Self-learning Processes Research Articles

Self-learning Processes in Smart Factories: Deep Reinforcement Learning for Process Control of Robot Brine Injection

The goal of this paper is to investigate the application of adaptive learning algorithms, which enables industrial robots to cope with natural variations exhibited in a brine injection process related to the production of bacon. Due to the variations in bacon meat, the traditional needle-based brine injection process is not capable of injecting the correct amount of brine, leading to either ruined or unflavored bacon. In the presented work a Deep Deterministic Policy Gradient (DDPG) reinforcement learning algorithm is introduced in the injection process to improve process control. To accelerate training of the reinforcement learning algorithm, a simulation environment of the brine absorption is generated based on 64 conducted experiments. The simulation environment estimates the amount of absorbed brine given injection pressure and injection time. Tests are run in the simulation where the starting mass is generated from a normal distribution with mean 80.5g, and a standard deviation of 4.8 g and 20.0 g respectively. With a target of 15 % mass increase, the agent can produce an average mass increase of 14.9 % for the first test and 14.6 % for the second test. This indicates that the model can successfully adapt to a high variety input, thereby showing potential for process control in brine injection, coping with natural variation in meat structure.

Method for constructing estimates of accuracy of measuring equipment based on Bayesian scientific approach

Before putting new unique samples of technical systems into commercial operation, as well as before introducing new technologies into production, as a rule, all kinds of tests are carried out. Small and very small volume of statistical data during testing is a characteristic feature of unique and small-scale products and technical systems. Therefore, the problem of constructing effective statistical estimates with a limited amount of statistical information is an important practical problem. The article proposes the development of the Bayesian approach to the construction of point and interval estimates of the parameters of the known distribution laws. The joint use of a priori and posterior information in the processing of statistical data of a limited volume can significantly increase the reliability of the result. As an example, we consider two most typical distribution laws that arise when testing new unique samples of measuring devices and equipment: normal distribution with an unknown average value and a known dispersion, as well as with an unknown average value and an unknown dispersion. It is shown that for these cases, the parameters of the distribution laws themselves are random variables and obey the normal law and gamma normal law. Recalculation formulas are obtained to refine the parameters of these laws, taking into account a posteriori information. If these formulas are applied several times successively, the process of self-learning of the system or self-tuning of the system occurs. Thus, the proposed scientific approach can find application in the development of intelligent self-learning and self-turning systems.

India's technological climate: a harbinger in resolving and reducing the carbon footprint

Research in artificial intelligence and cognitive computing (simulation of human thought processes in machines involving self-learning systems and processes that efficiently use pattern recognition such as detecting voice, or acquiring data (data mining) and imitating human thoughts in machines) is an evolutionary and innovative field acquiring knowledge from liberal arts, humanities such as management science, philosophy, psychology. The need to rely on these disciplines is of vital importance and strategic value in today's technology up-gradation as robots are designed to think and behave like human-beings. Robotic technology can assess and solve problems through the aid of human intervention and support. Issues that are of a laborious nature can be solved through machine technology and processes or machines and humans must work together to solve larger problems of which the dire need is where humans and machines need to work together in solving problems of global warming and climate change.

Self-Learning Mechanisms in the Multi-robot Systems Based on the Evolution Forests and Classification Trees

The article investigates different approaches to the problem of autonomous robots' self-learning. The knowledge, which a priori is introduced into the on-board control system of an intelligent autonomous robot for control of its expedient behavior in certain situations, should, in general, be supplemented with the results of the self-learning based on the analysis of the accumulated experience. A variety of the autonomous robots' applications in combination with the diversity of the environmental uncertainty types makes possible several options for augmentation of knowledge. The authors employ the construction methods of the classification trees and the decision forests to find the hidden patterns in the arrays of the sensory data, which accumulate the experience, gathered by the robots operating in a complex environment. The prospects of the decision forests construction method were demonstrated for organization of the self-learning processes in the multi-robot systems (MRS). A new approach to MRS self-learning was developed based on a combination of the decision forests and evolutionary computation methods. It was proved that the method of the evolutionary decision forests can serve as a constructive basis for development of the intelligent self-learning autonomous robots operating together within a multi-robot system. The authors demonstrated that the role of the robotic agents was not confined to accumulation of their own sensory data, but that they were also capable of a knowledge exchange and its incorporation into their personal experience. The results of the model simulation are presented, confirming the effectiveness of the proposed approach.

