Quality Control Problems Research Articles

Classification of Quality Defects using Multivariate Control Chart with Ensemble Machine Learning Model

Multivariate control charts enable to monitor processes affected by more than one variable. But, when the process is out of control, it cannot detect which variable is causing it. It is an important requirement to know which variables in the process need corrective actions. In this study, a machine learning-based model is proposed to predict the variable/s that make the process out of control. For this purpose, ensemble algorithms, which are known to have higher prediction performance than single algorithms, were preferred. Because it is aimed to determine the variable(s) that cause the process to be out of control in the most accurate way. It is thought that a classification model in which ensemble algorithms are used together can increase the prediction accuracy. The model, which has not been encountered before in a quality control problem, was applied to a real problem and 98.06% classification accuracy was achieved. Another benefit is that it can predict the variable/variables that make the process uncontrolled without the need for multivariate control charts.

Obtaining and Characterization of Experimental Diagnostic Brucellosis Rabbit Sera for the Development of a National Standard for Brucellosis Serum

Relevance. The production of brucellosis diagnosticums is currently being established in the medical and veterinary practice of the Republic of Uzbekistan. However, due to the lack of a national standard serum in the country and the high cost of analog standard serums on the market, problems may arise in the production of diagnostic tools. In addition, the lack of national standard serums causes problems in quality control of commercial and local antigens, hinders the development of local drugs – brucellosis diagnostics, which reduces the effectiveness of serological diagnosis of brucellosis in humans and animals. Given the above, it becomes necessary to develop and produce a standard serum with a high level of safety, which will improve the methods of laboratory diagnosis of various forms of brucellosis in patients and animals to identify hidden foci of infection in Uzbekistan. The aim of the study is to obtain and characterize experimental standard diagnostic brucellosis rabbit sera for the development of national and industry standard serum with appropriate titers. Materials and Methods. The experiments were carried out in full compliance with the European Council Directive 2010/63/EU on compliance with ethical principles in working with laboratory animals and the experiments were carried out on the basis of the methodological manual «Methods and rules of work» approved by the Ministry of Health of the Republic of Uzbekistan in 2016 with laboratory animals in experimental microbiological and immunological studies. To obtain positive standard sera against brucellosis pathogens, 12 rabbits weighing from 2.2 kg to 4.6 kg, aged 6 to 12 months, were used. The animals were kept under identical conditions on a standard vivarium diet. For the experiment, animals adapted to the conditions of the study were selected and kept in quarantine for 21 days. The maintenance and conduct of the studies followed international rules for the humane treatment of animals. Results and Discussion. During the evaluation of the heterologic specificity of the obtained sera for 23 collection and hospital strains, a weakly positive response (+) was observed in 16.7% of cases. Rabbit sera positive for heterologic specificity were adsorbed on suspensions of inactivated microorganisms (Citrobacter spp. and Enterobacteriaceae spp.) - no significant drop in titer was observed, and cross-agglutination was eliminated. A significant increase in the total protein level was noted after the first and fourth immunizations. Before the first immunization, the total protein level was 59.57 g/l, and after the fourth immunization, it increased threefold to 157.17 g/l. There was also an increase in albumin and globulin (33.2 g/L and 26.37 g/L, respectively) to 79.37 g/L and 77.43 g/L, respectively. IgM levels remained almost unchanged, increasing 3.5-fold after the second immunization and decreasing to 0.24 mg/ml after the fourth immunization. An increase in the level of IgG after the second and third immunizations was revealed, followed by a decrease after the fourth immunization. Conclusion. The obtained national and industry standard diagnostic polyvalent brucellosis sera, as well as the developed methods of laboratory control of its quality and efficiency testing will make it possible to produce candidate standard serum samples for agglutination reaction test and detection of Brucella strains. The obtained standard serum samples will be further used for control of the produced immunobiological diagnostic preparations and provision of unified requirements to their quality. The goal was achieved – improving the serological diagnosis of brucellosis, laying the foundation for further study and standardization of serum.

