Missing Areas Research Articles

Characterization Method and Application of Heterogeneous Reservoir Based on Different Data Quantity

Abstract Deep saline aquifers have strong heterogeneity under natural conditions, which affects the migration of carbon dioxide (CO2) injection into the reservoir. How to characterize the heterogeneity of rock mass is of great significance to research the CO2 migration law during CO2 storage. A method is proposed to construct different heterogeneous models from the point of view of whether the amount of data is sufficient or not, the wholly heterogeneous model with sufficient data, the deterministic multifacies heterogeneous model which is simplified by lithofacies classification, and the random multifacies heterogeneous model which is derived from known formation based on transfer probability theory are established, respectively. Numerical simulation is carried out to study the migration law of CO2 injected into the above three heterogeneous models. The results show that the migration of CO2 in heterogeneous deep saline aquifers shows a significant fingering flow phenomenon and reflect the physical process in CO2 storage; the migration law of CO2 in the deterministic multifacies heterogeneous model is similar to that in the wholly heterogeneous model and indicates that the numerical simulation of simplifying the wholly heterogeneous structure to the lithofacies classification structure is suitable for simulating the CO2 storage process. The random multifacies heterogeneous model based on the transfer probability theory accords with the development law of sedimentary formation and can be used to evaluate the CO2 migration law in unknown heterogeneous formations. On the other hand, by comparing the dry-out effect of CO2 in different heterogeneous models, it is pointed out that the multifacies characterization method will weaken the influence due to the local homogenization of the model in small-scale research; it is necessary to refine the grid and subdivide the lithofacies of the local key area elements to eliminate the research error. The research results provide feasible references and suggestions for the heterogeneous modeling of the missing data area and the simplification of large-scale heterogeneous models.

Shoreline Changed Analysis Due to the Sea Level Rise in Pariaman City West Sumatera Province

This study was conducted along the coastal line of Pariaman City from February to May 2021 which aims to determine and mapping the changes of the coastal line due to sea level rise. Survey methods with direct field observation was applied and satellite imageries were also used to find out the shoreline change of coast under study. Results showed that from 2001 to 2020 the mean sea level rise in Pariaman City was 2.01 cm/year. Predictions of sea level rise that will occur in 2025 and 2030 in the sequence are 17.036 cm and 27.068, in addition the wide of the missing area from 2020 to 2025 with an accumulation is around 3.74 ha and in 2025 to 2030 covering an area of 4.70 ha. The result to the year of 2025 occurs to shift considerable coastline with an average change of -9.03 m with the rate of the shoreline changed an average of -1.81 m/year. In the year 2030, shoreline changed with an average change of -29.13 m with the rate of the shoreline changed an average of -5.83 m/year

A Missing Data Tolerant Wide-Area Back-Up Protection Scheme for Transmission Network

The proposed scheme develops a missing data tolerant wide area back-up protection scheme for power transmission network with fewer PMUs. The scheme assumes division of power system into different coherent groups. The fault detection index (FDI) is used to detect a fault in the system network using active power transfer and angular difference between voltages of connected areas or summation of negative and zero sequence current components in each area. The faulted area is then identified by change in area-current (CAC) using current contribution towards each area and finally, the faulted line is identified for the respective faulted area using distance to fault (DF) index. The scheme is extensively tested on a New-England 39-bus system for several fault and stressed scenarios considering all PMU data available and PMU data loss at some of the buses. For this, the PMUs are deployed at less than half number of system buses. The maximum response time of the proposed scheme is approximately 260 ms which is well within the third zone operation time of distance relays for back-up protection. The test results including the comparative assessment with existing schemes indicate that the proposed scheme can be a potential candidate for enhancing the performance of the wide-area back-up protection in the transmission network.

Restoration of Laser Interference Image Based on Large Scale Deep Learning

Although the deep learning method has achieved some results in the challenging task of repairing the missing areas of images over the years, there is no report on the images disturbed by the laser entering the field of view. We propose a restoration model that can restore the laser interference image, the corresponding countermeasure network deep learning model and a new model training method, and no additional manual marking work is required in the data training set. After a large number of experiments, the loss function can rapidly converge under this method, accurately give the reasonable reconstruction results of the image disturbed by laser, and significantly improve the scores of many common image quality evaluation methods: high-quality repair results are obtained on the laser interference composite dataset of face (CelebA), Stanford automobile, aircraft, buildings (Facade) and satellite images. It has the characteristics of fast training speed, strong robustness, modular model design and wide application.

