Publication Search

Object detection plays a crucial role in intelligent transportation systems, particularly for outdoor traffic monitoring applications that require accurate and real-time performance under limited computational resources. Recent developments in YOLO-based architectures have introduced multiple model variants; however, their practical performance under constrained training conditions remains insufficiently explored. This study presents a comparative evaluation of YOLOv5, YOLOv7, and YOLOv8 for outdoor traffic object detection using a real-world dataset and identical experimental settings. The main objective of this research is to analyze the robustness and detection quality of different YOLO variants when trained with a limited number of epochs, reflecting practical deployment scenarios. All models were trained and evaluated using the same dataset, preprocessing pipeline, and hardware configuration to ensure a fair comparison. Performance evaluation was conducted using multiple metrics, including precision, recall, mAP@50, Precision–Recall curves, area under the curve (AUC), and peak F1-score. Experimental results indicate that YOLOv5 outperformed YOLOv7 and YOLOv8 in terms of overall detection stability and robustness. The merged Precision–Recall analysis shows that YOLOv5 achieved a higher effective AUC and superior mAP@50, reflecting better global detection performance. In addition, YOLOv5 exhibited a higher peak F1-score, indicating a more balanced trade-off between precision and recall. In contrast, YOLOv7 and YOLOv8 showed performance degradation under limited training conditions despite their more advanced architectures. These findings suggest that YOLOv5 remains a reliable and efficient solution for outdoor traffic object detection, particularly in resource-constrained environments. The study highlights the importance of comprehensive evaluation metrics and practical experimental settings when selecting object detection models for real-world applications.

Attention mechanisms have been widely incorporated into recurrent neural network architectures for financial time series forecasting, with most prior work reporting improvements in price-level error metrics. This study revisits that claim through a controlled empirical comparison of four deep learning architectures on nearly two decades of Telkom Indonesia (TLKM) closing price data from the Indonesia Stock Exchange (IDX). The models evaluated are a three-layer Gated Recurrent Unit (GRU) baseline, a comparable Long Short-Term Memory (LSTM) network, a Bahdanau end-attention GRU (Attn-GRU-V2), and a multi-head self-attention GRU hybrid (Attn-GRU-V3). Each architecture is trained over 30 independent runs with distinct random seeds, and performance is reported as 95% confidence intervals derived from the t-distribution. Statistical comparisons employ the Wilcoxon signed-rank test, a nonparametric paired test appropriate given the confirmed non-normality of residuals. The main finding is a consistent trade-off: the plain GRU achieves the lowest RMSE (94.02 ± 1.22 IDR) across all 30 runs, while Attn-GRU-V2 achieves the highest directional accuracy (45.91 ± 0.09%), surpassing GRU in every independent run. Bahdanau attention weights are nearly uniform across the 30-day lookback window (coefficient of variation: 3.21%), indicating that the mechanism cannot identify selectively informative timesteps in this univariate price series. This finding is consistent with the weak-form Efficient Market Hypothesis for the Indonesian market. An ablation study reveals that a 20-day lookback window maximizes directional accuracy (47.72 ± 0.21%) for the Attn-GRU-V2 model. These results suggest that Bahdanau end-attention consistently and significantly improves directional accuracy relative to a plain GRU baseline, providing an architecturally attributable advantage for direction-based applications, even when absolute price-level error is not reduced. The directional accuracy values remaining below 50% across all models are consistent with a weak-form efficiency characterization of the Indonesian market.

Instagram has evolved into a digital public sphere that enables collective interaction and the expression of social identity, particularly within the context of sports fandom. This study aims to analyze the representation of social identity among supporters of the Indonesian National Football Team in digital interactions found in the comment section of the "Round 4" post on the official Instagram account @timnasindonesia. This research employs a qualitative approach using netnography to examine communication practices, symbols, language, and emotional expressions manifested in online interactions among supporters. The analytical framework is grounded in Social Identity Theory proposed by Tajfel and Turner, which emphasizes three core processes: social categorization, social identification, and social comparison. The findings reveal that Instagram comment sections function as arenas for constructing collective identity among Indonesian national team supporters. Social categorization is reflected in the symbolic boundaries formed between "us" as supporters and "others" as outsiders or opponents. Social identification is expressed through displays of national pride, emotional loyalty, the use of national symbols, and narratives of digital solidarity. Meanwhile, social comparison emerges through evaluations of rival teams, criticism of dissenting voices, and efforts to maintain a positive in-group image. These results indicate that digital fanaticism toward the Indonesian National Team extends beyond sports support, representing a form of digital nationalism and social identity construction in the new media environment. This study contributes to digital communication scholarship by deepening the understanding of how social identity and nationalism are negotiated through symbolic interaction on social media platforms.

