Pattern-based Learning Research Articles

Logical–Mathematical Foundations of a Graph Query Framework for Relational Learning

Relational learning has attracted much attention from the machine learning community in recent years, and many real-world applications have been successfully formulated as relational learning problems. In recent years, several relational learning algorithms have been introduced that follow a pattern-based approach. However, this type of learning model suffers from two fundamental problems: the computational complexity arising from relational queries and the lack of a robust and general framework to serve as the basis for relational learning methods. In this paper, we propose an efficient graph query framework that allows for cyclic queries in polynomial time and is ready to be used in pattern-based learning methods. This solution uses logical predicates instead of graph isomorphisms for query evaluation, reducing complexity and allowing for query refinement through atomic operations. The main differences between our method and other previous pattern-based graph query approaches are the ability to evaluate arbitrary subgraphs instead of nodes or complete graphs, the fact that it is based on mathematical formalization that allows the study of refinements and their complementarity, and the ability to detect cyclic patterns in polynomial time. Application examples show that the proposed framework allows learning relational classifiers to be efficient in generating data with high expressiveness capacities. Specifically, relational decision trees are learned from sets of tagged subnetworks that provide both classifiers and characteristic patterns for the identified classes.

Pattern-based learning and control of nonlinear pure-feedback systems with prescribed performance

Pattern-based learning and control of nonlinear pure-feedback systems with prescribed performance

Novel favipiravir pattern-based learning model for automated detection of specific language impairment disorder using vowels.

Specific language impairment (SLI) is one of the most common diseases in children, and early diagnosis can help to obtain better timely therapy economically. It is difficult and time-consuming for clinicians to accurately detect SLI through standard clinical assessments. Hence, machine learning algorithms have been developed to assist in the accurate diagnosis of SLI. This work aims to investigate the graph of the favipiravir molecule-based feature extraction function and propose an accurate SLI detection model using vowels. We proposed a novel handcrafted machine learning framework. This architecture comprises the favipiravir molecular structure pattern, statistical feature extractor, wavelet packet decomposition (WPD), iterative neighborhood component analysis (INCA), and support vector machine (SVM) classifier. Two feature extraction models, statistical and textural, are employed in the handcrafted feature generation methodology. A new nature-inspired graph-based feature extractor that uses the chemical depiction of the favipiravir (favipiravir became popular with the COVID-19 pandemic) is employed for feature extraction. Finally, the proposed favipiravir pattern, statistical feature extractor, and wavelet packet decomposition are used to create a feature vector. Moreover, a statistical feature extractor is used in this work. The WPD generates multilevel features, and the most meaningful features are selected using the NCA feature selector. Finally, these chosen features are fed to SVM classifier for automated classification. Two validation methods, (i) leave one subject out (LOSO) and (ii) tenfold cross-validations (CV), are used to obtain robust classification results. Our proposed favipiravir pattern-based model developed using a vowel dataset can detect SLI children with an accuracy of 99.87% and 98.86% using tenfold and LOSO CV strategies, respectively. These results demonstrated the high vowel classification ability of the proposed favipiravir pattern-based model.

Thinking Outside the Pattern-Based Box in Jazz Improvisation

Jazz improvisation has long been considered an art form centered around creativity: To successfully improvise in the genre, one must play creatively, while adhering to the stylistic traits of the jazz genre. The classic methods of teaching jazz improvisation lean, in one way or another, on pattern-based learning. Relying on patterns ensures “appropriate” improvisation but is insufficient for creating a successful solo. In this research, we conducted semi-structured interviews with jazz educators to understand how they address the tension between pattern-based teaching and cultivating improvisational creativity.

Perception without preconception: comparison between the human and machine learner in recognition of tissues from histological sections