Sub-Bottom Profiler Sonar Image Missing Area Reconstruction Using Multi-Survey Line Patch Group Deep Learning

Air bubbles in seawater always lead to information loss for sub-bottom profiler (SBP) images. This common issue makes it difficult to interpret SBP data. Toward this end, this letter proposes a hybrid method to reconstruct the missing area on an SBP image. This method combines the information of multi-survey line to overcome the disadvantage of using a single survey line that has less observation information. First, based on an improved active contour model (ACM) algorithm and a bottom line match algorithm, the SBP images of adjacent survey lines are aligned, and the image patch group is obtained. Then, a multi-survey line patch group deep learning framework is trained to reconstruct the missing area using the patch group as the input layer. The global-local loss function is employed to optimize the deep learning training model. Both simulated and real experiments have been used to test the effectiveness of the proposed method, and good results have been achieved.

QINet: Decision Surface Learning and Adversarial Enhancement for Quasi-Immune Completion of Diverse Corrupted Point Clouds

In point cloud completion task, most previous works fail to deal with diverse corrupted point clouds with large missing areas. Meanwhile, they are restricted by discrete point clouds lacking smooth surfaces to represent an object, and the resolution of generated point clouds is fixed once their networks are determined. In addition, the evaluation metrics are not specific for this task. Thus, we propose an innovative quasi-immune completion architecture of point cloud called <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">QINet</i> in this paper, which is inspired by the artificial immunization process in biology. Specifically, to increase robustness and adaptation of the model, we conceive a mask algorithm named onion-peeling to generate diverse corrupted inputs. Meanwhile, two proposed modules are combined together to produce flexible resolution of point clouds, namely the decision surface learning and adversarial enhancement for the latent representation recovery. The first module transforms point clouds to surfaces with a continuous decision boundary function, which the second module is applied to deduce complete surface from corrupted point cloud by the cooperation of reinforcement learning and latent generative adversarial network. Besides, we evaluate the shortcomings of the existing methods and present two novel metrics to support multi-faceted comparisons. Experimental results verify that our approach can generate continuous 3D shapes with optional resolutions compared to other approaches, and achieves competitive results both quantitatively and qualitatively.

Generative Image Inpainting with Dilated Deformable Convolution

The image generation and completion model complement the missing area of the image to be repaired according to the image itself or the information of the image library so that the repaired image looks very natural and difficult to distinguish from the undamaged image. The difficulty of image generation and completion lies in the reasonableness of image semantics and the clear and true texture of the generated image. In this paper, a Wasserstein generative adversarial network with dilated convolution and deformable convolution (DDC-WGAN) is proposed for image completion. A deformable offset is added based on dilated convolution, which enlarges the receptive field and provides a more stable representation of geometric deformation. Experiments show that the DDC-WGAN method proposed in this paper has better performance in image generation and complementation than the traditional generative adversarial complementation network.

A novel complementation method of an acoustic shadow region utilizing a convolutional neural network for ultrasound-guided therapy.

Noise-free ultrasound images are essential for organ monitoring during regional ultrasound-guided therapy. When the affected area is located under the ribs, however, acoustic shadow is caused by the reflection of sound from hard tissues such as bone, and the image is output with missing information in this region. Therefore, in the present study, we attempt to complement the image in the missing area. The overall flow of the complementation method to generate a shadow-free composite image is as follows. First, we constructed a binary classification method for the presence or absence of acoustic shadow on a phantom kidney based on a convolutional neural network. Second, we created a composite shadow-free image by searching for a suitable image from a time-series database and superimposing the corresponding area without shadow onto the missing area of the target image. In addition, we constructed and verified an automatic kidney mask generation method utilizing U-Net. The complementation accuracy for kidney tracking could be enhanced by template matching. Zero-mean normalized cross-correlation (ZNCC) values after complementation were higher than that of before complementation under four different data generation conditions: (i) changing the position of the bed of the robotic ultrasound diagnostic system in the translational direction, (ii) changing the probe angle in the translational direction, (iii) with the addition of rotational motion of the probe to condition (ii). Although there was large variation in the shape of the kidney contour in condition (iii), the proposed method improved the ZNCC value from 0.5437 to 0.5807. The effectiveness of the proposed method was demonstrated in phantom experiments. Verification of its effectiveness in real organs is necessary in future study.

