The Android-based inventory management application for MSMEs is designed to enhance efficiency and accuracy in inventory management for micro, small, and medium enterprises (MSMEs). The application offers features such as adding, reducing, and updating stock items, tracking transaction history, and generating real-time stock and sales reports. With an intuitive and user-friendly interface, this application simplifies inventory management for users. User data security is ensured through secure authentication, data encryption, and regular backups. Continuous maintenance and user support are also provided to ensure the application remains stable and meets user needs. This application contributes to the digitalization process of MSMEs, helping them improve operational efficiency and compete in an increasingly digital market.

The development of information technology in the digital era provides a great opportunity for business actors to improve service quality, operational efficiency, and expand marketing reach through the use of e-commerce platforms. However, Bakso Koko as a culinary business still uses a conventional ordering and payment system, which often causes various obstacles such as slow service processes, a high risk of transaction recording errors, difficulties in managing order data, and limitations in reaching a wider customer base. These problems indicate the need for a more effective, integrated, and easily accessible system for customers. This study aims to design and build an Android-based Bakso Koko e-commerce application integrated with a payment gateway so that the ordering and payment process can be carried out online more easily, quickly, safely, and efficiently. The system development method used in this study is the Waterfall method which includes the stages of requirements analysis, system design, implementation, testing, and maintenance. The analysis technique used is system requirements analysis through observation and interviews to understand the ongoing business process, then modeled using the Unified Modeling Language (UML) in the form of use case diagrams and activity diagrams. The research results show that the application was successfully designed and built with user registration, a product catalog, a shopping cart, ordering, online payment, order status tracking, and integrated product and transaction data management. This system is expected to improve service efficiency, transaction efficiency, and expand the business's marketing reach.

This study aims to develop and evaluate a deep learning-based mobile application for the automated classification of ornamental plants, addressing challenges associated with visual similarity among species and environmental variability during image acquisition. The proposed system utilizes a Convolutional Neural Network (CNN) based on the MobileNetV2 architecture, selected for its lightweight structure and deployment efficiency on resource-constrained mobile devices. The dataset comprises approximately 600 images representing 10 ornamental plant classes, collected from real-world environments, and processed through a standardized preprocessing pipeline. Model training was conducted using the Teachable Machine platform over 100 epochs, with a batch size of 16 and a learning rate of 0.001, allocating 90% of the dataset for training and 10% for testing. Experimental results indicate that the proposed model achieves a classification accuracy of 96.3%, corroborated by evaluation metrics including accuracy curves, loss convergence, and class-wise performance analysis. The trained model was successfully converted into a lightweight format and integrated into an Android-based mobile application developed using the Flutter framework. Functional testing demonstrates that the application performs effectively in real-time classification scenarios, maintaining high accuracy and responsive on-device inference without relying on cloud computing. In conclusion, this study confirms that lightweight deep learning architectures, such as MobileNetV2, can be effectively implemented in mobile environments for ornamental plant classification. The proposed application enhances accessibility and usability, enabling rapid and accurate plant identification. Furthermore, this approach contributes to practical applications in horticulture, education, and biodiversity awareness, while demonstrating the feasibility of deploying efficient deep learning models on mobile platforms.

The demand for electric vehicles (EVs) is increasing rapidly due to high fuel prices and rising environmental concerns. EVs are considered a better option compared to petrol and diesel vehicles because they help reduce pollution and harmful emissions. However, even with these advantages, EV users still face some difficulties in daily use. One of the main problems is finding nearby charging stations, especially in unknown areas. This situation leads to range anxiety, where users worry about their vehicle battery getting discharged without access to a charging point. To solve this issue, this project presents an Androidbased mobile application that helps users locate EV charging stations easily. The main goal of the application is to provide a simple, fast, and easy-to-use platform for EV users. The app uses GPS to identify the user’s current location and shows nearby charging stations on a map. It also provides useful details such as station location and navigation support to help users reach the station without confusion. The application is developed using Android Studio, while Firebase is used as a cloud database for storing and managing data. Google Maps API is integrated to display maps and provide navigation. The design of the app is kept simple so that even new users can operate it without any technical knowledge. This system improves the overall experience of EV users by saving time and reducing effort in searching for charging stations. It also supports the adoption of electric vehicles by making charging facilities more accessible. In future, features like slot booking, online payment, and real- time updates can be added to enhance the system further

