Authors - Yad Sabah Hussein, Raid W. Daoud, hab Abdulrahman Satam, Mohammad Fakhreldin Abstract - This systematic review investigates the design strategies and performance outcomes of AI-powered robotic systems in warehouse automation. The study synthesizes recent advances in robotic navigation, object recognition, task scheduling, and multi-robot coordination, with particular emphasis on machine learning and reinforcement learning techniques that allow robots to adapt to dynamic environments and optimize decision-making in real time. Performance evaluation across the literature reveals significant improvements in throughput, accuracy, and flexibility when AI-driven robotics are deployed. Robots equipped with advanced sensors and computer vision systems demonstrate enhanced capabilities in obstacle avoidance, inventory management, and autonomous material handling. Integration with cloud computing and Internet of Things (IoT) infra-structures further strengthens interoperability and enables predictive analytics for supply chain optimization. Key performance metrics such as energy efficiency, error reduction, and scalability are analyzed to highlight the comparative ad-vantages of AI-enhanced solutions over conventional automation. Despite these advances, challenges remain in ensuring safety, interoperability among heteroge-neous systems, and cost-effective scalability. High implementation costs, cyber-security risks, and the absence of standardized protocols are identified as barriers to widespread adoption. The review concludes that hybrid approaches—combining learning-based adaptability with formal safety guarantees—represent a promising direction for future research. Moreover, sustainable design practices and energy-efficient robotics are essential to align warehouse automation with broader environmental goals. This review provides a consolidated perspective on the state of AI and robotics in warehouse automation, offering insights for re-searchers, practitioners, and industry leaders seeking to design resilient, intelligent, and sustainable warehouse systems.
Authors - Johanes Fernandes Andry, Hendy Tannady, Glisina Dwinoor Rembulan, Ongky Alex Sander, Guan Nan Abstract - Fast paced change in digital transformation, government institutions have been forced not only to embrace IT but to also govern it strategically for alignment with organizational goals. Unfortunately, most organizations still grapple with several major problems including lack of alignment between business and IT and unreliable configuration data management. In light of this, this research proposes an effective IT governance strategy that will address the out-lined challenges through utilization of the COBIT 2019 approach. Based on the results, the organization is moderately mature in terms of compliance and risk awareness but still needs improvement in the alignment between its IT and business objectives and the validation of configuration data. Moreover, organizational resistance and lack of user involvement were found to be among the most important obstacles to successful implementation. According to the findings, the application of COBIT 2019 framework in the process of governance is likely to lead to better governance capacity, higher quality of information, and improved decision-making processes.
Authors - Xinyi ZHU, Han Wang, Jun WU Abstract - In rainy-day images, rain patterns exhibit complex morphologies and significant variations in scale, and they tend to overlap with background textures and edge structures, posing significant challenges for rain removal tasks based on a single image. Addressing the shortcomings of existing methods in modeling complex rain patterns, enhancing key regions, and utilizing complementary information across channels, this paper proposes a multi-scale attention and multi-channel fusion image rain removal method tailored for complex rain pattern scenarios. First, we construct a parallel multi-scale feature extraction module that uses standard convolutions and dilated convolutions with varying dilation rates to capture fine-scale local rain patterns, mesoscale rain patterns, and large-scale contextual information, thereby enhancing the network's ability to perceive rain patterns across multiple scales. Second, an adaptive attention optimization module is designed to re-calibrate multi-scale features across both channel and spatial dimensions, enabling the model to focus more on areas with dense rain patterns, edge structures, and effective texture information. Finally, a multi-channel feature interaction and fusion mechanism is introduced. Through channel segmentation, cross-channel interaction, and residual fusion, this mechanism enhances information complementarity between different feature subspaces, thereby improving the structural preservation and visual naturalness of the restored results. Experimental results on the Rain100H, Rain100L, Rain12, and SPA-Data datasets demonstrate that our method achieves superior rain removal performance across multiple test scenarios, exhibiting particularly strong generalization capabilities in real-world rainy conditions.
