Global Accuracy Research Articles

Robotics for Heritage Surveying: preliminary test on Leica BLK ARC & Spot® toward autonomous 3D mapping

Abstract. Today, robotics technologies are revolutionizing surveying and construction in AEC fields, enhancing precision, safety, and efficiency and also in the realm of Cultural Heritage knowledge and protection, the integration of cutting-edge technologies is reshaping consolidated surveying methods for documentation, especially in risk scenarios. One such innovation making waves is the use of mobile mapping systems, where automation and expediency are the determining factors in technological development, both in the direction of in indoor positioning (visual/LiDAR SLAM, UWB, etc.) and 3D mapping of known and unknown spaces. The BLK ARC by Leica, equipping the Agile Mobile Robot Spot® by Boston Dynamics, as a dynamic sensing platform, is here presented and discussed. BLK ARC is part of a diverse landscape of mobile mapping systems, each offering unique features and specifications tailored to different surveying needs, from handheld devices and wearable systems, to vehicle-mounted systems, the options vary in dimension, weight, price, and technical capabilities and the recent companies and research are largely focusing on them. A preliminary evaluation takes into consideration the dual dynamic-static 3D data-types, considering local and global accuracy of the 3D data delivered from the first experimental tests in a case study. Different metrics have been considered including acquisition time, precision, resolution, density, accuracy, roughness, and completeness of the acquired data.

Prediction of Glass Chemical Composition and Type Identification Based on Machine Learning Algorithms

Ancient glass artifacts were susceptible to weathering from the environment, causing changes in their chemical composition, which pose significant obstacles to the identification of glass products. Analyzing the chemical composition of ancient glass has been beneficial for evaluating their weathering status and proposing measures to reduce glass weathering. The objective of this study was to explore the optimal machine learning algorithm for glass type classification based on chemical composition. A set of glass artifact data including color, emblazonry, weathering, and chemical composition was employed and various methods including logistic regression and machine learning techniques were used. The results indicated that a significant correlation (p < 0.05) could only observed between surface weathering and the glass types (high-potassium and lead–barium). Based on the random forest and logistic regression models, the primary chemical components that signify glass types and weathering status were determined using PbO, K2O, BaO, SiO2, Al2O3, and P2O5. The random forest model presented a superior ability to identify glass types and weathering status, with a global accuracy of 96.3%. This study demonstrates the great potential of machine learning for glass chemical component estimation and glass type and weathering status identification, providing technical guidance for the appraisal of ancient glass artifacts.

Online cognitive monitoring technology for people with Parkinson’s disease and REM sleep behavioural disorder

Automated online cognitive assessments are set to revolutionise clinical research and healthcare. However, their applicability for Parkinson’s Disease (PD) and REM Sleep Behavioural Disorder (RBD), a strong PD precursor, is underexplored. Here, we developed an online battery to measure early cognitive changes in PD and RBD. Evaluating 19 candidate tasks showed significant global accuracy deficits in PD (0.65 SD, p = 0.003) and RBD (0.45 SD, p = 0.027), driven by memory, language, attention and executive underperformance, and global reaction time deficits in PD (0.61 SD, p = 0.001). We identified a brief 20-min battery that had sensitivity to deficits across these cognitive domains while being robust to the device used. This battery was more sensitive to early-stage and prodromal deficits than the supervised neuropsychological scales. It also diverged from those scales, capturing additional cognitive factors sensitive to PD and RBD. This technology offers an economical and scalable method for assessing these populations that can complement standard supervised practices.

