Training Vectors Research Articles

Vibration-based identification of engine valve clearance using a convolutional neural network

Contemporary operation-related requirements for combustion engines force the necessity of ongoing assessment of their in operation technical condition (e.g. marine engines). The engine efficiency and durability depend on a variety of parameters. One of them is valve clearance. As has been proven in the paper, the assessment of the valve clearance can be based on vibration signals, which is not a problem in terms of signal measurement and processing and is not invasive into the engine structure. The authors described the experimental research aiming at providing information necessary to develop and validate the proposed method. Active experiments were used with the task of valve clearance and registration of vibrations using a three-axis transducer placed on the engine cylinder head. The tests were carried out during various operating conditions of the engine set by 5 rotational speeds and 5 load conditions. In order to extract the training examples, fragments of the signal related to the closing of individual valves were divided into 11 shorter portions. From each of them, an effective value of the signal was determined. Obtained total 32054 training vectors for each valve related to 4 classes of valve clearance including very sensitive clearance above 0.8 mm associat-ed with high dynamic interactions in cylinder head. In the paper, the authors propose to use a convolutional network CNN to assess the correct engine valve clearance. The obtained results were compared with other methods of machine learning (pattern recognition network, random forest). Finally, using CNN the valve clearance class identification error was less than 1% for the intake valve and less than 3.5% for the exhaust valve. Developed method replaces the existing standard methods based on FFT and STFT combined with regression calculation where approximation error is up to 10%. Such results are more useful for further studies related not only to classification, but also to the prediction of the valve clearance condition in real engine operations.

Dependency syntax guided BERT-BiLSTM-GAM-CRF for Chinese NER

Traditional named entity recognition (NER) methods derived from deep learning (DL) often ignore the long-distance syntactic dependence relationships between words. In such methods, the representation of Chinese word vectors is too simple to solve the problem of polysemy. To address these shortcomings, this paper proposes a syntactic dependency guided BERT-BiLSTM-GAM-CRF model for Chinese NER. First, the self-attention method guided by the dependency syntactic parsing tree is embedded in the transformer computing framework of the BERT model. This can not only obtain the deep two-way linguistic representation of a word according to the context information of the word, but it can also better express the long-distance syntactic dependency relationships between words; Second, the trained word vector sequence is input into the BiLSTM layer embedded in the global attention mechanism (GAM), and then the most important whole situation semantic information in the sentence is obtained. Finally, the CRF is employed to learn the dependence relationships between adjacent labels to obtain the best sentence level label sequence. A large number of experiments on the CLUENER-2020 corpus, MSRA corpus, Weibo corpus and OntoNotes4 corpus prove that the constructed model has good results for the Chinese NER task, and the F1 values are 81.08%, 94.97%, 63.60% and 75.64% respectively.

SAIL: A Deep-Learning-Based System for Automatic Gait Assessment From TUG Videos

Gait disorders are common in the elderly people, seriously hinder patients&#x2019; mobility and sometimes indicate underlying severe neurological diseases. Timely and automatic diagnosis of gait disorders is greatly desired. Existing methods with wearable devices put burdens on patients. We establish a video-based algorithm named <i>SAIL</i> to perform contactless gait assessment automatically. The SAIL contains three parts, namely, <i>skeleton detector</i>, <i>parameter extractor</i>, and <i>gait classifier</i>. Using a pose estimation algorithm, the skeleton detector converts RGB videos to a human skeleton sequence. Then, the parameter extractor extracts gait parameters from skeletons with a signal detection technique. Finally, a trained Support vector machine is used as a gait classifier to detect abnormal gait. The SAIL achieves 86.2&#x0025; sensitivity and 98.5&#x0025; specificity for abnormal gait detection on our <i>SAIL-TUG</i> dataset, outperforming general clinic doctors with 76.4&#x0025; and 97.4&#x0025;, respectively. Nine gait parameters and the binary gait classification result are included in the final gait report. We implement an automatic gait assessment system based on SAIL and deployed the user-interface software in more than 60 hospitals for practical applications. More than 30 000 gait reports have been automatically generated. Moreover, we establish a publicly available dataset named <i>SAIL-TUG</i> including 404 annotated Timed &#x201C;Up &amp; Go&#x201D; videos.