Simultaneous atrial and ventricular restitution and fibrillation analyses using a low-cost scalable panoramic whole-heart optical mapping configuration for whole-heart imaging of translational models

Abstract Introduction Optical mapping (OM) is the primary method for imaging electrophysiologically relevant parameters from the outer surface of Langendorff-perfused hearts. However, current panoramic OM systems are financially challenging, require multiple sensors to map wide areas of the surface with overlapping regions and missing areas of interest due to the intrinsic shape of the heart. We proposed different panoramic configurations to dynamically characterize atrial and ventricular function during arrhythmia and, in presence of a coronary occlusion. Methods We devised both a multi-sensor and a single sensor system integrated with the perfusion circuit comprising sensor elements, a control system for led illumination, electrical stimulation and sensing of physiological variables. Two configurations were tested: A multi-sensor panoramic approach including different camera views and, a precision near-ellipsoidal curved mirror (highly concentrated reflectance in the range 380nm-800nm), with exponential profile and diameter to harbor small to large hearts was used. Twelve-rabbits and two pig hearts were included in the study. OM was performed using di-4 ANDBQPQ near-infrared dye and 5–10uM blebbistatine. Initial camera calibration was done using a fishnet-like pattern and nylon landmarks. We characterized signal-tonoise ratios (SNR) of reconstructed action potentials (AP) and obtained parametric maps of the activation process. A custom-built computational pipeline for accurate motion compensation and AP reconstructions was used. Hearts were stimulated until ventricular fibrillation (VF) was induced with and without presence of a coronary occlusion in the LADartery (LADCO). Results High SNRs spatial maps were obtained after AP reconstruction (42.24±4.23dB,stimulated; 23.31±5.24dB,VF) in the most restrictive set-up, the single-sensor near-ellipsoidal configuration. Quantified activation and repolarization dynamic restitution properties were assigned to anatomically labelled scale-invariant areas in the atrium and ventricles during the induction process. Atrial and ventricular restitution dynamics could be reconstructed and analyzed simultaneously. Slower conduction (CT) and higher dispersion in repolarization (DoR) was observed after LADCO in LV (CT: 13.4±5.31ms-vs-22.42±6.82ms,DoR:23.24±4.23ms-vs-38.03±9.17ms,p&amp;lt;0.05). During VF, more heterogeneous activation patterns, enhanced left-to-right VV spectral gradient profiles, and spatially constraint shorter-lived filaments, partially explained the disturbances observed during LADCO. Results obtained with a direct multiple sensor configuration allowed for complete tracking of dominant sources, yet presenting overlapped information. Conclusion Hereby results comparing two low-cost configurations for panoramic imaging are presented and validated for the study of cardiac propagation throughout the whole epicardial surface for the study of arrhythmia, drug interventions and cardiovascular disease. Funding Acknowledgement Type of funding sources: Public grant(s) – National budget only. Main funding source(s): CIBERcv

TG-Net: Reconstruct visual wood texture with semantic attention

Defects, which arise during the growth and processing of the wood, affect the visual and mechanical properties. To improve the utilization of wood with defects, we propose an image inpainting method that reconstructs the texture at defects. The result of image inpainting is visually very consistent with the surrounding healthy board. According to the result, as an application, the plate that is most similar to the surrounding texture could be matched to fill the missing position due to the removal of defects.First, the image inpainting is divided into two stages: coarse inpainting and detailed inpainting. The coarse generator quickly generates the prediction result of the missing area, and the result is fed to the detailed generator to produce a more refined image. Then, the skip connection is applied to the classical Encoder–Decoder in order to solve the problem of information loss due to upsampling. Next, the attention block is introduced in the detailed generator to pay more attention to the meaningful semantics. Finally, normalizing missing and known regions together would result in a bias in the mean and standard deviation, so Partition Normalization was used instead of Batch Normalization. The feature map is divided into two parts, foreground and background, and the two parts are normalized separately.The experimental results show that the results of image inpainting are still high precision with less time spent on the training network. Code, demo and models are available at: https://github.com/NEFUJoeyChen/TG-Net.

