Publication Search

The development of Artificial Intelligence (AI) has significantly influenced the formation of contracts in civil law, particularly through the automation of clause drafting, risk analysis, and the standardization of contractual documents. The use of AI in contract drafting raises complex legal issues, especially concerning the validity of agreements and the attribution of legal liability in the event of default. This study aims to analyze the validity of contracts created through Artificial Intelligence from the perspective of Indonesian civil law and to examine models of legal liability in AI-based contracts. This research employs a normative legal method with statutory and conceptual approaches, examining the provisions of the Indonesian Civil Code, particularly Article 1320, as well as legal doctrines and scholarly perspectives on digital contracts and AI. The findings indicate that AI-based contracts are, in principle, legally valid as long as they fulfill the requirements of a valid agreement, namely the consent of the parties, legal capacity, a specific object, and a lawful cause. Artificial Intelligence cannot be positioned as a legal subject because it lacks intent, consciousness, and the capacity to bear rights and obligations, and therefore functions solely as a technological tool. Consequently, legal intent and liability remain attached to the human or legal entity that uses, controls, or benefits from AI. This study also emphasizes that the primary challenge of AI-based contracts lies in the absence of specific legal regulations governing the allocation of liability among AI users, system providers, and developers, particularly when default occurs due to algorithmic errors or system failures. Therefore, clearer, adaptive, and comprehensive regulations are required to ensure legal certainty, protect the parties involved, and maintain a balance between technological innovation and the principles of justice in AI-based contractual practices in Indonesia.

This research investigates the development of IT-based Automatic Identification System (AIS) data surveillance models supporting maritime safety through integration of advanced information technology, maritime engineering principles, and human factors optimization. AIS technology generates vast real-time vessel movement data creating unprecedented opportunities for safety enhancement through systematic surveillance, collision risk detection, traffic pattern analysis, and incident prevention, yet effectiveness depends critically on intelligent data processing algorithms, reliable IT infrastructure, and competent personnel capable of interpreting surveillance outputs and taking appropriate actions. Through qualitative analysis involving maritime safety authorities, vessel traffic service (VTS) operators, port authorities, marine engineers, IT specialists, data scientists, and maritime training institutions, this study examines how IT-based surveillance models incorporating pattern recognition, anomaly detection, predictive analytics, and crew-centered interfaces can transform maritime safety management from reactive incident response toward proactive risk prevention. Results demonstrate that intelligent AIS surveillance can identify 75-90% of high-risk situations 15-45 minutes before critical events, reduce collision risks by 60-80%, improve traffic management efficiency by 35-55%, and enhance crew situational awareness by 45-65% when integrated with appropriate training programs developing personnel competencies in data interpretation, system operation, and coordinated response. Key implementation challenges include data quality and completeness issues, computational infrastructure requirements, algorithm development complexity, personnel competency gaps requiring substantial training investments, organizational coordination barriers, and privacy/security concerns. Findings reveal that successful AIS surveillance implementation requires holistic sociotechnical approaches integrating IT systems engineering, maritime domain expertise, and human capability development through coordinated design, deployment, and training strategies. This research contributes to maritime safety literature by providing integrated frameworks for IT-based surveillance systems incorporating technical capabilities, operational requirements, and human factors supporting evidence-based safety management.

This study examines the ideas of Ziauddin Sardar and Azyumardi Azra in three major areas: Islamic education, digital religious authority, and religious moderation. Using a library research approach, this article analyzes how Sardar’s Postnormal Times (PNT) framework explains global complexity, chaos, and contradictions that shape the future of Islamic thought and education. Meanwhile, Azra’s concept of Islam Nusantara and wasathiyah provides a historical and cultural foundation for constructing moderate Islamic identity in Indonesia. Findings indicate that Sardar emphasizes adaptive education oriented toward future literacy, while Azra highlights the integration of tradition, modernity, and local culture. In the context of digital authority, Sardar views the transformation as a structural effect of postnormal conditions driven by algorithmic systems, while Azra stresses the need to strengthen scholarly legitimacy based on sanad, institutions, and ethical guidance. Both perspectives converge on the importance of moderation. Sardar presents moderation as a strategy to manage global complexity, whereas Azra positions wasathiyah as the inherent identity of Islam in the archipelago. This study concludes that synthesizing both frameworks can strengthen Islamic education, stabilize digital religious authority, and reinforce Indonesia’s moderate Islamic identity in responding to contemporary challenges.