Gout arthritis, or often called gout, is a type of arthritis caused by the accumulation of uric acid crystals in the joints and surrounding tissues. Arthritis itself is a term used to describe inflammation of the joints. The process of gout begins with an increase in uric acid levels in the blood, called hyperuricemia. Gout arthritis sufferers in the world affect approximately 10% to 25% of the world's population, the WHO prevalence of gout arthritis in the world is 34.2%. The type of research used in this study is quantitative research using a quasi-experimental research method, namely the pre-posttest control one group design method. This study is a study conducted on 1 group using an intervention without a comparison. This study has been conducted with a total of 20 elderly people who meet the inclusion and exclusion criteria. It is known that the Sig. (2-tailed) value of 0.00 is greater than 0.05. then there is a significant difference between the results before and after the warm cinnamon water compress. So it can be concluded that there is an effect of warm cinnamon compresses (Cinnamomun Burmannii) on gout arthritis in the elderly at the Sei Pancur Community Health Center.

Ineffective spare part inventory planning may lead to supply delays and reduced compliance with lead time supply key performance indicators (KPIs). This study aims to implement the Collaborative Planning, Forecasting, and Replenishment (CPFR) method in spare part inventory planning at PT XYZ and to compare lead time supply performance before and after the implementation of the CPFR method. This research utilizes spare part usage data from January to June 2025, focusing on fast-moving spare parts. Demand forecasting is conducted using an error forecasting approach with the moving average method. Forecast accuracy is evaluated using the Mean Absolute Deviation (MAD) and Mean Absolute Percentage Error (MAPE). Furthermore, inventory planning is carried out through the calculation of safety stock and reorder point (ROP) as the basis for determining replenishment decisions. The results indicate that the simulated implementation of the CPFR method provides a more structured and anticipative inventory planning process. The comparison of performance before and after the application of CPFR shows an improvement in lead time supply compliance with the established KPIs. Therefore, the CPFR method has the potential to support improved spare part inventory planning performance at PT XYZ.

This study was conducted to examine how social media influences Fear of Missing Out (FOMO) behavior among its users. The research employs a qualitative method with a literature review approach by analyzing and reviewing 20 previous research journals related to FOMO behavior in social media users. The reviewed journals were published. The findings indicate that FOMO behavior is driven by high-intensity social media use, in which increased frequency and duration of use are associated with higher levels of anxiety and fear of missing information and social experiences. Continuous exposure to content and activities shared by other users encourages social comparison, which contributes to increased anxiety, self-dissatisfaction, and difficulties in emotional regulation, particularly among individuals with low self-esteem. These conditions may lead to dependence on social validation and promote increasingly addictive patterns of social media use, which in the long term can reduce self-control and negatively affect psychological well-being. When self-esteem is low and psychological well-being is disrupted, individuals may experience heightened pessimism and an increased risk of engaging in self-harm behaviors. Overall, the findings suggest that self-regulation and self-determination serve as preventive factors against FOMO behavior and its psychological and mental health impacts; therefore, strengthening self-regulation and self-determination is essential to prevent FOMO.

Social media is one form of technological advancement that has become an integral part of students’ lives, including university students. Its use is not limited to communication and information sharing, but it may also generate psychological effects that influence both physical and mental health. The purpose of this review is to identify and explain the psychological impacts of social media use through appropriate theoretical approaches, which serve as a foundation for discussing the research findings. This study employs a literature review method by examining various academic books and relevant scientific articles. The findings indicate that excessive use of social media has the potential to cause psychological problems among university students, such as social comparison behavior, cyberbullying, decreased sleep quality, and reduced learning productivity. These issues are influenced by several factors, including the intensity of social media use, the type of content accessed, and individuals’ ability to manage emotions and time. Furthermore, uncontrolled social media use may lead to difficulties in social relationships, increased procrastination, poor time management, and reduced self-control in using social networking platforms. Therefore, students are encouraged to develop healthier patterns of social media use to reduce the risk of psychological disturbances. This review is also expected to assist healthcare professionals in understanding the relationship between the intensity of social media use and the occurrence of depressive symptoms among university students.

