Publication Search

This study aims to analyze the effect of the implementation of the Intelligent Tutoring Sistem (ITS) based on Artificial Intelligence (AI) on improving the understanding of mathematical concepts, especially in fractional and basic geometry materials, in Class V students of SD Negeri 2 Badran, Temanggung Regency. The research method used was a quasiexperimental experiment with a Non-equivalent Control Group Design. The research sample consisted of 48 students who were divided into two groups, namely the experimental group (n=24) who received learning with the help of AI-based ITS, and the control group (n=24) who received conventional learning with lecture methods and practice questions. The research instrument is in the form of a test of understanding of mathematical concepts that has been validated by experts and tested for reliability. Data were analyzed using parametric statistical tests of the Independent Sample t-test and N-Gain Score to measure the improvement. The results showed that there was a significant difference in understanding of mathematical concepts between the experimental group and the control group. The average post-test score of the experimental group (82.45) was significantly higher than that of the control group (70.12) with a p< value of 0.05. N-Gain analysis showed that the improvement in conceptual understanding in the experimental group was in the "moderate" category (g=0.56), while the control group was in the "low" category (g=0.32). These findings indicate that AI-based ITS is effective in improving students' understanding of mathematical concepts. The advantages of the system lie in its ability to provide instant feedback, personalize materials according to learning pace, and present interactive materials, thus helping to better construct students' conceptual understanding. It is recommended that schools consider the integration of ITS technology as a supplementary tool in mathematics learning at the elementary level.

This study focuses on the development of pumpkin shortcake (Curcubita moschata) as a dessert innovation, utilizing the potential of Indonesia’s local food resources, which are highly nutritious and widely available. Pumpkin is well known for its high dietary fiber content that supports digestion, as well as its antioxidant properties that may reduce the risk of cancer and chronic diseases. While traditional shortcakes are commonly made with strawberries, this innovation aims to substitute conventional ingredients with pumpkin, thereby not only enhancing nutritional value but also supporting the local farming economy. The main objectives of this research are to identify the production process and formulation of pumpkin shortcake, evaluate consumer acceptance of the product, and analyze packaging and presentation strategies that enhance consumer appeal. The production process involved selection, washing, steaming, and pureeing of pumpkin, followed by weighing, mixing, molding, baking, cooling, filling, and cutting. The third experiment successfully produced a product that met all sensory criteria, including color, taste, texture, and aroma. A hedonic test involving 35 untrained panelists indicated that pumpkin shortcake with 25% liquid milk and 75% pumpkin (Code 731) was the most preferred, particularly in terms of taste and color, while the 50% milk and 50% pumpkin formulation (Code 281) was most favored for aroma and texture. The findings conclude that the formulation of pumpkin shortcake with 25% liquid milk and 75% pumpkin is the most accepted by consumers. Attractive packaging and presentation are also emphasized as essential strategies to enhance product appeal and market value.

The development of the digital era has triggered a significant transformation in consumer shopping patterns, which have now shifted from conventional retail to Quick Commerce (Q-Commerce). This article analyzes the phenomenon of changing consumer behavior driven by preferences for speed, practicality, and time efficiency, with the COVID-19 pandemic as the main catalyst. The study highlights that the success of Q-Commerce is highly dependent on Logistics Service Quality (LSQ), particularly in terms of timeliness, courier interaction quality, and order condition. Despite offering convenience that disrupts physical retail, this business model faces serious sustainability challenges, including high last-mile operational costs, difficulty achieving profitability leading to the closure of several market players, and intense competition from hybrid retail models. In addition, traffic safety issues and increased carbon emissions are highlighted as social and environmental impacts. This study concludes that while Q-Commerce holds great potential, its sustainability requires strategic innovations that balance service speed with cost efficiency and ecological responsibility.vThe development of the digital era has triggered a significant transformation in consumer shopping patterns, which have now shifted from conventional retail to Quick Commerce (Q-Commerce). This article analyzes the phenomenon of changing consumer behavior driven by preferences for speed, practicality, and time efficiency, with the COVID-19 pandemic as the main catalyst. The study highlights that the success of Q-Commerce is highly dependent on Logistics Service Quality (LSQ), particularly in terms of timeliness, courier interaction quality, and order condition. Despite offering convenience that disrupts physical retail, this business model faces serious sustainability challenges, including high last-mile operational costs, difficulty achieving profitability leading to the closure of several market players, and intense competition from hybrid retail models. In addition, traffic safety issues and increased carbon emissions are highlighted as social and environmental impacts. This study concludes that while Q-Commerce holds great potential, its sustainability requires strategic innovations that balance service speed with cost efficiency and ecological responsibility.

