Research Publications

Authors

Husain, Alfiansyah Anugrah; Indra Dolly; Jabir Sitti Rahmah, Universitas Muslim Indonesia;

Abstract

Platform X menjadi ruang utama bagi masyarakat dalam mengekspresikan opini terhadap tokoh publik, termasuk Kang Dedi Mulyadi. Penelitian ini bertujuan menganalisis sentimen publik sekaligus menjawab keterbatasan studi sebelumnya yang umumnya berfokus pada isu politik nasional atau hanya menggunakan satu algoritma klasifikasi, sehingga perbandingan kinerja model pada konteks figur politik daerah masih terbatas. Data penelitian terdiri dari 7.190 tweet yang dikumpulkan melalui crawling selama Februari–September 2025. Data diproses melalui tahapan pre-processing, kemudian dilabeli otomatis menggunakan InSet Lexicon ke dalam sentimen positif dan negatif. Ekstraksi fitur dilakukan dengan TF-IDF menggunakan konfigurasi n-gram (1,2), dengan pembagian data 80:20 untuk pelatihan dan pengujian. Hasil pengujian menunjukkan bahwa SVM Linear memberikan performa terbaik dengan akurasi 0,8982, presisi 0,8991, recall 0,8970, dan F1-score 0,8977. Sementara itu, Naïve Bayes menghasilkan akurasi 0,8287, presisi 0,8297, recall 0,8268, dan F1-score 0,8276. Temuan ini menunjukkan bahwa SVM lebih efektif dibandingkan Naïve Bayes dalam mengklasifikasikan sentimen publik pada data media sosial X, serta memberikan kontribusi empiris pada kajian analisis sentimen tokoh politik berbasis media sosial

Related SDGs

Authors

Hayati, Lilis Nur; Indra Dolly, Universitas Muslim Indonesia; Djamereng Asdar;

Abstract

Buku “Rahasia Social Media Marketing untuk Bisnis Online” membahas bagaimana media sosial dapat dimanfaatkan secara optimal untuk mengembangkan bisnis di era digital. Pembahasan dimulai dari pemahaman dasar mengenai media sosial, jenis-jenis platform yang populer, serta peluang yang dapat dimanfaatkan oleh pelaku usaha untuk memperluas jangkauan pasar dan membangun hubungan dengan pelanggan. Buku ini juga menjelaskan berbagai keunggulan media sosial sebagai sarana promosi yang mudah diakses, interaktif, dan mampu menjangkau audiens secara luas. Selain peluang, dijelaskan pula tantangan yang sering dihadapi dalam mengelola media sosial sehingga pembaca dapat memahami pentingnya strategi yang tepat dalam menjalankan pemasaran digital. Buku ini memberikan panduan praktis mengenai cara membuat dan mengelola akun bisnis di berbagai platform media sosial, teknik membuat konten yang menarik, serta langkah membangun identitas brand yang kuat. Berbagai strategi promosi seperti kolaborasi, penggunaan influencer, hingga pemanfaatan fitur iklan juga dibahas secara sistematis agar bisnis dapat berkembang secara lebih efektif. Melalui penjelasan yang mudah dipahami dan disertai contoh penerapan, buku ini diharapkan dapat menjadi panduan bagi pelaku usaha, pelajar, maupun siapa saja yang ingin memanfaatkan media sosial sebagai sarana membangun dan mengembangkan bisnis online secara berkelanjutan.

Related SDGs

Authors

Astuti, Wistiani; Mude, Muh Aliyazid; Abdullah Syahrul Mubarak; Kurniati, Nia; Indra, Dolly; Manga, Abul Rachman; Ilmawan, Lutfi Budi, Universitas Muslim Infdonesia;

Abstract

Buku ini disusun secara sistematis agar mudah dipahami, mulai dari konsep dasar penilaian Openness dan Webometrics, hingga panduan teknis penggunaan Google Scholar dan SINTA. Pembaca akan dipandu langkah demi langkah dalam mengelola akun profil, meningkatkan jumlah sitasi, hingga strategi menulis artikel agar lebih mudah ditemukan secara global.

