Manual Input Research Articles

Circinus: An AI-Based Technical Description Plotting

Abstract. The digitization of maps poses a significant challenge for GIS operators and engineers, particularly in encoding bearings and distances into GIS software. This study, titled “Circinus: An AI-Based Technical Description Plotting,” represents a substantial advancement in the digitization process of land records. Leveraging artificial intelligence, this application enhances the efficiency of digitizing land survey maps, potentially surpassing the laborious manual input required for geographic information. By expediting the encoding process of scanned maps, the application enhances the accessibility and availability of digital land records. This advancement holds considerable benefits for effective land asset planning and improved financial operations, particularly benefiting prospective homebuyers and landowners. The tool offers streamlined encoding through its semi-automated features, facilitating ease of use. Additionally, its optimization features have the potential to significantly enhance the productivity of engineers and GIS operators involved in encoding scanned land survey maps.

The Transformative Impact of Artificial Intelligence and Machine Learning on Marketing Operations

This comprehensive article explores the transformative impact of Artificial Intelligence (AI) and Machine Learning (ML) on modern marketing operations. The research delves into key areas where AI and ML are revolutionizing marketing strategies, including hyper-personalization, predictive analytics, and conversational AI. Through an analysis of recent developments and case studies, the article demonstrates how AI-driven personalization significantly enhances customer engagement and relevance, with some implementations showing up to 25% increase in revenue and 15% improvement in customer retention rates. The article also examines the role of predictive analytics in shifting marketing strategies from reactive to proactive approaches, enabling more accurate forecasting of customer behavior, campaign performance, and market trends. Furthermore, the evolution of chatbots and conversational AI is explored, highlighting their capacity to automate lead qualification, scale customer engagement, and gather real-time insights without increasing manual input. The integration of AI in marketing operations is shown to improve campaign management efficiency, enhance personalization capabilities, and facilitate future-focused campaign development. However, the research also addresses the challenges and ethical considerations associated with AI integration in marketing, including data privacy concerns, skill gaps, and the need to balance automation with human creativity. This article provides a comprehensive overview of how AI and ML are reshaping the marketing landscape, offering valuable insights for marketers, researchers, and business leaders navigating this technological revolution.

Advancing the thermodynamic modeling of multicomponent phases in hydrogen-para-equilibrium

We present an advanced approach for the thermodynamic modeling of metal hydrides within the Calculation of Phase Diagrams (CALPHAD) framework. As the traditional CALPHAD method requires significant and time-consuming manual input, often introducing biases into the assessment process, we present a novel solution to automate this. The core of our approach is the development of an open-source, Python-based computational tool designed to calculate para-equilibrium states in hydrogen-multicomponent phases. This tool facilitates a semi-automatic pathway to enhance the CALPHAD evaluation procedure, significantly reducing manual input. We validated our approach by rapidly assessing the (Ce,La)Ni5–H system, a representative material system with significant implications for metal hydride-based hydrogen applications. Our method confirms existing data and reveals new insights into this system’s sorption properties and phase behavior. Using our Python-based tool to optimize parameter sets and calculate Pressure-Composition-Isotherms (PCI), we demonstrate the feasibility of predicting temperature-dependent plateau pressures and hydrogen capacities of multicomponent metal hydrides. This work holds significant potential for future applications in designing hydrogen storage materials, predicting their properties, and extending the methodology to other metal hydride systems.

Computer-aided design and fabrication of nasal prostheses: a semi-automated algorithm using statistical shape modeling.

This research aimed to develop an innovative method for designing and fabricating nasal prostheses that reduces anaplastologist expertise dependency while maintaining quality and appearance, allowing patients to regain their normal facial appearance. The method involved statistical shape modeling using a morphable face model and 3D data acquired through optical scanning or CT. An automated design process generated patient-specific fits and appearances using regular prosthesis materials and 3D printing of molds. Manual input was required for specific case-related details. The developed method met all predefined requirements, replacing analog impression-making and offering compatibility with various data acquisition methods. Prostheses created through this method exhibited equivalent aesthetics to conventionally fabricated ones while reducing the skill dependency typically associated with prosthetic design and fabrication. This method provides a promising approach for both temporary and definitive nasal prostheses, with the potential for remote prosthesis fabrication in areas lacking anaplastology care. While new skills are required for data acquisition and algorithm control, these technologies are increasingly accessible. Further clinical studies will help validate its effectiveness, and ongoing technological advancements may lead to even more advanced and skill-independent prosthesis fabrication methods in the future.

