A Solar-Powered IoT Weather Monitoring Network with Big Data Architecture and Deep Learning Hyperlocal Forecasting: Design, Deployment, and Validation in Vietnam
Đỗ Gia Bảo, Faculty of Information Technology, Nguyen Tat Thanh University, Ho Chi Minh City, Vietnam.
Nguyễn Tài Tiệp, Faculty of Information Technology, Nguyen Tat Thanh University, Ho Chi Minh City, Vietnam.
MSI Journal of AI and Technology | https://zenodo.org/records/19279335 | Page 01 to 19
Abstract
Vietnam ranks among the most climate-vulnerable countries in Southeast Asia, yet its operational weather monitoring network covers only approximately one station per 800 km², far below the World Meteorological Organization’s recommended density. This paper presents the design, implementation, and field validation of a fully solar-powered IoT weather station network integrated with a Lambda/Kappa Big Data architecture and a Temporal Fusion Transformer (TFT) deep learning model for hyperlocal, multi-horizon weather forecasting. Fifty prototype stations were deployed across three climatically distinct provinces — An Giang (Mekong Delta flooding), Quang Nam (Central Vietnam typhoons/flash floods), and Dak Lak (Central Highlands drought/landslides) — collecting eight meteorological variables at six-minute intervals over twelve months. A Federated Anomaly Detection framework with differential privacy guarantees (ε = 2.0, δ = 10⁻⁵) identifies five classes of sensor faults without transmitting raw data. The TFT model, pre-trained on 23 years of ERA5 reanalysis and fine-tuned on local observations, achieves a 2-metre temperature RMSE of 0.81°C at 24-hour lead time, surpassing Kriging interpolation by 31% and the operational NWP baseline by 18%. System uptime reaches 99.3% over the evaluation period. All data and model weights are released as open datasets (CC BY 4.0) to support future research.
Keywords — IoT; solar energy harvesting; Big Data; Apache Kafka; Apache Flink; Temporal Fusion Transformer; hyperlocal weather forecasting; federated learning; anomaly detection; Vietnam.
All articles published by MSIP are made immediately available worldwide under an open access license. No special permission is required to reuse all or part of any MSIP article, including figures and tables.
For articles published under a Creative Commons CC BY 4.0 license, any part of the article may be reused for any purpose, including commercial use, provided that the original MSIP article is clearly cited.
Sovereign Artificial Intelligence for Municipal Governance: A Case Study of Jazan Municipality's Local AI Ecosystem
Implementation of Open WebUI, RAG, Oracle 26ai, and Multi-Agent Systems
Rami Mohammed Zain Youssef, Systems and Cloud Computing Manager, Jazan Municipality, Kingdom of Saudi Arabia.
MSI Journal of AI and Technology | https://zenodo.org/records/19099891 | Page 01 to 10
Abstract
Background: The enterprise intelligent assistant system has recently undergone a series of architectural and operational updates aimed at enhancing local inference efficiency, improving language model integration with internal work environments, and strengthening reliance on a sovereign infrastructure that operates entirely within the organization without data leakage to external services.
Objective: To develop and evaluate a comprehensive AI platform that enables natural language interaction with municipal databases while maintaining complete data sovereignty and supporting Arabic language requirements.
Methods: The system architecture integrates Open Web UI as the operating layer, Oracle 26ai for database intelligence, Retrieval-Augmented Generation (RAG) for document processing, and specialized AI agents for various municipal functions. Recent updates include the addition of Qwen3.5-35B-A3B-FP8 model using a specialized Docker image (hellohal2064/vllm-qwen3.5-gb10) with advanced features including Flash Infer, FP8 KV Cache, and Prefix Caching.
Results: The pilot deployment with 12 internal users demonstrated significant improvements: 77 messages processed within 24 hours, 98% reduction in document search time (from 45 minutes to under 1 minute), and 65% improvement in task completion speed. The system achieved 100% data sovereignty with zero external data transmission. Technical challenges including 100% root partition utilization were successfully resolved through cache cleanup and storage optimization.
Conclusion: This study demonstrates the feasibility and effectiveness of sovereign AI implementation in municipal governance. The proposed architecture provides a scalable model for government agencies seeking to leverage AI capabilities while maintaining data security and linguistic compatibility.
