Automated Analysis Method Research Articles

The effect of complex extra-furnace treatment of metal melts on the formation of non-metallic inclusions in large-sized ingots

Abstract The article presents the results of studying non-metallic inclusions (NI) after extra-furnace treatment of the 13Cr9Mo2Co1NiVNbNB steel melt to produce large-sized ingots. The objects of the study were laboratory samples melted in a semi-industrial induction furnace with the capacity of 20 tons (the first batch), and samples obtained after melting in an electric arc furnace with the capacity of 120 tons, followed by modification and double vacuuming (the second batch).
Previously, using the Fact Sage software, modeling of the NI formation processes was carried out. The data were obtained on the possible NI composition and amount in this steel.
Studying NIs (the composition, the contamination index, inclusion parameters) was carried out on an ASPEX Explorer electron microscope using the method of automatic X-ray spectral analysis of particles (Automatic Features Analysis, AFA). It was established that in the samples of the first batch, the main part of the NIs consisted of chromium- and manganese-containing oxides: chromium-manganese spinels (Cr-Mn-O and Mn-Cr-Si-O groups), which occupy more than 94% of the total area of the NIs. In the samples of the second batch, the main part of the Nis was represented by Cr-Mn-O; Al-Cr-O; Cr-Al-Mn-O systems.
It was shown that the average size of non-ferrous substances in the samples of the laboratory batch and in industrial samples after extra-furnace treatment differs slightly (5-12%), however, the contamination index in industrial samples after vacuum treatment and especially after modification and repeated vacuum treatment was reduced by more than 10 times. The results obtained allow recommending vacuum treatment and complex modification with calcium and boron as measures to prevent the formation of non-ferrous metals and to improve metallurgical quality when smelting large ingots using complex alloy steels.

Automatic Image Analysis Method as a Tool to Evaluate the Anisotropy of Autoclaved Aerated Concrete for Moisture and Heat Transport

In this article, the results of studies testing the anisotropy of autoclaved aerated concrete in terms of water and heat transport are presented. Using image analysis techniques, a study was conducted on four different samples of concrete produced in the same process. To ensure the comparability of results, the pictures were taken from a fixed distance with the same lens settings trimmed to a set size. Cross-sectional profiles of the material were examined and were arranged in two directions: perpendicular and parallel to the growth direction occurring in the autoclave. For each block, approximately 4750 objects were obtained, with an average of 2700 objects along the wall and 2050 across it. As a result of the comparative analysis, metrics concerning pores, significantly distinguishing the profile direction, were identified. These included the pore area (area), the maximum and minimum distance between points on the perimeter (Feret, MinFeret), lengths of the major and minor axes of the fitted ellipse (major, minor), and the ratio of the area of selection to its convex hull (solidity). As a reference, standard investigations were conducted for moisture transport using the time domain reflectometry setup and for thermal conductivity values using the steady-state heat flow plate apparatus.

Research on lunar regolith of the Chang'E-4 landing site: An automated analysis method based on deep learning framework

On January 3, 2019, the Chang'E-4 lander successfully landed within the Von Kármán crater, located in the South P ole-Aitken Basin (SPA) on the farside of the Moon (45.5°S, 177.6°E), marking the first soft landing on the lunar farside. The lander, equipped with the Lunar Penetrating Radar (LPR) system, aimed to provide insights into the structure and evolution of the Moon. Previous research often relied on manually identifying hyperbolic features to analyze the lunar shallow subsurface properties. This inefficient approach may lead to subjective biases, resulting in unstable outcomes. This research constructed an automatic analysis framework by integrating the Swin Transformer with a 3D velocity spectrum, which is then applied to analyze the properties of the Chang'E-4 LPR data. The experimental results indicate that the framework achieved a precision of 98.9 % and a recall of 96.7 % in hyperbolic feature identification, with an F1 of 0.9782 and AP of 94.8 %. Additionally, it has been experimentally validated that the framework can accurately invert hyperbolic features' two-way travel time and velocity. Finally, the framework is applied to analyze the lunar shallow subsurface structure and properties within the landing area of the Chang'E-4 mission.

