Intelligent Data Analysis - Volume 24, issue 6

Article Type: Editorial

DOI: 10.3233/IDA-200016

Citation: Intelligent Data Analysis, vol. 24, no. 6, pp. 1235-1237, 2020

Authors: Wu, Xu | Yang, Youlong | Ren, Lingyu

Article Type: Research Article

Abstract: Class imbalance is often a problem in various real-world datasets, where one class contains a small number of data and the other contains a large number of data. It is notably difficult to develop an effective model using traditional data mining and machine learning algorithms without using data preprocessing techniques to balance the dataset. Oversampling is often used as a pretreatment method for imbalanced datasets. Specifically, synthetic oversampling techniques focus on balancing the number of training instances between the majority class and the minority class by generating extra artificial minority class instances. However, the current oversampling techniques simply consider the …imbalance of quantity and pay no attention to whether the distribution is balanced or not. Therefore, this paper proposes an entropy difference and kernel-based SMOTE (EDKS) which considers the imbalance degree of dataset from distribution by entropy difference and overcomes the limitation of SMOTE for nonlinear problems by oversampling in the feature space of support vector machine classifier. First, the EDKS method maps the input data into a feature space to increase the separability of the data. Then EDKS calculates the entropy difference in kernel space, determines the majority class and minority class, and finds the sparse regions in the minority class. Moreover, the proposed method balances the data distribution by synthesizing new instances and evaluating its retention capability. Our algorithm can effectively distinguish those datasets with the same imbalance ratio but different distribution. The experimental study evaluates and compares the performance of our method against state-of-the-art algorithms, and then demonstrates that the proposed approach is competitive with the state-of-art algorithms on multiple benchmark imbalanced datasets. Show more

Keywords: Imbalanced dataset, oversampling, entropy difference, kernel space, SVM

DOI: 10.3233/IDA-194761

Citation: Intelligent Data Analysis, vol. 24, no. 6, pp. 1239-1255, 2020

Authors: Zhao, Pinlong | Han, Zefeng | Yin, Qing | Li, Shuxiao | Wu, Ou

Article Type: Research Article

Abstract: Text sentiment analysis is an important natural language processing (NLP) task and has received considerable attention in recent years. Numerous deep-learning based methods have been proposed in previous literature in terms of new deep neural networks (DNN) including new embedding strategies, new attention mechanisms, and new encoding layers. In this study, an alternative technical path is investigated to further improve the state-of-the-art performance of text sentiment analysis. An new effective learning framework is proposed that combines knowledge distillation and sample selection. A dually-born-again network (DBAN) is presented in which the teacher network and the student network are simultaneously trained through …an iterative approach. A selection gate is defined to deal with training samples which are useless or even harmful for model training. Moreover, both the DBAN and sample selection are further improved by ensemble. The proposed framework can improve the existing state-of-the-art DNN models in sentiment analysis. Experimental results indicate that the proposed framework enhances the performances of existing networks. In addition, DBAN outperforms existing born-again network. Show more

Keywords: Classification, deep neural network, knowledge distillation, sample selection

DOI: 10.3233/IDA-194909

Citation: Intelligent Data Analysis, vol. 24, no. 6, pp. 1257-1271, 2020

Authors: Matsuda, Momo | Morikuni, Keiichi | Imakura, Akira | Ye, Xiucai | Sakurai, Tetsuya

Article Type: Research Article

Abstract: Irregular features disrupt the desired classification. In this paper, we consider aggressively modifying scales of features in the original space according to the label information to form well-separated clusters in low-dimensional space. The proposed method exploits spectral clustering to derive scaling factors that are used to modify the features. Specifically, we reformulate the Laplacian eigenproblem of the spectral clustering as an eigenproblem of a linear matrix pencil whose eigenvector has the scaling factors. Numerical experiments show that the proposed method outperforms well-established supervised dimensionality reduction methods for toy problems with more samples than features and real-world problems with more features …than samples. Show more

Keywords: Dimensionality reduction, spectral clustering, feature scaling, machine learning

