Open Journal - Universitas Komputer Indonesia
Not a member yet
4316 research outputs found
Sort by
Comparison of K-Means, Affinity Clustering, and Mini Batch K-Means Algorithms for Market Segmentation Analysis
No full textSegmentasi pasar adalah proses membagi pasar menjadi kelompok-kelompok pembeli yang homogen berdasarkan karakteristik tertentu. Segmentasi pasar penting bagi perusahaan untuk memahami kebutuhan dan perilaku konsumennya sehingga dapat mengembangkan strategi pemasaran yang lebih efektif. Penelitian ini membandingkan tiga metode clustering, yaitu K-Means Clustering, Affinity Propagation Clustering, dan Mini Batch K-Means, dalam konteks analisis segmentasi pasar. Data yang digunakan adalah dataset marketing_campaign.csv yang terdiri dari 29 kolom dan 2240 baris. Eksperimen dilakukan untuk mengevaluasi performa ketiga metode dengan menggunakan metrik siluet. Hasil eksperimen menunjukkan bahwa Affinity Propagation menghasilkan nilai silhouette tertinggi sebesar 0.5861, diikuti oleh K-Means dengan 0.4675, dan Mini Batch K-Means dengan 0.4659. Temuan ini mengindikasikan bahwa Affinity Propagation dapat menjadi pilihan yang baik untuk analisis segmentasi pasar pada dataset tersebut. Hasil perbandingan ini memberikan wawasan tentang keunggulan dan kelemahan masing-masing metode clustering, membantu pemilih dalam memilih pendekatan yang paling sesuai untuk tujuan analisis mereka. Studi ini memberikan kontribusi pada pemahaman praktis penerapan teknik clustering dalam konteks pemasaran.Market segmentation is the process of dividing a market into homogeneous groups of buyers based on certain characteristics. Market segmentation is important for businesses to understand the needs and behaviors of their customers so that they can develop more effective marketing strategies.This study compares three clustering methods, namely K-Means Clustering, Affinity Propagation Clustering, and Mini Batch K-Means, in the context of market segmentation analysis. The data used is the marketing_campaign.csv dataset consisting of 29 columns and 2240 rows. Experiments were conducted to evaluate the performance of the three methods using the silhouette metric. The results of the experiments showed that Affinity Propagation produced the highest silhouette value of 0.5861, followed by K-Means with 0.4675, and Mini Batch K-Means with 0.4659. The finding indicates that Affinity Propagation can be a good choice for market segmentation analysis on that dataset. The results of this comparison provide insights into the strengths and weaknesses of each clustering method, helping users choose the approach that is most appropriate for their analytical goals. The study contributes to the practical understanding of the application of clustering techniques in the context of marketing
Penerapan Metode Random Forest dalam Klasifikasi Huruf BISINDO dengan Menggunakan Ekstraksi Fitur Warna dan Bentuk
Get PDFDigital image processing is a field of study that focuses on how an image can be formed, processed, and analyzed to generate useful information for humans. In this research, the utilization of digital images is implemented to classify BISINDO (Indonesian Sign Language) letters from A to Z using the Random Forest classification method. The initial stage in the classification of BISINDO letter images involves pre-processing, which includes converting RGB images to grayscale and performing segmentation through three stages: thresholding, morphology, and edge detection using the Prewitt operator. Subsequently, features such as HSV color extraction and metric shape features, as well as eccentricity, are extracted. These extracted feature values are then utilized in the classification stage of BISINDO letter images from A to Z using the Random Forest method. In this study, three data comparison scenarios were employed for testing purposes. The first scenario involved an 80:20 data ratio, which achieved a testing accuracy of 94.2%. The second scenario with a 70:30 data ratio achieved a testing accuracy of 93.6%, while the third scenario with a 60:40 data ratio had a lower accuracy of only 77.9%. Based on the results of our testing, the system developed is capable of effectively classifying BISINDO letters from A to Z using color and shape feature extraction, along with the Random Forest classification method. The best results were obtained in the data comparison scenario of 80:20, achieving an accuracy rate of 94.2%.