Key vectors of training a new generation of education professionals

Key vectors of training a new generation of education professionals

Using an Automated Speech Recognition Approach to Differentiate Between Normal and Aspirating Swallowing Sounds Recorded from Digital Cervical Auscultation in Children

Use of machine learning to accurately detect aspirating swallowing sounds in children is an evolving field. Previously reported classifiers for the detection of aspirating swallowing sounds in children have reported sensitivities between 79 and 89%. This study aimed to investigate the accuracy of using an automatic speaker recognition approach to differentiate between normal and aspirating swallowing sounds recorded from digital cervical auscultation in children. We analysed 106 normal swallows from 23 healthy children (median 13 months; 52.1% male) and 18 aspirating swallows from 18 children (median 10.5 months; 61.1% male) who underwent concurrent videofluoroscopic swallow studies with digital cervical auscultation. All swallowing sounds were on thin fluids. A support vector machine classifier with a polynomial kernel was trained on feature vectors that comprised the mean and standard deviation of spectral subband centroids extracted from each swallowing sound in the training set. The trained support vector machine was then used to classify swallowing sounds in the test set. We found high accuracy in the differentiation of aspirating and normal swallowing sounds with 98% overall accuracy. Sensitivity for the detection of aspiration and normal swallowing sounds were 89% and 100%, respectively. There were consistent differences in time, power spectral density and spectral subband centroid features between aspirating and normal swallowing sounds in children. This study provides preliminary research evidence that aspirating and normal swallowing sounds in children can be differentiated accurately using machine learning techniques.

MRMR Based Feature Vector Design for Efficient Citrus Disease Detection

In recent times, the images and videos have emerged as one of the most important information source depicting the real time scenarios. Digital images nowadays serve as input for many applications and replacing the manual methods due to their capabilities of 3D scene representation in 2D plane. The capabilities of digital images along with utilization of machine learning methodologies are showing promising accuracies in many applications of prediction and pattern recognition. One of the application fields pertains to detection of diseases occurring in the plants, which are destroying the widespread fields. Traditionally the disease detection process was done by a domain expert using manual examination and laboratory tests. This is a tedious and time consuming process and does not suffice the accuracy levels. This creates a room for the research in developing automation based methods where the images captured through sensors and cameras will be used for detection of disease and control its spreading. The digital images captured from the field's forms the dataset which trains the machine learning models to predict the nature of the disease. The accuracy of these models is greatly affected by the amount of noise and ailments present in the input images, appropriate segmentation methodology, feature vector development and the choice of machine learning algorithm. To ensure the high rated performance of the designed system the research is moving in a direction to fine tune each and every stage separately considering their dependencies on subsequent stages. Therefore the most optimum solution can be obtained by considering the image processing methodologies for improving the quality of image and then applying statistical methods for feature extraction and selection. The training vector thus developed is capable of presenting the relationship between the feature values and the target class. In this article, a highly accurate system model for detecting the diseases occurring in citrus fruits using a hybrid feature development approach is proposed. The overall improvement in terms of accuracy is measured and depicted.

A Hybrid Deep Features PSO-ReliefF Based Classification of Brain Tumor

With technological advancements, deep machine learning can assist doctors in identifying the brain mass or tumor using magnetic resonance imaging (MRI). This work extracts the deep features from 18-pre-trained convolutional neural networks (CNNs) to train the classical classifiers to categorize the brain MRI images. As a result, DenseNet-201, EfficientNet-b0, and DarkNet-53 deep features trained support vector machine (SVM) model shows the best accuracy. Furthermore, the ReliefF method is applied to extract the best features. Then, the fitness function is defined to select the number of nearest neighbors of ReliefF algorithm and feature vector size. Finally, the particle swarm optimization algorithm minimizes the fitness function to determine the optimal feature vector for model training. The proposed approach is validated by using the available online dataset. The proposed approach enhances the classification accuracy to 97.1% using the optimal concatenated deep features of DenseNet-201and DarkNet-53. Therefore, owing to the high accuracy of the proposed approach, it can be helpful to use real-time applications in the future.