High-efficiency scattering field modeling in metallic components: a machine-learning-inspired approach

We present a highly efficient method for characterizing the scattering field distribution of surface plasmon polaritons in metallic components by combining the eXtended Pseudospectral Frequency-Domain (X-PSFD) method with an iterative, machine-learning-inspired procedure. Shifting away from traditional matrix operations, we utilize the “Adam” optimizer—an effective and swift machine learning algorithm—to solve the scattering field distribution. Our method encompasses the derivation of the associated cost function and gradient differentiation of the field, leveraging spectral accuracy at Legendre collocation points in the Helmholtz equation. We refine the total-field/scattered-field (TF/SF) formulation within the X-PSFD framework for optimized incident field management and employ Chebyshev–Lagrange interpolation polynomials for rapid, accurate computation of broad-band results. To ensure global accuracy, we introduce unique physical boundary conditions at subdomain interfaces. Demonstrating our method’s robustness and computational efficiency, we model perfect electric conductors (PECs) and silver nanocylinders, and we apply our approach to analyze the excited electric field on subtly distorted metallic surfaces, particularly plasmonic structures, thereby validating its wide-ranging effectiveness.

Coverage optimization of wireless sensor networks based on bottle sea sheath optimization algorithm

To tackle the problem of inadequate placement of wireless sensor networks’ sensor nodes, a proposed algorithm aims to enhance network coverage through a more optimal approach. Recognizing limitations in the Salp Swarm Algorithm (SSA) optimization, specifically its insufficient local search capability and susceptibility to local extreme values, a hybrid strategy is introduced in the search step. This strategy involves adaptive weight factor adjustments and incorporates Levy flight, achieving a better balance between global search, convergence speed, and computational accuracy. Consequently, this refinement contributes to improved effective network coverage, enhancing the overall network coverage in wireless sensor networks and facilitating faster coverage of the nodes.

Design and validation of an artificial intelligence system to detect the quality of colon cleansing before colonoscopy

Background and aimsPatients’ perception of their bowel cleansing quality may guide rescue cleansing strategies before colonoscopy. The main aim of this study was to train and validate a convolutional neural network (CNN) for classifying rectal effluent during bowel preparation intake as “adequate” or “inadequate” cleansing before colonoscopy. Patients and methodsPatients referred for outpatient colonoscopy were asked to provide images of their rectal effluent during the bowel preparation process. The images were categorized as adequate or inadequate cleansing based on a predefined 4-picture quality scale. A total of 1203 images were collected from 660 patients. The initial dataset (799 images), was split into a training set (80%) and a validation set (20%). The second dataset (404 images) was used to develop a second test of the CNN accuracy. Afterward, CNN prediction was prospectively compared with the Boston Bowel Preparation Scale (BBPS) in 200 additional patients who provided a picture of their last rectal effluent. ResultsOn the initial dataset, a global accuracy of 97.49%, a sensitivity of 98.17% and a specificity of 96.66% were obtained using the CNN model. On the second dataset, an accuracy of 95%, a sensitivity of 99.60% and a specificity of 87.41% were obtained. The results from the CNN model were significantly associated with those from the BBPS (P<0.001), and 77.78% of the patients with poor bowel preparation were correctly classified. ConclusionThe designed CNN is capable of classifying “adequate cleansing” and “inadequate cleansing” images with high accuracy.

A Study on Three-Dimensional Modelling of the Baitul Ilmi Mosque's Itera Using Terrestrial Laser Scanner Technology

As advancements in three-dimensional (3D) modeling continue to progress, the demand for precise and efficient measurement techniques has led to significant innovations in the methods and tools used for creating 3D models. Among these, the utilization of Terrestrial Laser Scanners (TLS) has become increasingly popular. This study focuses on the integration of TLS and total station technologies for 3D modeling of a mosque. The total station was employed to conduct five sets of perfectly bonded closed polygon measurements, each consisting of five polygon points, from which three marker points were derived. Concurrently, the TLS was used to perform a comprehensive scan of the mosque from 17 different positions. The data obtained from the TLS scan provided a detailed 3D model, while the total station measurements served as control points to ensure the model's global coordinate accuracy. The processing of the closed polygon data was executed using the Bowditch method, and the TLS data was registered using the cloud-to-cloud method. This approach yielded an overall quality assessment, including a bundle error of 0.008 m, an overlap of 27%, a strength of 65%, and a cloud-to-cloud discrepancy of 0.008 m. The integration of point clouds with total station coordinates resulted in an error margin of 0.160 m. Geometric validation of the model was conducted by comparing its dimensions to measurements obtained using a measuring tape, which yielded a Root Mean Square Error (RMSE) of 0.045 m.

