Publication Search

Lake Rawa Pening is one of Indonesia’s priority lakes facing serious ecological pressure due to the rapid proliferation of water hyacinth. This study aims to classify and map the distribution of water hyacinth in Rawa Pening Lake during the 2021–2025 period and to analyze the seasonal distribution patterns of water hyacinth. Sentinel-2 imagery processed on the Google Earth Engine platform was classified using the Random Forest algorithm combined with hybrid sampling and spectral indices (NDVI, NDWI, MNDWI, and SRI). Classification accuracy assessment showed high performance with an Overall Accuracy of 97.45% and a Kappa coefficient of 0.949. The results indicate significant spatial-temporal fluctuations, with the highest coverage recorded in March–April 2021 (855.75 ha) and the lowest in May–June 2022 (108.44 ha). Seasonal-Trend Decomposition using Loess (STL) revealed consistent seasonal patterns, with peak expansion occurring during the rainy season, particularly in January–February. Although initial implementation of lake management policies reduced coverage, subsequent increases suggest that control measures remain insufficiently sustainable. This study demonstrates the effectiveness of cloud-based satellite monitoring for evaluating lake management policies and supporting evidence-based environmental management strategies.

Early Marriage in Pagar Alam City is currently still quite high, the Pagar Alam Religious Court only relies on a recap of the number of cases per year to draw conclusions about the early marriage data. This method has limitations in classifying early marriage factors, so the Religious Court has difficulty in monitoring and controlling the occurrence of Early Marriage in Pagar Alam City. The purpose of this research thesis is to produce a classification system for Early Marriage factors using the K-Nearest Neighbor Algorithm to find out what factors influence the occurrence of Early Marriage, the method used in this study is the Cross Industry Standard Process for Data Mining (CRISP-DM) which has 6 stages, namely: Business Understanding, Data Understanding, Data Preparation, Modeling, Evaluation, and Deployment. The testing stage in this study uses Confusion Matrix and BlackBox Testing. The final results of this study indicate that the system can classify Early Marriage factors. The classification model built achieved an Accuracy of 94.12% and a Precise value of 85.71% and a Recall value of 100.00%, while testing using Black Box testing in the form of alpha obtained a feasibility value of 83.2%, so this system is very suitable for use.  

Exports as a component of international trade contribute significantly to the development and growth of a country’s economy. In Indonesia, export activities are considered one of the key drivers in increasing national economic performance. This research seeks to evaluate the role of Indonesia’s exports to the United States within the Harmonized System (HS) Code 71 commodity classification, encompassing pearls, gemstones, precious metals, and jewelry products, in influencing Indonesia’s economic growth as reflected by Gross Domestic Product (GDP) at constant prices.The analysis focuses on three specific commodity groups: Pearls and Precious Stones (HS 71.01–71.05), Precious Metals and Metals Clad with Precious Metals (HS 71.06–71.12), and Jewelry and Related Articles (HS 71.13–71.18). A descriptive quantitative research design was employed, utilizing secondary time-series data collected for the 2015–2024 period. Data sources included the Indonesian Central Bureau of Statistics (BPS) and Trade Map. To assess the relationship between variables, this study adopted multiple linear regression analysis accompanied by classical assumption testing and hypothesis testing using both t-test and F-test procedures. The empirical findings demonstrate that export performance within the HS Code 71 category underwent considerable fluctuations throughout the observation period, reaching its peak in 2024.Furthermore, the statistical results indicate that each commodity sub-category contributes differently and exerts varying effects on Indonesia’s real GDP, both individually and collectively. The outcomes of this research are expected to provide useful references for government institutions in developing trade cooperation strategies and policy decisions, while also supporting business actors in strengthening the international competitiveness of Indonesian products.

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.

This study aims to analyze the forms and functions of balaghah istifham that deviate from their original meaning (khurūj al-istifhām ‘an muqtadhā al-ẓāhir) in Surah Ṭāhā and Surah al-Anbiyā’. The study employs a descriptive qualitative approach using content analysis. The research data consists of all verses containing the istifham style in both surahs. Data collection was conducted through the identification, classification, and interpretation of verses based on the theory of ma‘ānī. The results show that there are 45 forms of istifham distributed across both surahs, comprising 20 forms in Surah Ṭāhā and 25 forms in Surah al-Anbiyā’. Most of the istifham forms identified fall under the category of figurative (istifham majazi), while literal (istifham hakiki) forms appear only in certain verses. The dominant rhetorical functions include al-inkār, al-taqrīr, al-taubīkh, al-tahdīd, al-tašwīq, al-‘arḍ, and al-‘itāb. These findings indicate that the use of interrogative sentences in both surahs does not merely serve as a tool for asking questions, but also functions as a rhetorical instrument to construct arguments, affirm doctrinal messages, and strengthen the persuasive and educational effects of the Qur’an.