Deep neural networks (DNNs) have shown success in image classification, with high accuracy in recognition of everyday objects. Performance of DNNs has traditionally been measured assuming human accuracy is perfect. In specific problem domains, however, human accuracy is less than perfect and a comparison between humans and machine learning (ML) models can be performed. In recognising everyday objects, humans have the advantage of a lifetime of experience, whereas DNN models are trained only with a limited image dataset. We have tried to compare performance of human learners and two DNN models on an image dataset which is novel to both, i.e. histological images. We thus aim to eliminate the advantage of prior experience that humans have over DNN models in image classification. Ten classes of tissues were randomly selected from the undergraduate first year histology curriculum of a Medical School in North India. Two machine learning (ML) models were developed based on the VGG16 (VML) and Inception V2 (IML) DNNs, using transfer learning, to produce a 10-class classifier. One thousand (1000) images belonging to the ten classes (i.e. 100 images from each class) were split into training (700) and validation (300) sets. After training, the VML and IML model achieved 85.67 and 89% accuracy on the validation set, respectively. The training set was also circulated to medical students (MS) of the college for a week. An online quiz, consisting of a random selection of 100 images from the validation set, was conducted on students (after obtaining informed consent) who volunteered for the study. 66 students participated in the quiz, providing 6557 responses. In addition, we prepared a set of 10 images which belonged to different classes of tissue, not present in training set (i.e. out of training scope or OTS images). A second quiz was conducted on medical students with OTS images, and the ML models were also run on these OTS images. The overall accuracy of MS in the first quiz was 55.14%. The two ML models were also run on the first quiz questionnaire, producing accuracy between 91 and 93%. The ML models scored more than 80% of medical students. Analysis of confusion matrices of both ML models and all medical students showed dissimilar error profiles. However, when comparing the subset of students who achieved similar accuracy as the ML models, the error profile was also similar. Recognition of ‘stomach’ proved difficult for both humans and ML models. In 04 images in the first quiz set, both VML model and medical students produced highly equivocal responses. Within these images, a pattern of bias was uncovered–the tendency of medical students to misclassify ‘liver’ tissue. The ‘stomach’ class proved most difficult for both MS and VML, producing 34.84% of all errors of MS, and 41.17% of all errors of VML model; however, the IML model committed most errors in recognising the ‘skin’ class (27.5% of all errors). Analysis of the convolution layers of the DNN outlined features in the original image which might have led to misclassification by the VML model. In OTS images, however, the medical students produced better overall score than both ML models, i.e. they successfully recognised patterns of similarity between tissues and could generalise their training to a novel dataset. Our findings suggest that within the scope of training, ML models perform better than 80% medical students with a distinct error profile. However, students who have reached accuracy close to the ML models, tend to replicate the error profile as that of the ML models. This suggests a degree of similarity between how machines and humans extract features from an image. If asked to recognise images outside the scope of training, humans perform better at recognising patterns and likeness between tissues. This suggests that ‘training’ is not the same as ‘learning’, and humans can extend their pattern-based learning to different domains outside of the training set.

Pattern-Based Deep Learning Method to Extract Information from the Log Dataset

It draws researchers’ attentions how to make use of the log data effectively without paying much for storing them. In this paper, we propose pattern-based deep learning method to extract the features from log datasets and to facilitate its further use at the reasonable expense of the storage performances. By taking the advantages of the neural network and thoughts to combine statistical features with experts’ knowledge, there are satisfactory results in the experiments on some specified datasets and on the routine systems that our group maintains. Processed on testing data sets, the model is 5%, at least, more likely to outperform its competitors in accuracy perspective. More importantly, its schema unveils a new way to mingle experts’ experiences with statistical log parser.

Pattern-Based Learning: An Educational Model for Radiology Assistants

Background: Studies show that planning, strategy making, and modeling have greater impact on the achievement of learners than other educational factors. The aim of the present study was to evaluate the changes in clinical competency of radiology residents by teaching and training educational models of radiologic Pattern recognition - diagnostic Approach - Feedback on diagnosis (PAF). Methods: This semi-experimental study was performed at Mashhad University of Medical Sciences from 2018 up to 2020. The participants were 60 radiology residents divided randomly into two groups of 30 subjects in two educational centers. Eight training sessions were held at one of the two educational centers for teaching this model to assistants. Then, the clinical competency of residents was evaluated by four exams. In addition, residents' satisfaction was also determined by a confidential survey conducted by the university. The parametric tests were used for data analysis. p Results: Comparison of the scores of two groups in OSCE exam showed that in the second and third-year of being assistance, the scores of the intervention group were significantly better than the control group (P=0.02 & 0.05), but no significant difference was found between the two groups in the formative (qualitative) and multiple-choice question exams. About 82.7% of radiology residents were satisfied with this educational model. Conclusion: Pattern-based learning, including PAF, is a practical suggestion for problem-based learning in medical imaging. It can lead to improvement of the clinical competency in radiology residents, especially levels 2 or 3.

