Garuda - Garba Rujukan Digital

IMPLEMENTASI CUSTOMER RELATIONSHIP MANAGEMENT PADA SISTEM INFORMASI PEMESANAN CAKE AND DESSERT Umar, Najirah; Rizkha, Andi Nur; Nasrullah, Nasrullah
Jurnal Teknoinfo Vol 18, No 1 (2024): Januari
Publisher : Universitas Teknokrat Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33365/jti.v18i1.2923

This study aims to implement Customer Relationship Management (CRM) in the Cake and Dessert ordering information system. The research was conducted with a focus on the use of CRM to improve customer relationships, improve operational efficiency, and improve service quality in the context of businesses engaged in making and ordering cakes and desserts. There are several problems faced, such as the promotion process has not used a marketing strategy through the website, the reach of buyers is very limited, there is often a buildup of cakes and desserts which results in many expired cakes, there is no system that records order transactions, customer data. Research Design using UML, includes model use case diagrams, activity diagrams, sequence diagrams and class diagrams. The results showed that the implementation of CRM in the Cake and Dessert ordering information system provides a number of benefits, such as increased customer interaction, more effective customer data management, optimization of the order process, and increased customer satisfaction. This research provides important insights into CRM implementation in the cake and dessert ordering industry, and can be a reference for SMES who want to introduce or improve the use of CRM in their information systemsabstract is a brief summary of a paper to help readers quickly ascertain the purpose of the study and according to research needs.

Analisis Peranan Pemilih Pemula dan Pentingnya Teknologi Digital Untuk Pemilihan Umum 2024 di Indonesia (Studi Kasus: Pemilih Pemula SMA Negeri 20 Makassar) Tamrin, Usman; RS, Asmaul Husna; Arsyad, Andi Asyhary J.; Umar, Najirah; Kurniawan, Dody
Journal of Digital Literacy and Volunteering Vol. 2 No. 2 (2024): July
Publisher : Puslitbang Akademi Relawan TIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57119/litdig.v2i2.89

This research aims to analyze the role of first-time voters, particularly high school students at SMA Negeri 20 Makassar, in facing the 2024 General Election through the utilization of digital media. The research method employed is descriptive quantitative method with the study population encompassing all students of SMA Negeri 20 Makassar, with a sample size of 208 individuals selected using random sampling method. The results of the study indicate that first-time voters can easily access political information in the current digital era through various online platforms such as social media, news websites, and political information portals. In this study, digital literacy emerges as significantly crucial in assisting students to comprehend the necessary technology and skills required to manage online information, with a success rate of digital literacy reaching 61%. The political perceptions of first-time voters are greatly influenced by social media, which serves as the primary platform. Good digital literacy enables them to access information quickly and evaluate the balance and authenticity of the information presented. Therefore, digital literacy aids students in forming critical attitudes toward political content disseminated on social media. Additionally, they also learn about the role of technology in shaping mature political views for the 2024 General Election.

Aplikasi Citra Digital untuk Klasifikasi Kematangan Buah Pepaya Ulfa Laela R; Asriayani Ismail; Raden Wirawan; Najirah Umar; Rahmat Hidayat
Prosiding SISFOTEK Vol 8 No 1 (2024): SISFOTEK VIII 2024
Publisher : Ikatan Ahli Informatika Indonesia

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

There are still many people who use the manual system by looking directly at or guessing the maturity level of papaya fruits, with classification results that are less than optimal. The purpose of this study is to design a digital image application that can be useful in distinguishing the ripeness of naturally ripe papaya fruits and carbites. This application uses 2 extraction features, namely texture and colour, for texture uses Grey Level Cooccurence Matrks (GLCM), while colour uses Hue, Saturation, Value (HSV) and K-Nearest Neighbour (K-NN) algorithm to classify. The result of this study is the creation of a digital image application, which can help distinguish the ripeness of papaya fruit from the results of the classification of natural ripe and ripe carbine. Based on the test results, 60 training data and 15 testing data were used. By producing an accuracy value of 80% on each testing data that has been carried out.

Klasifikasi Penentuan Kualitas Kayu Jati Berdasarkan Citra Digital Menggunakan Algoritma K-Nearest Neighbour Kamaruddin, Kamaruddin; Umar, Najirah; Wahyuningsih, Pujianti; Sudarsono, Firman
Jurnal Informatika dan Rekayasa Perangkat Lunak Vol 6, No 2 (2024): September
Publisher : Universitas Wahid Hasyim