Hypertension is one of the leading non-communicable diseases contributing significantly to cardiovascular morbidity and mortality worldwide. Despite the availability of extensive electronic medical record data in healthcare institutions, these data are often utilized only for administrative reporting rather than predictive analysis. Consequently, opportunities to identify age groups with a higher probability of developing hypertension remain underutilized. This study aims to implement the Naïve Bayes classification algorithm to analyze age distribution and classify the risk of hypertension among patients using healthcare data. The research adopted the Cross-Industry Standard Process for Data Mining (CRISP-DM) methodology, including business understanding, data understanding, data preparation, modeling, evaluation, and deployment. Patient medical record data consisting of demographic and clinical attributes, including age, systolic blood pressure, diastolic blood pressure, body weight, gender, and hypertension status, were processed using the Naïve Bayes algorithm. Model performance was evaluated using a confusion matrix by measuring accuracy, precision, recall, specificity, and balanced accuracy. The implementation demonstrates that the Naïve Bayes algorithm is capable of classifying hypertension risk efficiently while providing probabilistic information regarding age groups with a higher tendency to experience hypertension. The resulting classification model offers an effective decision-support tool for healthcare providers in conducting targeted screening, preventive interventions, and evidence-based health planning. The findings also indicate that data mining techniques can transform routinely collected medical records into valuable clinical knowledge for early hypertension prevention and healthcare decision-making.

Background:Flooding is one of the most common environmental problems in residential areas and is closely related to poor community awareness of waste management. Improper waste disposal can clog drainage systems, increase the risk of flooding, and lead to various environmental health problems. Objective: This community service activity aimed to improve community knowledge and awareness regarding waste management and environmental health as an effort to prevent flooding in Panompuan Jae Village. Methods: The activity was conducted on May 22, 2026, at the Panompuan Jae Village Prayer House involving 15 women from a local religious study group. The educational methods included lectures, discussions, and interactive question-and-answer sessions. The materials covered waste classification, household waste management, environmental health, and the relationship between environmental cleanliness and flooding. Results: The activity improved participants’ understanding of proper waste management. Participants were able to distinguish between organic and inorganic waste and understood appropriate waste handling practices. They actively participated in the discussion and showed an initial commitment to disposing of waste properly and maintaining environmental cleanliness. Conclusion: The community education program successfully improved public knowledge and awareness regarding waste management and environmental health, supporting flood prevention efforts in Panompuan Jae Village.

Flooding remains a recurrent hazard in the Special Capital Region of Jakarta (DKI Jakarta), causing substantial disruptions across multiple dimensions community life, including social well-being and economic activities. The availability of flood-related information through the Jakarta One Data Portal (Satu Data Jakarta) provides significant opportunities for broader data utilization; however, transforming such information into meaningful assessments regional vulnerability requires a systematic analytical approach to generate more comprehensive understanding of the conditions of individual urban villages (kelurahan). This study focuses on the classification areas based on the characteristics and impacts of flood events occurring throughout DKI Jakarta. The analysis utilizes flood event records from 2023 to 2025 and incorporates several indicators, including the number of flood occurrences, the number of affected neighborhood associations (RW), the number affected households, the number of affected residents, the number of evacuees, the number of evacuation sites, and floodwater depth. Data processing was conducted using the Knowledge Discovery in Databases (KDD) framework, encompassing data selection, cleaning and preprocessing, transformation, pattern exploration, result evaluation, and knowledge extraction. The findings demonstrate that three-cluster solution effectively captures variations in flood vulnerability levels, corresponding to low-, moderate-, and high-risk categories. A total of 96 urban villages were classified as low-risk, 27 as moderate-risk, and 46 as high-risk areas. The resulting clustering patterns provide a clearer spatial representation of flood-risk distribution across urban villages, thereby offering valuable insights for the development more targeted mitigation strategies, the prioritization of flood management interventions, and the enhancement of evidence-based decision-making processes in DKI Jakarta.