Keywords: Sovereign AI, Local LLM, Open Web UI, RAG, Oracle 26ai, Municipal Governance, Arabic NLP, Mixture of Experts, Qwen3.5, Flash Infer
All articles published by MSIP are made immediately available worldwide under an open access license. No special permission is required to reuse all or part of any MSIP article, including figures and tables.
For articles published under a Creative Commons CC BY 4.0 license, any part of the article may be reused for any purpose, including commercial use, provided that the original MSIP article is clearly cited.
INFORMATION AND COMMUNICATION TECHNOLOGY (ICT) AND SERVICE DELIVERY IN AKWA IBOM STATE POLYTECHNIC, IKOT OSURUA
Dr. Rex E. Enwieme, Department of Public Administration University of Uyo, Uyo, Akwa Ibom State, Nigeria.
MSI Journal of AI and Technology | https://zenodo.org/records/19049438 | Page 01 to 30
Abstract
The application of Information and Communication Technology (ICT) in public administration / institution has taken a new dimension as it has become the strength and driver of an efficient service delivery. Thanks to ICT, issues of accountability are addressed through the provision of various levels of information for citizens and public confidence is built in bureaucrats. The essence of this research was to establish the relationship that exists between ICT and services delivery, especially in the case of Akwa Ibom State Polytechnic, Ikot Osurua, Nigeria. Nonetheless, the study highlights certain issues that limit the reach of ICT in the institution which include poor internet connectivity, broken down computer systems, inadequacy of ICT trained personnel, resistance from the staff among other factors. This study was framed within the perspective of Communication Theory by Karl Deutsch (1952) where individuals are communicators at all times since sharing and receiving information occurs in all situations in society. It involved an investigation of the historical and descriptive prospects of the case concerning the problem under scrutiny. Content analysis primarily provided information in the study. The results of the research indicated that one of the variables under investigation, ICT use, and service delivery, are not only positively related but its application in the institution studied showed potential benefits. Furthermore, in connection with the evidence, it was found that the use of ICT has the best chance of facilitating the need for transparency and accountability by the implementation departments. The majority’s viewpoint based on the findings is that the use of ICT will comprise meaningful counseling and guidance as well as develop proper systemic structures for monitoring and evaluation of efficiency in the delivery of services. A point put forward was that the government should come up with ways to improve ICT services by making them more robust and provide I. C. T skills to individuals working in organizations so that they would be used efficiently within the operations of the Akwa Ibom State Polytechnic.
Keywords: Technology, Service Delivery, Internet connectivity computers Information Management System.
All articles published by MSIP are made immediately available worldwide under an open access license. No special permission is required to reuse all or part of any MSIP article, including figures and tables.
For articles published under a Creative Commons CC BY 4.0 license, any part of the article may be reused for any purpose, including commercial use, provided that the original MSIP article is clearly cited.
Assisted but Unguided: AI Tool Integration, Academic Performance, And Institutional Policy Gaps Among Filipino College Students
Cyrus P. Casingal, Department of Education – Schools Division Office of Makati City, Philippines.
Lovejoy R. Caerlang, Yamaguchi, Japan.
MSI Journal of AI and Technology | https://zenodo.org/records/19029680 | Page 01 to 25
Abstract
This research investigated how Artificial Intelligence (AI) tools can affect the performance of college students in one of the state universities in Pangasinan, Philippines. The research design was a convergent parallel mixed-method survey design, in which 300 first- year to fourth-year college students were surveyed in five focus group discussions of five academic colleges to produce both quantitative and qualitative data. A survey instrument developed by the researcher was used to collect quantitative data and semi-structured focus group discussions (FGDs) were used to collect qualitative data. Findings indicated that 91.3 percent of respondents adopted ChatGPT as the major tool of AI. The results also indicated the statistically significant difference in the increase of the General Weighted Average (GWA) of students before (M = 83.72) and after (M = 87.03) regular use of AI tools (p =.001). Generally, students were positive (M = 4.10) that AI tools had positive effects on their academic performance, especially in comprehension of lesson material, quality of writing and research effectiveness.
Nevertheless, qualitative results raised an issue related to over-reliance, academic integrity, and the lack of a formal institutional policy of AI. The article concludes that although it is evident that AI tools can enhance academic performance outcomes, their uncontrolled application has serious pedagogical consequences. The research proposes the creation of AI literacy curriculum, institutional policies about AI usage, and faculty training programs according to the existing and future educational technology standards.