Hyperglycemia is a condition of elevated blood sugar levels that can potentially lead to various health complications if not controlled early. This condition is often influenced by unhealthy eating habits, lack of physical activity, and low awareness among adolescents regarding regular blood sugar checks. Adolescents are an age group that is vulnerable to lifestyle changes, putting them at risk of developing metabolic disorders later in life. This community service activity aims to increase adolescent knowledge and awareness regarding the dangers of hyperglycemia and the importance of preventive measures from school age. The activity was carried out at SMK Nurul Ulum Lebaksiu, involving 59 students as participants. The methods used included health education through audio-visual media, interactive lectures, discussions, and Random Blood Sugar (GDS) tests for early detection. The results of the activity showed an increase in student knowledge based on a comparison of pre-test and post-test scores, as well as the implementation of GDS tests on all participants. This activity is expected to foster healthy lifestyle behaviors and increase adolescent awareness of the prevention of non-communicable diseases.

This research aims to examine the implementation of group guidance services in developing a positive self-concept among students who actively use social media. The rapid development of digital technology has positioned social media as a space for self-expression, yet uncontrolled use often leads to negative social comparisons that distort adolescents' self-perception. This study employed a qualitative approach with a descriptive design. Data were collected through deep interviews, observations, and documentation involving students at IAKN Toraja. The findings indicate that group guidance services, conducted through the stages of formation, transition, core activity, and termination, significantly contribute to the formation of a positive self-concept. There is a notable improvement in students' self-confidence, self-acceptance, and self-control regarding social media usage. The group dynamics provide a supportive social laboratory for students to share experiences and receive constructive feedback, allowing them to reconstruct a more realistic and healthy self-image. The implication of this study suggests that group guidance can be an effective intervention for school counselors to mitigate the negative psychological impacts of digital interaction and foster digital literacy among students.  

The incidence of hypertension at the Tadoy Community Health Center reached 29.4%, with 78 cases reported among pregnant women in 2023, half of which were pregnancy-induced hypertension (HDK). Hypertension during pregnancy poses short-term risks to both mother and fetus. In addition to pharmacological treatment, non-pharmacological therapies such as warm water foot soaking and Ambon banana consumption are considered beneficial. This study aimed to examine the effects of these two interventions on reducing blood pressure in pregnant women with hypertension. This research employed a qualitative method with a case study approach involving two pregnant women diagnosed with hypertension. The results showed that warm water foot soaking significantly reduced blood pressure from 150/90 mmHg at the first visit to 130/85 mmHg at the second visit, and further to 120/75 mmHg. Similarly, Ambon banana consumption reduced blood pressure from 150/90 mmHg to 140/90 mmHg, and eventually to 120/80 mmHg. Although both interventions were effective, warm water therapy demonstrated greater effectiveness in lowering blood pressure compared to banana consumption. These findings suggest that simple, non-pharmacological interventions can help manage hypertension in pregnancy. It is recommended that pregnant women apply warm water foot soaking independently to help control blood pressure and reduce pregnancy-related risks.

Measuring coal volume in the Stock ROM area played an important role in production control and mining evaluation. This research was conducted in the Stock ROM area at PT. Victor Dua Tiga Mega, where volume measurements were generally carried out using Total Station (TS) as the main method, howefer the use of Unmanned Aerial Vehicles (UAV) has begun to be implemented as a more efficient alternative. This study aims to compare the results of Stock ROM coal volume calculations using the Total Station and UAV methods. The research method was carried out by collecting data in the field, processing the digital Elevation Model (DEM), and calculating the volume using the Cut and Fill method. The results of the study the difference in volume between the two methods, where the UAV measurement results tend to be greater than those of the Total Station. The difference in Fine Coal volume was 724,15 m3 or 16,74% and Raw Coal volume of 9.335,98 m3 or 8,03%. Based on a comparison with weighing data, measurements using the Total Station provided results that were closer to the actual conditions in the field.

Social media has become integral to the daily lives of Generation Z (Gen Z) in Indonesia, with intensive daily usage contributing to significant mental health concerns. This narrative review synthesizes evidence from the literature published between 2021 and 2026 to examine the primary mechanisms social comparison and fear of missing out (FOMO) underlying the negative effects of social media on mental health, including anxiety, depression, low self-esteem, sleep disturbances, and social isolation. Drawing from 15 key open-access articles (including 7 Indonesia-specific studies and 8 global comparisons), social comparison through curated content on platforms such as Instagram and Facebook was consistently associated with diminished self-satisfaction and heightened dissatisfaction. FOMO, particularly amplified by fast-scrolling algorithms on TikTok, promoted compulsive behaviors such as doomscrolling and exacerbated emotional distress. Digital wellness strategies, including digital detox, mindful usage, and media literacy, showed promising potential for mitigation, although long-term effectiveness remains limited in the Indonesian context. Notable research gaps include the scarcity of longitudinal studies, culturally tailored interventions, and data from rural or non-urban populations. This review recommends integrating digital literacy education into school curricula and developing community-based mental health programs to address risks in the 2025–2026 digital era. The findings offer insights for prevention and intervention strategies targeting Gen Z mental health in Indonesia.