The Implementation of Curriculum by Using Motion Pattern-Based Learning Media for Pre-school Children

This study aims to determine the implementation of curriculum in learning activities of pre-school children and develop motion pattern-based learning media for pre-school children. This research was carried out in thirty kindergartens in East Jakarta. It was conducted in 4 months, from June to October 2018. This research is included in the development and evaluation research (mixed method). The scope of the research is the implementation of curriculum and the development of learning media for pre-school children by using customized tools. Data was collected by using questionnaires and analyzed by using Guttman scale and Likert scale. Percentage of the implementation of learning for pre-schoolers in Kindergarten in East Jakarta is very good. The goal dimension got 98.2%, the content dimension got 99.3%, the method dimension got 99.3% and the evaluation dimension got 98.3%. The product of this study is a learning media that is adjusted to the implementation of motion pattern-based learning activities for pre-school children.
 Keywords: Early childhood education curriculum, Motion Pattern-Based Learning Media, Pre-school children
 References
 Arikunto, S. (2010). Prosedur Penelitian Suatu Pendekatan Praktik. Jakarta: Asdi Mahasatya.
 Arikunto, S. (2014). Prosedur Penelitian. Jakarta: Rineka Cipta.
 Ayob, A., Badzis, M., & Nordin, A. L.Abdullah, R. (2016). Kurikulum Permata Negara. Tanjong Malim: NCDRC, UPSI.
 Azia, R. S. (1976). Curriculum Principles and Foundation. New York: Harper and Row Publisher.
 Boyle, T., & Phelps, R. (2010). Curriculum To Acknowledge Diversity. The International Journal of Learning, 17(2), 357–370.
 Brady, L. (1995). Curriculum development (5th ed.). Sydney: Prentice-Hall.
 Cholimah, N. (2012). Pengembangan Kurikulum PAUD Berdasarkan Permen 58 Tahun 2009.
 Criticos. (1996). Media. Amazon.
 George A.Beauchamp. (1981). Curriculum Theory. F.E. Peacock Publisher.
 Jamaris, M. (2006). Perkembangan dan Pengembangan Anak Usia Dini Taman Kanak-kanak. Jakarta: Gramedia Widiasarana.
 Johnson, M. (1967). Intentionality in Education. New York: Center for Curriculum Research and Services.
 Kawaitouw, Y. I., Widiastuti, A. A., & Kurniawan, M. (2018). Unit Studies Curriculum: Strategi Guru Dalam Implementasi Kurikulum di Jungle School Sidomukti. Jurnal Pendidikan Usia Dini, 12(November), 371–380.
 Kerlinger, F. N. (1990). Asas-asas Penelitian Behavioral (3th ed.). Yogyakarta: Gajah Mada University Press.
 Langgulung, H. (1989). Manusia dan Pendidikan: Suatu Analisa Psikologik dan Pendidikan. Jakarta: Pustaka al-Husna.
 MacDonald, J. B. (1965). Educational Models for Instruction. Washington DC: The Association for Supervision and Curriculum Development.
 Morrison, G. S. (2012). Dasar-dasar Pendidikan Anak Usia Dini. Jakarta: Indeks.
 Olivia, P. F. (1992). Developing the Curriculum (Third Edit). New York: Harper Collins Publishers Inc.
 Ornstein, A. C. (2004). Curriculum:Foundation, Principles, and Issues. Boston: Pearson Education, Inc.
 Ozturk, I. H. (2011). Curriculum Reform and Teacher Autonomy in Turkey: the case of the History Teaching". International Journal of Instruction, 4 (2)(2), 113–127.
 Prihatini, P. (2014). Kajian Ide Kurikulum 2012 PAUD dan Implikasinya dalam Pengembangan KTSP. Cakrawala: Jurnal Pendidikan Anak USia Dini.
 Rahelly, Y. (2018). Implementasi Kurikulum 2013 Pendidikan Anak Usia Dini di Sumatera Selatan. Jurnal Pendidikan Usia Dini, 12(November), 381–390. https://doi.org/https://doi.org/10.21009/JPUD.122.19
 Rohmansyah, N. A. (2017). Pengaruh Model Pembelajaran Problem Based Learning Terhadap Kemampuan Pemahaman Konsep Pendidikan Jasmani Pada Pembelajaran Tematik Terintegrasi Siswa Kelas IV. JURNAL PENJAKORA, 4(28–35).
 Saylor, J. G., & Alexander, W. M. (1981). Curriculum Planning for Better Teaching and Learning. Holt-Rinehart and Winston.
 Sujiono, Y. N. (2009). Konsep Dasar Pendidikan Anak Usia Dini. Jakarta: Indeks.
 Sukmadinata, N. S. (2000). Pengembangan Kurikulum Teori dan Praktek. Bandung: Remaja Rosdakarya.
 Sutapa, P. (2014). Pengembangan Model Pembelajaran Pendidikan Jasmani Berbasis Kinestetik Untuk Anak Usia Pra Sekolah. Yogyakarta.
 Webster. (1993). Webster’s New International Dictionary. GC Company.
 Widoyoko, E. P. (2012). Evaluasi Program Pembelajaran. Yogyakarta: Pustaka Pelajar.
 Winarno. (2011). Winarno. Metodologi dalam Penelitian Pendidikan Jasmani. Malang: Media Cakrawala Press.
 Winarso, W. (2017). Dasar Pengembangan Kurikulum Sekolah, (January 2015).