Background: Adolescent girls are particularly vulnerable to reproductive health problems due to limited knowledge and inadequate access to reliable information. Innovative educational strategies are needed to improve their understanding of reproductive health. Objective: This study aimed to evaluate the effectiveness of Android-based reproductive health education in improving knowledge among adolescent girls. Methods: A quasi-experimental study with a pretest–posttest control group design was conducted among 100 female students at a senior high school in Takalar, Indonesia. Participants were divided into an intervention group (n = 50) and a control group (n = 50). The intervention group received reproductive health education through an Android-based application, while the control group continued routine school activities. Knowledge was assessed using a structured questionnaire administered before and after the intervention. Data were analyzed using descriptive statistics and the Mann–Whitney U test. Results: The intervention group showed a substantial increase in mean knowledge scores from pre-test to post-test (11.52 ± 3.04 to 17.54 ± 2.29), while the control group demonstrated only a slight change (12.86 ± 3.74 to 13.24 ± 4.22), indicating greater short-term knowledge improvement in the intervention group. Conclusion: Android-based reproductive health education effectively improves knowledge among adolescent girls and represents a promising digital approach for school-based health promotion

This study examines the effectiveness of the URUBAH game as an Android-based Arabic learning application developed using the ADDIE instructional model and Unity 3D software, with the aim of improving second-language (L2) learners’ Arabic writing proficiency. The game was designed to support Indonesian learners of Arabic who experience difficulties in spelling, grammar, and sentence structure. It addresses these challenges by focusing on the morphological and syntactic features of Arabic while considering structural differences between Arabic and English writing systems. The objectives of this research are twofold: first, to develop an interactive digital learning tool that enhances Arabic writing skills through gamification; and second, to evaluate its effectiveness in comparison with traditional teaching methods. A mixed-methods approach was employed, integrating quantitative data derived from pre- and post-tests with qualitative insights gathered from surveys and learner feedback. The findings indicate that the game positively improves writing outcomes, including learners’ accuracy, fluency, and overall engagement. In addition, learners’ motivation increased, accompanied by reduced anxiety when practicing Arabic writing through the interactive platform. In conclusion, the URUBAH game presents a promising instructional approach with practical applications for teaching Arabic as a second language. It also demonstrates the potential of integrating advanced digital technology into language classrooms to enhance learning experiences

Abstract Managing daily expenses is a challenging task in today’s fast-paced lifestyle. Many individuals fail to track their spending resulting in, poor financial planning and unnecessary expenses. The proposed Expense - Mate Application is an Android-based mobile application designed to help users manage and monitor their daily expenses efficiently. The application allows users to add expenses, categorize transactions, filter records, and view analytics through graphical representations such as pie charts. It also generates monthly reports in PDF format. The system is designed to work offline, ensuring accessibility anytime and anywhere. This application reduces manual effort, improves financial awareness, and helps users maintain better budgeting habits.

The limited digitalization of buying and selling activities remains a significant challenge for micro, small, and medium enterprises (MSMEs), particularly at the local level. Although national e-commerce platforms continue to grow, many local MSMEs still face obstacles related to accessibility, usability, and system relevance to their business context. This condition underscores the need for localized e-commerce solutions designed to support MSME digital transformation. This research aims to design and develop an Android-based e-commerce application for Baubau City, named Oli Gholi Pay. The main objective is to produce an e-commerce application design that is easy to recognize, user-friendly, and relevant for MSME actors, local government stakeholders, and the general public. The study employs a descriptive qualitative approach combined with application Development methods. Data were collected through observations, interviews, and focus group discussions involving MSME actors. The prototype Development method was applied through the following stages: requirement identification, initial prototyping, prototype evaluation, application coding, testing, final evaluation, and implementation. The research scope includes participant recruitment analysis, system requirement analysis, system architecture and interface design, Development, functional testing, and application implementation and maintenance. The study successfully produced a functional design of a local Android-based e-commerce application that supports online transaction processes and aligns with MSME operational needs. The results indicate that Oli Gholi Pay can support MSME digitalization by expanding market access and facilitating secure, sustainable digital transactions, while also serving as a reference model for future local e-commerce application Development.

