Volume 26, Issue 1

This paper addresses the role of conversational memory in Embodied Conversational Agents (ECAs). It describes an investigation into developing such a memory architecture and integrating it into an ECA. ECAs are virtual agents whose purpose is to engage in conversations with human users, typically through natural language speech. While several works in the literature seek to produce viable ECA dialog architectures, only a few authors have addressed the episodic memory architectures in conversational agents and their role in enhancing their intelligence. In this work, we propose, implement, and test a unified episodic memory architecture for ECAs. We describe a process that determines the prevalent contexts in the conversations obtained from the interactions. The process presented demonstrates the use of multiple techniques to extract and store relevant snippets from long conversations, most of whose contents are unremarkable and need not be remembered. The mechanisms used to store, retrieve, and recall episodes from previous conversations are presented and discussed. Finally, we test our episodic memory architecture to assess its effectiveness. The results indicate moderate success in some aspects of the memory-enhanced ECAs, as well as some work still to be done in other aspects.

Knowledge discovery in multiple databases offers many opportunities and challenges. We have given a number of motivating points on knowledge discovery in multiple databases. In view of further studies on this aspect, we highlight some domains that generated numerous problems on multiple related databases. Activities related to data preprocessing in a multi-database mining environment are also discussed. Important techniques of mining multiple databases are outlined. Many interesting patterns that originated out of multi-database environments are highlighted. We shall witness more research outcomes and investigations as the number of multi-database domains is on the rise.

Knowledge integrated model (KIM) is regarded as an effective and critical way to enhance efficiency of product collaborative development (PCD). However, it is much knotty to establish a unified description rule as there exists diverse and heterogeneous designer knowledge. In this paper, an approach based on ontology for KIM is proposed to straightforwardly descript heterogeneous knowledge and achieve a matching of knowledge and design mission objectives easily. First, a KIM of PCD is presented in accordance with the characteristics of product design activities. Hereafter, a knowledge transformation method based on “problem domain – functional domain” model is developed to accurately reflect customer expectations for new products, wherein, knowledge ontology tree including “customer creativity, emotional knowledge, customer needs, and basic knowledge” is constructed to standardize customer needs. Then, a knowledge matching function (KMF) and a Backus–Naur form (BNF) are introduced to measure similarity of request and candidate. Thereafter, a service engine (SE) including KMF and BNF is generated by the knowledge integrated system (KIS). Finally, simulations and experiments illustrate the effectiveness of the proposed methods and models.

Resource pooling in ad hoc networks deals with accumulating computing and network resources to implement network control schemes such as routing, congestion, traffic management, and so on. Pooling of resources can be accomplished using the distributed and dynamic nature of ad hoc networks to achieve collaboration between the devices. Ad hoc networks need a resource-pooling technique that offers quick response, adaptability, and reliability. In this context, we are proposing an opportunistic resource-pooling scheme that uses a cognitive computing model to accumulate the resources with faster resource convergence rate, reliability, and lower latency. The proposed scheme is implemented using the behaviors-observations-beliefs cognitive model, in which the resource-pooling decisions are made based on accumulated knowledge over various behaviors exhibited by nodes in ad hoc networks.

Association rules provide important knowledge that can be extracted from transactional databases. Owing to the massive exchange of information nowadays, databases become dynamic and change rapidly and periodically: new transactions are added to the database and/or old transactions are updated or removed from the database. Incremental mining was introduced to overcome the problem of maintaining previously generated association rules in dynamic databases. In this paper, we propose an efficient algorithm (IMIDB) for incremental itemset mining in large databases. The algorithm utilizes the trie data structure for indexing dynamic database transactions. Performance comparison of the proposed algorithm to recently cited algorithms shows that a significant improvement of about two orders of magnitude is achieved by our algorithm. Also, the proposed algorithm exhibits linear scalability with respect to database size.

Time-dependent channel variations in wireless systems have been modeled using autoregressive (AR), moving average, and AR moving average (ARMA) approaches, which in certain conditions fail to provide the most suitable description of the scenarios. It lowers the quality of service, increases the dependence on the traditional tapped delay line model, and requires more reference symbols as fading in the channel increases. Non-linear attributes in channels are best described by non-linear AR (NAR) and non-linear ARMA (NARMA) models, which capture the channel state information (CSI) better. Learning-based systems like artificial neural networks (ANN) are better equipped to deal with NAR and NARMA approximations of channels, recover CSI, and provide proper channel estimation due to their natural association with non-linear computing. Though decision feedback equalizers (DFE) are the traditional and preferred approaches to reduce the ill effects of channel-induced variations, these are unable to mitigate noise-triggered responses that ANNs can. Here, DFEs and special forms of ANNs are combined to recover CSI from NAR and NARMA approximations of time-varying channels. We especially configure a class of fully focused time delay neural network designed in split form in unitary and composite modes with a DFE to track real and imaginary components of signals. Experimental results establish the effectiveness of such hybrid tools in tracking time-varying non-linear channels covering International Telecommunication Union pedestrian to vehicular conditions.