Machine learning for predictive AAC: Improving speech and gesture-based communication systems

Augmentative and alternative communication (AAC) systems play a crucial role in supporting individuals with severe communication disabilities by providing accessible means of expression and engagement. However, many conventional AAC devices rely on manual input or basic predictive functions, which can limit communication efficiency and responsiveness. The application of machine learning (ML) to AAC offers new opportunities to enhance these systems, enabling them to provide faster, more accurate, and contextually relevant communication assistance. Advances in ML, particularly in predictive text, speech recognition, and gesture interpretation, allow AAC systems to adapt more intuitively to user needs, predicting intent based on usage patterns and multimodal data, such as voice and gestures. Current research highlights the potential of ML to address key gaps in AAC technology by creating more responsive, personalized systems that align with individual user behaviours. This study proposes a novel ML framework designed to integrate these capabilities, promising improvements in communication speed, user autonomy, and accuracy. By addressing the challenges and limitations of traditional AAC devices, this research aims to advance accessible communication solutions that empower users and improve quality of life.

Otomatisasi Perhitungan OEE pada Mesin Filling ILAPAK 50g Menggunakan PLC dan HMI

This study addressed the limitations in calculating Overall Equipment Effectiveness (OEE) manually, which frequently led to inaccuracies and inefficiencies in industrial processes. The purpose of this research was to design an automated OEE calculation system for the ILAPAK 50g filling machine to improve data accuracy and reduce dependency on manual input. A Design Science Research (DSR) methodology was employed, involving stages of system analysis, design, implementation, and evaluation. The system utilized key components, including an Omron CP2E PLC, proximity sensors, relays, and a Human-Machine Interface (HMI) for real-time data acquisition. The findings indicated that the automated system significantly improved data accuracy, achieving reliable, continuous OEE calculations across different machine shifts. The system successfully replaced manual logbook methods, reducing human estimation errors, and displayed OEE data locally on the HMI, making it accessible for operational decisions. Furthermore, the implemented automation reduced overall downtime, enhanced machine availability, and minimized errors associated with manual record-keeping. This research has practical implications for industries aiming to optimize production efficiency. The automated OEE system demonstrated potential for scalability to other machines in manufacturing settings, highlighting its adaptability and utility in modern industrial environments. Future research could explore integration with cloud-based databases to enhance data storage and accessibility, providing a foundation for advanced predictive maintenance and performance monitoring across multiple machines.

RSPS-SAM: A Remote Sensing Image Panoptic Segmentation Method Based on SAM

Satellite remote sensing images contain complex and diverse ground object information and the images exhibit spatial multi-scale characteristics, making the panoptic segmentation of satellite remote sensing images a highly challenging task. Due to the lack of large-scale annotated datasets for panoramic segmentation, existing methods still suffer from weak model generalization capabilities. To mitigate this issue, this paper leverages the advantages of the Segment Anything Model (SAM), which can segment any object in remote sensing images without requiring any annotations and proposes a high-resolution remote sensing image panoptic segmentation method called Remote Sensing Panoptic Segmentation SAM (RSPS-SAM). Firstly, to address the problem of global information loss caused by cropping large remote sensing images for training, a Batch Attention Pyramid was designed to extract multi-scale features from remote sensing images and capture long-range contextual information between cropped patches, thereby enhancing the semantic understanding of remote sensing images. Secondly, we constructed a Mask Decoder to address the limitation of SAM requiring manual input prompts and its inability to output category information. This decoder utilized mask-based attention for mask segmentation, enabling automatic prompt generation and category prediction of segmented objects. Finally, the effectiveness of the proposed method was validated on the high-resolution remote sensing image airport scene dataset RSAPS-ASD. The results demonstrate that the proposed method achieves segmentation and recognition of foreground instances and background regions in high-resolution remote sensing images without the need for prompt input, while providing smooth segmentation boundaries with a panoptic segmentation quality (PQ) of 57.2, outperforming current mainstream methods.

Deep learning-based segmentation of abdominal aortic aneurysms and intraluminal thrombus in 3D ultrasound images.

