By considering the dexterous hand manipulation problem as a hybrid system, we propose a mixed logic dynamical (MLD) modeling formulation which encapsulates phases of continuous motion, switching between types of motio...
详细信息
By considering the dexterous hand manipulation problem as a hybrid system, we propose a mixed logic dynamical (MLD) modeling formulation which encapsulates phases of continuous motion, switching between types of motion, and occurrence of impacts. We first formulates the multi-contact manipulation system into a general nonlinear dynamical equation subject to (in)equality and complementarity constraints, then transform the constrained system to a MLD system model. Based on the derived MLD model, dexterous hand manipulation can be realized optimally via mixed integer quadric programming (MIQP) algorithm. This modeling formulation and an optimization approach are applied to a whole body manipulation task as an example.
In the era of ICT, our way of learning has known several improvements and changes. The objective of new educational systems is not delivering the learning materials through Internet or electronic devices, but they aim...
详细信息
ISBN:
(纸本)9781728100036
In the era of ICT, our way of learning has known several improvements and changes. The objective of new educational systems is not delivering the learning materials through Internet or electronic devices, but they aim to use many technics and methods to enhance our learning process. Recently, increasing attention is given to these aspects such as: learning styles, learner profile, adaptive learning and their impact on learning, and how the individual characteristics and features may be supported in learning systems. These investigations are motivated by pedagogical theories that claim if we provide courses that meet the individual characteristics of learners, then it makes learning easier for them and increases the progression of their learning. Personalized learning takes into account the abilities, preferences, backgrounds, intellectual capacities, needs of learners, and learning styles, that helps the educational system to provide the appropriate activities and learning content for a particular learner. In this paper, we propose an ontological approach for the representation of learner profile and learning styles to simply use them for a personalized E-learning and to allow greater flexibility and reusability. In addition, the ontological representation of learners' profiles and learning styles gives a detailed description about them which allows the delivery of the pertinent content for each learner according to his preferences and characteristics.
Fuzzy Quantile Inference (FQI) is a novel method that builds a simple and efficient connective between probabilistic and fuzzy paradigms and allows the classification of noisy, imprecise and complex motions while usin...
详细信息
ISBN:
(纸本)9783642165832
Fuzzy Quantile Inference (FQI) is a novel method that builds a simple and efficient connective between probabilistic and fuzzy paradigms and allows the classification of noisy, imprecise and complex motions while using learning samples of suboptimal size. A comparative study focusing on the recognition of multiple stances from 3d motion capture data is conducted. Results show that, when put to the test with a dataset presenting challenges such as real biologically noisy" data, cross-gait differentials from one individual to another, and relatively high dimensionality (the skeletal representation has 57 degrees of freedom), FQI outperforms sixteen other known time-invariant classifiers.
Using big data theory to analyze athletes39; performance data, this paper finds out the changing characteristics of athletes39; performance. Using the principle of big data, we find the performance characteristics...
详细信息
The proceedings contain 35 papers. The special focus in this conference is on Data Management, Analytics and Innovation. The topics include: Enhanced Prediction of Heart Disease Using Particle Swarm optimization and R...
ISBN:
(纸本)9789811393631
The proceedings contain 35 papers. The special focus in this conference is on Data Management, Analytics and Innovation. The topics include: Enhanced Prediction of Heart Disease Using Particle Swarm optimization and Rough Sets with Transductive Support Vector Machines Classifier;dataCan: Robust Approach for Genome Cancer Data Analysis;dataAutism: An Early Detection Framework of Autism in Infants using Data Science;anaBus: A Proposed Sampling Retrieval Model for Business and Historical Data Analytics;abrupt Scene Change Detection Using Block Based Local Directional Pattern;a Framework for Web Archiving and Guaranteed Retrieval;business Intelligence Through Big Data Analytics, Data Mining and Machine learning;the Effect of Big Data on the Quality of Decision-Making in Abu Dhabi Government Organisations;The Impact of Technology Readiness on the Big Data Adoption Among UAE Organisations;identifying Phishing Through Web Content and Addressed Bar-Based Features;sports Data Analytics: A Case Study of off-Field Behavior of Players;phrase Based Information Retrieval Analysis in Various Search Engines Using Machine learning Algorithms;The Politics of Artificial Intelligence Behaviour and Human Rights Violation Issues in the 2016 US Presidential Elections: An Appraisal;crop Prediction Using Artificial Neural Network and Support Vector Machine;a Hybrid and Adaptive Approach for Classification of Indian Stock Market-Related Tweets;generative Adversarial Networks as an Advancement in 2D to 3D Reconstruction Techniques;impact of Artificial Intelligence on Human Resources;role of Activation Functions and Order of Input Sequences in Question Answering;gestTalk—Real-Time Gesture to Speech Conversion Glove;a Unified Framework for Outfit Design and Advice.
