Journal of Nexural Intelligence
NEXURAL – Journal of Nexural Intelligence is an international peer-reviewed and open-access scholarly journal dedicated to publishing high-quality original research articles, review articles, comparative studies, and methodological advances in the fields of Artificial Intelligence and Intelligent Computing Systems. The journal provides an international academic forum for researchers, academics, engineers, practitioners, and industry professionals to disseminate scientific knowledge, innovative algorithms, computational models, intelligent system architectures, experimental findings, and responsible applications that contribute to the advancement of Artificial Intelligence and intelligent technologies. NEXURAL primarily focuses on the scientific development of Artificial Intelligence through machine learning, deep learning, neural computing, computational intelligence, autonomous reasoning, knowledge representation, optimization, intelligent data analysis, and adaptive intelligent systems. The journal also welcomes interdisciplinary studies that integrate Artificial Intelligence and Intelligent Computing Systems with scientific, technological, engineering, industrial, economic, educational, healthcare, environmental, and societal domains. However, Artificial Intelligence or Intelligent Computing must remain the principal scientific focus, methodological contribution, or object of evaluation in every manuscript submitted to the journal. NEXURAL was first published in 2026 and is published [twice a year in June and December] in an electronic or online medium. The journal publishes articles primarily in English and provides immediate open access to its published content to support the wider dissemination and development of scientific knowledge. The journal applies a rigorous peer-review process and is committed to publication ethics, scientific integrity, research transparency, methodological reproducibility, and responsible Artificial Intelligence development.
Articles
8 Documents
<![CDATA[Learning Analytics-Based Student Engagement Profiling Using Moodle Activity Logs Across Multiple Courses ]]>
<![CDATA[Abdul Rahman]]>;
<![CDATA[Abdul Karim]]>;
<![CDATA[Destiarini]]>
<![CDATA[ Journal of Nexural Intelligence Vol. 1 No. 1 (2026): Journal of Nexural Intelligence ]]>
Publisher : <![CDATA[Citra Air Nusantara ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.71200/nexural.v1.i1.259
<![CDATA[Learning management systems generate detailed event logs, yet these data are often underused for monitoring student engagement. This study develops a learning analytics workflow for profiling engagement from Moodle activity logs collected from 20 courses. The raw dataset contained 402,290 records recorded between 19 February 2025 and 2 June 2025. After removing administrative, reporting, and system-maintenance events, 369,592 learner-generated events from 760 users were analyzed. The method consisted of timestamp parsing, course mapping, anonymization, event-category mapping, feature engineering, engagement scoring, and K-Means clustering. Eight behavioral indicators were constructed, including total events, active days, course views, module views, quiz activity, assignment activity, resource access, and event diversity. The results show that quiz-related interactions dominated the logs, followed by system course views and assignment activities. Three engagement profiles were identified: low, moderate, and high engagement. The proposed workflow provides an interpretable basis for course monitoring and early identification of learners who may require academic support, while avoiding unsupported claims about academic achievement when final-grade data are unavailable.]]>
<![CDATA[Comparative Analysis of NIST SP 800-86 Framework in Handling Digital Evidence in Cloud Computing Environment ]]>
<![CDATA[Anton Maulana Ibrahim]]>;
<![CDATA[Mirza Sutrisno]]>;
<![CDATA[Asrudin]]>
<![CDATA[ Journal of Nexural Intelligence Vol. 1 No. 1 (2026): Journal of Nexural Intelligence ]]>
Publisher : <![CDATA[Citra Air Nusantara ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.71200/nexural.v1.i1.260
<![CDATA[This study analyzes the effectiveness of NIST SP 800-86 in handling digital evidence within cloud computing environments in Indonesia, employing a mixed-methods sequential explanatory approach. The research methods comprised a systematic literature review (SLR) of 120 publications, an implementation readiness survey (n = 110), in-depth interviews with 12 subject-matter experts, and a five-dimensional gap analysis. Findings indicate that NIST SP 800-86 exhibits an average coverage gap of 54.9% relative to the requirements of modern cloud forensics, with the most pronounced deficiencies in cloud-native structures (−77%), multi-tenancy (−75%), and emerging technologies (−53%). The level of cloud forensics implementation readiness in Indonesia falls within the moderate-to-low range (mean = 2.7/5), with law enforcement agencies facing the most critical obstacles owing to limited resources and an insufficient pool of certified practitioners. Multiple regression analysis (R² = 0.591) identified knowledge level, organizational support, and tools and infrastructure availability as the primary predictors of implementation readiness. Furthermore, a strong expert consensus emerged around the need for chain-of-custody standardization and a national forensic framework as prerequisite conditions for the legal admissibility of cloud-generated digital evidence. This study recommends the development of the Cloud Forensics Framework Indonesia (CFFI)—a hybrid framework integrating the procedural foundations of NIST SP 800-86, the legal provisions of ISO/IEC 27037, cloud-native technical specifications, and applicable national regulations—as the basis for policy reform and the advancement of cloud forensics practice in Indonesia]]>