Background: The development of industrial technology in the Industry 4.0 era has encouraged the implementation of intelligent monitoring systems to improve machine reliability and operational efficiency. However, machine fault diagnosis systems based on artificial intelligence often face limitations in terms of interpretability because the models used are complex and difficult to explain. Objective: This study aims to develop a deep learning-based industrial machine fault diagnosis system integrated with an Explainable Artificial Intelligence (XAI) approach to improve diagnostic accuracy while providing interpretable insights for users. Method: The research method involves collecting data from industrial machine sensors consisting of vibration signals, temperature measurements, and acoustic signals, followed by data preprocessing and feature extraction processes. The processed data are then used to train a deep learning-based diagnostic model, after which explainability methods such as SHAP or LIME are applied to analyze the contribution of each feature to the model’s prediction results. Model performance is evaluated using accuracy, precision, recall, and F1-score metrics. Results: The results indicate that the proposed deep learning model achieves better performance compared to conventional machine learning methods such as Support Vector Machine and Random Forest. Furthermore, the explainability analysis reveals that vibration amplitude, increases in machine component temperature, and anomalies in acoustic signals are the main factors influencing machine fault detection. Therefore, the proposed system not only improves the accuracy of machine fault diagnosis but also provides transparency in the decision-making process, thereby supporting the implementation of predictive maintenance in smart manufacturing environments.

The rapid development of modern manufacturing technology has driven the emergence of human-robot collaboration (HRC) as part of the transformation toward a human-centric intelligent production system. In collaborative work environments, robots are not only required to work efficiently but also to interact safely and responsively with operators. However, most conventional industrial robot systems still use rigid motion controls and are unable to dynamically adapt to human activity around them.This research aims to develop a human-robot collaboration system by integrating computer vision technology to detect operator movement and applying adaptive control algorithms to the robot manipulator. The research methodology includes designing a collaborative workstation, implementing a computer vision-based motion detection system, developing an adaptive control algorithm, and evaluating system performance through various experimental scenarios. Evaluation parameters include task completion time, safe distance, and system response time.The results show that the developed system significantly improves the efficiency and safety of human-robot interaction compared to conventional systems, with shorter task times, optimal safe distances, and faster system response to operator movements.

Background: The development of modern manufacturing systems requires production scheduling strategies that not only improve productivity but also optimize energy utilization. Multi-machine production systems with job-shop configurations exhibit high complexity due to dynamic interactions between machines, job queues, and varying processing times, making conventional scheduling methods less effective in handling changing operational conditions. Objective: This study aims to develop and evaluate a reinforcement learning based production scheduling approach to improve production efficiency while reducing energy consumption in multi-machine manufacturing systems. Methods: This research employs a job-shop based multi-machine production simulation model as the experimental environment. The scheduling problem is formulated as a Markov Decision Process, enabling the implementation of reinforcement learning algorithms, namely Q-learning and Deep Q-Network, to learn optimal scheduling policies through interaction with the simulation environment. Energy consumption parameters are incorporated into the reward function so that the learning agent can consider energy efficiency in the scheduling decision-making process. System performance is evaluated using three main metrics, namely energy consumption, throughput, and makespan. Results: The experimental results show that the reinforcement learning based scheduling approach achieves better performance compared to conventional scheduling methods, resulting in lower energy consumption, higher job completion rates, and shorter production completion times within the multi-machine manufacturing system.

Background: The increasing complexity of industrial production systems requires machine condition monitoring solutions that are capable of operating in real time with high accuracy and responsiveness to support predictive maintenance strategies. Conventional cloud based monitoring systems often experience limitations such as high latency and dependence on stable network connectivity, which can delay decision making processes in critical industrial operations. Objective: This study aims to design and evaluate an Industrial Internet of Things (IIoT) architecture based on edge computing to improve the efficiency of industrial sensor data processing and accelerate anomaly detection in industrial machines. Method: The research adopts an experimental approach by designing a system architecture consisting of a sensor layer, edge computing layer, and cloud layer. Industrial sensors, including vibration, temperature, and current sensors, continuously collect machine operational data, which are then processed locally at the edge node using a machine learning based anomaly detection algorithm. System testing is conducted in a simulated manufacturing environment to evaluate performance based on latency, reliability, and detection accuracy. Results: The results indicate that edge based data processing significantly reduces latency compared with cloud-based processing and enables faster responses to machine condition changes. Additionally, the implemented anomaly detection algorithm achieves high accuracy in identifying abnormal sensor data patterns.