ARCHICADВ ІНЖЕНЕРНО-БУДІВЕЛЬНІЙ ГРАФІЦІ БУДІВЕЛЬНИКІВ ТА АРХІТЕКТОРІВ

Urgency of the research. Currently, BIM technologies is a catalyst for changes in the development and management of construction projects. Combining the stages of the project life cycle with one software product ensures the predictability ofresults, simplifies the introduction of changes when editing is necessary, and reduces financial costs for the production of design and estimate documentation, increasing the quality of execution of an architectural projectTarget setting. In practice, changing the previous scenario of the project accordingto the new wishes of the customer, for example, re-planning, corrections of the interior style, finishing materials requires the development of several solution options, which significantly slows down the project implementationActual scientific researches and issues analysis. In Ukraine, at the state level, the concept of the implementation of con-struction information modeling technologies and the plan of measures for its implementation were approved. The use of sectoralCAD collections in the developmentof design projects in the context of the mentioned concept can be considered as one of the tools for further reforming, modernization and digital transformation of the construction industry of Ukraine.The purpose of the article is to study the possibilities of object-oriented three-dimensional CAD ArchiCAD for solving architectural and construction problems using the example of the "Prydesnyanskyi" housing complex in the city of Chernihiv.The statement of basic materials.The current trends in the use of BIM technologies in architectural and construction design in the ArchiCAD software product of the Graphisoft Company were analyzed. Architectural, planning and constructive solutions of the interior design project have been completed. The design project development algorithm has been created on the example of a specific living space. Ways to improve the effective design system from Graphisoft are defined.Conclusions.The created template for the development of a design project provides such advantages as reduction of financial costs for the production of design and estimate documentation, reduction of time and avoidance of errors when making changes to the project.The development of software for information modeling technologies is due, first of all, to the significant demand for VIM products abroad. This creates prerequisites for directing the training vector to the training of specialized specialists who will be able to apply the mentioned technologies in the development of real projects.The article is a publication of scientific and methodical character.

Main vectors in the pedagogical training of residents and postgraduate students of a medical university

The article describes the specifics of pedagogical training courses for residents and postgraduate students. Analysis of regulatory documents and scientific literature made it possible to assess the pedagogical activity of a doctor, and substantiate the need for its study in residency. Analysis of pedagogical training vectors for residents at the Pavlov First Saint Petersburg State Medical University showed that the training program includes following vectors: development of pedagogical competencies for work in “school for patients” and psychological and pedagogical support in the process of diagnosis, treatment, rehabilitation; ensuring the preservation of the patient dignity; facilitating patient-­centered care. It also describes the specifics of the pedagogical training of postgraduate students, related to activities of a higher school teacher: during this stage of training, competencies are formed that are focused on pedagogical activity, teaching at a medical university. As part of the training of postgraduate students at a medical university, knowledge and skills are developed in the planning and implementation of the pedagogical process in a higher educational medical institution. At the same time, for the doctor-­teacher practitioner, the importance of all the competencies that are included in the pedagogy program for residents remains. Thus, the principle of the continuity of post­-graduate pedagogical training is implemented.

Rail Corrugation Detection and Characterization Using Computer Vision.

Rail corrugation appears as oscillatory wear on the rail surface caused by the interaction between the train wheels and the railway. Corrugation shortens railway service life and forces early rail replacement. Consequently, service can be suspended for days during rail replacement, adversely affecting an important means of transportation. We propose an inspection method for rail corrugation using computer vision through an algorithm based on feature descriptors to automatically distinguish corrugated from normal surfaces. We extract seven features and concatenate them to form a feature vector obtained from a railway image. The feature vector is then used to build support vector machine. Data were collected from seven different tracks as video streams acquired at 30 fps. The trained support vector machine was used to predict test frames of rails as being either corrugated or normal. The proposed method achieved a high performance, with 97.11% accuracy, 95.52% precision, and 97.97% recall. Experimental results show that our method is more effective in identifying corrugated images than reference state-of the art works.