This research focuses on optimizing the control system to improve voltage stability in a 10 kW Solar Power Plant (PLTS) located in a tropical region. The main issue addressed is voltage fluctuation caused by the intermittent nature of solar radiation (200–1200 W/m²) and temperature variations (20–50°C), which result in up to 12% overshoot in the inverter. The proposed method implements a Proportional-Integral-Derivative (PID) controller optimized using the Particle Swarm Optimization (PSO) algorithm with real-time irradiation input data. The research integrates a 100 Hz digital low-pass filter to mitigate sensor noise under low irradiation conditions. Simulation results show that the PID-PSO system successfully reduces overshoot from 12.1% to 4.2% under high irradiation, and decreases settling time from 0.62 seconds to 0.31 seconds. The digital filter effectively reduces measurement deviation from 7.2% to 2.8% at 200 W/m² irradiation. The PSO optimization achieved optimal convergence within 37 iterations with an Integral of Time-weighted Absolute Error (ITAE) value of 0.18. This study concludes that the implementation of PID-PSO with a digital filter significantly enhances the voltage stability of the PLTS by 20.3% compared to conventional PID control and is ready to be applied in tropical-region smart grid systems.

The use of Large Language Models (LLMs) in scientific research is becoming increasingly widespread, but presents epistemic risks that are not yet fully understood. This article discusses how the probabilistic mechanisms of LLM can produce outputs that appear correct and justified but are actually dependent on epistemic luck, thus resembling the Gettier case pattern. Through a conceptual study approach, this research clarifies concepts, analytically reconstructs the generative structure of LLM, and conducts a normative analysis of its implications for scientific accountability and authorship. The results of the analysis show that Algorithmic Gettier Cases (AGCs) occur when linguistic coherence deceives users and creates the impression of justification, even though the truth that emerges is statistical coincidence and is not supported by valid causal relationships. This condition poses a serious challenge to the attribution of knowledge and author responsibility in the production of academic texts. To address this issue, this article proposes the principle of Hyper-Justification Obligation, which is the ethical obligation for researchers to actively verify and causally reason every AI output before using it in scientific works. This research provides a theoretical contribution to understanding the epistemic risks of LLM and offers an ethical foundation for academic practice in the era of generative AI.

The performance of the Indonesian National Team (Timnas) in the 2026 World Cup qualifications has triggered massive and diverse responses on social media, particularly on platform X. This study aims to identify and classify public sentiment regarding Timnas Indonesia's performance into positive, negative, and neutral categories using a data mining approach. Text data was processed through pre-processing stages, term weighting using TF-IDF, and the application of the Synthetic Minority Over-sampling Technique (SMOTE) to address significant class distribution imbalance. The classification algorithm employed was Multinomial Naïve Bayes. Model performance evaluation was conducted by comparing two training-testing data split scenarios: 90:10 and 80:20 ratios. The results indicate that public opinion is dominated by negative sentiment at 73.2%, reflecting public disappointment. In terms of model performance, the 90:10 ratio scenario yielded the best accuracy of 80%, outperforming the 80:20 ratio which recorded an accuracy of 75%. These findings demonstrate that combining Multinomial Naïve Bayes with the SMOTE technique is effective in handling imbalanced text data and is capable of accurately mapping public perception.