DOI: 10.3233/IDA-194942

Citation: Intelligent Data Analysis, vol. 24, no. 6, pp. 1273-1287, 2020

Authors: Sopchoke, Sirawit | Fukui, Ken-ichi | Numao, Masayuki

Article Type: Research Article

Abstract: In this research, we combine relational learning with multi-domain to develop a formal framework for a recommendation system. The design of our framework aims at: (i) constructing general rules for recommendations, (ii) providing suggested items with clear and understandable explanations, (iii) delivering a broad range of recommendations including novel and unexpected items. We use relational learning to find all possible relations, including novel relations, and to form the general rules for recommendations. Each rule is represented in relational logic, a formal language, associating with probability. The rules are used to suggest the items, in any domain, to the user whose …preferences or other properties satisfy the conditions of the rule. The information described by the rule serves as an explanation for the suggested item. It states clearly why the items are chosen for the users. The explanation is in if-then logical format which is unambiguous, less redundant and more concise compared to a natural language used in other explanation recommendation systems. The explanation itself can help persuade the user to try out the suggested items, and the associated probability can drive the user to make a decision easier and faster with more confidence. Incorporating information or knowledge from multiple domains allows us to broaden our search space and provides us with more opportunities to discover items which are previously unseen or surprised to a user resulting in a wide range of recommendations. The experiment results show that our proposed algorithm is very promising. Although the quality of recommendations provided by our framework is moderate, our framework does produce interesting recommendations not found in the primitive single-domain based system and with simple and understandable explanations. Show more

Keywords: Recommender system, explainable, multi-domain, recommendation rule generation, serendipity

DOI: 10.3233/IDA-194729

Citation: Intelligent Data Analysis, vol. 24, no. 6, pp. 1289-1309, 2020

Authors: Suto, Jozsef

Article Type: Research Article

Abstract: Nowadays there are hundreds of thousands known plant species on the Earth and many are still unknown yet. The process of plant classification can be performed using different ways but the most popular approach is based on plant leaf characteristics. Most types of plants have unique leaf characteristics such as shape, color, and texture. Since machine learning and vision considerably developed in the past decade, automatic plant species (or leaf) recognition has become possible. Recently, the automated leaf classification is a standalone research area inside machine learning and several shallow and deep methods were proposed to recognize leaf types. From …2007 to present days several research papers have been published in this topic. In older studies the classifier was a shallow method while in current works many researchers applied deep networks for classification. During the overview of plant leaf classification literature, we found an interesting deficiency (lack of hyper-parameter search) and a key difference between studies (different test sets). This work gives an overall review about the efficiency of shallow and deep methods under different test conditions. It can be a basis to further research. Show more

Keywords: Artificial neural network, deep learning, feature engineering, plant leaf recognition

DOI: 10.3233/IDA-194821

Citation: Intelligent Data Analysis, vol. 24, no. 6, pp. 1311-1328, 2020

Authors: Xie, Xiaolan | Pang, Shantian | Chen, Jili

Article Type: Research Article

Abstract: In the traditional recommendation algorithms, due to the rapid development of deep learning and Internet technology, user-item rating data is becoming increasingly sparse. The simple inner product interaction mode adopted by the collaborative filtering method has a cold start problem and cannot learn the complex nonlinear structural features between users and items, while the content-based algorithm encounters the difficulty of effective feature extraction. In response to this problem, a hybrid model is proposed based on deep learning and Stacking integration strategy. The traditional recommendation algorithm is first fused by using the Stacking integration strategy to make up for the shortcomings …of the single recommendation algorithm to achieve better recommendation performance. The fusion-based model learns the more abstract and deeper nonlinear interaction features by deep learning technology, which makes the model performance gain further. The experiment comparison on the MovieLens-1m dataset shows that the proposed hybrid recommendation model can significantly improve the accuracy of rating prediction. Show more

Keywords: Hybrid recommendation, deep learning, Stacking integration strategy, collaborative filtering, content-based

DOI: 10.3233/IDA-194961

Citation: Intelligent Data Analysis, vol. 24, no. 6, pp. 1329-1344, 2020

Authors: Ali, Bassel | Moriyama, Koichi | Kalintha, Wasin | Numao, Masayuki | Fukui, Ken-Ichi

Article Type: Research Article

Abstract: Data collection plays an important role in business agility; data can prove valuable and provide insights for important features. However, conventional data collection methods can be costly and time-consuming. This paper proposes a hybrid system R-EDML that combines a sequential feature selection performed by Reinforcement Learning (RL) with the evolutionary feature prioritization of Evolutionary Distance Metric Learning (EDML) in a clustering process. The goal is to reduce the features while maintaining or increasing the accuracy leading to less time complexity and future data collection time and cost reduction. In this method, features represented by the diagonal elements of EDML matrices …are prioritized using a differential evolution algorithm. Further, a selection control strategy using RL is learned by sequentially inserting and evaluating the prioritized elements. The outcome offers the best accuracy R-EDML matrix with the least number of elements. Diagonal R-EDML focusing on the diagonal elements is compared with EDML and conventional feature selection. Full Matrix R-EDML focusing on the diagonal and non-diagonal elements is tested and compared with Information-Theoretic Metric Learning. Moreover, R-EDML policy is tested for each EDML generation and across all generations. Results show a significant decrease in the number of features while maintaining or increasing accuracy. Show more