Related SDGs

Authors

Rezky, Putri Nur; Indra Dolly; Darwis, Herdianti, Universitas MUslim Indonesia;

Abstract

The Program Makan Bergizi Gratis (MBG) is a flagship program of the Prabowo Subianto administration launched in 2024, triggering diverse public responses on social media. Sentiment analysis using deep learning models offers an effective approach to understanding public opinion at scale. However, selecting the appropriate model for Indonesian social media text remains challenging. This study aims to compare the performance of two pretrained transformer models, RoBERTa Base and IndoBERTweet Base, in conducting automatic sentiment labeling on Indonesian tweets related to the MBG program using a zero-shot labeling approach without human-annotated ground truth. A total of 1,831 tweets were collected from platform X and preprocessed using case folding, normalization, and stopword removal. Both models were applied in parallel to label each tweet with sentiment categories (positive, neutral, negative) along with confidence scores. The comparison was evaluated using agreement rate, Cohen's Kappa, and confidence score analysis. RoBERTa Base exhibits a conservative tendency with 75.20% neutral labels, while IndoBERTweet Base produces a more balanced distribution (68.16% neutral). The comparison shows 77.28% agreement with Cohen's Kappa of 0.490 (Moderate Agreement). RoBERTa Base achieves higher confidence (mean: 0.9559, 83.01% above 0.95) compared to IndoBERTweet Base (mean: 0.9236, 68.65% above 0.95). IndoBERTweet Base is more effective in detecting negative sentiment, identifying nearly twice as many negative tweets (13.54% vs. 7.48%). This study recommends IndoBERTweet Base for exploratory research requiring sensitive sentiment detection and RoBERTa Base for precision-critical applications. An ensemble approach combining both models is recommended for production-critical applications

Related SDGs

Authors

Zahra, Andi Fathimatuz; Indra Dolly; Hayati, Lilis Nur, Universitas Muslim Indonesia

Abstract

Pemanfaatan aplikasi perbankan digital menjadi bagian penting dalam mendukung produktivitas masyarakat melalui layanan perbankan yang efisien dan praktis. Byond by BSI sebagai salah satu mobile banking turut berperan dalam memenuhi kebutuhan layanan keuangan nasabahnya. Seiring meningkatnya jumlah pengguna aplikasi Byond by BSI, muncul beragam opini yang belum terpetakan secara sistematis. Hal ini menciptakan kebutuhan akan analisis sistematis agar ulasan tersebut dapat dimanfaatkan sebagai basis evaluasi fungsionalitas aplikasi dan optimalisasi pengalaman pengguna. Penelitian ini bertujuan mengidentifikasi distribusi sentimen positif dan negatif pada ulasan pengguna aplikasi Byond by BSI serta menentukan algoritma terbaik berdasarkan nilai akurasi, presisi, recall, dan F1-score dalam mengklasifikasikan sentimen ulasan pengguna. Metode yang diterapkan untuk menentukan kategori sentimen ulasan adalah algoritma Naïve Bayes dan SVM. Hasil evaluasi penelitian menunjukkan bahwa algoritma SVM mampu menunjukkan kinerja lebih baik daripada Naïve Bayes dalam mengklasifikasikan ulasan. SVM menunjukkan kinerja terbaik pada pembagian data 90: 10 dengan akurasi 95.33%, presisi 97.12%, recall 94.94%, dan f1-score 96%. sedangkan Naïve Bayes mencapai kinerja terbaiknya pada pembagian data 70: 30 dengan akurasi 94%, presisi 95.10%, recall 94.45%, dan f1-score 94.81%.

Related SDGs

Authors

Indra, Dolly; Alwi, Erick Irawadi; Kasim, Fadil, Universitas Muslim Indonesia

Abstract

Indonesian Sign Language (BISINDO) is an essential means of communication for deaf people in Indonesia. However, communication challenges persist for the general public, who lack sign language proficiency. To bridge this gap, a real-time BISINDO recognition system is essential. This research compares the performance of several distance models in recognizing BISINDO letters using a camera-based recognition system. The study evaluated three distance methods City Block, Canberra, and Chebyshev applied to shape feature extraction through chain code analysis. Testing was conducted under both indoor and outdoor conditions to assess system robustness. The results revealed that the Chebyshev distance method achieved the highest accuracy in indoor scenarios, particularly when participants wore white clothing, reaching an accuracy of 100%. Meanwhile, in outdoor conditions, the Canberra distance method outperformed the others, achieving the highest accuracy of 96.15% with white clothing. However, outdoor accuracy was generally lower due to uncontrollable lighting, which affected recognition. Despite these challenges, the system demonstrated its capability to recognize BISINDO letters effectively in both environments.