Electroencephalography can Ubiquitously Delineate the Brain Dysfunction of Neurodegenerative Dementia by Both Visual and Automatic Analysis Methods: A Preliminary Study.

Introduction: The aim was to examine the differences in electroencephalography (EEG) findings by visual and automated quantitative analyses between Alzheimer's disease (AD) and dementia with Lewy bodies (DLB) and Parkinson's disease with dementia (PDD). Methods: EEG data of 20 patients with AD and 24 with DLB/PDD (12 DLB and 12 PDD) were retrospectively analyzed. Based on the awake EEG, the posterior dominant rhythm frequency and proportion of patients who showed intermittent focal and diffuse slow waves (IDS) were visually and automatically compared between the AD and DLB/PDD groups. Results: On visual analysis, patients with DLB/PDD showed a lower PDR frequency than patients with AD. In patients with PDR <8 Hz and occipital slow waves or patients with PDR <8 Hz and IDS, DLB/PDD was highly suspected (PPV 100%) and AD was unlikely (PPV 0%). On automatic analysis, the findings of the PDR were similar to those on visual analysis. Comparisons between visual and automatic analysis showed an overlap in the focal slow wave commonly detected by both methods in 10 of 44 patients, and concordant presence or absence of IDS in 29 of 43 patients. With respect to PDR <8 Hz and the combination of PDR <8 Hz and IDS, PPV and NPV in DLB/PDD and AD were not different between visual and automatic analysis. Conclusions: As the noninvasive, widely available clinical tool of low expense, visual analysis of EEG findings provided highly sufficient information to delineate different brain dysfunction in AD and DLB/PDD, and automatic EEG analysis could support visual analysis especially about PD.

Exploitation of long-range acoustic dependence for early change detection in dynamic machine running status

This paper suggests that the long-range dependence (LRD) in acoustic signal is an important indicator of dynamic behavior in data. Considering this information, a novel framework based on LRD in acoustic is proposed for detecting change-points in machine running status. Initially, the LRD phenomenon in acoustic is demonstrated. Subsequently, a change-point detection framework is developed, leveraging LRD to monitor machine running states. The framework includes two phases: (1) characteristic data prediction: the LRD value is predicted by the fractional autoregressive integrated moving average (FARIMA) model, which is applied to reflect changes in machine operation states. (2) date change detection: based on residual analysis, a null hypothesis testing based automatic analysis method for acoustic signals during machine successive operations is used to make decision. Experiments in real-world applications demonstrated the good potential of the proposed framework in practical engineering scenarios.

Automated analysis of a novel object recognition test in mice using image processing and machine learning

The novel object recognition test (NORT) is one of the most commonly employed behavioral tests in experimental animals designed to evaluate an animal's interest in and recognition of novelty. However, manual procedures, which rely on researchers’ observations, prevent high throughput analysis. In this study, we developed an automated analysis method for NORT utilizing machine learning-assisted exploratory behavior detection. We recorded the exploratory behavior of the mice using a video camera. The coordinates of the mouse nose and tail base in recorded video files were detected using a pre-trained machine learning model, DeepLabCut. Each video was then segmented into frame images, which were categorized into "exploratory,” or "non-exploratory" frames based on manual observation. Mouse feature vectors were calculated as vectors from the nose to the vertices of the object and were utilized for SVM training. The trained SVM effectively detected exploratory behaviors, showing a strong correlation with human observer assessments. Upon application to NORT, the duration of mouse exploratory behavior towards objects predicted by the SVM exhibited a significant correlation with the assessments made by human observers. The novelty discrimination index derived from the SVM predictions also aligned well with that from human observations.

