Key Performance Metrics Research Articles

Supply Chain and Logistics Management in the Automotive Industry

This examine investigates supply chain and logistics control practices inside the automobile enterprise, specializing in elements influencing deliver chain performance and organization profitability. The studies technique consists of stratified random sampling, device development, validation, and statistical analyses such as paired-samples t-take a look at, regression, ANCOVA, and Pearson correlational analyses. Descriptive records reveal key performance metrics, even as regression analyses show high-quality relationships between supply chain performance variables (inventory turnover, order achievement percentage, provider first-rate) and corporation profitability, controlling for corporation length. ANCOVA outcomes highlight mixed influences of deliver chain performance and organizational elements on profitability, while correlational analyses suggest robust positive correlations between stock turnover, order achievement percent, dealer high-quality, and organization profitability.

Identification of mycoplasma pneumonia in children based on fusion of multi-modal clinical free-text description and structured test data.

Mycoplasma pneumonia may lead to hospitalizations and pose life-threatening risks in children. The automated identification of mycoplasma pneumonia from electronic medical records holds significant potential for improving the efficiency of hospital resource allocation. In this study, we proposed a novel method for identifying mycoplasma pneumonia by integrating multi-modal features derived from both free-text descriptions and structured test data in electronic medical records. Our approach begins with the extraction of free-text and structured data from clinical records through a systematic preprocessing pipeline. Subsequently, we employ a pre-trained transformer language model to extract features from the free-text, while multiple additive regression trees are used to transform features from the structured data. An attention-based fusion mechanism is then applied to integrate these multi-modal features for effective classification. We validated our method using clinic records of 7157 patients, retrospectively collected for training and testing purposes. The experimental results demonstrate that our proposed multi-modal fusion approach achieves significant improvements over other methods across four key performance metrics.

Enhancing MANET Performance: A Novel Approach Through Nature-Inspired Scheduling Algorithms

In the rapidly evolving landscape of Mobile Ad Hoc Networks (MANETs), the quest for optimal performance through efficient scheduling remains paramount. This paper, titled "Enhancing MANET Performance: A Novel Approach Through Nature-Inspired Scheduling Algorithms," introduces an innovative methodology that leverages the intricate mechanisms of nature to address the complex challenges inherent in MANET scheduling. Drawing inspiration from the adaptive behaviors observed in natural systems, we have developed a suite of nature-inspired algorithms—encompassing the genetic algorithm, particle swarm optimization, and ant colony optimization—tailored specifically to enhance the scheduling efficiency within the dynamic and decentralized context of MANETs.
 Our research undertakes a comprehensive evaluation of these algorithms against traditional scheduling methods, showcasing a notable improvement in key performance metrics such as network throughput, latency, and energy consumption. The novel contribution of this study lies in the adaptation and optimization of these bio-inspired algorithms for the unique demands of MANET scheduling, culminating in the development of a proprietary analytical model that significantly outperforms existing strategies. Through a rigorous comparative analysis, our results illuminate the superiority of our approach, demonstrating not only enhanced network efficiency but also improved scalability and reliability under varying conditions.
 The implications of this research extend beyond the immediate enhancements to MANET performance, proposing a paradigm shift in how scheduling challenges are approached within ad hoc networks. By bridging the gap between biological principles and technological applications, this study paves the way for future innovations in network management, offering a blueprint for the development of more adaptive, robust, and efficient networking solutions.

Exploring Stress Detection in Tweets: A Comparative Business Analysis of Classification Algorithms

Abstract: In today's digitally-driven landscape, social media platforms such as Twitter, Facebook, and WordPress have emerged as critical conduits for public discourse, resulting in an overwhelming influx of unprocessed data, particularly on Twitter. Coping with the sheer volume of this data presents a significant challenge. To address this, sentiment analysis, a technique that categorizes sentiments into positive, negative, or neutral, offers a promising solution. This study delves into three main approaches for sentiment analysis: Machine learning-based methods, Sentiment lexicon-based approaches, and Hybrid methods. Its primary research objectives revolve around the identification of suitable algorithms and metrics for evaluating the performance of Machine Learning Classifiers. Additionally, the study aims to compare these metrics with respect to the dataset size, gauging their impact on the most appropriate sentiment analysis algorithm.The research methodology applied is experimental, entailing a rigorous assessment of algorithms using carefully selected metrics. The results of this investigation spotlight Naïve Bayes, Random Forest, XGBoost, and CNN-LSTM as the leading machine learning algorithms under consideration. These algorithms are assessed based on key performance metrics such as precision, accuracy, F1 score, and recall. Notably, the CNN-LSTM model emerges as the optimal choice for sentiment analysis of Twitter data within the specified dataset size, achieving a remarkable accuracy rate of 88%.In summary, this research successfully pinpoints the most suitable algorithm for sentiment analysis of Twitter data, especially in the context of dataset size. The CNN- LSTM model showcases its effectiveness, serving as a robust tool for sentiment analysis and delivering an impressive accuracy rate. This study significantly enhances our comprehension of public sentiment on Twitter, providing valuable insights into the ever-evolving realm of digital discourse and the analysis of vast unprocessed data