Mosque-based community economic empowerment activities have significant potential to improve community welfare, particularly for small businesses in the mosque's immediate vicinity. However, implementation is still largely conventional and lacks a data-driven approach, resulting in suboptimal beneficiary identification and activity evaluation. This community service initiative aims to promote a data-driven approach to mosque-based community economic empowerment through sharia bazaar activities. Implementation methods include initial observation, outreach and education for mosque managers and business owners, technical assistance for sharia entrepreneurship, and activity evaluation. The results demonstrate an increased public understanding of the importance of data use in determining beneficiaries, managing bazaar activities, and developing businesses based on sharia economic principles. The outcomes of this initiative include improved data management literacy, a simple data collection format for sharia bazaar activities, and recommendations for developing a mosque-based data collection system. It is hoped that this initiative will be the first step in building a sustainable, transparent, and data-driven community economic empowerment model within the mosque environment.

Flower disease detection is a common challenge in modern agriculture. Various factors, such as changes in leaf color, shape, petal structure, and environmental conditions, make it difficult to achieve high accuracy with conventional models. Transfer learning is an effective solution to improve model performance in image detection, especially when available data is limited. This study used several pre-trained models, namely VGG16, ResNet50, and EfficientNet-B0, to detect three types of flower diseases: black spot on roses, white powdery mildew, and leaf rust. The process included data processing, increasing the data volume, model training, and result verification. The results showed that the EfficientNet-B0 model provided the highest accuracy of 97.2%, significantly better than the CNN model created from scratch with an accuracy of 85.1%. This study proves that the transfer learning method is very effective in improving the accuracy of flower disease detection. These results confirm that transfer learning is effective for detecting plant diseases with higher accuracy, especially when the dataset is limited.  

Empowering agricultural human resources is a strategic approach to support sustainable agricultural development and the achievement of the Sustainable Development Goals (SDGs), particularly SDG 2 (Zero Hunger), SDG 4 (Quality Education), and SDG 8 (Decent Work and Economic Growth). This community service article aims to describe the implementation of an agricultural instructor empowerment training program conducted through collaboration between Universitas Negeri Surabaya (Unesa) and the Ngudi Luhur Self-Reliant Agricultural and Rural Training Center (P4S) in Blitar Regency. The activity involved approximately 50 participants consisting of agricultural instructors and local agricultural practitioners. The methods included Focus Group Discussions (FGDs) and field visits to superior corn cultivation areas managed by P4S. The results indicate an increase in participants’ understanding of the importance of agricultural innovation and technology utilization to enhance productivity, supported by experiential learning through direct observation of high-yield corn fields compared to conventional practices. This program strengthens the role of agricultural instructors as innovation dissemination agents and contributes to the achievement of sustainable development goals in the agricultural sector.

This quasi-experimental study examines the effectiveness of Artificial Intelligence (AI)-assisted learning in enhancing critical thinking skills among undergraduate history students. The study involved 60 students divided into experimental and control groups. The experimental group received AI-supported instruction integrating adaptive learning modules, scaffolded source-analysis prompts, and guided argumentative discussions facilitated by conversational AI tools, while the control group followed conventional lecture-based instruction. Data were collected using a validated critical thinking test, classroom observation protocols, and semi-structured interviews. Quantitative data were analyzed using paired and independent sample t-tests, while qualitative data were examined through Miles and Huberman’s interactive analysis model. Results indicate statistically significant improvements in critical thinking scores in the experimental group compared to the control group. Thematic findings reveal enhanced sourcing, contextualization, corroboration, and evidence-based argumentation skills. However, minor risks of over-reliance on AI highlight the need for instructional scaffolding and ethical guidance. The findings suggest that AI can function as a cognitive scaffold that strengthens historical thinking and metacognitive awareness when implemented within a structured pedagogical framework.

Per capita expenditure is an important indicator of household welfare because it reflects the economic capacity and consumption patterns of the community, as explained in Engel's Law. In regions with diverse geographical characteristics such as Papua Province, spatial analysis is needed to understand the variations in expenditure between districts/cities and the differences between urban and rural areas. This study aims to analyze the spatial distribution of per capita expenditure percentages for food and non-food items in nine districts/cities in Papua Province during the 2022–2024 period. The research data was sourced from the National Socioeconomic Survey (Susenas). The methods used included quantile-based choropleth mapping using QGIS, attribute data merging through table joins, and Pearson's correlation test to evaluate the consistency of spending patterns between years. The analysis results show that food and non-food spending patterns were relatively stable during the observation period with high correlation values (r = 0,85–0,93), although spatial variations between regions were still apparent. Mamberamo Raya Regency consistently had the highest proportion of food spending (>68%), while Jayapura City showed the lowest proportion. These findings indicate spatial disparities related to urbanization levels and economic access. Spatial visualization proved effective in revealing regional disparity patterns that were not fully apparent through conventional statistical tables and has the potential to support the formulation of more evidence-based regional development policies.  