The increasing demand for electrical energy, particularly in offices and commercial buildings, has made energy efficiency a critical aspect of sustainable development. Among various building components, lighting systems are recognized as one of the major consumers of energy. This study investigates the potential for energy savings through the adoption of a smart lighting system incorporating IoT-based sensors, motion detectors, and dimming controls. Employing a quantitative descriptive approach, the research was conducted at the workspace of Indie Light, comparing energy consumption before and after the implementation of the system. Data were collected using direct observation, light and power meters, and real-time monitoring devices to ensure accurate measurement. The results demonstrate that smart lighting systems can substantially reduce energy use without compromising lighting quality or comfort. By integrating intelligent sensors and adaptive control algorithms, the system not only optimizes energy efficiency but also aligns with national policies on energy conservation, supporting broader environmental sustainability efforts. These findings suggest that smart lighting solutions can play a significant role in promoting energy-efficient practices in commercial spaces while contributing to sustainable development goals.

Credit scoring is an important element in decision-making for providing financing, especially for microfinance institutions. Several methods for predicting credit scoring include Decession Tree, Gradient Boosted, Neural Network, K-NN, and Rule Induction. This study aims to improve the accuracy of financing risk prediction by efficiently integrating historical data. The Neural Network (NN) algorithm is a machine learning algorithm consisting of neurons (nodes) connected to each other in several layers (input, hidden, and output). NN is used for pattern recognition, classification, regression, and complex non-linear modeling. The NN algorithm has the advantage of working well on large and diverse data and unstructured data. However, the NN algorithm has weaknesses such as overfitting and data dependence. In this study, the integration of the Sample Bootstrapping and Weighted Principal Component Analysis (PCA) methods is proposed to improve optimal accuracy in the NN algorithm. The Sample Bootstrapping method is used to reduce the amount of training data to be processed. The Weighted PCA method is used to reduce attributes. This study uses a financing customer dataset. The results of the study show that the integration of the NN algorithm with Sample Bootstrapping and Weighted PCA resulted in an accuracy increase of 1-3% (97%-99%) compared to other algorithms. Therefore, it can be concluded that the integration of the NN algorithm with Sample Bootstrapping and Weighted PCA produces better accuracy than other algorithms

The growing interest in learning the Japanese language in Indonesia, driven by popular culture such as anime, creates a need to understand the effectiveness of different learning media. The non-uniform effectiveness of media for each individual poses a major challenge. Therefore, this study aims to analyze the effectiveness of both anime and textbooks by segmenting learner profiles and identifying key determinants of success using an artificial intelligence approach. This research employed a quantitative method through a questionnaire survey of 120 respondents. The data were analyzed in two stages: the K-Means Clustering algorithm was used to group respondents into learner profiles, and the Decision Tree algorithm was used to identify the most significant factors that differentiate these profiles. The analysis successfully identified three distinct learner profiles: "Intensive & Adaptive Learner," "Flexible Learner," and "Passive Learner." The decision tree revealed that the perception of textbook effectiveness and the frequency of anime use are the strongest predictors in determining a learner's profile, more so than theoretical learning style preferences. It is concluded that media effectiveness is highly dependent on the learner's behavioral and perceptual profile, which underscores the importance of a personalized approach in language education technology.

Current advances in information technology have encouraged universities to utilize student academic data as a basis for decision-making, one of which is predicting academic achievement. This study aims to apply the C4.5 algorithm to develop a system for predicting student academic success in the Islamic Religious Education Study Program. This method was chosen because it produces a decision tree model that is easy to understand and has a high level of accuracy. The data used comes from student achievement indexes from semesters 1 to 5. The research results showed that the prediction system achieved 99.62% accuracy and achieved high recall precision across each class category. This demonstrates the effectiveness of the C4.5 algorithm in predicting student academic achievement and has the potential to serve as a valuable tool for decision-makers in higher education.