Evaluating food portions and types in the Free Nutritious Meal (MBG) program is generally still performed manually, which is time-consuming and potentially subjective. This study aims to develop an automated deep learning-based system to efficiently detect food types and estimate their nutritional value. The method used is a quantitative experiment integrating the YOLOv11m architecture for real-time object detection and the Google Gemini 2.5 Flash Large Language Model (LLM) for contextual nutritional estimation reasoning. The model training utilized a dataset of 2,630 food tray images categorized into five classes (fruit, side dish, staple food, vegetable, milk) that had undergone an augmentation process. The results showed that the YOLOv11m model achieved excellent performance with a mean Average Precision (mAP@0.5) of 0.9727 and the highest F1-score of 0.9522 at a confidence threshold of 0.1. Furthermore, validation of the LLM integration demonstrated a high prediction agreement rate of 85%. In conclusion, the combination of the YOLOv11m algorithm and LLM reasoning is capable of detecting and validating nutritional classification quickly and precisely, showing strong potential as an objective nutritional evaluation monitoring solution for large-scale MBG program implementation.

The coffee shop industry has experienced substantial growth in recent years, creating intense competition that compels businesses to continuously enhance service performance in order to maintain customer satisfaction and market competitiveness. PT Jokopi Indonesia Group has encountered several service-related issues reflected in declining sales performance and recurring customer complaints, indicating the need for a comprehensive evaluation of service quality. This study aims to identify service attributes that fail to meet customer expectations and determine improvement priorities through the integration of the SERVQUAL and Kano methods. A quantitative approach was employed using questionnaire data collected from 50 customers who had prior experience with the company’s services. SERVQUAL was utilized to assess discrepancies between customer expectations and perceived service performance, while the Kano model was applied to classify attributes according to their contribution to customer satisfaction. The findings reveal that all evaluated attributes generated negative gap values, indicating that existing service performance has not yet reached the level expected by customers. The most critical gaps were identified in menu availability, air-conditioning and fan comfort, payment convenience, and straw availability. Kano classification further demonstrates that menu availability and thermal comfort facilities belong to the Must-Be category, meaning that failure to provide these attributes may trigger significant customer dissatisfaction. The integration of SERVQUAL and Kano highlights these attributes as the most urgent areas for improvement. The results provide managerial guidance for developing targeted service enhancement initiatives aimed at strengthening customer satisfaction, retention, and competitive advantage.

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.

Document-level sentiment analysis assigns a single polarity label to an entire review, often obscuring opinion diversity within multi-sentence submissions. This limitation is particularly evident in reviews of multi-service platforms, where users frequently express heterogeneous opinions toward different aspects of the platform in the same review. To address this challenge, this study proposes a sentence-level sentiment analysis framework for Indonesian Gojek app reviews collected from the Google Play Store. The proposed framework introduces a two-stage segmentation strategy that combines punctuation-aware rules with conjunction-aware splitting based on coordinating and adversative conjunctions (e.g., tapi [but], padahal [even though]) to identify opinion boundaries and decompose mixed-sentiment reviews into independently classifiable sentence units. A total of 14,730 raw reviews collected between May and July 2025 were subjected to data cleaning and quality filtering, resulting in 7,187 valid reviews that were further segmented into 14,187 sentence-level instances. Each instance was manually annotated by three annotators using a four-class labeling scheme consisting of app-positive, app-negative, app-neutral, and service categories. Sentiment-level inter-annotator agreement, computed on the subset of instances unanimously categorized as app-related by all three annotators (n = 4,384), achieved substantial agreement (Fleiss'  = 0.636). Hyperparameter optimization was conducted using Optuna with the Tree-structured Parzen Estimator (TPE) sampler across four experimental scenarios. The best performance was achieved by IndoBERTweet under Stratified K-Fold evaluation, attaining an accuracy of 0.751 and a macro F1-score of 0.729, outperforming all IndoBERT configurations. The results demonstrate the effectiveness of domain-adaptive pre-training on informal Indonesian text and highlight the value of conjunction-aware segmentation for preserving fine-grained opinion structures in mixed-sentiment reviews. These findings suggest that domain-aligned language representations provide a practical and effective solution for sentence-level sentiment analysis of Indonesian app reviews.

Clean water is a basic human necessity that plays a vital role in public health and well-being. However, access to clean water remains a challenge in many drought-prone areas. This condition requires effective planning and evaluation to ensure the sustainability of clean water supply programs. This article aims to examine the application of the Problem Solving Cycle (PSC) method in the planning and evaluation of clean water supply programs in drought-prone regions. The study employed a literature review method by analyzing various scientific articles and relevant documents. Data were analyzed descriptively through identification, classification, and information synthesis. The findings indicate that PSC supports program planning and evaluation through the stages of problem identification, cause analysis, action planning, implementation, monitoring, and evaluation. Clean water supply programs contribute to improving community access to safe water and adequate sanitation, although several challenges remain, including limited resources, infrastructure management issues, and program sustainability. Therefore, PSC can serve as an effective approach to support the success of clean water supply programs in drought-prone areas.