The discharge of surfactant-laden wastewater from the rapidly expanding laundry industry poses significant environmental risks, especially in densely populated urban areas. While constructed wetlands (CWs) and Eco-Enzyme technology have shown promise for surfactant remediation, their standalone application requires long hydraulic retention times (HRTs), limiting practical implementation. This study evaluated the efficacy of a novel integrated system combining a subsurface constructed wetland (SSFCW) with fruit peel-derived Eco-Enzyme to treat synthetic laundry wastewater. Over a 6-day treatment period, the combined system achieved a remarkable surfactant removal efficiency of 99.63%, reducing the concentration from 225 mg/L to 0.835 mg/L—well below the regulatory threshold of 3 mg/L. The synergistic degradation mechanism involves enzymatic hydrolysis via Eco-Enzyme lipase and protease activity, complemented by microbial mineralization in the wetland rhizosphere. This system maintains optimal environmental conditions, with a stable pH of 6.85-7.32 and a temperature of 30.9-35.2°C, supporting robust biological activity. These findings demonstrate that the integrated Eco-Enzyme/SSFCW system overcomes the limitations of conventional HRT approaches, offering a highly efficient, sustainable, and practical decentralized wastewater treatment solution for the laundry industry.  

The development of information technology has given rise to a new form of business transaction: the electronic contract. This contract form replaces the traditional process that requires a physical meeting between the parties. However, questions arise regarding the validity of e-contracts from the perspective of Indonesian civil law, specifically based on Article 1320 of the Indonesian Civil Code (KUHPerdata) and the provisions of Law Number 11 of 2008 concerning Electronic Information and Transactions (UU ITE). This research aims to analyze the validity of electronic contracts as legally binding agreements and to assess the extent to which the ITE Law can serve as their legal basis. Using a normative juridical legal research method, the research results show that e-contracts are valid and binding as long as they meet the requirements for the validity of an agreement under Article 1320 of the Civil Code, namely consent, capacity, a specific object, and a lawful cause. The ITE Law expands the recognition of electronic evidence and digital signatures as valid evidence in civil law. Thus, electronic contracts have the same legal force as conventional contracts, as long as they meet the principles of free will and the integrity of a reliable electronic system.

This study analyzes online fraud as one of the most common forms of cybercrime in Indonesia, which has expanded alongside rapid advances in information and communication technology. These crimes utilize digital platforms such as social media, online marketplaces, and fraudulent websites to deceive victims for unlawful financial gain. The research aims to examine online fraud from a criminological perspective by identifying its causes, patterns, and relevance to routine activity theory and differential association theory. A normative juridical method is employed, using statutory, conceptual, and case-based approaches, with qualitative and descriptive analysis. The findings show that online fraud reflects a shift from conventional fraud to digital-based crimes, driven by low public awareness of cybersecurity, easy access to technology, and weak online supervision. Several fraud schemes were identified, including online investment scams, phishing, and identity impersonation. This study highlights the need for an integrated approach that goes beyond law enforcement by emphasizing digital literacy, public education, and cross-sector collaboration to reduce cybercrime in Indonesia.

This study aims to develop an interactive digital learning media based on Wordwall, named TANGKAS (Tantangan Asyik Ngulik Pecahan Kelas Empat Seru), as a practice tool for addition and subtraction of fractions in fourth-grade elementary students. The development process employed the ADDIE model, which includes the Analyze, Design, Develop, Implement, and Evaluate stages. The research subjects consisted of 29 fourth-grade students at SDN Ngemplak I Baureno. The needs analysis revealed that learning activities were still dominated by conventional methods with limited use of digital media, resulting in low student engagement. To address this issue, TANGKAS was developed using a maze chase game design to enhance motivation and support engaging fraction practice. The validation results indicated a material validity score of 94% (highly valid) and a media validity score of 80% (valid). The practicality aspect obtained 81.8% from students, both categorized as highly practical. The effectiveness test showed an improvement in learning outcomes with N-Gain scores of 0.6 for fraction addition and 0.54 for fraction subtraction, both classified as moderate. Therefore, TANGKAS is proven to be feasible, practical, and effective as an interactive game-based learning media to support students’ understanding of mathematics in elementary school.