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36499/jinrpl.v6i2.10722

Peningkatan permintaan terkait barang yang terbuat dari kayu tidak dapat dibatasi terutama permintaan furniture meja, lemari dan lain sebagainya. Seiiring perkembangan, membuat produksi kayu jati untuk beralih ke jenis kayu jati unggul dikarenakan masa tumbuh lebih cepat, namun kondisi tersebut membuat kualitas dari kayu jati tidak seperti jenis kayu jati tua. Kesulitan dalam melihat kualitas kayu menjadi masalah yang dihadapi oleh para pengrajin dan pihak mebel. Tujuan penelitian ini untuk menentukan kualitas jenis kayu yang dibagi menjadi 3 kategori kelas yaitu kelas A, kelas B dan kelas C. Untuk menghasilkan klasifikasi kualitas kayu maka, peneliti menggunakan metode KNN dengan melakukan segmentasi warna HSV kemudian menganalisis nilai warna tiap piksel citra berdasarkan nilai toleransi pada dimensi warna HSV. Hasil dari penelitian ini adalah dengan menggunakan 65 data latih kayu jati pada setiap kelas. Pengujian dilakukan menggunakan 27 data uji kayu jati dengan tingkat akurasi 85,19%, presisi mencapai 85,46%, recall mencapai 85,18% dan F1 score mencapai 85,3%.

Meningkatkan Kesadaran Remaja Terhadap Phishing Melalui Literasi Digital: Studi Kasus di SMK Darussalam Makassar Arsyad, Andi Asyhary J.; Tamrin, Usman; Lande, Janisa Pascawati; Umar, Najirah
Jurnal Pengabdian Literasi Digital Indonesia Vol. 3 No. 2 (2024): December
Publisher : Puslitbang Akademi Relawan TIK Indonesia (ARTIKA)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57119/abdimas.v3i2.122

Phishing attacks are among the most common and damaging cybersecurity threats, exploiting human vulnerabilities such as a lack of awareness and digital literacy. This study aims to identify effective strategies for increasing awareness of phishing attacks through digital literacy among teenagers. The research was conducted at SMK Darussalam Makassar using a descriptive quantitative method and involved 227 respondents. The findings indicate that 80% of respondents agree that digital literacy plays a significant role in reducing the impact of phishing. Digital literacy, which includes understanding technology, identifying threats, and taking protective measures, has proven effective in protecting students from phishing attacks. Based on the Protection Motivation Theory (PMT), awareness of phishing threats and the effectiveness of protective actions increase students' motivation to protect themselves. This study recommends the development of sustainable digital literacy programs, policies to reduce unnecessary internet usage, and the blocking of access to harmful websites. By improving digital literacy, the community, especially teenagers, will be better prepared to face cyber threats and safeguard their personal information.

Klasifikasi Penentuan Kualitas Kayu Jati Berdasarkan Citra Digital Menggunakan Algoritma K-Nearest Neighbour Kamaruddin, Kamaruddin; Umar, Najirah; Wahyuningsih, Pujianti; Sudarsono, Firman
Jurnal Informatika dan Rekayasa Perangkat Lunak Vol. 6 No. 2 (2024): September
Publisher : Universitas Wahid Hasyim

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

The increase in demand for goods made from wood cannot be limited, especially the demand for table furniture, cupboards and so on. Along with development, teak wood production has shifted to superior types of teak wood because the growth period is faster, but this condition means that the quality of teak wood is not like the old type of teak wood. Difficulty in seeing the quality of wood is a problem faced by craftsmen and furniture makers. The aim of this research is to determine the quality of wood species which are divided into 3 class categories, namely class A, class B and class C. To produce a classification of wood quality, researchers use the KNN method by carrying out HSV color segmentation then analyzing the color value of each image pixel based on the tolerance value on HSV color dimensions. The results of this research were using 65 teak wood training data for each class. Testing was carried out using 27 teak wood test data with an accuracy level of 85.19%, precision reaching 85.46%, recall reaching 85.18% and F1 score reaching 85.3%.

Aplikasi 3D Menggunakan Virtual Reality sebagai Media Pengenalan Museum Kota Makassar Umar, Najirah; Tahir, Zaenal; Syam, Supriadi
Jurnal Riset dan Aplikasi Mahasiswa Informatika (JRAMI) Vol 6, No 02 (2025): Jurnal Riset dan Aplikasi Mahasiswa Informatika (JRAMI)
Publisher : Universitas Indraprasta PGRI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/jrami.v6i02.11134

Penelitian ini menggali potensi aplikasi virtual reality (VR) dalam meningkatkan pengalaman pengenalan Museum Kota Makassar. Melalui penggunaan aplikasi berbasis VR, penelitian ini bertujuan untuk menciptakan simulasi interaktif dari eksibisi museum, memungkinkan pengguna untuk menjelajahi isi museum secara virtual dengan detail yang lebih mendalam. Pendekatan metodologi UML (Unified Modeling Language) digunakan untuk merancang dan mengembangkan sistem aplikasi ini. Hasil penelitian menunjukkan bahwa aplikasi Virtual Reality dapat secara signifikan meningkatkan interaksi pengunjung dengan koleksi museum, serta memperkaya pengalaman belajar mereka dengan visual yang realistis dan interaksi yang mendalam. Ini membuktikan bahwa teknologi Virtual Reality memiliki potensi besar dalam menyajikan konten edukatif dan budaya secara lebih dinamis dan menarik, khususnya bagi generasi muda.

