Search

In this work, we consider transferring the structure information from large networks to compact ones for dense prediction tasks in computer vision. Previous knowledge distillation strategies used for dense prediction tasks often directly borrow the distillation scheme for image classification and perform knowledge distillation for each pixel separately, leading to sub-optimal performance. Here we propose to distill structured knowledge from large networks to compact networks, taking into account the fact that dense prediction is a structured prediction problem. Specifically, we study two structured distillation schemes: i) pair-wise distillation that distills the pair-wise similarities by building a static graph; and ii) holistic distillation that uses adversarial training to distill holistic knowledge. The effectiveness of our knowledge distillation approaches is demonstrated by experiments on three dense prediction tasks: semantic segmentation, depth estimation and object detection. Code is available at: https://git.io/StructKD, Comment: v1:10 pages cvpr2019 accepted; v2:15 pages for a journal version; Code is available at: https://github.com/irfanICMLL/structure_knowledge_distillation; fix typos

In this article, we investigate the problem of social link inference in a target location-aware social network (LSN), which aims at predicting the unobserved links between users within the network. This problem is critical for downstream applications, including network completion and friend recommendation. In addition to the network structures commonly used in general link prediction, the studies tailored for social link inference in an LSN leverage user trajectories from the spatial aspect. However, the temporal factor lying in user trajectories is largely overlooked by most of the prior studies, limiting the capabilities of capturing the temporal relevance between users. Moreover, effective user matching by fusing different views, i.e., social, spatial, and temporal factors, remains unresolved, which hinders the potential improvement of link inference. To this end, this article devises a novel multiview matching network (MVMN) by regarding each of the three factors as one view of any target user pair. MVMN enjoys the flexibility and completeness of modeling each factor by developing its suitable matching module: 1) location matching module; 2) time-series matching module; and 3) relation matching module. Each module learns a view-specific representation for matching, and MVMN fuses them for final link inference. Extensive experiments on two real-world data sets demonstrate the superiority of our approach against several competitive baselines for link prediction and sequence matching, validating the contribution of its key components.

Projection techniques are often used to visualize high-dimensional data, allowing users to better understand the overall structure of multi-dimensional spaces on a 2D screen. Although many such methods exist, comparably little work has been done on generalizable methods of inverse-projection -- the process of mapping the projected points, or more generally, the projection space back to the original high-dimensional space. In this paper we present NNInv, a deep learning technique with the ability to approximate the inverse of any projection or mapping. NNInv learns to reconstruct high-dimensional data from any arbitrary point on a 2D projection space, giving users the ability to interact with the learned high-dimensional representation in a visual analytics system. We provide an analysis of the parameter space of NNInv, and offer guidance in selecting these parameters. We extend validation of the effectiveness of NNInv through a series of quantitative and qualitative analyses. We then demonstrate the method's utility by applying it to three visualization tasks: interactive instance interpolation, classifier agreement, and gradient visualization.

To utilize a huge amount of observation data based on real-world events, a data assimilation process is needed to estimate the state of the system behind the observed data. The Kalman filter is a very commonly used technique in data assimilation, but it has a problem in terms of practical use from the viewpoint of processing efficiency and estimating the deterioration in precision when applied to particularly large-scale datasets. In this paper, we propose a method that simultaneously addresses these problems and demonstrate its usefulness. The proposed method improves the processing efficiency and suppresses the deterioration in estimation precision by introducing correction processes focusing on the non-negative nature and sparseness of data in wavelet space. We show that the proposed method can accurately estimate population dynamics (MAE ≤ 3, RMSE ≤ 7) on the basis of an evaluation done using population data generated from cellular networks. In addition, the possibility of wide area abnormality detection using the proposed method is shown from a situation analysis of when Category 5 typhoon Hagibis made landfall in Japan. The proposed method has been deployed in a commercial service to estimate real-time population dynamics in Japan.

The rapid growth of GPS technology and mobile devices has led to a massive accumulation of location data, bringing considerable benefits to individuals and society. One of the major usages of such data is travel time prediction, a typical service provided by GPS navigation devices and apps. Meanwhile, the constant collection and analysis of the individual location data also pose unprecedented privacy threats. We leverage the notion of geo-indistinguishability, an extension of differential privacy to the location privacy setting, and propose a procedure for privacy-preserving travel time prediction without collecting actual individual GPS trace data. We propose new concepts to examine the impact of geo-indistinguishability-based sanitization on the usefulness of GPS traces and provide analytical and experimental utility analysis for privacy-preserving travel time prediction. We also propose new metrics to measure the adversary error in learning individual GPS traces from the collected sanitized data. Our experiment results suggest that the proposed procedure provides travel time prediction with satisfactory accuracy at reasonably small privacy costs.

Extraction of information in enterprise applications due to complex distribution of information in large identical sources. In such a scenario, a single approach or method for extracting information text would limit information needs, which would require a high level of work and time. So, it is an open problem in data analysis application to construct a suitable classification model for unsupervised datasets which having multi level of information attributes. It is vital to analyse and discover the valuable pattern information to support the accurate classification. Selection of attributes and construction of relation model always is a challenging due the increasing attribute dimensionality. So, it is important to learn and select the best attributes patterns to enhance the information association through accurate classification. In this paper, we propose an ARP-RW method for construction of Attribute Relation Pattern (ARP) through computing attributes Relation Weightage (RW) to enhance the information classification. The ARP-RW method provides the solution to identifying the relation class of the multi-attributes documents. It initially constructs an attribute relation class matrix (ARCM) utilizing the set of data collection and the RW value of the MLA. Later, it builds an ARP based on the MLA selected to perform accurate classification. The evaluation of the proposal method using the datasets of UCI Machine Learning Repository shows improvisation in comparison the existing approaches.

