Publication Search

Tomato (Solanum lycopersicum) is a high-value horticultural commodity in Indonesia, yet its cultivation is frequently disrupted by leaf diseases that are difficult to distinguish visually. Diseases such as Bacterial Spot, Early Blight, and Tomato Yellow Leaf Curl Virus often present overlapping visual symptoms, making early and accurate diagnosis a significant challenge for farmers. The manual identification methods currently in use are inefficient and error-prone, ultimately leading to reduced crop yield  and quality. The general objective of this study is to develop software capable of automatically classifying tomato  leaf diseases. Specifically, this research aims to implement the MobileNetV3 Small architecture based on Convolutional Neural  Network (CNN) with ImageNet pre-trained weights to classify 10 types of tomato leaf diseases. The research methodology encompasses dataset collection from Kaggle comprising 10,000 images (1,000 per class), image pre-processing through resizing to 224x224 pixels, and normalization, as well as hyperparameter optimization (optimizer, learning rate, epoch, batch size) via scheduler. Model performance is evaluated using a confusion matrix encompassing accuracy, precision, recall, and F1-score.

Birth certificate ownership is a fundamental right of every citizen and an essential requirement for accessing various public services. However, the coverage of birth certificate ownership in North Central Timor Regency has not yet reached the national target. To address this issue, the Department of Population and Civil Registration of North Central Timor Regency implemented the Mobile Service Program (Jemput Bola) as an initiative to bring civil registration services closer to the community. This study aims to analyze the effectiveness of the Mobile Service Program in increasing birth certificate ownership in North Central Timor Regency. The research employed a qualitative approach using a descriptive method. Data were collected through observation, interviews, and documentation, and analyzed using the interactive model of Miles and Huberman. The analysis of program effectiveness was based on Richard M. Steers’ goal approach and strategic constituencies approach. The findings indicate that the Mobile Service Program is effective in expanding service accessibility, increasing the number of birth certificates issued, and facilitating public access to civil registration documents. The program also received positive responses from the community because it reduced barriers related to cost, time, and distance in obtaining birth certificates. Nevertheless, several challenges remain, including low public awareness, incomplete administrative requirements, limited internet connectivity, and geographical constraints. Therefore, strengthening public outreach, improving coordination with village governments, and establishing measurable program targets are necessary to enhance the program’s effectiveness in a sustainable manner.

Children's literacy can be improved through interactive learning media. A digital children's story platform, previously a mobile application, required web version development to expand user accessibility via browsers. The main challenge in this development was presenting multimedia content such as text, images, and audio dubbing synchronously scene-by-scene without degrading system performance, as well as facilitating reader interaction through a rating feature. This research aims to design and develop the platform using a Decoupled Architecture approach. The software development method used is Waterfall, encompassing requirement analysis, system design (UML, CDM, and PDM), implementation, testing, and maintenance. During implementation, ReactJS is utilized on the client-side for responsive interface rendering and state management, while Laravel is implemented on the server-side as a RESTful API provider to manage multimedia asset transmission, rating records, and the MySQL database. Functional system testing was evaluated using Black-box Testing, while user experience was validated using Spearman's Rank Correlation. The results indicate that this architectural separation (front-end and back-end) effectively resolves server overload issues commonly found in monolithic architectures and produces a seamless, stable asynchronous data transmission system across various devices.

