Poor Interpretation Research Articles

Estimating the Energy Consumption and Driving Range of Electric Vehicles with Machine Learning

The Data-driven methods have been widely used in the SOC, SOH and energy estimation of electric vehicles, and they are recognized as the most promising approaches. However, the popular machine learning methods used for electric vehicles are often “black boxes” which result in the poor interpretation of the model. In this paper, a highly efficient gradient boosting decision tree (LGBM) is proposed to accurately estimate the driving range of electric vehicle. In this model, the feature importance scores are provided to discover the relationship. In addition, the proposed LGBM-T model is capable of generalizing the abstractions by taking into account the key features of time and temperature. Experimental results illustrate that the proposed LGBM-T algorithm is able to reproduce the driving mileage trajectory, with a low mean absolute error (MAE) bounded by 1.681% on real-world vehicles under complex operating conditions. The availability of this algorithm is further corroborated by comparing to the support vector machines (SVM) based estimator.

Hard to Swallow Results.

The American Neurogastroenterology and Motility Society (ANMS) proposed quality measures (QMs) for performance and interpretation of esophageal manometry (EM). We implemented a quality improvement (QI) study at a large community hospital to assess and improve procedural adherence and interpretation of EM studies based on the ANMS QMs using the Chicago Classification 3.0 (CC) Guidelines. For pre-intervention, three motility independent reviewers reinterpreted 60 EM studies conducted by community gastroenterologists without Tier II-III motility training from October to December 2018 for compliance with pre-procedural, procedural, and data interpretation ANMS QMs. In December 2018, we developed a pre-procedural form, educated nurses on EM procedural compliance, and provided preliminary pre-intervention results to gastroenterologists along with literature utilizing the CC 3.0 Guidelines. For post-intervention, we reinterpreted 54 EM studies from January to August 2019 and investigated whether they met QMs for data interpretation with respect to the CC Guidelines and resulted in appropriate treatment. We found a statistically significant improvement in procedural compliance among nursing staff for 30s of swallows (76% post-intervention versus 12% pre-intervention, p < 0.001) and 7 evaluable swallows (94% post-intervention versus 53% pre-intervention, p < 0.001). However, quality metrics within data interpretation by physicians post-intervention showed mixed results. An incorrect diagnosis was made in 50% (n = 27)) of studies with 72% (n = 39) having at least one missing item based on the CC. The most missed diagnosis was fragmented peristalsis (30%, n = 29). Among the 39% (n = 21) of surgery referrals, 24% (n = 5) were incorrectly referred. Our study shows poor data interpretation by community gastroenterologists without formal motility training despite adequate performance by nursing staff. This further supports the need for a national ANMS certification process for formal HRM education.

Unbiased Fuzzy Estimators in Fuzzy Hypothesis Testing

In this paper, we develop fuzzy, possibilistic hypothesis tests for testing crisp hypotheses for a distribution parameter from crisp data. In these tests, fuzzy statistics are used, which are produced by the possibility distribution of the estimated parameter, constructed by the known from crisp statistics confidence intervals. The results of these tests are in much better agreement with crisp statistics than the ones produced by the respective tests of a popular book on fuzzy statistics, which uses fuzzy critical values. We also present an error that we found in the implementation of the unbiased fuzzy estimator of the variance in this book, due to a poor interpretation of its mathematical content, which leads to disagreement of some fuzzy hypotheses tests with their respective crisp ones. Implementing correctly this estimator, we produce test statistics that achieve results in hypotheses tests that are in much better agreement with the results of the respective crisp ones.

