Publication Search

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.

Manufacturing accounts for about 28.9% of global final energy use, making inefficient operations a major source of cost and greenhouse gas emissions. This review synthesizes how artificial intelligence supports energy optimization within Industry 4.0-enabled manufacturing systems. It organizes methods into four families: machine learning for forecasting and anomaly detection, deep learning for nonlinear and temporal modelling, reinforcement learning for adaptive scheduling and real-time control, and metaheuristics for balancing energy, throughput, and quality objectives. Applications span plant-level demand prediction and peak management, shop-floor rescheduling under dynamic pricing, equipment-level optimization through predictive maintenance, and system-wide planning using digital twins and cyber-physical integration. Reported benefits include lower energy costs, reduced downtime, improved productivity, and progress toward decarbonization. However, large-scale deployment is constrained by poor data quality and interoperability across IIoT, MES, ERP, and EMS platforms, high implementation and computational costs, skills gaps, and weak governance and benchmarking standards. Emerging solutions include federated learning and edge AI for privacy-preserving, low-latency analytics, explainable AI to enhance trust and auditability, tighter smart-grid integration, and circular economy-driven optimization. The review concludes with practical priorities for reliable, transparent, and scalable AI-enabled energy management.

The increasing sophistication of malware has rendered traditional signature-based detection methods insufficient, necessitating behavior-driven and adaptive analytical frameworks. This study presents a sequential deep learning framework that models system-level API call sequences as structured linguistic representations for behavioral malware detection. Unlike conventional comparative studies, this work systematically evaluates recurrent and attention-based architectures under controlled experimental conditions, with a particular focus on generalization performance and overfitting mitigation. Two neural architectures, a Long Short-Term Memory (LSTM) network and a Transformer-based attention model, are trained on publicly available API call sequence data for binary classification of malicious and benign executables. Beyond standard accuracy metrics, the study further examines model stability, convergence behavior, and the impact of long-range dependency modeling on detection robustness. Experimental results demonstrate that the Transformer architecture achieves superior performance, attaining 95.54% classification accuracy and consistent improvements in precision, recall, and F1-score, indicating a stronger ability to capture complex behavioral dependencies. These findings highlight the effectiveness of attention mechanisms in behavioral malware modeling and provide empirical evidence that NLP-inspired architectures offer a robust and scalable approach for real-world cybersecurity applications.

This study is based on the suboptimal management of waste transportation in Tanjungpinang City, caused by limited fleet capacity, uneven service routes, a lack of human resources, and inconsistent implementation of Standard Operating Procedures (SOPs). This situation has led to waste accumulation at various points and an excessive load on the Ganet Final Disposal Site (TPA), which uses a controlled landfill system. The system aims to minimize pollution through waste compaction, soil covering, and leachate and methane gas management, but its implementation has not been optimal due to limited facilities and infrastructure. This study aims to evaluate the management of waste transportation to the Ganet landfill and identify the obstacles that arise. The approach used is descriptive qualitative with observation techniques, in-depth interviews, and document analysis, involving the Environmental Agency, the Ganet Landfill Technical Implementation Unit, field officers, fleet drivers, and residents around the Temporary Cleaning Site (TPS). The findings reveal that waste transportation management is already being carried out through standard operating procedures (SOPs) and inter-unit coordination, but is still hampered by fleet limitations, landfill capacity that is nearly full, service routes that do not cover the entire area, and minimal community participation. Therefore, additional fleets, infrastructure improvements, strengthened supervision, and community outreach are needed to achieve sustainable waste management.

This study aims to analyze the factors influencing the implementation of Regional Regulation of Gorontalo Regency Number 04 of 2014 concerning the Control of Livestock in Ilomata Village, Bilato District. This research employs an empirical legal method with a sociological juridical approach to examine law not only as written norms but also as a social practice within society. Data were collected through interviews with village officials, regional regulation enforcement officers, and livestock owners, as well as through documentation and literature studies. The collected data were analyzed qualitatively using Lawrence M. Friedman’s legal system theory and Soerjono Soekanto’s theory on factors influencing law enforcement. The results indicate that the implementation of the regional regulation has not been optimal. The influencing factors include legal substance, legal structure (law enforcement officers), facilities and infrastructure, community factors, and legal culture. Normatively, the regulation contains clear provisions; however, its implementation is hindered by inconsistent enforcement, limited supporting facilities, and low levels of public legal awareness. Legal culture and the lack of consistency among law enforcement officers are the most dominant factors affecting the effectiveness of the regulation’s implementation. Therefore, it is necessary to strengthen consistent law enforcement, improve supporting facilities, and undertake continuous efforts to build public legal awareness in a participatory manner.