Comparison of semi and fully automated artificial intelligence driven softwares and manual system for cephalometric analysis

BackgroundCephalometric analysis has been used as one of the main tools for orthodontic diagnosis and treatment planning. The analysis can be performed manually on acetate tracing sheets, digitally by manual selection of landmarks or by recently introduced Artificial Intelligence (AI)-driven tools or softwares that automatically detect landmarks and analyze them. The use of AI-driven tools is expected to avoid errors and make it less time consuming with effective evaluation and high reproducibility.ObjectiveTo conduct intra- and inter-group comparisons of the accuracy and reliability of cephalometric tracing and evaluation done manually and with AI-driven tools that is WebCeph and CephX softwares.MethodsDigital and manual tracing of lateral cephalometric radiographs of 54 patients was done. 18 cephalometric parameters were assessed on each radiograph by 3 methods, manual method and by using semi (WebCeph) and fully automatic softwares (Ceph X). Each parameter was assessed by two investigators using these three methods. SPSS was then used to assess the differences in values of cephalometric variables between investigators, between softwares, between human investigator means and software means. ICC and paired T test were used for intra-group comparisons while ANOVA and post-hoc were used for inter-group comparisons.ResultsTwelve out of eighteen variables had high intra-group correlation and significant ICC p-values, 5 variables had relatively lower values and only one variable (SNO) had significantly low ICC value. Fifteen out of eighteen variables had minimal detection error using fully-automatic method of cephalometric analysis. Only three variables had lowest detection error using semi-automatic method of cephalometric analysis. Inter-group comparison revealed significant difference between three methods for eight variables; Witts, NLA, SNGoGn, Y-Axis, Jaraback, SNO, MMA and McNamara to Point A.ConclusionThere is a lack of significant difference among manual, semiautomatic and fully automatic methods of cephalometric tracing and analysis in terms of the variables measured by these methods. The mean detection errors were the highest for manual analysis and lowest for fully automatic method. Hence the fully automatic AI software has the most reproducible and accurate results.

Automatic retinal image analysis methods using colour fundus images for screening glaucomatous optic neuropathy

ObjectivesTrain an automatic retinal image analysis (ARIA) method to screen glaucomatous optic neuropathy (GON) on non-mydriatic retinal images labelled with the additional results of optical coherence tomography (OCT) and assess...

Search for anomalies in Stromboli's pre-paroxysm activity through an automatic hybrid method of time series analysis

Stromboli (Italy) is an open-vent volcano with persistent explosive activity producing up to five hundred mild explosions per day. Fluctuations in explosion intensity, varying even by orders of magnitude in terms of emitted volume and their subsequent impact on the surrounding regions, sometimes occur abruptly. Consequently, identifying precursors of larger eruptive activities, particularly for more intense (paroxysmal) explosions, is challenging. In order to search for anomalies in the pre-paroxysm activity related to the summer 2019 eruption, we applied a hybrid method to the automatic analysis of geophysical and geochemical time series. This approach is based on the combination of two methods: 1. the Empirical Mode Decomposition (EMD) and 2. the Support Vector Regression (SVR). The aggregation of these two methods allowed us to identify anomalies in the patterns of the geophysical and geochemical parameters measured on Stromboli in a ten-month period including the July–August 2019 eruption. The results of this study are encouraging for an improvement of the monitoring systems and for volcano early warning applications.

A Control Flow Graph Generation Method for Java Projects

Many software quality assurance methods depend on the control flow graph (CFG) for theanalyzing process. However, existing methods for Java projects have not described details of the CFGgeneration process, which is critical for having a fully automatic analysis method. This paper presentsa novel method, named CFG4J, for generating CFG associated with a given Java unit. The generatedCFG will be used in many other software quality assurance methods such as test data generation forunit testing, unit debugging, code coverage computation, etc. We have implemented CFG4J in a tooland performed some initial experiments with some common units with potential results. Finally, wegive some discussions about the experimental results at the end of the paper.Keywords: Control flow graph, unit testing, test data generation, Java projects.

Autofinding egg parasitoids in moth eggs by using machine learning methods in synchrotron-coherent X-ray imaging

The use of a non-destructive technique, such as the propagation-based X-ray phase contrast radiography (PBR) can be an innovative method for automatic parasitism analysis, especially if it presents standard structures. Herein, an artificial intelligence (AI) model is applied in order to establish a computer vision of egg parasitoids in PBRs of parasitized moth eggs acquired at the Synchrotron Radiation for Medical Physics (SYRMEP) beamline at ELETTRA. PBRs of eggs parasitized in four different stages of parasitism (0 days, 3 days, 5 days and 7 days) have been tested. The AI model performance was evaluated by using different metrics. Average Precision (AP), which measures the accuracy of object detection, was found to be 0.866 and 0.741 for the moth eggs and for the parasites, respectively. Additionally, we found that as stage of parasitism becomes longer, the accuracy of parasitism detection also increases (76 % at 7 days).