Authors - Jatmiko Yogopriyatno, Nursanty, Yorry Hardayani Abstract - Ambiguity in public decision-making constitutes a structural impediment to effective e-governance, manifesting as procedural uncertainty, inconsistent treatment of analogous cases, and unclear authority allocation. This study examines the Integrated Aspiration and Minutes Management Information System (SMART MURA) developed by the Regional Legislative Council (DPRD) of Musi Rawas Regency, Indonesia, as a sociotechnical solution for resolving decision ambiguity through stakeholder consensus-based participatory design. Employing design science research (DSR) methodology, the study analyses the SMART MURA User Guide as a social contract encoding collective stakeholder agreements generated through multi-stakeholder Focus Group Discussions involving five organisational levels. Three ambiguity-resolution mechanisms are identified: (1) bounded automation for standardising routine administrative processes, (2) explicit judgment points for clarifying the locus of professional discretion, and (3) flexible categorisation that accommodates case complexity without sacrificing treatment consistency. These mechanisms produce four interdependent governance benefits: procedural certainty for citizens, cross-case treatment consistency, traceable accountability through digital audit trails, and operational efficiency. The system further demonstrates structural adaptability to regulatory change and incorporates a tiered data governance architecture that balances operational transparency with individual privacy protection. The study advances e-governance theory by proposing a Transparent Discretionary Space Structuring (TDSS) framework that transcends the binary opposition between rigid Standardization and unstructured discretion. Keywords: E-Governance, Public Decision Ambiguity, Design Science Research, Digital Discretion, Participatory Design, Legislative Information System, Data Governance.
Authors - A. Aruna Kumari, Tamminana Visweswari, Sri Vishnu Prabhu Gudavalli Abstract - Globally, food waste accounts for almost one-third of total food production, which is approximately 1.3 billion tons annually. Some of the most wasted foodstuffs at the consumer level include fruits, vegetables and bread. This proposed work will help to solve this financial and environmental issue by creating an intelligent system to eliminate vegetable waste with the help of MobileNetV2 which is a Convolutional Neural Networks (CNN) based model to classify the freshness of vegetables and use object detection model called as YOLOv8n to recognize types of vegetables. It begins with the user uploading images of vegetables, which are pre-processed with the help of normalization and data augmentation. The MobileNetV2 model categorizes fresh and spoiled produce with accuracy rates of 95 percent, which is expected of a Freshness classifier. In the meantime, the YOLOv8n finder detects the specific type of vegetable with the help of a mAP50 of 0.934 to recommend the specific vegetable. If the vegetable is spoilt, it will provide instructions on how to compost and if it is fresh, it provides zero waste recipes. The entire system shall be made easily accessible in a web application that has Flask back-ends.
Authors - Marco Vinicio Lopez R., Maria Cristina Espin Melendez, Jeanette Elizabeth Jordan Buenano, Santiago Vayas Castro, Segundo Moises Toapanta Toapanta, Ruben Nogales Portero, Juan Escobar Naranjo, Diego Gustavo Andrade Armas, Rodrigo Del Pozo Durango Abstract - Connecting more devices to monitor energy and the environment creates serious hurdles for data security, integrity, and scale. This research presents a system merging blockchain with IoT, built specifically to respect Ecuador’s Organic Law on Personal Data Protection (LOPDP). The setup uses ESP32 microcontrollers and sensors to track environmental and power data, sending it over the MQTT protocol to a database. Digital fingerprints created with SHA-256 are locked onto a private blockchain using Proof-of-Authority to keep every record permanent and unchangeable. A 10-day experiment in two indoor spaces generated roughly 96,000 records to test how the system holds up in the real world. Results demonstrate the system's viability, achieving a median end-to-end latency of 182 ms (P95 < 240 ms), a Node Availability Index (NAI) of 98.6%, and an Anomaly Detection Rate (ADR) of 91.4%. Furthermore, the blockchain integration introduced a computational and energy overhead of less than 7%. The study concludes that this architecture provides a verifiable link between physical sensors and digital records, highlighting the bidirectional need for technology to comply with national privacy laws while urging regulatory frameworks to evolve and formalize smart contract applications.
