Category: World Wide Web

Abstract

Dictionary learning for sparse coding has been successfully used in different domains, however, has never been employed for the interesting itemset mining. In this paper, we formulate an optimization problem for extracting a sparse representation of itemsets and show that the discrete nature of itemsets makes it NP-hard. An efficient approximation algorithm is presented which greedily solves maximum set cover to reduce overall compression loss. Furthermore, we incorporate our sparse representation algorithm into a layered convolutional model to learn nonredundant dictionary items. Following the intuition of deep learning, our convolutional dictionary learning approach convolves learned dictionary items and discovers statistically dependent patterns using chi-square in a hierarchical fashion; each layer having more abstract and compressed dictionary than the previous. An extensive empirical validation is performed on thirteen datasets, showing better interpretability and semantic coherence of our approach than two existing state-of-the-art methods.

Abstract

Individuals’ interests and concerning topics are generally changing over time, with strong impact on their behaviors in social media. Accordingly, designing an intelligent recommender system which can adapt with the temporal characters of both factors becomes a significant research task. Namely both of temporal user interests and topics are important factors for improving the performance of recommender systems. In this paper, we suppose that users’ current interests and topics are transferred from the previous time step with a Markov property. Based on this idea, we focus on designing a novel dynamic recommender model based on collective factorization, named Temporal and Topic-Aware Recommender Model (TTARM), which can express the transition process of both user interests and relevant topics in fine granularity. It is a hybrid recommender model which joint Collaborative Filtering (CF) and Content-based recommender method, thus can produce promising recommendations about both existing and newly published items. Experimental results on two real life data sets from CiteULike and MovieLens, demonstrate the effectiveness of our proposed model.

Abstract

The increasingly serious problem of traffic congestion has become a critical issue that urban managers need to focus on. However, as urban scale and structure have already taken shape, the use of existing road resources to achieve effective route selection for vehicles is the key to solving this traffic congestion problem. Existing research has mainly focused on the following three points: (1) algorithms for controlling traffic signal lamp period at single intersections; (2) route recommendation algorithms for a single vehicle; and (3) route recommendation algorithms based on the traffic history experienced by a vehicle. These studies, however, have the following limitations: (1) the evaluation factor is singular, and therefore, cannot fully express the advantages and disadvantages of the route selection method; (2) real-time route selection is absent; (3) route selection for a single vehicle is ineffective in avoiding local congestion. In view of these problems, this paper proposes an improved quantum genetic algorithm (IQGA) to solve the problem of traffic congestion in route selection. The algorithm includes the following: (1) proposing a quantum chromosome initialization strategy (QCIS) to convert and code real traffic conditions and to construct quantum chromosomes based on the quantum coding for vehicles and roads; (2) proposing a quantum chromosome mapping algorithm (QCMA) to transform the calculation bits of quantum chromosomes into the results of route selection for different vehicles; (3) proposing a contemporary optimal solution decision strategy (COSDS) to judge the current route selection results; (4) proposing a quantum update algorithm (QUA) to update and iterate the quantum coding of the population. Two types of experiments were conducted in this study: (1) Artificial traffic networks with different scales were designed to carry out comparative experiments between IQGA and other algorithms. The experimental results show that IGQA has better robustness and adaptive ability. (2) Comparative experiments on an actual urban traffic network verified the high-performance and real-time performance capabilities of IQGA.

Abstract

With the emergence of many crowdsourcing platforms, crowdsourcing has gained much attention. Spatial crowdsourcing is a rapidly developing extension of the traditional crowdsourcing, and its goal is to organize workers to perform spatial tasks. Route recommendation is an important concern in spatial crowdsourcing. In this paper, we define a novel problem called the Online Delivery Route Recommendation (OnlineDRR) problem, in which the income of a single worker is maximized under online scenarios. It is proved that no deterministic online algorithm for this problem has a constant competitive ratio. We propose an algorithm to balance three influence factors on a worker’s choice in terms of which task to undertake next. In order to overcome its drawbacks resulting from the dynamic nature of tasks, we devise an extended version which attaches gradually increased importance to the destination of the worker over time. Extensive experiments are conducted on both synthetic and real-world datasets and the results prove the algorithms proposed in this paper are effective and efficient.

Abstract

Spatial prevalent co-location pattern mining is to discover interesting and potentially useful patterns from spatial data, and it plays an important role in identifying spatially correlated features in many domains, such as Earth science and Public transportation. Existing approaches in this field only take into account the clique instances where feature instances form a clique. However, they may neglect some important spatial correlations among features in practice. In this paper, we introduce star participation instances to measure the prevalence of co-location patterns such that spatially correlated instances which cannot form cliques will also be properly considered. Then we propose a new concept called sub-prevalent co-location patterns (SPCP) based on the star participation instances. Furthermore, two efficient algorithms -- the prefix-tree-based algorithm (PTBA) and the partition-based algorithm (PBA) -- are proposed to mine all the maximal sub-prevalent co-location patterns (MSPCP) in a spatial data set. PTBA uses a typical candidate generate-and-test way starting from candidates with the longest pattern-size, while PBA adopts a step-by-step manner starting from 3-size core patterns. We demonstrate the significance of our proposed new concepts as well as the efficiency of our algorithms through extensive experiments.