Keywords: Artificial intelligence in education, academic performance, college students, AI tools, ChatGPT, mixed-method research, Philippines, AI literacy.
All articles published by MSIP are made immediately available worldwide under an open access license. No special permission is required to reuse all or part of any MSIP article, including figures and tables.
For articles published under a Creative Commons CC BY 4.0 license, any part of the article may be reused for any purpose, including commercial use, provided that the original MSIP article is clearly cited.
Anthropomorphic Cues in AI Chat bots and Consumer Responses: An Empirical Survey of Trust and Purchase Intention in Online Services
Hafsa Noor Ayub, Hafsa Noor Ayub MBA, NUST
MSI Journal of AI and Technology | https://zenodo.org/records/19064474 | Page 01 to 30
Abstract
This study examines the effect of anthropomorphic cues in AI-powered chat bots on consumer’ purchase intention, investigating the roles of trust (affective pathway) and perceived usefulness (cognitive pathway) in this relationship. A quantitative cross-sectional survey design was used, collecting data from 170 experienced chat bot users across various digital service contexts comprising of e-commerce, online banking and airline booking platforms. Empirically validated multi-item construct measured anthropomorphism, trust, perceived usefulness and purchase intention. Data were studied using descriptive statistics, Pearson correlation and mediation analysis applying both classical product-of-coefficients (a x b) and bootstrapping methods with 1000 re samples to establish reliable confidence intervals. Results show that anthropomorphic cues significantly influence both trust (a = 0.335, p < 0.001) and perceived usefulness (a = 0.383, p < 0.001), supporting H1 and H2. Both mediators positively affect purchase intention (trust: b = 0.665, p < 0.001; perceived usefulness: b = 0.754, p < 0.001), confirming H3 and H4. mediation analysis reveals significant indirect effects through trust (indirect effect = 0.223, 95% CI [0.095, 0.301]) and perceived usefulness (indirect effect = 0.296, 95% CI [0.157, 0.382]), with both demonstrating partial mediation. Perceived usefulness exhibited a marginally stronger mediating effect that trust, suggesting cognitive evaluations may exert slightly greater influence on purchase decisions in task-oriented contexts. This study advances understanding of human-AI interaction by empirically validating a dual-path mediation framework integrating affective (trust) and cognitive (perceived usefulness) mechanism, an integrated approach previously unexplored in chat bot research. It also extends Technology Acceptance Model (TAM) by incorporating anthropomorphism as a predictor and demonstrating that emotional engagement operates alongside functional evaluations. The rigorous methodological approach combining classical and bootstrapped estimates strengthens confidence in the findings.
Keywords: AI chatbots, anthropomorphism, trust, perceived usefulness, purchase intention, technology acceptance model, human-AI interaction, dual mediation.
All articles published by MSIP are made immediately available worldwide under an open access license. No special permission is required to reuse all or part of any MSIP article, including figures and tables.
For articles published under a Creative Commons CC BY 4.0 license, any part of the article may be reused for any purpose, including commercial use, provided that the original MSIP article is clearly cited.
CHRISTIAN DISCIPLESHIP AS A RESPONSE TO CURTAILING NEGATIVE EXCESSES OF ARTIFICIAL INTELLIGENCE AMONG CHILDREN
Abigail Daniel Dariya, Baptist Theological Seminary, Kaduna.
MSI Journal of AI and Technology | https://zenodo.org/records/18862306 | Page 01 to 13
Abstract
Children are the future of any family, church and nation. When they are properly disciplined and trained for the future, they become helpful in the church, themselves, their families, and the community at large. Children are not left out in the era of technological advancement that has ushered in Artificial Intelligence (AI), as they are widely engaged with it. Whereby technology has become more available to them. AI has come to stay, and its continued usage has shaped the digital landscape. With all of these, the concerns about its harmful excesses, such as addiction, misinformation, overreliance on AI, and moral degradation among children, are growing. This paper explores Christian discipleship as a holistic response to these challenges, offering a faith-based framework for ethical engagement with AI. Discipleship fosters moral resilience. By integrating scriptural teachings, mentorship, and community support, Christian discipleship can guide children in developing a Christ-centered digital ethic. This approach not only mitigates AI’s harmful effects but also empowers children to use technology as a tool for good, aligning with their faith and values. Ultimately, this study highlights the role of Christian discipleship in equipping young believers to navigate AI-driven realities with wisdom and integrity.
