Progress in quantifying validation data

Feature Select Validation (FSV) is a widely used validation method for data comparison. FSV provides a quantitative standard to describe the similarity between two sets of data. In this paper, the application of the FSV technique is extended to data optimization. The raw data obtained from simulations or measurements are often non-ideal for further processing. Several techniques, such as data perturbation, can be used to improve the data quality in certain aspects. However, after modifications the new data could be very different to the original one. Using FSV as an objective function for the optimization process is discussed in this paper, in an example of causality enforcement, to ensure the enforced casual data has the minimum deviations from the original data. The results demonstrate that the proposed approach in this paper is effective for data modification and optimization.

It has been found that the feature-selective validation (FSV) method may demonstrate inconsistencies in the results when applied to the comparison of zero-crossing datasets. This type of data is typical of time-domain-based electromagnetic compatibility validation. This paper investigates the source of this inconsistency and proposes a solution. The reason was investigated using a set of typical transient data, which was related to the derivation of the formulas of FSV. It is demonstrated that the problem can be alleviated by enhancing the definition of the offset difference measure. The resulting enhanced performance of FSV is assessed by comparing the results with visual assessment. It is demonstrated that the improvement increases the agreement between FSV prediction and visual assessment. Meanwhile, this modification has a very limited effect on the comparison of other data structures which do not cross the axis.

Objective validation and ranking of measurements and simulations may be done by methods, such as FSV (Feature Selective Validation). In this paper, FSV is used to compare two EMC-measurement results. Due to the noisy nature of this type of data, the FSV results are corrupted. The reasons are discussed and solutions are proposed to make FSV feasible in a broader area of applications. The final solution is a combination of denoising the data and changing the weight of the data to be in accordance with our visual interpretation.

The increasing demand for Power-over-Ethernet (PoE) applications in Internet of Things (IoT) infrastructure has led to a rise in the use of augmented cables as it is cost-effective. Augmented category 6 (Cat 6a) cable is now the standard for new installations requiring the aforesaid functions. Cat 6a cables for POE applications are required to be able to withstand the effects of repeated coiling they would be subjected to during installation. There is a paucity of literature on the effect of coiling on the impedance profiles of augmented cables across their length. The drawback of the available pieces of literature is that the effect of coiling is based on the frequency of operation. Examining the effect of coiling on the impedance profiles of Cat 6a cables across their length can help determine their physical integrity and aid fault location. Therefore, a method that can be used to examine the effect of coiling on impedance profiles of augmented cables across their length using the Feature Selective Validation (FSV) technique is provided. The ability of the FSV to accurately present the comparison between two data sets as a comprehensible output makes it better than other common methods. Three Cat 6a cables from different manufacturers were selected for the experiment. The Cat 6a cables were exposed to two rounds of coiling and uncoiling to imitate the stress anticipated from handling during installation. The FSV results revealed the cables with the lowest and highest impedance profile variations from the stress tests. The approach presented showed that it can be used to undertake an objective quantification of the effect of coiling on the impedance profiles of the cables across the length.

The performance of text classification can be affected by the choice of appropriate term weighting scheme as well as other parameters. The terminology supervised term weighting scheme has become popular in recent years, as it may provide discriminative representation in vector space for text documents belonging to different classes. A term weighting scheme generally consists of three factors, namely term frequency factor, collection frequency factor, and length normalization factor. The researchers mostly have been focused on developing new collection frequency factors in term weighting studies. However, the term frequency factor has an important role, especially in supervised term weighting. In this study, we extensively analyzed the effects of using different term frequency factors on seven supervised term weighting schemes. While six of these supervised term weighting schemes were applied in the previous studies in the literature, we derived one of them from an existing feature selection method and it was not used as a weighting method before. This analysis is performed using SVM and Roccio classifiers on two widely known benchmark datasets with different characteristics. Experimental results showed that modification of term frequency factor in supervised term weighting schemes increased the performance of almost all weighting schemes. Also, term weighting schemes using square root function-based term frequency factor (SQRT_TF) are more successful than the ones using term frequency (TF) and logarithmic function-based term frequency (LOG_TF) factors. TF term frequency factor seems as the least effective one among three different term frequency factors according to the experimental results and statistical analysis.

