The optimization of project schedules in the presence of uncertainty remains a critical challenge in project management. This study proposes a hybrid methodology that combines Monte Carlo Simulation (MCS) with Integer Linear Programming (ILP) to optimize project crashing strategies under conditions of schedule risk. The approach was applied to a real-world telecommunications infrastructure project, which involved the construction of 50 towers within a stringent contractual deadline. MCS was employed to model the uncertainty in activity durations and assess the likelihood of on-time project completion, while ILP was used to determine the most cost-effective crashing strategy. The findings indicate that, without any mitigation measures, the probability of completing the project within the planned 68-day schedule was a mere 3%. However, upon implementing risk response measures, this probability increased to 21%. A comparative analysis demonstrated that delay penalties increase at a much higher rate than crashing costs, highlighting the significant financial benefits of early intervention. This study illustrates that the integration of probabilistic risk analysis with optimization techniques not only enhances schedule reliability but also minimizes cost overruns, providing a robust decision-making framework for complex projects. By leveraging the combination of MCS and ILP, the proposed methodology supports the development of more resilient and economically efficient project plans, particularly in projects characterized by high uncertainty and time-sensitive constraints.

The integration of heterogeneous medical data remains a major challenge for clinical decision support systems (CDSS). Most existing deep learning (DL) approaches rely primarily on imaging modalities, overlooking the complementary diagnostic value of electronic health records (EHR) and physiological signals such as electrocardiograms (ECG). This study introduces MIMIC-EYE, a secure and explainable multi-modal framework that fuses ECG, chest X-ray (CXR), and MIMIC-III EHR data to enhance diagnostic performance and interpretability. The framework employs a rigorous preprocessing pipeline combining min–max scaling, multiple imputation by chained equations (MICE), Hidden Markov Models (HMMs), Deep Kalman Filters (DKF), and denoising autoencoders to extract robust latent representations. Multi-modal features are fused through concatenation and optimized using a Hybrid Slime Mould–Moth Flame (HSMMF) strategy for feature selection. The predictive module integrates ensemble DL architectures with attention mechanisms and skip connections to capture complex inter-modal dependencies. Model explainability is achieved through Local Interpretable Model-agnostic Explanations (LIME) and Shapley Additive Explanations (SHAP), enabling transparent clinical reasoning. Experimental results demonstrate superior performance, achieving 98.41% accuracy, 98.99% precision, and 98.0% sensitivity—outperforming state-of-the-art baselines. The proposed MIMIC-EYE framework establishes a secure, interpretable, and generalizable foundation for trustworthy AI-driven decision support in critical care environments.

Drones have a problem with command transmission under Ultra-Reliable Low Latency Communication (URLLC) requirements. This paper discusses minimizing Packet Error Rate (PER) in an Unmanned Aerial Vehicle (UAV) relay system that transmits commands under Ultra-Reliable Low Latency Communication requirements. The problem is solved through joint optimization of block-length allocation and UAV placement. To tackle these challenges, the optimization problem was split into two sub-problems to analyze the convexity and monotonicity of each. An iterative optimization algorithm for PER minimization was then formulated, combining the Alternating Direction Method of the Multipliers algorithm (ADMM) with the bisection search method through a perturbation-based iterative approach. Simulation results confirm that the proposed algorithm achieves up to 16.42% improvement in computation time and up to 57.14% in convergence speed compared to the algorithm using the bisection method alone for both problems, and it gives the same performance as that of the exhaustive search method.

The rapid expansion of Internet of Things (IoT) systems and networks has led to increased challenges regarding security and system reliability. Anomaly detection has become a critical task for identifying system flaws, cyberattacks, and failures in IoT environments. This study proposes a hybrid deep learning (DL) approach combining Autoencoders (AE) and Long Short-Term Memory (LSTM) networks to detect anomalies in real-time within IoT networks. In this model, normal data trends were learned in an unsupervised manner using an AE, while temporal dependencies in time-series data were captured through the use of an LSTM network. Experiments conducted on publicly available IoT datasets, namely the Kaggle IoT Network Traffic Dataset and the Numenta Anomaly Benchmark (NAB) dataset, demonstrate that the proposed hybrid model outperforms conventional machine learning (ML) algorithms, such as Support Vector Machine (SVM) and Random Forest (RF), in terms of accuracy, precision, recall, and F1-score. The hybrid model achieved a recall of 96.2%, a precision of 95.8%, and an accuracy of 97.5%, with negligible false negatives and false positives. Furthermore, the model is capable of handling real-time data with a latency of just 75 milliseconds, making it suitable for large-scale IoT applications. The performance evaluation, which utilized a diverse set of anomaly scenarios, highlighted the robustness and scalability of the proposed model. The Kaggle IoT Network Traffic Dataset, consisting of approximately 630,000 records across six months and 115 features, along with the NAB dataset, which includes around 365,000 sensor readings and 55 features, provided comprehensive data for evaluating the model’s effectiveness in real-world conditions. These findings suggest that the hybrid DL framework offers a robust, scalable, and efficient solution for anomaly detection in IoT networks, contributing to enhanced system security and dependability.