Serial multi-class contour preserving classification can improve the representation of the contour of the data to improve the levels of classification accuracy for feed-forward neural network (FFNN). The algorithm synthesizes fundamental multi-class outpost vector (FMCOV) and additional multi-class outpost vector (AMCOV) at the decision boundary between consecutive classes of data to narrow the space of data. Both FMCOVs and AMCOVs will assist the FFNN to place the hyper-planes in such a way that can classify the data more accurately. However, the technique was designed to utilize only one processor. As a result, the execution time of the algorithm is significantly long. This article presents an improved version of the serial multi-class contour preserving classification that overcomes its time deficiency by utilizing thread-level parallelism to support parallel computing on multi-processor or multi-core system. The parallel algorithm distributes the data set and the processing of the FMCOV and AMCOV generators to be operated on available threads to increase the CPU utilization and the speedup factors of the FMCOV and AMCOV generators. The technique has been carefully designed to avoid data dependency issue. The experiments were conducted on both synthetic and real-world data sets. The experimental results confirm that the parallel multi-class contour preserving classification clearly outperforms the serial multi-class contour preserving classification in terms of CPU utilization and speedup factor.

Efficient QoS-based service selection from a pool of functionally substitutable web services (WS) for constructing composite WS is important for an efficient business process. Service composition based on diverse QoS requirements is a multi-objective optimization problem. Meta-heuristic techniques such as genetic algorithm (GA), particle swarm optimization (PSO), and variants of PSO have been extensively used for solving multi-objective optimization problems. The efficiency of any such meta-heuristic techniques lies with their rate of convergence and execution time. This article evaluates the efficiency of BAT and Hybrid BAT algorithms against the existing GA and Discrete PSO techniques in the context of service selection problems. The proposed algorithms are tested on the QWS data set to select the best fit services in terms of maximum aggregated end-to-end QoS parameters. Hybrid BAT is found to be efficient for service composition.

Recent advancements in science and technology and advances in the medical field have paved the way for the accumulation of huge amount of medical data in the digital repositories, where they are stored for future endeavors. Mining medical data is the most challenging task as the data are subjected to many social concerns and ethical issues. Moreover, medical data are more illegible as they contain many missing and misleading values and may sometimes be faulty. Thus, pre-processing tasks in medical data mining are of great importance, and the main focus is on feature selection, because the quality of the input determines the quality of the resultant data mining process. This paper provides insight to develop a feature selection process, where a data set subjected to constraint-governed association rule mining and interestingness measures results in a small feature subset capable of producing better classification results. From the results of the experimental study, the feature subset was reduced to more than 50% by applying syntax-governed constraints and dimensionality-governed constraints, and this resulted in a high-quality result. This approach yielded about 98% of classification accuracy for the Breast Cancer Surveillance Consortium (BCSC) data set.

The main problem of classical clustering technique is that it is easily trapped in the local optima. An attempt has been made to solve this problem by proposing the grey wolf algorithm (GWA)-based clustering technique, called GWA clustering (GWAC), through this paper. The search capability of GWA is used to search the optimal cluster centers in the given feature space. The agent representation is used to encode the centers of clusters. The proposed GWAC technique is tested on both artificial and real-life data sets and compared to six well-known metaheuristic-based clustering techniques. The computational results are encouraging and demonstrate that GWAC provides better values in terms of precision, recall, G-measure, and intracluster distances. GWAC is further applied for gene expression data set and its performance is compared to other techniques. Experimental results reveal the efficiency of the GWAC over other techniques.

The operational efficacy of the grid computing system depends mainly on the proper management of grid resources to carry out the various jobs that users send to the grid. The paper explores an alternative way of efficiently searching, matching, and allocating distributed grid resources to jobs in such a way that the resource demand of each grid user job is met. A proposal of resource selection method that is based on the concept of genetic algorithm (GA) using populations based on multisets is made. Furthermore, the paper presents a hybrid GA-based scheduling framework that efficiently searches for the best available resources for user jobs in a typical grid computing environment. For the proposed resource allocation method, additional mechanisms (populations based on multiset and adaptive matching) are introduced into the GA components to enhance their search capability in a large problem space. Empirical study is presented in order to demonstrate the importance of operator improvement on traditional GA. The preliminary performance results show that the proposed introduction of an additional operator fine-tuning is efficient in both speed and accuracy and can keep up with high job arrival rates.

As we are usually confronted with a large instance space for real-word data sets, it is significant to develop a useful and efficient multiple-instance learning (MIL) algorithm. MIL, where training data are prepared in the form of labeled bags rather than labeled instances, is a variant of supervised learning. This paper presents a novel MIL algorithm for an extreme learning machine called MI-ELM. A radial basis kernel extreme learning machine is adapted to approach the MIL problem using Hausdorff distance to measure the distance between the bags. The clusters in the hidden layer are composed of bags that are randomly generated. Because we do not need to tune the parameters for the hidden layer, MI-ELM can learn very fast. The experimental results on classifications and multiple-instance regression data sets demonstrate that the MI-ELM is useful and efficient as compared to the state-of-the-art algorithms.