Related SDGs

Authors

Irfan, Muhammad Naufal; Alwi, Erick Irawadi; Hasnawi, Mardiyyah, Universitas Muslim Indonesia;

Abstract

Ketersediaan jaringan internet yang andal merupakan kebutuhan mendasar bagi pengguna teknologi komunikasi masa kini. Namun, perkembangan teknologi jaringan seluler dari generasi ke generasi tidak selalu berbanding lurus dengan peningkatan kualitas layanan yang dirasakan pengguna secara aktual. Penelitian ini bertujuan membandingkan kualitas layanan (Quality of Service/QoS) jaringan 4G dan 5G pada layanan video streaming di Kota Makassar. Pengukuran dilakukan secara kuantitatif menggunakan empat parameter QoS, yaitu throughput, packet loss, delay, dan jitter, dengan instrumen aplikasi Wireshark berdasarkan standarisasi TIPHON. Data dikumpulkan selama 10 hari pada dua sesi waktu, yaitu siang hari (12.00–13.00 WITA) dan malam hari (19.00–20.00 WITA) di lantai dua Mall Panakkukang Square Makassar. Hasil penelitian menunjukkan bahwa indeks QoS jaringan 4G pada sesi siang sebesar 3,87 dan sesi malam sebesar 3,93, keduanya berada pada kategori "Memuaskan". Sementara itu, indeks QoS jaringan 5G pada sesi siang sebesar 3,86 dan sesi malam sebesar 3,90, yang juga termasuk dalam kategori yang sama. Rata-rata indeks QoS jaringan 4G (3,90) tercatat lebih tinggi dibandingkan jaringan 5G (3,88). Temuan ini mengindikasikan bahwa pada kondisi pengujian indoor dan tahap awal implementasi infrastruktur, kualitas jaringan 5G belum secara nyata melampaui jaringan 4G yang telah lebih mapan.

Related SDGs

Authors

Rafianto, Muh; Alwi, Erick Irawadi; Mansyur, St Hajra, Universitas Muslim Indonesia;

Abstract

Conventional digital identity systems often rely on centralized authorities that are vulnerable to data breaches and manipulation. The Developer Student Club Universitas Muslim Indonesia (DSC UMI) community requires a membership verification mechanism that is credible, secure, and preserves user privacy. This research aims to implement a decentralized digital identity system fully integrated on the Android platform using blockchain technology and Zero-Knowledge Proofs (ZKP), where the entire system logic—including blockchain interactions and cryptography—is processed independently on the client side (backendless) without dependence on intermediary servers. The development method applies a Minimum Viable Product (MVP) approach with a mobile-first architecture. The system is built on native Android using the Kotlin language, integrated with the Polygon Amoy Testnet network via the Web3j library. Authentication utilizes local biometric sensors to generate cryptographic proofs based on SHA-256 hashes without storing raw data on the server. White box testing results show that the application successfully connects to the MetaMask digital wallet, validates anti-duplication logic on the Smart Contract, and automatically issues a Soulbound Token (NFT) as legitimate proof of membership. In conclusion, blockchain integration on mobile devices is proven effective in delivering Self-Sovereign Identity (SSI) that is transparent and auditable without compromising the privacy of community member data.

Related SDGs

Authors

Satra, Ramdan; Mubarak Syahrul, Universitas Muslim Indonesia;

Abstract

A safe is a tool used to store valuables including money, jewelry, assets or valuable documents. A safe is a storage place that is considered practical but has a high risk. There are several shortcomings in existing safes, including using one key, which makes the safe easy to break into, which can cause losses to the owner. Therefore, it is necessary to innovate or develop by using a combination of several keys by applying fingerprint and keypad technology to add security features to the safe. The solution to this problem can be made by creating a Money Storage Safe Security With Two Key Combinations (Fingerprint + Keypad), this system can open the safe with two combinations of fingerprint and keypad so that it can increase security on the safe. This study aims to design a safe security system using fingerprint and keypad. This system is a prototype that will open the safe door based on the user's fingerprint that has been recognized and uses the keypad to enter a previously created password. Based on the results of research and testing of tools and fingerprints, an accuracy of 100% was obtained for tool testing and 53.33% for fingerprint testing, so it can be concluded that the design of the tool has worked well

Related SDGs

Authors

Huda, Besse Nurul; Anraeni, Siska, Universitas Muslim Indonesa;

Abstract

Acute Respiratory Infections (ARI) are one of the diseases that often affect children and are a major cause of morbidity and mortality in Indonesia. Accurate early diagnosis is very important to prevent complications, but limited medical personnel and the similarity of ARI symptoms to other diseases are often obstacles. In this context, an artificial intelligence-based expert system can be a solution to support medical decisions. This article presents a comparative analysis of two inference methods commonly used in expert systems, namely Certainty Factor (CF) and Dempster-Shafer (DS). Through a Systematic Literature Review (SLR) approach, this study evaluates the performance of both methods based on accuracy, complexity, flexibility, and ease of implementation. The results of the study show that Certainty Factor excels in simplicity and efficiency, while Dempster-Shafer is more reliable in handling uncertainty and cases with many overlapping symptoms. This article is expected to be a reference for the development of more accurate and efficient medical expert systems in assisting the diagnosis of ARI in children.