Keywords – BISINDO, HSV, Metric, Eccentricity, Random Forest.Pengolahan citra digital merupakan bidang ilmu yang mempelajari tentang bagaimana suatu citra dapat dibentuk, diolah, serta dianalisis sehingga menghasilkan informasi yang bermanfaat bagi manusia. Dalam penelitian ini, pemanfaatan citra digital diimplementasikan untuk melakukan klasifikasi huruf BISINDO (Bahasa Isyarat Indonesia) dari huruf A sampai Z, dengan menggunakan metode klasifikasi Random Forest. Tahap awal dalam melakukan klasifikasi citra huruf BISINDO adalah melakukan pre-processing yaitu konversi citra RGB ke grayscale, kemudian dilakukan segmentasi melalui tiga tahap yaitu thresholding, morfologi, dan pendeteksian tepi menggunakan operasi prewitt. Setelah itu peroleh nilai ekstraksi fitur warna HSV serta fitur bentuk metric dan eccentricity. Nilai dari ekstraksi fitur inilah yang akan digunakan dalam tahap pengklasifikasian citra huruf BISINDO dari A sampai Z dengan metode Random Forest. Pada penelitian ini digunakan tiga skenario perbandingan data yang diujikan, dimana pada skenario pertama yaitu perbandingan data 80:20 yang mencapai akurasi pengujian sebesar 94.2%. Kemudian untuk perbandingan data 70:30 mencapai akurasi pengujian sebesar 93.6%, sedangkan perbandingan data 60:40 lebih rendah, yaitu hanya mencapai 77.9%. Berdasarkan hasil pengujian yang kami lakukan, maka sistem yang dibuat mampu mengklasifikasikan huruf BISINDO dari A sampai Z dengan baik menggunakan ekstraksi fitur warna dan bentuk serta metode klasifikasi Random Forest, dimana hasil yang paling bagus ditunjukkan pada skenario perbandingan data 80:20 dengan tingkat akurasi sebesar 94.2%.
Kata Kunci – BISINDO, HSV, Metric, Eccentricity, Random Forest
Prototipe Sederhana Sistem Deteksi Kriminal Berbasis Internet Of Things Menggunakan Teknologi YOLOv5
Get PDFCrime is any action or thing carried out by an individual, group or community that violates the law or is a criminal act, which disturbs social balance or stability in society. One of the tools used to monitor security in various places such as homes, offices and other public places is Closed-Circuit Television (CCTV). However, even though many CCTVs have been installed, many crimes still occur due to limitations in monitoring and supervision by security officers. Therefore, developing a crime detection system on CCTV using deep learning methods is considered important to increase security and reduce crime rates. The aim of a criminal detection system is to increase security and prevent criminal acts in a certain area or place. The technology used is YOLOv5 and is supported by Internet of Things-based hardware. The system succeeded in detecting violence objects 92% of the time and robbery 91% of the time in initial testing without background. In the second background test, the system succeeded in detecting violence objects 93% of the time and robbery 53% of the time. The system succeeded in detecting violence objects 91% of the time and robbery 83% of the time in real-time testing.Kriminalitas merupakan segala tindakan atau sesuatu yang dilakukan individu, kelompok, maupun komunitas yang melanggar hukum atau suatu tindakan kejahatan, yang mengganggu keseimbangan atau stabilitas sosial dalam masyarakat. Salah satu alat yang digunakan dalam memantau keamanan di berbagai tempat seperti rumah, kantor, dan tempat umum lainnya adalah Closed-Circuit Television (CCTV). Namun, meskipun telah terpasang banyak CCTV, masih banyak kejahatan yang terjadi karena keterbatasan dalam pemantauan dan pengawasan oleh petugas keamanan. Oleh karena itu, pengembangan sistem deteksi kriminal pada CCTV menggunakan metode deep learning dianggap penting untuk meningkatkan keamanan dan menurunkan tingkat kriminalitas. Tujuan dari sistem deteksi kriminal untuk meningkatkan keamanan dan mencegah terjadinya tindak kriminal di suatu wilayah atau tempat tertentu. Teknologi yang digunakan yaitu YOLOv5 dan didukung perangkat keras berbasis Internet of Things. Sistem berhasil mendeteksi objek violence 92% dan robbery 91% dalam pengujian awal tanpa latar belakang. Pada pengujian kedua dengan latar belakang, sistem berhasil mendeteksi objek violence 93% dan robbery 53%. Sistem berhasil mendeteksi objek violence 91% dan robbery 83% pada pengujian secara real-time
Penerapan Augmented Reality pada Game Edukasi Tumbuhan Lumut untuk Siswa SMP Negeri 2 Parittiga