Indonesia masih menghadapi tantangan demografi berupa jumlah penduduk yang besar dengan laju pertumbuhan yang terus meningkat. Berdasarkan hasil Survei Demografi dan Kesehatan Indonesia (SDKI) tahun 2012, jumlah penduduk Indonesia mencapai sekitar 257 juta jiwa. Di sisi lain, penggunaan smartphone telah menjadi bagian dari kehidupan masyarakat, ditandai dengan peningkatan pengguna yang terus terjadi setiap tahun. Data dari Statista menunjukkan bahwa pada Oktober 2017, sekitar 75% pengguna smartphone di Indonesia menggunakan perangkat berbasis Android. Berdasarkan data integrasi Sistem Informasi Administrasi Kependudukan (SIAK) dengan KTP elektronik Kabupaten Tasikmalaya per Juni 2019, Kecamatan Cigalontang merupakan kecamatan dengan jumlah penduduk terbesar kedua setelah Karangnunggal, yaitu sebanyak 74.140 jiwa atau 4,14% dari total penduduk Kabupaten Tasikmalaya yang berjumlah 1.791.881 jiwa. Jumlah tersebut terdiri atas 37.998 laki-laki (4,17%) dan 36.142 perempuan (4,10%). Dalam program Keluarga Berencana (KB), metode kontrasepsi yang paling banyak digunakan adalah suntik 300 PUS sebesar 41,10% dan suntik 150 PUS sebesar 20,55%, dengan jumlah peserta aktif mencapai 506 akseptor atau sekitar 69% dari total 730 akseptor KB. Hasil Focus Group Discussion (FGD) bersama bidan dan akseptor KB menunjukkan masih sering terjadi keterlambatan maupun kelalaian dalam konsumsi pil KB serta jadwal kunjungan ulang suntik, sehingga diperlukan media atau sistem pengingat yang dapat membantu meningkatkan kepatuhan akseptor.  Penelitian ini dilakukan untuk menilai efektivitas aplikasi mobile “e-KABE” sebagai sarana pendukung pelayanan Keluarga Berencana di Desa Cigalontang, Kabupaten Tasikmalaya, pada tahun 2021.

The development of digital services by BPJS Ketenagakerjaan through the JMO (Jamsostek Mobile) application has triggered a surge in large-scale and unstructured user reviews on the Google Play Store, thereby complicating manual analysis and conventional sentiment analysis in accurately identifying specific issues. This research aims to implement the Aspect-Based Sentiment Analysis (ABSA) method to granularly evaluate JMO application reviews based on specific aspects, while simultaneously addressing class imbalance and computational efficiency issues. The proposed method combines the pretrained IndoBERT model as a contextual feature extractor, the SMOTE technique to balance the training data, and an artificial neural network (Neural Network) as the classification layer without performing full fine-tuning. The dataset used consists of 90,268 unique reviews categorized into five main aspects through keyword matching, namely General Satisfaction/Complaints, Performance & Stability, Service & Support, Feature Quality, and UI/UX, with initial lexicon-based labeling using the InSet Lexicon. The research results indicate that the proposed model successfully achieves highly optimal performance with an accuracy rate of 91.81% and a weighted F1-score of 92%. Furthermore, the implementation of SMOTE proved effective in enhancing model reliability on the minority class (negative sentiment), achieving an F1-score of 89%. The implications of this research contribute an accurate and efficient aspect-based sentiment analysis framework for developers, and serve as a strategic evaluation tool for BPJS Ketenagakerjaan in mapping specific user complaints to accelerate continuous improvements in the performance, stability, and service quality of the JMO application.

The purpose of this study was to analyze the implementation of Al-Qur’an and Hadith teaching at MAN 2 Karawang, including the challenges faced and approaches to resolving them. The method used was qualitative with a descriptive approach. Information was collected through interviews and documentation with the principal, Al-Qur’an and Hadith teachers, and eleventh-grade students. The research findings indicate that teaching is conducted in accordance with the madrasah curriculum, using a thematic and contextual approach that focuses on moral development and the application of Islamic values in daily life. Teachers use various methods, such as lectures, discussions, questions and answers, and hadith memorization. However, the teaching and learning process still faces several obstacles, such as a lack of infrastructure, including projectors, limited availability of textbooks, and unsupportive classroom conditions, which affect students’ concentration. Several solutions implemented include the gradual provision of facilities, the use of digital technology through students’ mobile phones and e-books, and the implementation of more interactive teaching methods to increase student motivation.