Automated Shape Correction for Wood Composites in Continuous Pressing

The effective and comprehensive utilization of forest resources has become the theme of the global “dual-carbon strategy”. Forestry restructured wood is a kind of wood-based panel made of wood-based fiber composite material by high-temperature and high-pressure restructuring–molding, and has become an important material in the field of construction, furniture manufacturing, as well as derivative processing for its excellent physical and mechanical properties, decorative properties, and processing performance. Taking Medium Density Fiberboard (MDF) as the recombinant material as the research object, an event-triggered synergetic control mechanism based on interventional three-way decision making is proposed for the viscoelastic multi-field coupling-distributed agile control of the “fixed thickness section” in the MDF continuous flat-pressing process, where some typical quality control problems of complex plate shape deviations including thickness, slope, depression, and bump tend to occur. Firstly, the idea of constructing the industrial event information of continuous hot pressing based on information granulation is proposed, and the information granulation model of the viscoelastic plate shape process mechanism is established by combining the multi-field coupling effect. Secondly, an FMEA-based cyber granular method for diagnosing and controlling the plate thickness diagnosis and control failure information expression of continuous flat pressing is proposed for the problems of plate thickness control failure and plate thickness deviation defect elimination that are prone to occur in the continuous flat-pressing process. The precise control of the plate thickness in the production process is realized based on event-triggered control to achieve the intelligent identification and processing of the various types of faults. The application test is conducted in the international mainstream production line of a certain type of continuous hot-pressing equipment for the production of 18 mm plate thickness; the synergistic effect is basically synchronized after 3 s, the control accuracy reaches 30%, and the average value of the internal bond strength is 1.40, which ensures the integrity of the slab. Practical tests show that the method in the actual production is feasible and effective, with detection and control accuracy of up to ±0.05 mm, indicating that in the production of E0- and E1-level products, the rate of superior products can reach more than 95%.

Современные подходы к организации контроля качества знаний студентов по дисциплине «Латинский язык»

The article is devoted to the study of the problems of quality control of knowledge of students of humanities faculties studying the discipline «Latin» and modern approaches to organizing this control. In light of modern educational requirements imposed by the Federal State Educational Standard for Higher Education and the development of new teaching technologies, it is necessary to constantly update knowledge assessment methods. The discipline of «Latin» is an important component of education in various fields, including medicine, law, biology, and other scientific disciplines. However, assessing students knowledge in this discipline often remains quite challenging for educators due to traditional assessment methods that may be ineffective or not adapted to modern requirements. The article discusses various approaches, including the use of information technology, interactive tasks, modern assessment and testing methods. Modern approaches to monitoring the quality of students knowledge in the discipline «Latin» are an important tool in modern education, allowing the use of an individual approach to assessing the knowledge of each student. The use of modern digital technologies and assessment methods can increase the effectiveness of learning and stimulate student interest in studying this discipline.

The Measurement Errors and Their Effects on the Cumulative Sum Schemes for Monitoring the Ratio of Two Correlated Normal Variables

Monitoring the ratio of two correlated normal random variables is often used in many industrial manufacturing processes. At the same time, measurement errors inevitably exist in most processes, which have different effects on the performance of various charting schemes. This paper comprehensively analyses the impacts of measurement errors on the detection ability of the cumulative sum (CUSUM) charting schemes for the ratio of two correlated normal variables. A thorough numerical assessment is performed using the Monte Carlo simulation, and the results indicate that the measurement errors negatively impact the performance of the CUSUM scheme for the ratio of two correlated normal variables. Increasing the number of measurements per set is not a lucrative approach for minimizing the negative impact of measurement errors on the performance of the CUSUM charting scheme when monitoring the ratio of two correlated normal variables. We consider a food formulation as an example that illustrates the quality control problems involving the ratio of two correlated normal variables in an industry with a measurement error. The results are presented, along with some suggestions for further study.