Authors - Mohammed Rasol Al Saidat, Khaled Shaalan, Suleiman Y. Yerima Abstract - This paper presents a technical bibliometric review of artificial intelligence for bilingual Arabic–English smishing detection. It maps the evolution of machine learning, deep learning, and NLP for SMS phishing detection, identifies Arabic–English linguistic and security challenges, and grounds the review in an empirical audit of a public Arabic SMS spam corpus. The methodology pairs a PRISMA-style protocol and bibliometric mapping with the parsing of 1,494 SMS records (747 ham, 747 spam) from a public GitHub dataset. The field has shifted from rules and classical feature engineering to CNN, LSTM, Bi-LSTM, transformer, and large language model approaches. The dataset audit reveals strong class-conditional cues: spam messages are far longer and far richer in digits, phone numbers, short codes, URLs, currency markers, and Latin residues. A reproducible bilingual character TF-IDF baseline with a Linear SVM reached 0.9779 mean accuracy and 0.9775 F1 under stratified three-fold validation, matching the referenced CNN-Bi-LSTM model (0.9699 accuracy, 0.9707 F1). Robust bilingual smishing detection therefore requires hybrid text–security features, Arabic morphology-aware normalization, Unicode safety screening, external validation, and explainable deployment.
Authors - Rodrigo Del Pozo Durango, Moises Toapanta T., Antonio Orizaga T., Rocio Maciel A., Victor Larios Rosillo, Jeanette Elizabeth Jordan Buenano, María Cristina Espin Melendez, Santiago Vayas Castro, Pamela Toapanta Pavon, Andres Hermann-Acosta Abstract - Cybersecurity governance in Higher Education Institutions (HEIs) in Ecuador faces persistent challenges: Information and Communication Technologies are regarded merely as operational tools, without adequate integration of international standards or a legal foundation within institutional processes. This situation generates high vulnerability to threats such as phishing, ransomware, and data breaches. The objective of this research is to define an integrated model for cybersecurity governance, public administration, and legal foundations for an HEI in Ecuador. A deductive method with a mixed quantitative–qualitative approach was employed, structured into four phases: systematic literature review indicator design, model construction, and scenario simulation. The main result is an integrated model structured into three hierarchical and interrelated levels: the Technical Level, comprising incident management, security infrastructure, and technological maturity, aligned with NIST CSF 2.0 and EGSI v3.0; the Administrative Level, focused on ICT strategic planning, organizational governance, and continuous improvement, based on COBIT 2019; and the Legal Foundation Level, grounded in the 2024 Constitution, the 2026 Organic Law on Cybersecurity, the 2021 Organic Law on Personal Data Protection, and the 2025 Comprehensive Organic Criminal Code. The model incorporates 15 weighted indicators and was validated through simulation across four scenarios, using an optimality threshold of ≥ 75 points. It is concluded that three-dimensional integration technical, administrative, and legal is a necessary condition for Ecuadorian HEIs to achieve ICT strategic alignment, resource optimization, and digital resilience, thereby positioning them as key actors in national cybersecurity public policy.
Authors - Eric Khang Heng Ooi, Yit Yin Wee Abstract - Printed circuit boards (PCBs) are increasingly dense and visually complex, making reliable component detection important for automated optical inspection and manufacturing quality control. This paper presents a modified R-CNN framework for integrated-circuit (IC) component detection in PCB images. The framework consists of PCB region extraction, colour-guided region proposal generation, Bayesian convolutional neural network (BCNN) feature extraction, and support vector machine (SVM) classification. Candidate regions are produced using colour masks that emphasize dark and silver IC-like regions. Each candidate is resized, represented by the BCNN, and classified by the SVM as IC or background. Experiments on a PCB component dataset show that the proposed method achieves an mAP of 0.613, outperforming R-CNN with Selective Search Fast (0.392) and Selective Search Quality (0.430). YOLO obtains the highest mAP of 0.686; however, the proposed framework remains useful as an interpretable region-based pipeline for PCB inspection.