Multi-view self-supervised learning for 3D facial texture reconstruction from single image

Recent years witnessed that deep learning based methods have achieved significant progresses in recovering 3D face shape from single image. However, reconstructing realistic 3D facial texture from single image is still a challenging task due to the unavailability of large-scale training datasets and the low expression ability of previous statistical texture models (e.g. 3DMM). In this paper, we introduce a novel deep architecture trained by self-supervision with multi-view setup, to reconstruct 3D facial texture. Specifically, we first obtain incomplete UV texture map from input facial image, and then introduce a Texture Completion Network (TC-Net) to inpaint missing areas. To train TC-Net, firstly, we collect 50,000 triplets of facial images from in-the-wild videos, each triplet consists of a nearly frontal, a left-side, and a right-side facial images. With this dataset, we propose a novel multi-view consistency loss that ensures consistent photometric, face identity, 3DMM identity, and UV texture among multi-view facial images. This loss allows to optimize TC-Net in a self-supervision way without using ground-truth texture map as supervision. In addition, multi-view input images are only required in training to provide self-supervision, and our method only needs single input image in inference. Extensive experiments show that our method achieves state-of-the-art performance in both qualitative and quantitative comparisons.

A Study on Intelligent Obscured Face Image Completion System Based on GAN Network

Image recognition and processing is an important part of modern information technology. However, in real life, the face will inevitably be blocked by hats, masks, or face photos are damaged, scratches, and images are added mosaic and other reasons, resulting in face image masking, increasing face information recognition and processing difficulties. Image completion is a kind of technology to restore the missing information of obscured image. By supplementing the information of missing area, it can reduce the difficulty of image recognition and simplify the processing of face information.So it has important research significance for the restoration of shaded image. The traditional image completion technology produces the face of poor natural degree. At present, most of the popular completion methods combine depth learning, and the repair methods based on generating anti-network GAN are the representatives of them.But the stability of the network is poor, so it is difficult to train pictures with large sheltered area or poor image quality.Some methods are not effective in the completion of arbitrary shaded areas. Therefore, this study focuses on the improvement of the stability of the generated adversarial network and the maintenance of the global and local semantic consistency between the completion image and the real image. The main work includes: (1) Sets a special network structure of global discriminator and local discriminator. When the input is arbitrarily shaded, the completion image can maintain the consistency of global and local semantics. (2) The least square loss function is used to improve the stability of the GAN network. So it performs great when the input image has large area masking or low visualization degree. (3) ADAM algorithm is used to accelerate the training of neural network. (4) Based on the completion model, a human-computer interaction software is designed and developed, which includes data set selection, image selection, image completion, result evaluation and so on. The system is applied to the removal of facial structures such as wrinkles and spots. Compared with some existing software, the system can effectively remove the selected facial structures without image distortion. Based on the design of special network structure, the system improves the supervision ability of global and local completion, the stability of GAN network and enhances its training ability in large area masking. The system is intelligent and has strong completion ability for arbitrary masking and large area masking. The research results of this paper effectively restore the information loss caused by image masking and prepare favorable conditions for subsequent image recognition and processing.

Intraoperative Digital Analysis of Ablation Margins (DAAM) by Fluorescent Confocal Microscopy to Improve Partial Prostate Gland Cryoablation Outcomes

Simple SummaryThis study tested the feasibility and reliability of a novel digital microscopy technique in assessing ablation margins during partial prostate gland cryoablation. Though preliminary, findings suggest that this novel technique may increase the efficacy of focal treatments, by reducing the risk of untreated prostate cancer areas not visible to an MRI, as well as safety, by more precisely sparing uninvolved areas and surrounding structures.Partial gland cryoablation (PGC) aims at destroying prostate cancer (PCa) foci while sparing the unaffected prostate tissue and the functionally relevant structures around the prostate. Magnetic Resonance Imaging (MRI) has boosted PGC, but available evidence suggests that ablation margins may be positive due to MRI-invisible lesions. This study aimed at determining the potential role of intraoperative digital analysis of ablation margins (DAAM) by fluoresce confocal microscopy (FCM) of biopsy cores taken during prostate PGC. Ten patients with low to intermediate risk PCa scheduled for PGC were enrolled. After cryo-needles placement, 76 biopsy cores were taken from the ablation margins and stained by the urologist for FCM analysis. Digital images were sent for “real-time” pathology review. DAAM, always completed within the frame of PGC treatment (median time 25 min), pointed out PCa in 1/10 cores taken from 1 patient, thus prompting placement of another cryo-needle to treat this area. Standard HE evaluation confirmed 75 cores to be cancer-free while displayed a GG 4 PCa in 7% of the core positive at FCM. Our data point out that IDAAM is feasible and reliable, thus representing a potentially useful tool to reduce the risk of missing areas of PCa during PGC.

