Search Results (20)

Cross-chain bridges represent one of the most damaging attack surfaces in decentralized finance, with major exploits (e.g., Ronin, Wormhole, Nomad, Multichain) arising not from broken signature schemes but from failures in proof verification, replay protection, and signer-set management, gaps that conventional threshold-signature multisignature wallets do not address. This study presents an incident-aware multisignature architecture combining three on-chain predicates—block-height freshness windows, epoch-bound signer sets, and Merkle inclusion-proof verification—with a non-authoritative off-chain LightGBM classifier that generates SHAP-attributed risk explanations to support governance actions such as pausing, vetoing, or rotating signers, without directly blocking or approving execution. The framework was evaluated on a simulated benchmark of 78,600 Ethereum testnet transactions containing six injected anomaly classes (gas spikes, nonce jitter, malformed call data, stale intents, proof-delivery delays, and epoch-rotation replays). The LightGBM advisor achieved ROC-AUC 0.92 (95% CI [0.906, 0.926]) and F1 0.73 ([0.712, 0.749]), outperforming five baselines—logistic regression, Random Forest, XGBoost, isolation forest, and a rule-based detector—with the highest F1 (0.731) and PR-AUC (0.799), while the rule-based detector, which by construction covers only the anomaly classes addressed by the deterministic predicates, attained F1 0.282. Differences were statistically significant except for the LightGBM–XGBoost PR-AUC comparison. The deterministic layer itself is verified through 28 property-level contract tests covering all seven modeled attack objectives, with measured per-function gas costs (execute_Intent: 118,756 gas, of which 28,432 gas is Merkle-proof verification). Within this controlled setting, the results indicate that a machine learning advisor can extend anomaly-prioritization coverage beyond the scope of the deterministic predicates while leaving execution control fully deterministic. This work is presented as a controlled proof of concept: the reported metrics quantify recovery of scripted injection patterns, and validation against real-world exploit traces remains future work. Full article

User-generated content (UGC) offers large-scale, naturalistic data for examining tourism destination image. Focusing on the Historic Centre of Macao (HCM), a World Cultural Heritage site, this study collected 3781 tourist reviews from Rednote, Ctrip, Dianping, and TripAdvisor and developed a multi-model text-mining framework integrating TF-IDF, BERTopic, and RoBERTa. The results show that HCM’s online tourism image comprises four dimensions: perceptions of history, culture, and heritage value; perceptions of spatial landmarks and urban landscapes; modes of travel behavior and embodied experience; and emotional evaluation and tourism experience quality. The TF-IDF results indicate that terms such as architecture, history, Portuguese, church, Ruins of St. Paul’s, and Senado Square constitute the core elements of tourists’ cognitive image. BERTopic further identified 18 valid topics and revealed three interrelated semantic clusters: heritage-space cognition, landmark and district experiences, and integrated tourism experiences. The RoBERTa-based sentiment analysis shows that tourists’ overall evaluations are dominated by positive emotions, while crowding, high visitor density, and gaps between expectations and actual experiences remain important sources of negative evaluations. This study demonstrates the applicability of the proposed framework in the Historic Centre of Macao and provides a methodological reference for tourism image research in other cultural heritage destinations. Full article

