Using the cloud to develop applications supporting geo-collaborative Situated Learning

Situated Learning stresses the importance of the context in which learning takes place. It has been therefore frequently associated with informal learning or learning outside the classroom. Cloud technologies can play an important role supporting this type of learning, since it requires ubiquitous computing support, connectivity and access to data across various scenarios: on the field, in the classroom, at home, etc. In this paper we first present the situated learning theory and how we can take advantage of services offered by Cloud Computing to implement computer applications implementing learning activities based on this theory, providing pertinent geographical information and discussion boards. Next we propose a software architecture schema which can be used as a basis for integrating existing cloud services into new applications supporting learning activities. Then we present two examples developed with this approach with its viability and advantages. These are discussed in the concluding chapter.     

A Kernel Approach for Semisupervised Metric Learning

While distance function learning for supervised learning tasks has a long history, extending it to learning tasks with weaker supervisory information has only been studied recently. In particular, some methods have been proposed for semisupervised metric learning based on pairwise similarity or dissimilarity information. In this paper, we propose a kernel approach for semisupervised metric learning and present in detail two special cases of this kernel approach. The metric learning problem is thus formulated as an optimization problem for kernel learning. An attractive property of the optimization problem is that it is convex and, hence, has no local optima. While a closed-form solution exists for the first special case, the second case is solved using an iterative majorization procedure to estimate the optimal solution asymptotically. Experimental results based on both synthetic and real-world data show that this new kernel approach is promising for nonlinear metric learning     

Supervised learning in a recurrent network of rate-model neurons exhibiting frequency adaptation

For gradient descent learning to yield connectivity consistent with real biological networks, the simulated neurons would have to include more realistic intrinsic properties such as frequency adaptation. However, gradient descent learning cannot be used straightforwardly with adapting rate-model neurons because the derivative of the activation function depends on the activation history. The objectives of this study were to (1) develop a simple computational approach to reproduce mathematical gradient descent and (2) use this computational approach to provide supervised learning in a network formed of rate-model neurons that exhibit frequency adaptation.The results of mathematical gradient descent were used as a reference in evaluating the performance of the computational approach. For this comparison, standard (nonadapting) rate-model neurons were used for both approaches. The only difference was the gradient calculation: the mathematical approach used the derivative at a point in weight space, while the computational approach used the slope for a step change in weight space. Theoretically, the results of the computational approach should match those of the mathematical approach, as the step size is reduced but floating-point accuracy formed a lower limit to usable step sizes. A systematic search for an optimal step size yielded a computational approach that faithfully reproduced the results of mathematical gradient descent.The computational approach was then used for supervised learning of both connection weights and intrinsic properties of rate-model neurons to convert a tonic input into a phasic-tonic output pattern. Learning produced biologically realistic connectivity that essentially used a monosynaptic connection from the tonic input neuron to an output neuron with strong frequency adaptation as compared to a complex network when using nonadapting neurons. Thus, more biologically realistic connectivity was achieved by implementing rate-model neurons with more realistic intrinsic properties. Our computational approach could be applied to learning of other neuron properties.     

A formative assessment-based mobile learning approach to improving the learning attitudes and achievements of students

The advancement of mobile and wireless communication technologies has encouraged an increasing number of studies concerning mobile learning, in which students are able to learn via mobile devices without being limited by space and time; in particular, the students can be situated in a real-world scenario associated with the learning content. Although such an approach seems interesting to the students, researchers have emphasized the need for well-designed learning support in order to improve the students’ learning achievements. Therefore, it has become an important issue to develop methodologies or tools to assist the students to learn in a mobile learning environment. Based on this perspective, this study proposes a formative assessment-based approach for improving the learning achievements of students in a mobile learning environment. A mobile learning environment has been developed based on this approach, and an experiment on a local culture course has been conducted in southern Taiwan to evaluate its effectiveness. The experimental results show that the proposed approach not only promotes the students’ learning interest and attitude, but also improves their learning achievement.     