Evaluation of mapped-plot variance estimators across a range of partial nonresponse in a post-stratified national forest inventory

When conducting a forest inventory, sometimes portions of plots cannot be measured due to inaccessibility. Two primary methods have been presented to account for partial nonresponse in the estimation phase: (i) use a ratio-to-size estimator or (ii) apply an adjustment factor to all plot observations in proportion to the missing area. Both approaches provide identical estimates of the population mean, but the estimates of variance differ when partial nonresponse is present. The performance of variance estimators was examined for a range of population forest area and partial nonresponse proportions in the sample. The ratio-to-size variance estimator performed unbiasedly with respect to simulation results, but the adjustment factor variance estimates were biased, with magnitude and direction dependent upon the forest area proportion and amount of partial nonresponse. The bias is relatively small when the partial nonresponse is small, which is often the case; however, the ratio-to-size method is preferred to ensure accurate variance estimation for a wide range of circumstances.

Fault Tolerant Strategies for Automated Insulin Delivery Considering the Human Component: Current and Future Perspectives.

Automated Insulin Delivery (AID) are systems developed for daily use by people with type 1 diabetes (T1D). To ensure the safety of users, it is essential to consider how the human factor affects the performance and safety of these devices. While there are numerous publications on hardware-related failures of AID systems, there are few studies on the human component of the system. From a control point of view, people with T1D using AID systems are at the same time the plant to be controlled and the plant operator. Therefore, users may induce faults in the controller, sensors, actuators, and the plant itself. Strategies to cope with the human interaction in AID systems are needed for further development of the technology. In this paper, we present an analysis of potential faults introduced by AID users when the system is under normal operation. This is followed by a review of current fault tolerant control (FTC) approaches to identify missing areas of research. The paper concludes with a discussion on future directions for the new generation of FTC AID systems.

Onward migration: An introduction

Onward migration: An introduction

Vectorized indoor surface reconstruction from 3D point cloud with multistep 2D optimization

Vectorized reconstruction from indoor point cloud has attracted increasing attention in recent years due to its high regularity and low memory consumption. Compared with aerial mapping of outdoor urban environments, indoor point cloud generated by LiDAR scanning or image-based 3D reconstruction usually contain more clutter and missing areas, which greatly increase the difficulty of vectorized reconstruction. In this paper, we propose an effective multistep pipeline to reconstruct vectorized models from indoor point cloud without the Manhattan or Atlanta world assumptions. The core idea behind our method is the combination of a sequence of 2D segment or cell assembly problems that are defined as global optimizations while reducing the reconstruction complexity and enhancing the robustness to different scenes. The proposed method includes a semantic segmentation stage and a reconstruction stage. First, we segment the permanent structures of indoor scenes, including ceilings, floors, walls and cylinders, from the input data, and then, we reconstruct these structures in sequence. The floorplan is first generated by detecting wall planes and selecting optimal subsets of projected wall segments with Integer Linear Programming (ILP), followed by constructing a 2D arrangement and recovering the ceiling and floor structures by Markov Random Filed (MRF) labeling on the arrangement. Finally, the wall structures are modeled by lifting each edge of the arrangement to a proper height by means of another global optimization. Merging the respective results yields the final model. The experimental results show that the proposed method could obtain accurate and compact vectorized models on both precise LiDAR data and defect-laden MVS data compared with other state-of-the-art approaches.