Improving wave energy conversion performance of a floating BBDB-OWC system by using dual chambers and a novel enhancement plate

In this study, a novel floating dual-chamber backward bent duct buoy oscillating water column (BBDB-OWC) wave energy converter (WEC) is introduced, featuring a horizontal plate at the bottom of the front chamber to act as an enhancement plate. A three-dimensional computational fluid dynamics (CFD) model is developed and validated by comparing its results with existing experimental measurements. The validated model is employed to investigate the hydrodynamic performance and power generation characteristics of the dual-chamber BBDB-OWC WEC under various conditions, including variations in the length of the horizontal plate (lp/lf) and different regular wave conditions. Key performance metrics, including peak to average ratio of power (PTARP), wave energy capture width ratio (ξtotal), and its wave period respond bandwidth (indicated by Pξtotal > 0.5 and Pξtotal > 0.7), are analyzed and compared with those of a traditional single-chamber BBDB-OWC WEC. The results reveal that, compared to the single-chamber WEC, the dual-chamber WEC with a specific horizontal plate length reduces the average PTARP from 2.88 to a minimum value of 1.82 for lp/lf = 0.5, improves the average ξtotal from 0.55 to a maximum value of 0.64 for lp/lf = 2.5, and increases Pξtotal > 0.5 and Pξtotal > 0.7 from 71 % and 14 % to maximum values of 86 % and 43 % for lp/lf = 2.5, respectively. An explanation for these observations is also provided in the context of structure motion and flow fields.

Goal-Guided Graph Attention Network with Interactive State Refinement for Multi-Agent Trajectory Prediction.

The accurate prediction of the future trajectories of traffic participants is crucial for enhancing the safety and decision-making capabilities of autonomous vehicles. Modeling social interactions among agents and revealing the inherent relationships is crucial for accurate trajectory prediction. In this context, we propose a goal-guided and interaction-aware state refinement graph attention network (SRGAT) for multi-agent trajectory prediction. This model effectively integrates high-precision map data and dynamic traffic states and captures long-term temporal dependencies through the Transformer network. Based on these dependencies, it generates multiple potential goals and Points of Interest (POIs). Through its dual-branch, multimodal prediction approach, the model not only proposes various plausible future trajectories associated with these POIs, but also rigorously assesses the confidence levels of each trajectory. This goal-oriented strategy enables SRGAT to accurately predict the future movement trajectories of other vehicles in complex traffic scenarios. Tested on the Argoverse and nuScenes datasets, SRGAT surpasses existing algorithms in key performance metrics by adeptly integrating past trajectories and current context. This goal-guided approach not only enhances long-term prediction accuracy, but also ensures its reliability, demonstrating a significant advancement in trajectory forecasting.

Advancements in Steel Surface Defect Detection: An Enhanced YOLOv5 Algorithm with EfficientNet Integration

Steel surface defect detection is of utmost importance for ensuring product quality, cost reduction, enhanced safety, and heightened customer satisfaction. To address the limitations of traditional steel surface defect detection algorithms, which often yielded singular detection results and suffered from high miss detection rates, we proposed an enhanced Yolov5 steel surface defect detection algorithm. In this approach, this paper employed the EfficientNet network as a replacement for the Yolov5 backbone network. Subsequently, we trained and tested this modified network on a steel surface defect dataset to mitigate the challenges associated with high miss detection rates and underperforming evaluation metrics. Our experimental findings underscored the superiority of the improved algorithm, particularly when compared to Yolov5. This enhanced algorithm exhibited substantial improvements across several key performance metrics, including Precision, Recall, mAP@0.5, parameter count, and pt file size. Noteworthy achievements included a 6.39% increase in Precision for Yolov5-EfficientNetB4, a remarkable 7.75% improvement in Recall for Yolov5-EfficientNetB0, and a 5.57% boost in mAP@0.5 for Yolov5-EfficientNetB6. Additionally, the pt file size for Yolov5-EfficientNetB0 saw a substantial 39.65% reduction, although it was important to note that the inference time for the improved algorithm increased. Among the models, Yolov5-EfficientNetB6 struck the best balance in terms of performance.