Ordinal Pattern: A New Descriptor for Brain Connectivity Networks.

Brain connectivity networks based on magnetic resonance imaging (MRI) or functional MRI (fMRI) data provide a straightforward way to quantify the structural or functional systems of the brain. Currently, there are several network descriptors developed for representing and analyzing brain connectivity networks. However, most of them are designed for unweighted networks, regardless of the valuable weight information of edges, or do not take advantage of the ordinal relationship of weighted edges (even though they are designed for weighted networks). In this paper, we propose a new network descriptor (i.e., ordinal pattern that contains a sequence of weighted edges) for brain connectivity network analysis. Compared with previous network properties, the proposed ordinal patterns cannot only take advantage of the weight information of edges but also explicitly model the ordinal relationship of weighted edges in brain connectivity networks. We further develop an ordinal pattern-based learning framework for brain disease diagnosis using resting-state fMRI data. Specifically, we first construct a set of brain functional connectivity networks, where each network is corresponding to a particular subject. We then develop an algorithm to identify ordinal patterns that frequently appear in brain connectivity networks of patients and normal controls. We further perform discriminative ordinal pattern selection and extract feature representations for subjects based on the selected ordinal patterns, followed by a learning model for automated brain disease diagnosis. Experimental results on both Alzheimer's Disease Neuroimaging Initiative and attention deficit hyperactivity disorder-200 data sets demonstrate that our method outperforms the several state-of-the-art approaches in the tasks of disease classification and clinical score regression.

PEMBELAJARAN BAHASA ARAB DENGAN PENDEKATAN ANALISIS MORFOLOGI

Arabic is a series of operations and processes train students to familiarize themselves to acquire skills / ability to understand everything that is heard, speaking, reading and writing in Arabic. One of proficiency is the skill to read and understand Arabic texts properly. However, in the practical realm is still encountered some problems and issues in this maharoh learning, students are still difficult to read or pronounce the word / phrase and find its meaning. This is because many students do not recognize and pronounce unfamiliar words based wazan (pronunciation rules) and sighot (type of word based dilalahnya). Of this problem researchers provide an alternative solution by presenting a pattern-based learning Arabic morphological analyzer. The objectives of this study were: 1) describe the procedures / technical-based learning Arabic morphology. 2) measure the effectiveness of pattern-based learning Arabic morphological analyzer in increasing reading competence. This study using a pre experimental design with a form of one-shot case Study. And the results of this study concluded that the pattern of learning is quite effective with indicators: 1) students are familiar and easy to pronounce and utter words corresponding wazan / shighot. 2) student easily to memory on vocabulary acquisition; origin of word and its meaning changes. 3) the students more easily and quickly understand a text with the stock of the results of the acquisition of vocabulary and understanding of the meaning of the vocabulary.Keywords: Learning Arabic, Morphology, Reading skill.

Efficient and cost-effective batch analysis of multi-electrode array (MEA) data from human iPS cardiomyocytes using Intelligent Waveform Service (IWS)

• Human induced pluripotent stem cell derived cardiomyocytes (hiPSC-CMs) with multi-electrode array (MEA) technology could be used to develop assays for predictive electrophysiological safety screening. • Large volumes of MEA data are generated and analysis using existing tools is time consuming. There is a need to improve timeliness and cost-effectiveness of data reporting. • Neural ID’s Intelligent Waveform Service (IWS) is propriety enterprise software that uses pattern-based learning of waveforms. • IWS was used to analyze MEA data generated from hiPSC-CMs treated with Terfenadine and results were compared to existing analysis tools. • We show that analysis and reporting times using IWS can be reduced by up to five times and employing pattern recognition technology will improve accuracy and facilitate greater use of MEAs in compound screening. Methods Results • The non-sedating anti-histamine Terfenadine was chosen to validate the IWS software. • Data was recorded from spontaneously beating hiPSCCMs (Cellular Dynamics International) using the MEA1060 system (Multi Channel Systems). Data was filtered (1Hz high pass, 3kHz low pass) and sampled at 10kHz. • After baseline recordings, Terfenadine was cumulatively added to the bath. The last minute of recording at baseline and each Terfenadine concentration was used for analysis. • IWS was used to analyze the following parameters: Field potential duration (FPD), total spike amplitude, beat rate and conduction time. • Data analysis is conducted on the server using templates which are batch processed for efficient resource utilization. • Gradient markers are defined to determine spike interval and context of targeted patterns. • Based on the marker locations, patterns are defined graphically (Fig. 2) to detect repolarization wave location and measure its peak value. • IWS creates an empirical data model and does not rely on a predetermined library of patterns, leading to higher recognition rates than industry standards and the ability to analyze a broader range of data. • By simply clicking and dragging, additional pattern examples can be added to the knowledge database (Fig. 3). • The same process is used to detect other types of patterns, such as spikes, with amplitude (maximum/minimum) measurements applied (Fig. 4). Intelligent Waveform Service (IWS) IWS is proprietary enterprise software (Fig. 1) that: • Leverages machine learning to provide waveform analytics of biosignals. • Automates and accelerates discovery & preclinical research, providing more complete results at a fraction of the time and cost. • Learns example patterns, then runs batch jobs against multiple file sets and data formats, making analytics shareable among researchers and groups. Figure 1 – IWS Architecture Figure 4 – Detecting Spike Patterns and Measuring Amplitude Figure 3 – Adding Pattern Examples to the Template Figure 2 – Pattern Creation and Metrology Set-Up