The water quality index has been universally accepted as an indicator to represent the water quality status of the surface water body comprehensively. The prevalent conventional Water Quality Indices (WQIs) suffer from limitations such as 'eclipsing' and 'ambiguity'. Artificial intelligence techniques such as artificial neural networks (ANNs) have gained importance to overcome the limitations of conventional WQIs. In the present study, the Levenberg Marquardt (LM) algorithm and the Scaled Conjugate Gradient (SCG) algorithm have been compared to develop WQI based on the ANN approach (i.e ANNWQI). It is observed that the LM algorithm outperforms the SCG algorithm for prediction of ANNWQI of Indian streams, while the Bayesian Regularization algorithm has not been found suitable for the same purpose in the present study. It is also observed that both LM and SCG algorithm gives robust predictions when the hidden layer contains ten neurons. The combination of data set partitioning of training (75%), Validation (15%), and testing (10%) have been found to give the robust performance of prediction of ANNWQI for Indian streams. The predicted ANNWQI model using the LM algorithm has a very high correlation with the measured WQI values and therefore recommended to be adopted as an effective alternative, to avoid lengthy calculations involved in prevalent conventional WQI.

This paper addresses the problem of anomaly detection for high-dimensional sensing data. The one-class support vector machine (OCSVM) is one of the most popular unsupervised methods for anomaly detection. When data are high dimensional and large scale, however, the efficiency of OCSVM-based methods in anomaly detection suffers. Although dimensionality-reduction tools, such as deep belief networks, can be applied to compress the high-dimensional data to alleviate the problem, the accuracy and timely detection are still hard to improve due to the inherent features of OCSVM. In this paper, we propose a new form of OCSVM model based on the structure of the compressed data and the characteristics of OCSVM. Based on the new model, we design both optimal and approximate methods for model training and testing. We evaluate the performance of our methods with extensive experiments on four real-world datasets. The experimental results demonstrate that our new methods, both optimal and approximate ones, not only significantly outperform the state-of-the-art in accuracy and efficiency, but also achieve the good performance without the need of manual parameter tuning. In addition, our approximate training and testing mechanism can reduce the computing time by three orders of magnitude with a negligible loss in accuracy.

The proposed work aims to solve data sparsity problem in the recommendation system. It handles two-level pre-processing techniques to reduce the data size at the item level. Additional resources like items genre, tag, and time are added to learn and analyse the behaviour of the user preferences in-depth. The advantage of the proposed method is to recommend the item, based on user interest pattern and avoid recommending the outdated items. User information are grouped based on similar item genre and tag feature. This effectively handle overlapping conditions that exist on item’s genre, as it has more than one genre at initial level. Further, based on time, it analyses the user non-static interest. Overall it reduces the dimensions which is an initial way to prepare data, to analyse hidden pattern. To enhance the performance, the proposed method utilized Apache’s spark Mllib FP-Growth and association rule mining approach in a distributed environment. To reduce the computation cost of constructing tree in FP-Growth, the candidate data set is stored in matrix form. The experiments were conducted using MovieLens data set. The observed results shows that the proposed method achieves 4% increase in accuracy when compared to earlier methods.

Data-driven methods have been extensively utilized in establishing predictive models from historical data for process monitoring and prediction of quality variables. However, most data-driven approaches assume that training data and testing data come from steady-state operating regions and follow the same distribution, which may not be the case when it comes to complex industrial processes. To avoid these restrictive assumptions and account for practical implementation, a novel online transfer learning technique is proposed to dynamically learn cross-domain features based on the variational Bayesian inference in this work. Stemming from the probabilistic slow feature analysis, a transfer slow feature analysis (TSFA) technique is presented to transfer dynamic models learned from different source processes to enhance prediction performance in the target process. In particular, two weighting functions associated with transition and emission equations are introduced and updated dynamically to quantify the transferability from source domains to the target domain at each time instant. Instead of point estimation, a variational Bayesian inference scheme is designed to learn the parameters under probability distributions accounting for corresponding uncertainties. The effectiveness of the proposed technique with applications to soft sensor modelling is demonstrated by a simulation example, a public dataset and an industrial case study.

Problem definition: Airports and airlines have been challenged to improve decision making by producing accurate forecasts in real time. We develop a two-phased predictive system that produces forecasts of transfer passenger flows at an airport. In the first phase, the system predicts the distribution of individual transfer passengers’ connection times. In the second phase, the system samples from the distribution of individual connection times and produces distributional forecasts for the number of passengers arriving at the immigration and security areas. Academic/practical relevance: To our knowledge, this work is the first to apply machine learning for predicting real-time distributional forecasts of journeys in an airport using passenger level data. Better forecasts of these journeys can help optimize passenger experience and improve airport resource deployment. Methodology: The predictive system developed is based on a regression tree combined with copula-based simulations. We generalize the tree method to predict distributions, moving beyond point forecasts. We also formulate a newsvendor-based resourcing problem to evaluate decisions made by applying the new predictive system. Results: We show that, when compared with benchmarks, our two-phased approach is more accurate in predicting both connection times and passenger flows. Our approach also has the potential to reduce resourcing costs at the immigration and transfer security areas. Managerial implications: Our predictive system can produce accurate forecasts frequently and in real time. With these forecasts, an airport’s operating team can make data-driven decisions, identify late passengers, and assist them to make their connections. The airport can also update its resourcing plans based on the prediction of passenger flows. Our predictive system can be generalized to other operations management domains, such as hospitals or theme parks, in which customer flows need to be accurately predicted. Funding: This work was funded by Eurocontrol (APOC Business Process Reengineering Big Data Study) [Grant 15-220643-AWP6.3.1]. Supplemental Material: The online appendix is available at https://doi.org/10.1287/msom.2021.0975 .

Mobile operators collect and store the network generated traffic data for analysis. Time Series Prediction (TSP) has been used in mobile network traffic data analysis to produce predictive results for network planning and resource allocation. We propose a novel method of predicting mobile network traffic using neural networks based on conditional probability modeling between adjacent data windows. Firstly, we develop a pre-processing method to aggregate the raw traffic log data and sample the aggregated time series to adjacent data windows, as training samples. Secondly, we use neural networks to parameterize the conditional probability between adjacent data windows and estimate the probability by training the neural networks with sampled data. The estimated conditional probability is then used to ensemble the prediction. Thirdly, we show theoretically that the prediction based on all historical data is equivalent to the prediction based on just previous data window, given the estimation of conditional probability between adjacent data windows. We also analyze computation complexity and show that seasonality will reduce the computational complexity. In the experiment, we compare the prediction performance among the models with different seasonality, sample size and number of hidden layers, and show that the proposed schemes achieve better prediction accuracy than state-of-the-art.