DEVELOPMENT OF LEARNING MANAGEMENT PROCESSES BASED ON THE CONTEMPLATIVE EDUCATION AND THE OPTIMUM EXPERIENCE APPROACHES FOR LEADING OF OPTIMUM LEARNING QUALITY TOWARD TEACHER-EARLY CHILDHOOD INTERACTIONAL RELATIONSHIPS

To develop learning management process based on the Contemplative Education Approach (CEA) and the Optimum Experience Approach (OEA) to enhance the ability relationships between teachers and students were built up, students’ responses of their effects to their learning management process based on the CEA and OEA towards teacher and Early childhoods were respected, such as, being lovely, affectively children, and creating conduction to their classroom learning environments. To administer which as 165 early childhood students in 11 classes and 11 teachers from the Early Childhood School at Bang Sai Royal Folk Arts and Crafts Center under the Royal Patronage of Her Royal Highness Princess Maha Chakri Sirindhorn were participated with the qualitative data, collectively. Research procedures were designed in 2 steps; first, teachers plans to manage the instructional design for including early childhoods who ought to practice their experiences and self-learning processes on self-awareness with practicing mindfulness through their self-observing activities, to improve the meditational activities and real life with themselves were observed by teachers, second, early childhoods respective learning of their opportunity on modern experience, self-literacy, self-mindfulness observation, observing a case study on their activities, and self-practicing daily life. Most of teachers were able to invent and change the increasing relationships between teachers and early childhoods’ abilities evidence from 1 to 2 scales. Relationships between teachers and students were invented the instructional processes with the role models’ teaching management to support and create children’ learning activities, children’ learning outcomes of their understanding, self-awareness, learning abilities, and were responded by teachers’ interaction behaviours with the CEA and OEA instructional methods to their classroom environments. Based on the findings, suggestions for enhancing teachers’ and children’ abilities of their associations between the CEA and OEA classroom environments are needs. The developing learning management processes are explored, respected, accepted, and loved ties for children, relatively. Article visualizations:

Enabling team learning when members are prone to contentious communication: The role of team leader coaching

Members of teams are often prone to interpersonal communication patterns that can undermine the team’s capacity to engage in self-learning processes that are critical to team adaptation and performance improvement. We argue that team leader coaching behaviors are critical to ensuring that team discussions that may foster learning new teamwork skills and strategies are unfettered by the tendency of two or more members to exhibit contentious interpersonal communications. We accordingly test a model in which team contentious communication moderates the mediated relationship of team leader coaching behaviors on team innovation effectiveness and team task performance. In a study of 82 work teams, team leader coaching behaviors exhibited indirect, positive relationships with both team innovation effectiveness and team task performance through team learning, but only among teams with an average or higher level of contentious interpersonal communication. We discuss theoretical and practical implications for the leadership of teams.

In Search for the Neural Mechanisms of Individual Development: Behavior-Driven Differential Hebbian Learning