SummaryAccurate prediction of the solubility of chemical substances in solvents remains a challenge. The sparsity of high-quality solubility data is recognized as the biggest hurdle in the development of robust data-driven methods for practical use. Nonetheless, the effects of the quality and quantity of data on aqueous solubility predictions have not yet been scrutinized. In this study, the roles of the size and the quality of data sets on the performances of the solubility prediction models are unraveled, and the concepts of actual and observed performances are introduced. In an effort to curtail the gap between actual and observed performances, a quality-oriented data selection method, which evaluates the quality of data and extracts the most accurate part of it through statistical validation, is designed. Applying this method on the largest publicly available solubility database and using a consensus machine learning approach, a top-performing solubility prediction model is achieved.

Occupational noise-induced hearing loss (ONIHL) represents a prevalent occupational health condition, traditionally necessitating multiple pure-tone audiometry assessments. We have developed and validated a machine learning model leveraging routine haematological and biochemical parameters, thereby offering novel insights into the risk prediction of ONIHL. This study analysed data from 3297 noise-exposed workers in Shenzhen, including 160 ONIHL cases, with the data set divided into D1 (2868 samples, 107 ONIHL cases) and D2 (429 samples, 53 ONIHL cases). The inclusion criteria were formulated based on the GBZ49-2014 Diagnosis of Occupational Noise-Induced Hearing Loss. Model training was performed using D1, and model validation was conducted using D2. Routine blood and biochemical indicators were extracted from the case data, and a range of machine learning algorithms including extreme gradient boosting (XGBoost) were employed to construct predictive models. The model underwent refinement to identify the most representative variables, and decision curve analysis was conducted to evaluate the net benefit of the model across various threshold levels. Model creation data set and validation data sets: ONIHL. The prediction model, developed using XGBoost, demonstrated exceptional performance, achieving an area under the receiver operating characteristic curve (AUC) of 0.942, a sensitivity of 0.875 and a specificity of 0.936 on the validation data set. On the test data set, the model achieved an AUC of 0.990. After implementing feature selection, the model was refined to include only 16 features, while maintaining strong performance on a newly acquired independent data set, with an AUC of 0.872, a balanced accuracy of 0.798, a sensitivity of 0.755 and a specificity of 0.840. The analysis of feature importance revealed that serum albumin (ALB), platelet distribution width (PDW), coefficient of variation in red cell distribution width (RDW-CV), serum creatinine (Scr) and lymphocyte percentage (LYMPHP) are critical factors for risk stratification in patients with ONIHL. The analysis of feature importance identified ALB, PDW, RDW-CV, Scr and LYMPHP as pivotal factors for risk stratification in patients with ONIHL. The machine learning model, using XGBoost, effectively distinguishes patients with ONIHLamong individuals exposed to noise, thereby facilitating early diagnosis and intervention.

_ This article, written by JPT Technology Editor Chris Carpenter, contains highlights of paper OTC 31680, “Successful Development and Deployment of a Global ROP-Optimization Machine-Learning Model,” by Timothy S. Robinson, SPE, Exebenus, Peter Batruny, SPE, Petronas, and Dalila Gomes, SPE, Exebenus, et al. The paper has not been peer reviewed. Copyright 2022 Offshore Technology Conference. Reproduced by permission. _ Drilling rate of penetration (ROP) is influenced by many factors, both controllable and uncontrollable, difficult to distinguish with the naked eye. Thus, machine-learning (ML) models such as neural networks have gained momentum in the drilling industry. Previous models were field-based or tool-based, which affected accuracy outside of the trained field. The authors of the complete paper aim to develop one generally applicable global ROP model, reducing the effort needed to redevelop models for every application. Introduction The authors have identified a need for an ROP model that can recommend parameters in real time, which ideally requires a general ROP model that can be applied with low prediction errors. Formation properties are available in real time from logging tools; however, incorporating logging data into a global ROP model is challenging. A distance usually exists between the bit and logging tools where the properties of the formation drilled in real time at the bit are not available. While strides have been made in ML interpretation of logs, human interpretation is still needed. Equipment and Processes A deep neural network was used for modeling ROP. This model was queried as a black box within the scope of a constrained optimization algorithm tasked with identifying combinations of controllable drilling parameters expected to increase ROP. An overview of the ROP optimization system powered by the ROP estimation model is shown in Fig. 1. The ROP model was fitted using training and validation data sets composed of data from independent wells. Four additional wells were held in reserve for final testing purposes, most importantly for assessing the model’s ability to generalize to completely unseen data. For optimization, a three-stage conditional parameter sweep was used where the value expected to optimize ROP was found sequentially for each of the controllable parameters while fixing the values of the other variables. The optimizing value for each parameter was used as a fixed value for the subsequent optimization steps. This approach maintains the simplicity of a grid search and converges to a local optimum quickly because of the relatively small number of search iterations required under this formulation. A variety of well types with global geographical diversity was present in the data, using different downhole drives and bottomhole assemblies. Twenty-nine wells were used for training the ROP model, with an additional five wells used for validation and a further four wells reserved for holdout testing. No overlap existed between the wells constituting the training, validation, and holdout data sets. The drilling data sets were preprocessed by methods detailed in the complete paper. To ensure consistency across all operations, an average ROP was calculated independently based on depth measurements and their associated timestamps. This ROP calculation was used as the target variable for the ROP estimation model and for assessing its predictive performance. Training and validating the neural network for ROP estimation using data from a variety of independent wells is very useful for assessing model generalization. This technique is superior to the common approach of randomly splitting data sets because it minimizes information leakage between training and validation data.