Unsupervised feature learning with reconstruction sparse filtering for intelligent fault diagnosis of rotating machinery

Sparse filtering (SF), as a recently emerging unsupervised feature learning method, has drawn much attention in intelligent fault diagnosis of rotating machinery. Generally, SF implements feature extraction by the trained basis vectors. However, similar features may be extracted by SF due to the lack of effective restrictions on the basis vectors during training, which leads to an adverse effect on the diagnostic performance. To address this drawback, reconstruction sparse filtering (RSF) is proposed based on SF, which explicitly constrains the basis vectors via a soft-reconstruction penalty (SRP). In particular, SRP enables RSF to learn a group of independent basis vectors so as to extract dissimilar and diverse features. These features contain comprehensive and rich fault information that can precisely describe the rotating machinery health conditions, so RSF can perform significantly better. Based on RSF, an intelligent diagnosis method is developed, and it is evaluated through experiments on a gear and two bearing datasets. The results testify that RSF is able to extract dissimilar features from the vibration signals, and it has better feature learning ability than SF and nine other popular unsupervised feature learning methods. Moreover, the superiority of the developed diagnosis method is verified by comparing with several state-of-the-art intelligent diagnosis methods on two famous bearing datasets.

Intuitionistic fuzzy evaluation of artificial neural network model

In this paper a method that evaluates a trained artificial neural network is presented. The learning type of an artificial neural network is supervised learning which requires labeled input training vectors. Labeled medical data is provided to train the network, where the labels can either be 1 if the person is alive, or 0 if the person has deceased. The data is divided into training and validation vectors. The validation input vectors are used to evaluate the model and the results are summarized by using intuitionistic fuzzy values.

Development, validation, and relevance of in vivo low-contrast task transfer function to estimate detectability in clinical CT images.

The current state-of-the-art calculation of detectability index (d') is largely phantom-based, with the latest being based on a hybrid phantom noise power spectrum (NPS) combined with patient-specific noise magnitude and high-contrast air-skin interface. The purpose of this study was to develop and assess the use of fully patient-specific measurements of noise and low-contrast resolution, derived entirely from patient images on d'. This study developed a d' calculation that is patient- and task-specific, employing newly developed algorithms for estimating patient-specific NPS and low-contrast task transfer function (TTF). The TTF estimation methodology used a trained regression support vector machine (SVM) to estimate a fitted form of the TTF given a variance-normalized estimate of the NPS (referred to as the TTFNPS ). The regression SVM was trained and tested using five-fold cross-validation on 192 scans (4 dose levels x 6 reconstruction kernels x 4 repeats) of a phantom with low-contrast polyethylene insert and reconstructed with filtered backprojection and iterative reconstructions across 12 clinically relevant kernels (FBP: B20f, B31f, B45f; SAFIRE: I26f, I31f, J45f with strengths: 2, 3, 5). To test the low-contrast TTF estimation method, the estimated TTFNPS measurements were compared to (1) TTF measurements from the air-phantom interface (referred to as the TTFair , representing the most patient-specific clinical alternative) and (2) TTF measurements from the edge of the low-contrast polyethylene insert (referred to as the TTFpoly ), which represented the gold standard of low-contrast TTF measurement. Patient-specific NPS, patient-specific noise magnitude, and patient-specific low-contrast TTF were further combined with a reference task function to calculate a d' (according to a non-prewhitening matched filter model) across 1120 lesions previously evaluated in 2AFC human observer detection of liver lesions. The resulting values were compared to the observer results using a generalized linear mixed-effects statistical model. The correlations between the model and observer results were also compared with previously reported values (using a hybrid method with phantom-derived NPS and TTFair ). The TTFNPS more accurately represented resolution across the considered reconstruction settings, compared with the TTFair . The out-of-fold predictions of the TTFNPS had statistically better root-mean-square error concordance (p<0.05, one-tailed Wilcoxon rank-sum test) to gold standard than the TTFair (the alternative, measured from the air-phantom interface). Detectability indices informed by purely patient-specific NPS and TTF were strongly correlated with 2AFC outcomes (p<0.05). R2 between human detection accuracy and model-predicted detection accuracy were shown to be greater for those measured with patient-specific d' than for the hybrid d' but failed to rise to the level of statistical significance (p≥0.05, bootstrap resampled corrected paired Student's t-test). The results suggest that fully patient-specific characterization of image quality based on in vivo NPS and low-contrast TTF offer advantages over hybrid methods. The results in terms of d' favorably relate to observer detection of liver lesions. The method can potentially be integrated into an automated image quality tracking system to assess image quality across a computed tomography clinical operation without needing phantom scans.