Robo-advisors have expanded access to automated investment services, but many platforms continue to rely on relatively static onboarding procedures and limited forms of user interaction. This study examines how participants with investment experience respond to two next-generation robo-advisory design features: financial digital twins, understood as dynamic investor profiles that integrate goals, risk tolerance, cash-flow patterns, and anticipated life events, and conversational artificial intelligence (AI), understood as an interactive interface for explaining recommendations. Using a scenario-based randomized 2 × 2 online experiment, 336 adult respondents with self-reported investment experience, recruited through professional and academic networks, were assigned to one of four robo-advisor scenarios that varied the personalization architecture, standard profile versus digital twin, and the interface style, plain dashboard versus conversational AI, while holding the portfolio recommendation constant. The results show that digital-twin personalization increases perceived personalization and privacy concern, indicating that more adaptive advisory architectures may be viewed as both more relevant and more data-intensive. Conversational AI increases the perceived interactive quality of the advisory experience, while selected willingness-related patterns, especially in the combined digital-twin and conversational-AI condition, are treated as exploratory because several secondary composites displayed limited internal consistency. The strongest confirmatory emphasis is therefore placed on perceived personalization and privacy concern, and the remaining findings are best interpreted as scenario-based investor responses rather than evidence of actual adoption behavior or confirmed psychological mechanisms. The study contributes to behavioral FinTech research by clarifying the personalization–privacy tension in AI-enabled robo-advisory services and by offering design implications for more transparent, interactive, and responsibly personalized digital wealth-management systems. Full article

The exponential rise of e-commerce platforms has resulted in a dramatic increase in online reviews, which creates a challenge in distinguishing fake reviews that erode consumer confidence and harm commerce ecosystems. Traditional approaches for fake review detection employ computationally expensive deep learning networks which are resource-intensive and difficult to use in practice. In this paper, we describe AdaptiveNet, a new lightweight neural architecture that achieves fake review detection with much lower computational resources while maintaining a higher detection and classification precision. The model proposed in this paper is based on three original innovations: a Multi-Scale Semantic Fusion (MSSF) layer for hierarchical feature extraction, Dynamic Attention Scaling (DAS) with complexity measure attention, and Adaptive Parameter Sharing (APS) context-gated networks. With thorough evaluation on Amazon, Yelp, and TripAdvisor datasets of reviews totalling 1.2 million reviews, AdaptiveNet attains 94.8% accuracy while achieving 65% computational overhead in comparison to traditional models. The architecture outperformed all other state-of-the-art models, BERT-base (92.1%), RoBERTa (91.8%), and other more recent efficient models, requiring 70% lower parameters and 60% lower energy consumption. This work markedly advances the other efficient deep learning architectures for text classification and allows for the practical implementation of fake review detection systems in resource-limited settings as process innovation. Full article

Digital cultural heritage platforms face a dual challenge: preserving rich historical information while engaging an audience with declining attention spans. This paper addresses that challenge by proposing a modular information architecture designed to mitigate cognitive overload in cultural heritage tourism applications. We begin by examining evidence of diminishing sustained attention in digital user experience and its specific ramifications for cultural heritage sites, where dense content can overwhelm users. Grounded in cognitive load theory and principles of user-centered design, we outline a theoretical framework linking mental models, findability, and modular information architecture. We then present a user-centric modeling methodology that elicits visitor mental models and tasks (via card sorting, contextual inquiry, etc.), informing the specification of content components and semantic metadata (leveraging standards like Dublin Core and CIDOC-CRM). A visual framework is introduced that maps user tasks to content components, clusters these into UI components with progressive disclosure, and adapts them into screen instances suited to context, illustrated through a step-by-step walkthrough. Using this framework, we comparatively evaluate personalization and information structuring strategies in three platforms—TripAdvisor, Google Arts and Culture, and Airbnb Experiences—against criteria of cognitive load mitigation and user engagement. We also discuss how this modular architecture provides a structural foundation for human-centered, explainable AI–driven personalization and recommender services in cultural heritage contexts. The analysis reveals gaps in current designs (e.g., overwhelming content or passive user roles) and highlights best practices (such as tailored recommendations and progressive reveal of details). We conclude with implications for designing cultural heritage experiences that are cognitively accessible yet richly informative, summarizing contributions and suggesting future research in cultural UX, component-based design, and adaptive content delivery. Full article

