Search results for: cloud computing privacy.

Authors: Ben Khayut, Lina Fabri, Maya Avikhana

Abstract:

The modern Artificial Narrow Intelligence (ANI) models cannot: a) independently, situationally, and continuously function without of human intelligence, used for retraining and reprogramming the ANI’s models, and b) think, understand, be conscious, and cognize under uncertainty and changing of the environmental objects. To eliminate these shortcomings and build a new generation of Artificial Intelligence systems, the paper proposes a Conception, Model, and Method of Computational Psycholinguistic Cognitive Situational-Fuzzy Self-Controlled Brain and Mind System (CPCSFSCBMSUU). This system uses a neural network as its computational memory, and activates functions of the perception, identification of real objects, fuzzy situational control, and forming images of these objects. These images and objects are used for modeling their psychological, linguistic, cognitive, and neural values of properties and features, the meanings of which are identified, interpreted, generated, and formed taking into account the identified subject area, using the data, information, knowledge, accumulated in the Memory. The functioning of the CPCSFSCBMSUU is carried out by its subsystems of the: fuzzy situational control of all processes, computational perception, identifying of reactions and actions, Psycholinguistic Cognitive Fuzzy Logical Inference, Decision Making, Reasoning, Systems Thinking, Planning, Awareness, Consciousness, Cognition, Intuition, and Wisdom. In doing so are performed analysis and processing of the psycholinguistic, subject, visual, signal, sound and other objects, accumulation and using the data, information and knowledge of the Memory, communication, and interaction with other computing systems, robots and humans in order of solving the joint tasks. To investigate the functional processes of the proposed system, the principles of situational control, fuzzy logic, psycholinguistics, informatics, and modern possibilities of data science were applied. The proposed self-controlled system of brain and mind is oriented on use as a plug-in in multilingual subject applications.

Keywords: Computational psycholinguistic cognitive brain and mind system, situational fuzzy control, uncertainty, AI.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 419

Authors: Adrián D. García-Soto, Alejandro Hernández-Martínez, Jesús G. Valdés-Vázquez, Reyna A. Vizguerra-Alvarez

Abstract:

Reinforced concrete bridges designed by code are intended to achieve target reliability levels adequate for the geographical environment where the code is applicable. Several methods can be used to estimate such reliability levels. Many of them require the establishment of an explicit limit state function (LSF). When such LSF is not available as a close-form expression, the simulation techniques are often employed. The simulation methods are computing intensive and time consuming. Note that if the reliability of real bridges designed by code is of interest, numerical schemes, the finite element method (FEM) or computational mechanics could be required. In these cases, it can be quite difficult (or impossible) to establish a close-form of the LSF, and the simulation techniques may be necessary to compute reliability levels. To overcome the need for a large number of simulations when no explicit LSF is available, the point estimate method (PEM) could be considered as an alternative. It has the advantage that only the probabilistic moments of the random variables are required. However, in the PEM, fitting of the resulting moments of the LSF to a probability density function (PDF) is needed. In the present study, a very simple alternative which allows the assessment of the reliability levels when no explicit LSF is available and without the need of extensive simulations is employed. The alternative includes the use of the PEM, and its applicability is shown by assessing reliability levels of reinforced concrete bridges in Mexico when a numerical scheme is required. Comparisons with results by using the Monte Carlo simulation (MCS) technique are included. To overcome the problem of approximating the probabilistic moments from the PEM to a PDF, a well-known distribution is employed. The approach mixes the PEM and other classic reliability method (first order reliability method, FORM). The results in the present study are in good agreement whit those computed with the MCS. Therefore, the alternative of mixing the reliability methods is a very valuable option to determine reliability levels when no close form of the LSF is available, or if numerical schemes, the FEM or computational mechanics are employed.

Keywords: Structural reliability, reinforced concrete bridges, mixing approaches, point estimate method, Monte Carlo simulation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1419

Authors: Mohammed Agbali, Claudia Trillo, Yusuf Arayici, Terrence Fernando

Abstract:

The wide-spread adoption of the Smart City concept has introduced a new era of computing paradigm with opportunities for city administrators and stakeholders in various sectors to re-think the concept of urbanization and development of healthy cities. With the world population rapidly becoming urban-centric especially amongst the emerging economies, social innovation will assist greatly in deploying emerging technologies to address the development challenges in core sectors of the future cities. In this context, sustainable health-care delivery and improved quality of life of the people is considered at the heart of the healthy city agenda. This paper examines the Boston innovation landscape from the perspective of smart services and innovation ecosystem for sustainable development, especially in transportation and healthcare. It investigates the policy implementation process of the Healthy City agenda and eHealth economy innovation based on the experience of Massachusetts’s City of Boston initiatives. For this purpose, three emerging areas are emphasized, namely the eHealth concept, the innovation hubs, and the emerging technologies that drive innovation. This was carried out through empirical analysis on results of public sector and industry-wide interviews/survey about Boston’s current initiatives and the enabling environment. The paper highlights few potential research directions for service integration and social innovation for deploying emerging technologies in the healthy city agenda. The study therefore suggests the need to prioritize social innovation as an overarching strategy to build sustainable Smart Cities in order to avoid technology lock-in. Finally, it concludes that the Boston example of innovation economy is unique in view of the existing platforms for innovation and proper understanding of its dynamics, which is imperative in building smart and healthy cities where quality of life of the citizenry can be improved.

Keywords: Smart city, social innovation, eHealth, innovation hubs, emerging technologies, equitable healthcare, healthy cities.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1731

Authors: Neelam Vats, Madhvi Pathak Pillai, Rajender Lal, Indu Dabas

Abstract:

The pressure of scoring higher marks to be able to get admission in a higher ranked institution has become a social stigma for school students. It leads to various social and academic pressures on them, causing psychological anxiety. This undue stress on students sometimes may even steer to aggressive behavior or suicidal tendencies. Human mind is always surrounded by the some desires, emotions and passions, which usually disturbs our mental peace. In such a scenario, we look for a solution that helps in removing all the obstacles of mind and make us mentally peaceful and strong enough to be able to deal with all kind of pressure. Preksha meditation is one such technique which aims at bringing the positive changes for overall transformation of personality. Hence, the present study was undertaken to assess the impact of Preksha Meditation on the academic anxiety on female teenagers. The study was conducted on 120 high school students from the capital city of India. All students were in the age group of 13-15 years. They also belonged to similar social as well as economic status. The sample was equally divided into two groups i.e. experimental group (N = 60) and control group (N = 60). Subjects of the experimental group were given the intervention of Preksha Meditation practice by the trained instructor for one hour per day, six days a week, for three months for the first experimental stage and another three months for the second experimental stage. The subjects of the control group were not assigned any specific type of activity rather they continued doing their normal official activities as usual. The Academic Anxiety Scale was used to collect data during multi-level stages i.e. pre-experimental stage, post-experimental stage phase-I, and post-experimental stage phase-II. The data were statistically analyzed by computing the two-tailed-‘t’ test for inter group comparison and Sandler’s ‘A’ test with alpha = or p < 0.05 for intra-group comparisons. The study concluded that the practice for longer duration of Preksha Meditation practice brings about very significant and beneficial changes in the pattern of academic anxiety.

Keywords: Academic anxiety, academic pressure, Preksha, meditation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 873

Authors: J.Partanen

Abstract:

Complexity, as a theoretical background has made it easier to understand and explain the features and dynamic behavior of various complex systems. As the common theoretical background has confirmed, borrowing the terminology for design from the natural sciences has helped to control and understand urban complexity. Phenomena like self-organization, evolution and adaptation are appropriate to describe the formerly inaccessible characteristics of the complex environment in unpredictable bottomup systems. Increased computing capacity has been a key element in capturing the chaotic nature of these systems. A paradigm shift in urban planning and architectural design has forced us to give up the illusion of total control in urban environment, and consequently to seek for novel methods for steering the development. New methods using dynamic modeling have offered a real option for more thorough understanding of complexity and urban processes. At best new approaches may renew the design processes so that we get a better grip on the complex world via more flexible processes, support urban environmental diversity and respond to our needs beyond basic welfare by liberating ourselves from the standardized minimalism. A complex system and its features are as such beyond human ethics. Self-organization or evolution is either good or bad. Their mechanisms are by nature devoid of reason. They are common in urban dynamics in both natural processes and gas. They are features of a complex system, and they cannot be prevented. Yet their dynamics can be studied and supported. The paradigm of complexity and new design approaches has been criticized for a lack of humanity and morality, but the ethical implications of scientific or computational design processes have not been much discussed. It is important to distinguish the (unexciting) ethics of the theory and tools from the ethics of computer aided processes based on ethical decisions. Urban planning and architecture cannot be based on the survival of the fittest; however, the natural dynamics of the system cannot be impeded on grounds of being “non-human". In this paper the ethical challenges of using the dynamic models are contemplated in light of a few examples of new architecture and dynamic urban models and literature. It is suggested that ethical challenges in computational design processes could be reframed under the concepts of responsibility and transparency.