Keywords: Clustering, distance metric learning, feature selection, reinforcement learning

DOI: 10.3233/IDA-194887

Citation: Intelligent Data Analysis, vol. 24, no. 6, pp. 1345-1364, 2020

Authors: Nalluri, Madhu Sudana Rao | K, Kannan | Gao, Xiao-Zhi | V, Swaminathan | Roy, Diptendu Sinha

Article Type: Research Article

Abstract: Automatic disease diagnosis is, in essence, a classification problem where the classifier has to be trained based on patients’ datasets and not entirely on doctors’ expert knowledge. In this paper, we present the design of such data-driven disease classifiers and fine-tuning classifier performance by a multi-objective evolutionary algorithm. We have used sequential minimal optimization (SMO) classifier as the base classifier and three evolutionary algorithms namely Cat Swarm Optimization (CSO), Invasive Weed Optimization (IWO) and Eagle Search based Invasive Weed Optimization (ESIWO) to diagnose disease from datasets available. In that sense, our approach is an offline data-driven approach with 18 benchmark …medical datasets, and the obtained results demonstrate the superiority of the proposed diagnoses in terms of multiple objectives such as classification Prediction accuracy, Sensitivity, and Specificity. Relevant statistical tests have been carried out to substantiate the cogence of the obtained results. Show more

Keywords: Classification, parameter evolution, disease diagnosis, data-driven approach, evolutionary algorithm

DOI: 10.3233/IDA-194687

Citation: Intelligent Data Analysis, vol. 24, no. 6, pp. 1365-1384, 2020

Authors: Mohanraj, G. | Mohanraj, V. | Senthilkumar, J. | Suresh, Y.

Article Type: Research Article

Abstract: There has been a major and rising interest in India for increasing vaccination rate among peoples to make the nation healthier and safer. In this paper, a new hybrid deep learning model is proposed to predict and target vaccination rates in the less immunized regions. The Rank-Based Multi-Layer Perceptron (R-MLP) hybrid deep learning framework uses the data collected from the recently updated District Level Household Survey-4 (DLHS). R-MLP model predicts and categorizes the percentage of partly immunized vaccination rates as extreme, low and medium ranges. This predicted findings are cross-verified by Deep Soft Cosine Semantic and Ranking SVM based model …(DSS-RSM). DSS-RSM model uses the data obtained from the medical practitioners through a location-based social network. The proposed model predicts and extracts patterns with high similarity frequency for identifying vulnerable low immunization regions. It classifies the predicted patterns into two classes such as Class 1 is denoted as high ranked regions and Class 2 is denoted as low ranked regions based on the percentage of pattern matches. Finally, the results from R-MLP and DSS-RSM models are cross-linked together using ensemble model. This model finds the loss values to identify the target regions were health care program need to be conducted for increasing the level of immunization among children’s. The proposed hybrid deep learning models trains and validates using python-based Keras and TensorFlow deep learning libraries. The performance of the proposed hybrid deep learning model is compared with other variant machine learning techniques such as Decision Tree C5.0, Naive Bayes and Linear Regression. This comparative results are evaluated using evaluation measures such as Precision, Recall, Accuracy and F1-Measure. Our results show that the hybrid deep learning system is clearly superior to any other alternative approach. Show more

Keywords: DLHS, R-MLP, DSS-RSM, ensemble model, child immunization, vaccination rate

DOI: 10.3233/IDA-194820

Citation: Intelligent Data Analysis, vol. 24, no. 6, pp. 1385-1402, 2020

Authors: Meeng, Marvin | de Vries, Harm | Flach, Peter | Nijssen, Siegfried | Knobbe, Arno

Article Type: Research Article

Abstract: Subgroup Discovery is a supervised, exploratory data mining paradigm that aims to identify subsets of a dataset that show interesting behaviour with respect to some designated target attribute. The way in which such distributional differences are quantified varies with the target attribute type. This work concerns continuous targets, which are important in many practical applications. For such targets, differences are often quantified using z -score and similar measures that compare simple statistics such as the mean and variance of the subset and the data. However, most distributions are not fully determined by their mean and variance alone. As …a result, measures of distributional difference solely based on such simple statistics will miss potentially interesting subgroups. This work proposes methods to recognise distributional differences in a much broader sense. To this end, density estimation is performed using histogram and kernel density estimation techniques. In the spirit of Exceptional Model Mining, the proposed methods are extended to deal with multiple continuous target attributes, such that comparisons are not restricted to univariate distributions, but are available for joint distributions of any dimensionality. The methods can be incorporated easily into existing Subgroup Discovery frameworks, so no new frameworks are developed. Show more