The effectiveness of zakat management within the educational sector plays a crucial role in improving mustahik welfare. This study aims to analyze the management of zakat by the School Zakat Management Unit (UPZ) at SMKN Pringkuku Pacitan in enhancing the well-being of its beneficiaries. Utilizing a descriptive qualitative approach, data were gathered through interviews, direct observations, and documentary reviews. The findings reveal that the zakat management mechanism has been structured systematically, encompassing collection, distribution, and mustahik classification based on the eight categories of asnaf. Specifically, professional zakat (zakat profesi) is collected via a 2.5% monthly salary deduction from civil servant (PNS) and government employee (PPPK) staff, while zakat fitrah is accumulated from all teachers, staff, and students. The allocated zakat funds are regularly distributed to underprivileged students, orphans, and the community residing around the school environment. This financial intervention is proven to yield a positive impact by supporting educational expenses, fulfilling daily basic needs, and boosting students' learning motivation. The implication of this study emphasizes that the school-based zakat management model holds significant potential to be replicated as an effective social empowerment instrument to secure student welfare.

This study aims to map the trajectory of syntactic acquisition in three-year-old children through syntactic patterns and communicative functions in naturalistic interaction. Using a mixed-methods approach, data from native Indonesian-speaking children were collected over a period of 1.5 months through the involve-conversation technique. Analysis of 80 utterances using frequency distribution, Mean Length of Utterance (MLU), and functional grammar revealed a dominant Subject–Verb–Object (S–V–O) structure (30%) and an MLU of 5.82 morphemes. These findings indicate a developmental transition from telegraphic speech to early multi-clause constructions, reflecting increasing linguistic complexity. Cognitive compensation is marked by the use of pragmatic particles and non-canonical sentence patterns driven by ideational, interpersonal, and textual functions. The results support the usage-based hypothesis, suggesting that early syntactic development is functional, sequential, and non-linear in nature. Furthermore, the study highlights the role of interactional experience in shaping emerging grammatical competence. This classification serves as a micro-longitudinal assessment tool and provides a pedagogical basis for scaffolding interventions aimed at stabilizing complex linguistic patterns and enhancing language development in early childhood education settings.

The Free Nutritional Meal Program (MBG) is a government policy that is widely discussed by the public through social media, especially TikTok. Various comments that have emerged indicate differences in public opinion towards the program, so an analysis is needed to determine the tendency of public sentiment. This study aims to analyze TikTok user sentiment towards the Free Nutritional Meal Program using the Naive Bayes method. The research method is carried out through several steps, namely collecting TikTok comment data, preprocessing text, labeling sentiment data into positive, negative, and neutral, feature transformation using TF-IDF, and classification using the Naive Bayes algorithm. Based on the analysis of 500 comment data, the results show that positive sentiment dominates public opinion by 42% (210 data), followed by negative sentiment by 36% (180 data), and neutral sentiment by 22% (110 data). Testing the classification model using Naive Bayes produces excellent performance with an accuracy rate of 86%, precision of 84%, recall of 85%, and F1-score of 84%. The conclusion of this study shows that the Naive Bayes method is effective as an approach in social media sentiment analysis to map public responses to government policies.

Batik motif classification has attracted growing attention in visual computing due to its role in cultural heritage preservation, textile informatics, museum documentation, and automated cataloging. Although many studies report high classification accuracy, robustness under real-world acquisition conditions remains insufficiently understood. Batik images are frequently affected by illumination variation, blur, folds, watermark overlays, wearable deformation, scale inconsistency, and background clutter, creating challenges that extend beyond conventional image-noise assumptions. Existing studies largely focus on improving classification performance, while the interactions among acquisition variability, feature representation, evaluation practice, and deployment constraints remain fragmented. This systematic literature review addresses this gap by synthesizing batik classification research through a robustness-aware perspective. Using query expansion, backward and forward citation chaining, relevance screening, and thematic coding, 116 candidate records were identified, resulting in 50 highly relevant studies for detailed analysis. The review reveals that robustness is shaped less by denoising alone than by the combined effects of acquisition conditions, representation design, evaluation realism, and deployment context. Handcrafted descriptors remain competitive for small datasets and structured motifs due to their data efficiency and interpretability, whereas deep learning models achieve the highest reported accuracy when supported by sufficient data diversity and realistic augmentation. Hybrid representations emerge as the most consistently balanced approach, combining local texture stability with higher-level abstraction across heterogeneous acquisition settings. The review further identifies recurring robustness failure patterns, including background dependency, illumination instability, motif-scale inconsistency, wearable deformation, and source-shift vulnerability. Based on these findings, a robustness-oriented research agenda is proposed, emphasizing cross-acquisition evaluation, representation-stability analysis, batik-specific robustness benchmarks, acquisition-aware augmentation, and deployable lightweight or hybrid architectures. The study contributes a domain-specific synthesis that reframes batik motif classification from an accuracy-centric task toward a robustness-aware visual recognition problem.