超分子连接性指数对醇类化合物定量结构-保留关系研究

基于分子间弱相互作用,提出一种拓扑指数——超分子连接性指数,运用该指数对醇类化合物定量结构-保留关系进行了研究。结果显示超分子连接性指数~1X_P和~6X_(Pc)与醇类化合物保留值显著相关,相关系数高达0.99。表明超分子连接性指数可成功用于醇类化合物的定量结构一保留关系研究。     

TCLAB: A New Topology Control Protocol in Cognitive MANETs Based on Learning Automata

The mobility of the nodes and their limited energy supply in mobile ad hoc networks (MANETs) complicates network conditions. Having an efficient topology control mechanism in the MANET is very important and can reduce the interference and energy consumption in the network. Indeed, since current networks are highly complex, an efficient topology control is expected to be able to adapt itself to the changes in the environment drawing upon a preventive approach and without human intervention. To accomplish this purpose, the present paper proposes a learning automata-based topology control method within a cognitive approach. This approach deals with adding cognition to the entire network protocol stack to achieve stack-wide and network-wide performance goals. In this protocol, two cognitive elements are embedded at each node: one for transmission power control, and the other for channel control. The first element estimates the probability of link connectivity, and then, in a non-cooperative game of learning automata, it sets the proper power for the corresponding node. Subsequently, the second element allocates efficient channel to the corresponding node, again using learning automata. Having a cognitive network perspective to control the topology of the network brings about many benefits, including a self-aware and self-adaptive topology control method and the ability of nodes to self-adjust dynamically. The experimental results of the study show that the proposed method yields more improvement in the quality of service (QoS) parameters of throughput and end-to-end delay more than do the other methods.     

Hebbian learning of recurrent connections: a geometrical perspective

We show how a Hopfield network with modifiable recurrent connections undergoing slow Hebbian learning can extract the underlying geometry of an input space. First, we use a slow and fast analysis to derive an averaged system whose dynamics derives from an energy function and therefore always converges to equilibrium points. The equilibria reflect the correlation structure of the inputs, a global object extracted through local recurrent interactions only. Second, we use numerical methods to illustrate how learning extracts the hidden geometrical structure of the inputs. Indeed, multidimensional scaling methods make it possible to project the final connectivity matrix onto a Euclidean distance matrix in a high-dimensional space, with the neurons labeled by spatial position within this space. The resulting network structure turns out to be roughly convolutional. The residual of the projection defines the nonconvolutional part of the connectivity, which is minimized in the process. Finally, we show how restricting the dimension of the space where the neurons live gives rise to patterns similar to cortical maps. We motivate this using an energy efficiency argument based on wire length minimization. Finally, we show how this approach leads to the emergence of ocular dominance or orientation columns in primary visual cortex via the self-organization of recurrent rather than feedforward connections. In addition, we establish that the nonconvolutional (or long-range) connectivity is patchy and is co-aligned in the case of orientation learning.     

Distributed learning automata based approach to inferring urban structure via traffic flow

Traffic flow can be used as a reference for knowledge generation, which is highly important in urban planning. One of the significant applications of traffic data is decision making about the structure of roads connecting zones of a city. It leads us to an optimal connection between important areas like business centers, shopping malls, construction sites, residential complexes, and other parts of a city which is the motivation of this research. The main question is how to infer the optimal connectivity network considering the current structure of an urban area and time-varying traffic dynamics. Therefore a novel formulation is created in this paper to solve the optimization problem using available data. A proposed algorithm is presented to infer the optimal structure that is a distributed learning automata-based approach. A matrix called estimated optimal connectivity represents the favorite structure and it is optimized utilizing signals about the current system and traffic dynamics from the environment. Two types of data, including synthetic and real-world, are used to show the algorithm’s ability. After many experiments, the algorithm showed capability of optimizing the structure by finding new paths connecting the most correlated areas.

     

Multiple domain feature mapping: a methodology based on deep models of features

In the research described in this paper, an approach that utilizes deep models of features to transform a component design represented by neutral features into domain-specific features has been developed. The neutral features are known as feature-oriented generic shapes (FOGSs). The proposed approach provides the flexibility needed to represent both the deep and shallow knowledge required in feature mapping. A deep model of a feature is represented in the form of a face connectivity graph (FCG) that embodies deep knowledge about its geometry, while other non-geometrical information can be represented as rules or procedural functions. By comparing the original faces of a product model with those of the resultant evaluated boundary model, faces of interest can be easily extracted and described using FCGs. A FCG can then be examined to determine its class and the relevant parameters for applications in such domains as process planning. The mapping shell is designed with layered architecture that makes it highly appropriate for implementation using blackboard technology.     