The maritime education sector faces complex challenges in preparing competent seafarers amid the rapid advancement of digital technology. This study investigates the effect of artificial intelligence-based simulations and AI-based competency assessments on competency achievement levels among nautical cadets at Indonesian maritime training institutions. The research design employed a convergent parallel mixed-methods approach, integrating quantitative and qualitative methods to gain a comprehensive understanding. Quantitative data were collected from 150 cadets using a validated questionnaire. In comparison, qualitative data were obtained through in-depth semi-structured interviews with fifteen instructors and ten cadets. Multiple regression analysis revealed that the research model significantly predicted cadet competency achievement. The findings indicate that AI-based assessments exert a stronger influence than AI simulations in improving competency. The qualitative exploration highlighted adaptive feedback mechanisms and personalized learning pathways as critical success factors in implementing learning technologies. This study provides empirical evidence for maritime institutions to prioritize strategic investments in AI-based assessment systems while maintaining a human-centered pedagogy. The research contribution lies in integrating fourth industrial revolution technologies into the training, certification, and watchkeeping standards compliance framework for seafarers, thereby strengthening Indonesia's maritime education ecosystem and aligning it with international standards.

Transaction logs in online retail provide opportunities for data-driven customer segmentation. This study segments customers at two scopes global (all countries) and United Kingdom (UK) using Recency, Frequency, and Monetary (RFM) features derived from the Online Retail transaction dataset. After cleaning cancellations and invalid records, RFM variables are computed per customer and normalized. K-Means clustering is applied separately for global and UK data, while the number of clusters is selected via the elbow criterion and validated using internal indices. The best configuration for both scopes yields five clusters, with moderate separation quality based on the silhouette score. Cluster profiling indicates distinct groups ranging from low-frequency low-spending customers to highly frequent high-spending customers. The comparison between global and UK segmentation shows similar structural patterns, yet different proportions across segments, supporting targeted retention and value-driven marketing actions.

This study is motivated by the importance of systematic evaluation in ensuring the quality and effectiveness of the implementation of educational programs, particularly the Al-Qur'an Halaqah Program as a means of developing the ability to read and memorize the Al-Qur'an and shaping the religious character of female students. This study aims to identify the gap between the established standards and the actual implementation of the program using the Discrepancy Evaluation Model (DEM). The approach used is qualitative evaluative with five stages of evaluation, namely design, installation, process, product, and comparison. Data was obtained through interviews, observations, and documentation studies, then analyzed through the stages of data collection, processing, presentation, and conclusion drawing using triangulation techniques. The results showed that the design and installation stages met the standards, while in the process stage, a gap was found in the consistency of female student attendance. In the product stage, the success rate reached 93.48%, but there was still an imbalance in memorization achievement. The implication is that the program should be continued with strengthened attendance monitoring and individual mentoring strategies to improve the equity of outcomes and the sustainability of the program.

Background: TikTok usage among adolescents is increasing and has the potential to impact psychological aspects, particularly self-esteem. Adolescents, who are in the stage of developing their identity, are vulnerable to the influence of interactions and social comparisons on social media. Therefore, this study aims to determine the relationship between TikTok usage behavior and self-esteem levels in students at SMA Negeri 2 Semarang. Method: This study employed a descriptive correlational research design with a cross-sectional approach. The population consisted of 424 students from grade 11 at SMA Negeri 2 Semarang. Sampling was conducted using the Simple Random Sampling technique, resulting in a total sample of 206 respondents, determined by the Slovin formula. Bivariate analysis was carried out using the Spearman Rank Correlation test. Result: The results of the Spearman Rank statistical test showed a correlation coefficient (r) of -0.412 with a significance value of 0.000. The negative correlation indicates an inverse relationship between TikTok usage behavior and students’ self-esteem levels, meaning that the higher the intensity of TikTok use, the lower the self-esteem of the students. The correlation coefficient of 0.412 falls within the category of a moderate relationship. Conclusion: There is a significant relationship between TikTok usage behavior and self-esteem levels among high school students.