Framework of airfoil max lift-to-drag ratio prediction using hybrid feature mining and Gaussian process regression

The maximum lift-to-drag coefficient of an airfoil directly affects the aerodynamic performance of wind turbine. Machine learning methods are known for being really effective in helping to predict this parameter in a faster and more accurate way. So far, the majority of related studies have focused on the use of artificial neural networks to make this prediction, but this model has issues with its poor interpretation and the confidence level of its results was unclear. In this paper, a novel framework is proposed, involving the Gaussian process regression and a hybrid feature mining process. The aim is to use the new framework to evaluate the maximum lift-to-drag ratio of given airfoils under a turbulent flow condition, where the Reynolds number is around 100,000. The feature mining process here designed contains a hybrid feature pool that comprises various geometric characters, and a hybrid feature selector that can assist the prediction performance and make it better. Based on the airfoil dataset of the University of Illinois at Urbana-Champaign that contains a total of 1432 profiles, a comparative analysis was conducted. The results showed that the current framework can provide a more accurate estimate than parallel models in both single-point and interval aspects of view. Noticeably, the model reached an overall precision of 95.2% and 94.1% on training and testing sets, respectively. Moreover, the simplicity and the confidence reference from the model output were further illustrated with a case study, which also verified that how it can serve real engineering application.

Analysing wideband absorbance immittance in normal and ears with otitis media with effusion using machine learning

Wideband Absorbance Immittance (WAI) has been available for more than a decade, however its clinical use still faces the challenges of limited understanding and poor interpretation of WAI results. This study aimed to develop Machine Learning (ML) tools to identify the WAI absorbance characteristics across different frequency-pressure regions in the normal middle ear and ears with otitis media with effusion (OME) to enable diagnosis of middle ear conditions automatically. Data analysis included pre-processing of the WAI data, statistical analysis and classification model development, and key regions extraction from the 2D frequency-pressure WAI images. The experimental results show that ML tools appear to hold great potential for the automated diagnosis of middle ear diseases from WAI data. The identified key regions in the WAI provide guidance to practitioners to better understand and interpret WAI data and offer the prospect of quick and accurate diagnostic decisions.

Early stopping technique using a genetic algorithm for calibration of an urban runoff model

ABSTRACT Identifying suitable parameter sets for use in catchment modelling remains a critical issue in hydrology. This paper describes an early stopping technique (EST) for use during calibration of a multi-parameter urban catchment modelling system. The proposed method takes advantage of MODE and lower confidence limit (LCL) functions in statistical analysis of spanning set of objective function values. The paper also introduces a monitoring process and regularization techniques to avoid under/overfitting during the calibration and to enhance generalisation performance. The methodology is assessed using SWMM and linked with a Genetic Algorithm for calibration of a Powells Creek catchment model in Sydney, Australia. Results demonstrate that the statistical spanning set analysis approach overcomes issues of poor interpretation and deterioration in the model’s generalisation properties. By stopping early, the calibration process avoided overfitting; this was indicated by too closely fitting to the calibration dataset and a failure to fit to the monitoring dataset.

A Novel Approach For Diagnosis Of Dermatologic Diseases Based On Multi-Objective Clustering Using Particle Swarm Optimization

The stratification of skin diseases plays a major role in enabling effective and customized medicine. An important task in the stratification of skin diseases is to discover subtypes of diseases for effective treatment. To achieve this goal, research into cluster algorithms for the stratification of skin diseases has attracted the attention of both scholars and the medical community in recent decades. However, cluster algorithms suffer from realistic limitations such as experimental sounds, high dimension and poor interpretation. In particular, cluster algorithms usually determine the quality of clusters with only one internal evaluation operation. Unfortunately, it is obvious that one internal evaluation operation is difficult to create and strong for all datasets. Therefore, this article proposes a novel of many descriptive frameworks called a multi objective cluster algorithm with a quick search and finding the density of peaks to deal with these limitations altogether. In the proposed framework, the variable component of the candidate is developed under many objectives to select properties and estimate the density of the cluster automatically. To guide the development of multi-objective, two cluster value indices are used, including the Calinski-Harabasz index and the Davies-Bouldin index. The clustering is performed with the help of a k-means cluster by finding the best clusters using particle optimization. PSO will solve the multi-objective to determine the best cluster. Here, the proposed method will test on the dermatology dataset from UCI repository using MATLAB R2020a, under windows10 environment. Then, the proposed method performance will be evaluating using the cluster evaluation indices.