Flow-through moisture meter for measuring grain moisture as part of an automated grain moisture control system

The methods of increasing the accuracy and efficiency of the production process, as well as ensuring high quality of final products in the grain processing industry, are investigated. It is shown that to solve the problem of insufficient quality control of grain materials, an automated system for monitoring the properties and characteristics of bulk granular materials is necessary. The features of the construction of automatic and automated systems for monitoring the properties and characteristics of bulk granular materials are considered. Measurement methods and control devices of the main technological parameters used in the management of grain processing facilities are briefly described. It is proposed to include a flow moisture meter in the automated grain moisture control system. The physical properties of grain and grain materials, measurement conditions and instrumentation for grain moisture control are analyzed. The use of devices based on the dielkometric method in the subsystem of an automated process control system is discussed. The application of intelligent sensors of a measuring system with a complex multilevel hierarchy is described. The structure of the interconnection of measuring devices for intellectual support of humidification processes and quality control of the studied materials is given. A functional diagram and metrological characteristics of a prototype grain moisture monitoring device, a flow moisture meter, are presented. The metrological characteristics of this device meet the requirements of the grain processing industry and allow it to be used as part of a humidity control system

National tertiary public hospital performance appraisal: Using FOCUS-PDCA to improve external quality assessment.

To innovatively use the FOCUS-PDCA quality improvement strategy to establish an external quality assessment (EQA) working group to continuously improve EQA performance, an important indicator of the national tertiary public hospital performance appraisal. The project was carried out at the National Center for Clinical Laboratories. Using FOCUS-PDCA, which combines problem-focused steps (FOCUS) and improvement steps (PDCA), a project team was established to carry out improvement work. Root cause analysis was carried out to analyze the problems in quality control from EQA project application to results analysis and an improvement plan was implemented according to the steps of FOCUS-PDCA. The project was executed in three cycles from 2019 to 2021 to obtain more satisfactory results. After implementing three cycles of FOCUS-PDCA, the EQA participation rate increased from 66.5% in 2018to 100% in 2021, and the EQA pass rate increased from 94.9% in 2018to 99.3% in 2021. Consequently, the hospital moved into the top 50 in performance assessment for the first time in 2020 and ranked 27th in 2021. The use of the FOCUS-PDCA quality improvement strategy can improve the EQA performance of national tertiary public hospitals and help them achieve satisfactory results in the national examination.

ЭКСПЕРТНАЯ ОЦЕНКА КАЧЕСТВА МЕДИЦИНСКОЙ ПОМОЩИ ДЛЯ СНИЖЕНИИ РЕПРОДУКТИВНЫХ ПОТЕРЬ

The paper considers and highlights the modern principles and methods for assessing the quality of the process of providing medical care, as the most complex and least regulated component of the entire multicomponent system for assessing the quality of medical care. To date, two directions have been formed - theoretical and practical - to solve the problem of quality control of the medical care process. One, standardization, is based on previous medical experience - "method of choice", protocols of management. The second is the quality of the medical care process technology. Quality control of the result is carried out "post factum". Purpose: introduction of effective methods for assessing the quality of medical care by trimesters of pregnancy to reduce reproductive losses. Material and methods: statistical, analytical, prognostic, epidemiological analysis. Results and discussion. The results of the analysis of the assessment of the quality of medical care received by a woman during pregnancy, based on a study of medical records, as well as a study of the opinions of pregnant women, are presented. Comparison of the data obtained makes it possible to reveal the correlation dependence of the results of an expert assessment of the quality of medical care on the timing of a woman's registration for pregnancy. Integral registration defects were determined in the collection of anamnesis data from the examined women in the process of dynamic observation of pregnancy at the outpatient stage. The study of the state of the quality of medical care provided to pregnant women, women in childbirth and puerperas, took place in a complex manner, including laboratory diagnostic studies, registration of medical documentation and possible errors in making a clinical diagnosis. It has been proven that errors in diagnosis and treatment, as a rule, negatively affect the patient's condition. The sub-optimal use of resources is reflected in the lack of respect and use of existing standards. In the study groups with the highest risk of providing medical care of inadequate quality, there were violations that are associated with the risk of worsening the condition of a pregnant woman and the development of gestational complications in the future.