<![CDATA[Live Network Acquisition with Pre-Serialization Hashing for Digital Evidence Integrity ]]>
<![CDATA[Mirza Sutrisno]]>;
<![CDATA[Anton Maulana Ibrahim]]>
<![CDATA[ Journal of Nexural Intelligence Vol. 1 No. 1 (2026): Journal of Nexural Intelligence ]]>
Publisher : <![CDATA[Citra Air Nusantara ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.71200/nexural.v1.i1.262
<![CDATA[The integrity of digital evidence remains a fundamental requirement in network forensic investigations, particularly during the live acquisition phase where packet captures are vulnerable to anti-forensic manipulation. Conventional forensic workflows generally perform cryptographic verification after packet data has been serialized into secondary storage, creating a temporary exposure window that may allow unauthorized modification before integrity validation occurs. This study proposes a proactive forensic acquisition framework that performs cryptographic hashing directly in volatile memory prior to storage serialization. The proposed architecture utilizes Python’s io.BytesIO() mechanism to temporarily preserve packet streams in RAM and generate SHA-256 signatures before physical .pcap file creation. To evaluate the robustness of the framework, ten PCAP datasets consisting of attack and normal traffic captures were processed using an in-memory hashing pipeline. A controlled single-bit tampering simulation was subsequently applied to each serialized file to measure cryptographic sensitivity through Hamming Distance and Avalanche Effect analysis. Experimental results demonstrate that all manipulated files produced complete cryptographic divergence from their original in-memory signatures. The average Hamming Distance reached 132.2 bits with a mean avalanche probability of 0.5164, closely matching the theoretical characteristics of secure hash functions. These findings indicate that pre-serialization integrity verification significantly improves the reliability of digital evidence preservation by reducing the vulnerability window associated with conventional post-acquisition hashing mechanisms.]]>
<![CDATA[Deep Learning Approaches For Distributed Denial Of Service (DDOS) Attack Detection In Software-Defined Networking: A Systematic Literature Review ]]>
<![CDATA[Ade Davy Wiranata]]>;
<![CDATA[Intan Murniasih]]>;
<![CDATA[Rudy Ansari]]>
<![CDATA[ Journal of Nexural Intelligence Vol. 1 No. 1 (2026): Journal of Nexural Intelligence ]]>
Publisher : <![CDATA[Citra Air Nusantara ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.71200/nexural.v1.i1.263
<![CDATA[Software-Defined Networking (SDN) has emerged as a foundational paradigm for programmable, centrally-managed networks, but its logically centralised control plane is highly attractive to Distributed Denial of Service (DDoS) adversaries. Traditional signature- and threshold-based defences struggle against polymorphic and low-rate attack patterns, motivating a rapid migration toward Deep Learning (DL) based detection. This Systematic Literature Review (SLR), conducted in accordance with the PRISMA 2020 guideline and a PICOC framework, identifies, classifies, and analyses 62 primary studies published between January 2020 and February 2026 on DL-based DDoS detection in SDN. Three research questions are answered, covering publication venues, the most active researchers, and the architectures, datasets, and evaluation metrics employed. The findings reveal that Convolutional Neural Networks (38.7%), hybrid CNN-LSTM models (24.2%), and Transformer/Graph Neural Networks (14.5%) dominate recent designs, while the InSDN and CIC-DDoS2019 datasets are the de-facto benchmarks. Macro-averaged accuracy across high-quality studies exceeds 99%, yet real-time deployment, explainability, and cross-dataset generalisability remain open challenges. The review provides a consolidated knowledge map and an empirically grounded research agenda for the next generation of intelligent SDN defences]]>
<![CDATA[Payment Data Processing in Web-Based Futsal Field Booking System (Futsal Sport Center Case Study) ]]>
<![CDATA[Akhmad Sayuti]]>;
<![CDATA[Rhaffi Ahmad Perdana]]>;
<![CDATA[Irwansyah]]>
<![CDATA[ Journal of Nexural Intelligence Vol. 1 No. 1 (2026): Journal of Nexural Intelligence ]]>
Publisher : <![CDATA[Citra Air Nusantara ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.71200/nexural.v1i1.264
<![CDATA[The demand for futsal field rentals continues to increase along with the popularity of futsal among the public. However, the ordering and payment process is still done manually, causing various problems such as recording errors, long queues, and late payment confirmation. This study aims to design and build a web-based information system that can help the ordering process and manage payment data digitally. This system was developed using the Waterfall method with the PHP programming language and MySQL database, and tested using the black box testing approach. The main features provided include field reservations, schedule management, uploading proof of payment, and validation by the admin. The test results show that the system runs well and provides convenience for both tenants and managers. The implementation of this system provides technopreneurial added value in the form of operational efficiency, improved customer service, and the potential for expanding digital-based services.]]>