Effect of hydrocyclone design in microplastics-water separation by using computational fluid dynamics simulations

Nowadays microplastics have become a significant environmental concern, impacting both freshwater and marine ecosystems. In response to this issue, extensive research has been conducted to explore methods for separating microplastics from water. One area of investigation involves the use of computational fluid dynamics (CFD) models to study hydrocyclones and their intricate flow patterns. In this study, CFD was systematically used to examine various hydrocyclone designs with different geometrical parameters, including the ratios of cylindrical diameter to underflow diameter and overflow diameter, the cone to cylindrical height ratio, and the inlet angle. The efficiency of these hydrocyclones has been evaluated based on key performance metrics, including microplastics recovery percentage, water split percentage, and pressure drop. The results of this study have revealed noteworthy findings. Moreover, statistical analysis, specifically the analysis of variance (ANOVA), was employed to determine the significance of various geometric parameters on microplastics separation within the hydrocyclone. As a result of this comprehensive investigation, an optimized hydrocyclone design was proposed. This optimized hydrocyclone featured an underflow diameter to diameter of the cylindrical ratio of 0.264, an overflow diameter to diameter of the cylindrical ratio of 0.3, a cone to cylindrical height ratio of 13.22:70.78, and a tangential inlet. This configuration achieved a remarkable 76% microplastics recovery, a 52% water split, and a pressure drop of 82,340 Pa.

Performance Analysis of G.711 and G.729 Codec Schemes under Various Queuing Techniques in Voice over Internet Protocol Transmissions

Advancements in internet technology have enabled the integration of different traffic types i.e. data, video, and voice into a single network. This technology offers many benefits but also presents some challenges. Real-time traffic services such as VoIP require a certain Quality of Service (QoS) which cannot be guaranteed on the Internet therefore, key performance metrics become all the more important. The choice of codecs and queuing techniques becomes crucial for ensuring optimal performance, especially in networks with diverse traffic types. This research therefore compared the effects of the combinations of these tools (i.e. queuing techniques and codec schemes) on the quality of VoIP. A simulation approach using the OPNET Modeler 14.5 tool has been used to simulate a network supporting three different types of traffic namely: FTP traffic, Video conferencing traffic, and VoIP traffic. While maintaining the same topology and traffic of the network, different types of codec schemes and queuing techniques have been tested through the measurement of parameters such as delay and throughput. The custom Queuing technique showed the best performance overall while FIFO suffered the highest delay. The graphs were observed to follow the same pattern regardless of the codec scheme used however, G729 performed the better of the two as it received higher amounts of voice traffic and slightly lower delays compared to G711.

Standardization of key performance indicators and metrics for investigational drug services: Consensus recommendations among IDS specialists.

There are currently no consensus guidelines on establishing metrics for investigational drug services (IDS). Because of the complexity of research protocols, it remains difficult for sites to track pharmacy productivity and create a baseline for IDS growth within the institution, as well as to perform benchmarking with peer institutions. The goal of this study was to help establish practical guidance for IDS metrics and site utility as applicable. This was a survey-based project conducted by the metrics subgroup of the Hematology/Oncology Pharmacy Association (HOPA) IDS special interest group (SIG), which was formed specifically for this analysis. Three surveys developed by the metrics subgroup were sent to members of the IDS HOPA SIG to gather metrics. The first survey included questions about what metrics IDS sites currently collect. The identified metrics were then condensed into categories. Through a consensus-based approach, standardized definitions were established and applied to future surveys. The 2 subsequent surveys sent to HOPA SIG members helped create a list of top recommended metrics that are recommended for every IDS site to track. A total of 3 surveys were sent to 75 recipients, with the response rate ranging from 24% to 38%. From these surveys and consensus with the metrics subgroup, 5 top recommended metrics were identified: (1) active protocols; (2) dispenses; (3) new clinical trials initiated; (4) patients treated; and (5) clinical interventions. These recommended metrics should serve as guidance and allow for standardization to help ensure adequate resources are available for IDS pharmacy staff. These recommendations should serve as a basis for standardization and benchmarking with peer institutions.

