Volume 26, Issue 3

The formal description of weighted hypergraph partitioning problem is presented. We describe the solution of the weighted hypergraph partitioning problem based on the multi-level method. We propose the multi-level discrete particle swarm optimization refinement algorithm, whose each particle’s position in |V|-dimensional can be considered as the corresponded partitioning. During the refinement process of the uncoarsening phase, the algorithm projects successively each particle’s corresponded partitioning back to the next-level finer hypergraph, and the degree of particle’s freedom increases with the increase in solution space’s dimension. The algorithm also regards the gain of vertex as particle information for the heuristic search and successfully searches the solution space based on the intelligent behavior between individuals’ collaboration. Furthermore, the improved compressed storage format of weighted hypergraph is presented and the two-dimensional auxiliary array is designed for counting the vertices of each hypergraph in different partitions. The rapid method of calculating the vertex’s gain and the cut’s size are proposed to avoid traversing each vertex of hyperedge and reduce the algorithm’s time complexity and space complexity. Experimental results show that the algorithm not only can find the better partitioning of weighted hypergraph than the move-based method but also can improve the search capability of the refinement algorithm.

In order to mitigate the problems of premature convergence and low search accuracy that exist in traditional particle swarm optimization (PSO), this paper presents PSO with enhanced global search and local search (EGLPSO). In EGLPSO, most of the particles would be concentrated in global search at the beginning. Along with the iteration, the particles would slowly focus on local search. A new updating strategy would be used for global search, and a partial mutation strategy is applied to the leader particle of local search for a better position. During each iteration, the best particle of global search would exchange information with some particles of local search. EGLPSO is tested on a set of 12 benchmark functions, and it is also compared with other four PSO variants and another six well-known PSO variants. The experimental results showed that EGLPSO can greatly improve the performance of traditional PSO in terms of search accuracy, search efficiency, and global optimality.

Forgetting is an oft-forgotten art. Many artificial intelligence (AI) systems deliver good performance when first implemented; however, as the contextual environment changes, they become out of date and their performance degrades. Learning new knowledge is part of the solution, but forgetting outdated facts and information is a vital part of the process of renewal. However, forgetting proves to be a surprisingly difficult concept to either understand or implement. Much of AI is based on analogies with natural systems, and although all of us have plenty of experiences with having forgotten something, as yet we have only an incomplete picture of how this process occurs in the brain. A recent judgment by the European Court concerns the “right to be forgotten” by web index services such as Google. This has made debate and research into the concept of forgetting very urgent. Given the rapid growth in requests for pages to be forgotten, it is clear that the process will have to be automated and that intelligent systems of forgetting are required in order to meet this challenge.

This study presents a decision support tool that uses a fuzzy logic model of expert knowledge to assist in the decision-making process in the context of mitigating shipping CO 2 emissions. The issue of selecting a market-based shipping CO 2 emission mechanism, as they were presented by the International Maritime Organization (IMO), has generated much discussion over the last decade due to the complexity of the industry. We built a fuzzy logic system using the input and output variables as well as their range values that have been set from the IMO Expert Group study. We developed 27 fuzzy rules based on the literature and our domain knowledge, and we ran the fuzzy inference system for four of the proposed market-based measures. Finally, we evaluated our results and compared them with the IMO Expert Group study. Although not all measures responded the same, especially regarding the emission reductions, the percentage agreement is satisfactory in most of the cases (60–95%). The strength of the tool is that it synthesizes a large amount of information in a logical and transparent framework, and has the potential to have wider application in the context of market-based measures.

Clustering is an unsupervised kind of grouping of data points based on the similarity that exists between them. This paper applied a combination of particle swarm optimization and K-means for data clustering. The proposed approach tries to improve the performance of traditional partition clustering techniques such as K-means by avoiding the initial requirement of number of clusters or centroids for clustering. The proposed approach is evaluated using various primary and real-world datasets. Moreover, this paper also presents a comparison of results produced by the proposed approach and by the K-means based on clustering validity measures such as inter- and intra-cluster distances, quantization error, silhouette index, and Dunn index. The comparison of results shows that as the size of the dataset increases, the proposed approach produces significant improvement over the K-means partition clustering technique.