<![CDATA[Flower Pollination Algorithm for Valley-Shaped Optimization: Convergence and Accuracy Evaluation ]]>
<![CDATA[Alfian Bahrul Alam]]>;
<![CDATA[Syariful Alim]]>;
<![CDATA[M. Mahaputra Hidayat]]>
<![CDATA[ Journal of Nexural Intelligence Vol. 1 No. 1 (2026): Journal of Nexural Intelligence ]]>
Publisher : <![CDATA[Citra Air Nusantara ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.71200/nexural.v1i1.266
<![CDATA[Optimization is fundamental to solving complex problems across engineering, economics, and computer science. However, navigating optimization landscapes characterized by numerous local extrema, such as valley-shaped functions, remains a significant computational challenge. To address this, this study implements the Flower Pollination Algorithm (FPA)—a robust nature-inspired metaheuristic—to efficiently solve valley-shaped optimization problems. The algorithm's performance is rigorously evaluated against four deceptive benchmark functions: Rosenbrock, Dixon-Price, Six-Hump Camel, and Three-Hump Camel, utilizing Python-based computational simulations. The evaluation focuses on convergence speed, solution accuracy, and the algorithm's capability to escape local optima. Experimental results demonstrate that FPA achieves exceptional accuracy and high computational efficiency. Specifically, FPA secured near-optimal fitness values of 0.00027 for the Rosenbrock function in under 0.83 seconds, and an impressive fitness of for the Three-Hump Camel function within 500 iterations. Furthermore, it successfully identified the true global minimum of -1.0316 for the Six-Hump Camel function at early stages. These empirical findings confirm FPA's strong global exploration capabilities, providing a solid foundation for its future application in more complex, high-dimensional engineering optimization tasks.]]>
<![CDATA[Predictive Analysis of Local Internet Service Stability Using QoS Parameters ]]>
<![CDATA[Ahlis Noor Kholili]]>;
<![CDATA[Nuur Halimatus Saadiah Masrukhin]]>
<![CDATA[ Journal of Nexural Intelligence Vol. 1 No. 1 (2026): Journal of Nexural Intelligence ]]>
Publisher : <![CDATA[Citra Air Nusantara ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.71200/nexural.v1i1.268
<![CDATA[The increasing use of internet services in local internet networks such as RT/RW Net and small-scale internet service providers requires stable network quality to support user activities optimally. Problems such as high delay, packet loss, jitter, and low throughput often cause a decrease in internet service quality. This study aims to analyze the stability of local internet services using Quality of Service (QoS) parameters and apply predictive analysis to predict network stability conditions. The QoS parameters used in this study include delay, throughput, jitter, and packet loss. The research method used is quantitative, with data collection conducted through network monitoring using tools such as Wireshark, MikroTik Monitoring, and Speedtest. The collected data were processed and analyzed using the Decision Tree predictive method to classify network conditions into stable, fairly stable, and unstable categories. The results showed that QoS parameters significantly affect internet service stability, where delay and packet loss are the most dominant factors influencing network quality. The predictive model used was able to classify network conditions with an accuracy rate of 87.5%. Based on these results, predictive analysis based on QoS parameters can be used as a solution to support monitoring and decision-making in managing local internet services more effectively and efficiently.]]>
<![CDATA[Intelligent Audio-Text Digital Archiving System for Court Proceedings Documentation ]]>
<![CDATA[Imam Solikin]]>;
<![CDATA[Nasrullah Nasrullah]]>
<![CDATA[ Journal of Nexural Intelligence Vol. 1 No. 1 (2026): Journal of Nexural Intelligence ]]>
Publisher : <![CDATA[Citra Air Nusantara ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.71200/nexural.v1i1.269
<![CDATA[Court proceedings documentation plays a crucial role in preserving legal records and ensuring efficient access to judicial information. However, conventional documentation and archiving processes often rely on manual procedures, leading to inefficiencies, difficulties in information retrieval, and inconsistencies in records management. This study aims to develop an intelligent audio-text digital archiving system for court proceedings to improve the effectiveness and efficiency of judicial record management through the integration of audio and textual data. The system was developed using the waterfall software development model, which consists of the requirements analysis, system design, implementation, testing, and maintenance phases. The proposed system provides functionalities such as audio recording management, text-based documentation, digital data storage, indexing, and search capabilities to facilitate efficient access to archived records. System testing was conducted to evaluate the functionality and usability of the system in supporting court documentation activities. The results indicate that the developed system improves documentation efficiency, simplifies information retrieval, and enhances the accuracy and reliability of court records. Furthermore, the proposed system contributes to the digital transformation of judicial information management by providing a more structured, efficient, and intelligent archiving solution.]]>