Navigating the future: A comprehensive survey of localization systems in autonomous vehicles

<p>This survey paper provides an in-depth analysis of localization systems for autonomous vehicles (AVs), a cornerstone technology crucial for the safe and efficient operation of AVs. The paper encompasses a comprehensive examination of various localization technologies, their comparative analysis, the challenges they face, and the emerging trends shaping their future. We begin by exploring the principal technologies employed in AV localization: GPS, LiDAR, radar, cameras, and ultrasonic sensors. Each technology is scrutinized to understand its strengths, weaknesses, and applicability in different environmental contexts. GPS offers broad geographical positioning but struggles with precision in dense urban areas. LiDAR provides high-resolution mapping but is hindered by adverse weather conditions. Radar ensures reliability in poor visibility but lacks the finer details provided by optical systems. Cameras offer rich visual data but are dependent on lighting conditions, and ultrasonic sensors, while effective for close-range detection, are limited to low-speed applications. The paper then presents a comparative analysis of these technologies against key performance metrics such as accuracy, reliability, latency, scalability, and cost-effectiveness. This analysis is critical in understanding the suitability of each technology for various driving scenarios, from congested urban streets to open highways and in diverse weather conditions. Challenges in AV localization are multifaceted, encompassing technological, environmental, and system integration issues. Technological challenges include sensor limitations and computational constraints, while environmental factors like weather and urban infrastructure significantly impact localization accuracy. System integration poses another significant challenge, necessitating seamless interaction between localization systems and other vehicle control systems for real-time decision-making. Emerging trends and potential solutions to these challenges are discussed, highlighting advancements in sensor technology, AI, machine learning, and 5G communications. These developments promise to overcome existing limitations and enhance the accuracy and reliability of AV localization. The integration of localization systems with smart city infrastructures and the implementation of collaborative technologies like V2X communication are speculated to further augment AV capabilities. In conclusion, the paper emphasizes that the future of AV localization is intrinsically linked to the continuous evolution of technologies and their integration. Addressing current challenges and harnessing emerging trends are pivotal for the advancement of AVs, steering us toward a future of autonomous transportation characterized by increased safety, efficiency, and reliability.<strong></strong></p>

Navigating the future: A comprehensive survey of localization systems in autonomous vehicles

<p>This survey paper provides an in-depth analysis of localization systems for autonomous vehicles (AVs), a cornerstone technology crucial for the safe and efficient operation of AVs. The paper encompasses a comprehensive examination of various localization technologies, their comparative analysis, the challenges they face, and the emerging trends shaping their future. We begin by exploring the principal technologies employed in AV localization: GPS, LiDAR, radar, cameras, and ultrasonic sensors. Each technology is scrutinized to understand its strengths, weaknesses, and applicability in different environmental contexts. GPS offers broad geographical positioning but struggles with precision in dense urban areas. LiDAR provides high-resolution mapping but is hindered by adverse weather conditions. Radar ensures reliability in poor visibility but lacks the finer details provided by optical systems. Cameras offer rich visual data but are dependent on lighting conditions, and ultrasonic sensors, while effective for close-range detection, are limited to low-speed applications. The paper then presents a comparative analysis of these technologies against key performance metrics such as accuracy, reliability, latency, scalability, and cost-effectiveness. This analysis is critical in understanding the suitability of each technology for various driving scenarios, from congested urban streets to open highways and in diverse weather conditions. Challenges in AV localization are multifaceted, encompassing technological, environmental, and system integration issues. Technological challenges include sensor limitations and computational constraints, while environmental factors like weather and urban infrastructure significantly impact localization accuracy. System integration poses another significant challenge, necessitating seamless interaction between localization systems and other vehicle control systems for real-time decision-making. Emerging trends and potential solutions to these challenges are discussed, highlighting advancements in sensor technology, AI, machine learning, and 5G communications. These developments promise to overcome existing limitations and enhance the accuracy and reliability of AV localization. The integration of localization systems with smart city infrastructures and the implementation of collaborative technologies like V2X communication are speculated to further augment AV capabilities. In conclusion, the paper emphasizes that the future of AV localization is intrinsically linked to the continuous evolution of technologies and their integration. Addressing current challenges and harnessing emerging trends are pivotal for the advancement of AVs, steering us toward a future of autonomous transportation characterized by increased safety, efficiency, and reliability.<strong></strong></p>