Analysis of The Quality of Plastic Sack Products using the Statistical Quality Control (SQC) Method

PT. XYZ is a PT work unit manufacturing company. Perkebunan Nusantara I Regional 4 is engaged in the plastic sack industry which produces 2 products, namely outer bags and inner bags. The research carried out aims to determine and measure the level of product quality and provide appropriate product improvement suggestions for quality control problems in plastic sack products in PT. XYZ. The method used is Statistical Quality Control (SQC). Based on the results of research on Statistical Quality Control (SQC), there are 5 production stations and there are each type of defect at each production station. The defects that affect product quality are 14,541 kg of holey film defects, 13,849 kg of uneven threads, 22,706 kg of outgoing threads, 17,876 kg of jagged webbing, 10,186 kg of misprinting, 8,846 kg of faded colors, 11,323 kg of inner holes. , and opened seal of 3,206 kg. There are suggestions for improvements that can be proposed for each defect by adjusting the factors in the fishbone diagram.

Establishment of multivariate digital high performance liquid chromatography fingerprints of fruit juice essence and its flavor quality evaluation

Quality control problem of essence and spices has always been the focus of food chemists in recent years. In this study, a multi-variate digital fingerprint profile of fruit juice essence sample was established using the combination of HPLC-DAD spectra and UPLC-MS spectra, which were collected to obtain the information about organic acids, polyphenols, sugars and sugar alcohols of the samples. The stability, reliability and repeatability of the combined fingerprinting method were verified in the work. A total of 36 markers in the established fingerprint were common (20 compounds were confirmed) belonging to different classes: organic acids, polyphenols, sugars, sugar alcohols, and other miscellaneous compounds. Those chromatographic peaks that significantly affect the quality of apple juice flavor were screened from principal component analysis (PCA). Moreover, PCA and cluster analysis of the proposed combined fingerprint gave the better evaluation of the sample quality stability and distinguish sample groups than the fingerprint from single data, which demonstrated its great significance to the quality control of fruit juice samples.

The Future of Automotive Quality Control: How Cloud-Based Reporting is Changing the Game

Abstract The automotive industry faces challenges in maintaining quality control while at the same time reducing costs and improving efficiency. Outsourcing has emerged as a potential solution. Such an approach can create issues such as communication barriers, quality control problems, and limited visibility into the manufacturing process. This study proposes a cloud-based quality reporting solution to overcome these challenges by providing real-time data analytics, facilitating proper communication, and enabling visibility into quality control processes. This solution significantly reduces waiting times for information regarding product quality status and allows interested parties to access data immediately. The outsourcing company, product producer and customer receive flexible, traceable, mobile cloud-based analytics in real-time. Challenges of this solution are the need to secure data, manage access and ensure the appropriate quality of data by persons performing control. The paper provides practical recommendations for implementing cloud-based quality reporting systems.

Hydrate formation due to moisture, occuring by mixing natural gas streams of dewatering different degrees

The key problem during transporting natural gas through gas pipelines is to ensure reliable, safe transportation and supply of gas to consumers. Reliable operation of the main gas pipeline depends on transported gas quality. Under production conditions, gas is saturated with moisture vapor to an equilibrium state, and when thermodynamic conditions (pressure, temperature) change, its condensation occurs. Due to the heterogeneity of the fields, the problem of gas quality control is the key reliability criterion, especially such as the moisture content in the gas. The main complication is the formation of hydrate plugs, which lead to an increase in hydraulic resistance and a decrease in pipeline capacity, which contributes to the occurrence of emergency situations. Therefore, before supplying natural gas to main gas pipelines, the gas is dried to its dew point, which prevents condensation of water from the gas.