A Smart campus increasingly operates on the basis of data-driven operations, but an increasing demand for energy puts their control over costs and sustainability at risk. This study addresses the challenge of anticipating and managing energy consumption peaks in multi-campus environments by proposing a hybrid framework that combines advanced time-series forecasting models with a large language model (LLM)-driven multi-agent system. Based on the UNICON dataset, LSTM, CNN, GRU, and a combination architecture are trained and compared in terms of MAE and RMSE. The hybrid configuration achieves the greatest forecasting results by returning the minimum loss values. For the identification of critical periods, we employed a strategy based on median thresholding, which offers a categorization into low, normal, and extreme category, allowing the targeting of peak mitigation actions. We also introduce a multi-agent system based on the LLM, including the data aggregator, the forecaster, and the policy advisor, which create actionable policies informed by context. We also compare LLMs (Qwen-2.5, Gemma-2, Phi-4, Mistral, Llama-3.3) in terms of context accuracy, response relevance, semantic similarity, and retrieval/recall accuracy and fidelity, with Llama-3.3 achieving the best overall results. This framework has shown great potential, not only for energy consumption forecasting but also for developing precise policies on how to effectively manage energy consumption peaks. Full article

Achieving zero-energy buildings (ZEBs) requires the appropriate planning of renewable energy systems, particularly photovoltaic (PV) systems, from the early design stage (EDS). Conventional PV system design tools have limitations, including insufficient integration with the architectural design process, complex operability, and inability to adequately reflect the characteristics of the EDS. In this study, we developed a PV system optimization tool based on SketchUp, which is widely used in the EDS. The developed tool inputs the building’s 3D modeling information and derives an optimal layout plan that minimizes the number of PV modules while achieving the target energy self-sufficiency rate (ESR) via particle swarm optimization. To verify the performance of the developed tool, a comparative analysis with the System Advisor Model (SAM) was performed, resulting in high accuracy with a maximum relative error of 2.25% in 15 verification cases. Through case studies of 20 different building masses, optimal PV layout plans that stably achieved a target ESR of 20% were successfully derived for diverse mass cases. This tool enables architects to perform preliminary sizing and performance evaluations of PV systems in the EDS without the support of engineers and provides an environment for the integrated consideration of energy performance and esthetics through the presentation of visualized results to support more effective decision-making in the EDS of ZEB projects. Full article

Delivering compelling presentations is a critical skill across academic, professional, and public domains—yet many presenters struggle with structuring content, maintaining visual consistency, and engaging their audience effectively. Existing tools offer isolated support for design or delivery but fail to promote long-term skill development. This paper presents a novel intelligent application, the Presentation Advisor application, powered by a personalized recommendation engine that goes beyond fixing slide content and visualization, enabling users to build presentation competence. The recommendation engine leverages a model based on hybrid multi-tower neural network architecture enhanced with temporal encoding, problem sequence modeling, and utility-based scoring to deliver adaptive context-aware feedback. Unlike current tools, the presented system analyzes user-submitted presentations to detect common issues and delivers curated educational content tailored to user preferences, presentation types, and audiences. The system also incorporates strategic cold-start mitigation, ensuring high-quality recommendations even for new users or unseen content. Comprehensive experimental evaluations demonstrate that the suggested model significantly outperforms content-based filtering, collaborative filtering, autoencoders, and reinforcement learning approaches across both accuracy and personalization metrics. By combining cutting-edge recommendation techniques with a pedagogical framework, the Presentation Advisor application enables users not only to improve individual presentations but to become consistently better presenters over time. Full article