This study aims to analyze the legal provisions on land rights for foreign nationals in the Indonesian land law system and to examine the validity and legal consequences of nominee agreements in the control of land rights by foreign investors. The background of this study is based on the practice of using nominee agreements (borrowing names) by foreign nationals to control land in Indonesia, which legally contradicts the provisions of the Basic Agrarian Law (UUPA) which prohibits ownership of land rights by foreign parties. This study uses a normative legal research method with a legislative approach and a conceptual approach. The legal sources used include primary, secondary, and tertiary legal materials that are analyzed qualitatively. The results of the study indicate that the regulation of land rights for foreign nationals in the Indonesian legal system is limited to use rights, lease rights, or through certain legal entities such as Foreign Investment Limited Liability Companies (PT PMA). Meanwhile, the practice of nominee agreements is a form of legal smuggling that contradicts the basic principles of national agrarian law, so that the agreement can be declared null and void. In addition, this practice creates legal uncertainty and has the potential to harm the state and society because it obscures the status of land ownership. In conclusion, firm law enforcement and regulatory harmonization between agrarian and investment law are needed to ensure legal certainty and safeguard state sovereignty over land, without hindering foreign investment in Indonesia.

This community service activity aims to improve the effectiveness of clean water distribution management through the implementation of a Water Level Control (WLC) system as an automatic control for water pumps and three-phase motors at a regional drinking water supply company in Lamongan. The methods employed include field observation, problem identification, system design and implementation, as well as periodic evaluation of system performance. The activity focuses on the water treatment unit by conducting control and monitoring of operational parameters such as frequency (Hz), pump pressure, and flow stability to ensure optimal water distribution according to consumer needs. The results indicate that the implementation of the WLC system enhances operational efficiency, minimizes human error, and supports more structured and sustainable equipment maintenance. In addition, this activity contributes to improving the knowledge and technical skills of personnel in operating, monitoring, and maintaining automated control systems. In managing automation-based technology in a professional and independent manner, human resource capacity is strengthened, while the quality of clean water services is also improved through this community service program.

This study aims to analyze gender-based political violence in the 2020 Regional Head Elections in South Tangerang City and its impact on women’s representation in politics. The case analyzed involves social media attacks against Rahayu Saraswati Djojohadikusumo during her campaign for Deputy Mayor, in which an old photo of her while pregnant was used as material for sexually charged attacks. This study employs a qualitative method using a case study approach through literature review. The analysis utilizes Kate Manne’s theory of misogyny, which views misogyny as a social mechanism within the patriarchal system to control and discipline women entering the public sphere. The results of the study indicate that gender-based political violence manifests in the form of the moral delegitimization of women, digital intimidation or harassment, policing of women in public spaces, and the objectification of women’s bodies. These phenomena demonstrate that gender bias remains a barrier for women in securing equal space in local political contests.

Vegetables are an important horticultural commodity in fulfilling community nutritional needs; however, their consumption level in Indonesia remains relatively low, necessitating efforts to increase production. Spinach (Amaranthus sp.) is a promising vegetable due to its short growth cycle, ease of cultivation, and high nutritional value. Limited agricultural land, particularly in urban areas, poses a major constraint to conventional cultivation, thereby encouraging the adoption of alternative technologies such as hydroponics. The hydroponic system, especially the Nutrient Film Technique (NFT), offers efficient use of land and water while enabling better control of plant growth. This review aims to identify hydroponic cultivation techniques for spinach in greenhouse conditions and to analyze factors influencing its success, including nutrient concentration, growing media, pH, temperature, and light intensity. The findings indicate that optimal nutrient concentration ranges from 410–900 ppm, supported by proper environmental and pH management to enhance vegetative growth. The implementation of the NFT system improves production efficiency, resulting in more uniform, cleaner, and higher-quality yields. Nevertheless, challenges remain, including nutrient management, environmental fluctuations, and pest and disease risks. Therefore, proper and sustainable system management is essential to ensure successful hydroponic spinach cultivation.