Modeling and Simulation of Shape Control Based on Digital Twin Technology in Hot Strip Rolling.

Focusing on the problem of strip shape quality control in the finishing process of hot rolling, a shape model based on metal flow and stress release with the application of varying contact rolling parameters is introduced. Combined with digital twin technology, the digital twin framework of the shape model is proposed, which realizes the deep integration between physical time-space and virtual time-space. With the utilization of the historical data, the parameters are optimized iteratively to complete the digital twin of the shape model. According to the schedule, the raw material information is taken as the input to obtain the simulation of the strip shape, which shows a variety of export shape conditions. The prediction absolute error of the crown and flatness are less than 5 μm and 5 I-unit, respectively. The results prove that the proposed shape simulation model with strong prediction performance can be effectively applied to hot rolling production. In addition, the proposed model provides operators with a reference for the parameter settings for actual production and promotes the intelligent application of a shape control strategy.

Практический опыт применения цито-гистологической корреляции как способ обеспечения контроля качества исследований при диагностике патологии шейки матки

Introduction. In Russia, cervical cancer screening with cytological techniques faces a problem of quality control. Currently, it is necessary to standardize the methodology for comparing the results of morphological methods. The aim of the paper was to compare the findings of cytological and histological studies when diagnosing cervical pathology, classify discrepancies, and evaluate the effectiveness of the cytological method. Materials and methods. A comparative retrospective analysis of cytological examination followed by histological examination was carried out in 2,739 patients. Results. Both methods showed coincidence in 57.9% of cases. Minor and major discrepancies were determined in 29% and 13.1% of cases, respectively. The cytologic technique showed the following figures: sensitivity of 79.3%, specificity of 77.6%, positive prognostic value of 80%, and negative predictive value of 76.9%. When using the liquid-based cytology method, the number of true positive results was significantly higher, while that of false negative results was lower. The interval of up to 2 months between cytological and histological examinations yielded the highest rate of true positive and the lowest rate of false negative results. Conclusion. Comparing the results of morphological methods is most likely to be the best option for ensuring quality control of laboratory tests. This should be a guideline with a subsequent revision of samples in the presence of discrepancies, analysis of their causes, and evaluation of method effectiveness.

Authentication of ten distinctive triterpenoids in Antrodia cinnamomea serves as a crucial aspect for ensuring the quality control of associated nutraceutical products.

Edible mushroom Antrodia cinnamomea is distinctive for its use in many health supplement products in relieving of diverse health-related conditions. A. cinnamomea is known for its rich array of bioactive secondary metabolites, predominantly terpenoids, that possess anti-inflammatory properties. Despite the abundance of these compounds, only some compounds have demonstrated notable anti-inflammatory activity. Moreover, there is a lack of established quality control methods specifically tailored to the active constituents of these products. Consequently, there is a great need for the development of precise and effective quality control methods for A. cinnamomea-based products, targeting their active components to ensure the consistency and reliability of these products in harnessing their anti-inflammatory potential. Herein we report a quantitative HPLC method for better evaluating the quality of A. cinnamomea based dietary supplements. Based on their bioactivities, we selected ten benchmark compounds, i. e. antcin K, (25S)-antcin H, (25R)-antcin H, (25R)-antcin C, (25S)-antcin C, (25R)-antcin A, 15α-acetyl-dehydrosulphurenic acid, versisponic acid D, dehydroeburicoic acid, and eburicoic acid and developed and validated a HPLC-UV method for quantification of these compounds simultaneously with high sensitivity, linearity and range, precision, and accuracy. Furthermore, we applied our method to quantify the commercially available A. cinnamomea containing supplements and found that the quality of these supplements varies greatly with only one product containing good amount of the active compounds. Our method provides a needed solution to quality control problem of the highly priced A. cinnamomea food and nutraceutical products that show great variety and inconsistency.