Design of sports training information analysis system based on a multi-target visual model under sensor-scale spatial transformation

In the contemporary realm of athletic training, integrating technology is a pivotal determinant for augmenting athlete performance and refining training outcomes. The amalgamation of multi-target visual modeling with sensor technology imparts an enriched stratum of sports training data. Subsequently, the sensor scale-space transformation accentuates the comprehensive apprehension of data across diverse scales and angles. Hence, within this manuscript, addressing the multi-target tracking intricacies during sports training and competition, we posit a framework that amalgamates the shortest path elucidated by the K shortest paths (KSP) methodology with the pose information emanating from the Alphapose network. This framework recognizes the athlete’s shortest path through a convolutional neural network and KSP, followed by the amalgamation of these divergent data sources. The fusion unfolds by incorporating the athlete’s pose information grounded in Alphapose, culminating in a comprehensive integration of the two data streams. Consequently, synthesizing alpha-derived athlete information precipitates the ultimate amalgamation of the two information streams. The accomplished fusion, premised on Alphapose, forms the bedrock for multi-target tracking, culminating in a feature-rich synthesis. Empirical results reveal that after integrating these information streams, the Multiple Object Tracking Accuracy (MOTA) index and Global Multiple Object Tracking Accuracy (GMOTA) index surpass those of the solitary information tracking methods, thereby furnishing a technical underpinning and a foundation for information fusion within prospective sports training analysis systems.

Variable horizon multivariate driving pattern recognition framework based on vehicle-road two-dimensional information for electric vehicle

Driving condition is the core factor influencing vehicle energy management and power output strategies, hence realistic and accurate driving pattern recognition is crucial for realizing intelligent control of Electric Vehicles in complex scenarios. However, driving patterns mismatch with real scenarios caused by lack of road environment information and the reduced global recognition accuracy triggered by the fixed recognition horizon together constrain the development of intelligent control strategies. In this study, a framework for variable horizon multivariate driving pattern recognition strategy based on vehicle-road two-dimensional (2D) information is proposed. Specifically, multivariate driving pattern extraction is carried out based on real vehicle-road 2D data, and the extraction data serves as input for training offline driving pattern recognizer. To meet the challenge of large differences and frequent changes in driving conditions during the online application, a variable horizon recognition strategy is proposed based on the optimal horizon matching regularity. Finally, test results show that the proposed approach achieves an average recognition accuracy of 88.42% under different cycles, including 88.39% for complex driving cycles. Furthermore, the recognition accuracy is improved by 63.14% and 47.51% compared with the fixed long/short horizon. The framework can provide a basis for intelligent control strategies, thus broadening the Electric Vehicle application scenarios.

Exhaustive distributed intrusion detection system for UAVs attacks detection and security enforcement (E-DIDS)

Distributed intrusion detection systems (DIDS) are a specialized subset of conventional IDSs designed for implementation in distributed environments. Each IDS is integrated into distinct entities within a monitored network, potentially distributed across various locations. These participating IDSs can be configured to detect either a particular or multiple attack types. Although DIDS has found extensive application in diverse IoT systems, its utilization in unmanned aerial vehicles (UAVs) still needs to be explored. Consequently, it is imperative to devise a comprehensive framework tailored explicitly for UAVs. It combines multiple detection units to enhance security. Based on the insights gained from previous studies, we propose an exhaustive DIDS for UAVs security enforcement in this paper. Our proposed solution offers a robust and scalable security approach. Through distributing the workload across interconnected IDSs deployed on the UAV, our solution was optimized for UAVs attacks detection to achieve high detection performance while reducing the complexity. To the best of our insight, there is no recorded DIDS for UAVs security, and attack detection has been proposed and evaluated. Furthermore, our paper provides a detailed analysis, outlining the development basis and the achieved results. We performed multiple experiments over different cases using different datasets. The achieved experimental results demonstrate that the proposed IDS has significantly high accuracy detection and low loss rates. Our proposed E-DIDS efficiently detects multiple attacks on different UAVs subsets with good global accuracy that reached 98.6% and low resource consumption.