EPS10.05 Measuring segmental lung changes of cystic fibrosis patients before and after elexacaftor-tezacaftor-ivacaftor (ETI) with an automated analysis method

EPS10.05 Measuring segmental lung changes of cystic fibrosis patients before and after elexacaftor-tezacaftor-ivacaftor (ETI) with an automated analysis method

Automatic Geological Facies Analysis in Crust-Mantle Transition Zone

The Oman Drilling Project was conducted as a part of the International Continental Scientific Drilling Program (ICDP) from 2017 to 2018, and several boreholes, including four across the crust-mantle transition zone, were drilled in the program (Matter et al., 2019; Kelemen et al., 2020; Takazawa, 2021). A full suite of slim and conventional wireline logs, as well as high-resolution electrical borehole image and geochemical spectroscopy logs (Ellis and Singer, 2007; Liu, 2017), were acquired near the coring borehole. Full core samples were acquired from the coring boreholes, and various core analyses were conducted manually with significant time and effort to create a detailed core description. Identification of geological facies is crucial to understanding the complicated crust-mantle transition zone. Being able to achieve this facies recognition from available logging data using an automated method would optimize the operation cost and analysis time. This would be useful for the future scientific ultradeep ocean drilling Mohole to Mantle (M2M) project (Umino, 2015; Moe et al., 2018) planned by the International Ocean Discovery Program (IODP). We propose an automatic geological facies analysis (FaciesSpect) method using borehole images and other petrophysical log data on the Oman Drilling Project. Among the available logging data, borehole image (resistivity type with dynamic color scaling) and two log curves (Fe and Ca) from geochemical spectroscopy log data were selected for the automatic facies analysis. Fifteen clusters were classified from the selected log data using the proposed approach. The cluster distribution trend was consistent with cuttings and core lithologies and indicated three major lithology zones: dunite, gabbro, and harzburgite. Two automatic facies analysis methods, class-based machine learning and heterogeneous rock analysis, were performed to compare the results with those of FaciesSpect. These are well-established methods that can validate the newer FaciesSpect method result. The class results of the three different methods were compared. They are matched at major lithology change boundaries. FaciesSpect class results calibrated by core data could be matched not only with core lithology changes but also with texture changes, such as massive, layered, severely altered, deformed, and fractured, due to the advantage of using borehole image data as one form of input. In this case study, we applied the automatic facies analysis to a complicated scientific drilling well in the crust-mantle transition zone for the first time. The result successfully identified different lithologies, such as dunite and harzburgite, which have a high potential for hydrogen generation and are important resources for emissions-free renewable energy. We validated that the FaciesSpect method is useful for rapidly understanding the overall lithology and texture trends such as fractured, deformed, and massive intervals. The FaciesSpect method can also save analysis time and provide a fit-for-purpose result for different objectives beyond petroleum evaluation in a way that does not rely on the individual interpreter’s experiences. The high-resolution borehole image and geochemical spectroscopy logs are crucial inputs for automatic facies analysis in this study.

Drilling dynamics measurement of drilling motors and its application in recognition of motor operation states through machine learning