Enhanced collaborative networking protocol based on clustering mechanism for UV networks

Developing a highly efficient multi-node media access control protocol tailored for ultraviolet (UV) networks poses a significant challenge. While our team's UV random-access collaborative networking protocol, utilizing time-division multiple access (UVCN-TDMA), has been instrumental, its scalability is hindered by the number of network nodes. To address this limitation and facilitate large-scale UV node networking, this study advances the UVCN protocol by introducing an enhanced collaborative networking protocol known as the enhanced collaborative clustering mechanism (eCOCM). This study examined the impact of network topology, various data services, and the number of cluster nodes on network performance within the proposed eCOCM framework. Additionally, a comparative analysis between the eCOCM protocol and conventional clustering systems was conducted. The findings demonstrate notable enhancements across key performance metrics including throughput, packet loss rate, delay, and channel utilization. Finally, functional experiments were conducted under two distinct network scenarios to validate the efficacy of the proposed protocol. This study addresses the immediate challenges in UV multi-node networking and offers pragmatic insights to steer its development forward.

Performance of geographically restricted flooding for emergency alert applications

ABSTRACT For various emergency alert applications like a disaster, accident, or hazard alert, geographically restricted flooding can prove to be extremely vital, especially considering the absence of any fixed infrastructure and the alert having spatio-temporal boundaries. Among various geographically restricted flooding schemes, in this work, a scheme called floating content is considered. Floating content uses geographically restricted flooding to make a piece of information available within a certain geographic area. In this work, an Android-based emergency alert application is deployed and tested in two different environments. One environment spans over a small geographic area (an office), while the other environment is a university campus. The application is used to log the mobility patterns of users for both the considered environments, and these mobility patterns are thoroughly analyzed. Then the performance of the considered emergency alert application in terms of key performance metrics is evaluated for both of the considered settings by considering single and multiple seeders (alert generators). Moreover, for the prediction of performance, two different analytical models are also evaluated, and the results of these models are compared with the ones obtained from real-world experiments, showing the performance limits of geographically restricted flooding.

Climate Change and the Future of Ski Tourism in Canada’s Western Mountains

Winter, snow, and mountains, epitomized by the world-renowned Rocky Mountain range, are an integral part of Canada’s sport-culture identity and international tourism brand, yet the climate change risk posed to this important ski tourism region remains uncertain. This study used the ski operations model SkiSim 2.0 to analyze the climate risk for the region’s ski industry (26 ski areas in the province of Alberta and 40 in British Columbia) with advanced snowmaking, including changes in key performance metrics of ski season length, snowmaking requirements, holiday operations, and lift and terrain capacity. If Paris Climate Agreement targets are met, average seasons across all ski areas decline 14–18% by mid-century, while required snowmaking increases 108–161%. Regional average operational terrain declined only 4–9% in mid-century, as the largest ski areas were generally more climate resilient. More pronounced impacts are projected under late-century, high-emission scenarios and in low latitudes and coastal British Columbia regions. When compared with continental and international ski tourism markets, Western Canada has relatively lower climate change impacts, which could improve its competitiveness. The results inform further research on demand-side as well as the winter sport-tourism industry and destination-scale climate change adaptation and mitigation strategies.

Reduction of NIFTI files storage and compression to facilitate telemedicine services based on quantization hiding of downsampling approach

Magnetic resonance imaging is a medical imaging technique to create comprehensive images of the tissues and organs in the body. This study presents an advanced approach for storing and compressing neuroimaging informatics technology initiative files, a standard format in magnetic resonance imaging. It is designed to enhance telemedicine services by facilitating efficient and high-quality communication between healthcare practitioners and patients. The proposed downsampling approach begins by opening the neuroimaging informatics technology initiative file as volumetric data and then planning it into several slice images. Then, the quantization hiding technique will be applied to each of the two consecutive slice images to generate the stego slice with the same size. This involves the following major steps: normalization, microblock generation, and discrete cosine transformation. Finally, it assembles the resultant stego slice images to produce the final neuroimaging informatics technology initiative file as volumetric data. The upsampling process, designed to be completely blind, reverses the downsampling steps to reconstruct the subsequent image slice accurately. The efficacy of the proposed method was evaluated using a magnetic resonance imaging dataset, focusing on peak signal-to-noise ratio, signal-to-noise ratio, structural similarity index, and Entropy as key performance metrics. The results demonstrate that the proposed approach not only significantly reduces file sizes but also maintains high image quality.