Documenting Maternal Deaths: Implications for National Statistics and Research.

The rate of women in the United States dying of pregnancy-related causes has significantly increased in less than two decades, making maternal mortality a significant public health issue. There are prominent racial disparities within these rising rates; non-Hispanic Black women are three times more likely to die from pregnancy-related causes than white women (The MITRE Corporation, 2019). Flaws in data collection lead to inaccurate data analyses, poor interpretation of community needs, and ultimately contribute to pregnant women not being given the care and treatment required to prevent maternal death.

TRANSLATION AND TRANSCULTURAL ADAPTATION OF THE PATIENT MEASURE OF SAFETY (PMOS) QUESTIONNAIRE TO BRAZILIAN PORTUGUESE

ABSTRACT Objective to translate and culturally adapt the Patient Measure of Safety questionnaire to Brazilian Portuguese. Method a transcultural adaptation study conducted in six stages: translation, synthesis, back-translation, review by experts committee, pre-test, and presentation of the documentation of the entire process to the authors of the instrument. Results in the initial translation and cultural adaptation stage, two versions of the questionnaire were generated. The divergences between both versions and other suggestions were discussed, and the decisions were made by consensus, thus creating a single version. In the back-translation stage, there were no significant differences between the versions and the original instrument. The assessment of the semantic, idiomatic, cultural and conceptual equivalences of the Patient Measure of Safety items was performed by a committee of experts from different Brazilian regions. The results of the content validity index were above 0.9 for most of the items. The pre-test was conducted with 30 patients. The mean time for the application of the questionnaire was 31.9 minutes. In relation to the understanding of the items by the patients, a regular or poor interpretation was identified only for 6 of the 44 items, which were modified. Conclusion the “Questionário de Avaliação da Segurança pelo Paciente”, name given to the translated and transculturally adapted version, resulted from a thoughtful process, presenting consistency in the equivalence of the translation and constituting an applicable instrument understood by the target population.

A Review of Methods to Determine Viability, Vitality, and Metabolic Rates in Microbiology.

Viability and metabolic assays are commonly used as proxies to assess the overall metabolism of microorganisms. The variety of these assays combined with little information provided by some assay kits or online protocols often leads to mistakes or poor interpretation of the results. In addition, the use of some of these assays is restricted to simple systems (mostly pure cultures), and care must be taken in their application to environmental samples. In this review, the necessary data are compiled to understand the reactions or measurements performed in many of the assays commonly used in various aspects of microbiology. Also, their relationships to each other, as metabolism links many of these assays, resulting in correlations between measured values and parameters, are discussed. Finally, the limitations of these assays are discussed.

Artificial Intelligence for Surgical Safety: Automatic Assessment of the Critical View of Safety in Laparoscopic Cholecystectomy Using Deep Learning.

To develop a deep learning model to automatically segment hepatocystic anatomy and assess the criteria defining the critical view of safety (CVS) in laparoscopic cholecystectomy (LC). Poor implementation and subjective interpretation of CVS contributes to the stable rates of bile duct injuries in LC. As CVS is assessed visually, this task can be automated by using computer vision, an area of artificial intelligence aimed at interpreting images. Still images from LC videos were annotated with CVS criteria and hepatocystic anatomy segmentation. A deep neural network comprising a segmentation model to highlight hepatocystic anatomy and a classification model to predict CVS criteria achievement was trained and tested using 5-fold cross validation. Intersection over union, average precision, and balanced accuracy were computed to evaluate the model performance versus the annotated ground truth. A total of 2854 images from 201 LC videos were annotated and 402 images were further segmented. Mean intersection over union for segmentation was 66.6%. The model assessed the achievement of CVS criteria with a mean average precision and balanced accuracy of 71.9% and 71.4%, respectively. Deep learning algorithms can be trained to reliably segment hepatocystic anatomy and assess CVS criteria in still laparoscopic images. Surgical-technical partnerships should be encouraged to develop and evaluate deep learning models to improve surgical safety.