Related SDGs

Authors

Anraeni, SIska; Septiawan, M Fiqry; Resa, Muhammad Raihan; Lahuddin, Herlinda; Darwis, Herdianti, Universitas Muslim Indonesia

Abstract

Precise quantification of pineapple (Ananas comosus) cultivation is vital for strategic agricultural decisionmaking and operational efficiency. Traditional manual enumeration methods are resource-intensive, time-consuming, and susceptible to human error. This research presents an automated detection framework utilizing unmanned aerial vehicle (UAV) photography combined with digital image analysis techniques. A YOLO-formatted dataset of high-resolution photos was gathered in Pujananting, Barru, South Sulawesi, Indonesia. An object detection model built on the YOLOv8 architecture was then trained using these pictures. Standard criteria such as precision, recall, and mean Average Precision at a 0.5 Intersection over Union threshold were used to assess the model. Experimental findings indicate the proposed framework achieves excellent detection performance, with mean Average Precision attaining 0.979 and both precision and recall reaching 0.95. The framework was additionally validated for automated plant enumeration, with outcomes aligning closely with manual field observations. These findings demonstrate that UAV-based imaging integrated with deep learning provides an accurate and efficient methodology for pineapple crop monitoring, supporting intelligent agricultural applications and informed management strategies.

Related SDGs

Authors

Belluano, Poetri Lestari Lokapitasari; Majid, Abd; Fuad Muhammad Nur; Scania, Muhammad Rifky Saputra, Universitas Muslim Indonesia;

Abstract

Event notification systems play a crucial role in supporting academic and student organizational activities. However, many institutions still rely on monolithic architectures with synchronous processing that are unable to handle spikes in communication loads, resulting in high latency and reduced delivery reliability. This study proposes a notification system based on Event-Driven Architecture (EDA) integrated with a microservices environment to improve the efficiency, scalability, and reliability of information dissemination, particularly through the WhatsApp Business API as the primary communication channel. The proposed system leverages asynchronous event processing, distributed message brokers, and isolated gateway services to enable parallel message delivery while addressing external service constraints such as rate limiting. The system is evaluated within a single controlled experimental setup using 1,011 notification messages under consistent workload conditions. For comparison purposes, a simulated synchronous baseline is used to represent the characteristics of traditional sequential processing systems. The results show that the EDA-based system achieved a 100% delivery success rate with an average latency of 3,222 ms and a stable throughput of 17 messages per second, while the simulated baseline exhibits limitations in maintaining performance under the same conditions. These findings indicate that the proposed architecture improves system performance within the evaluated experimental context and demonstrates strong potential for scalable real-time communication in controlled deployment environments.

Related SDGs

Authors

Musdalifah, Musdalifah; Indra, Dolly; Jabir, Sitti Rahmah, Faculty Of Computer Science, Universitas Muslim Indonesia, Makassar, Indonesia

Abstract

Pemanfaatan sistem informasi di tingkat pemerintahan desa menjadi krusial untuk memenuhi ekspektasi publik terhadap pelayanan yang responsif dan transparan. Penelitian ini bertujuan untuk mengevaluasi efektivitas website resmi Desa Lamundre (https://lamundre.kolakadesa.id/) dalam menunjang efisiensi operasional aparatur desa serta kualitas layanan bagi masyarakat. Metode evaluasi yang digunakan adalah kerangka kerja PIECES yang meninjau enam dimensi utama: performance, information, economy, control, efficiency, dan service. Data dikumpulkan melalui observasi, wawancara, dan penyebaran kuesioner kepada 10 aparatur desa serta 30 responden masyarakat dengan teknik analisis statistik deskriptif menggunakan skala Likert. Hasil penelitian menunjukkan bahwa secara keseluruhan sistem informasi Desa Lamundre berada pada kategori "Puas". Dimensi control mendapatkan penilaian tertinggi (skor 3,66), sedangkan dimensi efficiency memerlukan perhatian lebih untuk peningkatan performa sistem di masa mendatang. Evaluasi ini diharapkan menjadi acuan bagi Pemerintah Desa Lamundre dalam mengoptimalkan sistem informasi desa.