Research on soft sensor modeling method for complex chemical processes based on local semi-supervised selective ensemble learning

To address the adverse effects of nonlinearity and dynamic time-varying in complex chemical processes on the accuracy of the soft sensor model, a local-semi-supervised ensemble learning for soft sensor modeling (local semi-supervised-selective ensemble learning-long short term memory, LS-SEL-LSTM) method is proposed in this article. Firstly, a hierarchical clustering method incorporating spatiotemporal criteria is proposed to reduce the influence of nonlinearity in global model prediction accuracy. The method considers the dynamic time-varying characteristics of temporal data and generates multiple local datasets. Then, to address the issue of multi-rate between auxiliary variables and dominant variables, a semi-supervised weight fusion mechanism based on temporal correlation is proposed, which effectively utilizes auxiliary variables to reconstruct local semi-supervised datasets and establishes local soft sensing models using LSTM. Concurrently, the parameters of the established model were optimized using the flower pollination algorithm. Subsequently, a selective ensemble learning method based on sub-model prediction accuracy and an adaptive combination weight calculation method for sub-models were proposed to improve the prediction accuracy. Finally, the effectiveness of the proposed method was verified through the actual dataset of the sulfur recovery process. The results indicate that LS-SEL-LSTM performs well in handling complex chemical processes with nonlinear and dynamic time-varying characteristics.

RETRACTED: SFL-MDrone: Synchronous federated learning enabled multi drones

This article has been retracted. A retraction notice can be found at https://doi.org/10.3233/JIFS-219433.

Online Monitoring of Iron Ore Pellet Size Distribution Using Lightweight Convolutional Neural Network

An improved U-Net based convolutional neural network (CNN) is proposed in this paper for online size monitoring of iron ore pellets. The proposed CNN model is a lightweight version of U-Net. In the proposed model each convolution block of the encoder subnet consists of a concatenated <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$1\times 1$</tex-math> </inline-formula> and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$3\times 3$</tex-math> </inline-formula> filter kernel, a batch normalization layer, and a ReLU nonlinearity. The proposed CNN model efficiently detects the pellets even under variable illumination conditions and images with overlapping pellets. The proposed model is evaluated using images of iron ore pellets acquired at the discharge end of a pelletizer disc. The proposed CNN model performs satisfactorily using <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\sim$</tex-math> </inline-formula> 39% less learnable parameters, and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\sim$</tex-math> </inline-formula> 16% reduced computational cost than the original U-Net model. The proposed model outperforms the conventional U-Net, different variants of U-Nets, FCN, and SegNet in weighted IoU, BF Score, global accuracy, SSIM, and PSNR. Experimental validation also shows a good agreement between the obtained pellet size distribution and the manual sieving result. This makes the proposed algorithm suitable for online pellet size-distribution measuring instruments. This method provides a more accurate and fast size monitoring system for iron ore pellets, ideal for real-time industrial applications. The image dataset and source codes are available at the below given link. https://github.com/aryadeo/Pellet_Size_Distribution. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —Due to the advent of digitalization in industries, several attempts are being made to use innovative industrial monitoring systems in steel manufacturing plants. Most of the pellet plants in steel industries use human supervision for pellet growth monitoring. In this paper, a camera-based pellet size distribution monitoring method is proposed. A novel deep learning-based algorithm is used for the detection of pellets from the captured image followed by computation of pellet size analysis. Due to low computational complexity and better accuracy, the proposed method is suitable for online pellet size distribution system development compared to other previously proposed methods. However, protection from the harsh industrial environment is required for the uninterrupted and continuous operation of the system. As a future scope, the obtained pellet size information can be used as one of the control variables in designing a control system for the automated operation of the pelletizer disc.