The use of artificial intelligence technology in elementary education is becoming increasingly relevant as teachers demand to develop creative and efficient teaching materials. Problems faced by fifth-grade elementary school teachers include limited time, a variety of ideas, and reliance on conventional methods in developing teaching materials, resulting in suboptimal learning creativity. This study aims to describe the use of ChatGPT by fifth-grade elementary school teachers in developing creative teaching materials and to identify the benefits and constraints of its use in the learning process. The research method used is a descriptive qualitative approach with data collection techniques through literature studies and online questionnaires based on Google Forms. The research respondents were fifth-grade elementary school teachers who were familiar with and used ChatGPT in lesson planning. The data obtained were analyzed using qualitative descriptive analysis techniques through the stages of data reduction, data presentation, and drawing conclusions. The results of the study are expected to provide a comprehensive picture of the role of ChatGPT as a digital assistant for teachers in increasing the efficiency and creativity of teaching material development in elementary schools.

This study examines the application of double integrals in calculating the volume of cylindrical concrete piles as a basis for estimating material requirements in building foundation structures. The volume calculation was carried out using a double-integral approach in polar coordinates for three pile segments with lengths of 4 m, 3.9 m, and 4 m, each having a diameter of 60 cm. The results were then validated using the standard geometric formula to ensure consistency and mathematical reliability. The obtained concrete volume was subsequently used to estimate material needs based on a 1:1.5:3 mix proportion consisting of cement, sand, and gravel. The findings indicate that double integrals can be effectively applied to generate accurate estimations of both volume and material requirements, supporting logistical planning in construction. This approach also highlights the strong connection between mathematical concepts—particularly multivariable calculus—and practical applications in civil engineering. Furthermore, the study emphasizes that double integrals may serve as a relevant alternative when structural modeling requires deeper analytical exploration or validation beyond conventional geometry. Therefore, the implementation of double integrals not only reinforces theoretical understanding but also enhances precision in evaluating structural components within building foundation planning.

This study examines the implementation of an Islamic Religious Education (PAI) learning model based on Project-Based Learning (PjBL) and collaborative approaches in shaping students’ noble character at SD Negeri Besuk Kidul, Besuk District. The study is grounded in the research gap that PAI learning in elementary schools is often still dominated by conventional, teacher-centered methods that emphasize cognitive achievement while providing limited space for the internalization of moral values through authentic learning experiences. This research aims to analyze how PjBL and collaborative learning are designed and implemented in PAI instruction and to explore their contribution to students’ character development. A qualitative approach with a descriptive case study design was employed. The research subjects included the school principal, a PAI teacher, and elementary school students. Data were collected through observation, in-depth interviews, and documentation, and analyzed using an interactive data analysis model. The findings reveal that the integration of project-based and collaborative learning in PAI instruction enhances students’ noble character, particularly in terms of honesty, discipline, responsibility, cooperation, respect, and social awareness. Students actively engage in learning activities, apply Islamic values in real-life contexts, and demonstrate positive behavioral changes both in and outside the classroom. These results indicate that Project-Based Learning and collaborative approaches constitute an effective and meaningful strategy for strengthening character education in PAI at the elementary school level.

The main objective of the Citizenship Education (PKn) course in higher education is to develop students into individuals with nationalist, participatory, and critical characters towards national dynamics. Conventional learning approaches that are still dominant in higher education, such as one-way lectures and memorization of materials, are considered less able to encourage active participation and the development of critical thinking patterns of students in the Citizenship Education (PKn) course. This study aims to identify the effectiveness of the application of innovative learning methods in improving students' activeness and critical thinking skills. Using a descriptive qualitative approach, data were collected through classroom observations, interviews with lecturers and students, and analysis of lecture documents from three study programs at Merdeka University of Malang. The results of the study showed that the application of learning strategies such as Project Based Learning, role playing, utilization of interactive multimedia, collaborative discussions, and nationality-based simulations were able to significantly increase students' participation and critical understanding. This method is relevant to the needs of learning in the era of globalization that demands digital literacy, cross-disciplinary collaboration, and contextual problem solving. Based on these findings, this study recommends the integration of innovative methods into the Civics curriculum in higher education, pedagogical training for lecturers, and the provision of technological infrastructure that supports the implementation of competency-based learning in the era of globalization.