Behind the success of the Free Nutritious Meal Program (MBG), there are several problems related to the health factors of the program targets, namely, there are several cases of allergies that occur in schools, inadequate understanding of allergen management owned by food processing vendors, and the high cost of laboratory tests and the process that takes a long time. So, to overcome these problems, an application is proposed that can help detect allergens in food products using data mining and machine learning approaches. SVM and AdaBoost algorithms each have advantages that can be used to help build an optimal allergen detection model. This research uses a cross-validation model validation method with a value of K = 10 to help improve the performance of the model built. In this study, from the entire fold, an average accuracy value of 98.74% was obtained. To evaluate the model built, this research has also conducted several new data inputs, and in each new data input, the accuracy value is obtained above 99%. This indicates that the model built, namely the combination of SVM and AdaBoost algorithms with the cross-validation model validation method, produces high accuracy, so this model can greatly assist the allergen detection process in food products.

This research examines the application of the Elliptic Curve Digital Signature Algorithm (ECDSA) in a blockchain system as a security solution for digital payment systems in Indonesia. Using a descriptive-qualitative approach based on literature review and conceptual simulations using Python, this study discusses the working principles of ECDSA, its advantages over other digital signature algorithms, and the challenges of its adoption in Indonesia. The results show that ECDSA provides high cryptographic efficiency, maintains transaction authenticity and integrity, and supports a transparent decentralized system. The academic simulations include not only KYC processes, top-ups, transactions, validation by validators, and block recording, but also demonstrates the formation of an interconnected multi-level blockchain and tests scenarios for rejecting manipulated or invalid transactions. The contribution of this research lies not only in the theoretical review but also in the implementation illustrations that can be used as a basis for education and the initial development of blockchain-based digital payment systems. The research results show that ECDSA is capable of providing a high level of efficiency in the encryption and transaction verification process, maintaining data integrity and authenticity, and supporting a decentralized and transparent system. The academic simulations included the KYC process, wallet creation using ECDSA keys, balance top-ups through bank integration, transaction creation and validation, and block recording in the blockchain. Specifically, the simulations successfully demonstrated how new blocks are added to the chain by referencing the previous block's hash, as well as how transactions with corrupted signatures, manipulated amounts, or insufficient balances are automatically rejected by the validator consensus mechanism, maintaining system integrity. This research contributes not only theoretically, but also through conceptual representations that can be used as an educational foundation and for the initial development of blockchain-based digital payment systems in Indonesia.

Crime, an unlawful act that contradicts ethics and norms, has now become a primary factor for the police in Lampung province. This presents a challenge for the police institution in predicting high crime rates. However, there are still many crimes that have not become the main focus of problem-solving at the Lampung Regional Police.This research aims to identify the types and criminal acts of crime with the highest recorded incidence in a crime dataset by performing classification using the Naïve Bayes algorithm. The data was obtained from investigators at the Directorate of General Criminal Investigation of the Lampung Regional Police, with a total of 12,034 JTP (Total Criminal Acts) and 7,518 PTP (Crime Resolution) data points for each type of crime, distributed across the Regional Police, City Police, and District Police throughout Lampung province. The classification process using the Naïve Bayes algorithm reveals the relationship between the work unit (Satker) and the type of crime handled, thereby identifying crime patterns based on the location where they are handled. The results of the research, which involved converting numerical data into binomial (binary) form using the "Numerical to Binominal" feature in Rapid miner, show that the analysis and modeling process, especially in algorithms like Naïve Bayes or decision trees, is more effective when using data in a binary format. Thus, the initial dataset can be visualized in the form of a , with the size of the text varying according to the level of each high-incidence crime; the larger the text, the more frequently or significantly the crime occurred or was reported. The application of this method can help in identifying patterns, dominant trends, and areas of focus for more targeted law enforcement efforts or crime prevention policies.