The offshore industry has spent the last several years developing semisubmersible platforms capable of supporting both drilling and production activities. The production trees are located on top of the top tensioned risers (TTRs) on a Dry Tree Semisubmersible. A key challenge in the design of these vessels is to reduce the heave motion as much as possible to enable the use of state-of-the-art riser tensioners. A model test campaign was executed as part of the developmental program. The primary objective of this campaign was to improve the accuracy of the numerical tools to be used in the design process. Riser tensioners are typically hydro-pneumatic devices, with a nonlinear tension-stroke relationship. A riser tensioner was developed at model scale which had a similar nonlinear behavior to the prototype. Examining the effect of this tensioner on the global motions was an additional objective of this test campaign. The techniques used to model this nonlinear spring is described, and its effect on global motions investigated. A key challenge in model testing platforms intended for ultra-deep water (e.g. greater than 7000 ft) is the modeling of the mooring and riser system. The premise for the design of the model mooring system is 1.) maintain as best as possible the force-offset relationship of the mooring lines and 2.) be able to describe the model test configuration in the numerical tools to be used for global design. The near taut behavior of the prototype mooring system is modeled using heavy chain and a high-catenary mooring line.

Road inconsistency may cause dangerous driving experience that leads to carelessness while handling the vehicle. To determine the road inconsistency, development of models which are based on the 85th percentile of speed is adopted. The models which are taken into consideration are other geometric road characteristics such as superelevation, radius of curve, width of curve, tangent length, and road gradient that can help to minimize the risk of accidents at curve. To further analyze the effectiveness of these developed models, validation of the models using new set of data and comparing it with other established models is crucial. The validation process is conducted by calculating the mean squared error (MSE), mean absolute error (MAE), and mean absolute percentage error (MAPE). MSE value will indicate the differences between the empirical results with the predicted results, while MAE calculates the absolute difference between the empirical results and predicted results. MAPE evaluates the percentage errors between the empirical results with the predicted results. Small values of MSE, MAE, and MAPE is a proof that the models can predict good results.

The demonstrated technological feasibility of Sodium-cooled Fast Reactors (SFRs) makes them stand out among the other reactor concepts proposed by Generation IV International Forum (GIF) for short-term deployment. The availability of reliable computational tools in support of safety analyses and plant simulations under complex transient scenarios is essential to assure SFR’s compliance with the highest safety goals.Answering this need, a multi-physics three-dimensional core and system model is being developed to enable a more detailed representation of the physics of the plant and to anticipate more accurately plant behaviour, even under wider three-dimensional scenarios, such as asymmetric transients. The coupling will be performed using the U.S.NRC system codes TRACE-PARCS, modified to simulate more accurately when using sodium as coolant.The publicly available end-of-life tests conducted in the French SFR Phenix were chosen as baseline to perform a first validation of the computational model. The development of the tool started with a three-dimensional thermal-hydraulic nodal system of Phenix using the TRACE system code.The system simulates the Phenix end-of-life natural circulation test and the result have been compared with published experimental and benchmark results. The main physical phenomena of the 3 phases of the transient (rise in temperature in the low part of the reactor vessel, establishment of natural convection and subsequent cooling of the lower and upper part of the vessel) are predicted by the developed nodal system. More specifically, the analysis of parameters such as Intermediate Heat Exchangers (IHX), primary pumps and core temperatures, shows that the developed system is able to predict and study natural convection phenomena in Phenix-type reactors.The three-dimensional nodal system is able to clearly illustrate the existing thermal stratification in the hot pool, which is neglected by one-dimensional systems and enables the modelling of thermal hydraulic asymmetric behaviour, as it is shown by the uneven flow distribution in Phenix’s primary IHXs as they are asymmetrically located in the reactor vessel.