Keywords: urban planning, architecture, dynamic modeling, ethics, complexity theory.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1893

Authors: N. Siva Shanmugam, G. Buvanashekaran, K. Sankaranarayanasamy

Abstract:

In this research work, investigations are carried out on Continuous Wave (CW) Nd:YAG laser welding system after preliminary experimentation to understand the influencing parameters associated with laser welding of AISI 304. The experimental procedure involves a series of laser welding trials on AISI 304 stainless steel sheets with various combinations of process parameters like beam power, beam incident angle and beam incident angle. An industrial 2 kW CW Nd:YAG laser system, available at Welding Research Institute (WRI), BHEL Tiruchirappalli, is used for conducting the welding trials for this research. After proper tuning of laser beam, laser welding experiments are conducted on AISI 304 grade sheets to evaluate the influence of various input parameters on weld bead geometry i.e. bead width (BW) and depth of penetration (DOP). From the laser welding results, it is noticed that the beam power and welding speed are the two influencing parameters on depth and width of the bead. Three dimensional finite element simulation of high density heat source have been performed for laser welding technique using finite element code ANSYS for predicting the temperature profile of laser beam heat source on AISI 304 stainless steel sheets. The temperature dependent material properties for AISI 304 stainless steel are taken into account in the simulation, which has a great influence in computing the temperature profiles. The latent heat of fusion is considered by the thermal enthalpy of material for calculation of phase transition problem. A Gaussian distribution of heat flux using a moving heat source with a conical shape is used for analyzing the temperature profiles. Experimental and simulated values for weld bead profiles are analyzed for stainless steel material for different beam power, welding speed and beam incident angle. The results obtained from the simulation are compared with those from the experimental data and it is observed that the results of numerical analysis (FEM) are in good agreement with experimental results, with an overall percentage of error estimated to be within ±6%.

Keywords: Laser welding, Butt weld, 304 SS, FEM.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4990

Authors: Sana Hamdi, Emna Bouazizi, Sami Faiz

Abstract:

In recent years, real-time spatial applications, like location-aware services and traffic monitoring, have become more and more important. Such applications result dynamic environments where data as well as queries are continuously moving. As a result, there is a tremendous amount of real-time spatial data generated every day. The growth of the data volume seems to outspeed the advance of our computing infrastructure. For instance, in real-time spatial Big Data, users expect to receive the results of each query within a short time period without holding in account the load of the system. But with a huge amount of real-time spatial data generated, the system performance degrades rapidly especially in overload situations. To solve this problem, we propose the use of data partitioning as an optimization technique. Traditional horizontal and vertical partitioning can increase the performance of the system and simplify data management. But they remain insufficient for real-time spatial Big data; they can’t deal with real-time and stream queries efficiently. Thus, in this paper, we propose a novel data partitioning approach for real-time spatial Big data named VPA-RTSBD (Vertical Partitioning Approach for Real-Time Spatial Big data). This contribution is an implementation of the Matching algorithm for traditional vertical partitioning. We find, firstly, the optimal attribute sequence by the use of Matching algorithm. Then, we propose a new cost model used for database partitioning, for keeping the data amount of each partition more balanced limit and for providing a parallel execution guarantees for the most frequent queries. VPA-RTSBD aims to obtain a real-time partitioning scheme and deals with stream data. It improves the performance of query execution by maximizing the degree of parallel execution. This affects QoS (Quality Of Service) improvement in real-time spatial Big Data especially with a huge volume of stream data. The performance of our contribution is evaluated via simulation experiments. The results show that the proposed algorithm is both efficient and scalable, and that it outperforms comparable algorithms.