Ultrasound (US)-based patient-specific rupture risk analysis of abdominal aortic aneurysms (AAAs) has shown promising results. Input for these models is the patient-specific geometry of the AAA. However, segmentation of the intraluminal thrombus (ILT) remains challenging in US images due to the low ILT-blood contrast. This study aims to improve AAA and ILT segmentation in time-resolved three-dimensional (3D + t) US images using a deep learning approach. In this study a "no new net" (nnU-Net) model was trained on 3D + t US data using either US-based or (co-registered) computed tomography (CT)-based annotations. The optimal training strategy for this low-contrast data was determined for a limited dataset. The merit of augmentation was investigated, as well as the inclusion of low-contrast areas. Segmentation results were validated with CT-based geometries as the ground truth. The model trained on CT-based masks showed the best performance in terms of DICE index, Hausdorff distance, and diameter differences, covering a larger part of the AAA. With a higher accuracy and less manual input the model outperforms conventional methods, with a mean Hausdorff distance of 4.4mm for the vessel and 7.8mm for the lumen. However, visibility of the lumen-ILT interface remains the limiting factor, necessitating improvements in image acquisition to ensure broader patient inclusion and enable rupture risk assessment of AAAs in the future.

AI-based open-source software for cephalometric analysis from limited FOV radiographs

BackgroundArtificial Intelligence (AI) in dental diagnostics is evolving, offering innovative approaches for conducting cephalometric analysis with less manual input and overcoming the limitations of traditional imaging methods. To enhance the diagnostic processes in dentistry, an open-source software that utilises AI to improve the extraction of cephalometric values from limited field of view (FOV) images was created. Material and MethodsReduced FOV images lack several vital cephalometric landmarks, prompting the creation of predictive models to estimate missing values. The GridSearchCV algorithm and other algorithms were used to construct predictive models using software and to select the best models. The software was validated by comparing the predicted values with the actual measurements and calculating the mean squared error using Excel. Further validation involved a randomly selected cohort of 25 untreated orthodontic cases. ResultsEvaluation of the software showed that it was effective in accurately predicting key cephalometric measurements, suggesting that it could be a reliable tool for clinical use. However, some variations were noted in its predictive accuracy across different measurements, indicating areas that could benefit from further development. The software could align closely with the actual cephalometric measurements through detailed statistical analysis. ConclusionsThe integration of AI into cephalometric analysis with the software could represent progress, potentially leading to more efficient dental diagnostics and a reduction in the need for additional X-rays. This study aimed to advance the integration and refinement of AI in healthcare, focusing on minimising bias and understanding its impact on clinical decisions. In future studies, the application of AI in dental practice should be expanded to address these challenges. Clinical Significance StatementThis software integrates AI into clinical practice to enhance the diagnostic and therapeutic phases for patient benefit. It enables precise and comprehensive cephalometric analyses using data previously considered insufficient, thereby reducing the need for X-rays and improving patient care.

Segmenting RFI Using Meta’s Segment Anything Model

Radio Frequency Interference (RFI), radio signals from electronics, permeates through astronomical observations using radio telescopes. The interference results in lower sensitivity and higher noise when present. Existing methods, such as TFCrop and RFlag, flag RFI to prevent the contamination of observations. However, these approaches are partially automatic and require manual input to flag RFI. We explore artificial intelligence methods using Meta’s Segment Anything Model (SAM) and its parameter space in segmenting RFI. We have developed an open-source pipeline called SamRFI, which segments and flags RFI from measurement sets. We trained SAM’s masking weights from Hugging Face to fine-tune the model using Very Large Array data and synthetic waterfall plots injected with RFI. We define a metric, calcquality, to measure the performance of our models based on sensitivity and overflagging. Retrained SAM models identify RFI structure and allow for further exploration in RFI segmentation.

Automatic Planning Method of Construction Schedule under Multi-Dimensional Spatial Resource Constraints

To enhance the application of building information modeling (BIM) in schedule management for engineering projects, improve spatial planning capabilities, and minimize subjective factors in schedule preparation, this paper presents a framework and method for automatic construction schedule planning based on BIM and data-driven approaches under multi-dimensional spatial resource constraints. The method includes data acquisition, construction process reasoning, time parameter calculation, and schedule generation and scheduling. Initially, the construction data from the BIM model and manual input are imported into the reasoning system to establish the logical relationships of the construction process. Construction time parameters and spatial resource requirements are then automatically calculated using MySQL. Subsequently, the spatial layout and resource allocation data exported from the BIM model are compared to assess whether the space meets the project requirements. Finally, a construction schedule that satisfies the space constraints is generated. The method was validated through a case study, demonstrating its effectiveness in automatic schedule planning under human-computer interaction. This study introduces an innovative approach that considers spatial conflicts in the automatic scheduling process, improving planning efficiency and reducing the risk of spatial conflicts on construction sites.