The increasing desire for people to own personal cars, combined with their reluctance to use public transportation, has led to traffic jams and delays in emergency vehicle arrivals. Traffic lights in densely populated cities pose a significant challenge because they rely on fixed or variable timings, yet are not particularly effective. As a result, they can worsen congestion or cause traffic jams instead of alleviating it. For example, a city like Baghdad faces severe traffic congestion, requiring intervention from traffic police. Additionally, there is no specific system in place for emergency vehicle passage, and public transportation remains ineffective, as people are hesitant to use buses due to longer congestion times and the difficulty in navigating, which is exacerbated by their larger size compared to private small cars. Unlike previous YOLO-based systems, our system integrates emergency vehicle and public transport buses prioritization. It adjusts timing based on vehicle type, number, and estimated speed, showing a 31.11% improvement in flow efficiency and reducing queue delays by 21.64% compared to fixed-time signal systems. The improved algorithm can recognize all four vehicle classes (fire trucks, ambulances, public transport buses, and cars) with an accuracy of 85-99%, depending on vehicle density and complex lighting conditions.

Automated Guided Vehicles (AGVs) are increasingly used in industrial and logistics operations for material handling, offering benefits such as reduced human error, improved efficiency, and lower operational costs. This study presents the design and implementation of a real-time intelligent management system for Forklift AGVs based on deep learning techniques. The core of the system is an optimized version of YOLOv3, termed YOLOX, enhanced with Adaptive Spatial Feature Fusion (ASFF) and advanced data augmentation strategies. The ASFF module employs spatially adaptive weights (α, β, γ) to dynamically integrate multi-scale features across the Feature Pyramid Network, improving the detection of small, occluded, and overlapping objects. The system is trained on a combined Pascal VOC dataset using mix-up and label smoothing to enhance generalization and model robustness. It is deployed on embedded hardware, including Raspberry Pi 4, enabling real-time processing of visual data and sensor inputs under various lighting and environmental conditions. Evaluation results indicate that the model achieves a high mean Average Precision (mAP) of 94.17%, with real-time confidence scores reaching 98.1% in natural lighting and 94.3% in dim conditions. The system effectively detects and classifies a wide range of objects—including static, dynamic, small, distant, and partially occluded—in complex scenes. The proposed solution demonstrates robust real-time performance and adaptability, making it suitable for deployment in resource-constrained environments. It offers a scalable and intelligent framework for autonomous AGV navigation, contributing to safer and more efficient material transportation in real-world applications.

The objectives of this study are to (i) ascertain the major quantitative and qualitative factors influencing the determination of materiality thresholds in the private sector external audits performed by large and medium-sized Maltese audit firms, (ii) assess the effectiveness of ISA 320 in the determination of such materiality thresholds, as well as the impact of introducing more prescriptive guidelines within the Standard, and (iii) assess the current level of professional judgement and its effectiveness in determining materiality thresholds, as well as ascertain the typical challenges involved in exercising such judgement. A predominantly qualitative mixed-methods approach was adopted. Semi-structured interviews were carried out with twelve audit partners from large and medium-sized Maltese audit firms. The findings indicated that the major quantitative factors influencing overall materiality were 5–10% of profit before tax and 1–3% of total revenue. The major quantitative factor influencing performance materiality and the clearly trivial threshold was 75% and 5% of overall materiality, respectively. Additionally, the major qualitative factors influencing materiality thresholds were fraud and litigation risk, quality of client internal controls, auditor critical thinking skills, client complexity, the client’s sector and a change in auditor. Furthermore, the findings indicated that ISA 320 provided sufficient guidance for determining materiality thresholds. Moreover, the most cited benefit of introducing more prescriptive guidelines within the Standard was greater consistency among auditors, while the most cited drawback was the limitation on professional judgement. The findings also revealed that professional judgement was crucial and generally effective in determining materiality thresholds. However, auditors typically faced a few challenges when exercising such judgement, of which time pressure and the setting of appropriate thresholds are particularly significant.

The aviation industry is experiencing a rapid digital transformation driven by globalization, technological advancements, and evolving customer expectations. Among these technologies, AI-based chatbots have emerged as a powerful tool to streamline operations, enhance customer service, and support internal business functions. However, their adoption in air ticket reservation services is still in its early stages. This study aims to provide innovative insights into understanding the factors that determine the adoption of AI-based chatbots for air ticket reservations from the organization’s perspective. The study introduces two new constructs, diversity and sensibility, and conceptually integrates the “Technology Organization Environment” theory and the “Diffusion of Innovation” theory. Data from 154 respondents were modeled using PLS-SEM, suitable for models with many variables and small sample sizes. The finding reveals that the organization's technical capability is a key factor influencing the adoption. Diversity, referring to the chatbot’s multifunctionality, promotes broader acceptance. Moreover, the impact of sensibility on adoption intention posits that a user-friendly design of the chatbot that enhances the “look” and provides a sense of human touch significantly increases the adoption intention. The relative advantage of AI-based chatbots on adoption illustrates that among all other ticket reservation channels, they prove to be the most efficient and profitable. Also, the complexity and government involvement were identified as relevant predictors of adoption. This study provides valuable insights for organizations and stakeholders and offers both theoretical and practical implications. The study concludes with limitations and proposes directions for future research.