Toward a Professional Platform for Chinese Character Conversion

Increasing communication among Chinese-speaking regions using respectively traditional and simplified Chinese character systems has highlighted the subtle-yet-extensive differences between the two systems, which can lead to unexpected hindrance in converting characters from one to the other. This article proposes a new priority-based multi-data resources management model, with a new algorithm called Fused Conversion algorithm from Multi-Data resources (FCMD), to ensure more context-sensitive, human controllable, and thus more reliable conversions, by drawing on reverse maximum matching, n -gram-based statistical model and pattern-based learning and matching. After parameter training on the Tagged Chinese Gigaword corpus, its conversion precision reaches 91.5% in context-sensitive cases, the most difficult part in the conversion, with an overall precision rate at 99.8%, a significant improvement over the state-of-the-art models. The conversion platform based on the model has extra features such as data resource selection and n -grams self-learning ability, providing a more sophisticated tool good especially for high-end professional uses.

Integrative mapping of global-scale processes and patterns on “ imaginary Earth ” continental geometries: A teaching tool in an Earth History course

The complexity and interrelatedness of aspects of the geosciences is an important concept to convey in an undergraduate geoscience curriculum. A synthesis capstone project has served to integrate pattern-based learning of an introductory Earth History course into an active and process-based exercise in hypothesis production. In this exercise, students are given (1) an imaginary global continental configuration and (2) a general categorization of the global climate. Students then work through cause/ effect relationships in Earth processes and hypothesize global biotic and abiotic patterns to be mapped upon the imaginary continental framework. Presentation and discussion of each student ’ s imaginary earth and his/her interpretation of the various mappable parameters engages students in each other’s reasoning and creative thought processes while promoting group learning and increasing science communication skills. Examination of the evidence and procedures used in the retrodiction of actual global paleogeographic scenarios is then placed in the context of this project. In practice, students have responded enthusiastically to the opportunity to develop geographic interpretations of an imaginary paleogeographic framework using their understanding of modern Earth systems. Upon exit evaluation, greater than 85% of the students taking part in the exercise felt more confident in their ability to hypothesize patterns from process.

Retroactive interference in neural networks and in humans: The effect of pattern-based learning

Catastrophic interference is addressed as a problem that arises from pattern-based learning algorithms. As such, it is not limited to artificial neural networks but can be demonstrated in human subjects in so far as they use a pattern-based learning strategy. The experiment tests retroactive interference in humans learning lists of consonant-vowel-consonant nonsense syllable pairs. Results show significantly more interference for subjects learning patterned lists than subjects learning arbitrarily paired lists. To examine how different learning strategies depend on the structure of the learning task, a mixture-of-experts neural network model is presented. The results show how these strategies may interact to give rise to the results seen in the human data.

Representation of process trends—IV. Induction of real-time patterns from operating data for diagnosis and supervisory control

A methodology for pattern-based supervisory control and fault diagonsis is presented, based on the multi-scale extraction of trends from process data described in Part III of this series (Bakshi and Stephanopoulos, Computers Chem. Engng 17, 1993). An explicit mapping is learned between the features extracted at multiple scales, and the corresponding process conditions, using the technique of induction by decision trees. Simple rules may be derived from the induced decision tree, to relate the relevant qualitative or quantitative features in the measured process data to process conditions. These rules are often physically interpretable and provide physical insight into the process. Industrial case studies from fine chemicals manufacturing, reactive crystallization and fed-batch fermentation are used to illustrate the characteristics of the pattern-based learning methodology and its application to process supervision and diagnosis.