<p><strong>Description: </strong></p> <p>Community-weighted mean traits from tree species that make up more than 80% basal area in plots in selectively logged forest at SAFE and in old-growth forest in Danum Valley and Maliau Basin. Sampled during the BALI project traits campaign</p> <p><strong>Project: </strong>This dataset was collected as part of the following SAFE research project: <a href="https://www.safeproject.net/projects/project_view/55"><strong>Biodiversity and land-use impacts on tropical ecosystem function (BALI): Quantifying functional trait distributions across the disturbance gradient</strong></a></p> <p><strong>Funding: </strong>These data were collected as part of research funded by:</p> <ul> <li>NERC (Standard grant, NE/K016253/1)</li> </ul> <p>This dataset is released under the CC-BY 4.0 licence, requiring that you cite the dataset in any outputs, but has the additional condition that you acknowledge the contribution of these funders in any outputs.</p> <p> </p> <p><strong>Permits: </strong>These data were collected under permit from the following authorities:</p> <ul> <li>Sabah Biodiversity Centre (Research licence JKM/MBS.1000-2.2(385))</li> </ul> <p> </p> <p><strong>XML metadata: </strong>GEMINI compliant metadata for this dataset is available <a href="https://www.safeproject.net/datasets/xml_metadata?id=3247602">here</a></p> <p><strong>Files: </strong>This dataset consists of 3 files: Both_CWM_traits.xlsx, CSP_protocol_Chlorophyll_and_Carotenoids.pdf, CSP_protocol_Phenols_Tannins_Analysis.pdf</p> <p><strong>Both_CWM_traits.xlsx</strong></p> <p>This file contains dataset metadata and 1 data tables:</p> <ol> <li> <p><strong>CMW_traits</strong> (described in worksheet CMW_traits)</p> <p>Description: Community-weighted mean traits of tree in plots in SAFE , Danum Valley and Maliau Basin sampled during the BALI project traits campaign</p> <p>Number of fields: 36</p> <p>Number of data rows: 8</p> <p>Fields:</p> <ul> <li><strong>location</strong>: Location (Field type: Categorical)</li> <li><strong>forest_type</strong>: Forest type (Field type: Categorical)</li> <li><strong>forestplots_name</strong>: Plot name coherent with forestplots database (Field type: ID)</li> <li><strong>plot_name_trait_campaign</strong>: Plot name used during the BALI trait campaign (Field type: ID)</li> <li><strong>CWM_total_K_mg.g_log</strong>: CWM foliar potassium concentration in mg per g dry weight, log transformed data (Field type: Numeric)</li> <li><strong>CWM_total_Ca_mg.g_log</strong>: CWM foliar calcium concentration in mg per g dry weight, log transformed data (Field type: Numeric)</li> <li><strong>CWM_total_Mg_mg.g_log</strong>: CWM foliar magnesium concentration in mg per g dry weight, log transformed data (Field type: Numeric)</li> <li><strong>CWM_total_P_mg.g_log</strong>: CWM foliar phosporus concentration in mg per g dry weight, log transformed data (Field type: Numeric)</li> <li><strong>CWM_N_perc</strong>: CWM foliar nitrogen concentration (Field type: Numeric)</li> <li><strong>CWM_15N_per_mil</strong>: CWM foliar 15N isotope concentration (Field type: Numeric)</li> <li><strong>CWM_C_perc</strong>: CWM foliar carbon concentration (Field type: Numeric)</li> <li><strong>CWM_13C_per_mil</strong>: CWM foliar 13C isotope concentration, expressed relative to Vienna Pee Dee Belemnite (VPDB) as δ13C in units of per mil [‰] (Field type: Numeric)</li> <li><strong>CWM_DR</strong>: CWM dark respiration measured on leaf attached to a branch that is cut under water and remains in water (Field type: Numeric)</li> <li><strong>CWM_Asat</strong>: CWM light-saturated net photosynthesis measured on leaf attached to a branch that is cut under water and remains in water. (Field type: Numeric)</li> <li><strong>CWM_Amax</strong>: CWM maximum photosynthetic capacity measured on leaf attached to a branch that is cut under water and remains in water. (Field type: Numeric)</li> <li><strong>CWM_leaf_thickness_mm_log</strong>: CWM thickness of leaf, log transformed data (Field type: Numeric)</li> <li><strong>CWM_dry_weight_mg_log</strong>: CWM leaf oven-dried weight, log transformed data (Field type: Numeric)</li> <li><strong>CWM_LA_mm2_log</strong>: CWM leaf area (LA) calculated from fresh leaves collected from branches, scanned immediately, log transformed data (Field type: Numeric)</li> <li><strong>CWM_SLA_mm2_mg</strong>: CWM specific leaf area (SLA) determined as the one-sided area of a fresh leaf, divided by its oven-dry mass. (Field type: Numeric)</li> <li><strong>CWM_LDMC_mg.g</strong>: CWM leaf dry-matter content (LDMC) is the oven-dry mass (mg) of a leaf, divided by its water-saturated fresh mass (g) mg g–1 (Field type: Numeric)</li> <li><strong>CWM_chla_mg.g</strong>: CWM foliar chlorophyll a content (Field type: Numeric)</li> <li><strong>CWM_chlb_mg.g</strong>: CWM foliar chlorophyll b content (Field type: Numeric)</li> <li><strong>CWM_carot_mg.g</strong>: CWM foliar carotenoids content (Field type: Numeric)</li> <li><strong>CWM_Fp_N_mm_log</strong>: CWM force to punch leaf, dividing the observed force (N) required to puncture the leaf lamina by the circumference of the instrument's rod, log transformed data (Field type: Numeric)</li> <li><strong>CWM_specific_Fp_log</strong>: CWM specific force to punch (Fp divided by lamina thickness), log transformed data (Field type: Numeric)</li> <li><strong>CWM_WD_B</strong>: CWM branch wood density from branch segment with bark (Field type: Numeric)</li> <li><strong>CWM_hemicellulose_perc</strong>: CWM foliar hemicellulose concentration (Field type: Numeric)</li> <li><strong>CWM_cellulose_perc</strong>: CWM foliar cellulose concentration (Field type: Numeric)</li> <li><strong>CWM_lignin_recalcitrants_perc</strong>: CWM foliar lignin and recalcitrants concentration (Field type: Numeric)</li> <li><strong>CWM_total_tannin_mg.g</strong>: CWM foliar tannin concentration (Field type: Numeric)</li> <li><strong>CWM_total_phenol_mg.g</strong>: CWM total foliar phenol concentration (Field type: Numeric)</li> <li><strong>CWM_chla_mg.mm2</strong>: CWM foliar chlorophyll a content expressed on leaf area basis (Field type: Numeric)</li> <li><strong>CWM_chlb_mg.mm2</strong>: CWM foliar chlorophyll b content expressed on leaf area basis (Field type: Numeric)</li> <li><strong>CWM_carot_mg.mm2</strong>: CWM foliar carotenoids content expressed on leaf area basis (Field type: Numeric)</li> <li><strong>CWM_N_mg.mm2</strong>: CWM foliar nitrogen concentration expressed on leaf area basis (Field type: Numeric)</li> <li><strong>CWM_total_P_mg.mm2.l</strong>: CWM foliar phosporus concentration expressed on leaf area basis, log transformed data (Field type: Numeric)</li> </ul> </li> </ol> <p><strong>CSP_protocol_Chlorophyll_and_Carotenoids.pdf</strong></p> <p>Description: Methodology of chlorophyll and carotenoids analysis, Carnegie Spectranomics protocol: https://drive.google.com/file/d/0B58dyv8L3FpMdGw0QWtiZElHQzQ/view</p> <p><strong>CSP_protocol_Phenols_Tannins_Analysis.pdf</strong></p> <p>Description: Methodology of phenols and tannins analysis, Carnegie Spectranomics protocol: https://drive.google.com/file/d/0B58dyv8L3FpMcTBHblQwRHdyRE0/view</p> <p><strong>Date range: </strong>2014-05-01 to 2018-09-01</p> <p><strong>Latitudinal extent: </strong>4.5000 to 5.0700</p> <p><strong>Longitudinal extent: </strong>116.7500 to 117.8200</p>