The estimation of the density of a population of behaviourally diverse agents based on limited sensor data is a challenging task. We employed different machine learning algorithms and assessed their suitability for so...
详细信息
ISBN:
(纸本)9783319729268;9783319729251
The estimation of the density of a population of behaviourally diverse agents based on limited sensor data is a challenging task. We employed different machine learning algorithms and assessed their suitability for solving the task of finding the approximate number of honeybees in a circular arena based on data from an autonomous stationary robot's short range proximity sensors that can only detect a small proportion of a group of bees at any given time. We investigate the application of different machine learning algorithms to classify datasets of pre-processed, highly variable sensor data. We present a new method for the estimation of the density of bees in an arena based on a set of rules generated by the algorithms and demonstrate that the algorithm can classify the density with good accuracy. This enabled us to create a robot society that is able to develop communication channels (heat, vibration and airflow stimuli) to an animal society (honeybees) on its own.
Deep Reinforcement learning (DRL) methods often rely on the meticulous tuning of hyperparameters to successfully resolve problems. One of the most influential parameters in optimization procedures based on stochastic ...
详细信息
ISBN:
(纸本)9781728187013
Deep Reinforcement learning (DRL) methods often rely on the meticulous tuning of hyperparameters to successfully resolve problems. One of the most influential parameters in optimization procedures based on stochastic gradient descent (SGD) is the learning rate. We investigate cyclical learning and propose a method for defining a general cyclical learning rate for various DRL problems. In this paper we present a method for cyclical learning applied to complex DRL problems. Our experiments show that, utilizing cyclical learning achieves similar or even better results than highly tuned fixed learning rates. This paper presents the first application of cyclical learning rates in DRL settings and is a step towards overcoming manual hyperparameter tuning.
This paper describes and evaluates T3, an algorithm that builds trees of depth at most three, and results in high accuracy whilst keeping the size of the tree reasonably small. T3 is an improvement over T2 in that it ...
详细信息
ISBN:
(纸本)3540440259
This paper describes and evaluates T3, an algorithm that builds trees of depth at most three, and results in high accuracy whilst keeping the size of the tree reasonably small. T3 is an improvement over T2 in that it builds larger trees and adopts a less greedy approach. T3 gave better results than both T2 and C4.5 when run against publicly available data sets: T3 decreased classification error on average by 47% and generalisation error by 29%, compared to T2;and T3 resulted in 46% smaller trees and 32% less classification error compared to C4.5. Due to its way of handling unknown values, T3 outperforms C4.5 in generalisation by 99% to 66%, on a specific medical dataset.
Experience in leaching engineering related subjects has Shown that a complementary approach combining theoretical and practical exercises is vital for effective learning. Increasingly, leaching institutions are offeri...
详细信息
ISBN:
(纸本)0769523161
Experience in leaching engineering related subjects has Shown that a complementary approach combining theoretical and practical exercises is vital for effective learning. Increasingly, leaching institutions are offering remote access to distant laboratories as part of an overall e-learning strategy. However, the majority of remote laboratories developed to date have suffered from a major deficiency, namely the provision of a web based environment that accurately recreates the group working and tutor driven experience of traditional on-campus based laboratories. This paper addresses one of these issues and presents an architecture for a collaborative learning environment for remote experimentation.
The Malian education system, and higher education in particular, is facing problems of various kinds: lack of infrastructure, materials and equipment, poor governance, and a shortage of sufficiently qualified human re...
详细信息
暂无评论