Multi-view clustering has attracted increasing attention in multimedia, machine learning and data mining communities. As one kind of the essential multi-view clustering algorithm, multi-view subspace clustering (MVSC) becomes more and more popular due to its strong ability to reveal the intrinsic low dimensional clustering structure hidden across views. Despite superior clustering performance in various applications, we observe that existing MVSC methods directly fuse multi-view information in the similarity level by merging noisy affinity matrices; and isolate the processes of affinity learning, multi-view information fusion and clustering. Both factors may cause insufficient utilization of multi-view information, leading to unsatisfying clustering performance. This paper proposes a novel consensus one-step multi-view subspace clustering (COMVSC) method to address these issues. Instead of directly fusing multiple affinity matrices, COMVSC optimally integrates discriminative partition-level information, which is helpful to eliminate noise among data. Moreover, the affinity matrices, consensus representation and final clustering labels matrix are learned simultaneously in a unified framework. By doing so, the three steps can negotiate with each other to best serve the clustering task, leading to improved performance. Accordingly, we propose an iterative algorithm to solve the resulting optimization problem. Extensive experiment results on benchmark datasets demonstrate the superiority of our method against other state-of-the-art approaches.

Extracting relevant information from a large amount of data is a challenging task. Automatic text summarization is a potential solution for obtaining this information. In this paper, a nature inspired swarm intelligence-based algorithm viz. firefly algorithm for multi-document text summarization is proposed. A new fitness function consisting of three features viz. topic relation factor, cohesion factor and readability factor is utilized. The experiments are performed on datasets from Document Understanding Conference i.e. DUC-2002, DUC-2003 and DUC-2004. The performance of the algorithm has been evaluated using ROUGE score. The performance of the proposed algorithm is compared with some other nature inspired ones such as particle swarm optimization (PSO) and genetic algorithm (GA). The performance of the proposed algorithm outperforms the other adopted ones.

In recent days, social media, online services, smartphones, and the Internet of Things (IoT) produces large quantities of data every second. The generated data is structured, unstructured, or semi-structured and available in various formats. Therefore, traditional approaches are not sufficient to handle such kind of data effectively. High utility pattern mining is a famous study area of data analytics that incorporates utility measures to consider user-based constraints such as number of units and benefit, in addition to frequency statistics of datasets. It is also essential to make effective decisions, and their demand is increasing in the last decade. Several techniques have been suggested for utility-based frequent pattern extraction. However, these approaches are limited to data size and operate on standalone systems. We have proposed a parallel approach named distributed memory-optimized utility mining (DMOUM) for high utility-based frequent pattern mining to address this issue. A new pruning technique is implemented that greatly reduces processing time and memory use. The proposed approach can handle huge amounts of data, i.e., big data. DMOUM approach is implemented in cluster-node architecture using Spark. The results are validated on various real-time datasets and found proposed approach has better performance than cutting edge approaches in terms of run-time, memory consumption, and scalability measures. The proposed work will provide solutions to real-time issues such as health care, education, e-commerce, and so on.

The rapid growth in the cloud data center needs a dynamic resource provision to maintain the Quality of Services parameters. To guarantee it, Virtual Machine Migration as part of VM Consolidation has a significant role. Efficient VM migration requires knowledge of the host’s future utilization in advance. Because of the high variation in cloud resource usage and dynamic workloads, predicting host utilization using utilization history is challenging. This paper proposes a Support Vector Regression-based methodology to predict a host‘s future utilization using multiple resource's utilization history. A Hybrid Kernel function that includes radial basis function and polynomial kernel function has been proposed and then trains the Support Vector Machine using multiple-resource utilization history. Compared to the existing approaches: multiple linear regression-based prediction, Euclidean distance, and Absolute Summation based regression, the proposed method performs better in terms of root mean square error, mean square error, mean absolute percentage error, mean absolute error, and R 2 . The result section concludes that on evaluating error percent, the prediction error is 16% for the proposed approach and predicts host utilization with 7%, 64%, and 67% more accuracy than MRHOD, MDRHU-ED, MDRHU-AS approaches, respectively.

Wireless Sensor Networks (WSNs) are developed significantly from the last decades and attracted the attention of scientific and industrial domains. In WSNs, sensor nodes distributed autonomously in harsh environments are easily vulnerable to faults and attacks that cause sensor readings unreliable and inaccurate. In this scenario, sensor readings that have differed considerably from healthy behaviors will be considered abnormal data or anomalies/outliers. The inclusion of such outliers in data analytics will inevitably affect the outcome of the decision-making process. Thus, detecting outliers in WSNs using data-driven approaches becomes a novel technique among the Machine Learning (ML) communities. Meanwhile, various research issues are there in measuring the performance of the deployed ML algorithms in detecting outliers in WSNs, which generally contains minimum resources in terms of computational capability and power sources to ensure data quality. Hence, this paper presents a comprehensive overview of the state-of-the-art Statistical and Artificial Intelligence (AI) based techniques used in WSNs to detect outliers in the view of architecture, type, degree, approach, and detection mode. Furthermore, each aforementioned outlier detection approach is presented with detailed discussions and future scope for developments.

The healthcare industry has become increasingly challenging, requiring retrieval of knowledge from large amounts of complex data to find the best treatments. Several works have suggested the use of Data Mining tools to overcome the challenges; however, none of them has suggested the best tool to do so. To fill this gap, this paper presents a survey of popular open-source data mining tools in which data mining tool selection criteria based on healthcare application requirements is proposed and the best ones using the proposed selection criteria are identified. The following popular open-source data mining tools are assessed: KNIME, R, RapidMiner, Scikit-learn, and Spark. The study shows that KNIME and RapidMiner provide the largest coverage of healthcare data mining requirements.

This paper presents a new contribution to the recommendation system following E-commerce reviews. Here, it implements a dictionary-based sentiment analysis based on four main steps (i) Pre-processing (ii) Semantic word extraction (iii) Feature Extraction (iv) Classification. Initially, the tweets or reviews extracted from the database are subjected to pre-processing, which involves three processes: stop word removal, stemming, and blank space removal. In the semantic word extraction process, the semantic words from the dictionary will be extracted by matching with the extracted keywords. The next process is the feature extraction, which extracts joint holoentropy and cross holoentropy of all keywords, and further proceeds with conditional holoentropy-based feature selection process. Finally, the selected features are subjected to a classification process using Deep Belief Network (DBN), which is a well-performing deep learning algorithm. Moreover, the main contribution of the paper relies on the improvement of DBN architecture, where the number of hidden neurons and activation function is optimally tuned by a hybrid optimization algorithm termed as Grey linked Chick Update-based Chicken Swarm Optimization (GCU-CSO). At last, the comparative analysis of proposed and conventional algorithms in terms of various performance metrics proves the efficacy of the proposed E-commerce recommendation system.