Automatic sign language recognition (SLR) is a current area of research as this is meant to serve as a substitute for sign language interpreters. In this paper, we present the design of a continuous SLR system that can extract out the meaningful signs and consequently recognize them. Here, we have used height of the hand trajectory as a salient feature for separating out the meaningful signs from the movement epenthesis patterns. Further, we have incorporated a unique set of spatial and temporal features for efficient recognition of the signs encapsulated within the continuous sequence. The implementation of an efficient hand segmentation and hand tracking technique makes our system robust to complex background as well as background with multiple signers. Experiments have established that our proposed system can identify signs from a continuous sign stream with a 92.8% spotting rate.

Finding the optimal number of clusters and the appropriate partitioning of the given dataset are the two major challenges while dealing with clustering. For both of these, cluster validity indices are used. In this paper, seven widely used cluster validity indices, namely DB index, PS index, I index, XB index, FS index, K index, and SV index, have been developed based on line symmetry distance measures. These indices provide the measure of line symmetry present in the partitioning of the dataset. These are able to detect clusters of any shape or size in a given dataset, as long as they possess the property of line symmetry. The performance of these indices is evaluated on three clustering algorithms: K -means, fuzzy- C means, and modified harmony search-based clustering (MHSC). The efficacy of symmetry-based validity indices on clustering algorithms is demonstrated on artificial and real-life datasets, six each, with the number of clusters varying from 2 to n,$\sqrt n ,$ where n is the total number of data points existing in the dataset. The experimental results reveal that the incorporation of line symmetry-based distance improves the capabilities of these existing validity indices in finding the appropriate number of clusters. Comparisons of these indices are done with the point symmetric and original versions of these seven validity indices. The results also demonstrate that the MHSC technique performs better as compared to other well-known clustering techniques. For real-life datasets, analysis of variance statistical analysis is also performed.

Wireless multimedia sensor networks (WMSNs) are usually resource constrained, and where the sensor nodes have limited bandwidth, energy, processing power, and memory. Hence, resource mapping is required in a WMSN, which is based on user linguistic quality of service (QoS) requirements and available resources to offer better communication services. This paper proposes an adaptive neuro fuzzy inference system (ANFIS)-based resource mapping for video communications in WMSNs. Each sensor node is equipped with ANFIS, which employs three inputs (user QoS request, available node energy, and available node bandwidth) to predict the quality of the video output in terms of varying number of frames/second with either fixed or varying resolution. The sensor nodes periodically measure the available node energy and also the bandwidth. The spatial query processing in the proposed resource mapping works as follows. (i) The sink node receives the user query for some event. (ii) The sink node sends the query through an intermediate sensor node(s) and cluster head(s) in the path to an event node. A cluster head-based tree routing algorithm is used for routing. (iii) The query passes through ANFIS of intermediate sensor nodes and cluster heads, where each node predicts the quality of the video output. (iv) The event node chooses the minimum quality among all cluster heads and intermediate nodes in the path and transmits the video output. The work is simulated in different network scenarios to test the performance in terms of predicted frames/second and frame format. To the best of our knowledge, the proposed resource mapping is the first work in the area of sensor networks. The trained ANFIS predicts the output video quality in terms of number of frames/second (or H.264 video format) accurately for the given input.

Differential evolution (DE) is a population-based algorithm using Darwinian and Mendel principles to find out an optimal solution to difficult problems. In this work, the dynamics of the DE algorithm are modeled by using a longitudinal social network. Because a population of the DE algorithm is improved in generations, each generation of DE algorithm is represented by one short-interval network. Each short-interval network is created by individuals contributing to population improvement. On the basis of this model, a new parent selection in the mutation operation is presented and a well-known benchmark set CEC 2013 Special Session on Real-Parameter Optimization (including 28 functions) is used to evaluate the performance of the proposed algorithm.