Enhancing user experience: Unveiling the impact of website speed optimisation on user engagement

Optimising for a good user experience means not only making sure that the website is intuitive to use, but also that it responds quickly and loads fast. This paper discusses a study1 conducted by The Boutique Agency in 2022, in collaboration with roastmarket, a fast-growing e-commerce company specialising in coffee products. The case study examines the impact of website speed optimisation on user interaction. Through a meticulous three-month optimisation process, targeting key performance metrics for website speed, roastmarket achieved positive results in Google Core Web Vitals and a respective uplift in user engagement metrics such as page visit duration. The study demonstrates the value of prioritising the Core Web Vitals factors for enhancing overall website performance and user satisfaction.

Night Guardian: Empowering Women’s Safety with Hand Sign – Based Communication and AI

Abstract: In an era where technology continually shapes the way we interact with the world, there arises a pressing need for innovative solutions that enhance women's safety. Ensuring women's safety, especially at night, is crucial due to the unique challenges and risks they may face during nighttime hours. Our project aims to address critical issues related to women's safety, such as harassment, assault, and emergencies, particularly in public spaces. We leverage advanced technologies like MediaPipe and machine learning algorithms to create an effective and responsive safety solution. The project employs various machine learning algorithms, including random forest, support vector machine, Hybrid model and k-nearest neighbor, to train the model. Rigorous testing is conducted to evaluate and select the optimal model, utilizing key performance metrics such as F1 score, precision, and recall.

Predicting the Need for Cardiovascular Surgery: A Comparative Study of Machine Learning Models

This research examines the efficacy of ensemble Machine Learning (ML) models, mainly focusing on Deep Neural Networks (DNNs), in predicting the need for cardiovascular surgery, a critical aspect of clinical decision-making. It addresses key challenges such as class imbalance, which is pivotal in healthcare settings. The research involved a comprehensive comparison and evaluation of the performance of previously published ML methods against a new Deep Learning (DL) model. This comparison utilized a dataset encompassing 50,000 patient records from a large hospital between 2015-2022. The study proposes enhancing the efficacy of these models through feature selection and hyperparameter optimization, employing techniques like grid search. A novel aspect of this research was the comparison of a newly developed DNN model with existing ensemble models based on similar cardiovascular datasets. The results indicated the DNN model's superior predictive accuracy, demonstrating an Area Under the Curve (AUC) of 74%, alongside notable precision (68%) and recall (72%) for the minority class, which indicates patients requiring surgery. The model further achieved a 70% F1-Score and a balanced accuracy rate of 72%, significantly outperforming the existing ensemble models in every key performance metric. The study underscores the transformative potential of DNNs in predictive modeling for cardiovascular care and highlights the importance of integrating advanced ML techniques into clinical workflows. Future research should delve into the practical application and integration of these models.

A U-Net Architecture for Inpainting Lightstage Normal Maps

In this paper, we investigate the inpainting of normal maps that were captured from a lightstage. Occlusion of parts of the face during performance capture can be caused by the movement of, e.g., arms, hair, or props. Inpainting is the process of interpolating missing areas of an image with plausible data. We build on previous works about general image inpainting that use generative adversarial networks (GANs). We extend our previous work on normal map inpainting to use a U-Net structured generator network. Our method takes into account the nature of the normal map data and so requires modification of the loss function. We use a cosine loss rather than the more common mean squared error loss when training the generator. Due to the small amount of training data available, even when using synthetic datasets, we require significant augmentation, which also needs to take account of the particular nature of the input data. Image flipping and inplane rotations need to properly flip and rotate the normal vectors. During training, we monitor key performance metrics including the average loss, structural similarity index measure (SSIM), and peak signal-to-noise ratio (PSNR) of the generator, alongside the average loss and accuracy of the discriminator. Our analysis reveals that the proposed model generates high-quality, realistic inpainted normal maps, demonstrating the potential for application to performance capture. The results of this investigation provide a baseline on which future researchers can build with more advanced networks and comparison with inpainting of the source images used to generate the normal maps.