Authors - Chandravadan Goritiyal, Aditi Bairolu Abstract - The engine of the world is energy. Fossil fuels continue to be the primary source of energy generation. Nonetheless, several of the world's most important organizations and nations banded together to address the greatest sustainability challenge facing humanity: climate change caused by greenhouse gas emissions. It has been noted that the most workable approach would be to refocus attention from fossil-fuel energy production to renewable energy. However, there are year-round availability issues with renewable energy as well. For instance, solar energy can only be produced during the day, and in India, during the monsoon season hardly solar energy produced. Similar issues are noted in other nations as well. When there is not enough wind to support its spin, wind power frequently stands still and is entirely dependent on air currents. Therefore, the study focuses on what India as a nation should do. For example, investigating clean base load electricity, such as nuclear, to guarantee a constant demand for grid power; solar and wind power will support this, making the total power supply sustainable and environmentally friendly. Also Industry requires continuous and reliable power all the time.
Authors - Monica Cruz, Abilio Oliveira, Ricardo Dias Abstract - Although immersive technologies such as VR, AR, MR and XR are increasingly integrated into university teaching, existing research remains conceptually fragmented and technologically heterogeneous. This study examines how the Metaverse is represented, characterised, and applied in higher‑education contexts through a meta-analysis using Voyant tools for text analysis. To address this gap, the study investigates recent publications to answer the research question: How is the Metaverse being represented, characterised, and applied within higher‑education contexts? Three objectives guided the analysis: identifying how the Metaverse is conceptualised in educational literature, examining the dimensions that facilitate or hinder its adoption, and mapping the leading Metaverse‑related technologies used in higher‑education environments. The findings show that adoption is shaped by perceived usefulness, immersion, social presence and technological readiness, while challenges persist regarding accessibility, infrastructure and conceptual clarity. The study contributes to the scientific literature by consolidating dispersed definitions, clarifying adoption‑related factors and identifying the immersive technologies most frequently associated with Metaverse‑based learning. The results provide a structured foundation for future research and offer higher‑education institutions insights into the opportunities and constraints of integrating Metaverse technologies into teaching and learning.
Authors - Ali Fenjan, Mohammed Almulla, Jalil Md Desa Abstract - Android malware detection datasets are commonly designed for classification accuracy, while their ability to support explainability, forensic interpretation, and analyst-driven security reasoning remains limited. This paper presents APU-Android, an explainable static–behaviour feature dataset for An-droid malware forensics and security analytics. The dataset contains 4,594 APK records; after duplicate removal, 4,281 cleaned records were used in the strict evaluation. APU-Android represents each APK using nine interpretable features: requested permissions, API calls, file size, encryption usage, obfuscation level, network requests, suspicious keywords, network-risk flag, and Behaviour Score. Unlike opaque high-dimensional representations, each feature is mapped to a security-relevant meaning, allowing model decisions to be interpreted in terms of privilege abuse, API capability, concealment, communication risk, suspicious string evidence, and behavioural risk. The evaluation excluded du-plicated normalized columns, applied group-aware splitting using App_Name, and benchmarked five machine-learning classifiers. Under group-aware evaluation, Extra Trees achieved 98.72% accuracy, 99.38% precision, 98.37% recall, 98.87% F1-score, and 99.84% ROC-AUC using only the nine original explain-able features. Ablation analysis further examined the role of Behaviour Score and Obfuscation Level, while SHAP analysis showed that Network_Requests, API_Calls, and Permissions_Requested were the most influential prediction features. The results demonstrate that APU-Android is not only classification-ready, but also explanation-ready and forensic-ready for Android malware security analytics.