Quantifying connectivity in wireless sensor networks with grid-based deployments

Measuring network connectivity under grid-based deployment in 3D space is a challenging problem in wireless sensor networks (WSNs). Solving such a problem becomes an even more intricate task with realistic deployment factors such as placement uncertainty and hindrances to wireless communication channels. While much work has been published on optimizing connectivity, only a few papers have addressed such realistic aspects which cause severe connectivity problems in practice. In this paper, we introduce a novel grid-based deployment metric, called Average Connectivity Percentage in order to characterize the deployed network connectivity when sensor placements are subject to random errors around their corresponding grid locations. A generic approach is proposed to assess and evaluate the proposed metric. This generic approach is independent of the grid-shape, random error distributions, and different environment-based channel characteristics. We apply the generic approach in two practical deployment scenarios: the grid-based deployment with bounded uniform errors and with unbounded normal errors. In both cases, the average connectivity percentage is computed numerically and verified via extensive simulations. Based on the numerical results, quantified effects of positioning errors and grid edge length on the average connectivity percentage are outlined.     

An approach to online identification of Takagi-Sugeno fuzzy models.

An approach to the online learning of Takagi-Sugeno (TS) type models is proposed in the paper. It is based on a novel learning algorithm that recursively updates TS model structure and parameters by combining supervised and unsupervised learning. The rule-base and parameters of the TS model continually evolve by adding new rules with more summarization power and by modifying existing rules and parameters. In this way, the rule-base structure is inherited and up-dated when new data become available. By applying this learning concept to the TS model we arrive at a new type adaptive model called the Evolving Takagi-Sugeno model (ETS). The adaptive nature of these evolving TS models in combination with the highly transparent and compact form of fuzzy rules makes them a promising candidate for online modeling and control of complex processes, competitive to neural networks. The approach has been tested on data from an air-conditioning installation serving a real building. The results illustrate the viability and efficiency of the approach. The proposed concept, however, has significantly wider implications in a number of fields, including adaptive nonlinear control, fault detection and diagnostics, performance analysis, forecasting, knowledge extraction, robotics, behavior modeling.     

基于Adaboost算法的人脸检测

该文提出了一种基于改进的Adaboost算法的人脸检测方法.Adaboost是一种构建准确分类器的学习算法,它将一族弱学习算法通过一定规则结合成为一个强学习算法,从而通过样本训练得到一个识别准确率理想的分类器.但是,Adaboost在有高噪音样本的情况下,有可能发生过配现象,该文在Adaboost算法的基础上,对其权值更新规则做了改进,并结合PCA进行人脸检测.仿真试验表明,该方法具有良好的性能,同时可以在一定程度上有效防止过配现象的发生.     

Feature elimination based random subspace ensembles learning for ECG arrhythmia diagnosis

Various methods for ensembles selection and classifier combination have been designed to optimize the performance of ensembles of classifiers. However, use of large number of features in training data can affect the classification performance of machine learning algorithms. The objective of this paper is to represent a novel feature elimination (FE) based ensembles learning method which is an extension to an existing machine learning environment. Here the standard 12 lead ECG signal recordings data have been used in order to diagnose arrhythmia by classifying it into normal and abnormal subjects. The advantage of the proposed approach is that it reduces the size of feature space by way of using various feature elimination methods. The decisions obtained from these methods have been coalesced to form a fused data. Thus the idea behind this work is to discover a reduced feature space so that a classifier built using this tiny data set would perform no worse than a classifier built from the original data set. Random subspace based ensembles classifier is used with PART tree as base classifier. The proposed approach has been implemented and evaluated on the UCI ECG signal data. Here, the classification performance has been evaluated using measures such as mean absolute error, root mean squared error, relative absolute error, F-measure, classification accuracy, receiver operating characteristics and area under curve. In this way, the proposed novel approach has provided an attractive performance in terms of overall classification accuracy of 91.11 % on unseen test data set. From this work, it is shown that this approach performs well on the ensembles size of 15 and 20.     

Real-time learning capability of neural networks

In some practical applications of neural networks, fast response to external events within an extremely short time is highly demanded and expected. However, the extensively used gradient-descent-based learning algorithms obviously cannot satisfy the real-time learning needs in many applications, especially for large-scale applications and/or when higher generalization performance is required. Based on Huang's constructive network model, this paper proposes a simple learning algorithm capable of real-time learning which can automatically select appropriate values of neural quantizers and analytically determine the parameters (weights and bias) of the network at one time only. The performance of the proposed algorithm has been systematically investigated on a large batch of benchmark real-world regression and classification problems. The experimental results demonstrate that our algorithm can not only produce good generalization performance but also have real-time learning and prediction capability. Thus, it may provide an alternative approach for the practical applications of neural networks where real-time learning and prediction implementation is required.     