Women's leadership plays an important role in the success of organizations, including in the government sector at the sub-district level. Leaders not only act as directors but also as mentors who are able to understand the needs and character of their subordinates. The female head of TG Sub-district in Surabaya City demonstrates the application of reciprocal relationships between leaders and subordinates through a system of rewards and punishments according to performance achievements, actively monitors subordinate performance, identifies work standard errors, and takes corrective actions. The study aims to analyze the application of transactional leadership style by the female head of TG Sub-district in Surabaya City using Bernard M. Bass's (1990) theory. The type of research used is a qualitative research method with a descriptive approach. Data collection techniques were carried out through observation, interviews, and documentation. Samples were determined using purposive sampling, and data sources included primary and secondary data. The research results indicate that the transactional leadership style of the female village head in TG Village is not yet fully optimal. The application of Contingent Reward can increase motivation and employee performance control, but its implementation in the community is still limited. Management by Exception (Active) carried out on employees has not been consistent, and its application in the community is also not sufficiently felt. Management by Exception (Passive) and Laissez-Faire are shown through corrective actions after problems arise and the freedom to take initiative and make decisions according to standards and policies. The implementation of transactional leadership by female village heads needs to be improved, especially in strengthening the mechanisms of reward and punishment as well as the consistency of supervision of employees and the community so that the leadership implementation runs more optimally.

This study aims to design and develop a functionally efficient and operationally effective Internet of Things (IoT)-based air quality monitoring system for radiology departments. The system utilises a DHT22 sensor integrated with an ESP32 microcontroller to monitor the temperature and humidity of diagnostic rooms in real time, and to display the data via the UdaraKu mobile application. The research method employed a quantitative experimental approach focused on measuring system performance, specifically the accuracy of the temperature and humidity sensors. The research model used was the Research and Development (R&D) method, aimed at transforming conventional air quality monitoring in radiology into a real-time digital system based on IoT. The research results indicate that the IoT-based monitoring system is capable of maintaining room temperature and humidity stability within the ideal range, namely 22–24°C and 50–60% RH, in accordance with international standards. This improvement in environmental stability has a direct impact on reducing noise in digital radiography images, as evidenced by an increase in the Signal-to-Noise Ratio (SNR). Instrument validation demonstrated a high level of reliability with a Cronbach’s Alpha value of 0.848, reinforcing the reliability of the data and the system. Overall, the IoT-based air quality monitoring system has proven effective in controlling noise in digital radiography images, improving the quality of diagnostic services, and supporting patient safety principles and operational efficiency within radiology departments.

Hypertension is a chronic health problem whose prevalence continues to increase and is a major risk factor for cardiovascular disease. In addition to pharmacological therapy, non-pharmacological interventions are needed to help control blood pressure safely and sustainably. One complementary therapy that has the potential to lower blood pressure is Slow Stroke Back Massage (SSBM), which works through relaxation mechanisms and modulation of the autonomic nervous system. This study aims to determine the effect of SSBM therapy on reducing blood pressure in hypertensive patients in the Camar Room of RSKD Dadi, South Sulawesi Province. The study used a quantitative quasi-experimental design with a two-group pretest–posttest design. A sample of 32 respondents was selected using a purposive sampling technique, divided into an intervention group and a control group. Data collection was carried out by measuring systolic and diastolic blood pressure before and after the intervention using a standard sphygmomanometer. The results showed a significant decrease in systolic and diastolic blood pressure in the group receiving SSBM therapy compared to the control group. Thus, SSBM therapy has a significant effect on reducing blood pressure in hypertensive patients and can be recommended as a complementary therapy in nursing care.