Authors - Senaya Nurandhi Jayawickrama, Tithira Mojitha Ranasingha, Dineth Randika Kumaranayake, Udageeth Dias, Kavinga Yapa Abeywardena, Amila Nuwan Senarathne Abstract - The increased digitization of banking operations has increased the value of data assets while also exposing them to growing cyber risks, creating a need for effective risk management mechanisms. Cyber insurance is a risk transfer mechanism that enables organizations to mitigate financial losses by transferring cyber risks to third party insurers. However, in many emerging markets, including Sri Lanka, cyber insurance remains underdeveloped due to limitations in existing premium calculation models, as they lack transparency and fail to incorporate data asset valuation and relevant security parameters, resulting in inaccurate and unfair premiums. This study proposes a structured framework that integrates data asset valuation with premium calculation, while defining multiple insurance coverage categories to address financial losses arising from regulatory, operational and recovery risks. By incorporating data asset value, operational criticality and organizational security posture into the premium calculation process, the proposed models enhance the accuracy and fairness of premium values.
Authors - Nguyen Ngoc-Tuan, Nguyen Van-Giap Abstract - Blended learning (BL) has played an important role in the improvement of learners. The special features of BL are useful for teachers and students, such as various learning contents, personal learning activities, and the mechanism related to authentic learning. However, the BL influences for different major students should be carefully studied and will contribute to the community. This study investigates the influences of BL based on a blended learning system (BLS) on university students’ achievement in different majors. Based on 247 courses in two years (2023 and 2024), without and with the BLS, we gathered and analysed the learning achievements of more than 9000 students from different majors stud-ying at a university. We also categorised the students into two main majors, in-cluding social science (SSCI) majors and engineering majors (SCI). Learning based on the system, the learning achievement of SSCI students is significantly higher than that of SCI students. We also found that the BLS improved the learning scores of the good students learning in both SSCI and SCI majors. Addition-ally, the SSCI students’ scores were significantly higher than those of the SCI students. The direction in the skills assessment of the SCI majors may be the main cause of the differences in university educational settings. Several suggestions on how to attract the low-scoring students to learn actively with BLS were also given. The important findings can contribute to the community to develop and apply blended learning for the different university major contexts.
Authors - Janitha Prabodha Bandara Dissanayaka, Pumudu A. Fernando, Manul Randula Singhe Abstract - Three-dimensional scene representation has moved quickly from Neural Radiance Fields (NeRF) to explicit volumetric methods such as 3D Gaussian Splatting (3DGS). 3DGS can render photorealistic scenes in real time, but editing these scenes is still difficult because Gaussian primitives do not have a fixed mesh structure or explicit topology. This becomes more challenging in dynamic scenes, where edits must remain stable across time and viewpoint. This paper presents a systematic literature review of neural volumetric editing methods for dynamic 3DGS and related NeRF-based representations. The review follows a PRISMA-guided process and analyses studies published between 2023 and 2026. The selected methods are grouped into three main paradigms: text-guided editing, interaction-based editing, and physics-based simulation. The review compares these methods using control precision, rendering speed, memory usage, editing time, temporal stability, and practical limitations. The findings show that text-guided methods are easy to use but often suffer from weak localisation and temporal inconsistency. Interaction-based methods provide stronger geometric control but struggle with complex topology changes. Physics-based methods produce more realistic motion but require higher computation and reliable material parameters. The review identifies the consistency gap, including flickering and texture swimming, as the main barrier to real-world dynamic neural volumetric editing.