Related SDGs

Authors

Anraeni, Siska; Lahuddin, Harlinda; Ramdaniah, Ramdaniah; Melani, Erika Riski; Amalia, Andi Cici; Amaliah, Tazkirah, Faculty Of Computer Science, Universitas Muslim Indonesia, Makassar, Indonesia

Abstract

This study develops a digital image processing technique to distinguish between fresh and rotten chicken. Chicken freshness has a significant impact on public health and industry sustainability. This study uses a multistage approach including data acquisition, preprocessing, feature extraction, and classification. A total of 1,000 chicken images were obtained, consisting of 800 images for training and 200 images for testing, with a proportion of 80:20. Feature extraction was performed using a combination of the HSI (Hue, Saturation, Intensity) color model to capture the color characteristics of chicken, and Local Binary Pattern (LBP) to extract texture information. Classification was performed using the K-Nearest Neighbor (KNN) algorithm with various K values and distance metrics. The experimental results show that the combination of color and texture features provides higher accuracy than using either feature alone. The best model using HSI and LBP feature extraction with K = 1 and K = 3 in the Euclidean distance metric, achieved the highest accuracy of 95.4%. With a promising level of accuracy, this method can be applied in automated inspections in the poultry supply chain, improving food safety, and helping consumers make better purchasing decisions. However, the main challenge in this study is the variation in lighting during image capture, which causes the fresh and rotten chicken feature values to overlap, thus hindering perfect classification.

Related SDGs

Authors

Rezky, Aditya; Hayati, Lilis Nur; Sugiarti, Sugiarti, Faculty Of Computer Science, Universitas Muslim Indonesia, Makassar, Indonesia

Abstract

Banana leaf disease (Musa spp.) poses a critical threat to tropical agricultural productivity in Indonesia, with harvest loss estimates reaching 30–50% during rainy seasons due to undetected pathogen infections. Limited manual diagnostic capacity among farmers produces disease misidentification and delayed control interventions, particularly at early infection stages when inter-class visual symptom similarity remains high. This study proposes an automated banana leaf disease detection system leveraging deep learning through the You Only Look Once version 5 (YOLOv5) architecture as a digital image-based diagnostic solution. The dataset comprises 9,684 images across eight banana leaf disease classes, curated via Roboflow with 87% training (8,460 images), 8% validation (820 images), and 4% testing (404 images) splits. Preprocessing includes 2×2 tiling, auto-orientation, and 512×512 pixel stretch resizing. Data augmentation applies horizontal and vertical flip alongside 0–25% zoom crop, generating three outputs per training image. Model performance evaluation employs precision, recall, F1-score, and mean Average Precision (mAP@0.5) metrics. Results demonstrate YOLOv5 capability in accurately detecting and classifying banana leaf diseases under Indonesian tropical field imaging conditions.

Related SDGs

Authors

Iha, Eka Inggraha; Herman, Herman; Hayati, Lilis Nur; Amir, Nur Hikmah, Faculty Of Computer Science, Universitas Muslim Indonesia, Makassar, Indonesia

Abstract

Pemerintah Kabupaten Fakfak belum memiliki kanal digital resmi untuk menerima dan menanggapi keluhan masyarakat secara terstandarisasi, sehingga seluruh pengaduan diproses melalui kunjungan fisik dan media sosial tanpa alur penanganan baku. Penelitian membangun sistem berbasis web menggunakan PHP, MySQL, dan Bootstrap 5 dengan metode pengembangan SDLC model Waterfall, mengintegrasikan empat aktor yaitu Masyarakat, Admin, Petugas/Instansi, dan Walikota dalam satu platform terpadu berautentikasi NIK. Pengujian Black-Box Testing membuktikan seluruh fungsi utama berjalan sesuai spesifikasi kebutuhan, mencakup pengajuan keluhan, verifikasi akun, distribusi penugasan, pembaruan status, dan pemantauan analitik eksekutif. Uji penerimaan pengguna menunjukkan masyarakat berani dan aktif memposting pengaduan secara terbuka melalui platform, mengindikasikan tingkat kepercayaan pengguna terhadap sistem terbentuk sejak tahap pengujian awal. Sistem terbukti mampu mengubah budaya pengaduan konvensional menjadi partisipasi publik digital yang terukur dan akuntabel di lingkungan Pemerintah Kabupaten Fakfak

Related SDGs