Search engines are crucial for information gathering systems (IGS). New challenges face search engines concerning automatic learning from user requests. In this paper, a new hybrid intelligent system is proposed to enhance the search process. Based on a Multilayer Fuzzy Inference System (MFIS), the first step is to implement a scalable system to relay logical rules in order to produce three classifications for search behavior, user profiles, and query characteristics from analysis of navigation log files. These three outputs from the MFIS are used as inputs for the second step, an Adaptive Neuro-Fuzzy Inference System (ANFIS). The training process of the ANFIS replaced the rules by adjusting the weights in order to find the most relevant result for the search query. This proposed system, called MFIS-ANFIS, is implemented as an experimental system. The system performance is evaluated using quantitative and comparative analysis. MFIS-ANFIS aimed to be the core of intelligent and reliable search process.

Blockchain technology is rapidly changing the transaction behavior and efficiency of businesses in recent years. Data privacy and system reliability are critical issues that is highly required to be addressed in Blockchain environments. However, anomaly intrusion poses a significant threat to a Blockchain, and therefore, it is proposed in this article a collaborative clustering-characteristic-based data fusion approach for intrusion detection in a Blockchain-based system, where a mathematical model of data fusion is designed and an AI model is used to train and analyze data clusters in Blockchain networks. The abnormal characteristics in a Blockchain dataset are identified, a weighted combination is carried out, and the weighted coefficients among several nodes are obtained after multiple rounds of mutual competition among clustering nodes. When the weighted coefficient and a similarity matching relationship follow a standard pattern, an abnormal intrusion behavior is accurately and collaboratively detected. Experimental results show that the proposed algorithm has high recognition accuracy and promising performance in the real-time detection of attacks in a Blockchain.

Hybrid systems, which combine statistical and machine learning (ML) techniques using residual (error forecasting) modeling, have been highlighted in the literature due to their accuracy and ability to forecast time series with different characteristics. In these architectures, a crucial task is the proper modeling of the residuals since they may present random fluctuations, complex nonlinear patterns, and heteroscedastic behavior. Hence, the selection, specification, and training of one ML model to forecast the residuals are costly and challenging tasks since issues, such as underfitting, overfitting, and misspecification, can lead to a system with low accuracy or even deteriorate the linear forecast of the time series. This article proposes a hybrid system, named dynamic residual forecasting (DReF), that employs a modified dynamic selection (DS) algorithm to decide: the most suitable ML model to forecast a pattern of the residual series and if it is a promising candidate to increase the accuracy of the time series forecast from the linear combination. Thus, the DReF aims to reduce the uncertainty of the ML model selection and avoid the deterioration of the time series forecast. Furthermore, the proposed system searches for the most suitable parameters of the DS algorithm for each data set. In this article, the proposed method uses a pool of five ML models widely adopted in the literature: multilayer perceptron, support vector regression, radial basis function, long short-term memory, and convolutional neural network. An experimental evaluation was conducted using ten well-known time series. The results show that the DReF obtains superior results for the majority of the data sets compared with single and hybrid models of the literature.

Evidential reasoning (ER) rule has been widely used in dealing with uncertainty. As an important parameter to measure the inherent property of evidence, the evidence reliability makes the ER rule constitute a generalized reasoning framework. In current research of the ER rule, the evidence reliability tends to be expressed in the form of quantitative value by certain methods or expert knowledge. The single quantitative value lacks the ability to describe the statistical property of reliability, which leads to unreasonable results. In this article, a new ER rule with continuous probability distribution of reliability denoted by ERr-CR is proposed. The combination of two pieces of evidence is discussed in detail, where the reliability is profiled as random variables with specific probability distribution. To characterize the output of ERr-CR, a novel concept of expectation of the expected utility is proposed. In addition, the ERr-CR is expanded to multiple pieces of evidence to show its universality. Further, the basic performances of the ERr-CR are explored to illustrate the rationality. Moreover, a case study of safety assessment of natural gas storage tanks (NGSTs) is conducted to show the potential applications of ERr-CR, which makes the proposed method more practical.

This article describes the capability of online data storage which has been enhanced by the emergence of cloud datacenter development. Distributed Hash Table (DHT) based image retrieval system using locality sensitive hash (LSH) has provided an efficient way to set up distributed Content Based Image Retrieval (CBIR) frameworks. However, with the fixed LSH function adopted, LSH and other codebook-based distributed retrieval systems are facing the problem of flexibility, and also are difficult to satisfy the user's demand. In this article, LRFMIR is proposed to introduce semantic search into DHT based CBIR system. LRFMIR is established on a DHT based network, where a flexible result truncating strategy is employed to fuse provided results by using multiple features measurements. Experiments show that LRFMIR provides a higher accuracy and recall rate than single feature employed retrieval systems, and possesses good load balancing and query efficiency performance.

The problem of representative selection amounts to sampling few informative exemplars from large datasets. Existing approaches to data selection often fall short of simultaneously handling non-linear data structures, sampling concise and non-redundant subsets, rejecting outliers, and yielding interpretable outcomes. This paper presents a novel representative selection approach, dubbed MOSAIC, for drawing descriptive sketches of arbitrary manifold structures. Resting upon a novel quadratic formulation, MOSAIC advances a multi-criteria selection approach that maximizes the global representation power of the sampled subset, ensures novelty of the samples by minimizing redundancy, and rejects disruptive information by effectively detecting outliers. Theoretical analyses shed light on geometrical characterization of the obtained sketch and reveal that the sampled representatives maximize a well-defined notion of data coverage in a transformed space. In addition, we present a highly scalable randomized implementation of the proposed algorithm shown to bring about substantial speedups. MOSAIC's superiority in achieving the desired characteristics of a representative subset all at once while exhibiting remarkable robustness to various outlier types is demonstrated via extensive experiments conducted on both real and synthetic data with comparisons to state-of-the-art algorithms.