Robust calibration of surround-view camera systems with Planar-Eccentric Constraint: A novel Apriltag approach

This research tackles calibrating surround view camera systems for automated driving, where traditional methods require extensive manual measurements and precise conditions. We introduce a novel automatic calibration method that ensures portability and accuracy using only custom-designed calibration boards placed in the cameras’ common view. To address visual interference from extraneous objects, we design a unique board with AprilTag 2D codes, offering clear advantages over traditional checkerboards. Additionally, we’ve developed an Adaptive Angle Projection to counteract fisheye lens distortions. We also introduce a hierarchical pose optimization strategy that transitions from local to global, incorporating a “Planar-Eccentric constraint” to leverage the calibration board’s geometric positioning. Our method achieved 4.01 cm measurement error, with 0.075°angle error and 1.18 cm translation error. Our method’s efficacy and robustness were confirmed through extensive testing on an experimental vehicle and simulation dataset, proving its superiority in achieving precise calibration and measurement with minimal manual input.

Cross-Subject EEG Feedback for Implicit Image Generation.

Generative models are powerful tools for producing novel information by learning from example data. However, the current approaches require explicit manual input to steer generative models to match human goals. Furthermore, how these models would integrate implicit, diverse feedback and goals of multiple users remains largely unexplored. Here, we present a first-of-its-kind system that produces novel images of faces by inferring human goals directly from cross-subject brain signals while study subjects are looking at example images. We report on an experiment where brain responses to images of faces were recorded using electroencephalography in 30 subjects, focusing on specific salient visual features (VFs). Preferences toward VFs were decoded from subjects' brain responses and used as implicit feedback for a generative adversarial network (GAN), which generated new images of faces. The results from a follow-up user study evaluating the presence of the target salient VFs show that the images generated from brain feedback represent the goal of the study subjects and are comparable to images generated with manual feedback. The methodology provides a stepping stone toward humans-in-the-loop image generation.

An unsupervised learning framework for health diagnosis by incorporating multiscale data

Integrating real-time evaluations of health states with Structural Health Monitoring (SHM) data and environmental observations is crucial, particularly under large datasets. Not only is the volume of real-time data analysis substantial, but traditional algorithms like wavelet analysis often require extensive prior work and significant manual input, limiting the application of SHM and big data technologies in structural analysis. To overcome this limitation, this study introduces an unsupervised analytical framework coupling a Denoising Sparse Wavelet Network (DeSpaWN) and a dynamic-inner Principal Component Analysis (DiPCA) algorithm. The DeSpaWN is designed to extract sparse representation from multiscale sensor signals, and the features are subsequently analyzed using the DiPCA to assess health diagnoses. The DeSpaWN is specifically tailored for monitoring high-frequency time series dynamically and adaptively, enabling reconstruction and extraction of signals across various frequency domains. Additionally, the DiPCA effectively handles large-scale time-series data, providing precise evaluations by accounting for dynamic latent correlations. To validate the method, a 5-Degree of Freedom (DoF) structure model is established, equipped with five virtual sensors at each DoF and an anemometer at the top DoF. The sensor signals, obtained under different health states and subjected to artificial excitations, are input into the proposed framework. Validation results demonstrate the effectiveness in synthesizing multi-sensor data and assessing structural integrity. The framework's practical utility is showcased through a real-world case study that assesses the structural integrity of a wind turbine. By integrating real and virtual sensor data collected over a year and cross-referencing this with the fault log, the study validates the algorithm's efficacy in processing multisource heterogeneous data and its precision in structural health diagnosis. The study substantiates real-time tracking of health states for SHM-equipped structures, underscoring its potential to enhance safety and reliability in civil infrastructure.