This study investigates the performance of Internet of Things (IoT)-based monitoring systems using a mobile hotspot and IoT sensors for temperature and humidity data transmission. The research is based on the IoT concept, which enables electronic devices to communicate and exchange data through internet networks without direct human intervention. System performance was evaluated using standard Quality of Service (QoS) parameters, including throughput, packet loss, delay, and jitter. The experimental setup utilized a NodeMCU ESP32 microcontroller and a DHT22 sensor, with measurements conducted at various transmission distances through wireless communication media. The objective was to determine the reliability of hotspot connectivity and sensor communication in supporting IoT applications. The results indicate that the optimal performance was achieved at a distance of 20 meters using a 40-lambda variation. Furthermore, the communication signal between the ESP32 device and the mobile hotspot remained detectable up to a maximum distance of 32 meters. These findings demonstrate the effectiveness of the proposed IoT system for environmental monitoring applications within specific transmission ranges.

Typhoid fever is a febrile illness that commonly occurs in urban areas with poor sanitation. It is usually caused by the consumption of untreated water and contaminated food. Because the S. typhi bacterium can survive in water for days, contamination of surface water—such as wastewater, freshwater, and groundwater—serves as the primary cause of typhoid fever. The patient presented to the Emergency Department of Cut Meutia General Hospital with complaints of high fever for approximately 4 days prior to admission, which had worsened over the past 2 days. The fever fluctuated and was accompanied by chills. It worsened at night and was not influenced by weather or temperature. These symptoms were accompanied by vomiting every time the patient tried to eat, nausea, abdominal pain, headache, and weakness. The patient reported vomiting the contents of their meal every time they ate, leading to a loss of appetite. These symptoms began when the patient first developed a fever. The patient also experienced abdominal pain. Spontaneous bleeding was denied. On physical examination, the patient appeared weak but was alert and oriented. On neck examination, palpable enlargement of the thyroid glands was found on the right and left sides of the neck, measuring 2x2 cm, mobile, and soft. On abdominal examination, increased bowel sounds were noted. Vital signs were normal except for the patient’s febrile temperature. Laboratory tests revealed a Tubex blood test result of scale 4 and a positive dengue IgG serology result.

Postpartum depression is a postpartum mental health disorder that significantly impacts maternal well-being, infant development, and family functioning. The high prevalence of postpartum depression in Indonesia is due to limited access to health services, low mental health literacy, and social stigma in the community. This indicates a significant gap between the need for maternal mental health services and the availability of existing interventions, making education a crucial component in efforts to prevent postpartum depression early. This study aims to analyze the prevention of postpartum depression in postpartum mothers through telenursing-based education and screening using the Edinburgh Postnatal Depression Scale (EPDS) in the community. A descriptive case study design was used, involving one respondent, a 25-year-old primigravida mother residing in the Bantul area. The intervention was implemented online via WhatsApp and video calls, including structured health education on postpartum psychological changes, adaptive coping strategies, and the importance of social support. The intervention also included daily remote monitoring of the respondent's condition via the WhatsApp mobile application. The EPDS was administered as a pre-test and post-test to evaluate changes in the respondent's psychological condition. The findings showed a significant decrease in the EPDS score from 16 (moderate depression) to 6 (minimal depression), indicating significant psychological improvement. These results imply that integrating EPDS screening, structured health education, and daily monitoring is an effective and accessible community-based approach to preventing postpartum depression, particularly for mothers with limited mobility and access to health services.

This study aims to develop a financial saving application to improve the saving habits of students, particularly in Islamic boarding schools, through an adaptive challenge approach. The system integrates a mobile iOS application with a backend service and Large Language Model (LLM) processing via Ollama. Transaction data entered by users is processed by the backend to generate contextual and personalized saving challenges, applying Reinforcement Learning concepts in an adaptive and data-driven manner. The research adopts a descriptive quantitative method using surveys and system testing with 50 respondents. Results indicate that the application functions as designed, with no significant bugs detected. User evaluation shows high satisfaction, with an average score of 4.3 out of 5, covering ease of use, interface design, and increased awareness of saving. The combination of gamification, reward systems, and adaptive personalization successfully motivates users to save regularly. This system demonstrates the potential of integrating AI-driven personalization to strengthen financial literacy and healthy financial habits among students in a fun and interactive way.methods, and a summary of the results. The abstract should end with a comment about the significance of the results or conclusions brief.