Security issues have resulted in severe damage to the cloud computing environment, adversely affecting the healthy and sustainable development of cloud computing. Intrusion detection is one of the technologies for protecting the cloud computing environment from malicious attacks. However, network traffic in the cloud computing environment is characterized by large scale, high dimensionality, and high redundancy, these characteristics pose serious challenges to the development of cloud intrusion detection systems. Deep learning technology has shown considerable potential for intrusion detection. Therefore, this study aims to use deep learning to extract essential feature representations automatically and realize high detection performance efficiently. An effective stacked contractive autoencoder (SCAE) method is presented for unsupervised feature extraction. By using the SCAE method, better and robust low-dimensional features can be automatically learned from raw network traffic. A novel cloud intrusion detection system is designed on the basis of the SCAE and support vector machine (SVM) classification algorithm. The SCAE+SVM approach combines both deep and shallow learning techniques, and it fully exploits their advantages to significantly reduce the analytical overhead. Experiments show that the proposed SCAE+SVM method achieves higher detection performance compared to three other state-of-the-art methods on two well-known intrusion detection evaluation datasets, namely KDD Cup 99 and NSL-KDD.

In terms of pipeline leak detection, the unavoidable fact is that existing data could not provide enough effective leak data to train a high accuracy model. To address this issue, this article proposes mixed generative adversarial networks (mixed-GANs) as a practical way to provide additional data, ensuring data reliability. First, multitype generative networks with heterogeneous parameter-updating mechanisms are designed to explore a variety of different solutions and eliminate the potential risks of instable training and scenario collapse. Then, based on expert experience, two data constraints are proposed to describe leak characteristics and further evaluate the quality of generated leak data in the training process. Through integrating the particle swarm optimization algorithm into generative model training, mixed-GAN has better generation performance than the conventional gradient descent algorithm. Based on the above-mentioned contents, the proposed model is able to provide satisfactory leak data with different scenarios, contributing to data quantity expansion, data credibility enhancement, and data variety enrichment. Finally, extensive experiments are given to illustrate the effectiveness of the proposed generative model for pipeline network leak detection.

Multi-output regression aims to predict multiple continuous outputs simultaneously using the common set of input variables. The significant challenge arises from modeling relevance between inputs and outputs. Moreover, the shortage of labeled multi-output data and the divergence of data are other factors that impede the development of multi-output regression problems. The recent emergence of transfer learning techniques, which have the ability of leveraging previously acquired knowl- edge from a similar domain, provide a solution to the above issues. In this paper, a novel fuzzy transfer learning method is proposed to tackle the multi-output regression problems in ho- mogeneous and heterogeneous scenarios. By considering output- input dependencies and inter-output correlations, fuzzy rules are extracted to reflect the shared characteristics of different outputs and capture their uniqueness. For a homogeneous scenario, fuzzy rules are first accumulated in a related domain (called the source domain), which has a sufficient amount of training data. Based on different transform strategies, the fuzzy rules are then transferred to improve the new but similar regression tasks in the current domain (called the target domain), where only a few data have multiple responses. On this basis, we handle a more complex heterogeneous scenario by learning a latent input space to reduce the disagreement of variables between domains. The experiment results on thirteen real-world datasets with multiple outputs illustrate the effectiveness of our method. The impact of core coefficients on performance is also analyzed.

Finding relevant objects in a large repository is a fundamental research problem occurring in many applications, such as: data cleaning, data integration, web search, and information retrieval. Instant type-ahead fuzzy search, where user types her query character by character and find the top-k relevant objects, has become widely involved in many applications because it provides the users with rapid response results and improves the user’s experience. The state-of-the-art algorithms are generally inefficient due to their breadth first search algorithm that results in repeated computations. To this end, we propose a novel depth-oriented instant type-ahead fuzzy search algorithm, that largely avoids repeated computations. The efficiency and effectiveness of the proposed approach are empirically demonstrated using real-world datasets. Experimental results show that our approach is 5–10 times faster than state-of-the-art approaches.

A major drawback of nonlinear dimensionality reduction (DR) techniques is their inability to preserve some authentic information from the source domain, leading to projections that are often hard to interpret when it comes to observing anything other than the topological structure of the data. In this paper, we propose a nonlinear DR approach enforcing projection constraints resulting from an a priori knowledge about the structure of the data in multivariate periodical time series. We then propose several ways of exploiting this constrained projection to extract user-relevant information, such as the nominal behavior of a periodical dynamical system or the deviant behaviors which may occur at different time scales. The techniques are demonstrated on both a synthetic dataset composed of simulated multivariate data exhibiting a periodical behavior, and a real dataset corresponding to six months of sensor data acquisitions and recordings inside experimental buildings. 1 We would like to thank the Institut National de l'Energie Solaire (INES) and the CEA, LITEN, Laboratoire Energetique du Bâtiment for providing the data.

In the autonomous ocean monitoring task, the sampling robot moves in the environment and accumulates data continuously. The widely adopted spatial modeling method - standard Gaussian process (GP) regression - becomes inadequate in processing the growing sensing data of a large size. To overcome the computational challenge, this paper presents an environmental modeling framework using a sparse variant of GP called streaming sparse GP (SSGP). The SSGP is able to handle streaming data in an online and incremental manner, and is therefore suitable for long-term autonomous environmental monitoring. The SSGP summarizes the collected data using a small set of pseudo data points that best represent the whole dataset, and updates the hyperparameters and pseudo point locations in a streaming fashion, leading to high-quality approximation of the underlying environmental model with significantly reduced computational cost and memory demand., Proceedings of OCEANS 2019, SEATTLE

Knowledge graphs have received intensive research interests. When the labels of most nodes or datapoints are missing, anchor graph and hierarchical anchor graph models can be employed. With an anchor graph or hierarchical anchor graph, we only need to optimize the labels of the coarsest anchors, and the labels of datapoints can be inferred from these anchors in a coarse-to-fine manner. The complexity of optimization is therefore reduced to a cubic cost with respect to the number of the coarsest anchors. However, to obtain a high accuracy when a data distribution is complex, the scale of this anchor set still needs to be large, which thus inevitably incurs an expensive computational burden. As such, a challenge in scaling up these models is how to efficiently estimate the labels of these anchors while keeping classification performance. To address this problem, we propose a novel approach that adds an anchor label predictor in the conventional anchor graph and hierarchical anchor graph models. In the proposed approach, the labels of the coarsest anchors are not directly optimized, and instead, we learn a label predictor which estimates the labels of these anchors with their spectral representations. The predictor is optimized with a regularization on all datapoints based on a hierarchical anchor graph, and we show that its solution only involves the inversion of a small-size matrix. Built upon the anchor hierarchy, we design a sparse intra-layer adjacency matrix over these anchors, which can simultaneously accelerate spectral embedding and enhance effectiveness. Our approach is named Faster Learning6 on Anchor Graph (FLAG) as it improves conventional anchor-graph-based methods in terms of efficiency. Experiments on a variety of publicly available datasets with sizes varying fromthousands to millions of Q1 samples demonstrate the effectiveness of our approach.