A student's learning success is largely determined by their academic evaluation. Estimating a student's final grade can assist educational institutions in conducting initial assessments of academic achievement. This study aims to analyze the performance of the Multiple Linear Regression (MLR) and Random Forest (RF) algorithms in predicting students' final grades using Google Colab. This research method uses a quantitative approach using secondary data that includes age, mid-term exam scores, final exam scores, and categorical variables as independent variables, with the final grade as the dependent variable. The research process is carried out through data preprocessing steps, dividing training and test data, model training, and performance evaluation using Mean Squared Error (MSE), Mean Absolute Error (MAE), and the coefficient of determination (R2). The results show that the Random Forest algorithm provides more accurate prediction accuracy compared to the Multiple Linear Regression algorithm, especially in identifying nonlinear relationships between variables. Therefore, the Random Forest algorithm is more recommended for predicting students' final grades with complex data characteristics.

The development of information and communication technology has changed the paradigm of proof in civil cases, where the interaction of the parties is now mostly carried out through electronic media such as instant messages, electronic mails, and digital documents. This condition places electronic evidence as an important instrument in the practice of civil justice. Normatively, the recognition of electronic evidence has been affirmed in Law Number 1 of 2024 concerning Electronic Information and Transactions (ITE Law), which states that electronic information, electronic documents, and their printed results are legal evidence. However, the application of these norms has not been completely consistent in civil justice practice. The assessment of the evidentiary strength of electronic evidence is still highly dependent on the discretion of judges, as there are no detailed technical guidelines regarding assessment standards, relevance, and adequacy. This inconsistency can be seen in a comparison of the Magelang District Court Decision Number 18/Pdt.G/2023/PN Mgg and the Decision of the Lolak Religious Court Number 3/Pdt.G/2022/PA. Llk, which shows the difference in the judge's approach in assessing electronic evidence. This study uses a normative juridical method with a legislative approach and decision analysis. The results of the study emphasized the need for reform of civil procedure law and the preparation of clear technical guidelines to realize uniformity and legal certainty in the assessment of electronic evidence.

State revenue holds a vital position in sustaining national development and the functioning of government, with taxation serving as the primary contributor to Indonesia’s State Budget (APBN). The substantial reliance on tax income obliges the government to manage the taxation system in an optimal, efficient, and sustainable manner. Nevertheless, the attainment of tax revenue targets in practice remains challenged by various issues, including structural, administrative, and strategic limitations. This study seeks to examine the role of strategic tax management in supporting the achievement of state revenue objectives. The research adopts a literature review approach by analyzing textbooks, national and international scholarly journals, official government publications, and relevant regulatory frameworks. The data are analyzed using a descriptive qualitative method through processes of classification, comparison, and synthesis of findings from previous studies. The findings reveal that strategic tax management has a crucial influence on enhancing state revenue performance through coherent policy formulation, flexible strategy execution, and ongoing performance assessment. The integration of information technology, the reinforcement of tax administration, and the improvement of taxpayer compliance emerge as key determinants in achieving revenue targets. Accordingly, strategic tax management constitutes a fundamental tool for ensuring fiscal resilience and promoting sustainable national development.

The phenomenon of Fear of Missing Out (FOMO) has become increasingly prominent among Generation Z due to the high intensity of social media use. Social media serves not only as a communication tool but also as a space for identity construction and the pursuit of social validation. Exposure to influencer content portraying ideal lifestyles, social achievements, and trending activities encourages individuals to remain constantly connected in order to avoid feeling left behind in digital communities. This study aims to analyze the influence of social media influencer content on the level of FOMO among Generation Z. The research employs a qualitative descriptive approach using a literature review method by examining relevant national and international academic journals published within the last five years. Data were analyzed by identifying patterns linking influencer content exposure, psychological mechanisms of FOMO, and its impact on Generation Z’s behavior and psychological well-being. The findings indicate that influencer content significantly contributes to social comparison processes and increases the need for digital validation, such as likes and comments, which are perceived as indicators of social acceptance. This condition strengthens FOMO tendencies and leads to excessive digital engagement, consumptive behavior, and psychological pressure. The discussion highlights that social media algorithms further intensify this cycle by repeatedly promoting popular and viral content. In conclusion, influencer content plays a crucial role in intensifying FOMO among Generation Z, emphasizing the importance of digital literacy and critical awareness to mitigate its negative effects.