A Reconsideration of Ştefania Mărăcineanu’s Measurements of Polonium-210’s Half-Life: Understanding Her Claim to the Discovery of Artificial Radioactivity

I re-examine the raw data of the measurements of the half-life of 210Po from the Romanian physicist Ştefania Mărăcineanu’s doctoral thesis, performed at the Institut du Radium, 1921–1923, under the supervision of Marie Curie. The half-life values reported in the thesis show relatively large divergences and a possible dependence on the (metallic) support on which the Po source was deposited. These findings influenced Mărăcineanu’s subsequent independent research, and later compelled her to claim priority for the discovery of artificial radioactivity. The present analysis of these data, performed with the least-squares method, certifies the outstanding accuracy of the experimental measurements by providing values with good agreement between the different series of measurements and an average value that is close to the currently adopted half-life value of this isotope. On the other hand, this analysis changes our perspective by showing that the rudimentary procedure Mărăcineanu used to processing the data introduced errors in her reported values, which favored a poor interpretation of the results.

A Body Condition Score for Crocodilians

Body condition (BC) has been used extensively to evaluate fitness in animals. In traditional studies of crocodiles, the paradigm of evaluating BC with the Fulton index and interpreting the results with quartiles is predominant. However, the wide variety of indices available provides a diversity of tools with which BC can be interpreted in multiple ways. In this study, three indices based on the function of length and weight were evaluated: the Fulton index (K), relative condition index (Kn), and scaled mass index (SMI). The body condition score (BCS) index was also adapted. This was performed as a clinical evaluation of specific morpho-anatomical points. The Fulton index presented a strong relationship with corporal size that generates poor interpretation, scoring low BC in small individuals and high BC in large individuals. This problem does not occur in Kn, SMI nor BCS. SMI and Kn are difficult to interpret, but this is normally conducted by quartiles, generating ambiguous and potentially misleading explanations. The use of BCS avoids these complications because its direct and simple evaluation acts to convert the abstract numbers of the indices to a clinical reality.

Study on quantitative detection of turbid solution components based on ellipse fitting.

It is of great significance to detect the components of turbid solutions using hyperspectral imaging technology in analytical chemistry. To solve the problems including complex computations and poor interpretations in previous researches, this study proposed a novel quantitative detection model based on contour extraction and ellipse fitting for turbid solutions. A wedge-shaped sample reservoir was firstly designed to increase the dimensions of light spot information. Subsequently, the visual features of the spot were extracted from their hyperspectral images using ellipse fitting. Partial least squares regression was performed for the concentrations of Intralipid-20% and the ellipse eigenvectors, and it gave a good prediction ability with the correlation coefficient (Rp) of 0.98 and the root-mean-square error (RMSEP) of 0.07%. Experimental results indicate that ellipse fitting model shows excellent performances in more reasonable interpretation, better stability, less computation, clearer visualization effect and lower requirements for data acquisition process, compared with conventional light intensity model and abstract textural features model. It can be concluded that using ellipse fitting method based on hyperspectral imaging to detect compositions of complex mixed solutions is a potential progress.

WRITTEN AND ORAL TRANSLATION CHALLENGES AND SOLUTIONS IN KOSOVO

Despite the fact that thousands of people nowadays work and earn their living from translation and/ or interpreting, the widely spread opinion is that one does not need any special training in order to become a translator or an interpreter. Nevertheless, people who deal with translation and interpreting are aware that this assumption does not hold. The fact that translation is not just a linguistic procedure but is socially constructed and oriented just like language itself, is gradually accepted. Hence, translators are becoming fully aware that training is necessary just as in any other profession if one wants to keep up with global changes. One of the major challenges in translation and interpretation in Kosovo is the inadequate translation quality of texts as well as poor simultaneous and consecutive interpreting during conferences, training, and other important events. However, in the case of written translations, the translator has the chance to intervene, correct, and proofread the text through proofreaders, which is not a touch that can be done during oral interpretation. This does not mean that interpretation has any lower stakes; poor oral interpretation can even result in the failure of an event, e.g. interlocutors may misunderstand each other or convey an inaccurate intellectual or professional picture of the speakers. Therefore, this paper explores the challenges and solutions of translation in Kosovo, in general, and oral interpretation, in particular.