This paper addresses the issue of reliability in Industrial Internet of Things (IIoT) in case of missing sensors measurements due to network or hardware problems. We propose to support the fault detection and classification modules, which are the two critical components of a monitoring system for IIoT, with a generative model. The latter is responsible of imputing missing sensor measurements so that the monitoring system performance is robust to missing data. In particular, we adopt Generative Adversarial Networks (GANs) to generate missing sensor measurements and we propose to fine-tune the training of the GAN based on the impact that the generated data have on the fault detection and classification modules. We conduct a thorough evaluation of the proposed approach using the extended Tennessee Eastman Process dataset. Results show that the GAN-imputed data mitigate the impact on the fault detection and classification even in the case of persistently missing measurements from sensors that are critical for the correct functioning of the monitoring system.

Objective: Globally, cardiovascular diseases (CVDs) are one of the most leading causes of death. In medical screening and diagnostic procedures of CVDs, electrocardiogram (ECG) signals are widely used. Early detection of CVDs requires acquisition of longer ECG signals. It has triggered the development of personal healthcare systems which can be used by cardio-patients to manage the disease. These healthcare systems continuously record, store, and transmit the ECG data via wired/wireless communication channels. There are many issues with these systems such as data storage limitation, bandwidth limitation and limited battery life. Involvement of ECG data compression techniques can resolve all these issues. Method: In the past, numerous ECG data compression techniques have been proposed. This paper presents a methodological review of different ECG data compression techniques based on their experimental performance on ECG records of the Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) arrhythmia database. Results: It is observed that experimental performance of different compression techniques depends on several parameters. The existing compression techniques are validated using different distortion measures. Conclusion: This study elaborates advantages and disadvantages of different ECG data compression techniques. It also includes different validation methods of ECG compression techniques. Although compression techniques have been developed very widely but the validation of compression methods is still a prospective research area to accomplish an efficient and reliable performance.

Geochemical parameters are useful properties to enhance hydrocarbon exploration certainty. Though, attaining these parameters, for instance total organic carbon (TOC), volatile and residual hydrocarbon (S1 & S2) has a challenge for geologists due to high cost and time consumption. Therefore, addressing this issue has become an interesting subject for many researchers. As a result, on the ground of conventional well logs, vast kinds of methods, for example, back propagation artificial neural network (BPANN), have been introduced to solve this problem. Implementing these kinds of methods bring scientists tremendous amounts of information related to the richness of organic matter in a meantime. However, the precision of the aforementioned method is inadequate and BPANN is affected negatively by local optimum. Therefore, in the current study to cope with this issue and alleviate the uncertainty, Least Squares Support Vector Machine (LSSVM) and Adaptive-Neuro Fuzzy Inference System (ANFIS) algorithms cooperating with the particle swarm optimization (PSO) were suggested as a suitable method to increase the precision of estimating geochemical factors. The Data bank for this research was attained from available sources of Shahejie formation from Bohai bay basin located in China which consists of geochemical and well logging information. Outputs of this study illustrated that ANFIS-PSO and LSSVM-PSO have a great ability to estimate geochemical parameters. The values of R2 obtained for these two models in order to predict the output parameters of TOC, S1 and S2 are equal to 0.6846 & 0.785, 0.6864 & 0.778, and 0.7343 & 0.8128, respectively. The statistical comparison between these models shows that LSSVM-PSO shows a better performance compared to another model. Also, a new attempt was implemented to evaluate the impacts of input parameters on the outputs and the results of sensitivity analysis suggest that transit interval time had the greatest effect on the output parameters.

Cloud service selection assists cloud users to find the best cloud services as per their needs and minimizes the loss occurring due to improper selection of services. This paper aims to develop a cloud service selection framework for the neutrosophic environment using single-valued neutrosophic set (SVNS) theory and multi-criteria decision making (MCDM) based technique for order of preference by similarity to ideal solution (TOPSIS). The SVNS helps cloud users and experts to express their opinion in linguistic terms rather than crisp value due to partial knowledge involving some degree of truth, indeterminacy and falsehood. TOPSIS is used to rank cloud services efficiently. A case study has been performed on a real dataset obtained from CloudHarmony to demonstrate its practicality and usefulness. Sensitivity analysis has been carried out with the addition and deletion of cloud services to rank them and found that the framework is consistent and robust to rank reversal problem. The framework is also capable to strongly handle a fuzzy environment without rank reversal phenomenon in comparison with other MCDM based cloud service selection frameworks available in the literature.

Countries have different specifications for License Plates (LPs), therefore developing one Automatic license plate recognition (ALPR) system that works well for all LPs types is a difficult task. This paper aims to develop an accurate ALPR for Jordanian LPs. Two-stage Convolutional Neural Networks (CNNs) are used in the proposed approach, the CNNs are based on the YOLO3 framework. The sizes of LPs' characters are very small compared with the frame size, therefore the YOLO3 network architecture is modified to a shallow network to detect small objects. The proposed approach uses temporal information from different frames to remove false predictions. A set of arrays data structure is used to track the vehicles’ LPs and eliminate incorrect ones. To my knowledge, the proposed approach represents the first end-to-end Jordanian ALPR that processes video stream in real-time. To my knowledge, there is no dataset for Jordanian license plates, therefore this paper proposes a new dataset called JALPR dataset. The dataset is available online and includes many real videos for moving vehicles in Jordan. Two well-known commercial software packages are used for comparisons. The experimental results in real videos from YouTube show that the proposed approach is very efficient in recognizing the Jordanian license plates and achieved 87% recognition accuracy, whereas the commercial systems have recognition accuracies that are less than 81%.