Deep Learning Models for Dental Conditions Classification Using Intraoral Images

This paper presents the digitalization of dentistry medical records to support the dentist in the patient examination process. A dentist uses manual input to fill out the evaluation form by drawing and labeling each patient’s tooth condition based on their observations. Consequently, it takes too long to finish only one examination. For time efficiency, using AI-based digitalization technology can be a promising solution. To address the problem, we made and compared several classification models to recognize human dental conditions to help doctors analyze patient teeth. We apply the YOLOv5, MobileNet V2, and IONet (proposed CNN model) as deep learning models to recognize the five common human dental conditions: normal, filling, caries, gangrene radix, and impaction. We tested the ability of YOLO classification as an object detection model and compared it with classification models. We used a dataset of 3.708 intraoral dental images generated by various augmentation methods from 1.767 original images. We collected and annotated the dataset with the help of dentists. Furthermore, the dataset is divided into three parts: 90% of the total dataset is used as training and validation data, then divided again into 80% training data and 20% validation data. 10% of the total dataset will be used as testing data to compare classification performance. Based on our experiments, YOLOv5, as an object detection model, can classify dental conditions in humans better than the classification model. YOLOv5 produces an 82% accuracy testing value and performs better than the classification model. MobileNet V2 and IONet only get 80% and 70% testing accuracy. Although statistically, there is not much of a difference between the test accuracy values for YOLOv5 and MobileNet v2, the speed in classifying dental objects using YOLOv5 is more efficient, considering that YOLOv5 is an object detection model. There are still challenges with the deep learning technique used in this research, but these can be addressed in further development. A more complex model and the enlargement of more data, ensuring it is varied and balanced, can be used to address the limitations.

ФОРМИРОВАНИЕ ОБЪЕКТИВНЫХ ПОКАЗАТЕЛЕЙ РАБОТЫ СОРТИРОВОЧНОЙ СТАНЦИИ НА ОСНОВЕ ДАННЫХ «ОТ КОЛЕСА»

The paper presents a new principle for forming freight marshalling yard indicators based on the use of data from various reading devices and sensors located on the station tracks (data “from the wheel”). The paper shows the relevance and objectivity of using the proposed approach, implementing the presented principles for obtaining real freight yard indicators. The implementation is presented on the basis of data generated by the system for monitoring and preparing information on the movements of wagons and locomotives at the station in real time. The difference between the results obtained as a result of implementing the proposed approach and the information generated in real certificates and reporting journals of Russian Railways JSC is shown. Hypotheses-descriptions of the difference between information “from the wheel” and information obtained by manual input of data on the movements of cars and locomotives are proposed. The conclusion describes further prospects for automation of calculation and forecasting of station operation based on data “from the wheel”.

Binning Metagenomic Contigs Using Contig Embedding and Decomposed Tetranucleotide Frequency.

Metagenomic binning is a crucial step in metagenomic research. It can aggregate the genome sequences belonging to the same microbial species into independent bins. Most existing methods ignore the semantic information of contigs and lack effective processing of tetranucleotide frequency, resulting in insufficient and complex feature information extracted for binning and poor binning results. To address the above problems, we propose CedtBin, a metagenomic binning method based on contig embedding and decomposed tetranucleotide frequency. First, the improved BERT model is used to learn the contigs to obtain their embedding representation. Secondly, the tetranucleotide frequencies are decomposed using a non-negative matrix factorization (NMF) algorithm. After that, the two features are spliced and input into the clustering algorithm for binning. Considering the sensitivity of the DBSCAN clustering algorithm to input parameters, in order to solve the drawbacks of manual parameter input, we also propose an Annoy-DBSCAN algorithm that can adaptively determine the parameters of the DBSCAN algorithm. This algorithm uses Approximate Nearest Neighbors Oh Yeah (Annoy) and combines it with a grid search strategy to find the optimal parameters of the DBSCAN algorithm. On simulated and real datasets, CedtBin achieves better binning results than mainstream methods and can reconstruct more genomes, indicating that the proposed method is effective.

Development of a Natural Language Processing (NLP) model to automatically extract clinical data from electronic health records: results from an Italian comprehensive stroke center

IntroductionData collection often relies on time-consuming manual inputs, with a vast amount of information embedded in unstructured texts such as patients’ medical records and clinical notes. Our study aims to develop a pipeline that combines active learning (AL) and NLP techniques to enhance data extraction in an acute ischemic stroke cohort. Materials and methodsConsecutive acute ischemic stroke patients who received reperfusion therapies at IRCCS Humanitas Research Hospital were included. The Italian NLP Bidirectional Encoder Representations from Transformers (BERT) model was trained with AL to automatically extract clinical variables from electronic health text. Simulated active learning performances were evaluated on a set of labels representing patients’ comorbidities, comparing Bayesian Uncertainty Sampling by Disagreement (BALD) and random text selection. Prognostic models predicting patients’ functional outcomes using Gradient Boosting were trained on manually labelled and semi-automatically extracted data and their performance was compared. ResultsThe active learning process initially showed null performance until around 20% of texts were labelled, possibly due to root layers freezing in the BERT model, yet overall, active learning improves model learning efficiency across most comorbidities. Prognostic modelling showed no significant difference in performance between models trained on manually labelled versus semi-automatically extracted data, indicating effective prediction capabilities in both settings. ConclusionsWe developed an efficient language model to automate the extraction of clinical data from Italian unstructured health texts in a cohort of ischemic stroke patients. In a preliminary analysis, we demonstrated its potential applicability for enhancing prediction model accuracy.