When Donald Hebb published his 1949 book ``The Organization of Behavior'' he opened a new way of thinking in theoretical neuroscience which, in retrospective, is very close to contemporary ideas in self-organization. His metaphor of ``wiring'' together what ``fires together'' matches very closely the common paradigm that global organization can derive from simple local rules. While ingenious at his time and inspiring the research over decades, the results still fall short of the expectations. For instance, unsupervised as they are, such neural mechanisms should be able to explain and realize the self-organized acquisition of sensorimotor competencies. This paper proposes a new synaptic law which replaces Hebb's original metaphor by that of ``chaining together'' what ``changes together''. Starting from differential Hebbian learning, the new rule grounds the behavior of the agent directly in the internal synaptic dynamics. Therefore, one may call this a behavior-driven synaptic plasticity. Neurorobotics is an ideal testing ground for this new, unsupervised learning rule. This paper focuses on the close coupling between body, control, and environment in challenging physical settings. The examples demonstrate how the new synaptic mechanism induces a self-determined ``search and converge'' strategy in behavior space, generating spontaneously a variety of sensorimotor competencies. The emerging behavior patterns are qualified by involving body and environment in an irreducible conjunction with the internal mechanism. The results may not only be of immediate interest for the further development of embodied intelligence. They also offer a new view on the role of self-learning processes in natural evolution and in the brain. Videos and further details may be found under \url{http://robot.informatik.uni-leipzig.de/research/supplementary/NeuroAutonomy/}.

Integrated OMICS tools for personalised medicine.

System-wide adoption of Personalised Healthcare requires an active and flexible but highly integrated infrastructure, joining many different competences and technologies and allowing continuous upgrading, also through self-learning processes. In this system, clinics and diagnostics would no longer be partitioned, according to a stepwise scheme, from other disciplines as basic science, information technologies, ethics and policies. Each player constitutes a node of a cabled network, where input and output from each node are automatically transferred to all nodes, to systematically retune and coordinate the global activity. Since 2005 the Sant'Andrea Hospital of Rome is an in-house built model of Personalised Healthcare Service, which auto-catalytically drives its own development, which may furnish good evidence that translation of Personalised Medicine into clinical practice is not so elusive. The interaction between usually distant academic departments and wards (as Biochemistry, Internal Medicine, Psychiatry, Oncology), favoured by a farsighted management of hospital resources by the administrators, allowed to create a shared, innovative laboratory, the Advanced Molecular Diagnostics Unit (DiMA). The availability of advanced technologies, as mass spectrometry and medium-to-high throughput DNA analysis paved the way to a “real-time” evaluation of the benefits brought into the “real-world” clinical practice by implementation of new diagnostics aimed to therapy tailoring. This allowed the start up of a health service based on the principles of personalised medicine, in order to optimize the amount of tests necessary to evaluate the patient, to interpret the results correctly and, finally, to plan a personalised therapy and to periodically evaluate and/or modify it, to obtain the best clinical results with the least side effects. Our OMICS platform for personalised medicine offers the following combined approaches: i) Epigenetics, to obtain information on the regulation of gene expression and to evaluate the methylation profile change during hypomethylation therapies; ii) Functional genomics, to measure genetic expression in normal and pathologic conditions, in order to define genetic expression profiles; iii) Structural genomics, which defines genomic differences with clinical impact in the patient populations; iv) Metabolomics and terapeutic drug managment, to define all molecules of interest in a specific clinical context and the actual drug and metabolite concentration during therapies. The MIFAR (Metabolismo Integrato FARmaci – drug metabolism integration) including about 60 gene variants has been developed. The data interpretation is ruled out using the Charite Bioinformatic platform (Berlin DE) and allows adaptation of drug therapies to the individual MIFAR profile, improving efficacy and safety of treatments. The DiMA Unit provides pharmacogenomics and theranostics report for at least 5,000 patients/year.