Automatic design synthesis with artificial intelligence techniques

Design synthesis represents a highly complex task in the field of industrial design. The main difficulty in automating it is the definition of the design and performance spaces, in a way that a computer can generate optimum solutions. Following a different line from the machine learning, and knowledge-based methods that have been proposed, our approach considers design synthesis as an optimization problem. From this outlook, neural networks and genetic algorithms can be used to implement the fitness function and the search method needed to achieve optimum design. The proposed method has been tested in designing a telephone handset. Although the objective of this application is based on esthetic and ergonomic cues (subjective information), the algorithm successfully converges to good solutions.     

A hybrid recommendation algorithm adapted in e-learning environments

With the rapid development of online learning technology, a huge amount of e-learning materials have been generated which are highly heterogeneous and in various media formats. Besides, e-learning environments are highly dynamic with the ever increasing number of learning resources that are naturally distributed over the network. On the other hand, in the online learning scenario, it is very difficult for users without sufficient background knowledge to choose suitable resources for their learning. In this paper, a hybrid recommender system is proposed to recommend learning items in users’ learning processes. The proposed method consists of two steps: (1) discovering content-related item sets using item-based collaborative filtering (CF), and (2) applying the item sets to sequential pattern mining (SPM) algorithm to filter items according to common learning sequences. The two approaches are combined to recommend potentially useful learning items to guide users in their current learning processes. We also apply the proposed approach to a peer-to-peer learning environment for resource pre-fetching where a central directory of learning items is not available. Experiments are conducted in a centralized and a P2P online learning systems for the evaluation of the proposed method and the results show good performance of it.     

A contextual game-based learning approach to improving students' inquiry-based learning performance in social studies courses

Inquiry-based learning, an effective instructional strategy, can be in the form of a problem or task for triggering student engagement. However, how to situate students in meaningful inquiry activities remains to be settled, especially for social studies courses. In this study, a contextual educational computer game is developed to improve students' learning performance based on an inquiry-based learning strategy. An experiment has been conducted on an elementary school social studies course to evaluate the effects of the proposed approach on the inquiry-based learning performances of students with different learning styles. The experimental results indicate that the proposed approach effectively enhanced the students' learning effects in terms of their learning achievement, learning motivation, satisfaction degree and flow state. Furthermore, it is also found that the proposed approach benefited the “active” learning style students more than the “reflective” style students in terms of learning achievement. This suggests the need to provide additional supports to students with particular learning styles in the future.     

干扰车载网络中增强连通性的资源分配算法

随着车载网络中各种业务的飞速增长,网络密集程度不断增加,因此,愈发严重的干扰问题对网络的连通性构成了很大的挑战。已有研究中网络的连通性仅由信号强度或车辆之间的距离确定,而没有考虑资源分配引起的干扰对网络连通性的影响。针对这个问题,为了表征网络中资源与干扰对连通性的影响,使用图论对网络连通性进行了建模,定义了与资源分配相关的连通性度量指标;利用染色理论对能够保证网络连通性的所需资源数目的最小值进行了分析;提出了一种基于最小生成树的资源分配算法,以改善网络的连通性。仿真结果证实了相比其他算法,该算法能够提高车载网络的连通性。     

A multi-expert approach for developing testing and diagnostic systems based on the concept-effect model

With the popularization of computer and communication technologies, researchers have attempted to develop computer-assisted testing and diagnostic systems to help students improve their learning performance on the Internet. In developing a diagnostic system for detecting students’ learning problems, it is difficult for individual teachers to address the exact relationships between the test items and the concepts. To cope with this problem, this study proposes an innovative approach to eliciting and integrating the weightings of test item-concept relationships from multiple experts. Based on the proposed approach, a testing and diagnostic system has been implemented; moreover, an experiment was conducted to evaluate the performance of our approach. By analyzing the results from four groups of students using learning suggestions provided by different models, it was found that the learning performance of the students who received learning suggestions by applying the innovative approach was significantly better than for those who received guidance based on the original model.