Malware represents an evolving cybersecurity threat that demands more effective detection methods. Conventional signature-based detection systems have limitations in identifying new variants, driving the development of deep learning-based approaches. This research implements and evaluates four variants of the YOLOv11 algorithm (n, s, m, l) for malware classification based on visual image representation. The dataset consists of 22,056 malware and benign images, divided into 70% training, 15% validation, and 15% testing across 8 classes (adware, backdoor, benign, downloader, spyware, trojan, virus, worm). Each model was trained for 100 epochs with batch size 32 using Google Colab with GPU support. Results demonstrate that all variants achieve high accuracy (97.8%-98.1%) with YOLOv11m as the best performer (98.1%). YOLOv11n offers optimal balance between accuracy (97.9%) and efficiency (1.5M parameters, 0.3 ms/img inference) ideal for real-time applications. This research surpasses previous methods such as K-NN (97.18%) and hybrid CNN (96.55%) with superior inference speed (0.3-0.9 ms/img vs tens to hundreds of ms/img), proving the effectiveness of YOLOv11 for fast, accurate, and scalable malware detection.

Sandstone aquifers in tropical sedimentary basins are major groundwater reservoirs, yet their public-health safety is often underestimated when assessment is restricted to physicochemical quality. This review addresses the persistent mismatch between chemically acceptable groundwater and microbiologically unsafe water, especially in shallow, permeable aquifers exposed to intense rainfall, pit latrines, septic systems, dumpsites, agricultural runoff, and weak wellhead protection. A structured narrative synthesis was conducted using peer-reviewed hydrogeological, hydrogeochemical, microbiological, vulnerability, and environmental health studies from Scopus, Web of Science, ScienceDirect, SpringerLink, and Google Scholar. The review focused on tropical sandstone aquifer systems in Africa, Asia, and South America. It examined lithological controls, major-ion evolution, microbial indicators, contamination pathways, WHO-based classification, Water Quality Index applications, contamination indices, multivariate statistics, GIS-based vulnerability mapping, and integrated hydro-microbial risk scoring. The synthesis shows that groundwater chemistry is governed mainly by silicate weathering, carbonate dissolution, cation exchange, shale interbeds, residence time, and anthropogenic inputs. However, chemical compliance does not confirm potable safety. Reported evidence includes TDS below 500 mg/L in chemically acceptable Nigerian basin aquifers, while all 12 shallow wells in Abeokuta tested positive for total coliform and Escherichia coli. Microbial loads increased during wet seasons, with Calabar groundwater recording total coliform increases from 76 to 468 CFU/100 mL and Salmonella/Shigella reaching 1081 CFU/100 mL. DRASTIC mapping further classified 21% of the Dahomey Basin as highly vulnerable. The review therefore proposes an integrated framework linking hydrochemistry, microbial evidence, vulnerability, GIS, and health-risk interpretation for safer, adaptive, and evidence-based groundwater governance.

This study was conducted to analyze the relationship between students’ critical thinking skills and mathematical problem-solving abilities through a literature review approach. The study is based on the importance of mastering higher-order thinking skills in the mathematics learning process, particularly when students are faced with complex problems related to real-life situations. The method used in this research was a literature review by examining various relevant scientific journals and academic books published between 2021 and 2026. The data analysis process was carried out through stages of identification, classification, evaluation, and synthesis of the collected sources. The findings revealed a significant and positive relationship between critical thinking skills and students’ mathematical problem-solving abilities. Critical thinking skills play an important role in helping students understand problems, process and analyze information, select appropriate solution strategies, and systematically review the results obtained. Students with strong critical thinking skills generally demonstrate more optimal mathematical problem-solving abilities. In addition, the implementation of learning models such as Problem-Based Learning and contextual approaches has been considered effective in improving both abilities. Therefore, critical thinking skills are regarded as an essential aspect that needs to be developed in mathematics learning in order to enhance students’ mathematical problem-solving abilities.