This study evaluates the efficiency of two artificial intelligence models, DeepSeek and OpenAI, in generating code for algorithmic systems. Efficiency is assessed through execution speed, code accuracy, and the number of code characters produced. Data were collected from 100 tests covering search, sorting, graph, dynamic programming, optimization, data processing, text, and machine learning algorithms. The objective is to compare the performance of both models to support the development of efficient information retrieval systems. The method involves algorithm testing with statistical analysis of execution time, accuracy, and code length. Results indicate that DeepSeek has an average execution time of 28.74 seconds, slightly slower than OpenAI’s 28.49 seconds. However, DeepSeek’s accuracy (85.88%) surpasses OpenAI’s (85.03%). The average number of code characters is identical at 96.35 characters. The study concludes that DeepSeek excels in accuracy, while OpenAI is faster in certain cases, providing valuable insights for developers in selecting AI models for information retrieval applications.

Infectious diseases remain a dynamic and evolving public health threat, requiring data-driven approaches for early detection and targeted policy planning. This study aims to model spatio-temporal trends and clustering patterns of HIV transmission in Bogor Regency during the period 2020–2023 by utilizing a combination of unsupervised and supervised machine learning techniques. The dataset was obtained from the Bogor Regency Health Office and includes annual data on the number of HIV cases across 40 sub-districts. The research methodology consists of data preprocessing stages, clustering using the K-Means algorithm, and classification using a Decision Tree model. The preprocessing steps include data integration, attribute selection, temporal aggregation, handling of missing data, and normalization using Z-score. K-Means clustering is applied to identify hidden patterns in the development of HIV cases, resulting in three distinct clusters based on multi-year trends. The resulting cluster labels are then used as target classes in the supervised classification process. The Decision Tree classification model demonstrates high accuracy in predicting cluster membership, indicating a strong relationship between the temporal patterns of HIV cases and cluster identity. The integration of clustering and classification techniques provides a robust analytical framework for understanding the dynamics of HIV transmission, while also supporting the formulation of more precise, evidence-based, and region-specific public health interventions.

Communication is a fundamental aspect of human life. However, individuals with hearing and speech impairments often face barriers in communicating with the general public. The Indonesian Sign System (SIBI) serves as a communication solution for the deaf and speech-impaired community in Indonesia, yet public understanding of SIBI remains limited. To address this issue, this study aims to develop an automatic translation model from SIBI sign language into Indonesian text by utilizing Deep Learning technology, specifically the Convolutional Neural Network (CNN) algorithm. CNN was chosen for its ability to effectively recognize visual patterns, making it suitable for processing hand gesture images in sign language. This research involved collecting and classifying a dataset of hand images based on the alphabet or words in SIBI, which were then used to train the CNN model. The designed CNN model was built to accurately classify hand signs and translate them into Indonesian text. The results of this study have the potential to serve as a supportive solution for inclusive communication between the deaf community and the wider public, and can be further developed for contextual sentence translation. Keywords: Indonesian Sign System (SIBI), CNN, Deep Learning, Automatic Translation, Inclusive Communication

This study aims to analyze the factors that influence students' interest in continuing their education to college using a machine learning approach. Data was collected through an online questionnaire completed by 727 students between July 27 and August 22, 2025, covering 23 variables consisting of respondent identity (gender, grade level, major) as well as internal and external factors such as parental support, learning motivation, and preferred type of college. The data preparation stage was carried out through column cleaning, deletion of empty data, encoding of categorical variables, and division of the dataset into 80% training data and 20% test data. The Naive Bayes algorithm of the CategoricalNB type was used because it was suitable for the categorical nature of the data. The evaluation results showed that the model was able to predict student interest with 96% accuracy. For the class of students interested in continuing their studies, the precision, recall, and F1-score values were above 0.95, while the performance in the class of students who were not interested was slightly lower due to the smaller amount of data. These findings show that Naive Bayes is proven to be effective and reliable in classifying students' interest in continuing their studies and can be the basis for decision-making in designing more targeted educational strategies.