Mathematics learning in elementary school often relies on repetitive exercises that can reduce student engagement and motivation. Digital game-based learning provides opportunities to create interactive learning environments by integrating instructional content into gameplay. In addition, ethnomathematics emphasizes connecting mathematical concepts with familiar cultural contexts. One traditional Indonesian game with mathematical potential is Dakon, which involves counting, comparison, and distribution activities. This study aimed to develop and evaluate a culturally contextualized digital mathematics game based on Dakon for elementary school students. The study contributes by integrating ethnomathematics into a structured digital game-based learning environment using the ADDIE instructional design model. The game was implemented as an Android-based application using Unity game engine with a rule-based AI opponent. Arithmetic questions were embedded into gameplay across three progressive levels to support gradual learning. The implementation involved twenty third-grade students from MI Fajar Siddiq Elementary School in Palembang, Indonesia. System functionality was validated using black-box testing, while user evaluation was conducted using a 13-item Likert-scale questionnaire measuring usability, attractiveness, effectiveness, and user acceptance. The results showed that all system features functioned as expected. User evaluation indicated positive perceptions with mean scores of 4.19 (usability), 4.17 (attractiveness), 4.38 (effectiveness), and 4.30 (user acceptance), with an overall mean of 4.25 and a feasibility percentage of 85%. The reliability test yielded a Cronbach’s alpha of 0.88, indicating strong internal consistency. These findings suggest that integrating culturally relevant games into digital learning environments can enhance engagement and support mathematics learning.

The ripeness level of bananas is an important indicator that determines the quality, selling value, and suitability of distribution in the agricultural supply chain. However, manual maturity assessments are still subjective and difficult to apply consistently on a large scale. The use of Convolutional Neural Networks (CNN) offers a more accurate and objective solution, but most previous studies have only evaluated high-powered devices so they do not reflect the real performance of low-spec smartphones. This study aims to compare the efficiency of three lightweight CNN architectures: MobileNetV1, EfficientNetB0, and NASNetMobile for the classification of banana ripeness and evaluate its feasibility of being implemented on low-end Android devices. The research method included model training using the Banana Ripeness Classification dataset containing 13,478 images with three maturity classes. Augmentation-based oversampling was applied to address data imbalances, while all three models were trained on transfer learning strategies before being converted to the TensorFlow Lite format. Direct testing was conducted on the Samsung Galaxy A3 (2016) device to measure accuracy, inference time, model size, and RAM usage. The experimental results showed that MobileNetV1 provided the best performance with an accuracy of 98.14%, an inference time of 287.57 ms, and a model size of 3.23 MB, much more efficient than EfficientNetB0 and NASNetMobile. In conclusion, MobileNetV1 is the most optimal architecture for Android-based banana ripeness classification applications on low-spec devices, while making an empirical contribution to the selection of efficient CNN models for mobile implementation in the context of digital agriculture.

This study aims to develop an android-based Javanese phoneme pronunciation tech culture application for learning Javanese at the sound level. This research uses a simplified research and design (R&D) research method of the Borg & Gall model. The research stages include the pre-development, development, and post-development stages. The data in this study are in the form of vowel phonemes, consonants, and Javanese language clusters and their realization in Javanese words. The source of research data is in the form of literature related to Javanese phonology as well as phonologists and linguists.

Augmented reality (AR) has become a pivotal tool for enhancing museum engagement through interactive experiences. This study developed and evaluated an Android-based AR application for the Popa Eyato Archaeological Museum, comparing marker-based (Vuforia), and markerless (EasyAR) tracking methods. While previous studies often focus on technical development, this research provides empirical insights into usability within the Southeast Asian Museum context. Using a mixed-methods approach with 35 participants, the application was evaluated using the system usability scale (SUS) and handheld augmented reality usability scale (HARUS). Results show that the application achieved an average SUS score of 78, classified as “Good” and “Acceptable”. The comparative analysis reveals that while marker-based AR offers higher stability, markerless AR provides greater flexibility for spatial exploration. However, environmental factors like museum lighting significantly impact markerless tracking performance. These findings offer practical recommendations for museum curators and AR designers in selecting appropriate tracking technologies based on infrastructural constraints and visitor demographics. The study concludes that balancing technical stability with user mobility is essential for optimizing digital heritage preservation and educational engagement in regional museums.