A Privacy-Aware and Incremental Defense Method Against GAN-Based Poisoning Attack

Federated learning is usually utilized as a fraud detection framework in the domain of financial risk management, which promotes the model accuracy without training data exchange. One of the challenges in federated learning is the GAN-based poisoning attack. The GAN-based poisoning attack is a type of intractable poisoning attack that causes global model accuracy degradation and privacy leak. Most of the existing defenses for GAN-based poisoning attack have the three problems: 1) dependence on validation datasets; 2) incompetence of dealing with incremental poisoning attack; and 3) privacy leak. To address the above problems, we present a privacy-aware and incremental defense (PID) method to detect malicious participants and protect privacy. In PID, we design a method to accumulate the offset of model parameters from participants in all current epochs to represent the moving tendency for model parameters. Thus, we can distinguish the adversaries from normal participants based on the accumulations in this incremental poisoning attack. We also use multiple trust domains to reduce the rate of misjudging benign participants as adversaries. Moreover, a differentiated differential privacy is utilized before the global model sending to protect the privacy of participants’ training datasets in PID. The experiments conducted on two real-world datasets under financial fraud detection scenario demonstrate that the PID reduces the fallout of adversaries detection (the rate of misjudging benign participants as adversaries) by at least 51.1% and improve the speed of detecting all malicious participants by at least 33.4% compared with two popular defense methods. Besides, the privacy preserving of PID is also effective.

A novel global calibration method for vision measurement system based on mirror-image stereo target

Using three-dimensional (3D) targets to solve the transformation relationship between the local and global coordinate systems is a common global calibration method. However, 3D targets have complex structures and high costs. And multiple coordinate transformations during global calibration can cause significant cumulative errors. Therefore, based on reflection imaging, this paper designs a new mirror-image stereo target (MST) and analyzes its view area and three structural parameter constraints. A new global calibration method is proposed, as well as three optimization algorithms for pose solution between MST, optical 3D sensor and global camera to improve the global calibration accuracy. The experimental results show that the registration errors of two workpieces are 0.086 mm and 0.114 mm, respectively, confirming the feasibility and precision of the proposed method. Our method is flexible, requiring only a planar target and a mirror, rather than complex 3D targets, to achieve global calibration with non-overlapping field of view.

Evaluation of Infrared Thermography Dataset for Delamination Detection in Reinforced Concrete Bridge Decks

Structural health monitoring and condition assessment of existing bridge decks is a growing challenge. Conventional manned inspections are costly, labor-intensive, and often risky to execute. Sub-surface delamination, a leading cause of deck replacement, can be autonomously and objectively detected using infrared thermography (IRT) data with developed deep learning AI models to address some of the limitations associated with manned inspection. As one of the most promising classifiers, deep convolutional neural networks (DCNNs) have not been utilized to their fullest potential for delamination detection, arguably due to the scarcity of realistic ground truth datasets. In this study, a common encoder–decoder semantic segmentation-based DCNN is adapted through domain adaptation. The model was tuned and trained on a publicly available dataset to detect subsurface delamination in IRT data collected from in-service bridge decks. The authors investigated the effect of dataset augmentation, class imbalance, the number of classes, and the effect of background removal in the training dataset, resulting in an overall number of seventy-five UNET models. Four out of five bridges were adopted for training and validation, and the fifth bridge was for testing. Most models averaged 80 iterations, and the training progress finally reached a training accuracy of 75% with a loss of about 0.6 without any overfitting. The result showed a substantial difference in the minimum and maximum values for the evaluated performance metrics (0.447 and 0.773 for global accuracy, 0.494 and 0.657 for mean accuracy, 0.239 and 0.716 for precision, 0.243 and 0.558 for true positive rate (TPR), 0.529 and 0.899 for true negative rate (TNR), 0.282 and 0.550 for F1-score. The results also indicated that the models trained on the raw annotated balanced dataset performed best for half of the metrics. In contrast, the models trained on raw data (with no dataset enhancement) performed better when only global accuracy was considered.