Drilling motors are widely used in unconventional oil and gas exploration. Due to the increased non-productive time and drilling costs brought about by accidental damage to drilling motors, predictive maintenance for drilling motors is necessary to optimize asset utilization. However, service companies face significant challenges in achieving predictive maintenance: operational data acquisition, automated statistics analysis, and drilling state recognition. This paper presents a miniature vibration recorder, an automatic statistical analysis method, and a layered recognition algorithm to resolve these challenges and improve tool maintenance efficiency. The designed recorder can be installed in the catch of a conventional mud motor to record drilling dynamics over a drilling motor's entire operation cycle. Time-series data from the recorder can be used to automatically generate operation statistics, mitigating the costs incurred by manual data analysis. The layered recognition algorithm then enables the automatic identification of drilling operation states, i.e., surface, downhole non-drilling, downhole sliding, and downhole rotation. The solutions were validated by deploying the recorder in drilling field runs and analyzing recorded data using the associated design software, yielding a functional data collection, automatic data statistical analysis, and operation state recognition accuracy of 95%. Through achieving improved data collection and analysis, the recorder and software introduced in this work can notify motor owners of the detailed operation history of their tools and enable informed preventive maintenance.

Knowledge-based Data Processing for Multilingual Natural Language Analysis

Natural Language Processing (NLP) aids the empowerment of intelligent machines by enhancing human language understanding for linguistic-based human-computer communication. Recent developments in processing power, as well as the availability of large volumes of linguistic data, have enhanced the demand for data-driven methods for automatic semantic analysis. This paper proposes multilingual data processing using feature extraction with classification using deep learning architectures. Here, the input text data has been collected based on various languages and processed to remove missing values and null values. The processed data has been extracted using Histogram Equalization based Global Local Entropy (HEGLE) and classified using Kernel-based Radial basis Function (Ker_Rad_BF). These architectures could be utilized to process natural language. We present solutions to the multilingual sentiment analysis issue in this research article by implementing algorithms, and we compare precision factors to discover the optimum option for multilingual sentiment analysis. For the HASOC dataset, the proposed HEGLE_ Ker_Rad_BF achieved an accuracy of 98%, a precision of 97%, a recall of 90.5%, an f-1 score of 85%, RMSE of 55.6%, and a loss curve analysis attained 44%. For the TRAC dataset, the accuracy of 98%, the precision attained is 97%, the Recall is 91%, the F-1 score is 87%, and the RMSE of the proposed neural network is 55%.

Development of a sequential injection analysis method for the automatic speciation of inorganic selenium in water samples

Selenium is an important micronutrient for the human body, but biological concentrations on either side of its narrow nutritional window can lead to serious health impacts. Furthermore, Se(IV) has been reported to be more toxic than Se(VI). Therefore, prudent control and monitoring of Se intake should involve speciation of this element. Herein, the development and validation of an automatic sequential injection analysis (SIA) system and method for the speciation of Se(IV) and Se(VI) in water samples is reported for the first time. This method is based on the starch-iodide reaction using Se(IV) as the oxidant, which subsequently forms a blue compound with starch. Total selenium is determined after an online pre-reduction of Se(VI) to Se(IV) with HCl at 75 °C. The concentration of Se(VI) is then calculated as the difference between the total Se and Se(IV) concentrations. The calibration curves for Se(IV) and total Se are characterised by linear ranges of 0 – 1.5 mg L-1 and 0 – 2.5 mg L-1, limits of detection (LODs) of 0.02 mg L-1 and 0.07 mg L-1, and averaged relative standard deviations (RSDs) (n = 3) of 1.33 % and 2.95 % respectively, with a sampling rate of 10 h−1. The newly developed SIA method has been successfully applied to drinking water samples spiked with both Se species and good recoveries in the range 94 – 109 % have been achieved.

Methods of Automatic Analysis of Information Presentation Dynamics in Texts Based on Adaptable Dictionaries of Scientific Terms

The paper proposes a method for determining the dynamics of aspectual content of scientific texts. The problems arising in the automatic processing of scientific texts are discussed, approaches to the creation of a combined method of aspect-oriented analysis of scientific texts are proposed. The results of experiments of aspect analysis of scientific publications in the field of mathematics are given. The algorithm of aspect analysis is built on the basis of processing both the semantic domain graph formed as a result of automatic extraction of information from the text of the mathematical encyclopedia and the weighted semantic graph of the publication. Weighting functions for calculating the dependence of links between professional terms of the semantic domain graph are proposed. During the processing the text of a scientific publication, the semantic domain graph is transformed into the semantic graph of the publication, the two-phase processing algorithm of which forms semantic dependencies between text fragments.