While the importance of indexing strategies for optimizing query performance in database systems is widely acknowledged, the impact of rapidly evolving hardware architectures on indexing techniques has been an underexplored area. As modern computing systems increasingly leverage parallel processing capabilities, multi-core CPUs, and specialized hardware accelerators, traditional indexing approaches may not fully capitalize on these advancements. This comprehensive experimental study investigates the effects of hardware-conscious indexing strategies tailored for contemporary and emerging hardware platforms. Through rigorous experimentation on a real-world database environment using the industry-standard TPC-H benchmark, this research evaluates the performance implications of indexing techniques specifically designed to exploit parallelism, vectorization, and hardware-accelerated operations. By examining approaches such as cache-conscious B-Tree variants, SIMD-optimized hash indexes, and GPU-accelerated spatial indexing, the study provides valuable insights into the potential performance gains and trade-offs associated with these hardware-aware indexing methods. The findings reveal that hardware-conscious indexing strategies can significantly outperform their traditional counterparts, particularly in data-intensive workloads and large-scale database deployments. Our experiments show improvements ranging from 32.4% to 48.6% in query execution time, depending on the specific technique and hardware configuration. However, the study also highlights the complexity of implementing and tuning these techniques, as they often require intricate code optimizations and a deep understanding of the underlying hardware architecture. Additionally, this research explores the potential of machine learning-based indexing approaches, including reinforcement learning for index selection and neural network-based index advisors. While these techniques show promise, with performance improvements of up to 48.6% in certain scenarios, their effectiveness varies across different query types and data distributions. By offering a comprehensive analysis and practical recommendations, this research contributes to the ongoing pursuit of database performance optimization in the era of heterogeneous computing. The findings inform database administrators, developers, and system architects on effective indexing practices tailored for modern hardware, while also paving the way for future research into adaptive indexing techniques that can dynamically leverage hardware capabilities based on workload characteristics and resource availability. Full article

The determination of water requirements for crops holds a crucial role in optimizing irrigation and enhancing agricultural productivity. However, identifying these needs remains a significant challenge due to the variety of factors influencing this decision, such as meteorological conditions, soil structure, and the phenological stages of each crop. In this study, we propose the design and development of a dedicated web-based irrigation advisory platform for arboriculture named ‘Soqia-Advice’. This platform will provide services to farmers, advisors, and decision-makers. The proposed methodology is based on four main steps: (1) need assessments; (2) definition of functionalities to fulfill these needs; (3) design of the overall architecture and the conceptual data model; and (4) implementation of key features of the module dedicated to farmers. The prototype of the “Farmer” module was tested on a farm in Azrou city, Morocco, as a case study. Seven-day weather forecasts were seamlessly integrated using the Weatherbit API. Additionally, the irrigation schedule was accurately displayed, ensuring efficient water management. Functionality tests were conducted on each menu to ensure the seamless and reliable operation of all planned features. The results were rigorously assessed to ensure that each feature aligned with the identified needs. Full article

Based on big data, a new public space evaluation method is proposed. Using programming technology to collect visitor reviews from the travel website TripAdvisor to build a database, based on the data of 99,240 words in 1573 visitor reviews in 10 years, the connection between data and reality is established through systematic data classification and visualization. Following an assessment of the Kimbell Art Museum’s functionality, architectural design, and landscape design, along with visitor feedback, a new evaluation methodology was formulated for application to public buildings with landscapes. By utilizing the unique advantages of big data, it provides convenient and efficient analysis methods for public spaces with similar data foundations and opens the way for the optimization of the built environment in the information age. Full article

Recent advancements in artificial intelligence have enabled reinforcement learning (RL) agents to exceed human-level performance in various gaming tasks. However, despite the state-of-the-art performance demonstrated by model-free RL algorithms, they suffer from high sample complexity. Hence, it is uncommon to find their applications in robotics, autonomous navigation, and self-driving, as gathering many samples is impractical in real-world hardware systems. Therefore, developing sample-efficient learning algorithms for RL agents is crucial in deploying them in real-world tasks without sacrificing performance. This paper presents an advisor-based learning algorithm, incorporating prior knowledge into the training by modifying the deep deterministic policy gradient algorithm to reduce the sample complexity. Also, we propose an effective method of employing an advisor in data collection to train autonomous navigation agents to maneuver physical platforms, minimizing the risk of collision. We analyze the performance of our methods with the support of simulation and physical experimental setups. Experiments reveal that incorporating an advisor into the training phase significantly reduces the sample complexity without compromising the agent’s performance compared to various benchmark approaches. Also, they show that the advisor’s constant involvement in the data collection process diminishes the agent’s performance, while the limited involvement makes training more effective. Full article