This paper proposes the salp swarm algorithm (SSA) combined with a backpropagation neural network (BPNN) to solve the software fault prediction (SFP) problem. The SFP problem is one of the well-known software engineering problems that are concerned with anticipating the software defects that are likely to appear during a software project or thereafter. In order to find the optimal BPNN parameters, a combination of SSA optimizer and BPNN named (SSA-BPNN) is proposed, so as to enhance prediction accuracy. The proposed method is evaluated against several datasets for the SFP problem. These datasets vary in both size and complexity. The results obtained are evaluated using a variety of performance measures (i.e., the AUC, Confusion Matrix, Sensitivity, Specificity, Accuracy, and Error Rate). The results obtained by SSA-BPNN are better than those obtained by the conventional BPNN over all of the datasets. The proposed method also has the ability to outperform several state-of-the-art methods over the same datasets in respect of most of the aforementioned performance measures. Therefore, the hybridization of SSA with BPNN is a valuable addition to the software engineering issues and can be utilized to achieve higher prediction accuracy for a variety of prediction problems.

Attribute reduction is one of the most important preprocessing steps in machine learning and data mining. As a key step of attribute reduction, attribute evaluation directly affects classification performance, search time, and stopping criterion. The existing evaluation functions are greatly dependent on the relationship between objects, which makes its computational time and space more costly. To solve this problem, we propose a novel separability-based evaluation function and reduction method by using the relationship between objects and decision categories directly. The degree of aggregation (DA) of intraclass objects and the degree of dispersion (DD) of between-class objects are first defined to measure the significance of an attribute subset. Then, the separability of attribute subsets is defined by DA and DD in fuzzy decision systems, and we design a sequentially forward selection based on the separability (SFSS) algorithm to select attributes. Furthermore, a postpruning strategy is introduced to prevent overfitting and determine a termination parameter. Finally, the SFSS algorithm is compared with some typical reduction algorithms using some public datasets from UCI and ELVIRA Biomedical repositories. The interpretability of SFSS is directly presented by the performance on MNIST handwritten digits. The experimental comparisons show that SFSS is fast and robust, which has higher classification accuracy and compression ratio, with extremely low computational time.

Advancement in the fields of electronic communication, data processing, and internet technologies enable easy access to and interaction with a variety of physical devices throughout the globe. Our whole world is enveloped by a blanket of innumerable smart devices equipped with the sensors and actuators. Extensive research on the Internet of things (IoT) with cloud technologies, make it possible to accumulate tremendous data created from this heterogeneous environment and transform it into precious knowledge by utilizing data mining technologies. Furthermore, this generated knowledge will play a key role in intelligent decision making, system performance boosting, and optimum management of resources and services. With this background, this paper presents a systematic and detailed review of various data mining techniques employed in the large and small scale IoT applications to formulate an intelligent environment. It also presents an overview of cloud-assisted IoT Big data mining system to better understand the importance of data mining for an IoT environment.

The greater interest of research in the field of bioinformatics and the ample amount of available data across the different domains paved the way for the generation of the dataset with high dimensionality. The number of features in the dataset with high dimensionality are very high and number of rows are less. The significance of the Frequent Colossal Closed Itemsets (FCCI) is high for diverse applications and also for the field of bioinformatics. FCCI are very prominent in the process of the decision making. Amount of information extraction from the dataset with high dimensionality is huge and this extraction is a non-trivial task. The pruning of all the inadmissible features and rows is not performed by the state-of-the-art algorithms. The proposed work articulates the pruning of all the inadmissible features and rows, an efficient pruning strategy to snip the row enumeration mining search space and closure method for checking the closeness of the rowset. An efficient row enumeration algorithm enclosing the rowset closure checking method and pruning strategy is designed to efficiently mine the complete set of FCCI. The experimental results demonstrate the effectiveness of pruning all the inadmissible features and rows.

Machine learning-based sentiment classification is the best-performing method to understand public sentiment. However, the method has some problems, such as noisy features and high-dimensional feature space which affect the sentiment classification performance. To address the problems, this paper proposes a new feature selection using hybrid Query Expansion Ranking and Binary Particle Swarm Optimization with Adaptive Inertia Weights. The proposed method was validated using five tweet datasets on different topics both in Indonesian and English, and compared with state-of-the-art of filter and wrapper-based feature selection methods. Experimental results show the proposed method significantly improves sentiment classification performance and decrease computational time.

Imbalanced data typically refers to a condition in which several data samples in a certain problem is not equally distributed, thereby leading to the underrepresentation of one or more classes in the dataset. These underrepresented classes are referred to as a minority, while the overrepresented ones are called the majority. The unequal distribution of data leads to the machine's inability to carry out predictive accuracy in determining the minority classes, thereby causing various costs of classification errors. Currently, the standard framework used to solve the unequal distribution of imbalanced data learning is the Synthetic Minority Oversampling Technique (SMOTE). However, SMOTE can produce synthetic minority data samples considered as noise, which is also part of the majority classes. Therefore, this study aims to improve SMOTE to identify the noise from synthetic minority data produced in handling imbalanced data by adding the Local Outlier Factor (LOF). The proposed method is called SMOTE-LOF, and the experiment was carried out using imbalanced datasets with the results compared with the performance of the SMOTE. The results showed that SMOTE-LOF produces better accuracy and f-measure than the SMOTE. In a dataset with a large number of data examples and a smaller imbalance ratio, the SMOTE-LOF approach also produced a better AUC than the SMOTE. However, for a dataset with a smaller number of data samples, the SMOTE's AUC result is arguably better at handling imbalanced data. Therefore, future research needs to be carried out using different datasets with combinations varying from the number of data samples and the imbalanced ratio.