To be an effective platform for performance-sensitive real-time and embedded applications, off-the-shelf CORBA middleware must preserve communication-layer quality of service (QoS) properties to applications end-to-end. However, the standard CORBA’s GIOP/IIOP interoperability protocols are not well suited for applications that cannot tolerate the message footprint size, latency, and jitter associated with general-purpose messaging and transport protocols. It is essential, therefore, to develop standard pluggable protocols frameworks that allow custom messaging and transport protocols to be configured flexibly and used transparently by applications. This paper provides three contributions to research on pluggable protocols frameworks for performance-sensitive communication middleware. First, we outline the key design challenges faced by pluggable protocols developers. Second, we describe how TAO, our high-performance, real-time CORBAcompliant ORB, addresses these challenges in its pluggable protocols framework. Third, we present the results of benchmarks that pinpoint the impact of TAO’s OO design on its endto-end efficiency, predictability, and scalability. Our results demonstrate how applying optimizations to communication middleware can yield highly flexible/reusable designs and highly efficient/predictable implementations. In particular, the overall round-trip latency of a TAO two-way method invocation using the standard inter-ORB protocol and using a commercial, off-the-self Pentium II Xeon 400 MHz workstation running in loopback mode is 125 secs. The ORB middleware accounts for approximately 48% or 60 secs of the total round-trip latency. These results illustrate that (1) communication middleware performance is largely This work was supported in part by Boeing, DARPA contract 9701516, GDIS, NSF grant NCR-9628218, Nortel, Siemens, and Sprint. an implementation detail and (2) the next-generation of optimized, standards-based CORBA middleware can replace ad hoc and proprietary solutions. Subject areas: Frameworks; Design Patterns; Distributed and Real-Time Systems