Bullying in the school environment is a social health problem that has a massive impact on children’s physical, mental, and social well-being. As the primary educational environment, schools need to implement a structured, safe, and child-friendly bullying reporting system. Objective: This conceptual study aims to design the implementation of a bullying reporting system based on school health administration using the functional management approach: planning, organizing, actuating, and controlling (POAC). The methods and components of the reporting system are designed through the four POAC pillars, namely the establishment of an Anti-Bullying Team, the preparation of Standard Operating Procedures (SOPs), the provision of child-friendly reporting media both physical and digital through the School Health Unit (UKS), and the development of monitoring and evaluation mechanisms (controlling). School health administration is used as an initial screening tool to identify indications of victim trauma discreetly and safely. The implementation of this POAC-based system is expected to improve the early detection of bullying cases, accelerate case handling responses, and eliminate stigma and fear of reporting among children. Conclusion: The integration of health administration and POAC management has proven to be a strong framework for creating a safe, inclusive school environment that strongly supports students’ mental health recovery.

In the era of digital transformation, the utilization of information technology in business activities has become an important factor in improving operational efficiency and effectiveness. Dzikri Baby Shop, a business engaged in the sale of baby equipment, still faces challenges in managing sales transactions and inventory manually, which may lead to recording errors, process delays, and less optimal customer service. This study aims to design and develop a sales information system for Dzikri Baby Shop to support digital transformation in its business processes. The system development method used in this research is Rapid Application Development (RAD), as it enables software to be developed in a relatively short time through an iterative approach and active user involvement. The system developed includes product data management, sales transaction processing, inventory control, and report generation. The testing results using the Black Box Testing method show that all system features function in accordance with user requirements. Therefore, the implementation of this sales information system is expected to improve operational efficiency, accelerate transaction processes, minimize errors in data management, and enhance the quality of customer service.

This research aims to control the planning of inventory control of palm raw materials to obtain the optimal quantity of raw material orders at PT. Gruti Lestari Pratama in 2020. The method used in this research is the model of Period Order Quantity (POQ) method which is the development of the Economic Order Quantity (EOQ) method. The result of this research obtained an optimal order quantity using the POQ method in 2020 which is 7.563,08 tons. The frequency of ordering based on company policy is 314 times in a year, while using the POQ method the order frequency 23 times in a year. Where safety stock with POQ method of 2.702,50 tons and reorder point of 3.256,35 tons. Total inventory cost of palm raw material by using POQ method of Rp. 8.907.361.822 in a year. Overall, this study shows that the application of the POQ method in controlling palm oil raw material inventory at PT. Gruti Lestari Pratama provides optimal results in reducing order frequency, saving costs, and ensuring timely raw material availability. The results of this study can serve as a basis for the company to implement a more efficient and effective inventory control system, supporting smooth production at a more affordable cost.

The money market plays a vital role in the global financial architecture as a provider of short-term liquidity and a primary channel for monetary policy transmission. This research is motivated by the rapid transformation of financial instruments, which now encompass conventional and Sharia-compliant sectors, as well as digital innovations such as e-money and stablecoins. The purpose of this study is to examine the concept of the money market, identify the diversity of modern instruments, and analyze their strategic role in economic stability through a qualitative literature review approach. The analysis shows that the money market is highly effective in managing bank cash reserves and controlling inflation by regulating the money supply. The presence of digital instruments has been proven to accelerate liquidity flows, while Sharia schemes provide transparent and equitable investment alternatives. However, the emergence of digital assets also brings challenges of volatility that require adaptive regulation and professional skepticism from market participants. The implications of this research emphasize the importance of synergy between monetary authorities and financial technology to address global disruption. Strengthening regulations on future instruments is expected to create a more inclusive and stable financial system that can respond precisely to economic shocks.

This study aims to analyze the effect of implementing STEM-based learning integrated with ethnoscience on improving science process skills, learning interest, and learning outcomes of students at SMAN 1 Girimarto. This study uses a quantitative approach with a quasi-experimental research type. The research design used is One Shot Case Study, which is a design that only involves one experimental group without a control group. The population in this study were all students in grade XI at SMA Negeri 1 Girimarto. The research sample was 32 students in grade XI D. The sampling technique used purposive sampling. The results of observations of basic science process skills (KPSD) show varying achievements across five main indicators, with patterns that reflect the level of cognitive difficulty of each skill. The overall average score of 73.06 (medium category) indicated that students collectively responded positively to the integration of local wisdom values in science learning, although individual variability remained. The distribution of student learning outcomes shows very encouraging academic achievement with a dominance of good to very good categories, indicating the success of the implementation of ethnoscience-based STEM learning in improving understanding of excretory system concepts. It can be concluded that the implementation of STEM learning based on ethnoscience on the excretory system material has a positive impact on the three aspects of learning studied with varying levels of success.

