This paper introduces a novel and robust approach known as the Slime Mould Algorithm (SMA) for the optimal placement and sizing of capacitors in an IEEE distribution network. Initially, candidate buses for capacitor installation are identified using various indices, including Loss Sensitivity Factors (LSF), Voltage Stability Index (VSI), and Power Loss Index (PLI). These indices aid in determining the most suitable locations for capacitor installation. Subsequently, the SMA is applied to optimize the size and placement of capacitors at these selected buses. The primary objective function focuses on minimizing the total net cost and maximizing annual savings. The proposed method is applied to an IEEE distribution system and its results are compared with other conventional techniques to highlight its effectiveness. The findings demonstrate significant improvements in reducing power losses, lowering costs, and enhancing the voltage profile, thereby showcasing the potential of the SMA for improving the performance of radial distribution networks.
High-technology augmentative and alternative communication (AAC) devices are essential tools for individuals with complex communication needs. Automated data logging in these devices enables researchers and clinicians to analyze user performance. However, existing systems cannot distinguish between users when multiple individuals access the same device, compromising the validity of data logs and complicating performance evaluation. This paper proposes a deep neural network-based visual analysis approach to address this limitation. By processing video recordings of practice sessions, the method detects and identifies different AAC users, ensuring that data logs accurately reflect individual contributions. This solution has the potential to significantly improve the validity of performance data, streamline analysis, and ultimately enhance AAC outcome measures. Through a combination of advanced video processing and neural network techniques, this approach represents a major step forward in AAC research and clinical practice. It addresses a critical gap in current data logging systems and paves the way for more accurate, user-specific performance evaluation.
This paper examines the methodologies for assessing AI vendor capabilities in the context of Roy Hill, a prominent iron ore mining company in Western Australia. Through the use of Monte Carlo simulations and Large Language Models (LLMs), including innovative techniques like the Multi-Persona LLM (MP-LLM), we evaluate potential AI vendors to identify those that align with Roy Hill's strategic and operational goals. A robust vendor evaluation framework was developed, integrating survey data with independent assessments of LLMs and their products. The MP-LLM framework was specifically tested for its problem-solving ability and demonstrated enhanced performance when combined with tailored prompt engineering and curated personas. To mitigate challenges such as information asymmetry and confirmation bias, vendor feedback was incorporated, and evaluation metrics were refined using both LLMs and Monte Carlo simulations. The study contributes to AI vendor selection methodologies in the mining sector, emphasizing the importance of adaptive strategies in a rapidly changing technological landscape. Future work will explore advanced techniques such as knowledge graphs and expanded persona libraries to improve AI capability assessments and support operational excellence across industries.
This paper presents the development of a predictive model to correlate the mean heart dose (MHD) in left breast radiotherapy with treatment geometry, specifically aiming to minimize cardiac complications due to heart proximity. Given the importance of constraining MHD, we propose a methodology to quantify geometric arrangements using the Expansion Intersection Histogram (EIH) method. This approach involves progressive isotropic expansions of the target volume and mapping the overlap with the heart. From the resulting EIH graph, two key parameters—separation (S) and wrapping (W)—are derived, alongside the omolateral breast volume (OBV), which serve as inputs for a multivariate linear regression model. The study includes data from 19 breast cancer patients who received a treatment course of 15 fractions, with a breast dose of 40.5 Gy and a 48 Gy simultaneous integrated boost (SIB) planned via volumetric modulated arc therapy (VMAT). Descriptive statistics for the model parameters showed mean values of 1.21±0.41 cm (S), 8.25±3.33 %/cm (W), and 708.13±388.64 cc (OBV), while the MHD averaged 3.25±0.78 Gy. The regression model demonstrated a high R² value of 0.9, with significant coefficients for S, W, and OBV. The results suggest that the developed model provides a reliable method for predicting MHD based on treatment geometry, offering potential for better heart dose management in radiotherapy.
This study examines the temporal dynamics of vehicle circulation within an interconnected network of arterial roads using continuous Markov chains. Traditional approaches to vehicle flow modeling rely on discrete Markov chains, where each transition represents the passage of vehicles between intersections at fixed time steps. In this paper, we introduce a modification by modeling the process as a continuous system, enhancing the temporal resolution and accuracy of traffic predictions. By representing the network as a digraph and associating it with an ad hoc steady-state matrix, we develop a continuous evolution matrix that allows for the seamless tracking of vehicle populations over time. The model begins with an initial population of vehicles within the network, represented as a vector, and applies the continuous evolution matrix iteratively to predict traffic flow dynamics. This approach improves upon traditional discrete models by enabling finer temporal predictions and providing insights into the steady-state conditions of the system. The results demonstrate the potential of continuous Markov chains to offer more accurate and efficient traffic flow predictions, supporting better traffic management strategies and optimizations for large-scale network arteries.