Get PDFKemajuan teknologi yang pesat di era saat ini memberikan peluang yang sangat baik untuk mengintegrasikan inovasi dalam sektor pendidikan. Keterlibatan teknologi dalam pembelajaran tidak hanya meningkatkan efisiensi proses belajar mengajar, tetapi juga membuka peluang untuk menciptakan pengalaman pendidikan yang lebih interaktif dan menarik bagi para siswa. Pemanfaatan augmented reality dan game edukasi diharapkan dapat membantu guru dalam memvisualisasikan benda yang berbentuk abstrak serta para siswa dapat bermain sambil belajar, sehingga mudah dijelaskan dan dimengerti oleh para siswa serta memberikan pengalaman belajar yang menarik sehinga dapat menumbuhkan motivasi belajar siswa. Penelitian ini memiliki tujuan untuk merancang aplikasi augmented reality dan permainan edukatif mengenai tumbuhan lumut yang disesuaikan dengan pembelajaran dan kebutuhan siswa SMP Negeri 2 Parittiga. Aplikasi ini akan menyediakan pengalaman belajar yang interaktif dan menyenangkan, meningkatkan motivasi belajar siswa tentang tumbuhan lumut, dan memberikan kontribusi positif terhadap kualitas pendidikan di sekolah ini. Metode pengembangan aplikasi yang digunakan adalah Game Development Life Cycle (GDLC). Pengembangan aplikasi game menggunakan Unity dengan bahasa pemrograman C# dan perancangan objek 3D dan 2D menggunakan aplikasi Blender dan Adobe Ilustrator. Berdasarkan hasil pengujian dari ahli materi mendapat hasil 92,22% yang menunjukkan aplikasi sudah menggunakan materi yang sesuai dengan pembelajaran, sedangkan untuk User Acceptance Testing yang dilakukan kepada para siswa SMP Negeri 2 Parittiga mendapat persentase kelayakan sebesar 91,53%, aplikasi berjalan dengan baik dengan tanpa adanya masalah validitas fungsi-fungsi aplikasi yang ditemukan
Sistem Informasi Manajemen Transaksi Layanan Fotografi di Qlise Photography
Get PDFThe rapid digital development has driven Qlise Photography, a provider of photography services including wedding, prewedding, and studio photography, to address the complexity in managing its services. The aim of this research is to enhance the efficiency in managing and booking photography services provided by Qlise Photography through the development of a Website-Based Information System. To tackle the challenges in managing services like wedding, prewedding, and studio photography, the primary approach adopted in this research is the waterfall method, utilizing PHP programming language and leveraging CodeIgniter Framework as the development tool. The findings of this research have positively impacted Qlise Photography, with the implementation of an optimal system. Previously manual, the process of booking photography services can now be accessed and managed efficiently through the online platform. System testing using the Black Box method and the application of the System Usability Scale (SUS) yielded a score of 77, categorizing it as GOOD, indicating a positive acceptance rate from users. This marks a significant step in improving customer experience and operational efficiency in addressing the challenges of photography services in the digital era
Perancangan Antarmuka Aplikasi Mobile Perguruan Tinggi Menggunakan Kansei Engineering (Studi Kasus: STIS Nahdatul Ulama Cianjur)
Get PDFMobile Apps program-based has given a major influence towards the education sector, specifically in general information about college, especially in stakeholder needs. On the other hand, it also assists in reading the latest events and news, the notification of class schedules, also the information of grades and attendances. The focus of this research is to analyze user preferences including increasing user satisfaction, user retention and design preferences for the interface of Sekolah Tinggi Ilmu Syariah Nahdatul Ulama College mobile app using the Kansei Engineering Type 1 method. The study used Kansei engineering method was conducted to analyze various emotional factors relating to the interface of users by comparing five specimens of college’s mobile apps. A total of twenty kansei words were found from thirty Kansei words based on the selection of UI/UX experts. The data obtained is then analyzed using multivariate statistical methods, such as Cronbach\u27s Alpha (CA), Coefficient Correlation Analysis (CCA), and Factor Analysis (FA). The result is four Kansei words that are influential and have the greatest value, namely Dynamic, Impressive, Professional, and Formal. One selected Kansei word produces recommendations for the appearance of the mobile application interface Sekolah Tinggi Ilmu Syariah Nahdatul Ulama The analysis was conducted on all participants with a focus on the "Formal" emotion concept
Language Style Used by Peter Parker in the Spiderman Movie