The Research of Convolutional Neural Network Based on Integrated Classification in Question Classification

As a new generation of search engine, automatic question answering system (QAS) is becoming more and more important and has become one of the hotspots of computer application research and natural language processing (NLP). However, as an indispensable part of the QAS, the role of question classification is an understood thing in the system. In view of this, to further make the performance of question classification much better, both the feature extraction and the classification model were explored. On the study of existing CNN research, an improved CNN model based on Bagging integrated classification (“W2V + B-CNN” for short) is proposed and applied to question classification. Firstly, we combine the characteristics of short texts, use the Word2Vec tool to map the features of the words to a certain dimension, and organize the question sentences into the form of a two-dimensional matrix similar to the image. Then, the trained word vectors are used as the input of the CNN for feature extraction. Finally, the Bagging integrated classification algorithm is used to replace the Softmax classification of the traditional CNN for classification. In other words, the good of W2V + B-CNN model is that it can make use of the advantages of CNN and Bagging integrated classification at the same time. Overall, the new model can not only use the powerful feature extraction capabilities of CNN to extract the potential features of natural language questions but also use the good data classification capabilities of the integrated classification algorithm for feature classification at the same time, which can help improve the accuracy of the W2V + B-CNN in the application of question classification. The comparative experiment results prove that the effect of the W2V + B-CNN is significantly better than that of the CNN and other classification algorithms in question classification.

Using Machine Learning to Predict Remission in Patients With Major Depressive Disorder Treated With Desvenlafaxine.

BackgroundMajor depressive disorder (MDD) is a common and burdensome condition that has low rates of treatment success for each individual treatment. This means that many patients require several medication switches to achieve remission; selecting an effective antidepressant is typically a sequential trial-and-error process. Machine learning techniques may be able to learn models that can predict whether a specific patient will respond to a given treatment, before it is administered. This study uses baseline clinical data to create a machine-learned model that accurately predicts remission status for a patient after desvenlafaxine (DVS) treatment.MethodsWe applied machine learning algorithms to data from 3,399 MDD patients (90% of the 3,776 subjects in 11 phase-III/IV clinical trials, each described using 92 features), to produce a model that uses 26 of these features to predict symptom remission, defined as an 8-week Hamilton Depression Rating Scale score of 7 or below. We evaluated that learned model on the remaining held-out 10% of the data (n = 377).ResultsOur resulting classifier, a trained linear support vector machine, had a holdout set accuracy of 69.0%, significantly greater than the probability of classifying a patient correctly by chance. We demonstrate that this learning process is stable by repeatedly sampling part of the training dataset and running the learner on this sample, then evaluating the learned model on the held-out instances of the training set; these runs had an average accuracy of 67.0% ± 1.8%.ConclusionsOur model, based on 26 clinical features, proved sufficient to predict DVS remission significantly better than chance. This may allow more accurate use of DVS without waiting 8 weeks to determine treatment outcome, and may serve as a first step toward changing psychiatric care by incorporating clinical assistive technologies using machine-learned models.

VALUE POTENTIAL OF MUSIC TEACHERS’ ARTISTIC AND EDUCATIONAL ACTIVITY

The purpose of the article is to analyze the phenomenon of music teachers’ artistic and educational activity in the artistic and value context as well as projections for professional training. The integral content of such activity in the teaching profession is revealed in general, and its connection with the values of culture is considered. It is emphasized that art education covers all disciplines of professional music and pedagogical training. At the same time, the tasks of the particular discipline always are in the centre of the solution of problems of other disciplines. Moreover, the place of education in life and work of prominent artists and teachers of Ukraine, China, and other countries is indicated. The role of poly-artistic training of music teachers as a basis for the formation of artistic values is emphasized. The requirements of artistic and educational activity for professional training of music teachers are outlined as the following: attitude towards educational activity, self-development of cultural skills, mastery of information space, development of performing skills, mastering the techniques of verbal and nonverbal communication with the audience. &#x0D; The article specifies the essence of music teacher’s artistic and educational activity as a purposeful permanent process that integrates various components of artistic cognition. The interdependent vectors of professional training of music students are formulated. They are the following: a directed influence on artistic values of others and conscious enrichment of one’s own artistic value sphere. The potential of music teacher’s artistic and educational activity as a foundation and reference point for acquiring personal artistic values is revealed, which includes motivation to expand general artistic erudition, the possibility of holistic practice-oriented immersion in art, presentation of the results of artistic search, and self-presentation.