A diagnosis tool for early detection and classification of heart disease in individuals using transformer mechanisms.

Wasting among children remains a major global public health problem. Strengthening cross-sector collaboration is considered an effective approach to address this issue. This study aimed to analyze the development of the e-RESTO Balita innovation in strengthening cross-sector collaboration commitment in efforts to control wasting. This study employed a quantitative pre–post test design involving 20 participants representing cross-sector stakeholders in the Banyuanyar Community Health Center work area. Data were collected using questionnaires measuring application development and cross-sector collaboration commitment, supported by interviews. Statistical analysis was performed using the Wilcoxon test. The findings showed that the development of the e-RESTO Balita application significantly improved and strengthened cross-sector collaboration commitment in efforts to control wasting (p 0.05). The development of the e-RESTO Balita innovation was effective in enhancing cross-sector collaboration in the management of child malnutrition. Future development of the system is recommended through the integration of a more user-friendly Android-based application to facilitate faster and easier access for stakeholders.

The Kreasi Tani Group in Bunton Village, Cilacap Regency, faces two main challenges in developing oyster mushroom cultivation and pioneering shallot cultivation. First, the significant water requirement for mushroom spraying and shallot seedling watering causes quite burdensome electricity costs for water pump operations. Second, the farmer group does not yet have an adequate financial bookkeeping system, making it difficult for them to accurately monitor financial conditions and make strategic considerations for future business development. This community service activity aims to implement two technological solutions. The first solution is to design and install a Solar power plants system to operate the water pump. Solar power plants system uses 2 200 Wp photovoltaic units, 1 1500 VA inverter unit, and 2 60 AH batteries. The second solution is to develop and train the use of an Android-based mobile bookkeeping application (created with MIT App Inventor) designed to record production results, prices, and summarize sales results of oyster mushrooms and shallots periodically (weekly or monthly). The implementation of Solar Power Plant system can significantly reduce production costs through electricity savings. Meanwhile, mobile bookkeeping applications make it easier for managers to create financial reports, provide accurate data sources, and support strategic decision-making for future business development.

Background: Radiation plays a vital role in medical diagnosis and treatment. However, insufficient radiation protection education poses serious risks to patients and healthcare professionals. Nursing students often have limited formal training, and traditional lecture-based methods foster passive learning, which may not promote deep understanding. Augmented reality (AR) technology offers a novel approach by overlaying digital models onto real-world images, enabling students to intuitively visualize abstract concepts such as time, distance, and shielding. This study was conducted to evaluate an AR-based radiation protection application integrated with conventional lectures to enhance the knowledge of nursing students and calibrate their perceptions of radiation safety.Materials and Methods: A cross-sectional, pre–post-intervention study was conducted at Tokyo Metropolitan University among 80 second-year nursing students (95% female) without prior radiation safety training. The intervention comprised two phases: a standardized 90-minute lecture covering the nature and biological effects of ionizing radiation and the principles of time, distance, and shielding; and a hands-on AR session using an Android-based application that overlays a three-dimensional model of scattered radiation dose onto a live camera view, demonstrating exposure effects. Radiation knowledge was assessed using a 50-item questionnaire, and risk perception was measured using a 30-item, seven-point Likert scale. Data in this study were analyzed using nonparametric tests and compared with reference data.Results and Discussion: Post-intervention knowledge scores were significantly higher than pre-intervention and reference scores (<i>p</i><0.05). Additionally, risk perception ratings for ‘nuclear power’ and ‘X-ray’ decreased by one rank, suggesting a more balanced and realistic evaluation of risks.Conclusion: Integrating AR with traditional lectures significantly improves radiation protection knowledge and risk assessment among nursing students, supporting the promising role of AR in healthcare education. Future research should include longitudinal follow-up and explore AR features, such as dose simulation.