Keywords: Subgroup discovery, continuous target, complex target concepts, kernel density estimation

DOI: 10.3233/IDA-194719

Citation: Intelligent Data Analysis, vol. 24, no. 6, pp. 1403-1439, 2020

Authors: Li, Jun | Li, Chao | Tian, Bin | Liu, Yanzhao | Si, Chengxiang

Article Type: Research Article

Abstract: We consider the problem of efficiently online computing/filtering or analysis multimedia streams. In this scenario, we register a large scale of continuous analysis queries to filter pornographic stream items. Each query is a conjunction of filters. For instance, the query “does this image contain a people basking in the beach?” can be resolved by applying the conjunction of water, people, sand, sea filters successively on the stream item. However, the online evaluation of multimedia filters is indeed very expensive, fortunately there usually exist multiple filters shared among a lot of queries. In other words, each filter may occur …in multiple queries. An open problem in such a filtering scenario is how to order the filters in an optimal sequence to achieve significant performance. Existing methods are based on a greedy strategy which orders the filters according to three factors (selectivity, popularity, cost ). Although all these methods achieve good results, there are still some problems that haven’t addressed yet. First, the selectivity factor is set empirically, which can not adaptively adjust with multimedia stream. Second, the proportion relationships among the three factors (selectivity, cost, popularity ) were not considerably explored. Under these observations,in this paper, we propose a Dynamic-Analytic hierarchy process Framework (DAF ) which use a time-based compositional forecasting method, which is based on the idea of exponential smoothing, to deal with the factors’ proportion relationships dynamics. Experiments on both synthetic and real lift multimedia streams demonstrate that our proposed framework (DAF ) provides much great adaptability in modeling the factors proportion relationships changing over multimedia stream environment. Show more

Keywords: Multimedia streams, analytic hierarchy process, pipeline filter ordering

DOI: 10.3233/IDA-194640

Citation: Intelligent Data Analysis, vol. 24, no. 6, pp. 1441-1453, 2020

Authors: Wang, Xuejian | Fairhurst, Michael C. | Canuto, Anne M.P.

Article Type: Research Article

Abstract: Although several automatic computer systems have been proposed to address facial expression recognition problems, the majority of them still fail to cope with some requirements of many practical application scenarios. In this paper, one of the most influential and common issues raised in practical application scenarios when applying automatic facial expression recognition system, head pose variation, is comprehensively explored and investigated. In order to do this, two novel texture feature representations are proposed for implementing multi-view facial expression recognition systems in practical environments. These representations combine the block-based techniques with Local Ternary Pattern-based features, providing a more informative and efficient …feature representation of the facial images. In addition, an in-house multi-view facial expression database has been designed and collected to allow us to conduct a detailed research study of the effect of out-of-plane pose angles on the performance of a multi-view facial expression recognition system. Along with the proposed in-house dataset, the proposed system is tested on two well-known facial expression databases, CK+ and BU-3DFE datasets. The obtained results shows that the proposed system outperforms current state-of-the-art 2D facial expression systems in the presence of pose variations. Show more

Keywords: Facial expression recognition, feature selection, machine learning, classification

DOI: 10.3233/IDA-194798

Citation: Intelligent Data Analysis, vol. 24, no. 6, pp. 1455-1476, 2020

Authors: Sivanaiah, Rajalakshmi | Sakaya Milton, R. | Mirnalinee, T.T.

Article Type: Research Article

Abstract: The main goal of a recommendation system is to recommend items of interest to users by analyzing their historical data. Content-based and collaborative filtering are the traditional recommendation strategies, each with its own strengths and weaknesses. Some of their weaknesses can be overcome by combining the two strategies. The resulting hybrid system performs qualitatively better than the traditional recommendation systems. However, historical data of some users may consist largely of only likes or only dislikes. Those users are termed as optimistic or pessimistic users respectively. On an average there are around 10 to 20% of pessimistic users present in a …given dataset. For pessimistic users, whose profiles have mostly dislikes and very few likes, content-based filtering can hardly recommend any items of interest. In content-based filtering technique pessimistic users get poor recommendations of either uninteresting movies or no recommendations at all. This can be alleviated by boosting the content profiles of pessimistic users using the top-n recommendations of collaborative filtering. This content boosted hybrid filtering system provides a novel list of recommendations even for pessimistic users, with predictive accuracy better than that of a traditional content-based filtering system. Show more

Keywords: Content boosted, hybrid filtering, user-profile, pessimistic user, boosted profile, movie recommendation

DOI: 10.3233/IDA-205244

Citation: Intelligent Data Analysis, vol. 24, no. 6, pp. 1477-1496, 2020