This study discusses a student concentration detection system using Convolutional Neural Network (CNN) with the MobileNetV2 architecture. The dataset was adapted from Classroom Student Behaviors and mapped into four concentration categories: highly focused, focused, less focused, and unfocused. The system was tested with a 720p webcam and produced real-time detection data. The evaluation results show an overall accuracy of 75.85%, with the highest precision achieved in the focused class (0.9859) and the highest recall in the highly focused (0.9739) and unfocused (0.9811) classes. The confusion matrix indicates that the focused class was detected most consistently, while highly focused and unfocused classes were often misclassified as focused, resulting in lower precision. In real-time testing, the system operated at an average of 7 FPS and worked optimally when students faced the camera directly with sufficient lighting, but its performance decreased significantly at face angles greater than 45°. User evaluation shows that 75% of students rated the detection results as accurate/very accurate with an average satisfaction score of 3.6 out of 5, and 75% felt assisted in recognizing their concentration level. From the teachers’ perspective, most stated that the results were consistent with classroom observations, and all expressed willingness to reuse the system.

This study examines the effect of digital banking transformation on financial inclusion in emerging economies, using Indonesia as a case study. Digital banking transformation refers to the technological development of banking services, including accessibility, transaction speed, system security, service integration, and the availability of user-relevant financial features. Financial inclusion is defined as individuals’ ability to access, use, and benefit from formal financial services in an easy, secure, affordable, and sustainable way. This research employs a quantitative explanatory design. Data were collected through structured questionnaires distributed to users of mobile banking, internet banking, digital bank applications, and digital payment services in Indonesia. Respondents were selected using purposive sampling with criteria of being at least 17 years old, residing in Indonesia, and having used digital banking services within the last six months. Data were analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM). The results indicate that digital banking transformation has a positive and significant effect on financial inclusion, with a path coefficient of 0.684, a t-value of 14.276, and a p-value of 0.000. The R-square value of 0.468 shows that 46.8% of the variance in financial inclusion is explained by digital banking transformation. These findings suggest that digital banking expands access to financial services, increases usage of formal financial products, and reduces barriers related to distance and cost. However, its effectiveness still depends on digital literacy, security, trust, infrastructure, and consumer protection. The study implies that banks and regulators should strengthen inclusive, secure, and affordable digital financial services for underserved communities.

Usability evaluation plays a crucial role in ensuring the quality of digital systems, particularly in terms of comfort, effectiveness, and ease of use. Instruments such as the System Usability Scale (SUS), User Experience Questionnaire (UEQ), and Heuristic Evaluation (HE) are widely used in modern usability studies. This research conducts a Systematic Literature Review (SLR) to identify patterns and trends in the use of these instruments. A total of 27 initial studies were collected, and 16 were selected through the PRISMA screening procedure. The findings show that UEQ is the most frequently used instrument, especially in Learning Management Systems (LMS) and academic platforms, while SUS is commonly applied to mobile applications and digital libraries for rapid usability assessment. HE is effective in revealing fundamental interface issues such as non-intuitive navigation and layout inconsistencies. Overall, digital systems perform well in Efficiency and Perspicuity, but consistently show low scores in Novelty. This study provides an integrative knowledge map that highlights cross-instrument insights and supports the development of more intuitive, innovative, and user-centered digital systems

This research aims to develop an Android-based boarding house search application that can provide boarding house information quickly, accurately, and easily accessed by the public, especially students and migrant workers. The research employed a Research and Development (R&D) method, encompassing user needs analysis, system design, application development, implementation, and system testing. The application is designed with key features such as searching for boarding houses based on location, price, facilities, and room availability, making it easier for users to make choices based on their needs. Furthermore, the application also provides features for boarding house owners to manage and promote their properties digitally. The application development process was conducted using the Android Studio platform with an integrated database to support real-time information management. System testing was conducted using the Black Box Testing method to ensure all application functions run according to user needs. The results show that the developed application can improve the efficiency of the boarding house search process, accelerate information access, and facilitate boarding house owners in promoting and managing property data. Therefore, this application is expected to be an effective digital solution to support mobile-based housing search services.