Authors - Mazin Alshamrani Abstract - Wearable physiological monitoring systems are increasingly deployed in health-critical contexts, yet existing approaches address state classification, transition detection, and signal safety as isolated problems. This paper introduces SafeWear, a unified signal quality-aware machine learning framework that jointly addresses (i) real-time and anticipatory detection of physiological state transitions, and (ii) multimodal anomaly detection and out-of-distribution (OOD) safety screening. The framework centres on a modality-level Signal Quality Index (SQI) acting as a front-end reliability gate distinguishing sensor-level failures from genuine physiological irregularities. Causal temporal models are evaluated for transition detection, while reconstruction-based and one-class detectors are benchmarked for anomaly safety under strict Leave-One-Subject-Out Cross-Validation (LOSO-CV) across 37 subjects and five wearable modalities. Preliminary results show causal models achieve median detection latencies below 5.2 s with early-detection rates exceeding 79%, and Deep SVDD with VAE yield the strongest anomaly discrimination (AUROC = 0.539 and 0.538).
Authors - Hoang Anh Tuan, Le Thien Nhi Abstract - As governments digitize public services, educational platforms have emerged as essential e-governance infrastructure managing users’ personal and academic data. Vietnam’s National Digital Transformation Program enforces higher education digitalization as a strategic priority, but how users’ perceive the security of these systems, and whether such perceptions translate into trust, remains underexplored. This study review literature linking Perceived Information Security Assurance, Perceived Information Security Risk, Trust, Intention to Use, and Intention to Share Personal Information among university students in Hanoi and Ho Chi Minh City. Drawing on the Technology Acceptance Model, Protection Motivation Theory, and the CIA triad, the review proposed that security assurance strongly predicts trust, and trust drives both usage intention and willingness to share personal data. Contrary to expectations, perceived risk does not diminish trust but coexists with continuous platform use. As artificial intelligence features become more standardized in educational e-governance, these trust dynamics gain urgency as citizens or users must trust not only data handling but algorithmic/AI decision-making. The review synthesizes evidence from e-government adoption, educational systems and AI governance literatures to understand trust formation in AI-enhanced educational e-governance, with implications for platform design, policy development, and future research addressing accountability and e-governance in educational contexts.
Authors - Israel Herrera-Miranda, Miguel Apolonio Herrera-Miranda, Juan Villagomez-Mendez, Silvia Lizbeth Herrera-Lopez Abstract - This paper analyzes the characterization and adoption of Information and Communication Technologies (ICT) and GenAI (GAI) within the framework of digital governance and higher education policies in México. Framed around the early years of President Claudia Sheinbaum Pardo's administration (2024–2030), the study evaluates how emerging regulatory instruments and administrative agencies—specifically the newly enacted Telecommunications and Broadcasting Law (2025) and the Agency for Digital Transformation and Telecommunications (ADTT)—act as institutional backbones to reduce technological gaps and preserve digital sovereignty. Methodologically, this study relies on a documentary and reflective analysis, utilizing empirical indicators from the OECD Digital Government Index (DGI) and the results of México's 2025 National Survey on GAI in Higher Education. The findings indicate that while México exhibits a strong performance in digital-by-design policy frameworks, structural challenges persist regarding proactive public sector AI integration. Concurrently, higher education data reveals an accelerated, mass adoption of GAI by over 60% of students and faculty, transforming traditional pedagogical paradigms. In response, the Ministry of Public Education (SEP) has advanced a ten-point strategy targeting digital literacy, curricular overhauls, and ethical boundaries. Ultimately, this paper underscores that bridging the digital divide requires co-aligning public innovation frameworks with human-centric, ethically-governed higher education policies to foster national technological autonomy and sustainable socioeconomic development.
Authors - Humberto Merritt Abstract - In recent years, the use of digital applications for data management, information access, communication and resource exchange has grown worldwide. Advances in telecommunications have been particularly pervasive in Mexico, where the widespread use of smartphones has encouraged the adoption of digital technology. In this study, we examine the implementation of the APP CDMX electronic platform, which was designed to enhance Mexico City's functionality. The research aims to determine how this tool has helped citizens learn about available public services and how they evaluate it. In particular, the research describes how smartphone users are leveraging the application to access real-time data on local procedures and their fees, the traffic conditions, specific transit routes and stations, and other touristic venues, thereby achieving not only more efficient mobility but also encouraging a sustainable lifestyle. Using a qualitative methodology based on the lexical analysis of user opinions and adopting a multidisciplinary approach, the study concludes that the APP CDMX has positively transformed citizen interaction, accelerating administrative processes and democratizing access to key information.