Communication deficits are a common challenge experienced by children with Autism Spectrum Disorder (ASD). Existing Augmentative and Alternative Communication (AAC) applications, such as VICARA, are limited to unidirectional communication—only transmitting raw card sequences to another application (e.g., "I, Eat, Noodle"). This limitation renders the conversation flow non-interactive and prone to miscommunication. This study aims to develop a new version of VICARA, named Talk of the Heart AAC, a bidirectional Android-based application capable of bridging the communication gap between autistic children and their caregivers. The application is designed to translate the constructed card sequences into complete, natural, and semantically logical sentences in Bahasa Indonesia through the implementation of a Sequence-to-Sequence model with a Gated Recurrent Unit architecture augmented by an attention mechanism. To train the model, a synthetic dataset comprising 7,000 data pairs was generated using the Google Gemini API and validated by a speech-language pathology expert. Model evaluation results demonstrated a good performance in sentence translation, yielding a BLEU score of 42.95%, ROUGE-1 94.94%, ROUGE-2 87.12%, and ROUGE-L 93.70%. From the application perspective, non-functional testing produced an average System Usability Scale score of 91.67, categorized as "excellent."

Urbanization and migration for education and employment have significantly increased the demand for rental accommodations. However, traditional rental systems suffer from inefficiency, lack of transparency, and poor communication mechanisms. This paper presents StayEasy, an Android-based rental accommodation application developed using Android Studio and integrated with Firebase services. The application provides secure authentication, property listing, advanced search filtering, and real-time booking functionality. The proposed system enhances accessibility, transparency, and efficiency in rental management while ensuring scalability and data security. Experimental results show improved response time and user satisfaction compared to traditional rental processes.

Chicken eggs are a widely consumed animal food commodity, along with other products such as chicken meat, beef, and milk. Chicken eggs are produced by laying hens, scientifically known as Gallus gallus domesticus. Manual grading of chicken eggs in West Sumatra relies on subjective sensory assessment, resulting in inconsistent classification outcomes. The development of a chicken egg grading application using Android-based digital images is a solution to this problem. This study presents the development and validation of an Android-based digital image processing system for automated mass-based grading of chicken eggs using the five-grade local classification system in Payakumbuh (pelor, bujang, remban, super, and jumbo). The image processing pipeline employed Otsu thresholding for segmentation, mean filtering for noise removal, and eccentricity-based shape determination to calculate egg volume, which was subsequently converted to Mass using a density constant of 1.0801 g/cm³. A total of 100 eggs were tested: 67 for correlation analysis and 33 for validation. The system achieved a mass correlation coefficient of r = 0.9986, a volume correlation of r = 0.9976, a mass RMSE of 0.4486 g, and a volume RMSE of 0.3972 ml. Out of 67 tested samples, 64 were correctly classified (95.5% accuracy). These results confirm that the developed application can reliably replace manual grading for small-scale poultry farmers, providing a practical and measurable digital innovation for the agricultural sector. These results indicate that Android-based image processing applications exhibit small errors, enabling the designed application to be implemented. Contribution to Sustainable Development Goals (SDGs):SDG 2 (Zero Hunger)SDG 8 (Decent Work and Economic Growth).SDG 9 (Industry, Innovation and Infrastructure)SDG 12 (Responsible Consumption and Production)

Background: The rapid expansion of agent banking in Indonesia has increased the need for reliable and timely delivery of financial technology applications. The choice of Software Development Life Cycle (SDLC) methodology plays a critical role in project schedule performance, yet empirical comparisons particularly involving hybrid approaches within regulated banking environments remain limited. Objective: This study analyzes the impact of SDLC methods on project time performance in IT application development, with particular attention to the testing phase as a recurrent source of delay. Method: A quantitative comparative design was applied to 18 internal IT projects conducted in 2025 using Waterfall and Agile methodologies across Android-based EDC applications, mobile apps, and web systems. Independent-samples t-tests were used to examine differences in Schedule Performance Index (SPI), actual project duration, and delay. A phase-selective Hybrid SDLC was subsequently implemented in the EDC Android v1.0.5 project, applying Agile practices in testing while maintaining Waterfall in other phases. Result: Statistically significant differences were found between Agile and Waterfall across all time performance indicators, with Agile demonstrating superior schedule outcomes. The hybrid implementation further improved performance, reflected by an SPI greater than 1 and reduced testing duration. Conclusion: A phase-selective Hybrid SDLC provides an effective strategy to enhance schedule performance, particularly when testing is a bottleneck. The findings support selective SDLC adoption based on phase-specific characteristics. Limitations include the single-institution scope and absence of cost and quality metrics, suggesting directions for future multi-institutional research.