 The rapid adoption of smartphones among Indonesian digital natives has increased reliance on biometric authentication systems. However, empirical evidence regarding the relationship between user satisfaction and security risk awareness remains limited, particularly in developing-country contexts. This study investigates the behavioral dynamics of biometric security perception among 266 respondents, consisting of 221 high school students and 45 university students in Indonesia. A Python-based computational pipeline incorporating Akaike Information Criterion (AIC) validation and 1,000-iteration stochastic bootstrapping was employed to evaluate nonlinear behavioral patterns using Polynomial Regression and Ordinary Least Squares (OLS) multivariate analysis. The results confirm the existence of a nonlinear Security Paradox. While the overall population demonstrates a positive quadratic trajectory, the university student group exhibits a concave-down parabolic relationship (a=−0.0460), indicating a decline in perceived utility beyond a specific security threshold. The identified behavioral breaking point occurs at X≈5.45 (95% CI: 2.99–20.77), suggesting that excessive security hardening may reduce perceived usability and increase cognitive friction. Furthermore, the ablation analysis reveals that security risk awareness (p<0.001) is the strongest predictor of user satisfaction, exceeding the influence of daily usage intensity. Segment-level analysis further demonstrates behavioral divergence between respondent groups. High school students exhibit relatively uniform satisfaction toward biometric systems, whereas university students display greater variability and more critical perceptions regarding authentication friction. These findings indicate that highly rigid security configurations may become less effective for users with higher digital literacy and risk awareness. This study contributes a computationally validated behavioral framework for understanding security–utility trade-offs and provides a conceptual foundation for developing adaptive, user-centric, and friction-aware biometric authentication systems.

This study presents an innovation design for an Internet of Things (IoT)-based watering and liquid fertilizer control system for chili plants using a NodeMCU ESP32. The main problem addressed is the manual watering and fertilizing process, which makes it difficult for farmers to monitor soil moisture, temperature, air humidity, and light intensity in real time. The recommended method used in this draft is Research and Development (R&D) with a prototyping approach because the study focuses on designing, building, integrating, and testing an IoT device through iterative stages. The system is designed using a soil moisture sensor, DHT11, LDR sensor, two-channel relay, two 12 V DC pumps, 16x2 I2C LCD, and the Blynk Mobile application for remote monitoring and control. Sensor data are transmitted to Blynk as percentage values and plant condition statuses, while the water and fertilizer pumps can be controlled using virtual buttons. The control logic defines the optimal condition for chili plants based on soil moisture of 60-80%, temperature of 25-30°C, air humidity of 60-80%, and light intensity of 50-90%. Prototype documentation and functional testing data will be completed in the next stage.

This study aims to develop a sentiment classification method for YouTube user comments related to the game Love and Deepspace using the Naïve Bayes algorithm, focusing on improving the text data processing and understanding user perceptions. Comment data were collected through scraping from YouTube videos, followed by preprocessing including text cleaning, normalization, stopword removal, stemming, and translation into English. Initial labeling was conducted using TextBlob, then the data were randomly sampled for training the Naïve Bayes model. Evaluation involved comparing sentiment distributions and visualization using Word Cloud and bar charts. The Naïve Bayes model achieved an accuracy of 77.36% in sentiment classification. The sentiment distribution shows differences between TextBlob (positive: 1,011, neutral: 1,312, negative: 575) and Naïve Bayes (positive: 901, neutral: 1,627, negative: 370), with Naïve Bayes being more conservative. The Word Cloud visualization identifies dominant words such as "bang," "game," and "main," while the bar chart shows the largest proportion of neutral sentiment. Naïve Bayes is effective for sentiment classification on informal comment data, with significant differences from rule-based methods like TextBlob. This research contributes to the development of text data processing techniques and user perception analysis, as well as opening up optimization opportunities with other algorithms like SVM for better accuracy.