Keywords: Christian Discipleship, Curtailing, Negative Excesses, Artificial Intelligence, and Children.
All articles published by MSIP are made immediately available worldwide under an open access license. No special permission is required to reuse all or part of any MSIP article, including figures and tables.
For articles published under a Creative Commons CC BY 4.0 license, any part of the article may be reused for any purpose, including commercial use, provided that the original MSIP article is clearly cited.
Design and Evaluation of the Performance of an Electronic Accelerator for Electric Vehicles
Nnaemeka G. Ajah, Department of Electrical Engineering University of Nigeria, Nsukka, Enugu, Nigeria.
Chukwuemeke, Jolly, Department of Electrical Engineering University of Nigeria, Nsukka, Enugu, Nigeria.
Emenike C. Ejiogu, Department of Electrical Engineering University of Nigeria, Nsukka, Enugu, Nigeria.
MSI Journal of AI and Technology | https://zenodo.org/records/18440663 | Page 01 to 09
Abstract
Accelerator pedals can be found in different devices from conventional electronic sewing machines to motorcycles and automobiles. Generally, they are used to control flow from valve or power from pneumatic, hydraulic or electrical systems. In this work, the electronic pedal is designed for use in electric vehicles. It is well understood that when pressure is applied to the throttle pedal in a vehicle, the engine gains acceleration and speed, the opposite occurs when the pressure is withdrawn. This paper discusses the design and evaluation of an electric throttle applicable in electric vehicles.
Keywords: Signal processing, electronic throttle, electric vehicle.
All articles published by MSIP are made immediately available worldwide under an open access license. No special permission is required to reuse all or part of any MSIP article, including figures and tables.
For articles published under a Creative Commons CC BY 4.0 license, any part of the article may be reused for any purpose, including commercial use, provided that the original MSIP article is clearly cited.
Vloggers in Tourism Sector
Associate Professor Dr. Helen Abd El-Hamid Abd El-Hakim Mohamed, Higher Institute of Specific Studies Heliopolis, Cairo, Egypt.
MSI Journal of AI and Technology | https://zenodo.org/records/18411778 | Page 01 to 17
Abstract
The rise of digital media has transformed the travel and hospitality sector, with video content creators “vloggers” emerging as influential figures in shaping travel narratives. digital media platforms has revolutionized the travel and hospitality sector through platforms like YouTube, Instagram, and TikTok, where video content creators (video bloggers) create and share travel-related content. These influencers often provide first-hand experiences, recommendations, and visual narratives that shape audience perceptions of destinations. The influence of video content creators in tourism is a growing research field, focusing on traveler decision-making patterns, travel destination promotion, branding, and the socio-cultural impact of digital media.
The research explores the video content creators’ “vloggers” role in tourism, their influence on consumer decision-making, and the implications for tourism marketers and destination management organizations (DMOs). The issue will involve an interdisciplinary approach, combining theories from marketing, media studies, psychology, and tourism management. The present study determines how video content creators influence modern tourism, creating a new paradigm in travel destination promotion and travel consumption.
The present study examines the following key questions:
How do video content creators impact travelers’ destination choices?
What characteristics define successful travel vlogs?
How do tourism businesses engage with video content creators for marketing purposes?
Keywords: Tourism, Social Marketing, Process Management, Vlog.
All articles published by MSIP are made immediately available worldwide under an open access license. No special permission is required to reuse all or part of any MSIP article, including figures and tables.
For articles published under a Creative Commons CC BY 4.0 license, any part of the article may be reused for any purpose, including commercial use, provided that the original MSIP article is clearly cited.
The Effect of Cybercrime on Digital Economy Growth: A Global Analysis
Arif Mainuddin, Police Staff College Bangladesh, Bangladesh.
Md. Nazmul Huda Masud, University of Dhaka, Bangladesh.
Tamjid Mohd Imrul Ibrahim, International Islamic University Chittagong, Bangladesh.
Rafsan Anwar, United International University, Bangladesh.
Md. Mehedi Hasan Babu, United International University, Bangladesh.