Механизмы интеллектуальных обратных связей, обработки знаний и самообучения в системах управления автономными роботами и мультиагентными робототехническими группировками

The article is devoted to analysis of various approaches aimed to ensure adaptive properties of the automatic control systems designed for maintenance of the demanded reliability and functioning quality in the presence of disturbances and uncertainty factors. A review is provided of the development of the creation principles for the automatic control systems - from organization of an internal feedback, up to creation of intelligent feedback contours with self-training mechanisms. Examples of various robots equipped with intelligent self-learning control systems are presented. A list of tasks of self-learning of the intelligent control systems is presented both for the autonomous robots and for the multi-agent robot systems. A generalized structure of a control system of the autonomous mobile robots is offered based on the intelligent feedback as means of new knowledge formation. Knowledge formation is possible in a self-learning mode on the basis of processing of the accumulated sensory information. The main problems with creation of the intelligent self-learning control systems are discussed. It is shown that one of the most perspective approaches to realization of the self-learning process in the intelligent control systems of the autonomous robots and multi-robot systems is related to the method of classification of tree formation. The article gives an example of a practical solution to the self-learning problem of the autonomous mobile robots. The solution is based on the automatic knowledge formation of the passability characteristics of the surface underlying a robot. The results of a complex modeling are presented, which testify to the expediency and efficiency of incorporation of the self-learning methods in the structure of a mobile robot intelligent onboard control system for improvement of its adaptation properties. The prospects of the self-learning processes are described for the autonomous robots operating in the structure of the multi-agent systems. As a prove experimental estimates of the efficiency are given for application of the self-learning methods aimed at adaptation of the autonomous mobile robots under conditions of environmental uncertainty on the basis of a mutual exchange of the terrain passability knowledge.

Contemporary approaches to informatization of educational process in higher education in Ukraine

The article describes the modern approaches to the informatization of educational process in higher educational institutions of Ukraine. The relevance of introducing of and its regulatory framework are investigated and the views of scientists to the definitions of "distance learning" and "information-educational environment" are summarizes. The system of work with students using distance learning courses "Business Foreign Language" and "Modern children's literature English-speaking countries" is shown on the example of BorysGrinchenko Kyiv University (Kyiv, Ukraine). The results of investigation based on a survey of students at the beginning and end of the distance courses work demonstrated that the use of distance learning coursespromotes to the self-organization of the student, improving computer skills, facilitates the process of self-learning.

Being a Woman in The World of Physics Education: Female Physics Student Teachers’ Beliefs About Gender Issues, in the City of Valparaiso, Chile, from a Qualitative Perspective

Gender Equality is undoubtedly one of the crucial discussions we are having as a society, since the past century. Science Educators can’t stay aside due to the relationship between STEM and women: In OECD countries, only 30% of degrees in the aforementioned area go to women. Education plays a fundamental role in changing the deeply ingrained social conceptions and unresolved issues regards Gender Equality and, in a broader perspective, Human Rights. Therefore, teachers must be aware of their role and beliefs on the matter. The present manuscript address in an exploratory, qualitative level, the views of a group of Chilean female physics student teachers regards their own educational experience and projections as science educators, unraveling their understandings, doubts, hopes and concerns. We performed in deep interviews, analyzed their discourse, and provided a group of ten categories of findings. The main domains of study were: parity, stereotyping, gender equality definition, and gender equality perspective in education; meanwhile the emergent categories were: naïve view of gender issues, selfsabotage, sexist behavior, parity, working environment, self-learning processes, informed view of gender issues, access, futurestudents’ learning processes, and expectations, of which the last was the most frequently addressed by our subjects. Each category is fully explained and supported by examples. Our findings are coherent with the current literature. We were able to define a clear profile of this particular group of our society: female students that are aware of gender issues in education, although with a lack of theoretical framework. Finally, it was interesting to find evidence about how females perceive gender issues regard their male classmates as well. The relationship between their experiences and the prolongation of gender issues is discussed.

Supporting Students’ Learning To Learn in General Chemistry Using Moodle

A combination of regular classroom teaching with the use of resources available on the Moodle platform has been designed to foster the development of skills for learning to learn for students in an undergraduate general chemistry course. The use of the Moodle platform essentially aimed at strengthening the students’ prior knowledge of chemistry concepts and laws, and at enhancing self-assessment of their study skills. In this combined approach, the use of platform resources is designed to contribute to time management, as well as for information seeking and understanding, in a communication and problem-solving approach. Assessment of the results was made through student surveys, discussion forums, and anecdotal observation by the instructors. The results indicate a high degree of acceptance by students of the use of this combined approach, promoting an increase of self-awareness on their learning process, which is an essential prerequisite for developing self-learning processes throughout life.