EVALUATION OF THE RECOMMENDATIONS PART OF THESES IN THE FIELD OF HEALTH MANAGEMENT

Problem of Research: Health institutions are structures that exist for medical, economic and social purposes. The field of Health Management is a discipline that examines health systems and institutions in the system from a managerial perspective. The health care system is of interest in the fields of social, economic and administrative sciences, especially Health Sciences, and researchers from these fields conduct many studies. One of these research methods is theses made at the graduate level. Graduate theses represent an important part of the emerging literature in the field of Health Management and provide important information on the course of scientific studies. In theses, the recommendations given depending on the work done are also the results of theses from a point of view. The recommendations in the theses deserve to be examined, as they arise on the basis of a scientific study.&#x0D; &#x0D; Purpose of the Study: In this study, it was aimed to evaluate the recommendations given to the researchers by the graduate theses completed in the Department of Health Management from a holistic point of view and to bring a new perspective to the studies to be conducted.&#x0D; &#x0D; Method: The postgraduate theses that constitute the research subject were obtained as a result of the screening made in the national thesis center (https://tez.yok.gov.tr/UlusalTezMerkezi/). When the postgraduate theses in the Electronic Thesis Archive of the Higher Education Institution were examined, it was found that a total of 785 graduate theses were written in the field of health management in a 23-year period between 1997 and 2020. Looking at these theses, 76 of them are doctoral theses and 709 are master's theses. This study is limited to 100 (90 master's and 10 doctoral) graduate theses, which were found to be completed in the field of Health Management in 2019. In the classification made according to the suggestions given to the researchers, suggestions and conclusion parts were taken into account. Suggestions were evaluated in five categories: made to managers, made to employees, made to policy makers, made to researchers, and made to other stakeholders.&#x0D; &#x0D; Findings: Highlights of the recommendations of graduate theses completed in 2019 in the field of Health Management in Turkey are as follows: Managers have important duties and responsibilities in all areas in terms of both employees and patients in health institutions, supporting employees ' training and personal development is important for patient satisfaction, policy makers need to make the necessary legal arrangements by including medical tourism, students ' internship experience, rational drug use, preparation of collateral packages, accidents at work and mobbing concepts, presenting its social benefits by addressing the media in many studies as other stakeholders. It was emphasized that researchers should find innovative field-specific methods, that increasing the number of studies similar to those conducted, or expanding the field of study could be more guiding and enlightening about the validity of the results obtained. It was stated that there is need for scientific cooperation, different techniques can be used in studies, and the experts referred to in their opinion can be differentiated in number and quality. It was emphasized that analyses in the field of health are developing and studies can be done with developing analysis techniques, and the application of the same scales in different health institutions will allow the sector to be looked at from a wider perspective.&#x0D; &#x0D; At the end of the study, the developments and trends in the field, the missing or new areas to be studied were determined in line with the suggestions and inferences were made.

Toward semantic image inpainting: where global context meets local geometry

Image inpainting attempts to fill the missing areas of an image with plausible content that is visually coherent with the image context. Semantic image inpainting has remained a challenging task even with the emergence of deep learning-based approaches. We propose a deep semantic inpainting model built upon a generative adversarial network and a dense U-Net network. Such a design helps achieve feature reuse while avoiding feature explosion along the upsampling path of the U-Net. The model also uses a composite loss function for the generator network to enforce a joint global and local content consistency constraint. More specifically, our new loss function combines the global reconstruction loss characterizing the semantic similarity between the missing and known image regions with the local total variation loss characterizing the natural transitions among adjacent regions. Experimental results on CelebA-HQ and Paris StreetView datasets have demonstrated encouraging performance when compared with other state-of-the-art methods in terms of both quantitative and qualitative metrics. For the CelebA-HQ dataset, the proposed method can more faithfully infer the semantics of human faces; for the StreetView dataset, our method achieves improved inpainting results in terms of more natural texture transitions, better structural consistency, and enriched textural details.

A Novel Ensemble Machine Learning Approach for Bioarchaeological Sex Prediction

I present a novel machine learning approach to predict sex in the bioarchaeological record. Eighteen cranial interlandmark distances and five maxillary dental metric distances were recorded from n = 420 human skeletons from the necropolises at Alfedena (600–400 BCE) and Campovalano (750–200 BCE and 9–11th Centuries CE) in central Italy. A generalized low rank model (GLRM) was used to impute missing data and Area under the Curve—Receiver Operating Characteristic (AUC-ROC) with 20-fold stratified cross-validation was used to evaluate predictive performance of eight machine learning algorithms on different subsets of the data. Additional perspectives such as this one show strong potential for sex prediction in bioarchaeological and forensic anthropological contexts. Furthermore, GLRMs have the potential to handle missing data in ways previously unexplored in the discipline. Although results of this study look promising (highest AUC-ROC = 0.9722 for predicting binary male/female sex), the main limitation is that the sexes of the individuals included were not known but were estimated using standard macroscopic bioarchaeological methods. However, future research should apply this machine learning approach to known-sex reference samples in order to better understand its value, along with the more general contributions that machine learning can make to the reconstruction of past human lifeways.