MSI Journal of AI and Technology | https://zenodo.org/records/18366461 | Page 01 to 16
Abstract
The rapid expansion of the digital global economy in the modern digital era has delved led re-conceptualized global relations, unleashing a seldom-before-seen competition, innovation and interactivity. But this extraordinary growth is countered by the equally accelerated growth in cybercrime which undermines trust in digital infrastructures, exudes costs in the operation framework and threatens unsustainable economic growth. It is in this context that the current paper has sought to delve into the global implications of cyber criminality on the development pattern of digital economies thus sealing a respected gap in the current academic literature that has focused its study to regional or industrial levels. Using cross nation repositories such as the World Bank, the IMD Digital Competitiveness Index, ITU, UNODC, and the Global Cyber security Index, the analysis illustrates serious economies of scale to measure the correlation between cybercrime events and the economic performance in digital space through rigorous econometric methods, including, panel regression enhanced by Generalized Method of Moments (GMM). It is found that a negative relationship is statistically robust, with negative impacts over-represented in developing economies that have weaker institutional resilience and suboptimal cyber security readiness. Banking and e- commerce are also identified as specifically vulnerable and they may receive more emphasis due to a nuanced breakdown of sectors; a burden of the costs and lack of customers confidence. However, the evidence highlights that the negative significance of these effects can be reduced by applying strategic investment in the cyber security innovation; thus, enhancing the resilience and restoring digital trust. The theoretical work is found in both the application of the Solow growth model and the Becker crime model to the online realm, and the empirical knowledge generates policy usefulness in the hands of policy makers. Recommendations promote reinforcement of legal systems of the world, increased cross-border collaboration, and raising cyber security to higher levels of development. After all, the challenge of cybercrime is presumed to be not only a security need but, to inclusive digital expansion, an undeniable economic necessity.
Keywords: digital economy, cybercrime, global relations, institutional resilience, cyber security
All articles published by MSIP are made immediately available worldwide under an open access license. No special permission is required to reuse all or part of any MSIP article, including figures and tables.
For articles published under a Creative Commons CC BY 4.0 license, any part of the article may be reused for any purpose, including commercial use, provided that the original MSIP article is clearly cited.
Design and Numerical Validation of an AI-Based Early Cardiac Arrest Detection Machine
Omariba Geofrey Ong’era, Department of Pure and Applied Mathematics, School of Mathematical and Physical Sciences, Jomo Kenyatta University of Agriculture and Technology (JKUAT), Juja, Kenya.
MSI Journal of AI and Technology | https://zenodo.org/records/18329062 | Page 01 to 42
Abstract
Sudden cardiac arrest remains a leading cause of mortality worldwide, largely due to delayed detection and intervention. Most existing monitoring systems identify cardiac arrest only after circulatory collapse has already occurred, significantly limiting the effectiveness of emergency response. This study presents the design and numerical validation of an AI-based early cardiac arrest detection system capable of predicting imminent cardiac arrest prior to its onset. The proposed framework integrates non-invasive physiological sensing with a hybrid physics–artificial intelligence approach. Blood flow dynamics are modeled using the incompressible Navier–Stokes equations, while oxygen transport is represented by a convection–diffusion–reaction model to capture the progressive development of hypoxia under pre-arrest conditions. Numerical simulations are conducted to investigate hemodynamic instability and oxygen depletion patterns associated with declining cardiac output. Key outputs from the numerical model, including velocity fields, oxygen concentration gradients, and a derived hypoxia index, are combined with physiological signals and processed by a machine learning–based prediction engine. The results demonstrate that the proposed system successfully identifies critical pre-arrest signatures and provides early warning within a clinically meaningful time window. This work establishes a robust foundation for predictive cardiac monitoring and highlights the potential of physics-informed AI to improve survival outcomes, enhance emergency medical decision-making, and support the future development of intelligent, real-time cardiac arrest detection devices.
Keywords: Cardiac arrest; Blood flow; Oxygen transport; Numerical simulation; Navier–Stokes equations; Convection–diffusion.
All articles published by MSIP are made immediately available worldwide under an open access license. No special permission is required to reuse all or part of any MSIP article, including figures and tables.
For articles published under a Creative Commons CC BY 4.0 license, any part of the article may be reused for any purpose, including commercial use, provided that the original MSIP article is clearly cited.