Root Cause Analysis Of Quality Control And Cost Control Of Implementing The Referback Program In First Level Health Facilities

Background: The incidence of chronic diseases in Jambi City is still high from year to year. The Referback Program (PRB) is one of the government's efforts through BPJS Health in collaboration with health facilities to ensure chronic disease sufferers have easier access to obtain the medicines they need at an efficient cost. This research aims to analyze the main problems of quality control and cost control of PRB implementation in terms of man, material-machine, method, market, money and time elements at FKTP in Jambi City. Methods: The research was conducted using qualitative methods using the perspective of Root Cause Analysis (RCA) theory to form research procedures. The informants consisted of the person in charge of PRB, the head of the community health center and PRB participants at FKTP in Jambi City. The research instrument is a structured interview sheet. Data analysis uses thematic analysis techniques according to the RCA flow Results: The research results found that the main cause of the problem was weak coordination between PRB officers and BPJS Health in implementing PRB at FKTP. Conclusion: It is recommended that BPJS Health be more active in providing outreach and special training to PRB officers as well as setting up a clear monitoring and evaluation system regarding the implementation of PRB in FKTP

DEVELOPMENT OF QUALITY INDICATORS OF TRICHODERMA ATROBRUNNEUM CULTURE FLUID EXTRACT VKPM F-1434

Relevance. It is relevant to solve the problems of quality control of medicinal substances, drugs, preparations by conducting pharmaceutical analy-sis. The purpose of the study – determination of physico-chemical and biological properties of Trichoderma atrobrunneum VKPM F-1434 culture fluid ex-tract. Development of a method for determining the mass concentration of culture fluid extract T. atrobrunneum VKPM F-1434 in bioproducts. Material and methods. The strain Trichoderma atrobrunneum VKPM F-1434 synthesizing low molecular weight biologically active compounds with bacteriostatic effect was used in the work. The extract was obtained by single-stage mixing and settling extraction with ethyl acetate from the culture liquid of T. atrobrunneum VKPM F-1434 after 5 days of deep cultivation at a temperature of 28 ° C, the seed material was the vegetative mycelium of the producer in the late exponential growth phase. The mass concentration of T. atrobrunneum VKPM F-1434 culture fluid extract was determined in a healing liniment for wound healing. Results. Based on the study of physico-chemical and biological properties of culture fluid extract T. atrobrunneum VKPM F-1434, its individual charac-teristics have been established. The method "Determination of the mass concentration of culture fluid extract T. atrobrunneum VKPM F-1434 in the fin-ished bioproduct" has been developed. Scope of the method: determination of the extract’s mass concentration at the stages of the technological pro-cess of preparation, as well as in ready-made dosage forms, therapeutic and preventive orientation of zootechnical and veterinary purposes. Character-istic of the method: the range of determined values – mass concentrtion (ω): 1 – 10%; repeatability: CV = 1.69%; reproducibility CV1 = 1.68%; CV2 = 1.78%; Fr = 1.09; Ft = 3.44; correctness: R = 100.1%. Conclusions. Physico-chemical and biological properties of culture fluid extract T. atrobrunneum VKPM F-1434 can be used to establish its authenticity and quality assessment. The method of determining the mass concentration of culture fluid extract T. atrobrunneum VKPM F-1434 can be considered suitable for a reliable assessment of the composition of the finished bioproduct.

Pengendalian Kualitas Produk Menggunakan Lean Six Sigma dan Fuzzy FMEA Dalam Upaya Menekan Kecacatan Produk