The importance of digital elevation model accuracy in XCO2 retrievals: improving the Orbiting Carbon Observatory 2 Atmospheric Carbon Observations from Space version 11 retrieval product

Abstract. Knowledge of surface pressure is essential for calculating column-averaged dry-air mole fractions of trace gases, such as CO2 (XCO2). In the NASA Orbiting Carbon Observatory 2 (OCO-2) Atmospheric Carbon Observations from Space (ACOS) retrieval algorithm, the retrieved surface pressures have been found to have unacceptable errors, warranting a parametric bias correction. This correction depends on the difference between retrieved and a priori surface pressures, which are derived from a meteorological model that is hypsometrically adjusted to the surface elevation using a digital elevation model (DEM). As a result, the effectiveness of the OCO-2 bias correction is contingent upon the accuracy of the referenced DEM. Here, we investigate several different DEM datasets for use in the OCO-2 ACOS retrieval algorithm: the OCODEM used in ACOS v10 and previous versions, the NASADEM+ (a composite of SRTMv4, ASTER GDEMv3, GIMP, and RAMPv2 DEMs) used in ACOS v11, the Copernicus GLO-90 DEM (GLO-90 DEM), and two polar regional DEMs (ArcticDEM and REMA). We find that the NASADEM+ (ASTER GDEMv3) has a persistent negative bias on the order of 10 to 20 m across most regions north of 60° N latitude, relative to all the other DEMs considered (OCODEM, ArcticDEM, and GLO-90 DEM). Variations of 10 m in DEM elevations lead to variations in XCO2 of approximately 0.4 ppm, meaning that the XCO2 from OCO-2 ACOS v11 retrievals tends to be 0.4 to 0.8 ppm lower across regions north of 60° N than XCO2 from OCO-2 ACOS v10. Our analysis also suggests that the GLO-90 DEM has superior global continuity and accuracy compared to the other DEMs, motivating a post-processing update from OCO-2 v11 Lite files (which used NASADEM+) to OCO-2 v11.1 by substituting the GLO-90 DEM globally. We find that OCO-2 v11.1 improves accuracy and spatial continuity in the bias-corrected XCO2 product relative to both v10 and v11 in high-latitude regions while resulting in marginal or no change in most regions within ± 60° latitude. In addition, OCO-2 v11.1 provides increased data throughput after quality control filtering in most regions, partly due to the change in DEM but mostly due to other corrections to quality control parameters. Given large-scale differences north of 60° N between the OCODEM and NASADEM+, we find that replacing the OCODEM with NASADEM+ yields a ∼ 100 TgC shift in inferred carbon uptake for the zones spanning 30 to 60° N and 60 to 90° N, which is on the order of 5 % to 7 % of the estimated pan-Arctic land sink. Changes in inferred fluxes from replacing the OCODEM with the GLO-90 DEM are smaller, and given the evidence for improved accuracies from this DEM, this suggests that large changes in inferred fluxes from the NASADEM+ are likely erroneous.

Kriging-based multi-objective optimization on high-speed train aerodynamics using sequential infill criterion with gradient information

For models with large numerical simulation costs, such as high-speed trains, using as few samples as possible to construct a high-precision surrogate model during aerodynamic multi-objective optimization is critical to improving optimization efficiency. This study proposes a sequential infill criterion (SIC) appropriate for the Kriging surrogate model to address this issue. Three multi-objective functions are employed to test the feasibility of constructing a surrogate model based on SIC, and the SIC surrogate model then performs multi-objective aerodynamic optimizations on the high-speed train. The findings indicate that the expected improvement infill criterion (EIC) in the first stage can enhance the global prediction accuracy of the SIC. An infill criterion based on EIC that fuses gradient information (PGEIC) in the second stage is proposed to seek samples in the Pareto front. The PGEIC surrogate model achieves the lowest generational distance and prediction error. The performance of EIC for global search, EIC for Pareto front search, and infill criterion for Pareto front search using only gradient information is poor. The final PGEIC–SIC surrogate model of train aerodynamics has less than 1% prediction error for the three optimization objectives. The optimal solution reduces the aerodynamic drag force of the head car and the aerodynamic drag and lift force of the tail car by 4.15%, 3.21%, and 3.56%, respectively, compared with the original model. Furthermore, sensitivity analysis of key parameters revealed that the nose height v1, cab window height v3, and lower contour line have a greater impact on aerodynamic forces. Moreover, the nose and cab window heights of the optimal model have been reduced, and the lower contour line is concave. Correspondingly, the streamlined shape appears more rounded and slender.

