SLSteven Harazaki Lase

Steven Harazaki Lase

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Steven Harazaki Lase has a total of 17 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Deep Learning Enabled Security Monitoring for Intrusion Detection in Smart Campus Networks

    by Ruli Supriati, Nuke Puji Lestari Santoso, Steven Harazaki Lase, Carlos Perez

    The increasing complexity of smart campus networks has heightened the need for advanced cybersecurity measures to protect sensitive data and ensure seamless operations. Traditional Intrusion Detection Systems (IDS) often struggle to cope with the dynamic and heterogeneous nature of network traffic in smart campus environments, necessitating the development of more effective solutions. This study aims to propose a deep learning-based intrusion detection system for smart campus networks, utilizing a Hybrid CNN-LSTM model to enhance security monitoring. The proposed methodology integrates Convolutional Neural Networks (CNN) for feature extraction and Long Short-Term Memory (LSTM) networks for capturing temporal dependencies in network traffic. The model was trained and evaluated on a combination of publicly available datasets and simulated smart campus data, measuring performance through key metrics such as accuracy, precision, recall, and F1-score. Results show that the Hybrid CNN-LSTM model outperforms traditional machine learning models, achieving an accuracy of 97.3% and a ROC-AUC of 0.99, demonstrating superior detection of both known and unknown intrusions. The findings suggest that deep learning models, especially when tailored to smart campus contexts, offer significant advantages in real-time threat detection and adaptive learning. This research contributes to the growing body of knowledge on AI-driven network security and provides practical insights for improving cybersecurity infrastructures in higher education institutions.

  • Open Access

    Smart Contract Regulation for Decentralized Justice and Cross-Border Digital Transactions

    by Shofiyul Millah, Steven Harazaki Lase, Natalie Septiani, Suca Rusdian

    Blockchain-based smart contracts have introduced new mechanisms for executing cross-border digital transactions through automated and decentralized contractual arrangements. However, their code-based execution creates legal challenges concerning jurisdiction, enforceability, accountability, dispute resolution, and the protection of fundamental legal rights. This study aims to develop a human-centric regulatory framework for smart contracts that strengthens legal certainty, accountability, and access to justice in decentralized and cross-border digital transactions. This study employs normative legal research with a comparative regulatory approach. Primary legal materials, including national legislation and international regulatory instruments governing electronic transactions, blockchain, digital contracts, and dispute resolution, are analyzed through statutory, conceptual, and comparative approaches. The analysis identifies regulatory gaps and formulates principles for interoperable smart contract governance. The study demonstrates that existing legal frameworks insufficiently address automated contractual execution, cross-border jurisdiction, liability for code-based outcomes, and human intervention in decentralized dispute resolution. The proposed framework integrates seven regulatory principles: legal validity and enforceability, transparency and explainability, accountability and liability, human oversight, cross-border jurisdiction, data protection and digital rights, and regulatory interoperability. The framework provides a human centric regulatory architecture for aligning smart contract automation with fun amental legal principles and cross-border regulatory requirements. It contributes to decentralized justice by preserving technological efficiency while ensuring procedural fairness, legal accountability, and protection of digital rights.

  • Open Access

    Adaptive Legal Architectures for Governing AutonomousTechnologies in Sustainable Digital Societies

    by Qurotul Aini, Steven Harazaki Lase, Alfri Adiwijaya, Fanani Islamia Ningrum, Dimas Aditya Prabowo, Thomas Green

    Building effective governance structures for rapidly evolving autonomous technologies represents a significant legal challenge in contemporary digital societies. The rapid integration of AI, algorithmic decision making, and autonomous systems into digital infrastructures has created increasing regulatory complexity, while existing legal frameworks often struggle to adapt to the speed of technological innovation. This condition creates a regulatory gap between technological development and the capacity of legal systems to ensure accountability, transparency, and ethical governance. This study aims to examine how adaptive legal architectures can be designed to regulate autonomous technologies in sustainable digital societies. The research employs a qualitative conceptual approach by reviewing interdisciplinary literature on digital governance, technology law, and AI ethics. Through this approach, the study identifies key governance principles that support flexible and responsive regulatory systems. The findings suggest that adaptive legal architectures should incorporate dynamic regulatory mechanisms, multi stakeholder participation, and ethical oversight frameworks that allow legal systems to respond to rapid technological change. These mechanisms enable governance models that balance technological innovation with risk management, transparency, and long-term societal sustainability. This study contributes to the development of digital governance frameworks by proposing a conceptual foundation for adaptive legal regulation capable of addressing the governance challenges posed by autonomous technologies.