Developing an audiovisual notebook as a self‐learning tool in histology: Perceptions of teachers and students

Videos can be used as didactic tools for self-learning under several circumstances, including those cases in which students are responsible for the development of this resource as an audiovisual notebook. We compared students' and teachers' perceptions regarding the main features that an audiovisual notebook should include. Four questionnaires with items about information, images, text and music, and filmmaking were used to investigate students' (n = 115) and teachers' perceptions (n = 28) regarding the development of a video focused on a histological technique. The results show that both students and teachers significantly prioritize informative components, images and filmmaking more than text and music. The scores were significantly higher for teachers than for students for all four components analyzed. The highest scores were given to items related to practical and medically oriented elements, and the lowest values were given to theoretical and complementary elements. For most items, there were no differences between genders. A strong positive correlation was found between the scores given to each item by teachers and students. These results show that both students' and teachers' perceptions tend to coincide for most items, and suggest that audiovisual notebooks developed by students would emphasize the same items as those perceived by teachers to be the most relevant. Further, these findings suggest that the use of video as an audiovisual learning notebook would not only preserve the curricular objectives but would also offer the advantages of self-learning processes.

Self-learning metabasin escape algorithm for supercooled liquids

A generic history-penalized metabasin escape algorithm that contains no predetermined parameters is presented in this work. The spatial location and volume of imposed penalty functions in the configurational space are determined in self-learning processes as the 3N-dimensional potential energy surface is sampled. The computational efficiency is demonstrated using a binary Lennard-Jones liquid supercooled below the glass transition temperature, which shows an O(10(3)) reduction in the quadratic scaling coefficient of the overall computational cost as compared to the previous algorithm implementation. Furthermore, the metabasin sizes of supercooled liquids are obtained as a natural consequence of determining the self-learned penalty function width distributions. In the case of a bulk binary Lennard-Jones liquid at a fixed density of 1.2, typical metabasins are found to contain about 148 particles while having a correlation length of 3.09 when the system temperature drops below the glass transition temperature.

An Investigation of Students’ Academic Development, Views, and Feelings through Journals

The purpose of this study was to investigate upper primary school students’ academic development in science courses and to evaluate their views and feelings about self-learning processes through journals. Students in 6th and 7th grade wrote journals twice a week for nine weeks. We evaluated the journals weekly according to the Science Journal Rubric (SCR), and individually observed students’ academic developments. Subsequently, we also evaluated the journals by focusing on expressions in which students revealed their views and feelings about learning processes, excluding scientific concepts. We grouped the expressions containing views and/or feelings about the learning process into five categories. These categories were classmates, teacher, self-expressions, courses, and journals. The results supported the assertion that journals contain information not only about students’ academic development but also about their personal and affective sides.

Knowledge management in a community setting using action research: a case study of Lumpaya community, Nakorn Pathom Province, Thailand

This study promoted self-learning and participatory learning processes in the Lumpaya Community of Thailand to facilitate the development of local public policy to reduce the problem of poverty. The process used action research utilizing practice and learning from that practice. This research serves as an example of how a human resource development (HRD) intervention, knowledge management, can be applied in a context that extends beyond individual organizational boundaries to strengthen the community.