AI-based software applications for personalized nutrition have recently gained increasing attention to help users follow a healthy lifestyle. In this paper, we present a knowledge-based recommendation framework that exploits an explicit dataset of expert-validated meals to offer highly accurate diet plans spanning across ten user groups of both healthy subjects and participants with health conditions. The proposed advisor is built on a novel architecture that includes (a) a qualitative layer for verifying ingredient appropriateness, and (b) a quantitative layer for synthesizing meal plans. The first layer is implemented as an expert system for fuzzy inference relying on an ontology of rules acquired by experts in Nutrition, while the second layer as an optimization method for generating daily meal plans based on target nutrient values and ranges. The system’s effectiveness is evaluated through extensive experiments for establishing meal and meal plan appropriateness, meal variety, as well as system capacity for recommending meal plans. Evaluations involved synthetic data, including the generation of 3000 virtual user profiles and their weekly meal plans. Results reveal a high precision and recall for recommending appropriate ingredients in most user categories, while the meal plan generator achieved a total recommendation accuracy of 92% for all nutrient recommendations. Full article

Compilation often takes a long time, especially for large projects or when identifying better optimization options. Currently, compilers are mainly installed on local machines and used as standalone software. Despite the availability of several online compilers, they do not offer an efficient all-in-one package for private account management, command line interface (CLI), code advisors, and optimization techniques. Today, the widespread usage of Software as a Service (SaaS) is ever-growing, and compilers are not an exception. In this paper, we describe a symmetric approach to compilation and how to compile code on distributed systems. Although some improvements in cloud compilers have been made, it is possible to harness the potential of the most-modern technologies and architecture patterns toward designing efficient, in-cloud compilers. In this paper, we propose an architecture design of a cloud-based compiler that is fully compatible with orchestration technologies, such as Kubernetes, providing a higher level of scalability, reliability, security, and maintainability. Microservice architecture alongside containerization and orchestration technologies assist us in making a scalable system that provides a high level of availability. We propose this architecture so that the system can handle a higher workload as it receives a large number of compilation requests per second. Distributed compilation is a prominent benefit of this approach, as each phase of the compilation can be executed in a separate server, which supplies a kind of workload mitigation to the whole system. In other words, we propose a new perspective for an intelligent way of advisor, error detection, and optimization of compilers. We also propose an implementation example of the developed architecture. Finally, we analyze the results from an experimental implementation, proving that we can compile code from more than 100k requests concurrently on a cloud cluster with one master node and three worker nodes. Full article

The extensive use of Internet of Things (IoT) technology has recently enabled the development of smart cities. Smart cities operate in real-time to improve metropolitan areas’ comfort and efficiency. Sensors in these IoT devices are immediately linked to enormous servers, creating smart city traffic flow. This flow is rapidly increasing and is creating new cybersecurity concerns. Malicious attackers increasingly target essential infrastructure such as electricity transmission and other vital infrastructures. Software-Defined Networking (SDN) is a resilient connectivity technology utilized to address security concerns more efficiently. The controller, which oversees the flows of each appropriate forwarding unit in the SDN architecture, is the most critical component. The controller’s flow statistics are thought to provide relevant information for building an Intrusion Detection System (IDS). As a result, we propose a five-level classification approach based on SDN’s flow statistics to develop a Smart Attacks Learning Machine Advisor (SALMA) system for detecting intrusions and for protecting smart cities from smart threats. We use the Extreme Learning Machine (ELM) technique at all levels. The proposed system was implemented on the NSL-KDD and KDDCUP99 benchmark datasets, and achieved 95% and 99.2%, respectively. As a result, our approach provides an effective method for detecting intrusions in SDNs. Full article