Keywords: Real-Time Spatial Big Data, Quality Of Service, Vertical partitioning, Horizontal partitioning, Matching algorithm, Hamming distance, Stream query.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1060

Authors: Heng Ma

Abstract:

Third-party warehousing logistics has an important role in the development of external logistics. At present, the third-party logistics in our country is still a new industry, the accounting system has not yet been established, the current financial accounting system of third-party warehousing logistics is mainly in the traditional way of thinking, and only able to provide the total cost information of the entire enterprise during the accounting period, unable to reflect operating indirect cost information. In order to solve the problem of third-party logistics industry cost information distortion, improve the level of logistics cost management, the paper combines theoretical research and case analysis method to reflect cost allocation by building third-party logistics costing model using Time-Driven Activity-Based Costing(TDABC), and takes S company as an example to account and control the warehousing logistics cost.Based on the idea of “Products consume activities and activities consume resources”, TDABC put time into the main cost driver and use time-consuming equation resources assigned to cost objects. In S company, the objects focuses on three warehouse, engaged with warehousing and transportation (the second warehouse, transport point) service. These three warehouse respectively including five departments, Business Unit, Production Unit, Settlement Center, Security Department and Equipment Division, the activities in these departments are classified by in-out of storage forecast, in-out of storage or transit and safekeeping work. By computing capacity cost rate, building the time-consuming equation, the paper calculates the final operation cost so as to reveal the real cost.The numerical analysis results show that the TDABC can accurately reflect the cost allocation of service customers and reveal the spare capacity cost of resource center, verifies the feasibility and validity of TDABC in third-party logistics industry cost accounting. It inspires enterprises focus on customer relationship management and reduces idle cost to strengthen the cost management of third-party logistics enterprises.

Keywords: Third-party logistics enterprises, TDABC, cost management, S company.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2440

Authors: Adel S. Alanazi

Abstract:

The transition of a student with a disability from school to work is the most crucial phase while moving from the stage of adolescence into early adulthood. In this process, young individuals face various difficulties and challenges in order to accomplish the next venture of life successfully. In this respect, this paper aims to examine the challenges encountered by the individuals with intellectual disabilities in transition to work in Saudi Arabia. For this purpose, this study has undertaken a qualitative research-based methodology; wherein interpretivist philosophy has been followed along with inductive approach and exploratory research design. The data for the research has been gathered with the help of semi-structured interviews, whose findings are analysed with the help of thematic analysis. Semi-structured interviews were conducted with parents of persons with intellectual disabilities, officials, supervisors and specialists of two vocational rehabilitation centres providing training to intellectually disabled students, in addition to that, directors of companies and websites in hiring those individuals. The total number of respondents for the interview was 15. The purposive sampling method was used to select the respondents for the interview. This sampling method is a non-probability sampling method which draws respondents from a known population and allows flexibility and suitability in selecting the participants for the study. The findings gathered from the interview revealed that the lack of awareness among their parents regarding the rights of their children who are intellectually disabled; the lack of adequate communication and coordination between various entities; concerns regarding their training and subsequent employment are the key difficulties experienced by the individuals with intellectual disabilities. Training in programmes such as bookbinding, carpentry, computing, agriculture, electricity and telephone exchange operations were involved as key training programmes. The findings of this study also revealed that information technology and media were playing a significant role in smoothing the transition to employment of individuals with intellectual disabilities. Furthermore, religious and cultural attitudes have been identified to be restricted for people with such disabilities in seeking advantages from job opportunities. On the basis of these findings, it can be implied that the information gathered through this study will serve to be highly beneficial for Saudi Arabian schools/ rehabilitation centres for individuals with intellectual disability to facilitate them in overcoming the problems they encounter during the transition to work.

Keywords: Intellectual disability, transition services, rehabilitation centre.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1332

Authors: C. Ardil

Abstract:

This paper aims to present an objective quantitative methodology on how to evaluate individual’s scholarly research output using multiple criteria decision analysis. A multiple criteria decision making analysis (MCDMA) methodological process is adopted to build a multiple criteria evaluation model. With the introduction of the scholar index, which gives significant information about a researcher's productivity and the scholarly impact of his or her publications in a single number (s is the number of publications with at least s citations); cumulative research citation index; the scholar index is included in the citation databases to cover the multidimensional complexity of scholarly research performance and to undertake objective evaluations with scholar index. The scholar index, one of publication activity indexes, is analyzed by considering it to be the most appropriate sciencemetric indicator which allows to smooth over many drawbacks of scholarly output assessment by mere calculation of the number of publications (quantity) and citations (quality). Hence, this study includes a set of indicators-based scholar index to be used for evaluating scholarly researchers. Google Scholar open science database was used to assess and discuss scholarly productivity and impact of researchers. Based on the experiment of computing the scholar index, and its derivative indexes for a set of researchers on open research database platform, quantitative methods of assessing scholarly research output were successfully considered to rank researchers. The proposed methodology considers the ranking, and the selection of data on which a scholarly research performance evaluation was based, the analysis of the data, and the presentation of the multiple criteria analysis results.