A computer-supported learning system to help teachers to teach Fuzzy Information Retrieval Systems

This paper describes a computer-supported learning system to teach students the principles and concepts of Fuzzy Information Retrieval Systems based on weighted queries. This tool is used to support the teacher's activity in the degree course Information Retrieval Systems Based on Artificial Intelligence at the Faculty of Library and Information Sciences at the University of Granada. Learning of languages of weighted queries in Fuzzy Information Retrieval Systems is complex because it is very difficult to understand the different semantics that could be associated to the weights of queries together with their respective strategies of query evaluation. We have developed and implemented this computer-supported education system because it allows to support the teacher's activity in the classroom to teach the use of weighted queries in FIRSs and it helps students to develop self-learning processes on the use of such queries. We have evaluated the performance of its use in the learning process according to the students' perceptions and their results obtained in the course's exams. We have observed that using this software tool the students learn better the management of the weighted query languages and then their performance in the exams is improved.

韓国セマングム干拓反対運動における成人の自己学習過程―干潟体験学習場「クレ」の役割を中心に

The reclamation of Saemangeum area in the west coast of Korea implied for a variety of lessons in terms of environmental study and education. The adult residents' self-learning started to overcome regional environmental problems. With the meaning of implements for the shellfish gathering, “Gre” was designated by the local residents to activate and promote learning of their own culture and ecosystem in the tidal wetland area. This learning process has an emphasis on understanding and reinterpretation of life, culture and labor in the relation with communication among community members and reconstruction of reality through the process of self-learning.

Assessment of learning with multiple-choice questions

Nurse educators aspire to learning outcomes that will produce competent practitioners. Assessment strategies should be consistent with desired learning outcomes [Manogue, M., Kelly, M., Bartakova Masaryk, S., Brown, G., Catalanotto, F., Choo-Soo, T., Delap, E., Godoroja, P., Murio, I., Rotgans, J., Saag, M., 2002. Evolving methods of assessment. European Journal of Dental Education 6 (3) 53-66] and there is a requirement to diversify approaches. Objective testing, specifically multiple-choice questions (MCQ's) are one of the approaches that may diversify the assessment approach in Irish undergraduate nursing education. In this paper, Quinn's [Quinn, F.M., 2000. The Principles and Practice of Nurse Education, fourth ed., Stanley Thorne (Publishers) Ltd, Cheltenham] cardinal criteria of assessment, practicality, reliability, validity and discrimination provide a useful framework to discuss the issues associated with the implementation of this type of assessment strategy. MCQ examinations that are consistent with educational outcomes can be used to effectively assess aspects of student performance and can facilitate timely feedback and contribute to the process of self-learning. Significant commitment is required to prepare MCQ test items and examination formats that are reliable and consistent with curriculum objectives. Appropriately constructed MCQ examinations are efficient, objective, capable of discrimination and can be combined with other assessment strategies to contribute to a comprehensive student assessment strategy for use in nursing education.

Evaluation of energy-saving driving styles for bus drivers

A procedure is presented for evaluating the performance in terms of driving style of public transport bus drivers, within the context of a programme for energy savings in urban public transportation. The purpose of this evaluation is that of providing suitable tools for training of personnel with the objective of attaining more energy-efficient driving styles and improving driving quality. Quality can be defined as the combination of an energy saving driving style with a behaviour that is respectful of the environment (noise, pollution and safety) and of the vehicle and is comfortable for the passengers as well. Economical driving provides direct savings in fuel of up to 25 per cent as well as indirect savings deriving from general improvements in quality; a more controlled driving style can also be accompanied by reductions in air pollution and noise emission. The procedure utilizes a fuzzy logic approach and can be implemented aboard vehicles in an automatic monitoring system, the sole requirement being that of measuring the instantaneous road speed of the vehicle and its current load. The procedure has been developed and validated on the basis of data coming from a test campaign carried out on vehicles equipped with automatic and manual transmission, operating over both urban and intercity itineraries in three different cities, and adopting different driving styles with different drivers. By analysing the results, in relation to the itinerary and conditions of traffic, stops, load, etc., it can be determined which conditions, for each driver, lead to either good or poor performance. Such specific information, together with assessment of the overall driving style, provides useful indications for training drivers, both through training programmes with specific itineraries and trials, and through self-learning processes with the procedure implemented using an on-board monitoring system.