A Theological Analysis of Issues Arising from the Christian Asante Chief’s Relationship with the Black Stool (Akonwa Tuntum)

One of several issues of contention that have created a gulf between Christianity and the traditional Asante chieftaincy institution is the chief’s relationship with the black stool. The general perception of Christians is that the black stool is an object of worship, it is demonic and should be avoided by Christian chiefs. This paper theologically analyzes the issues of contention in the Christian chief’s relationship with the black stool and presents a Christian response to guide them. This is an empirical qualitative study, and it uses a phenomenological approach to understand the phenomena related to the issues of contention in the Christianity-chieftaincy encounter. The method of obtaining information included interviews of fifty (50) Christian Asante chiefs, a representative group obtained by the purposeful sampling method. Information was also obtained through personal observation of some of the traditional religious rituals they perform. The issues of contention were then examined in the light of scripture in order to help bridge the seeming gulf between Asante chieftaincy and Christianity. This research has established the fact that the black stool is not a demonic object. In fact, the issues of contention in the Christianity and chieftaincy encounter, relating to the black stool, have arisen not only from a lack of understanding and proper appreciation of the traditional rituals but also from lack of proper understanding and poor interpretation of scriptural texts used in relating the gospel to the chieftaincy institution. Keywords: Tradition, ritual, Christianity, Black stool (Akonwa Tuntum), worship.

A Theological Analysis of Issues Arising from the Christian Asante Chief’s Relationship with the Black Stool (Akonwa Tuntum)

One of several issues of contention that have created a gulf between Christianity and the traditional Asante chieftaincy institution is the chief’s relationship with the black stool. The general perception of Christians is that the black stool is an object of worship, it is demonic and should be avoided by Christian chiefs. This paper theologically analyzes the issues of contention in the Christian chief’s relationship with the black stool and presents a Christian response to guide them. This is an empirical qualitative study, and it uses a phenomenological approach to understand the phenomena related to the issues of contention in the Christianity-chieftaincy encounter. The method of obtaining information included interviews of fifty (50) Christian Asante chiefs, a representative group obtained by the purposeful sampling method. Information was also obtained through personal observation of some of the traditional religious rituals they perform. The issues of contention were then examined in the light of scripture in order to help bridge the seeming gulf between Asante chieftaincy and Christianity. This research has established the fact that the black stool is not a demonic object. In fact, the issues of contention in the Christianity and chieftaincy encounter, relating to the black stool, have arisen not only from a lack of understanding and proper appreciation of the traditional rituals, but also from lack of proper understanding and poor interpretation of scriptural texts used in relating the gospel to the chieftaincy institution.

Reliable Euler deconvolution estimates throughout the vertical derivatives of the total-field anomaly