Get PDFThis undergraduate thesis is entitled Language Style Used by Peter Parker in the “Spider-Man” Movie. This study focused on the language style particularly to identify and analyze the type language style and function of language in Peter Parker’s utterances. The object of this study is Peter Parker’s utterances in the “Spider-Man” movie. This study used observation and documentation methods with taking note technique in collecting data. The data was analyzed using descriptive qualitative methods, means the results are explaining descriptively. The results of the analysis are presented in informal method. This study used two theories; the theory of type of language style proposed by Joos and the theory of function of language proposed by Jakobson. Based on the theory, the type of language style in this study shows three types of language style. There are formal style, consultative style, and casual style. In this study, there are types of language style which is not found, namely frozen style and intimate style. These types of language style do not exist because in the movie, the situations and Peter Parker’s utterances does not contain frozen style and intimate style. Meanwhile, the function of language in this study shows four functions of language. There are phatic function, conative function, referential function, and expressive function. There are two functions of language that are not in the movie, namely poetic function and metalingual function because it does not match the contents of the story and Peter Parker’s utterances. The result shows that Peter Parker used more casual style to communicate with other characters and expressive functions, which aimed to express Peter Parker’s emotions and feelings.
Keywords: Sociolinguistics, Type of language style, Function of languag
Didactic Value in Disney\u27s Movie Turning Red
Get PDFThis study analyzes the didactic value in the Turning red film by using a classification that divides it into: religious value, social value, moral value, and cultural value. Using qualitative descriptive s and an objective approach. The results of the study found that there were 15 data, points: 2 on religious values describing the Meilin family regarding their beliefs; 5 on social values describing the social behavior of the characters in the film; 5 on moral values regarding the good and bad actions of the characters; 3 on cultural values regarding the red panda ritual that the Meilin family underwent.Keywords: Animated movie, Didactic value, Turning Red movi
Women\u27s Language Features Found In "The Help" Movie
Get PDFThis study investigates the features, functions and differences of women’s language styles used by female characters of different skin colors in “The Help” movie. The movie was chosen because it involves many female characters and conversations among women of different races which are related to the purpose of this study. The data was collected by using documentation techniques and analyzed using qualitative methods based on the theory from Lakoff (1975) about women’s language; the formal method is used to present the analysis. The result shows there are 23 utterances identified with a total of six of women\u27s language features used by women\u27s characters, namely empty adjective, super polite form, lexical hedges, intensifier, tag question and hypercorrect grammar. Two categories of functions in the features of women\u27s language are found in this study, that is weakening and strengthening the function. However, the most used features that are useful as weakening the function of the speech, namely lexical hedges, tag questions, super polite form, and hypercorrect grammar. There are several differences in the language styles of women characters of different races in this study, such as the differences in the frequency and the features used in women’s language.
Keywords: Women’s Language, Women’s Language Features, Lakof
The Merit and Beyond; Portraying Student Exchange as Synergetic International Relations
Get PDFThe breakthrough on developing the synergy of international relations among countries is by fostering student exchange as the so-called worthwile programs that link the bilateral relationship and cultural identities. These student exchange programs accentuate the mutual liaison among the countries. It, indeed, exerts influence on students both positively and unforgettably. This research was designed in qualitative method and researcher utilized inquiry strategy of phenomenological study. Three main informants were participated in this research because they experienced the student exchange in advance. Researcher gathered the data through in-depth interview. Specifically, there were four major themes found in the research, they were 1) The lifetime experiences, 2) The challenges and barriers, 3) The problem solving, and 4) The impacts and changes. These findings highlighted the primary goal of the student exchange program itself and also fostered interconnection among the countries in forging impacts for the students as well as the country they belong to.
Keywords: Student Exchange, Synergetic Impacts, and International Relations