Quality control is a process used to ensure the level of quality in a product or service so as to lead to customer satisfaction. UMKM Eko bubut is a UMKM that produces wooden handicrafts with product marketing that reaches the international market. In the problem of product quality control at UMKM Eko Bubut, it was found that there were five types of defects, namely wavy, rough, perforated, cracked, and broken defects. In addition, it was found that there was wastage that occurred which had an effect on disability. Solving quality control problems at UMKM Eko Bubut is by using lean six sigma to identify the sigma level and fuzzy FMEA is used to determine the main priority for repairs to the causes of production defects that occur. The results of the calculation of the defect level of bowl products, it was found that the types of defects were wavy (55.06%), rough (28.29%), perforated (7.82%), cracked (7.22%) and broken (1.61%). The identification results of the waste that occurs are waste defects (28.1%), waste overproduction (17.7%), waste waiting (16.2%), waste motion (16.0%), waste inventory (10.75%), waste transportation (6.55%), and over-processing (4.9%). The results of calculating the DPMO value obtained an average sigma of 3.27 with a DPMO value of 38890.41. This shows that for every 1,000,000 production, there is a possibility that there will be product defects in as many as 38,890 products. Factors that affect product defects are humans, raw materials, methods, machines, and the environment.

ImageNomer: Description of a functional connectivity and omics analysis tool and case study identifying a race confound

Most packages for the analysis of fMRI-based functional connectivity (FC) and genomic data are used with a programming language interface, lacking an easy-to-navigate GUI frontend. This exacerbates two problems found in these types of data: demographic confounds and quality control in the face of high dimensionality of features. The reason is that it is too slow and cumbersome to use a programming interface to create all the necessary visualizations required to identify all correlations, confounding effects, or quality control problems in a dataset. FC in particular usually contains tens of thousands of features per subject, and can only be summarized and efficiently explored using visualizations. To remedy this situation, we have developed ImageNomer, a data visualization and analysis tool that allows inspection of both subject-level and cohort-level demographic, genomic, and imaging features. The software is Python-based, runs in a self-contained Docker image, and contains a browser-based GUI frontend. We demonstrate the usefulness of ImageNomer by identifying an unexpected race confound when predicting achievement scores in the Philadelphia Neurodevelopmental Cohort (PNC) dataset, which contains multitask fMRI and single nucleotide polymorphism (SNP) data of healthy adolescents. In the past, many studies have attempted to use FC to identify achievement-related features in fMRI. Using ImageNomer to visualize trends in achievement scores between races, we find a clear potential for confounding effects if race can be predicted using FC. Using correlation analysis in the ImageNomer software, we show that FCs correlated with Wide Range Achievement Test (WRAT) score are in fact more highly correlated with race. Investigating further, we find that whereas both FC and SNP (genomic) features can account for 10–15% of WRAT score variation, this predictive ability disappears when controlling for race. We also use ImageNomer to investigate race-FC correlation in the Bipolar and Schizophrenia Network for Intermediate Phenotypes (BSNIP) dataset. In this work, we demonstrate the advantage of our ImageNomer GUI tool in data exploration and confound detection. Additionally, this work identifies race as a strong confound in FC data and casts doubt on the possibility of finding unbiased achievement-related features in fMRI and SNP data of healthy adolescents.

3DWS: reliable segmentation on intelligent welding systems with 3D convolutions

AbstractAutomated industrial welding processes depend on a large number of factors interacting with high complexity resulting in some sporadic and random variability of the manufactured product that may affect its quality. It is therefore very important to have an accurate and stable quality control. In this work, a deep learning (DL) model is developed for semantic segmentation of weld seams using 3D stereo images of the seam. The objective is to correctly identify the shape and volume of the weld seam as this is the basic problem of quality control. To achieve this, a model called UNet$${\mathcal {L}}$$ L ++ has been developed, based on the UNet and UNet++ architectures, with a more complex topology and a simple encoder to achieve a good adaptation to the specific characteristics of the 3D data. The proposed model receives as input a voxelized 3D point cloud of the freshly welded part where noise is abundantly visible, and generates as output another 3D voxel grid where each voxel is semantically labeled. The experiments performed with parts built by a real weld line show a correct identification of the weld seams, obtaining values between 0.935 and 0.941 for the Dice Similarity Coefficient (DSC). As far as the authors are aware, this is the first 3D analysis proposal capable of generating shape and volume information of weld seams with almost perfect noise filtering.