We propose a novel methodology to select reliable Euler deconvolution estimates throughout the vertical derivatives of the total-field anomaly, grounded on the capability of this quantity to locate anomalies due to its higher signal decay with distance. In applying Euler deconvolution to a small moving-data window, we compute the standard deviation of the vertical derivatives of the total-field anomaly for each data window. Then, we define the reliable source-location estimates as those estimates that are obtained by using the data windows with the largest standard deviations of the vertical derivatives of the total-field anomaly. For all tentative values of the structural index (SI), the reliable estimates with tight clustering define the correct SI and the mean of these estimates define the source position. We compared our methodology to select reliable Euler source-position estimates with two available methodologies in the literature based on the rejection criteria of data amplitude and of depth uncertainty. We conducted tests on synthetic noise-corrupted data to investigate the sensitivity of our method to deal with the presence of: i) an additive nonlinear background that simulates a regional field; ii) interfering anomalies with distinct amplitudes; iii) weak-, mid-, and strong-interfering anomalies; and iv) distinct noise levels. Most of tests in the sensitivity analysis shows that our methodology to select reliable Euler source-position estimates yielded better interpretation of the simulated magnetic sources than the methodology based on the rejection criteria of data amplitude and of depth uncertainty. The only exception was the tests with high noise levels in which the reliable Euler estimates selected either by our method or by the rejection criteria yielded poor interpretations. Applications to a real aeromagnetic survey from southern Brazil interpreted an isolated plug intrusion over the Anitápolis anomaly and a swarm of shallow-seated dikes with northwest-southeast trend over the Paranaguá Terrane.

Optimized contrast enhancement for tumor detection

AbstractMagnetic resonance imaging (MRI) is a real assistant for doctors. It provides rich information about anatomy of human body for precise diagnosis of a diseases or disorder. But it is quite challenging to extract relevant information from low contrast and poor quality MRI images. Poor visual interpretation is a hindrance in correct diagnosis of a disease. This creates a strong need for contrast enhancement of MRI images. Study of existing literature shows that conventional techniques focus on intensity histogram equalization. These techniques face the problems of over enhancement, noise and unwanted artifacts. Moreover, these are incapable to yield the maximum entropy and brightness preservation. Thus ineffective in diagnosis of a defect/disease such as tumor. This motivates the authors to propose the contrast enhancement model namely optimized double threshold weighted constrained histogram equalization. The model is a pipelined approach that incorporates Otsu's double threshold method, particle swarm optimized weighted constrained model, histogram equalization, adaptive gamma correction, and Wiener filtering. This algorithm preserves all essential information recorded in an image by automatically selecting an appropriate value of threshold for image segmentation. The proposed model is effective in detecting tumor from enhanced MRI images.

The Use of Machine Learning Tools to Analyse Wideband Absorbance Immittance in Normal and Ears With Otitis Media With Effusion

Background: Wideband Absorbance Immittance (WAI) has been available for more than a decade, however its clinical use still faces the challenges of limited understanding and poor interpretation of WAI results. This study aimed to develop Machine Learning (ML) tools to identify the WAI absorbance characteristics across different frequency-pressure regions in the normal middle ear and ears with otitis media with effusion (OME) to enable diagnosis of middle ear conditions automatically. Methods: A total of 672 sets of WAI sample data (423 normal middle ears and 249 ears with OME) were collected using the Titan IMP440. Data analysis included pre-processing of the WAI data, statistical analysis and classification model development, together with significant region extraction from the 2D frequency-pressure WAI images. Findings: Statistical analysis at each frequency-pressure point showed 88% of the data points to have significant differences in absorbance values between normal ears and ears with OME. The performance of the examined classifiers to automatically diagnose the OME and normal cases showed the accuracy at around 80%. Feature selection using RF classifiers and tests of statistical significance identified an area of importance at frequencies between 1090Hz to 2310 Hz and pressures from -40 to +90 daPa from the 2D frequency-pressure WAI images. Interpretation: ML tools appear to hold great potential for the automated diagnosis of middle ear diseases from WAI data. The identified key regions in the WAI provide guidance to practitioners to better understand and interpret WAI data and offer the prospect of quick and accurate diagnostic decisions. Funding Statement: This work is supported by Ser Cymru III Enhancing Competitiveness Infrastructure Award (MA/KW/5554/19), Great Britain Sasakawa Foundation (5826), Cardiff Metropolitan University Research Innovation Award and The Global Academies Research and Innovation Development Fund. Declaration of Interests: None declared. Ethics Approval Statement: The study was approved by Cardiff School of Sport and Health Sciences under the Cardiff Metropolitan University Ethics Framework (Ethical reference number: Sta-3013).