King Royal Hotel Restaurant still applies manual sales transaction recording, causing data management and revenue report preparation to be less than optimal. This study aims to design and implement a Flutter-based sales and revenue reporting application that utilizes local storage as a data storage mechanism on the device. The system development method used is the Waterfall method, which includes the stages of requirements analysis, design, implementation, testing, and maintenance. The application was developed using the Flutter framework with the Dart programming language and utilizes the shared_preferences and hive packages for local data management on the device without requiring an internet connection or external database server. In addition, the application is designed to be easy for restaurant employees to use in recording daily transactions more quickly and accurately. Testing was conducted using the Black Box Testing method, which showed that all application features functioned according to functional requirements. The results of the study indicate that the Flutter-based application with a local storage approach is capable of improving transaction recording efficiency and generating revenue reports automatically at King Royal Hotel Restaurant.

Pesatnya perkembangan teknologi informasi mendorong terjadinya digitalisasi di berbagai bidang usaha, termasuk pada layanan jasa cuci sepatu. Penggunaan aplikasi mobile menjadi salah satu alternatif untuk meningkatkan kualitas layanan, efisiensi operasional, serta kemudahan akses bagi pelanggan. Namun demikian, keberhasilan sebuah aplikasi tidak hanya bergantung pada fungsi yang dimiliki, tetapi juga pada kualitas desain antarmuka (User Interface/UI) dan pengalaman pengguna (User Experience/UX) yang mampu memberikan kenyamanan dan kemudahan dalam penggunaan. Tujuan dari penelitian ini adalah merancang desain UI/UX pada aplikasi mobile layanan cuci sepatu OurShoes agar lebih mudah dipahami, menarik, dan efisien digunakan. Metode yang diterapkan adalah Design Thinking yang meliputi tahapan empathize, define, ideate, prototype, dan testing. Hasil yang diperoleh berupa rancangan antarmuka aplikasi mobile dengan fitur utama seperti halaman login dan registrasi, pemesanan layanan, sistem pembayaran, notifikasi status pesanan, serta pengelolaan profil pengguna. Rancangan ini diharapkan dapat meningkatkan kualitas pengalaman pengguna, mempermudah proses transaksi, serta membantu pelaku usaha dalam mengelola layanan secara lebih efektif dan efisien. Dengan demikian, aplikasi ini berpotensi menjadi solusi digital yang mendukung pengembangan usaha cuci sepatu di era modern.

Penelitian ini bertujuan untuk menganalisis dan membandingkan kinerja model YOLOv11 dan MobileNetV3 dalam mengklasifikasikan varietas padi berdasarkan gambar digital. Kumpulan data terdiri dari 10.000 gambar yang mewakili lima varietas padi, yaitu Arborio, Basmati, Ipsala, Jasmine, dan Karacadag. Kumpulan data tersebut dibagi menjadi set pelatihan dan set pengujian, dengan proses pelatihan dilakukan selama 100 epoch. Hasil evaluasi menunjukkan bahwa MobileNetV3 mencapai akurasi klasifikasi sebesar 100%, sedangkan YOLOv11 memperoleh akurasi sebesar 99,8%. Meskipun akurasinya sedikit lebih rendah, YOLOv11 menunjukkan kinerja yang stabil dengan kesalahan klasifikasi yang minimal. Analisis matriks kebingungan menunjukkan bahwa sebagian besar prediksi masuk ke dalam kelas yang benar, dengan hanya sedikit kesalahan yang terjadi pada kategori yang secara visual mirip. Temuan ini menunjukkan bahwa kedua model tersebut sangat efektif untuk tugas klasifikasi varietas padi. Namun, evaluasi lebih lanjut menggunakan dataset yang lebih kompleks diperlukan untuk memastikan ketahanan dan generalisasi model dalam skenario dunia nyata.