An Assessment of Medication Errors Among Pediatric Patients in Three Hospitals in Freetown Sierra Leone: Findings and Implications for a Low-Income Country.

Pediatric patients are prone to medicine-related problems like medication errors (MEs), which can potentially cause harm. Yet, this has not been studied in this population in Sierra Leone. Therefore, this study investigated the prevalence and nature of MEs, including potential drug-drug interactions (pDDIs), in pediatric patients. The study was conducted in three hospitals among pediatric patients in Freetown and consisted of two phases. Phase one was a cross-sectional retrospective review of prescriptions for completeness and accuracy based on the global accuracy score against standard prescription writing guidelines. Phase two was a point prevalence inpatient chart review of MEs categorized into prescription, administration, and dispensing errors and pDDIs. Data was analyzed using frequency, percentages, median, and interquartile range. Kruskal-Wallis H and Mann-Whitney U-tests were used to compare the prescription accuracy between the hospitals, with p<0.05 considered statistically significant. Three hundred and sixty-six (366) pediatric prescriptions and 132 inpatient charts were reviewed in phases one and two of the study, respectively. In phase one, while no prescription attained the global accuracy score (GAS) gold standard of 100%, 106 (29.0%) achieved the 80-100% mark. The patient 63 (17.2%), treatment 228 (62.3%), and prescriber 33 (9.0%) identifiers achieved an overall GAS range of 80-100%. Although the total GAS was not statistically significant (p=0.065), the date (p=0.041), patient (p=<0.001), treatment (p=0.022), and prescriber (p=<0.001) identifiers were statistically significant across the different hospitals. For phase two, the prevalence of MEs was 74 (56.1%), while that of pDDIs was 54 (40.9%). There was a statistically positive correlation between the occurrence of pDDI and number of medicines prescribed (r=0.211, P=0.015). A Low GAS indicates poor compliance with prescription writing guidelines and high prescription errors. Medication errors were observed at each phase of the medication use cycle, while clinically significant pDDIs were also reported. Thus, there is a need for training on prescription writing guidelines and medication errors.

End-to-end multimodal 3D imaging and machine learning workflow for non-destructive phenotyping of grapevine trunk internal structure

Quantifying healthy and degraded inner tissues in plants is of great interest in agronomy, for example, to assess plant health and quality and monitor physiological traits or diseases. However, detecting functional and degraded plant tissues in-vivo without harming the plant is extremely challenging. New solutions are needed in ligneous and perennial species, for which the sustainability of plantations is crucial. To tackle this challenge, we developed a novel approach based on multimodal 3D imaging and artificial intelligence-based image processing that allowed a non-destructive diagnosis of inner tissues in living plants. The method was successfully applied to the grapevine (Vitis vinifera L.). Vineyard’s sustainability is threatened by trunk diseases, while the sanitary status of vines cannot be ascertained without injuring the plants. By combining MRI and X-ray CT 3D imaging with an automatic voxel classification, we could discriminate intact, degraded, and white rot tissues with a mean global accuracy of over 91%. Each imaging modality contribution to tissue detection was evaluated, and we identified quantitative structural and physiological markers characterizing wood degradation steps. The combined study of inner tissue distribution versus external foliar symptom history demonstrated that white rot and intact tissue contents are key-measurements in evaluating vines’ sanitary status. We finally proposed a model for an accurate trunk disease diagnosis in grapevine. This work opens new routes for precision agriculture and in-situ monitoring of tissue quality and plant health across plant species.