As the number of people involved in a decision-making problem increases, the complexity of the group decision-making (GDM) process increases accordingly. The size of participants and the heterogeneous information have important effects on the consensus reaching process in GDM. To deal with these two issues, traditional methods divide large groups into smaller ones to reduce the scale of GDM and translate heterogeneous information into a uniform format to handle the heterogeneity problem. These methods face two challenges: 1) how to determine the appropriate group size? and 2) how to avoid or reduce loss of information during the transformation process? To address these two challenges, this article uses fuzzy cluster analysis to integrate heterogeneous information for large-scale GDM problems. First, a large group is divided into smaller ones using fuzzy cluster analysis and the F-statistic is applied to determine the satisfactory number of clusters. The original information is retained based on the similarity degree. Then, a consensus reaching process is conducted within these small groups to form a unified opinion. A feedback mechanism is developed to adjust the small GDM matrix when any group cannot reach a consensus, and the heterogeneous technique for order preference by similarity to an ideal solution (TOPSIS) is used to select the best alternative. To validate the proposed approach, an experiment study is conducted using a practical example of selecting the best rescue plan in an emergency situation. The result shows that the proposed approach helps to choose the best rescue plan faster.

This study encompasses the proposal of a novel hybrid-security model that incorporates the benefits of both the centralised data mining system as well the distributed data mining system. The hybrid model provides two levels of security. The first security level perturbs the individual datasets by transforming it into a non-understandable form using the four-dimensional rotation transformation, and the second security level helps in performing secure distributed data mining using the ratio of secure summation protocol. The trivial data mining techniques, such as k-means clustering technique and naive Bayes classification technique, verifies the efficiency and accuracy of the hybrid security model. The hybrid security model provides security to sensitive data without compromising the quality of the data. The accuracy obtained in classification task and clustering task using naive Bayes and k-means technique is high when different datasets in a privacy-enhanced distributed data mining environment verify the working of the hybrid security model.

The research in this paper aims to set up a new consumer profile definition method based on fuzzy technology and fuzzy AHP. The result of the study could be applied to garment recommendation systems for a special consumer. Consumer profiles are chosen as research objects. The fuzzy technology and fuzzy AHP are applied in this research, which aims to provide a new method of using fuzzy technology and fuzzy AHP to define consumer profiles. We define tall–short and fat–thin by fuzzy technology and set up the weights of consumer profile by fuzzy AHP methods. The fuzzy technology and fuzzy AHP are applied for building consumer profiles that can be used for a consumer-oriented intelligent garment recommendation system.

Spatially distributed hydrological models are commonly employed to optimize the locations of engineering control measures across a watershed. Yet, parameter screening exercises that aim to reduce the dimensionality of the calibration search space are typically completed only for gauged locations, like the watershed outlet, and use screening metrics that are relevant to calibration instead of explicitly describing the engineering decision objectives. Identifying parameters that describe physical processes in ungauged locations that affect decision objectives should lead to a better understanding of control measure effectiveness. This paper provides guidance on evaluating model parameter uncertainty at the spatial scales and flow magnitudes of interest for such decision-making problems. We use global sensitivity analysis to screen parameters for model calibration, and to subsequently evaluate the appropriateness of using multipliers to adjust the values of spatially distributed parameters to further reduce dimensionality. We evaluate six sensitivity metrics, four of which align with decision objectives and two of which consider model residual error that would be considered in spatial optimizations of engineering designs. We compare the resulting parameter selection for the basin outlet and each hillslope. We also compare basin outlet results for four calibration-relevant metrics. These methods were applied to a RHESSys ecohydrological model of an exurban forested watershed near Baltimore, MD, USA. Results show that (1) the set of parameters selected by calibration-relevant metrics does not include parameters that control decision-relevant high and low streamflows, (2) evaluating sensitivity metrics at the basin outlet misses many parameters that control streamflows in hillslopes, and (3) for some multipliers, calibrating all parameters in the set being adjusted may be preferable to using the multiplier if parameter sensitivities are significantly different, while for others, calibrating a subset of the parameters may be preferable if they are not all influential. Thus, we recommend that parameter screening exercises use decision-relevant metrics that are evaluated at the spatial scales appropriate to decision making. While including more parameters in calibration will exacerbate equifinality, the resulting parametric uncertainty should be important to consider in discovering control measures that are robust to it.

Pattern mining is a fundamental technique of data mining to discover interesting correlations in the data set. There are several variations of pattern mining, such as frequent itemset mining, sequence mining, and high utility itemset mining. High utility itemset mining is an emerging data science task, aims to extract knowledge based on a domain objective. The utility of a pattern shows its effectiveness or benefit that can be calculated based on user priority and domain-specific understanding. The sequential pattern mining (SPM) issue is much examined and expanded in various directions. Sequential pattern mining enumerates sequential patterns in a sequence data collection. Researchers have paid more attention in recent years to frequent pattern mining over uncertain transaction dataset. In recent years, mining itemsets in big data have received extensive attention based on the Apache Hadoop and Spark framework. This paper seeks to give a broad overview of the distinct approaches to pattern mining in the Big Data domain. Initially, we investigate the problem involved with pattern mining approaches and associated techniques such as Apache Hadoop, Apache Spark, parallel and distributed processing. Then we examine major developments in parallel, distributed, and scalable pattern mining, analyze them in the big data perspective and identify difficulties in designing the algorithms. In particular, we study four varieties of itemsets mining, i.e., parallel frequent itemsets mining, high utility itemset mining, sequential patterns mining and frequent itemset mining in uncertain data. This paper concludes with a discussion of open issues and opportunity. It also provides direction for further enhancement of existing approaches.

In our day to day life, we face so many decision-making problems. The heavy text data sets and these data sets are increasing drastically in such a way that it reaches to the big data environment. Here, We have not only proposed a framework for big data sentiment analysis on real-time updates in online reviews or text for optimal or best decision selection (for example selection of a restaurant) from existing huge list of N number of restaurants but also implemented our proposed framework as a mathematical algorithm (named as Algorithm 4.1) by using soft computing technique for finding reduct soft set of consolidated review matrix. We further quantified sentiments in three values (1, −1, and 0), either in 1 for (positive/yes/true) or −1 for (negative/no/False) and 0 for (neutral or absence of sentiment) and stored them in a table (named as ternary sentiment table). Then, we have done an entropic calculation on this ternary sentiment table to find the quantity of information stored in its associated rows and columns. This proposed quantification further helps to identify the most important attribute of the table. It helps to decide weight for the different attributes and applying calculated weights to corresponding attributes to obtain the quantified ordered decision-making values.