O85 THE ACCEPTANCE, ADOPTION AND ACCESSIBILITY OF HEALTH TECHNOLOGICAL MANAGEMENT ON HOME BLOOD PRESSURE AMONG 18,867 PARTICIPANTS IN HONG KONG

Objective: Various health-related Apps have been launched to aid home blood pressure (HBP) self-management. This study aimed to investigate the acceptance, adoption, and accessibility of the HBP self-monitoring App using either photo recognition or manual input for the HBP records in Asia population. Design and Method: The participants downloaded HealthCap, the HBP self-monitoring App, aged 18 or above with at least 10 BP records were included. Elderly participants were selected from a community-based cohort for HBP self-monitoring. Well-being surveys were conducted to assess the demographic and morbidity. All participants were categorized into 2 groups, photo recognition and manually record input. Photo recognition was defined as using camera to capture the numbers on BP device for BP record upload. Manual record input was defined as selecting the number on the App. Logistic regression has been used to investigate the predictors among the group of photo recognition and manual input. Results: Total of 2,284,026 BP records collected from 18,867 participants in Hong Kong from June 2018 to November 2023. Among the 8,970 participants who met the inclusion criteria, BP records collected by photo recognition, manual input and mixture of both methods were 2,475(28%), 2,621(29%) and 3,892(43%) respectively. The mean frequency of weekly BP measurement was 4.21±7.91 times, the mean duration was 16 months, maximum was 37 months. The mean age of the participants using photo recognition, manual input and mixture were 63.81±13.14, 65.09±13.49 and 64.43±12.87 respectively. A subgroup of 1,321 elderlies aged 55 or above was analyzed with their characteristics. Logistic regression was applied to compare the group of photo recognition and manual input (Table 1). Elderlies living with children tended to use photo recognition. Less sarcopenia and those self-reported memory complaint without worries also tended to use photo recognition. Conclusion: Younger age, lower morbidity, and living with children are associated with higher usage of photo recognition for HBP self-management. Elderlies showed high acceptance, adoption, and accessibility of health technological management. Table 1. Multivariate Analysis for the Usage of Photo Recognition on Blood Pressure Monitoring.

Pilots' Reactions to Different Types of Alerts When Using Head-Up Displays.

INTRODUCTION: The benefits of using head-up displays (HUDs) include reducing head-down time during critical flight phases, enhancing awareness of the external environment, and improving in-flight crew performance. However, the monochromatic nature of HUDs, increased head rotation, and longer gaze movement paths might affect pilots' reactions to different types of alerts.METHODS: Pilot workload and behavior differences were examined between HUD and head-down display (HDD) configurations in three alert scenarios. The study was carried out in an A320 flight simulator and 12 pilots participated.RESULTS: Except for one engine-on-fire scenario, pilot workload when using a HUD was significantly lower than using an HDD. In one engine-on-fire (3.98 s vs. 3.57 s) and one gear-disagree (5.42 s vs. 4.69 s) scenario, pilot response time to alerts using HUD was significantly longer than using an HDD. The angle deviations were significantly smaller when using HUDs in both go-around-under-crosswind (2.67° vs. 3.37°) and one engine-on-fire scenario (1.22° vs. 1.89°).DISCUSSION: The HUD is suitable for a lengthy process of manual flight control inputs, which not only reduces workload but also promotes control accuracy. For tasks that rely on automation, the benefits for workload become less obvious. In addition, head rotation and reorientation of attention adversely affected the response time to non-time-critical warnings and cautions. For instantaneous control with high precision requirements, HUDs did not demonstrate a significant advantage.Zheng Y, Lu Y, Jie Y, Fu S. Pilots' reactions to different types of alerts when using head-up displays. Aerosp Med Hum Perform. 2024; 95(9):688-694.