Keywords: Multiple Criteria Decision Making Analysis, MCDMA, Research Performance Evaluation, Scholar Index, h index, Science Citation Index, Science Efficiency, Cumulative Citation Index, Sciencemetrics

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 482

Authors: Neil Bar, Andrew Heweston

Abstract:

Probability of failure (PF) often appears alongside factor of safety (FS) in design acceptance criteria for rock slope, underground excavation and open pit mine designs. However, the design acceptance criteria generally provide no guidance relating to how PF should be calculated for homogeneous and heterogeneous rock masses, or what qualifies a ‘reasonable’ PF assessment for a given slope design. Observational and kinematic methods were widely used in the 1990s until advances in computing permitted the routine use of numerical modelling. In the 2000s and early 2010s, PF in numerical models was generally calculated using the point estimate method. More recently, some limit equilibrium analysis software offer statistical parameter inputs along with Monte-Carlo or Latin-Hypercube sampling methods to automatically calculate PF. Factors including rock type and density, weathering and alteration, intact rock strength, rock mass quality and shear strength, the location and orientation of geologic structure, shear strength of geologic structure and groundwater pore pressure influence the stability of rock slopes. Significant engineering and geological judgment, interpretation and data interpolation is usually applied in determining these factors and amalgamating them into a geotechnical model which can then be analysed. Most factors are estimated ‘approximately’ or with allowances for some variability rather than ‘exactly’. When it comes to numerical modelling, some of these factors are then treated deterministically (i.e. as exact values), while others have probabilistic inputs based on the user’s discretion and understanding of the problem being analysed. This paper discusses the importance of understanding the key aspects of slope design for homogeneous and heterogeneous rock masses and how they can be translated into reasonable PF assessments where the data permits. A case study from a large open pit gold mine in a complex geological setting in Western Australia is presented to illustrate how PF can be calculated using different methods and obtain markedly different results. Ultimately sound engineering judgement and logic is often required to decipher the true meaning and significance (if any) of some PF results.

Keywords: Probability of failure, point estimate method, Monte-Carlo simulations, sensitivity analysis, slope stability.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1202

Authors: Michael Russelle S. Alvarez, Noel S. Quiming, Francisco M. Heralde

Abstract:

This study aims to: a) obtain ethanolic (95% EtOH) and aqueous extracts of Selaginella elmeri, Christella dentata, Elatostema sinnatum, Curculigo capitulata, Euphorbia hirta, Murraya koenigii, Alpinia speciosa, Cymbopogon citratus, Eucalyptus globulus, Jatropha curcas, Psidium guajava, Gliricidia sepium, Ixora coccinea and Capsicum frutescens and screen them for larvicidal activities against Aedes aegypti (Linn.) and Aedes albopictus (Skuse) larvae; b) to fractionate the most active extract and determine the most active fraction; c) to determine the larvicidal properties of the most active extract and fraction against by computing their percentage mortality, LC50, and LC90 after 24 and 48 hours of exposure; and d) to determine the nature of the components of the active extracts and fractions using phytochemical screening. Ethanolic (95% EtOH) and aqueous extracts of the selected plants will be screened for potential larvicidal activity against Ae. aegypti and Ae. albopictus using standard procedures and 1% malathion and a Piper nigrum based ovicide-larvicide by the Department of Science and Technology as positive controls. The results were analyzed using One-Way ANOVA with Tukey’s and Dunnett’s test. The most active extract will be subjected to partial fractionation using normal-phase column chromatography, and the fractions subsequently screened to determine the most active fraction. The most active extract and fraction were subjected to dose-response assay and probit analysis to determine the LC50 and LC90 after 24 and 48 hours of exposure. The active extracts and fractions will be screened for phytochemical content. The ethanolic extracts of C. citratus, E. hirta, I. coccinea, G. sepium, M. koenigii, E globulus, J. curcas and C. frutescens exhibited significant larvicidal activity, with C. frutescens being the most active. After fractionation, the ethyl acetate fraction was found to be the most active. Phytochemical screening of the extracts revealed the presence of alkaloids, tannins, indoles and steroids. A formulation using talcum powder–300 mg fraction per 1 g talcum powder–was made and again tested for larvicidal activity. At 2 g/L, the formulation proved effective in killing all of the test larvae after 24 hours.