SOCIAL AND CULTURAL FACTORS OF PRIMARY SCHOOL TEACHER TRAINING IN CANADA (1950–1990S)

The article analyzes the demographic and economic ties and describes the social and cultural factors that in Canada in the 1950 -1990s determined changes in the tasks, organization, and training of teachers to work in primary school, taking into account the cultural needs of the population and government education policies. The application of historical and genetic as well as comparative methods of documentary sources analysis made it possible to identify the social and cultural-regional conditionality of the tasks and content of teacher training and their preparation for work in primary schools in different provinces. The article highlights the main contexts according to which the professional training of Canadian primary school teachers was carried out: historical, multicultural, traditional cultural, pedagogical, and religious. As a result of the comparative analysis of historical development, it was found that in Canadian cities such as Montreal, Toronto, and Vancouver there were concentrated large settlements of migrants, which played a dominant role in social and cultural development of Canada. Two main vectors of teacher training, multicultural and cross-cultural, which met the requirements of Canadian social environments and educational policy of Canadian governments, are studied. The training programs for primary school teachers in the provinces of Quebec, Ontario, and British Columbia, initiated mainly by the federal government of Canada, are described. The Government of Canada, together with the Ministries of Education, colleges and universities, has been found to have influenced the training of Canadian primary school teachers by creating a variety of educational programs best suited for the needs of society.

Bahasa Indonesia pre-trained word vector generation using word2vec for computer and information technology field

Words embedding or distributed representations is a popular method for representing words. In this method, the resulting vector value is a set of real values with specific dimensions that are more effective than the Bag of Word (BoW) method. Also, the advantages of distributed representations can produce word vectors that contain semantic and syntactic information, so that word vectors with close meanings will have close word vectors. However, distributed representation requires a huge corpus with a long training time. For this reason, many researchers have created trained word vectors that can be used repeatedly. The problem is that the available trained word vectors are usually general domain word vectors. This study aims to form pre-trained word vectors for specific domains, namely computers and information technology. Researchers used a dataset of student scientific papers from the Universitas Sumatera Utara (USU) repository. Researchers used the word2vec model, where the model has two architectures, namely the Continuous Bag-of-Words (CBOW) and Skip-gram. This research’s result is word2vec model with the CBOW method is more effective than the Skip-gram method.

Pedestrian Motion Path Detection Method Based on Deep Learning and Foreground Detection

For the surveillance video images captured by monocular camera, this paper proposes a method combining foreground detection and deep learning to detect moving pedestrians, making full use of the invariable background of video image. Firstly, the motion region is extracted by the method of interframe difference and background difference. Then, the normalized motion region extracts the feature vectors based on the improved YOLOv3 tiny network. Finally, the trained linear support vector machine is used for pedestrian detection, and the performance of the fusion detection algorithm on caviar dataset is given, which proves the effectiveness of the proposed fusion detection algorithm. Experimental results show that the proposed method not only improves the practical application of pedestrian rerecognition but also reduces the detection range, computational complexity, and false detection rate compared with sliding window method.

Obey validity limits of data-driven models through topological data analysis and one-class classification

Data-driven models are becoming increasingly popular in engineering, on their own or in combination with mechanistic models. Commonly, the trained models are subsequently used in model-based optimization of design and/or operation of processes. Thus, it is critical to ensure that data-driven models are not evaluated outside their validity domain during process optimization. We propose a method to learn this validity domain and encode it as constraints in process optimization. We first perform a topological data analysis using persistent homology identifying potential holes or separated clusters in the training data. In case clusters or holes are identified, we train a one-class classifier, i.e., a one-class support vector machine, on the training data domain and encode it as constraints in the subsequent process optimization. Otherwise, we construct the convex hull of the data and encode it as constraints. We finally perform deterministic global process optimization with the data-driven models subject to their respective validity constraints. To ensure computational tractability, we develop a reduced-space formulation for trained one-class support vector machines and show that our formulation outperforms common full-space formulations by a factor of over 3000, making it a viable tool for engineering applications. The method is ready-to-use and available open-source as part of our MeLOn toolbox (https://git.rwth-aachen.de/avt.svt/public/MeLOn).