustering method in grouping animal images with striking visual differences and offer potential applications in conservation and intelligent farming systems.]]>
<![CDATA[Klasifikasi Jenis Kendaraan (Helikopter, Mobil, Motor) Menggunakan Metode K-Means Clustering pada Pengolahan Citra ]]>
<![CDATA[Nurjannah, Farah]]>;
<![CDATA[Ramadhanu, Agung]]>
<![CDATA[ Jurnal Sains dan Teknologi (JSIT) Vol. 5 No. 3 (2025): September-Desember ]]>
Publisher : <![CDATA[CV. Information Technology Training Center - Indonesia (ITTC) ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.47233/jsit.v5i3.3631
<![CDATA[Digital image-based vehicle type classification still faces obstacles because the identification process is generally done manually, so it takes a long time and has the potential to result in object recognition errors. This condition indicates the need for an image processing-based automation system that is able to recognize vehicle types accurately and efficiently. This study aims to develop a vehicle image classification system (helicopters, cars, and motorcycles) using the K-Means Clustering method to improve identification accuracy based on visual characteristics. This study was conducted with a quantitative approach through four main stages, namely image preprocessing (RGB to LAB conversion and size normalization), segmentation using the K-Means Clustering algorithm, extraction of shape features (metric, eccentricity) and texture (contrast, correlation, energy, homogeneity) based on Gray Level Co-occurrence Matrix (GLCM), and evaluation of accuracy using a confusion matrix. The research dataset consists of 30 vehicle images divided equally for each class. The results show that the combination of the K-Means Clustering method and GLCM feature extraction is able to classify three types of vehicles with an accuracy level reaching 100%. These findings prove that the K-Means method is effective for vehicle image recognition automation, and can be used as a basis for developing artificial intelligence-based visual identification systems in the future.]]>
<![CDATA[A Implementasi K-Means Clustering dalam Segmentasi Citra Hewan pada Kucing, Kambing, dan Burung ]]>
<![CDATA[Delvi, Syerlin Aprilia]]>;
<![CDATA[Ramadhanu, Agung]]>
<![CDATA[ Jurnal Sains dan Teknologi (JSIT) Vol. 5 No. 3 (2025): September-Desember ]]>
Publisher : <![CDATA[CV. Information Technology Training Center - Indonesia (ITTC) ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.47233/jsit.v5i3.3632
<![CDATA[Image segmentation is one of the most important challenges in digital image processing because it determines the successof separating the main object from the background so that visual information can be further analyzed. The problem ariseswhen the object has complex color, texture, and shape characteristics, as in animal images that often have color patternssimilar to their surroundings, making object boundaries difficult to distinguish clearly. This study aims to apply the KMeans Clustering method in the process of animal image segmentation—specifically for cats, goats, and birds—and toevaluate its effectiveness in identifying and separating the main object from the background. The method used is the KMeans Clustering algorithm, an unsupervised learning technique that groups image pixels based on color similarity in theRGB color space through an iterative process until centroid stability is achieved and clusters representing different imageregions are formed. The results show that the K-Means method can produce good segmentation performance for imageswith uniform lighting and simple backgrounds but experiences a decrease in accuracy when the object’s color is similar toits environment. Overall, this algorithm is effective, simple, and can serve as a foundation for developing automatedanimal image identification and classification systems]]>
<![CDATA[Penerapan K-Means Clustering untuk Klasifikasi Citra Aksesoris Ekstraksi Warna dan Tekstur GLCM ]]>
<![CDATA[Zubaidah, Rima Puti]]>;
<![CDATA[Ramadhanu, Agung]]>
<![CDATA[ Jurnal Sains dan Teknologi (JSIT) Vol. 5 No. 3 (2025): September-Desember ]]>
Publisher : <![CDATA[CV. Information Technology Training Center - Indonesia (ITTC) ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.47233/jsit.v5i3.3633
<![CDATA[The main problem in accessory image recognition lies in the similarity of physical shapes among objects such as bracelets, necklaces, and earrings, which often causes difficulties in the automatic classification process. This study aims to develop an accessory image classification system capable of accurately grouping objects based on a combination of color and texture features using the K-Means Clustering algorithm. The method used includes several preprocessing stages such as resizing images to ensure uniform dimensions and normalizing pixel values to achieve consistent data scales. Color features were extracted using RGB and HSV histograms to represent color variations, while texture features were obtained through the Gray Level Co-occurrence Matrix (GLCM) method with four parameters: contrast, correlation, energy, and homogeneity. All extracted features were then combined and analyzed using the K-Means algorithm with k=3, corresponding to the number of accessory categories. The results show that combining color and texture features produces a more optimal cluster separation compared to using single-feature extraction. The K-Means algorithm successfully grouped accessory images according to their respective categories with high consistency. These findings have potential applications in digital catalog management systems and product recommendation systems on e-commerce platforms.]]>
<![CDATA[Penerapan K-Means Clustering Pada Pengolahan Citra Jam Digital, Analog dan Monograph dengan Matlab ]]>
<![CDATA[Dinantia, Triend]]>;
<![CDATA[Ramadhanu, Agung]]>
<![CDATA[ Jurnal Sains dan Teknologi (JSIT) Vol. 5 No. 3 (2025): September-Desember ]]>
Publisher : <![CDATA[CV. Information Technology Training Center - Indonesia (ITTC) ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.47233/jsit.v5i3.3634
<![CDATA[Manual grouping of clock types is time-consuming and prone to errors, necessitating an automatic method to accuratelyclassify digital, analog, and chronograph clocks. This study aims to implement the K-Means Clustering method ingrouping clock types using image processing techniques with Matlab. The applied method involves image processing withcolor space conversion from RGB to LAB, texture feature extraction using Gray-Level Co-occurrence Matrix (GLCM),and grouping using K-Means Clustering algorithm. Analysis was performed by calculating silhouette coefficient andDavies-Bouldin Index to evaluate cluster quality. Results show three clusters formed: analog clocks, digital clocks, andchronograph clocks with 99% accuracy, where 30 out of 30 image data were correctly identified. K-Means Clusteringmethod is proven effective and accurate in determining clock categories.]]>