Analisis Peranan Pemilih Pemula dan Pentingnya Teknologi Digital Untuk Pemilihan Umum 2024 di Indonesia (Studi Kasus: Pemilih Pemula SMA Negeri 20 Makassar) Tamrin, Usman; RS, Asmaul Husna; Arsyad, Andi Asyhary J.; Umar, Najirah; Kurniawan, Dody
Journal of Digital Literacy and Volunteering Vol. 2 No. 2 (2024): July
Publisher : Puslitbang Akademi Relawan TIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57119/litdig.v2i2.89

This research aims to analyze the role of first-time voters, particularly high school students at SMA Negeri 20 Makassar, in facing the 2024 General Election through the utilization of digital media. The research method employed is descriptive quantitative method with the study population encompassing all students of SMA Negeri 20 Makassar, with a sample size of 208 individuals selected using random sampling method. The results of the study indicate that first-time voters can easily access political information in the current digital era through various online platforms such as social media, news websites, and political information portals. In this study, digital literacy emerges as significantly crucial in assisting students to comprehend the necessary technology and skills required to manage online information, with a success rate of digital literacy reaching 61%. The political perceptions of first-time voters are greatly influenced by social media, which serves as the primary platform. Good digital literacy enables them to access information quickly and evaluate the balance and authenticity of the information presented. Therefore, digital literacy aids students in forming critical attitudes toward political content disseminated on social media. Additionally, they also learn about the role of technology in shaping mature political views for the 2024 General Election.

Implementasi Algoritma Learning Vector Quantization untuk Deteksi Dini Penyakit Mata Mansur, Mansur; Umar, Najirah; Zuhriyah, Sitti
Jurnal Sains dan Informatika Vol. 11 No. 1 (2025): Jurnal Sains dan Informatika
Publisher : Teknik Informatika, Politeknik Negeri Tanah Laut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34128/jsi.v11i1.907

The eye is one of the senses of human vision that is very important in human life. The lack of online eye health consultation services is often ignored by the public because it considers eye diseases not to be dangerous diseases and have no impact on everyday life. On this issue, then developed an eye disease detection system using the Learning Vector Quantization method. (LVQ). This method is capable of giving a classification of patterns that would represent a particular class. In this study, there are 25 symptoms and 10 eye diseases that will be processed in training and testing with the data being divided into training and test data. The LVQ method will perform several steps to obtain the final weight. Using the LVQ method, the parameter values obtained include Learning rate 0.1, 0.2, Iteration 1 and 2. In the accuracy test of this system, the average accuracy result received with the training data 90 Iterations 2 Learning rates 0.1, testing of the test data 19 yielded accuration of 100% and Iterating 2 Learning rate 0,2 testing of testing data 19 was accurate of 100%. which indicates that the system can function properly. So the LVQ method can be applied to the classification of eye diseases.

EVALUATION OF INDOBERT AND ROBERTA: PERFORMANCE OF INDONESIAN LANGUAGE TRANSFORMER MODELS IN SENTIMENT CLASSIFICATION Nur, M. Adnan; Umar, Najirah; Feng, Zhipeng; Gani, Hamdan
JIKO (Jurnal Informatika dan Komputer) Vol 8, No 2 (2025)
Publisher : Universitas Khairun

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33387/jiko.v8i2.9988

The development of Natural Language Processing (NLP) technology has had a significant impact on various fields, especially in sentiment analysis. This analysis becomes important in understanding public perception, especially on social media which has a lot of opinions. Indonesian, with its morphological complexity, dialectal variations, and dynamic everyday vocabulary usage, presents unique challenges in the development of NLP models. This study aims to evaluate and compare the performance of two Indonesian language transformer models, namely IndoBERT (Indonesia Bidirectional Encoder Representations from Transformers) and RoBERTa Indonesia (Robustly Optimized BERT Pretraining Approach) in applying sentiment classification using the Indonesian General Sentiment Analysis Dataset. Both models were fine-tuned using consistent hyperparameter configurations to ensure the validity of the comparison. Evaluation was conducted based on classification metrics, namely precision, recall, F1-score, and accuracy. The results show that the IndoBERT model excels in all aspects of evaluation. IndoBERT achieved an accuracy of 70%, while RoBERTa Indonesia only reached 67%. Additionally, the average F1-score of IndoBERT at 0.69 is higher compared to RoBERTa, which only reached 0.65. The performance of IndoBERT is also more balanced in classifying the three sentiment categories (negative, neutral, and positive), whereas RoBERTa shows less consistent performance, especially in negative and positive sentiments. In the loss analysis, IndoBERT produced a lower evaluation loss value, indicating better generalization capability. Additionally, IndoBERT also shows faster and more stable training times compared to RoBERTa. This performance difference shows that the architecture and pre-trained data used by each model affect their ability to understand Indonesian contextually. This research provides a comprehensive comparative overview of the effectiveness of two transformer models in the task of Indonesian language sentiment analysis, as well as lays the groundwork for selecting a more optimal model in the development of NLP systems for social media.

Title

Found 28 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 28 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 28 Documents
Search