Authors - Luis Romel Assis Oliveira Junior, Olivan da Silva Rabelo, Paulo Henrique da Silva Santos Abstract - The article proposes the Dodecahedral Framework as a conceptual model to analyze Metaverse Experience Networks, differentiating them from Internet Social Networks and characterizing them as a new object of academic study. The approach explores four dimensions – Immersive Realism, Spatiotemporal Disruption, Meta Culture and Tokenized Economy. The methodology consists of a bibliographic review and the theoretical formulation of the model. The results indicate that Metaverse Experience Networks offer new forms of socialization, interactivity, and engagement, profoundly impacting marketing, consumption, work, and digital culture. It is concluded that the Dodecahedral Framework can serve as a tool for researchers and professionals, assisting in the understanding, planning, and implementation of strategies within the metaverse, in addition to opening paths for new investigations on its technological and social implications.
Authors - Meshak Ratshikombo, Mehrdad Ghaziasgar Abstract - Deep Reinforcement Learning has emerged as a promising approach for algorithmic trading, but trading performance remains highly sensitive to reward design. This study investigates how reward engineering shapes learned trading behavior by training agents exclusively on FTSE market data under identical conditions while varying only the reward formulation. Evaluation across multiple unseen equity indices demonstrates that reward functions induce distinct behavioral biases governing exposure timing, volatility sensitivity, and downside risk. Profit-oriented rewards encourage aggressive trading and higher variability, whereas risk-aware and sparse rewards produce more stable policies with improved drawdown control. The findings show that reward engineering acts as a strong inductive bias influencing both trading behavior and cross-market generalization in reinforcement-learning-based trading systems.
Authors - Lydie Simone Tapsoba, Salifou Ouoba, Athanase Sawadogo Abstract - Malaria is the leading cause of child mortality in Burkina Faso and accounts for over 40% of public health expenditure. This study develops and validates a hybrid machine learning model combining Random Forest (40%) and XGBoost (60%) to predict the spatio-temporal dynamics of malaria across the country’s 13 health regions over the period 2010–2024. The model incorporates satellite-derived climatic variables (CHIRPS precipitation, MODIS NDVI, temperature) and demographic variables, enhanced by advanced feature engineering: 3- and 6-month moving averages of precipitation, temporal lags and circular encoding of seasonality. Validation combines a prospective temporal split for 2024 and spatial GroupKFold cross-validation. On the independent 2024 test set, the hybrid model achieves exceptional performance, substantially outperforming the best previously published approaches for this context. Interpretability analysis reveals surprising determinants of transmission, highlighting the equal role of environmental and anthropogenic factors in Burkina Faso. The SHAP analysis identifies the 3-month moving average of rainfall as the dominant variable, ahead of population density, highlighting the equal role of environmental and anthropogenic factors. The priority areas are Hauts-Bassins, the East and the South-West. The risk maps and 6-month predictions serve as operational tools for the National Malaria Control Programme.
Authors - Yasmany Prieto, Christopher Moyano Abstract - Communication systems are shifting toward more software-based development, driven by technologies such as Software-defined Networking and Network Function Virtualization. This new paradigm improves flexibility, scalability, and resource efficiency, shortens time-to-market, but opens a new dimension of system failure through bugs, backdoors, and software vulnerabilities. In this work, we build a Decision Tree (DT) classifier to predict vulnerability exploitability in networking systems. A list of vulnerabilities affecting those systems is obtained from the National Vulnerability Database. To measure exploitability, we employ the Cybersecurity and Infrastructure Security Agency Known Exploited Vulnerabilities Catalog, which lists vulnerabilities that have been exploited in the wild. The DT classifier achieved a recall of 0.878 in detecting exploitable vulnerabilities.