  • Open Access

    Data Driven A or B Testing Methodology for Website Effectiveness

    by Qurotul Aini, Aulia Khanza, Vinkan Likita, Steven Harazaki Lase, Yasir Mustafa Kareem

    Website design and optimization decisions are often driven by subjective opinions, internal organizational preferences, or prevailing industry trends rather than empirical evidence derived from large-scale user interaction data, resulting in suboptimal performance and inconsistent user experiences. In digital environments characterized by high data volume and velocity, the absence of a structured experimentation methodology limits organizations’ ability to effectively leverage Big Data for continuous website improvement. This paper presents a comprehensive and systematic methodological guide to A or B testing as a data-driven approach for enhancing website effectiveness in data-intensive contexts. Unlike existing A or B testing guides that focus mainly on tools or isolated experimental outcomes, this study proposes an end-to-end framework integrating hypothesis formulation, scalable experimental design, statistical rigor, iterative learning, and practical decision-making into a unified and replicable process. The methodology outlines the complete A or B testing lifecycle, including alignment of business objectives with measurable data signals, development of testable hypotheses, controlled experiment implementation, large-scale data collection, and statistical analysis to ensure validity and significance of findings. The results demonstrate that a disciplined and continuous A or B testing program supported by Big Data analytics enables incremental yet compounding improvements in website performance. Through illustrative case examples, the study shows that relatively small, data-informed changes to website elements such as headlines, calls-to-action, images, and layout structures can lead to statistically significant gains in conversion rates, user engagement, and overall user experience. The paper concludes that A or B testing serves as a strategic Big Data analytics mechanism that supports evidence-based website optimization decisions grounded in empirical user behavior rather than intuition.

  • Open Access

    Data Driven A or B Testing Methodology for Website Effectiveness

    by Qurotul Aini, Aulia Khanza, Vinkan Likita, Steven Harazaki Lase, Yasir Mustafa Kareem

    Website design and optimization decisions are often driven by subjective opinions, internal organizational preferences, or prevailing industry trends rather than empirical evidence derived from large-scale user interaction data, resulting in suboptimal performance and inconsistent user experiences. In digital environments characterized by high data volume and velocity, the absence of a structured experimentation methodology limits organizations’ ability to effectively leverage Big Data for continuous website improvement. This paper presents a comprehensive and systematic methodological guide to A or B testing as a data-driven approach for enhancing website effectiveness in data-intensive contexts. Unlike existing A or B testing guides that focus mainly on tools or isolated experimental outcomes, this study proposes an end-to-end framework integrating hypothesis formulation, scalable experimental design, statistical rigor, iterative learning, and practical decision-making into a unified and replicable process. The methodology outlines the complete A or B testing lifecycle, including alignment of business objectives with measurable data signals, development of testable hypotheses, controlled experiment implementation, large-scale data collection, and statistical analysis to ensure validity and significance of findings. The results demonstrate that a disciplined and continuous A or B testing program supported by Big Data analytics enables incremental yet compounding improvements in website performance. Through illustrative case examples, the study shows that relatively small, data-informed changes to website elements such as headlines, calls-to-action, images, and layout structures can lead to statistically significant gains in conversion rates, user engagement, and overall user experience. The paper concludes that A or B testing serves as a strategic Big Data analytics mechanism that supports evidence-based website optimization decisions grounded in empirical user behavior rather than intuition.


  • Open Access

    Machine Learning and Blockchain Integration for RealTime Sentiment Analysis and Digital Rupiah Ecosystem

    by Ninda Lutfiani, Umi Rusilowati, Steven Harazaki Lase, Kristina Vaher

    The rapid growth of digital streaming platforms and global online communities has significantly increased the volume of user generated content, making it difficult for organizations to understand viewer engagement trends in real time. This study develops and evaluates machine learning models for real time sentiment analysis to identify global viewer engagement patterns across large scale digital data streams. Analytical framework is employed by collecting viewer comments and interaction data from multiple online platforms, followed by preprocessing techniques including text normalization, tokenization, and feature extraction. Several machine learning algorithms, including supervised classification models and natural language processing techniques, are trained and evaluated to detect positive, negative, and neutral sentiments in real time. Model performance is assessed using accuracy, precision, recall, and F1 score to determine the most effective approach for large scale sentiment monitoring. The findings demonstrate that optimized machine learning models significantly improve the accuracy and responsiveness of real time sentiment detection, enabling more reliable identification of global viewer engagement trends and behavioral patterns. The integration of automated sentiment analysis also enhances the capability of organizations to process large volumes of streaming textual data efficiently. This research highlights the importance of machine learning driven sentiment analysis systems as strategic tools for understanding global audience engagement, supporting data driven decision making, and improving adaptive content strategies in rapidly evolving digital media environments.