Keywords: Larvicidal activity screening, partial purification, dose-response assay, Capsicum frutescens.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1738

Authors: Suraiya Jabin, Kamal K. Bharadwaj

Abstract:

In the recent past Learning Classifier Systems have been successfully used for data mining. Learning Classifier System (LCS) is basically a machine learning technique which combines evolutionary computing, reinforcement learning, supervised or unsupervised learning and heuristics to produce adaptive systems. A LCS learns by interacting with an environment from which it receives feedback in the form of numerical reward. Learning is achieved by trying to maximize the amount of reward received. All LCSs models more or less, comprise four main components; a finite population of condition–action rules, called classifiers; the performance component, which governs the interaction with the environment; the credit assignment component, which distributes the reward received from the environment to the classifiers accountable for the rewards obtained; the discovery component, which is responsible for discovering better rules and improving existing ones through a genetic algorithm. The concatenate of the production rules in the LCS form the genotype, and therefore the GA should operate on a population of classifier systems. This approach is known as the 'Pittsburgh' Classifier Systems. Other LCS that perform their GA at the rule level within a population are known as 'Mitchigan' Classifier Systems. The most predominant representation of the discovered knowledge is the standard production rules (PRs) in the form of IF P THEN D. The PRs, however, are unable to handle exceptions and do not exhibit variable precision. The Censored Production Rules (CPRs), an extension of PRs, were proposed by Michalski and Winston that exhibit variable precision and supports an efficient mechanism for handling exceptions. A CPR is an augmented production rule of the form: IF P THEN D UNLESS C, where Censor C is an exception to the rule. Such rules are employed in situations, in which conditional statement IF P THEN D holds frequently and the assertion C holds rarely. By using a rule of this type we are free to ignore the exception conditions, when the resources needed to establish its presence are tight or there is simply no information available as to whether it holds or not. Thus, the IF P THEN D part of CPR expresses important information, while the UNLESS C part acts only as a switch and changes the polarity of D to ~D. In this paper Pittsburgh style LCSs approach is used for automated discovery of CPRs. An appropriate encoding scheme is suggested to represent a chromosome consisting of fixed size set of CPRs. Suitable genetic operators are designed for the set of CPRs and individual CPRs and also appropriate fitness function is proposed that incorporates basic constraints on CPR. Experimental results are presented to demonstrate the performance of the proposed learning classifier system.

Keywords: Censored Production Rule, Data Mining, GeneticAlgorithm, Learning Classifier System, Machine Learning, PittsburgApproach, , Reinforcement learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1534

Authors: Mohammad H. Taheri, David J. Brown, Nasser Sherkat

Abstract:

Engagement is one of the most important factors in determining successful outcomes and deep learning in students. Existing approaches to detect student engagement involve periodic human observations that are subject to inter-rater reliability. Our solution uses real-time multimodal multisensor data labeled by objective performance outcomes to infer the engagement of students. The study involves four students with a combined diagnosis of cerebral palsy and a learning disability who took part in a 3-month trial over 59 sessions. Multimodal multisensor data were collected while they participated in a continuous performance test. Eye gaze, electroencephalogram, body pose, and interaction data were used to create a model of student engagement through objective labeling from the continuous performance test outcomes. In order to achieve this, a type of continuous performance test is introduced, the Seek-X type. Nine features were extracted including high-level handpicked compound features. Using leave-one-out cross-validation, a series of different machine learning approaches were evaluated. Overall, the random forest classification approach achieved the best classification results. Using random forest, 93.3% classification for engagement and 42.9% accuracy for disengagement were achieved. We compared these results to outcomes from different models: AdaBoost, decision tree, k-Nearest Neighbor, naïve Bayes, neural network, and support vector machine. We showed that using a multisensor approach achieved higher accuracy than using features from any reduced set of sensors. We found that using high-level handpicked features can improve the classification accuracy in every sensor mode. Our approach is robust to both sensor fallout and occlusions. The single most important sensor feature to the classification of engagement and distraction was shown to be eye gaze. It has been shown that we can accurately predict the level of engagement of students with learning disabilities in a real-time approach that is not subject to inter-rater reliability, human observation or reliant on a single mode of sensor input. This will help teachers design interventions for a heterogeneous group of students, where teachers cannot possibly attend to each of their individual needs. Our approach can be used to identify those with the greatest learning challenges so that all students are supported to reach their full potential.

Keywords: Affective computing in education, affect detection, continuous performance test, engagement, flow, HCI, interaction, learning disabilities, machine learning, multimodal, multisensor, physiological sensors, Signal Detection Theory, student engagement.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1272