This paper presents a mathematically enhanced genetic algorithm (MEGA) using the mathematical properties of the single-machine scheduling of multiple jobs with a common due date. The objective of the problem is to minimize the sum of earliness and tardiness penalty costs in order to encourage the completion time of each job as close as possible to the common due date. The importance of the problem is derived from its NP-hardness and its ideal modeling of just-in-time concept. This philosophy becomes very significant in modern manufacturing and service systems, where policy makers emphasize that a job should be completed as close as possible to its due date. That is to avoid inventory costs and loss of customer’s goodwill. Five mathematical properties are identified and integrated into a genetic algorithm search process to avoid premature convergence, reduce computational effort, and produce high-quality solutions. The computational results demonstrate the significant impact of the introduced properties on the efficiency and effectiveness of MEGA and its competitiveness to state-of-the-art approaches.

Planning a trip not only depends on the traveling cost, time, and path, but also on the socio-economic status of the traveler. This paper attempts to introduce a new trip planning model that is able to work on real-time data with multiple socio-economic constraints. The proposed trip planning model processes real-time data to extract the relevant socio-economic attributes; later, it mines the most frequent as well as the feasible attributes to plan the trip. The relevance of the socio-economic constraints is defined using correlations, whereas the frequent as well as the feasible attributes are mined through the sequential pattern mining approach. Real-time travel information of about 38,303 trips was acquired from the Indian city of Hyderabad, and the proposed model was subjected to experimentation. The proposed model maintained a substantial trade-off between multiple performance metrics, though the trip mean model performed statistically.

With the extensive application of spatial databases to various fields ranging from remote sensing to geographical information systems, computer cartography, environmental assessment, and planning, discovery of interesting and hidden knowledge in the spatial databases is a considerable chore for classifying and using the spatial data and knowledge bases. The literature presents different spatial data mining methods to mine knowledge from spatial databases. In this paper, spatial association rules are mined to automatic grouping of spatial data objects using a candidate generation process with three constraint measures, such as support, confidence, and lift. Then, the proposed multiple kernel-based probabilistic clustering is applied to the associate vector to further group the spatial data objects. Here, membership probability based on probabilistic distance is used with multiple kernels, where exponential and tangential kernel functions are utilized. The performance of the proposed method is analyzed with three data sets of three different geometry types using the number of rules and clustering accuracy. From the experimentation, the results proved that the proposed multi-kernel probabilistic clustering algorithm achieved better accuracy as compared with the existing probabilistic clustering.

Existing systems for diagnosing heart diseases are time consuming, expensive, and error prone. Aiming at this, a detection algorithm for factors inducing heart diseases based on a particle swarm optimisation-support vector machine (PSO-SVM) optimised by association rules (ARs) was proposed. Firstly, AR was used to select features from a disease data set so as to train feature sets. Then, PSO-SVM was used to classify training and testing sets, and then the factors inducing heart diseases were analysed. Finally, the effectiveness and reliability of the proposed algorithm was verified by experiments on the UCI Cleveland data set with confidence as the index. The experimental results showed that females have less risk of having a heart attack than males. Irrespective of gender, once diagnosed with chest pain without symptoms and angina caused by exercise, people are more likely to suffer from heart disease. Moreover, compared with another two advanced classification algorithms, the proposed algorithm showed better classification performance and therefore can be used as a powerful tool to help doctors diagnose and treat heart diseases.

Due to the ever-increasing number of digital lecture libraries and lecture video portals, the challenge of retrieving lecture videos has become a very significant and demanding task in recent years. Accordingly, the literature presents different techniques for video retrieval by considering video contents as well as signal data. Here, we propose a lecture video retrieval system using multimodal features and probability extended nearest neighbor (PENN) classification. There are two modalities utilized for feature extraction. One is textual information, which is determined from the lecture video using optical character recognition. The second modality utilized to preserve video content is local vector pattern. These two modal features are extracted, and the retrieval of videos is performed using the proposed PENN classifier, which is the extension of the extended nearest neighbor classifier, by considering the different weightages for the first-level and second-level neighbors. The performance of the proposed video retrieval is evaluated using precision, recall, and F -measure, which are computed by matching the retrieved videos and the manually classified videos. From the experimentation, we proved that the average precision of the proposed PENN+VQ is 78.3%, which is higher than that of the existing methods.