Connected Speech Fluency in Poststroke and Progressive Aphasia: A Scoping Review of Quantitative Approaches and Features.

Speech fluency has important diagnostic implications for individuals with poststroke aphasia (PSA) as well as primary progressive aphasia (PPA), and quantitative assessment of connected speech has emerged as a widely used approach across both etiologies. The purpose of this review was to provide a clearer picture on the range, nature, and utility of individual quantitative speech/language measures and methods used to assess connected speech fluency in PSA and PPA, and to compare approaches across etiologies. We conducted a scoping review of literature published between 2012 and 2022 following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews guidelines. Forty-five studies were included in the review. Literature was charted and summarized by etiology and characteristics of included patient populations and method(s) used for derivation and analysis of speech/language features. For a subset of included articles, we also charted the individual quantitative speech/language features reported and the level of significance of reported results. Results showed that similar methodological approaches have been used to quantify connected speech fluency in both PSA and PPA. Two hundred nine individual speech-language features were analyzed in total, with low levels of convergence across etiology on specific features but greater agreement on the most salient features. The most useful features for differentiating fluent from nonfluent aphasia in both PSA and PPA were features related to overall speech quantity, speech rate, or grammatical competence. Data from this review demonstrate the feasibility and utility of quantitative approaches to index connected speech fluency in PSA and PPA. We identified emergent trends toward automated analysis methods and data-driven approaches, which offer promising avenues for clinical translation of quantitative approaches. There is a further need for improved consensus on which subset of individual features might be most clinically useful for assessment and monitoring of fluency. https://doi.org/10.23641/asha.25537237.

Development of a Wafer Defect Pattern Classifier Using Polar Coordinate System Transformed Inputs and Convolutional Neural Networks

Defect pattern analysis of wafer bin maps (WBMs) is an important means of identifying process problems. Recently, automated analysis methods using machine learning or deep learning have been studied as alternatives to manual classification by engineers. In this paper, we propose a method to improve the feature extraction performance of defect patterns by transforming the polar coordinate system instead of the existing WBM image input. To reduce the variability of the location representation, defect patterns in the Cartesian coordinate system, where the location of the distributed defect die is not constant, were converted to a polar coordinate system. The CNN classifier, which uses polar coordinate transformed input, achieved a classification accuracy of 91.3%, which is 4.8% better than the existing WBM image-based CNN classifier. Additionally, a tree-structured classifier model that sequentially connects binary classifiers achieved a classification accuracy of 94%. The method proposed in this paper is also applicable to the defect pattern classification of WBMs consisting of different die sizes than the training data. Finally, the paper proposes an automated pattern classification method that uses individual classifiers to learn defect types and then applies ensemble techniques for multiple defect pattern classification. This method is expected to reduce labor, time, and cost and enable objective labeling instead of relying on subjective judgments of engineers.

A systematic evaluation of text mining methods for short texts: Mapping individuals’ internal states from online posts

Short texts generated by individuals in online environments can provide social and behavioral scientists with rich insights into these individuals’ internal states. Trained manual coders can reliably interpret expressions of such internal states in text. However, manual coding imposes restrictions on the number of texts that can be analyzed, limiting our ability to extract insights from large-scale textual data. We evaluate the performance of several automatic text analysis methods in approximating trained human coders’ evaluations across four coding tasks encompassing expressions of motives, norms, emotions, and stances. Our findings suggest that commonly used dictionaries, although performing well in identifying infrequent categories, generate false positives too frequently compared to other methods. We show that large language models trained on manually coded data yield the highest performance across all case studies. However, there are also instances where simpler methods show almost equal performance. Additionally, we evaluate the effectiveness of cutting-edge generative language models like GPT-4 in coding texts for internal states with the help of short instructions (so-called zero-shot classification). While promising, these models fall short of the performance of models trained on manually analyzed data. We discuss the strengths and weaknesses of various models and explore the trade-offs between model complexity and performance in different applications. Our work informs social and behavioral scientists of the challenges associated with text mining of large textual datasets, while providing best-practice recommendations.