In this study, measurements inside the fuselage of an unmanned air vehicle (UAV) are conducted using a novel double-loaded loop probe. The characterization and evaluation of electromagnetic interference (EMI) within VAVs is a main research topic and requires state-of-the-art measurement methodologies. The developed probe is capable of obtaining accurate measurements as commercial reference E-Field broadband probes, introducing new advantages based on the reduction of the probe's electronics and the availability of the full time-domain data. Allowing to compute simultaneously the electric and the magnetic field and to measure high-amplitude electromagnetic pulses. The laser-probe works together with multi-channel full-time domain system computing the electromagnetic fields using an oscilloscope. Regarding the double-loaded loop probe characterization and validation, it has been carried out by comparing the results with different validation methods, like Feature Selective Validation Method and the Integrated Error against Logarithmic Frequency.

The crop growth model DSSAT (Decision Support Systems for Agrotechnology Transfer) used to simulate the weather parameters impacts on crop growth and yield. The experiment was conducted on Wheat crop in North Eastern Plain Zone of India. The main objective of the study was to evaluate wheat phenological stages and yield in major wheat growing zone of India. Among the parameters of the crop Yield and Days of flowering has been used for calibration and validation purpose. For the study CERES-Wheat model was used for the calibration and validation. Different data sets were used for the calibration and validation of the model. Methods of deviation statistics like Index of Agreement (d), RMSE and NRMSE are used to measure the efficiency of the model. For Yield it shows (d), RMSE and NRMSE values 0.961, 199.25 and 5.17 respectively and for Days of flowering it shows (d), (RMSE) and NRMSE values are 0.970, 4.37 and 4.35 respectively. Study results shows that model is adequate to simulate the effects of climate change on wheat yield in North Eastern Plain Zone of India that are free from all pests. The model may also be used to improve and evaluate the current practices of wheat growth management to enhance wheat production.