This study examines the evolving landscape of racket sports and its implications for injury patterns among diverse athlete populations. Over the past decade, traditional sports such as tennis and badminton have remained popular, while emerging sports like padel, pickleball, and beach tennis have experienced rapid growth, attracting participants across a wide age spectrum. However, the high-speed, repetitive, and multidirectional demands of these sports increase the risk of musculoskeletal injuries, making it essential to understand their epidemiology for effective prevention. This systematic literature review followed PRISMA 2020 guidelines, analyzing peer-reviewed studies published between January 2020 and early 2025 from databases including PubMed, ScienceDirect, Europe PMC, and Open Alex. A total of 22 studies met the inclusion criteria, comprising randomized controlled trials, cohort studies, and cross-sectional surveys. Methodological quality was assessed using the Cochrane Risk of Bias Tool (RoB 2) and the Newcastle-Ottawa Scale (NOS). The findings reveal significant variation in injury prevalence across sports, ranging from 34.2% in recreational pickleball to 92% in competitive padel. Badminton injuries were predominantly acute and affected the lower limbs, while tennis showed a higher incidence of overuse injuries in the upper limbs and trunk. Padel players frequently experienced elbow overuse injuries, with higher rates reported among females. In contrast, pickleball injuries were largely associated with falls among older adults. Preventive interventions involving supervised, sport-specific functional training and structured warm-up programs were found to be most effective. In conclusion, injury burden in racket sports is substantial and influenced by both intrinsic and extrinsic factors, highlighting the need for targeted, sport-specific prevention strategies.

This research review identifies and analyzes the potential of Romaine lettuce (Lactuca sativa var. longifolia) cultivation using the Nutrient Film Technique (NFT) in greenhouse environments as a high-value horticultural commodity. Horticulture is a strategic sector in Indonesia for improving farmer welfare and meeting the growing demand for healthy food. Conventional farming faces challenges such as land conversion, climate instability, and high pesticide residues. This study examines how the NFT hydroponic system serves as an innovative solution by providing controlled environments that enhance growth and quality. Findings indicate that Romaine lettuce grown via NFT achieves higher productivity and faster harvest cycles, with a feasibility study showing an R/C ratio of 2.40, indicating high profitability. Furthermore, the integration of controlled environment agriculture supports urban farming initiatives and mitigates risks from climate change and pests. This review concludes that adopting NFT technology is essential for developing a sustainable, efficient, and high-quality agricultural system in Indonesia, particularly in urban areas with limited space.

The hospitality industry is a strategic sector within the global tourism system that heavily depends on service quality and food safety assurance. In hotel operations, the pastry division represents a high-risk unit due to the use of perishable ingredients and intensive manual handling processes. This study aims to analyze the implementation of hygiene and sanitation practices in the Pastry Division of Hotel Aruss Semarang in supporting food safety standards within the hospitality industry. This research employs a qualitative approach with a case study design. Data were collected through participatory observation, semi-structured interviews, and document analysis, including Standard Operating Procedures (SOPs), sanitation checklists, and temperature control records. Data validity was strengthened through triangulation and member checking, while thematic analysis was used to identify key implementation patterns. The findings indicate that the implementation of personal hygiene, environmental sanitation, and Good Manufacturing Practices (GMP) has generally complied with most of the requirements of Good Processed Food Manufacturing Practices (CPPOB). The availability of sanitation facilities, periodic medical check-ups, equipment maintenance, and FIFO-based storage systems demonstrate management commitment to preventive risk control. However, inconsistencies in handwashing practices and minor construction details that do not fully meet hygienic design standards indicate areas requiring improvement. Overall, hygiene and sanitation implementation in the Pastry Division has been effective in supporting food safety. Strengthening behavioral compliance, continuous training, and facility optimization are recommended to achieve a more sustainable and comprehensive food safety management system.