Abstract

The fast and explosive growth of digital data in social media and World Wide Web has led to numerous opportunities and research activities in multimedia big data. Among them, disaster management applications have attracted a lot of attention in recent years due to its impacts on society and government. This study targets content analysis and mining for disaster management. Specifically, a multimedia big data framework based on the advanced deep learning techniques is proposed. First, a video dataset of natural disasters is collected from YouTube. Then, two separate deep networks including a temporal audio model and a spatio-temporal visual model are presented to analyze the audio-visual modalities in video clips effectively. Thereafter, the results of both models are integrated using the proposed fusion model based on the Multiple Correspondence Analysis (MCA) algorithm which considers the correlations between data modalities and final classes. The proposed multimodal framework is evaluated on the collected disaster dataset and compared with several state-of-the-art single modality and fusion techniques. The results demonstrate the effectiveness of both visual model and fusion model compared to the baseline approaches. Specifically, the accuracy of the final multi-class classification using the proposed MCA-based fusion reaches to 73% on this challenging dataset.

Abstract

An individual-like intelligent artifact is a special kind of humanoid which resembles a human being in assimilating aspects of its real human counterpart’s cognition and neurological functions. Such an individual-like intelligent artifact could have a number of far-reaching applications, such as in creating a digital clone of an individual and bringing about forms of digital immortality. Although such intelligent artifacts have been created in various forms, such as physical robots or digital avatars, these creations are still far from modeling the inner cognitive and neurological mechanisms of an individual human. To imbue individual-like intelligent artifacts with the characteristics of individuals, we propose a Personal Character Model that consists of personality, the characteristics of affect, behavior, and cognition, and the relations between these characteristics. According to differential psychology and personality psychology, personality is the set of essential characteristics that make a person unique whereas characteristics in affect, behavior, and cognition explain a person’s stable and abstract personality in their diverse daily behavior. In addition, relations among these characteristics serve as a bridge from one characteristic to another. To illustrate the computing process of the personal character model, we first designed three experiments to collect physiological data and behavior data from twenty participants. Then we selected data features from the collected data using correlational analysis. Finally, we computed several representative characteristics from selected data features and represented the computed results.

Abstract

An individual-like intelligent artifact is a special kind of humanoid which resembles a human being in assimilating aspects of its real human counterpart’s cognition and neurological functions. Such an individual-like intelligent artifact could have a number of far-reaching applications, such as in creating a digital clone of an individual and bringing about forms of digital immortality. Although such intelligent artifacts have been created in various forms, such as physical robots or digital avatars, these creations are still far from modeling the inner cognitive and neurological mechanisms of an individual human. To imbue individual-like intelligent artifacts with the characteristics of individuals, we propose a Personal Character Model that consists of personality, the characteristics of affect, behavior, and cognition, and the relations between these characteristics. According to differential psychology and personality psychology, personality is the set of essential characteristics that make a person unique whereas characteristics in affect, behavior, and cognition explain a person’s stable and abstract personality in their diverse daily behavior. In addition, relations among these characteristics serve as a bridge from one characteristic to another. To illustrate the computing process of the personal character model, we first designed three experiments to collect physiological data and behavior data from twenty participants. Then we selected data features from the collected data using correlational analysis. Finally, we computed several representative characteristics from selected data features and represented the computed results.

Abstract

As a common technology in social network, clustering has attracted lots of research interest due to its high performance, and many clustering methods have been presented. The most of existing clustering methods are based on unsupervised learning. In fact, we usually can obtain some/few labeled samples in real applications. Recently, several semi-supervised clustering methods have been proposed, while there is still much space for improvement. In this paper, we aim to tackle two research questions in the process of semi-supervised clustering: (i) How to learn more discriminative feature representations to boost the process of the clustering; (ii) How to effectively make use of both the labeled and unlabeled data to enhance the performance of clustering. To address these two issues, we propose a novel semi-supervised clustering approach based on deep metric learning (SCDML) which leverages deep metric learning and semi-supervised learning effectively in a novel way. To make the extracted features of the contribution of data more representative and the label propagation network more suitable for real applications, we further improve our approach by adopting triplet loss in deep metric learning network and combining bedding with label propagation strategy to dynamically update the unlabeled to labeled data, which is named as semi-supervised clustering with deep metric learning and graph embedding (SCDMLGE). SCDMLGE enhances the robustness of metric learning network and promotes the accuracy of clustering. Substantial experimental results on Mnist, CIFAR-10, YaleB, and 20-Newsgroups benchmarks demonstrate the high effectiveness of our proposed approaches.